diff options
Diffstat (limited to 'include/linux')
567 files changed, 18457 insertions, 6453 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 137e4a3d89c5..502af53ec012 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -26,6 +26,7 @@ #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/property.h> +#include <linux/uuid.h> #ifndef _LINUX #define _LINUX @@ -64,14 +65,14 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) if (!fwnode) return NULL; - fwnode->type = FWNODE_ACPI_STATIC; + fwnode->ops = &acpi_static_fwnode_ops; return fwnode; } static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) { - if (WARN_ON(!fwnode || fwnode->type != FWNODE_ACPI_STATIC)) + if (WARN_ON(!is_acpi_static_node(fwnode))) return; kfree(fwnode); @@ -223,8 +224,8 @@ struct acpi_subtable_proc { int count; }; -char * __acpi_map_table (unsigned long phys_addr, unsigned long size); -void __acpi_unmap_table(char *map, unsigned long size); +void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); +void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); void acpi_boot_table_init (void); @@ -422,6 +423,8 @@ void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); +int acpi_dev_get_dma_resources(struct acpi_device *adev, + struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); @@ -457,7 +460,6 @@ struct acpi_osc_context { struct acpi_buffer ret; /* free by caller if success */ }; -acpi_status acpi_str_to_uuid(char *str, u8 *uuid); acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ @@ -552,6 +554,25 @@ extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, #define ACPI_OST_SC_DRIVER_LOAD_FAILURE 0x81 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 +enum acpi_predicate { + all_versions, + less_than_or_equal, + equal, + greater_than_or_equal, +}; + +/* Table must be terminted by a NULL entry */ +struct acpi_platform_list { + char oem_id[ACPI_OEM_ID_SIZE+1]; + char oem_table_id[ACPI_OEM_TABLE_ID_SIZE+1]; + u32 oem_revision; + char *table; + enum acpi_predicate pred; + char *reason; + u32 data; +}; +int acpi_match_platform_list(const struct acpi_platform_list *plat); + extern void acpi_early_init(void); extern void acpi_subsystem_init(void); @@ -741,7 +762,7 @@ static inline bool acpi_driver_match_device(struct device *dev, } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, - const u8 *uuid, + const guid_t *guid, int rev, int func, union acpi_object *argv4) { @@ -770,6 +791,12 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) return DEV_DMA_NOT_SUPPORTED; } +static inline int acpi_dma_get_range(struct device *dev, u64 *dma_addr, + u64 *offset, u64 *size) +{ + return -ENODEV; +} + static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { @@ -964,6 +991,8 @@ int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); void devm_acpi_dev_remove_driver_gpios(struct device *dev); +bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index); #else static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, @@ -980,6 +1009,11 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, } static inline void devm_acpi_dev_remove_driver_gpios(struct device *dev) {} +static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio) +{ + return false; +} static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { return -ENXIO; @@ -996,13 +1030,14 @@ struct acpi_reference_args { }; #ifdef CONFIG_ACPI -int acpi_dev_get_property(struct acpi_device *adev, const char *name, +int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); -int __acpi_node_get_property_reference(struct fwnode_handle *fwnode, +int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct acpi_reference_args *args); -static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, +static inline int acpi_node_get_property_reference( + const struct fwnode_handle *fwnode, const char *name, size_t index, struct acpi_reference_args *args) { @@ -1010,22 +1045,25 @@ static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, MAX_ACPI_REFERENCE_ARGS, args); } -int acpi_node_prop_get(struct fwnode_handle *fwnode, const char *propname, +int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); -int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname, - enum dev_prop_type proptype, void *val); -int acpi_node_prop_read(struct fwnode_handle *fwnode, const char *propname, - enum dev_prop_type proptype, void *val, size_t nval); -int acpi_dev_prop_read(struct acpi_device *adev, const char *propname, +int acpi_dev_prop_read_single(struct acpi_device *adev, + const char *propname, enum dev_prop_type proptype, + void *val); +int acpi_node_prop_read(const struct fwnode_handle *fwnode, + const char *propname, enum dev_prop_type proptype, + void *val, size_t nval); +int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval); -struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode, +struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); -struct fwnode_handle *acpi_node_get_parent(struct fwnode_handle *fwnode); +struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle *acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode, - struct fwnode_handle *prev); -int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode, +struct fwnode_handle * +acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, + struct fwnode_handle *prev); +int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint); @@ -1093,35 +1131,36 @@ static inline int acpi_dev_get_property(struct acpi_device *adev, } static inline int -__acpi_node_get_property_reference(struct fwnode_handle *fwnode, +__acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct acpi_reference_args *args) { return -ENXIO; } -static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, - const char *name, size_t index, - struct acpi_reference_args *args) +static inline int +acpi_node_get_property_reference(const struct fwnode_handle *fwnode, + const char *name, size_t index, + struct acpi_reference_args *args) { return -ENXIO; } -static inline int acpi_node_prop_get(struct fwnode_handle *fwnode, +static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return -ENXIO; } -static inline int acpi_dev_prop_get(struct acpi_device *adev, +static inline int acpi_dev_prop_get(const struct acpi_device *adev, const char *propname, void **valptr) { return -ENXIO; } -static inline int acpi_dev_prop_read_single(struct acpi_device *adev, +static inline int acpi_dev_prop_read_single(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val) @@ -1129,7 +1168,7 @@ static inline int acpi_dev_prop_read_single(struct acpi_device *adev, return -ENXIO; } -static inline int acpi_node_prop_read(struct fwnode_handle *fwnode, +static inline int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) @@ -1137,7 +1176,7 @@ static inline int acpi_node_prop_read(struct fwnode_handle *fwnode, return -ENXIO; } -static inline int acpi_dev_prop_read(struct acpi_device *adev, +static inline int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) @@ -1146,26 +1185,27 @@ static inline int acpi_dev_prop_read(struct acpi_device *adev, } static inline struct fwnode_handle * -acpi_get_next_subnode(struct fwnode_handle *fwnode, struct fwnode_handle *child) +acpi_get_next_subnode(const struct fwnode_handle *fwnode, + struct fwnode_handle *child) { return NULL; } static inline struct fwnode_handle * -acpi_node_get_parent(struct fwnode_handle *fwnode) +acpi_node_get_parent(const struct fwnode_handle *fwnode) { return NULL; } static inline struct fwnode_handle * -acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode, +acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { return ERR_PTR(-ENXIO); } static inline int -acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode, +acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint) @@ -1198,6 +1238,7 @@ static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE +extern bool qdf2400_e44_present; int parse_spcr(bool earlycon); #else static inline int parse_spcr(bool earlycon) { return 0; } diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 3ff9acea8616..8d3f0bf80379 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -31,17 +31,15 @@ void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); -bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ -void iort_set_dma_mask(struct device *dev); +void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); const struct iommu_ops *iort_iommu_configure(struct device *dev); #else static inline void acpi_iort_init(void) { } -static inline bool iort_node_match(u8 type) { return false; } static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) { return req_id; } static inline struct irq_domain *iort_get_device_domain(struct device *dev, @@ -49,7 +47,8 @@ static inline struct irq_domain *iort_get_device_domain(struct device *dev, { return NULL; } static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ -static inline void iort_set_dma_mask(struct device *dev) { } +static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, + u64 *size) { } static inline const struct iommu_ops *iort_iommu_configure(struct device *dev) { return NULL; } diff --git a/include/linux/aer.h b/include/linux/aer.h index 04602cbe85dc..43799bd17a02 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -39,7 +39,7 @@ struct aer_capability_regs { }; #if defined(CONFIG_PCIEAER) -/* pci-e port driver needs this function to enable aer */ +/* PCIe port driver needs this function to enable AER */ int pci_enable_pcie_error_reporting(struct pci_dev *dev); int pci_disable_pcie_error_reporting(struct pci_dev *dev); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev); @@ -67,7 +67,6 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity, struct aer_capability_regs *aer); int cper_severity_to_aer(int cper_severity); void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, - int severity, - struct aer_capability_regs *aer_regs); + int severity, struct aer_capability_regs *aer_regs); #endif //_AER_H_ diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index a270f25ee7c7..1b0a17b22cd3 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -36,6 +36,8 @@ int ahci_platform_init_host(struct platform_device *pdev, const struct ata_port_info *pi_template, struct scsi_host_template *sht); +void ahci_platform_shutdown(struct platform_device *pdev); + int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); int ahci_platform_suspend(struct device *dev); diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h new file mode 100644 index 000000000000..516a6fda83c5 --- /dev/null +++ b/include/linux/amba/clcd-regs.h @@ -0,0 +1,86 @@ +/* + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#ifndef AMBA_CLCD_REGS_H +#define AMBA_CLCD_REGS_H + +/* + * CLCD Controller Internal Register addresses + */ +#define CLCD_TIM0 0x00000000 +#define CLCD_TIM1 0x00000004 +#define CLCD_TIM2 0x00000008 +#define CLCD_TIM3 0x0000000c +#define CLCD_UBAS 0x00000010 +#define CLCD_LBAS 0x00000014 + +#define CLCD_PL110_IENB 0x00000018 +#define CLCD_PL110_CNTL 0x0000001c +#define CLCD_PL110_STAT 0x00000020 +#define CLCD_PL110_INTR 0x00000024 +#define CLCD_PL110_UCUR 0x00000028 +#define CLCD_PL110_LCUR 0x0000002C + +#define CLCD_PL111_CNTL 0x00000018 +#define CLCD_PL111_IENB 0x0000001c +#define CLCD_PL111_RIS 0x00000020 +#define CLCD_PL111_MIS 0x00000024 +#define CLCD_PL111_ICR 0x00000028 +#define CLCD_PL111_UCUR 0x0000002c +#define CLCD_PL111_LCUR 0x00000030 + +#define CLCD_PALL 0x00000200 +#define CLCD_PALETTE 0x00000200 + +#define TIM2_PCD_LO_MASK GENMASK(4, 0) +#define TIM2_PCD_LO_BITS 5 +#define TIM2_CLKSEL (1 << 5) +#define TIM2_IVS (1 << 11) +#define TIM2_IHS (1 << 12) +#define TIM2_IPC (1 << 13) +#define TIM2_IOE (1 << 14) +#define TIM2_BCD (1 << 26) +#define TIM2_PCD_HI_MASK GENMASK(31, 27) +#define TIM2_PCD_HI_BITS 5 +#define TIM2_PCD_HI_SHIFT 27 + +#define CNTL_LCDEN (1 << 0) +#define CNTL_LCDBPP1 (0 << 1) +#define CNTL_LCDBPP2 (1 << 1) +#define CNTL_LCDBPP4 (2 << 1) +#define CNTL_LCDBPP8 (3 << 1) +#define CNTL_LCDBPP16 (4 << 1) +#define CNTL_LCDBPP16_565 (6 << 1) +#define CNTL_LCDBPP16_444 (7 << 1) +#define CNTL_LCDBPP24 (5 << 1) +#define CNTL_LCDBW (1 << 4) +#define CNTL_LCDTFT (1 << 5) +#define CNTL_LCDMONO8 (1 << 6) +#define CNTL_LCDDUAL (1 << 7) +#define CNTL_BGR (1 << 8) +#define CNTL_BEBO (1 << 9) +#define CNTL_BEPO (1 << 10) +#define CNTL_LCDPWR (1 << 11) +#define CNTL_LCDVCOMP(x) ((x) << 12) +#define CNTL_LDMAFIFOTIME (1 << 15) +#define CNTL_WATERMARK (1 << 16) + +/* ST Microelectronics variant bits */ +#define CNTL_ST_1XBPP_444 0x0 +#define CNTL_ST_1XBPP_5551 (1 << 17) +#define CNTL_ST_1XBPP_565 (1 << 18) +#define CNTL_ST_CDWID_12 0x0 +#define CNTL_ST_CDWID_16 (1 << 19) +#define CNTL_ST_CDWID_18 (1 << 20) +#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) +#define CNTL_ST_CEAEN (1 << 21) +#define CNTL_ST_LCDBPP24_PACKED (6 << 1) + +#endif /* AMBA_CLCD_REGS_H */ diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h index 1035879b322c..d0c3be77c18e 100644 --- a/include/linux/amba/clcd.h +++ b/include/linux/amba/clcd.h @@ -10,73 +10,7 @@ * for more details. */ #include <linux/fb.h> - -/* - * CLCD Controller Internal Register addresses - */ -#define CLCD_TIM0 0x00000000 -#define CLCD_TIM1 0x00000004 -#define CLCD_TIM2 0x00000008 -#define CLCD_TIM3 0x0000000c -#define CLCD_UBAS 0x00000010 -#define CLCD_LBAS 0x00000014 - -#define CLCD_PL110_IENB 0x00000018 -#define CLCD_PL110_CNTL 0x0000001c -#define CLCD_PL110_STAT 0x00000020 -#define CLCD_PL110_INTR 0x00000024 -#define CLCD_PL110_UCUR 0x00000028 -#define CLCD_PL110_LCUR 0x0000002C - -#define CLCD_PL111_CNTL 0x00000018 -#define CLCD_PL111_IENB 0x0000001c -#define CLCD_PL111_RIS 0x00000020 -#define CLCD_PL111_MIS 0x00000024 -#define CLCD_PL111_ICR 0x00000028 -#define CLCD_PL111_UCUR 0x0000002c -#define CLCD_PL111_LCUR 0x00000030 - -#define CLCD_PALL 0x00000200 -#define CLCD_PALETTE 0x00000200 - -#define TIM2_CLKSEL (1 << 5) -#define TIM2_IVS (1 << 11) -#define TIM2_IHS (1 << 12) -#define TIM2_IPC (1 << 13) -#define TIM2_IOE (1 << 14) -#define TIM2_BCD (1 << 26) - -#define CNTL_LCDEN (1 << 0) -#define CNTL_LCDBPP1 (0 << 1) -#define CNTL_LCDBPP2 (1 << 1) -#define CNTL_LCDBPP4 (2 << 1) -#define CNTL_LCDBPP8 (3 << 1) -#define CNTL_LCDBPP16 (4 << 1) -#define CNTL_LCDBPP16_565 (6 << 1) -#define CNTL_LCDBPP16_444 (7 << 1) -#define CNTL_LCDBPP24 (5 << 1) -#define CNTL_LCDBW (1 << 4) -#define CNTL_LCDTFT (1 << 5) -#define CNTL_LCDMONO8 (1 << 6) -#define CNTL_LCDDUAL (1 << 7) -#define CNTL_BGR (1 << 8) -#define CNTL_BEBO (1 << 9) -#define CNTL_BEPO (1 << 10) -#define CNTL_LCDPWR (1 << 11) -#define CNTL_LCDVCOMP(x) ((x) << 12) -#define CNTL_LDMAFIFOTIME (1 << 15) -#define CNTL_WATERMARK (1 << 16) - -/* ST Microelectronics variant bits */ -#define CNTL_ST_1XBPP_444 0x0 -#define CNTL_ST_1XBPP_5551 (1 << 17) -#define CNTL_ST_1XBPP_565 (1 << 18) -#define CNTL_ST_CDWID_12 0x0 -#define CNTL_ST_CDWID_16 (1 << 19) -#define CNTL_ST_CDWID_18 (1 << 20) -#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) -#define CNTL_ST_CEAEN (1 << 21) -#define CNTL_ST_LCDBPP24_PACKED (6 << 1) +#include <linux/amba/clcd-regs.h> enum { /* individual formats */ diff --git a/include/linux/amba/pl080.h b/include/linux/amba/pl080.h index 580b5323a717..ab036b6b1804 100644 --- a/include/linux/amba/pl080.h +++ b/include/linux/amba/pl080.h @@ -44,7 +44,14 @@ #define PL080_SYNC (0x34) -/* Per channel configuration registers */ +/* The Faraday Technology FTDMAC020 variant registers */ +#define FTDMAC020_CH_BUSY (0x20) +/* Identical to PL080_CONFIG */ +#define FTDMAC020_CSR (0x24) +/* Identical to PL080_SYNC */ +#define FTDMAC020_SYNC (0x2C) +#define FTDMAC020_REVISION (0x30) +#define FTDMAC020_FEATURE (0x34) /* Per channel configuration registers */ #define PL080_Cx_BASE(x) ((0x100 + (x * 0x20))) @@ -55,13 +62,20 @@ #define PL080_CH_CONFIG (0x10) #define PL080S_CH_CONTROL2 (0x10) #define PL080S_CH_CONFIG (0x14) - -#define PL080_LLI_ADDR_MASK (0x3fffffff << 2) +/* The Faraday FTDMAC020 derivative shuffles the registers around */ +#define FTDMAC020_CH_CSR (0x00) +#define FTDMAC020_CH_CFG (0x04) +#define FTDMAC020_CH_SRC_ADDR (0x08) +#define FTDMAC020_CH_DST_ADDR (0x0C) +#define FTDMAC020_CH_LLP (0x10) +#define FTDMAC020_CH_SIZE (0x14) + +#define PL080_LLI_ADDR_MASK GENMASK(31, 2) #define PL080_LLI_ADDR_SHIFT (2) #define PL080_LLI_LM_AHB2 BIT(0) #define PL080_CONTROL_TC_IRQ_EN BIT(31) -#define PL080_CONTROL_PROT_MASK (0x7 << 28) +#define PL080_CONTROL_PROT_MASK GENMASK(30, 28) #define PL080_CONTROL_PROT_SHIFT (28) #define PL080_CONTROL_PROT_CACHE BIT(30) #define PL080_CONTROL_PROT_BUFF BIT(29) @@ -70,16 +84,16 @@ #define PL080_CONTROL_SRC_INCR BIT(26) #define PL080_CONTROL_DST_AHB2 BIT(25) #define PL080_CONTROL_SRC_AHB2 BIT(24) -#define PL080_CONTROL_DWIDTH_MASK (0x7 << 21) +#define PL080_CONTROL_DWIDTH_MASK GENMASK(23, 21) #define PL080_CONTROL_DWIDTH_SHIFT (21) -#define PL080_CONTROL_SWIDTH_MASK (0x7 << 18) +#define PL080_CONTROL_SWIDTH_MASK GENMASK(20, 18) #define PL080_CONTROL_SWIDTH_SHIFT (18) -#define PL080_CONTROL_DB_SIZE_MASK (0x7 << 15) +#define PL080_CONTROL_DB_SIZE_MASK GENMASK(17, 15) #define PL080_CONTROL_DB_SIZE_SHIFT (15) -#define PL080_CONTROL_SB_SIZE_MASK (0x7 << 12) +#define PL080_CONTROL_SB_SIZE_MASK GENMASK(14, 12) #define PL080_CONTROL_SB_SIZE_SHIFT (12) -#define PL080_CONTROL_TRANSFER_SIZE_MASK (0xfff << 0) -#define PL080S_CONTROL_TRANSFER_SIZE_MASK (0x1ffffff << 0) +#define PL080_CONTROL_TRANSFER_SIZE_MASK GENMASK(11, 0) +#define PL080S_CONTROL_TRANSFER_SIZE_MASK GENMASK(24, 0) #define PL080_CONTROL_TRANSFER_SIZE_SHIFT (0) #define PL080_BSIZE_1 (0x0) @@ -102,11 +116,11 @@ #define PL080_CONFIG_LOCK BIT(16) #define PL080_CONFIG_TC_IRQ_MASK BIT(15) #define PL080_CONFIG_ERR_IRQ_MASK BIT(14) -#define PL080_CONFIG_FLOW_CONTROL_MASK (0x7 << 11) +#define PL080_CONFIG_FLOW_CONTROL_MASK GENMASK(13, 11) #define PL080_CONFIG_FLOW_CONTROL_SHIFT (11) -#define PL080_CONFIG_DST_SEL_MASK (0xf << 6) +#define PL080_CONFIG_DST_SEL_MASK GENMASK(9, 6) #define PL080_CONFIG_DST_SEL_SHIFT (6) -#define PL080_CONFIG_SRC_SEL_MASK (0xf << 1) +#define PL080_CONFIG_SRC_SEL_MASK GENMASK(4, 1) #define PL080_CONFIG_SRC_SEL_SHIFT (1) #define PL080_CONFIG_ENABLE BIT(0) @@ -119,6 +133,73 @@ #define PL080_FLOW_PER2MEM_PER (0x6) #define PL080_FLOW_SRC2DST_SRC (0x7) +#define FTDMAC020_CH_CSR_TC_MSK BIT(31) +/* Later versions have a threshold in bits 24..26, */ +#define FTDMAC020_CH_CSR_FIFOTH_MSK GENMASK(26, 24) +#define FTDMAC020_CH_CSR_FIFOTH_SHIFT (24) +#define FTDMAC020_CH_CSR_CHPR1_MSK GENMASK(23, 22) +#define FTDMAC020_CH_CSR_PROT3 BIT(21) +#define FTDMAC020_CH_CSR_PROT2 BIT(20) +#define FTDMAC020_CH_CSR_PROT1 BIT(19) +#define FTDMAC020_CH_CSR_SRC_SIZE_MSK GENMASK(18, 16) +#define FTDMAC020_CH_CSR_SRC_SIZE_SHIFT (16) +#define FTDMAC020_CH_CSR_ABT BIT(15) +#define FTDMAC020_CH_CSR_SRC_WIDTH_MSK GENMASK(13, 11) +#define FTDMAC020_CH_CSR_SRC_WIDTH_SHIFT (11) +#define FTDMAC020_CH_CSR_DST_WIDTH_MSK GENMASK(10, 8) +#define FTDMAC020_CH_CSR_DST_WIDTH_SHIFT (8) +#define FTDMAC020_CH_CSR_MODE BIT(7) +/* 00 = increase, 01 = decrease, 10 = fix */ +#define FTDMAC020_CH_CSR_SRCAD_CTL_MSK GENMASK(6, 5) +#define FTDMAC020_CH_CSR_SRCAD_CTL_SHIFT (5) +#define FTDMAC020_CH_CSR_DSTAD_CTL_MSK GENMASK(4, 3) +#define FTDMAC020_CH_CSR_DSTAD_CTL_SHIFT (3) +#define FTDMAC020_CH_CSR_SRC_SEL BIT(2) +#define FTDMAC020_CH_CSR_DST_SEL BIT(1) +#define FTDMAC020_CH_CSR_EN BIT(0) + +/* FIFO threshold setting */ +#define FTDMAC020_CH_CSR_FIFOTH_1 (0x0) +#define FTDMAC020_CH_CSR_FIFOTH_2 (0x1) +#define FTDMAC020_CH_CSR_FIFOTH_4 (0x2) +#define FTDMAC020_CH_CSR_FIFOTH_8 (0x3) +#define FTDMAC020_CH_CSR_FIFOTH_16 (0x4) +/* The FTDMAC020 supports 64bit wide transfers */ +#define FTDMAC020_WIDTH_64BIT (0x3) +/* Address can be increased, decreased or fixed */ +#define FTDMAC020_CH_CSR_SRCAD_CTL_INC (0x0) +#define FTDMAC020_CH_CSR_SRCAD_CTL_DEC (0x1) +#define FTDMAC020_CH_CSR_SRCAD_CTL_FIXED (0x2) + +#define FTDMAC020_CH_CFG_LLP_CNT_MASK GENMASK(19, 16) +#define FTDMAC020_CH_CFG_LLP_CNT_SHIFT (16) +#define FTDMAC020_CH_CFG_BUSY BIT(8) +#define FTDMAC020_CH_CFG_INT_ABT_MASK BIT(2) +#define FTDMAC020_CH_CFG_INT_ERR_MASK BIT(1) +#define FTDMAC020_CH_CFG_INT_TC_MASK BIT(0) + +/* Inside the LLIs, the applicable CSR fields are mapped differently */ +#define FTDMAC020_LLI_TC_MSK BIT(28) +#define FTDMAC020_LLI_SRC_WIDTH_MSK GENMASK(27, 25) +#define FTDMAC020_LLI_SRC_WIDTH_SHIFT (25) +#define FTDMAC020_LLI_DST_WIDTH_MSK GENMASK(24, 22) +#define FTDMAC020_LLI_DST_WIDTH_SHIFT (22) +#define FTDMAC020_LLI_SRCAD_CTL_MSK GENMASK(21, 20) +#define FTDMAC020_LLI_SRCAD_CTL_SHIFT (20) +#define FTDMAC020_LLI_DSTAD_CTL_MSK GENMASK(19, 18) +#define FTDMAC020_LLI_DSTAD_CTL_SHIFT (18) +#define FTDMAC020_LLI_SRC_SEL BIT(17) +#define FTDMAC020_LLI_DST_SEL BIT(16) +#define FTDMAC020_LLI_TRANSFER_SIZE_MASK GENMASK(11, 0) +#define FTDMAC020_LLI_TRANSFER_SIZE_SHIFT (0) + +#define FTDMAC020_CFG_LLP_CNT_MASK GENMASK(19, 16) +#define FTDMAC020_CFG_LLP_CNT_SHIFT (16) +#define FTDMAC020_CFG_BUSY BIT(8) +#define FTDMAC020_CFG_INT_ABT_MSK BIT(2) +#define FTDMAC020_CFG_INT_ERR_MSK BIT(1) +#define FTDMAC020_CFG_INT_TC_MSK BIT(0) + /* DMA linked list chain structure */ struct pl080_lli { diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 5308eae9ce35..79d1bcee738d 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -47,8 +47,6 @@ enum { * devices with static assignments * @muxval: a number usually used to poke into some mux regiser to * mux in the signal to this channel - * @cctl_memcpy: options for the channel control register for memcpy - * *** not used for slave channels *** * @addr: source/target address in physical memory for this DMA channel, * can be the address of a FIFO register for burst requests for example. * This can be left undefined if the PrimeCell API is used for configuring @@ -63,12 +61,28 @@ struct pl08x_channel_data { int min_signal; int max_signal; u32 muxval; - u32 cctl_memcpy; dma_addr_t addr; bool single; u8 periph_buses; }; +enum pl08x_burst_size { + PL08X_BURST_SZ_1, + PL08X_BURST_SZ_4, + PL08X_BURST_SZ_8, + PL08X_BURST_SZ_16, + PL08X_BURST_SZ_32, + PL08X_BURST_SZ_64, + PL08X_BURST_SZ_128, + PL08X_BURST_SZ_256, +}; + +enum pl08x_bus_width { + PL08X_BUS_WIDTH_8_BITS, + PL08X_BUS_WIDTH_16_BITS, + PL08X_BUS_WIDTH_32_BITS, +}; + /** * struct pl08x_platform_data - the platform configuration for the PL08x * PrimeCells. @@ -76,6 +90,11 @@ struct pl08x_channel_data { * platform, all inclusive, including multiplexed channels. The available * physical channels will be multiplexed around these signals as they are * requested, just enumerate all possible channels. + * @num_slave_channels: number of elements in the slave channel array + * @memcpy_burst_size: the appropriate burst size for memcpy operations + * @memcpy_bus_width: memory bus width + * @memcpy_prot_buff: whether memcpy DMA is bufferable + * @memcpy_prot_cache: whether memcpy DMA is cacheable * @get_xfer_signal: request a physical signal to be used for a DMA transfer * immediately: if there is some multiplexing or similar blocking the use * of the channel the transfer can be denied by returning less than zero, @@ -90,7 +109,10 @@ struct pl08x_channel_data { struct pl08x_platform_data { struct pl08x_channel_data *slave_channels; unsigned int num_slave_channels; - struct pl08x_channel_data memcpy_channel; + enum pl08x_burst_size memcpy_burst_size; + enum pl08x_bus_width memcpy_bus_width; + bool memcpy_prot_buff; + bool memcpy_prot_cache; int (*get_xfer_signal)(const struct pl08x_channel_data *); void (*put_xfer_signal)(const struct pl08x_channel_data *, int); u8 lli_buses; diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h new file mode 100644 index 000000000000..716ce587247e --- /dev/null +++ b/include/linux/arch_topology.h @@ -0,0 +1,19 @@ +/* + * include/linux/arch_topology.h - arch specific cpu topology information + */ +#ifndef _LINUX_ARCH_TOPOLOGY_H_ +#define _LINUX_ARCH_TOPOLOGY_H_ + +#include <linux/types.h> + +void topology_normalize_cpu_scale(void); + +struct device_node; +bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); + +struct sched_domain; +unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu); + +void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); + +#endif /* _LINUX_ARCH_TOPOLOGY_H_ */ diff --git a/include/linux/ata.h b/include/linux/ata.h index ad7d9ee89ff0..c7a353825450 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -20,7 +20,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ * @@ -60,7 +60,8 @@ enum { ATA_ID_FW_REV = 23, ATA_ID_PROD = 27, ATA_ID_MAX_MULTSECT = 47, - ATA_ID_DWORD_IO = 48, + ATA_ID_DWORD_IO = 48, /* before ATA-8 */ + ATA_ID_TRUSTED = 48, /* ATA-8 and later */ ATA_ID_CAPABILITY = 49, ATA_ID_OLD_PIO_MODES = 51, ATA_ID_OLD_DMA_MODES = 52, @@ -336,11 +337,16 @@ enum { /* READ_LOG_EXT pages */ ATA_LOG_DIRECTORY = 0x0, ATA_LOG_SATA_NCQ = 0x10, - ATA_LOG_NCQ_NON_DATA = 0x12, - ATA_LOG_NCQ_SEND_RECV = 0x13, - ATA_LOG_SATA_ID_DEV_DATA = 0x30, + ATA_LOG_NCQ_NON_DATA = 0x12, + ATA_LOG_NCQ_SEND_RECV = 0x13, + ATA_LOG_IDENTIFY_DEVICE = 0x30, + + /* Identify device log pages: */ + ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, + + /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, ATA_LOG_DEVSLP_SIZE = 0x08, ATA_LOG_DEVSLP_MDAT = 0x00, @@ -884,6 +890,13 @@ static inline bool ata_id_has_dword_io(const u16 *id) return id[ATA_ID_DWORD_IO] & (1 << 0); } +static inline bool ata_id_has_trusted(const u16 *id) +{ + if (ata_id_major_version(id) <= 7) + return false; + return id[ATA_ID_TRUSTED] & (1 << 0); +} + static inline bool ata_id_has_unload(const u16 *id) { if (ata_id_major_version(id) >= 7 && diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index c1da539f5e28..0ec9bdb1cc9f 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -11,6 +11,7 @@ #include <linux/uio.h> #include <net/sock.h> #include <linux/atomic.h> +#include <linux/refcount.h> #include <uapi/linux/atmdev.h> #ifdef CONFIG_PROC_FS @@ -158,7 +159,7 @@ struct atm_dev { struct k_atm_dev_stats stats; /* statistics */ char signal; /* signal status (ATM_PHY_SIG_*) */ int link_rate; /* link rate (default: OC3) */ - atomic_t refcnt; /* reference count */ + refcount_t refcnt; /* reference count */ spinlock_t lock; /* protect internal members */ #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; /* proc entry */ @@ -254,20 +255,20 @@ static inline void atm_return(struct atm_vcc *vcc,int truesize) static inline int atm_may_send(struct atm_vcc *vcc,unsigned int size) { - return (size + atomic_read(&sk_atm(vcc)->sk_wmem_alloc)) < + return (size + refcount_read(&sk_atm(vcc)->sk_wmem_alloc)) < sk_atm(vcc)->sk_sndbuf; } static inline void atm_dev_hold(struct atm_dev *dev) { - atomic_inc(&dev->refcnt); + refcount_inc(&dev->refcnt); } static inline void atm_dev_put(struct atm_dev *dev) { - if (atomic_dec_and_test(&dev->refcnt)) { + if (refcount_dec_and_test(&dev->refcnt)) { BUG_ON(!test_bit(ATM_DF_REMOVED, &dev->flags)); if (dev->ops->dev_close) dev->ops->dev_close(dev); diff --git a/include/linux/atomic.h b/include/linux/atomic.h index c56be7410130..40d6bfec0e0d 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -38,6 +38,9 @@ * Besides, if an arch has a special barrier for acquire/release, it could * implement its own __atomic_op_* and use the same framework for building * variants + * + * If an architecture overrides __atomic_op_acquire() it will probably want + * to define smp_mb__after_spinlock(). */ #ifndef __atomic_op_acquire #define __atomic_op_acquire(op, args...) \ diff --git a/include/linux/audit.h b/include/linux/audit.h index 2150bdccfbab..74d4d4e8e3db 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -351,7 +351,7 @@ extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); -extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout); +extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, @@ -412,7 +412,7 @@ static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } -static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout) +static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); @@ -549,7 +549,7 @@ static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, - const struct timespec *abs_timeout) + const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h new file mode 100644 index 000000000000..2b038442c352 --- /dev/null +++ b/include/linux/avf/virtchnl.h @@ -0,0 +1,706 @@ +/******************************************************************************* + * + * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver + * Copyright(c) 2013 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along + * with this program. If not, see <http://www.gnu.org/licenses/>. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +#ifndef _VIRTCHNL_H_ +#define _VIRTCHNL_H_ + +/* Description: + * This header file describes the VF-PF communication protocol used + * by the drivers for all devices starting from our 40G product line + * + * Admin queue buffer usage: + * desc->opcode is always aqc_opc_send_msg_to_pf + * flags, retval, datalen, and data addr are all used normally. + * The Firmware copies the cookie fields when sending messages between the + * PF and VF, but uses all other fields internally. Due to this limitation, + * we must send all messages as "indirect", i.e. using an external buffer. + * + * All the VSI indexes are relative to the VF. Each VF can have maximum of + * three VSIs. All the queue indexes are relative to the VSI. Each VF can + * have a maximum of sixteen queues for all of its VSIs. + * + * The PF is required to return a status code in v_retval for all messages + * except RESET_VF, which does not require any response. The return value + * is of status_code type, defined in the shared type.h. + * + * In general, VF driver initialization should roughly follow the order of + * these opcodes. The VF driver must first validate the API version of the + * PF driver, then request a reset, then get resources, then configure + * queues and interrupts. After these operations are complete, the VF + * driver may start its queues, optionally add MAC and VLAN filters, and + * process traffic. + */ + +/* START GENERIC DEFINES + * Need to ensure the following enums and defines hold the same meaning and + * value in current and future projects + */ + +/* Error Codes */ +enum virtchnl_status_code { + VIRTCHNL_STATUS_SUCCESS = 0, + VIRTCHNL_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH = -38, + VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR = -39, + VIRTCHNL_STATUS_ERR_INVALID_VF_ID = -40, + VIRTCHNL_STATUS_NOT_SUPPORTED = -64, +}; + +#define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 +#define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 +#define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 +#define VIRTCHNL_LINK_SPEED_40GB_SHIFT 0x4 +#define VIRTCHNL_LINK_SPEED_20GB_SHIFT 0x5 +#define VIRTCHNL_LINK_SPEED_25GB_SHIFT 0x6 + +enum virtchnl_link_speed { + VIRTCHNL_LINK_SPEED_UNKNOWN = 0, + VIRTCHNL_LINK_SPEED_100MB = BIT(VIRTCHNL_LINK_SPEED_100MB_SHIFT), + VIRTCHNL_LINK_SPEED_1GB = BIT(VIRTCHNL_LINK_SPEED_1000MB_SHIFT), + VIRTCHNL_LINK_SPEED_10GB = BIT(VIRTCHNL_LINK_SPEED_10GB_SHIFT), + VIRTCHNL_LINK_SPEED_40GB = BIT(VIRTCHNL_LINK_SPEED_40GB_SHIFT), + VIRTCHNL_LINK_SPEED_20GB = BIT(VIRTCHNL_LINK_SPEED_20GB_SHIFT), + VIRTCHNL_LINK_SPEED_25GB = BIT(VIRTCHNL_LINK_SPEED_25GB_SHIFT), +}; + +/* for hsplit_0 field of Rx HMC context */ +/* deprecated with AVF 1.0 */ +enum virtchnl_rx_hsplit { + VIRTCHNL_RX_HSPLIT_NO_SPLIT = 0, + VIRTCHNL_RX_HSPLIT_SPLIT_L2 = 1, + VIRTCHNL_RX_HSPLIT_SPLIT_IP = 2, + VIRTCHNL_RX_HSPLIT_SPLIT_TCP_UDP = 4, + VIRTCHNL_RX_HSPLIT_SPLIT_SCTP = 8, +}; + +/* END GENERIC DEFINES */ + +/* Opcodes for VF-PF communication. These are placed in the v_opcode field + * of the virtchnl_msg structure. + */ +enum virtchnl_ops { +/* The PF sends status change events to VFs using + * the VIRTCHNL_OP_EVENT opcode. + * VFs send requests to the PF using the other ops. + * Use of "advanced opcode" features must be negotiated as part of capabilities + * exchange and are not considered part of base mode feature set. + */ + VIRTCHNL_OP_UNKNOWN = 0, + VIRTCHNL_OP_VERSION = 1, /* must ALWAYS be 1 */ + VIRTCHNL_OP_RESET_VF = 2, + VIRTCHNL_OP_GET_VF_RESOURCES = 3, + VIRTCHNL_OP_CONFIG_TX_QUEUE = 4, + VIRTCHNL_OP_CONFIG_RX_QUEUE = 5, + VIRTCHNL_OP_CONFIG_VSI_QUEUES = 6, + VIRTCHNL_OP_CONFIG_IRQ_MAP = 7, + VIRTCHNL_OP_ENABLE_QUEUES = 8, + VIRTCHNL_OP_DISABLE_QUEUES = 9, + VIRTCHNL_OP_ADD_ETH_ADDR = 10, + VIRTCHNL_OP_DEL_ETH_ADDR = 11, + VIRTCHNL_OP_ADD_VLAN = 12, + VIRTCHNL_OP_DEL_VLAN = 13, + VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE = 14, + VIRTCHNL_OP_GET_STATS = 15, + VIRTCHNL_OP_RSVD = 16, + VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + VIRTCHNL_OP_IWARP = 20, /* advanced opcode */ + VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21, /* advanced opcode */ + VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22, /* advanced opcode */ + VIRTCHNL_OP_CONFIG_RSS_KEY = 23, + VIRTCHNL_OP_CONFIG_RSS_LUT = 24, + VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, + VIRTCHNL_OP_SET_RSS_HENA = 26, + VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, +}; + +/* This macro is used to generate a compilation error if a structure + * is not exactly the correct length. It gives a divide by zero error if the + * structure is not of the correct size, otherwise it creates an enum that is + * never used. + */ +#define VIRTCHNL_CHECK_STRUCT_LEN(n, X) enum virtchnl_static_assert_enum_##X \ + { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } + +/* Virtual channel message descriptor. This overlays the admin queue + * descriptor. All other data is passed in external buffers. + */ + +struct virtchnl_msg { + u8 pad[8]; /* AQ flags/opcode/len/retval fields */ + enum virtchnl_ops v_opcode; /* avoid confusion with desc->opcode */ + enum virtchnl_status_code v_retval; /* ditto for desc->retval */ + u32 vfid; /* used by PF when sending to VF */ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_msg); + +/* Message descriptions and data structures.*/ + +/* VIRTCHNL_OP_VERSION + * VF posts its version number to the PF. PF responds with its version number + * in the same format, along with a return code. + * Reply from PF has its major/minor versions also in param0 and param1. + * If there is a major version mismatch, then the VF cannot operate. + * If there is a minor version mismatch, then the VF can operate but should + * add a warning to the system log. + * + * This enum element MUST always be specified as == 1, regardless of other + * changes in the API. The PF must always respond to this message without + * error regardless of version mismatch. + */ +#define VIRTCHNL_VERSION_MAJOR 1 +#define VIRTCHNL_VERSION_MINOR 1 +#define VIRTCHNL_VERSION_MINOR_NO_VF_CAPS 0 + +struct virtchnl_version_info { + u32 major; + u32 minor; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_version_info); + +#define VF_IS_V10(_v) (((_v)->major == 1) && ((_v)->minor == 0)) +#define VF_IS_V11(_ver) (((_ver)->major == 1) && ((_ver)->minor == 1)) + +/* VIRTCHNL_OP_RESET_VF + * VF sends this request to PF with no parameters + * PF does NOT respond! VF driver must delay then poll VFGEN_RSTAT register + * until reset completion is indicated. The admin queue must be reinitialized + * after this operation. + * + * When reset is complete, PF must ensure that all queues in all VSIs associated + * with the VF are stopped, all queue configurations in the HMC are set to 0, + * and all MAC and VLAN filters (except the default MAC address) on all VSIs + * are cleared. + */ + +/* VSI types that use VIRTCHNL interface for VF-PF communication. VSI_SRIOV + * vsi_type should always be 6 for backward compatibility. Add other fields + * as needed. + */ +enum virtchnl_vsi_type { + VIRTCHNL_VSI_TYPE_INVALID = 0, + VIRTCHNL_VSI_SRIOV = 6, +}; + +/* VIRTCHNL_OP_GET_VF_RESOURCES + * Version 1.0 VF sends this request to PF with no parameters + * Version 1.1 VF sends this request to PF with u32 bitmap of its capabilities + * PF responds with an indirect message containing + * virtchnl_vf_resource and one or more + * virtchnl_vsi_resource structures. + */ + +struct virtchnl_vsi_resource { + u16 vsi_id; + u16 num_queue_pairs; + enum virtchnl_vsi_type vsi_type; + u16 qset_handle; + u8 default_mac_addr[ETH_ALEN]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); + +/* VF capability flags + * VIRTCHNL_VF_OFFLOAD_L2 flag is inclusive of base mode L2 offloads including + * TX/RX Checksum offloading and TSO for non-tunnelled packets. + */ +#define VIRTCHNL_VF_OFFLOAD_L2 0x00000001 +#define VIRTCHNL_VF_OFFLOAD_IWARP 0x00000002 +#define VIRTCHNL_VF_OFFLOAD_RSVD 0x00000004 +#define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 +#define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 +#define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 +#define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 +#define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 +#define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 +#define VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 +#define VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 +#define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 +#define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 + +#define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ + VIRTCHNL_VF_OFFLOAD_VLAN | \ + VIRTCHNL_VF_OFFLOAD_RSS_PF) + +struct virtchnl_vf_resource { + u16 num_vsis; + u16 num_queue_pairs; + u16 max_vectors; + u16 max_mtu; + + u32 vf_cap_flags; + u32 rss_key_size; + u32 rss_lut_size; + + struct virtchnl_vsi_resource vsi_res[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_vf_resource); + +/* VIRTCHNL_OP_CONFIG_TX_QUEUE + * VF sends this message to set up parameters for one TX queue. + * External data buffer contains one instance of virtchnl_txq_info. + * PF configures requested queue and returns a status code. + */ + +/* Tx queue config info */ +struct virtchnl_txq_info { + u16 vsi_id; + u16 queue_id; + u16 ring_len; /* number of descriptors, multiple of 8 */ + u16 headwb_enabled; /* deprecated with AVF 1.0 */ + u64 dma_ring_addr; + u64 dma_headwb_addr; /* deprecated with AVF 1.0 */ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info); + +/* VIRTCHNL_OP_CONFIG_RX_QUEUE + * VF sends this message to set up parameters for one RX queue. + * External data buffer contains one instance of virtchnl_rxq_info. + * PF configures requested queue and returns a status code. + */ + +/* Rx queue config info */ +struct virtchnl_rxq_info { + u16 vsi_id; + u16 queue_id; + u32 ring_len; /* number of descriptors, multiple of 32 */ + u16 hdr_size; + u16 splithdr_enabled; /* deprecated with AVF 1.0 */ + u32 databuffer_size; + u32 max_pkt_size; + u32 pad1; + u64 dma_ring_addr; + enum virtchnl_rx_hsplit rx_split_pos; /* deprecated with AVF 1.0 */ + u32 pad2; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_rxq_info); + +/* VIRTCHNL_OP_CONFIG_VSI_QUEUES + * VF sends this message to set parameters for all active TX and RX queues + * associated with the specified VSI. + * PF configures queues and returns status. + * If the number of queues specified is greater than the number of queues + * associated with the VSI, an error is returned and no queues are configured. + */ +struct virtchnl_queue_pair_info { + /* NOTE: vsi_id and queue_id should be identical for both queues. */ + struct virtchnl_txq_info txq; + struct virtchnl_rxq_info rxq; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(64, virtchnl_queue_pair_info); + +struct virtchnl_vsi_queue_config_info { + u16 vsi_id; + u16 num_queue_pairs; + u32 pad; + struct virtchnl_queue_pair_info qpair[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); + +/* VIRTCHNL_OP_CONFIG_IRQ_MAP + * VF uses this message to map vectors to queues. + * The rxq_map and txq_map fields are bitmaps used to indicate which queues + * are to be associated with the specified vector. + * The "other" causes are always mapped to vector 0. + * PF configures interrupt mapping and returns status. + */ +struct virtchnl_vector_map { + u16 vsi_id; + u16 vector_id; + u16 rxq_map; + u16 txq_map; + u16 rxitr_idx; + u16 txitr_idx; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_vector_map); + +struct virtchnl_irq_map_info { + u16 num_vectors; + struct virtchnl_vector_map vecmap[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(14, virtchnl_irq_map_info); + +/* VIRTCHNL_OP_ENABLE_QUEUES + * VIRTCHNL_OP_DISABLE_QUEUES + * VF sends these message to enable or disable TX/RX queue pairs. + * The queues fields are bitmaps indicating which queues to act upon. + * (Currently, we only support 16 queues per VF, but we make the field + * u32 to allow for expansion.) + * PF performs requested action and returns status. + */ +struct virtchnl_queue_select { + u16 vsi_id; + u16 pad; + u32 rx_queues; + u32 tx_queues; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select); + +/* VIRTCHNL_OP_ADD_ETH_ADDR + * VF sends this message in order to add one or more unicast or multicast + * address filters for the specified VSI. + * PF adds the filters and returns status. + */ + +/* VIRTCHNL_OP_DEL_ETH_ADDR + * VF sends this message in order to remove one or more unicast or multicast + * filters for the specified VSI. + * PF removes the filters and returns status. + */ + +struct virtchnl_ether_addr { + u8 addr[ETH_ALEN]; + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); + +struct virtchnl_ether_addr_list { + u16 vsi_id; + u16 num_elements; + struct virtchnl_ether_addr list[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list); + +/* VIRTCHNL_OP_ADD_VLAN + * VF sends this message to add one or more VLAN tag filters for receives. + * PF adds the filters and returns status. + * If a port VLAN is configured by the PF, this operation will return an + * error to the VF. + */ + +/* VIRTCHNL_OP_DEL_VLAN + * VF sends this message to remove one or more VLAN tag filters for receives. + * PF removes the filters and returns status. + * If a port VLAN is configured by the PF, this operation will return an + * error to the VF. + */ + +struct virtchnl_vlan_filter_list { + u16 vsi_id; + u16 num_elements; + u16 vlan_id[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list); + +/* VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE + * VF sends VSI id and flags. + * PF returns status code in retval. + * Note: we assume that broadcast accept mode is always enabled. + */ +struct virtchnl_promisc_info { + u16 vsi_id; + u16 flags; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_promisc_info); + +#define FLAG_VF_UNICAST_PROMISC 0x00000001 +#define FLAG_VF_MULTICAST_PROMISC 0x00000002 + +/* VIRTCHNL_OP_GET_STATS + * VF sends this message to request stats for the selected VSI. VF uses + * the virtchnl_queue_select struct to specify the VSI. The queue_id + * field is ignored by the PF. + * + * PF replies with struct eth_stats in an external buffer. + */ + +/* VIRTCHNL_OP_CONFIG_RSS_KEY + * VIRTCHNL_OP_CONFIG_RSS_LUT + * VF sends these messages to configure RSS. Only supported if both PF + * and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during + * configuration negotiation. If this is the case, then the RSS fields in + * the VF resource struct are valid. + * Both the key and LUT are initialized to 0 by the PF, meaning that + * RSS is effectively disabled until set up by the VF. + */ +struct virtchnl_rss_key { + u16 vsi_id; + u16 key_len; + u8 key[1]; /* RSS hash key, packed bytes */ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); + +struct virtchnl_rss_lut { + u16 vsi_id; + u16 lut_entries; + u8 lut[1]; /* RSS lookup table*/ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); + +/* VIRTCHNL_OP_GET_RSS_HENA_CAPS + * VIRTCHNL_OP_SET_RSS_HENA + * VF sends these messages to get and set the hash filter enable bits for RSS. + * By default, the PF sets these to all possible traffic types that the + * hardware supports. The VF can query this value if it wants to change the + * traffic types that are hashed by the hardware. + */ +struct virtchnl_rss_hena { + u64 hena; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena); + +/* VIRTCHNL_OP_EVENT + * PF sends this message to inform the VF driver of events that may affect it. + * No direct response is expected from the VF, though it may generate other + * messages in response to this one. + */ +enum virtchnl_event_codes { + VIRTCHNL_EVENT_UNKNOWN = 0, + VIRTCHNL_EVENT_LINK_CHANGE, + VIRTCHNL_EVENT_RESET_IMPENDING, + VIRTCHNL_EVENT_PF_DRIVER_CLOSE, +}; + +#define PF_EVENT_SEVERITY_INFO 0 +#define PF_EVENT_SEVERITY_CERTAIN_DOOM 255 + +struct virtchnl_pf_event { + enum virtchnl_event_codes event; + union { + struct { + enum virtchnl_link_speed link_speed; + bool link_status; + } link_event; + } event_data; + + int severity; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_pf_event); + +/* VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP + * VF uses this message to request PF to map IWARP vectors to IWARP queues. + * The request for this originates from the VF IWARP driver through + * a client interface between VF LAN and VF IWARP driver. + * A vector could have an AEQ and CEQ attached to it although + * there is a single AEQ per VF IWARP instance in which case + * most vectors will have an INVALID_IDX for aeq and valid idx for ceq. + * There will never be a case where there will be multiple CEQs attached + * to a single vector. + * PF configures interrupt mapping and returns status. + */ + +struct virtchnl_iwarp_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); + +struct virtchnl_iwarp_qvlist_info { + u32 num_vectors; + struct virtchnl_iwarp_qv_info qv_info[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_iwarp_qvlist_info); + +/* VF reset states - these are written into the RSTAT register: + * VFGEN_RSTAT on the VF + * When the PF initiates a reset, it writes 0 + * When the reset is complete, it writes 1 + * When the PF detects that the VF has recovered, it writes 2 + * VF checks this register periodically to determine if a reset has occurred, + * then polls it to know when the reset is complete. + * If either the PF or VF reads the register while the hardware + * is in a reset state, it will return DEADBEEF, which, when masked + * will result in 3. + */ +enum virtchnl_vfr_states { + VIRTCHNL_VFR_INPROGRESS = 0, + VIRTCHNL_VFR_COMPLETED, + VIRTCHNL_VFR_VFACTIVE, +}; + +/** + * virtchnl_vc_validate_vf_msg + * @ver: Virtchnl version info + * @v_opcode: Opcode for the message + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * validate msg format against struct for each opcode + */ +static inline int +virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, + u8 *msg, u16 msglen) +{ + bool err_msg_format = false; + int valid_len = 0; + + /* Validate message length. */ + switch (v_opcode) { + case VIRTCHNL_OP_VERSION: + valid_len = sizeof(struct virtchnl_version_info); + break; + case VIRTCHNL_OP_RESET_VF: + break; + case VIRTCHNL_OP_GET_VF_RESOURCES: + if (VF_IS_V11(ver)) + valid_len = sizeof(u32); + break; + case VIRTCHNL_OP_CONFIG_TX_QUEUE: + valid_len = sizeof(struct virtchnl_txq_info); + break; + case VIRTCHNL_OP_CONFIG_RX_QUEUE: + valid_len = sizeof(struct virtchnl_rxq_info); + break; + case VIRTCHNL_OP_CONFIG_VSI_QUEUES: + valid_len = sizeof(struct virtchnl_vsi_queue_config_info); + if (msglen >= valid_len) { + struct virtchnl_vsi_queue_config_info *vqc = + (struct virtchnl_vsi_queue_config_info *)msg; + valid_len += (vqc->num_queue_pairs * + sizeof(struct + virtchnl_queue_pair_info)); + if (vqc->num_queue_pairs == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_CONFIG_IRQ_MAP: + valid_len = sizeof(struct virtchnl_irq_map_info); + if (msglen >= valid_len) { + struct virtchnl_irq_map_info *vimi = + (struct virtchnl_irq_map_info *)msg; + valid_len += (vimi->num_vectors * + sizeof(struct virtchnl_vector_map)); + if (vimi->num_vectors == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_ENABLE_QUEUES: + case VIRTCHNL_OP_DISABLE_QUEUES: + valid_len = sizeof(struct virtchnl_queue_select); + break; + case VIRTCHNL_OP_ADD_ETH_ADDR: + case VIRTCHNL_OP_DEL_ETH_ADDR: + valid_len = sizeof(struct virtchnl_ether_addr_list); + if (msglen >= valid_len) { + struct virtchnl_ether_addr_list *veal = + (struct virtchnl_ether_addr_list *)msg; + valid_len += veal->num_elements * + sizeof(struct virtchnl_ether_addr); + if (veal->num_elements == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_ADD_VLAN: + case VIRTCHNL_OP_DEL_VLAN: + valid_len = sizeof(struct virtchnl_vlan_filter_list); + if (msglen >= valid_len) { + struct virtchnl_vlan_filter_list *vfl = + (struct virtchnl_vlan_filter_list *)msg; + valid_len += vfl->num_elements * sizeof(u16); + if (vfl->num_elements == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: + valid_len = sizeof(struct virtchnl_promisc_info); + break; + case VIRTCHNL_OP_GET_STATS: + valid_len = sizeof(struct virtchnl_queue_select); + break; + case VIRTCHNL_OP_IWARP: + /* These messages are opaque to us and will be validated in + * the RDMA client code. We just need to check for nonzero + * length. The firmware will enforce max length restrictions. + */ + if (msglen) + valid_len = msglen; + else + err_msg_format = true; + break; + case VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP: + break; + case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: + valid_len = sizeof(struct virtchnl_iwarp_qvlist_info); + if (msglen >= valid_len) { + struct virtchnl_iwarp_qvlist_info *qv = + (struct virtchnl_iwarp_qvlist_info *)msg; + if (qv->num_vectors == 0) { + err_msg_format = true; + break; + } + valid_len += ((qv->num_vectors - 1) * + sizeof(struct virtchnl_iwarp_qv_info)); + } + break; + case VIRTCHNL_OP_CONFIG_RSS_KEY: + valid_len = sizeof(struct virtchnl_rss_key); + if (msglen >= valid_len) { + struct virtchnl_rss_key *vrk = + (struct virtchnl_rss_key *)msg; + valid_len += vrk->key_len - 1; + } + break; + case VIRTCHNL_OP_CONFIG_RSS_LUT: + valid_len = sizeof(struct virtchnl_rss_lut); + if (msglen >= valid_len) { + struct virtchnl_rss_lut *vrl = + (struct virtchnl_rss_lut *)msg; + valid_len += vrl->lut_entries - 1; + } + break; + case VIRTCHNL_OP_GET_RSS_HENA_CAPS: + break; + case VIRTCHNL_OP_SET_RSS_HENA: + valid_len = sizeof(struct virtchnl_rss_hena); + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + break; + /* These are always errors coming from the VF. */ + case VIRTCHNL_OP_EVENT: + case VIRTCHNL_OP_UNKNOWN: + default: + return VIRTCHNL_ERR_PARAM; + } + /* few more checks */ + if ((valid_len != msglen) || (err_msg_format)) + return VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH; + + return 0; +} +#endif /* _VIRTCHNL_H_ */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 557d84063934..854e1bdd0b2a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -66,37 +66,17 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) static inline void __add_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { - __percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH); -} - -static inline void __inc_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, 1); + percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __inc_wb_stat(wb, item); - local_irq_restore(flags); -} - -static inline void __dec_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, -1); + __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __dec_wb_stat(wb, item); - local_irq_restore(flags); + __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) @@ -104,22 +84,9 @@ static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) return percpu_counter_read_positive(&wb->stat[item]); } -static inline s64 __wb_stat_sum(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - return percpu_counter_sum_positive(&wb->stat[item]); -} - static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { - s64 sum; - unsigned long flags; - - local_irq_save(flags); - sum = __wb_stat_sum(wb, item); - local_irq_restore(flags); - - return sum; + return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); diff --git a/include/linux/bcm47xx_nvram.h b/include/linux/bcm47xx_nvram.h index 2793652fbf66..a414a2b53e41 100644 --- a/include/linux/bcm47xx_nvram.h +++ b/include/linux/bcm47xx_nvram.h @@ -8,6 +8,7 @@ #ifndef __BCM47XX_NVRAM_H #define __BCM47XX_NVRAM_H +#include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/vmalloc.h> diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 05488da3aee9..fb44d6180ca0 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -25,11 +25,25 @@ struct linux_binprm { struct mm_struct *mm; unsigned long p; /* current top of mem */ unsigned int - cred_prepared:1,/* true if creds already prepared (multiple - * preps happen for interpreters) */ - cap_effective:1;/* true if has elevated effective capabilities, - * false if not; except for init which inherits - * its parent's caps anyway */ + /* + * True after the bprm_set_creds hook has been called once + * (multiple calls can be made via prepare_binprm() for + * binfmt_script/misc). + */ + called_set_creds:1, + /* + * True if most recent call to the commoncaps bprm_set_creds + * hook (due to multiple prepare_binprm() calls from the + * binfmt_script/misc handlers) resulted in elevated + * privileges. + */ + cap_elevated:1, + /* + * Set by bprm_set_creds hook to indicate a privilege-gaining + * exec has happened. Used to sanitize execution environment + * and to set AT_SECURE auxv for glibc. + */ + secureexec:1; #ifdef __alpha__ unsigned int taso:1; #endif @@ -46,7 +60,7 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; -}; +} __randomize_layout; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) @@ -81,7 +95,7 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ -}; +} __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); diff --git a/include/linux/bio.h b/include/linux/bio.h index a7e29fa0981f..275c91c99516 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -38,7 +38,15 @@ #define BIO_BUG_ON #endif +#ifdef CONFIG_THP_SWAP +#if HPAGE_PMD_NR > 256 +#define BIO_MAX_PAGES HPAGE_PMD_NR +#else #define BIO_MAX_PAGES 256 +#endif +#else +#define BIO_MAX_PAGES 256 +#endif #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) @@ -118,7 +126,6 @@ static inline void *bio_data(struct bio *bio) /* * will die */ -#define bio_to_phys(bio) (page_to_phys(bio_page((bio))) + (unsigned long) bio_offset((bio))) #define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) /* @@ -166,10 +173,27 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, { iter->bi_sector += bytes >> 9; - if (bio_no_advance_iter(bio)) + if (bio_no_advance_iter(bio)) { iter->bi_size -= bytes; - else + iter->bi_done += bytes; + } else { bvec_iter_advance(bio->bi_io_vec, iter, bytes); + /* TODO: It is reasonable to complete bio with error here. */ + } +} + +static inline bool bio_rewind_iter(struct bio *bio, struct bvec_iter *iter, + unsigned int bytes) +{ + iter->bi_sector -= bytes >> 9; + + if (bio_no_advance_iter(bio)) { + iter->bi_size += bytes; + iter->bi_done -= bytes; + return true; + } + + return bvec_iter_rewind(bio->bi_io_vec, iter, bytes); } #define __bio_for_each_segment(bvl, bio, iter, start) \ @@ -304,8 +328,6 @@ struct bio_integrity_payload { struct bvec_iter bip_iter; - bio_end_io_t *bip_end_io; /* saved I/O completion fn */ - unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ @@ -373,8 +395,11 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors, return bio_split(bio, sectors, gfp, bs); } -extern struct bio_set *bioset_create(unsigned int, unsigned int); -extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int); +extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags); +enum { + BIOSET_NEED_BVECS = BIT(0), + BIOSET_NEED_RESCUER = BIT(1), +}; extern void bioset_free(struct bio_set *); extern mempool_t *biovec_create_pool(int pool_entries); @@ -392,11 +417,6 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set); } -static inline struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask) -{ - return bio_clone_bioset(bio, gfp_mask, fs_bio_set); -} - static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); @@ -414,7 +434,13 @@ extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); +} + +static inline void bio_wouldblock_error(struct bio *bio) +{ + bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } @@ -445,10 +471,11 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -void generic_start_io_acct(int rw, unsigned long sectors, - struct hd_struct *part); -void generic_end_io_acct(int rw, struct hd_struct *part, - unsigned long start_time); +void generic_start_io_acct(struct request_queue *q, int rw, + unsigned long sectors, struct hd_struct *part); +void generic_end_io_acct(struct request_queue *q, int rw, + struct hd_struct *part, + unsigned long start_time); #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" @@ -475,6 +502,24 @@ extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); +#define bio_set_dev(bio, bdev) \ +do { \ + (bio)->bi_disk = (bdev)->bd_disk; \ + (bio)->bi_partno = (bdev)->bd_partno; \ +} while (0) + +#define bio_copy_dev(dst, src) \ +do { \ + (dst)->bi_disk = (src)->bi_disk; \ + (dst)->bi_partno = (src)->bi_partno; \ +} while (0) + +#define bio_dev(bio) \ + disk_devt((bio)->bi_disk) + +#define bio_devname(bio, buf) \ + __bdevname(bio_dev(bio), (buf)) + #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); @@ -719,13 +764,10 @@ struct biovec_slab { bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern void bio_integrity_free(struct bio *); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); -extern bool bio_integrity_enabled(struct bio *bio); -extern int bio_integrity_prep(struct bio *); -extern void bio_integrity_endio(struct bio *); +extern bool bio_integrity_prep(struct bio *); extern void bio_integrity_advance(struct bio *, unsigned int); -extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); +extern void bio_integrity_trim(struct bio *); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); @@ -738,11 +780,6 @@ static inline void *bio_integrity(struct bio *bio) return NULL; } -static inline bool bio_integrity_enabled(struct bio *bio) -{ - return false; -} - static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) { return 0; @@ -753,14 +790,9 @@ static inline void bioset_integrity_free (struct bio_set *bs) return; } -static inline int bio_integrity_prep(struct bio *bio) +static inline bool bio_integrity_prep(struct bio *bio) { - return 0; -} - -static inline void bio_integrity_free(struct bio *bio) -{ - return; + return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, @@ -775,8 +807,7 @@ static inline void bio_integrity_advance(struct bio *bio, return; } -static inline void bio_integrity_trim(struct bio *bio, unsigned int offset, - unsigned int sectors) +static inline void bio_integrity_trim(struct bio *bio) { return; } diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 3b77588a9360..700cf5f67118 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -112,9 +112,8 @@ extern int __bitmap_intersects(const unsigned long *bitmap1, extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); - -extern void bitmap_set(unsigned long *map, unsigned int start, int len); -extern void bitmap_clear(unsigned long *map, unsigned int start, int len); +extern void __bitmap_set(unsigned long *map, unsigned int start, int len); +extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, @@ -267,10 +266,8 @@ static inline int bitmap_equal(const unsigned long *src1, { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); -#ifdef CONFIG_S390 - if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) return !memcmp(src1, src2, nbits / 8); -#endif return __bitmap_equal(src1, src2, nbits); } @@ -315,6 +312,30 @@ static __always_inline int bitmap_weight(const unsigned long *src, unsigned int return __bitmap_weight(src, nbits); } +static __always_inline void bitmap_set(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __set_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0xff, nbits / 8); + else + __bitmap_set(map, start, nbits); +} + +static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __clear_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0, nbits / 8); + else + __bitmap_clear(map, start, nbits); +} + static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, int nbits) { @@ -340,6 +361,38 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen, } /* + * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. + * + * Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit + * integers in 32-bit environment, and 64-bit integers in 64-bit one. + * + * There are four combinations of endianness and length of the word in linux + * ABIs: LE64, BE64, LE32 and BE32. + * + * On 64-bit kernels 64-bit LE and BE numbers are naturally ordered in + * bitmaps and therefore don't require any special handling. + * + * On 32-bit kernels 32-bit LE ABI orders lo word of 64-bit number in memory + * prior to hi, and 32-bit BE orders hi word prior to lo. The bitmap on the + * other hand is represented as an array of 32-bit words and the position of + * bit N may therefore be calculated as: word #(N/32) and bit #(N%32) in that + * word. For example, bit #42 is located at 10th position of 2nd word. + * It matches 32-bit LE ABI, and we can simply let the compiler store 64-bit + * values in memory as it usually does. But for BE we need to swap hi and lo + * words manually. + * + * With all that, the macro BITMAP_FROM_U64() does explicit reordering of hi and + * lo parts of u64. For LE32 it does nothing, and for BE environment it swaps + * hi and lo words, as is expected by bitmap. + */ +#if __BITS_PER_LONG == 64 +#define BITMAP_FROM_U64(n) (n) +#else +#define BITMAP_FROM_U64(n) ((unsigned long) ((u64)(n) & ULONG_MAX)), \ + ((unsigned long) ((u64)(n) >> 32)) +#endif + +/* * bitmap_from_u64 - Check and swap words within u64. * @mask: source bitmap * @dst: destination bitmap diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a83c822c35c2..8fbe259b197c 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -19,10 +19,11 @@ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ #define GENMASK(h, l) \ - (((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) #define GENMASK_ULL(h, l) \ - (((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index fb790b8449c1..b97be27e5a85 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -29,6 +29,8 @@ static inline u32 __bitrev32(u32 x) #endif /* CONFIG_HAVE_ARCH_BITREVERSE */ +#define __bitrev8x4(x) (__bitrev32(swab32(x))) + #define __constant_bitrev32(x) \ ({ \ u32 __x = x; \ @@ -50,6 +52,15 @@ static inline u32 __bitrev32(u32 x) __x; \ }) +#define __constant_bitrev8x4(x) \ +({ \ + u32 __x = x; \ + __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ + __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ + __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ + __x; \ +}) + #define __constant_bitrev8(x) \ ({ \ u8 __x = x; \ @@ -75,6 +86,14 @@ static inline u32 __bitrev32(u32 x) __bitrev16(__x); \ }) +#define bitrev8x4(x) \ +({ \ + u32 __x = x; \ + __builtin_constant_p(__x) ? \ + __constant_bitrev8x4(__x) : \ + __bitrev8x4(__x); \ + }) + #define bitrev8(x) \ ({ \ u8 __x = x; \ diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 01b62e7bac74..9d92153dd856 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -518,7 +518,7 @@ static inline void blkg_stat_exit(struct blkg_stat *stat) */ static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val) { - __percpu_counter_add(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); } /** @@ -597,14 +597,14 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; - __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); if (op_is_sync(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); } /** @@ -691,6 +691,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, rcu_read_lock(); blkcg = bio_blkcg(bio); + /* associate blkcg if bio hasn't attached one */ + bio_associate_blkcg(bio, &blkcg->css); + blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { spin_lock_irq(q->queue_lock); diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h new file mode 100644 index 000000000000..b4ade198007d --- /dev/null +++ b/include/linux/blk-mq-rdma.h @@ -0,0 +1,10 @@ +#ifndef _LINUX_BLK_MQ_RDMA_H +#define _LINUX_BLK_MQ_RDMA_H + +struct blk_mq_tag_set; +struct ib_device; + +int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set, + struct ib_device *dev, int first_vec); + +#endif /* _LINUX_BLK_MQ_RDMA_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index fcd641032f8d..50c6485cb04f 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -33,14 +33,12 @@ struct blk_mq_hw_ctx { struct blk_mq_ctx **ctxs; unsigned int nr_ctx; - wait_queue_t dispatch_wait; + wait_queue_entry_t dispatch_wait; atomic_t wait_index; struct blk_mq_tags *tags; struct blk_mq_tags *sched_tags; - struct srcu_struct queue_rq_srcu; - unsigned long queued; unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 @@ -62,6 +60,9 @@ struct blk_mq_hw_ctx { struct dentry *debugfs_dir; struct dentry *sched_debugfs_dir; #endif + + /* Must be the last member - see also blk_mq_hw_ctx_size(). */ + struct srcu_struct queue_rq_srcu[0]; }; struct blk_mq_tag_set { @@ -87,7 +88,8 @@ struct blk_mq_queue_data { bool last; }; -typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, + const struct blk_mq_queue_data *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); @@ -95,7 +97,6 @@ typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *, unsigned int, unsigned int); typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *, unsigned int); -typedef int (reinit_request_fn)(void *, struct request *); typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); @@ -141,7 +142,8 @@ struct blk_mq_ops { */ init_request_fn *init_request; exit_request_fn *exit_request; - reinit_request_fn *reinit_request; + /* Called from inside blk_get_request() */ + void (*initialize_rq_fn)(struct request *rq); map_queues_fn *map_queues; @@ -155,10 +157,6 @@ struct blk_mq_ops { }; enum { - BLK_MQ_RQ_QUEUE_OK = 0, /* queued fine */ - BLK_MQ_RQ_QUEUE_BUSY = 1, /* requeue IO for later */ - BLK_MQ_RQ_QUEUE_ERROR = 2, /* end IO with error */ - BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, BLK_MQ_F_SG_MERGE = 1 << 2, @@ -204,10 +202,10 @@ enum { BLK_MQ_REQ_INTERNAL = (1 << 2), /* allocate internal/sched tag */ }; -struct request *blk_mq_alloc_request(struct request_queue *q, int rw, +struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, unsigned int flags); -struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op, - unsigned int flags, unsigned int hctx_idx); +struct request *blk_mq_alloc_request_hctx(struct request_queue *q, + unsigned int op, unsigned int flags, unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); enum { @@ -230,8 +228,8 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) int blk_mq_request_started(struct request *rq); void blk_mq_start_request(struct request *rq); -void blk_mq_end_request(struct request *rq, int error); -void __blk_mq_end_request(struct request *rq, int error); +void blk_mq_end_request(struct request *rq, blk_status_t error); +void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, @@ -247,6 +245,8 @@ void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); +void blk_mq_quiesce_queue(struct request_queue *q); +void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); @@ -259,11 +259,14 @@ void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_reinit_tagset(struct blk_mq_tag_set *set); +int blk_mq_reinit_tagset(struct blk_mq_tag_set *set, + int (reinit_request)(void *, struct request *)); int blk_mq_map_queues(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); +void blk_mq_quiesce_queue_nowait(struct request_queue *q); + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 61339bc44400..a2d2aa709cef 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -17,6 +17,27 @@ struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); +/* + * Block error status values. See block/blk-core:blk_errors for the details. + */ +typedef u8 __bitwise blk_status_t; +#define BLK_STS_OK 0 +#define BLK_STS_NOTSUPP ((__force blk_status_t)1) +#define BLK_STS_TIMEOUT ((__force blk_status_t)2) +#define BLK_STS_NOSPC ((__force blk_status_t)3) +#define BLK_STS_TRANSPORT ((__force blk_status_t)4) +#define BLK_STS_TARGET ((__force blk_status_t)5) +#define BLK_STS_NEXUS ((__force blk_status_t)6) +#define BLK_STS_MEDIUM ((__force blk_status_t)7) +#define BLK_STS_PROTECTION ((__force blk_status_t)8) +#define BLK_STS_RESOURCE ((__force blk_status_t)9) +#define BLK_STS_IOERR ((__force blk_status_t)10) + +/* hack for device mapper, don't use elsewhere: */ +#define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) + +#define BLK_STS_AGAIN ((__force blk_status_t)12) + struct blk_issue_stat { u64 stat; }; @@ -27,14 +48,16 @@ struct blk_issue_stat { */ struct bio { struct bio *bi_next; /* request queue link */ - struct block_device *bi_bdev; - int bi_error; + struct gendisk *bi_disk; + u8 bi_partno; + blk_status_t bi_status; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use * accessors. */ unsigned short bi_flags; /* status, etc and bvec pool number */ unsigned short bi_ioprio; + unsigned short bi_write_hint; struct bvec_iter bi_iter; @@ -205,6 +228,7 @@ enum req_flag_bits { /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ + __REQ_NOWAIT, /* Don't wait if request will block */ __REQ_NR_BITS, /* stops here */ }; @@ -223,6 +247,7 @@ enum req_flag_bits { #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) +#define REQ_NOWAIT (1ULL << __REQ_NOWAIT) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1ddd36bd2173..460294bb0fa5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -55,7 +55,7 @@ struct blk_stat_callback; */ #define BLKCG_MAX_POLS 3 -typedef void (rq_end_io_fn)(struct request *, int); +typedef void (rq_end_io_fn)(struct request *, blk_status_t); #define BLK_RL_SYNCFULL (1U << 0) #define BLK_RL_ASYNCFULL (1U << 1) @@ -134,7 +134,7 @@ typedef __u32 __bitwise req_flags_t; struct request { struct list_head queuelist; union { - struct call_single_data csd; + call_single_data_t csd; u64 fifo_time; }; @@ -225,6 +225,8 @@ struct request { unsigned int extra_len; /* length of alignment and padding */ + unsigned short write_hint; + unsigned long deadline; struct list_head timeout_list; @@ -412,8 +414,12 @@ struct request_queue { rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; lld_busy_fn *lld_busy_fn; + /* Called just after a request is allocated */ init_rq_fn *init_rq_fn; + /* Called just before a request is freed */ exit_rq_fn *exit_rq_fn; + /* Called from inside blk_get_request() */ + void (*initialize_rq_fn)(struct request *rq); const struct blk_mq_ops *mq_ops; @@ -562,7 +568,6 @@ struct request_queue { #if defined(CONFIG_BLK_DEV_BSG) bsg_job_fn *bsg_job_fn; - int bsg_job_size; struct bsg_class_device bsg_dev; #endif @@ -590,38 +595,41 @@ struct request_queue { void *rq_alloc_data; struct work_struct release_work; + +#define BLK_MAX_WRITE_HINTS 5 + u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -#define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ -#define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ -#define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */ -#define QUEUE_FLAG_DYING 5 /* queue being torn down */ -#define QUEUE_FLAG_BYPASS 6 /* act as dumb FIFO queue */ -#define QUEUE_FLAG_BIDI 7 /* queue supports bidi requests */ -#define QUEUE_FLAG_NOMERGES 8 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 9 /* complete on same CPU-group */ -#define QUEUE_FLAG_FAIL_IO 10 /* fake timeout */ -#define QUEUE_FLAG_STACKABLE 11 /* supports request stacking */ -#define QUEUE_FLAG_NONROT 12 /* non-rotational device (SSD) */ +#define QUEUE_FLAG_QUEUED 0 /* uses generic tag queueing */ +#define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ +#define QUEUE_FLAG_DYING 2 /* queue being torn down */ +#define QUEUE_FLAG_BYPASS 3 /* act as dumb FIFO queue */ +#define QUEUE_FLAG_BIDI 4 /* queue supports bidi requests */ +#define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ +#define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ +#define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ +#define QUEUE_FLAG_STACKABLE 8 /* supports request stacking */ +#define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 13 /* do IO stats */ -#define QUEUE_FLAG_DISCARD 14 /* supports DISCARD */ -#define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */ -#define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 17 /* supports secure erase */ -#define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */ -#define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ -#define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ -#define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/ -#define QUEUE_FLAG_POLL 22 /* IO polling enabled if set */ -#define QUEUE_FLAG_WC 23 /* Write back caching */ -#define QUEUE_FLAG_FUA 24 /* device supports FUA writes */ -#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ -#define QUEUE_FLAG_DAX 26 /* device supports DAX */ -#define QUEUE_FLAG_STATS 27 /* track rq completion times */ -#define QUEUE_FLAG_POLL_STATS 28 /* collecting stats for hybrid polling */ -#define QUEUE_FLAG_REGISTERED 29 /* queue has been registered to a disk */ +#define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ +#define QUEUE_FLAG_DISCARD 11 /* supports DISCARD */ +#define QUEUE_FLAG_NOXMERGES 12 /* No extended merges */ +#define QUEUE_FLAG_ADD_RANDOM 13 /* Contributes to random pool */ +#define QUEUE_FLAG_SECERASE 14 /* supports secure erase */ +#define QUEUE_FLAG_SAME_FORCE 15 /* force complete on same CPU */ +#define QUEUE_FLAG_DEAD 16 /* queue tear-down finished */ +#define QUEUE_FLAG_INIT_DONE 17 /* queue is initialized */ +#define QUEUE_FLAG_NO_SG_MERGE 18 /* don't attempt to merge SG segments*/ +#define QUEUE_FLAG_POLL 19 /* IO polling enabled if set */ +#define QUEUE_FLAG_WC 20 /* Write back caching */ +#define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ +#define QUEUE_FLAG_FLUSH_NQ 22 /* flush not queueuable */ +#define QUEUE_FLAG_DAX 23 /* device supports DAX */ +#define QUEUE_FLAG_STATS 24 /* track rq completion times */ +#define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ +#define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ +#define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ +#define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -633,6 +641,13 @@ struct request_queue { (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_POLL)) +/* + * @q->queue_lock is set while a queue is being initialized. Since we know + * that no other threads access the queue object before @q->queue_lock has + * been set, it is safe to manipulate queue flags without holding the + * queue_lock if @q->queue_lock == NULL. See also blk_alloc_queue_node() and + * blk_init_allocated_queue(). + */ static inline void queue_lockdep_assert_held(struct request_queue *q) { if (q->queue_lock) @@ -712,10 +727,13 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) +#define blk_queue_scsi_passthrough(q) \ + test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) +#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) static inline bool blk_account_rq(struct request *rq) { @@ -814,7 +832,8 @@ static inline bool rq_mergeable(struct request *rq) static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { - if (bio_data(a) == bio_data(b)) + if (bio_page(a) == bio_page(b) && + bio_offset(a) == bio_offset(b)) return true; return false; @@ -862,19 +881,6 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) -#ifdef CONFIG_BOUNCE -extern int init_emergency_isa_pool(void); -extern void blk_queue_bounce(struct request_queue *q, struct bio **bio); -#else -static inline int init_emergency_isa_pool(void) -{ - return 0; -} -static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) -{ -} -#endif /* CONFIG_MMU */ - struct rq_map_data { struct page **pages; int page_order; @@ -933,7 +939,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); -extern struct request *blk_get_request(struct request_queue *, int, gfp_t); +extern struct request *blk_get_request(struct request_queue *, unsigned int op, + gfp_t gfp_mask); extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, @@ -941,12 +948,11 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); extern void blk_rq_unprep_clone(struct request *rq); -extern int blk_insert_cloned_request(struct request_queue *q, +extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_delay_queue(struct request_queue *, unsigned long); -extern void blk_queue_split(struct request_queue *, struct bio **, - struct bio_set *); +extern void blk_queue_split(struct request_queue *, struct bio **); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, @@ -967,7 +973,6 @@ extern void __blk_run_queue(struct request_queue *q); extern void __blk_run_queue_uncond(struct request_queue *q); extern void blk_run_queue(struct request_queue *); extern void blk_run_queue_async(struct request_queue *q); -extern void blk_mq_quiesce_queue(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); @@ -981,6 +986,9 @@ extern void blk_execute_rq(struct request_queue *, struct gendisk *, extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); +int blk_status_to_errno(blk_status_t status); +blk_status_t errno_to_blk_status(int errno); + bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) @@ -1113,16 +1121,16 @@ extern struct request *blk_fetch_request(struct request_queue *q); * blk_end_request() for parts of the original function. * This prevents code duplication in drivers. */ -extern bool blk_update_request(struct request *rq, int error, +extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_finish_request(struct request *rq, int error); -extern bool blk_end_request(struct request *rq, int error, +extern void blk_finish_request(struct request *rq, blk_status_t error); +extern bool blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_end_request_all(struct request *rq, int error); -extern bool __blk_end_request(struct request *rq, int error, +extern void blk_end_request_all(struct request *rq, blk_status_t error); +extern bool __blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void __blk_end_request_all(struct request *rq, int error); -extern bool __blk_end_request_cur(struct request *rq, int error); +extern void __blk_end_request_all(struct request *rq, blk_status_t error); +extern bool __blk_end_request_cur(struct request *rq, blk_status_t error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); @@ -1374,11 +1382,6 @@ enum blk_default_limits { #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) -static inline unsigned long queue_bounce_pfn(struct request_queue *q) -{ - return q->limits.bounce_pfn; -} - static inline unsigned long queue_segment_boundary(struct request_queue *q) { return q->limits.seg_boundary_mask; @@ -1780,7 +1783,7 @@ struct blk_integrity_iter { const char *disk_name; }; -typedef int (integrity_processing_fn) (struct blk_integrity_iter *); +typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); struct blk_integrity_profile { integrity_processing_fn *generate_fn; diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index d2e908586e3d..67b4d4dfc19c 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -28,10 +28,12 @@ struct blk_trace { atomic_t dropped; }; +struct blkcg; + extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(2, 3) -void __trace_note_message(struct blk_trace *, const char *fmt, ...); +extern __printf(3, 4) +void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -46,12 +48,14 @@ void __trace_note_message(struct blk_trace *, const char *fmt, ...); * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_trace_msg(q, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ struct blk_trace *bt = (q)->blk_trace; \ if (unlikely(bt)) \ - __trace_note_message(bt, fmt, ##__VA_ARGS__); \ + __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ } while (0) +#define blk_add_trace_msg(q, fmt, ...) \ + blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) #define BLK_TN_MAX_MSG 128 static inline bool blk_trace_note_message_enabled(struct request_queue *q) @@ -82,6 +86,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) +# define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0) # define blk_trace_remove_sysfs(dev) do { } while (0) # define blk_trace_note_message_enabled(q) (false) static inline int blk_trace_init_sysfs(struct device *dev) diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 962164d36506..e223d91b6439 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -358,6 +358,7 @@ extern void *alloc_large_system_hash(const char *tablename, #define HASH_EARLY 0x00000001 /* Allocating during early boot? */ #define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min * shift passed via *_hash_shift */ +#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ /* Only NUMA needs hash distribution. 64bit NUMA architectures have * sufficient vmalloc space. diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index c970a25d2a49..d41d40ac3efd 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -7,6 +7,7 @@ struct sock; struct cgroup; struct sk_buff; +struct bpf_sock_ops_kern; #ifdef CONFIG_CGROUP_BPF @@ -42,6 +43,10 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, int __cgroup_bpf_run_filter_sk(struct sock *sk, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, + struct bpf_sock_ops_kern *sock_ops, + enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -75,6 +80,18 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled && (sock_ops)->sk) { \ + typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ + if (__sk && sk_fullsock(__sk)) \ + __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + } \ + __ret; \ +}) #else struct cgroup_bpf {}; @@ -85,6 +102,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6bb38d76faf4..8390859e79e7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -14,8 +14,10 @@ #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> +#include <linux/numa.h> struct perf_event; +struct bpf_prog; struct bpf_map; /* map is generic key/value storage optionally accesible by eBPF programs */ @@ -36,6 +38,7 @@ struct bpf_map_ops { int fd); void (*map_fd_put_ptr)(void *ptr); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); + u32 (*map_fd_sys_lookup_elem)(void *ptr); }; struct bpf_map { @@ -46,6 +49,8 @@ struct bpf_map { u32 max_entries; u32 map_flags; u32 pages; + u32 id; + int numa_node; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; @@ -115,38 +120,40 @@ enum bpf_access_type { }; /* types of values stored in eBPF registers */ +/* Pointer types represent: + * pointer + * pointer + imm + * pointer + (u16) var + * pointer + (u16) var + imm + * if (range > 0) then [ptr, ptr + range - off) is safe to access + * if (id > 0) means that some 'var' was added + * if (off > 0) means that 'imm' was added + */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ - UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ - FRAME_PTR, /* reg == frame_pointer */ - PTR_TO_STACK, /* reg == frame_pointer + imm */ - CONST_IMM, /* constant integer value */ - - /* PTR_TO_PACKET represents: - * skb->data - * skb->data + imm - * skb->data + (u16) var - * skb->data + (u16) var + imm - * if (range > 0) then [ptr, ptr + range - off) is safe to access - * if (id > 0) means that some 'var' was added - * if (off > 0) menas that 'imm' was added - */ - PTR_TO_PACKET, + PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ +}; - /* PTR_TO_MAP_VALUE_ADJ is used for doing pointer math inside of a map - * elem value. We only allow this if we can statically verify that - * access from this register are going to fall within the size of the - * map element. - */ - PTR_TO_MAP_VALUE_ADJ, +/* The information passed from prog-specific *_is_valid_access + * back to the verifier. + */ +struct bpf_insn_access_aux { + enum bpf_reg_type reg_type; + int ctx_field_size; }; -struct bpf_prog; +static inline void +bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) +{ + aux->ctx_field_size = size; +} struct bpf_verifier_ops { /* return eBPF function prototype for verification */ @@ -156,13 +163,13 @@ struct bpf_verifier_ops { * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type); + struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, - struct bpf_prog *prog); + struct bpf_prog *prog, u32 *target_size); int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); }; @@ -171,6 +178,8 @@ struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; + u32 stack_depth; + u32 id; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_verifier_ops *ops; @@ -244,6 +253,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); +struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); @@ -254,7 +264,7 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); -void *bpf_map_area_alloc(size_t size); +void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; @@ -276,9 +286,11 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); +int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); void bpf_fd_array_map_clear(struct bpf_map *map); int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); +int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. @@ -298,6 +310,19 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); + +/* Map specifics */ +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +void __dev_map_insert_ctx(struct bpf_map *map, u32 index); +void __dev_map_flush(struct bpf_map *map); + +/* Return map's numa specified by userspace */ +static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) +{ + return (attr->map_flags & BPF_F_NUMA_NODE) ? + attr->numa_node : NUMA_NO_NODE; +} + #else static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -328,6 +353,12 @@ static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) return ERR_PTR(-EOPNOTSUPP); } +static inline struct bpf_prog *__must_check +bpf_prog_inc_not_zero(struct bpf_prog *prog) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) { return 0; @@ -336,8 +367,39 @@ static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } + +static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + +static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __dev_map_flush(struct bpf_map *map) +{ +} #endif /* CONFIG_BPF_SYSCALL */ +#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) +struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); +int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); +#else +static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) +{ + return NULL; +} + +static inline int sock_map_prog(struct bpf_map *map, + struct bpf_prog *prog, + u32 type) +{ + return -EOPNOTSUPP; +} +#endif + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; @@ -354,6 +416,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; +extern const struct bpf_func_proto bpf_sock_map_update_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 03bf223f18be..6f1a567667b8 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -10,6 +10,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) @@ -34,3 +36,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) +#ifdef CONFIG_NET +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +#ifdef CONFIG_STREAM_PARSER +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) +#endif +#endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d5093b52b485..b8d200f60a40 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -9,40 +9,75 @@ #include <linux/bpf.h> /* for enum bpf_reg_type */ #include <linux/filter.h> /* for MAX_BPF_STACK */ +#include <linux/tnum.h> - /* Just some arbitrary values so we can safely do math without overflowing and - * are obviously wrong for any sort of memory access. - */ -#define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) -#define BPF_REGISTER_MIN_RANGE -1 +/* Maximum variable offset umax_value permitted when resolving memory accesses. + * In practice this is far bigger than any realistic pointer offset; this limit + * ensures that umax_value + (int)off + (int)size cannot overflow a u64. + */ +#define BPF_MAX_VAR_OFF (1ULL << 31) +/* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures + * that converting umax_value to int cannot overflow. + */ +#define BPF_MAX_VAR_SIZ INT_MAX + +/* Liveness marks, used for registers and spilled-regs (in stack slots). + * Read marks propagate upwards until they find a write mark; they record that + * "one of this state's descendants read this reg" (and therefore the reg is + * relevant for states_equal() checks). + * Write marks collect downwards and do not propagate; they record that "the + * straight-line code that reached this state (from its parent) wrote this reg" + * (and therefore that reads propagated from this state or its descendants + * should not propagate to its parent). + * A state with a write mark can receive read marks; it just won't propagate + * them to its parent, since the write mark is a property, not of the state, + * but of the link between it and its parent. See mark_reg_read() and + * mark_stack_slot_read() in kernel/bpf/verifier.c. + */ +enum bpf_reg_liveness { + REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ + REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */ + REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */ +}; struct bpf_reg_state { enum bpf_reg_type type; union { - /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ - s64 imm; - - /* valid when type == PTR_TO_PACKET* */ - struct { - u16 off; - u16 range; - }; + /* valid when type == PTR_TO_PACKET */ + u16 range; /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; }; + /* Fixed part of pointer offset, pointer types only */ + s32 off; + /* For PTR_TO_PACKET, used to find other pointers with the same variable + * offset, so they can share range knowledge. + * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we + * came from, when one is tested for != NULL. + */ u32 id; + /* Ordering of fields matters. See states_equal() */ + /* For scalar types (SCALAR_VALUE), this represents our knowledge of + * the actual value. + * For pointer types, this represents the variable part of the offset + * from the pointed-to object, and is shared with all bpf_reg_states + * with the same id as us. + */ + struct tnum var_off; /* Used to determine if any memory access using this register will - * result in a bad access. These two fields must be last. - * See states_equal() + * result in a bad access. + * These refer to the same value as var_off, not necessarily the actual + * contents of the register. */ - s64 min_value; - u64 max_value; - u32 min_align; - u32 aux_off; - u32 aux_off_align; + s64 smin_value; /* minimum possible (s64)value */ + s64 smax_value; /* maximum possible (s64)value */ + u64 umin_value; /* minimum possible (u64)value */ + u64 umax_value; /* maximum possible (u64)value */ + /* This field must be last, for states_equal() reasons. */ + enum bpf_reg_liveness live; }; enum bpf_stack_slot_type { @@ -60,6 +95,7 @@ struct bpf_verifier_state { struct bpf_reg_state regs[MAX_BPF_REG]; u8 stack_slot_type[MAX_BPF_STACK]; struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; + struct bpf_verifier_state *parent; }; /* linked list of verifier states used to prune search */ @@ -73,6 +109,8 @@ struct bpf_insn_aux_data { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ }; + int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ + int converted_op_size; /* the valid value width after perceived conversion */ }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -100,7 +138,6 @@ struct bpf_verifier_env { u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; bool seen_direct_write; - bool varlen_map_value_access; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ }; diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index e34dde2da0ef..b1be0233ce35 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -24,6 +24,7 @@ #define _BLK_BSG_ #include <linux/blkdev.h> +#include <scsi/scsi_request.h> struct request; struct device; @@ -37,6 +38,7 @@ struct bsg_buffer { }; struct bsg_job { + struct scsi_request sreq; struct device *dev; struct request *req; @@ -66,8 +68,9 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); -struct request_queue *bsg_setup_queue(struct device *dev, char *name, - bsg_job_fn *job_fn, int dd_job_size); +struct request_queue *bsg_setup_queue(struct device *dev, const char *name, + bsg_job_fn *job_fn, int dd_job_size, + void (*release)(struct device *)); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bd029e52ef5e..c8dae555eccf 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -149,6 +149,7 @@ void buffer_check_dirty_writeback(struct page *page, */ void mark_buffer_dirty(struct buffer_head *bh); +void mark_buffer_write_io_error(struct buffer_head *bh); void init_buffer(struct buffer_head *, bh_end_io_t *, void *); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, @@ -201,6 +202,8 @@ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); +loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset, + loff_t length, int whence); extern int buffer_heads_over_limit; diff --git a/include/linux/bug.h b/include/linux/bug.h index 687b557fc5eb..5d5554c874fd 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -3,6 +3,7 @@ #include <asm/bug.h> #include <linux/compiler.h> +#include <linux/build_bug.h> enum bug_trap_type { BUG_TRAP_TYPE_NONE = 0, @@ -13,80 +14,9 @@ enum bug_trap_type { struct pt_regs; #ifdef __CHECKER__ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_ZERO(e) (0) -#define BUILD_BUG_ON_NULL(e) ((void*)0) -#define BUILD_BUG_ON_INVALID(e) (0) -#define BUILD_BUG_ON_MSG(cond, msg) (0) -#define BUILD_BUG_ON(condition) (0) -#define BUILD_BUG() (0) #define MAYBE_BUILD_BUG_ON(cond) (0) #else /* __CHECKER__ */ -/* Force a compilation error if a constant expression is not a power of 2 */ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON(((n) & ((n) - 1)) != 0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) - -/* Force a compilation error if condition is true, but also produce a - result (of value 0 and type size_t), so the expression can be used - e.g. in a structure initializer (or where-ever else comma expressions - aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) -#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) - -/* - * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the - * expression but avoids the generation of any code, even if that expression - * has side-effects. - */ -#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) - -/** - * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied - * error message. - * @condition: the condition which the compiler should know is false. - * - * See BUILD_BUG_ON for description. - */ -#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) - -/** - * BUILD_BUG_ON - break compile if a condition is true. - * @condition: the condition which the compiler should know is false. - * - * If you have some code which relies on certain constants being equal, or - * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to - * detect if someone changes it. - * - * The implementation uses gcc's reluctance to create a negative array, but gcc - * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to - * inline functions). Luckily, in 4.3 they added the "error" function - * attribute just for this type of case. Thus, we use a negative sized array - * (should always create an error on gcc versions older than 4.4) and then call - * an undefined function with the error attribute (should always create an - * error on gcc 4.3 and later). If for some reason, neither creates a - * compile-time error, we'll still have a link-time error, which is harder to - * track down. - */ -#ifndef __OPTIMIZE__ -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#else -#define BUILD_BUG_ON(condition) \ - BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) -#endif - -/** - * BUILD_BUG - break compile if used. - * - * If you have some code that you expect the compiler to eliminate at - * build time, you should use BUILD_BUG to detect if it is - * unexpectedly used. - */ -#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") - #define MAYBE_BUILD_BUG_ON(cond) \ do { \ if (__builtin_constant_p((cond))) \ diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h new file mode 100644 index 000000000000..b7d22d60008a --- /dev/null +++ b/include/linux/build_bug.h @@ -0,0 +1,84 @@ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#include <linux/compiler.h> + +#ifdef __CHECKER__ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_ZERO(e) (0) +#define BUILD_BUG_ON_NULL(e) ((void *)0) +#define BUILD_BUG_ON_INVALID(e) (0) +#define BUILD_BUG_ON_MSG(cond, msg) (0) +#define BUILD_BUG_ON(condition) (0) +#define BUILD_BUG() (0) +#else /* __CHECKER__ */ + +/* Force a compilation error if a constant expression is not a power of 2 */ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON(((n) & ((n) - 1)) != 0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) + +/* + * Force a compilation error if condition is true, but also produce a + * result (of value 0 and type size_t), so the expression can be used + * e.g. in a structure initializer (or where-ever else comma expressions + * aren't permitted). + */ +#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) +#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); })) + +/* + * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the + * expression but avoids the generation of any code, even if that expression + * has side-effects. + */ +#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) + +/** + * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied + * error message. + * @condition: the condition which the compiler should know is false. + * + * See BUILD_BUG_ON for description. + */ +#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) + +/** + * BUILD_BUG_ON - break compile if a condition is true. + * @condition: the condition which the compiler should know is false. + * + * If you have some code which relies on certain constants being equal, or + * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to + * detect if someone changes it. + * + * The implementation uses gcc's reluctance to create a negative array, but gcc + * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to + * inline functions). Luckily, in 4.3 they added the "error" function + * attribute just for this type of case. Thus, we use a negative sized array + * (should always create an error on gcc versions older than 4.4) and then call + * an undefined function with the error attribute (should always create an + * error on gcc 4.3 and later). If for some reason, neither creates a + * compile-time error, we'll still have a link-time error, which is harder to + * track down. + */ +#ifndef __OPTIMIZE__ +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) +#else +#define BUILD_BUG_ON(condition) \ + BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) +#endif + +/** + * BUILD_BUG - break compile if used. + * + * If you have some code that you expect the compiler to eliminate at + * build time, you should use BUILD_BUG to detect if it is + * unexpectedly used. + */ +#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") + +#endif /* __CHECKER__ */ + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 89b65b82d98f..ec8a4d7af6bd 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -22,6 +22,7 @@ #include <linux/kernel.h> #include <linux/bug.h> +#include <linux/errno.h> /* * was unsigned short, but we might as well be ready for > 64kB I/O pages @@ -39,6 +40,8 @@ struct bvec_iter { unsigned int bi_idx; /* current index into bvl_vec */ + unsigned int bi_done; /* number of bytes completed */ + unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; @@ -66,12 +69,14 @@ struct bvec_iter { .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) -static inline void bvec_iter_advance(const struct bio_vec *bv, - struct bvec_iter *iter, - unsigned bytes) +static inline bool bvec_iter_advance(const struct bio_vec *bv, + struct bvec_iter *iter, unsigned bytes) { - WARN_ONCE(bytes > iter->bi_size, - "Attempted to advance past end of bvec iter\n"); + if (WARN_ONCE(bytes > iter->bi_size, + "Attempted to advance past end of bvec iter\n")) { + iter->bi_size = 0; + return false; + } while (bytes) { unsigned iter_len = bvec_iter_len(bv, *iter); @@ -80,12 +85,38 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, bytes -= len; iter->bi_size -= len; iter->bi_bvec_done += len; + iter->bi_done += len; if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { iter->bi_bvec_done = 0; iter->bi_idx++; } } + return true; +} + +static inline bool bvec_iter_rewind(const struct bio_vec *bv, + struct bvec_iter *iter, + unsigned int bytes) +{ + while (bytes) { + unsigned len = min(bytes, iter->bi_bvec_done); + + if (iter->bi_bvec_done == 0) { + if (WARN_ONCE(iter->bi_idx == 0, + "Attempted to rewind iter beyond " + "bvec's boundaries\n")) { + return false; + } + iter->bi_idx--; + iter->bi_bvec_done = __bvec_iter_bvec(bv, *iter)->bv_len; + continue; + } + bytes -= len; + iter->bi_size += len; + iter->bi_bvec_done -= len; + } + return true; } #define for_each_bvec(bvl, bio_vec, iter, start) \ diff --git a/include/linux/byteorder/big_endian.h b/include/linux/byteorder/big_endian.h index 392041475c72..ffd215988392 100644 --- a/include/linux/byteorder/big_endian.h +++ b/include/linux/byteorder/big_endian.h @@ -3,5 +3,9 @@ #include <uapi/linux/byteorder/big_endian.h> +#ifndef CONFIG_CPU_BIG_ENDIAN +#warning inconsistent configuration, needs CONFIG_CPU_BIG_ENDIAN +#endif + #include <linux/byteorder/generic.h> #endif /* _LINUX_BYTEORDER_BIG_ENDIAN_H */ diff --git a/include/linux/byteorder/little_endian.h b/include/linux/byteorder/little_endian.h index 08057377aa23..ba910bb9aad0 100644 --- a/include/linux/byteorder/little_endian.h +++ b/include/linux/byteorder/little_endian.h @@ -3,5 +3,9 @@ #include <uapi/linux/byteorder/little_endian.h> +#ifdef CONFIG_CPU_BIG_ENDIAN +#warning inconsistent configuration, CONFIG_CPU_BIG_ENDIAN is set +#endif + #include <linux/byteorder/generic.h> #endif /* _LINUX_BYTEORDER_LITTLE_ENDIAN_H */ diff --git a/include/linux/capability.h b/include/linux/capability.h index 6ffb67e10c06..b52e278e4744 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -248,4 +248,6 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); +extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size); + #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/ccp.h b/include/linux/ccp.h index 3285c944194a..7e9c991c95e0 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -1,7 +1,7 @@ /* * AMD Cryptographic Coprocessor (CCP) driver * - * Copyright (C) 2013,2016 Advanced Micro Devices, Inc. + * Copyright (C) 2013,2017 Advanced Micro Devices, Inc. * * Author: Tom Lendacky <thomas.lendacky@amd.com> * Author: Gary R Hook <gary.hook@amd.com> @@ -20,12 +20,10 @@ #include <crypto/aes.h> #include <crypto/sha.h> - struct ccp_device; struct ccp_cmd; -#if defined(CONFIG_CRYPTO_DEV_CCP_DD) || \ - defined(CONFIG_CRYPTO_DEV_CCP_DD_MODULE) +#if defined(CONFIG_CRYPTO_DEV_SP_CCP) /** * ccp_present - check if a CCP device is present @@ -71,7 +69,7 @@ unsigned int ccp_version(void); */ int ccp_enqueue_cmd(struct ccp_cmd *cmd); -#else /* CONFIG_CRYPTO_DEV_CCP_DD is not enabled */ +#else /* CONFIG_CRYPTO_DEV_CCP_SP_DEV is not enabled */ static inline int ccp_present(void) { @@ -88,7 +86,7 @@ static inline int ccp_enqueue_cmd(struct ccp_cmd *cmd) return -ENODEV; } -#endif /* CONFIG_CRYPTO_DEV_CCP_DD */ +#endif /* CONFIG_CRYPTO_DEV_SP_CCP */ /***** AES engine *****/ @@ -231,6 +229,7 @@ enum ccp_xts_aes_unit_size { * AES operation the new IV overwrites the old IV. */ struct ccp_xts_aes_engine { + enum ccp_aes_type type; enum ccp_aes_action action; enum ccp_xts_aes_unit_size unit_size; diff --git a/include/linux/cdev.h b/include/linux/cdev.h index 408bc09ce497..cb28eb21e3ca 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -17,7 +17,7 @@ struct cdev { struct list_head list; dev_t dev; unsigned int count; -}; +} __randomize_layout; void cdev_init(struct cdev *, const struct file_operations *); diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index fd8b2953c78f..040dd105c3e7 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -2,103 +2,174 @@ #define __CEPH_FEATURES /* - * feature bits + * Each time we reclaim bits for reuse we need to specify another bit + * that, if present, indicates we have the new incarnation of that + * feature. Base case is 1 (first use). */ -#define CEPH_FEATURE_UID (1ULL<<0) -#define CEPH_FEATURE_NOSRCADDR (1ULL<<1) -#define CEPH_FEATURE_MONCLOCKCHECK (1ULL<<2) -#define CEPH_FEATURE_FLOCK (1ULL<<3) -#define CEPH_FEATURE_SUBSCRIBE2 (1ULL<<4) -#define CEPH_FEATURE_MONNAMES (1ULL<<5) -#define CEPH_FEATURE_RECONNECT_SEQ (1ULL<<6) -#define CEPH_FEATURE_DIRLAYOUTHASH (1ULL<<7) -#define CEPH_FEATURE_OBJECTLOCATOR (1ULL<<8) -#define CEPH_FEATURE_PGID64 (1ULL<<9) -#define CEPH_FEATURE_INCSUBOSDMAP (1ULL<<10) -#define CEPH_FEATURE_PGPOOL3 (1ULL<<11) -#define CEPH_FEATURE_OSDREPLYMUX (1ULL<<12) -#define CEPH_FEATURE_OSDENC (1ULL<<13) -#define CEPH_FEATURE_OMAP (1ULL<<14) -#define CEPH_FEATURE_MONENC (1ULL<<15) -#define CEPH_FEATURE_QUERY_T (1ULL<<16) -#define CEPH_FEATURE_INDEP_PG_MAP (1ULL<<17) -#define CEPH_FEATURE_CRUSH_TUNABLES (1ULL<<18) -#define CEPH_FEATURE_CHUNKY_SCRUB (1ULL<<19) -#define CEPH_FEATURE_MON_NULLROUTE (1ULL<<20) -#define CEPH_FEATURE_MON_GV (1ULL<<21) -#define CEPH_FEATURE_BACKFILL_RESERVATION (1ULL<<22) -#define CEPH_FEATURE_MSG_AUTH (1ULL<<23) -#define CEPH_FEATURE_RECOVERY_RESERVATION (1ULL<<24) -#define CEPH_FEATURE_CRUSH_TUNABLES2 (1ULL<<25) -#define CEPH_FEATURE_CREATEPOOLID (1ULL<<26) -#define CEPH_FEATURE_REPLY_CREATE_INODE (1ULL<<27) -#define CEPH_FEATURE_OSD_HBMSGS (1ULL<<28) -#define CEPH_FEATURE_MDSENC (1ULL<<29) -#define CEPH_FEATURE_OSDHASHPSPOOL (1ULL<<30) -#define CEPH_FEATURE_MON_SINGLE_PAXOS (1ULL<<31) -#define CEPH_FEATURE_OSD_SNAPMAPPER (1ULL<<32) -#define CEPH_FEATURE_MON_SCRUB (1ULL<<33) -#define CEPH_FEATURE_OSD_PACKED_RECOVERY (1ULL<<34) -#define CEPH_FEATURE_OSD_CACHEPOOL (1ULL<<35) -#define CEPH_FEATURE_CRUSH_V2 (1ULL<<36) /* new indep; SET_* steps */ -#define CEPH_FEATURE_EXPORT_PEER (1ULL<<37) -#define CEPH_FEATURE_OSD_ERASURE_CODES (1ULL<<38) -#define CEPH_FEATURE_OSD_TMAP2OMAP (1ULL<<38) /* overlap with EC */ -/* The process supports new-style OSDMap encoding. Monitors also use - this bit to determine if peers support NAK messages. */ -#define CEPH_FEATURE_OSDMAP_ENC (1ULL<<39) -#define CEPH_FEATURE_MDS_INLINE_DATA (1ULL<<40) -#define CEPH_FEATURE_CRUSH_TUNABLES3 (1ULL<<41) -#define CEPH_FEATURE_OSD_PRIMARY_AFFINITY (1ULL<<41) /* overlap w/ tunables3 */ -#define CEPH_FEATURE_MSGR_KEEPALIVE2 (1ULL<<42) -#define CEPH_FEATURE_OSD_POOLRESEND (1ULL<<43) -#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V2 (1ULL<<44) -#define CEPH_FEATURE_OSD_SET_ALLOC_HINT (1ULL<<45) -#define CEPH_FEATURE_OSD_FADVISE_FLAGS (1ULL<<46) -#define CEPH_FEATURE_OSD_REPOP (1ULL<<46) /* overlap with fadvise */ -#define CEPH_FEATURE_OSD_OBJECT_DIGEST (1ULL<<46) /* overlap with fadvise */ -#define CEPH_FEATURE_OSD_TRANSACTION_MAY_LAYOUT (1ULL<<46) /* overlap w/ fadvise */ -#define CEPH_FEATURE_MDS_QUOTA (1ULL<<47) -#define CEPH_FEATURE_CRUSH_V4 (1ULL<<48) /* straw2 buckets */ -#define CEPH_FEATURE_OSD_MIN_SIZE_RECOVERY (1ULL<<49) -// duplicated since it was introduced at the same time as MIN_SIZE_RECOVERY -#define CEPH_FEATURE_OSD_PROXY_FEATURES (1ULL<<49) /* overlap w/ above */ -#define CEPH_FEATURE_MON_METADATA (1ULL<<50) -#define CEPH_FEATURE_OSD_BITWISE_HOBJ_SORT (1ULL<<51) /* can sort objs bitwise */ -#define CEPH_FEATURE_OSD_PROXY_WRITE_FEATURES (1ULL<<52) -#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V3 (1ULL<<53) -#define CEPH_FEATURE_OSD_HITSET_GMT (1ULL<<54) -#define CEPH_FEATURE_HAMMER_0_94_4 (1ULL<<55) -#define CEPH_FEATURE_NEW_OSDOP_ENCODING (1ULL<<56) /* New, v7 encoding */ -#define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */ -#define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */ -#define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ -// duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 -#define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ -#define CEPH_FEATURE_FS_FILE_LAYOUT_V2 (1ULL<<58) /* file_layout_t */ +#define CEPH_FEATURE_INCARNATION_1 (0ull) +#define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL + +#define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ + static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t CEPH_FEATUREMASK_##name = \ + (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); + +/* this bit is ignored but still advertised by release *when* */ +#define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ + static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* - * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature - * vector to evaluate to 64 bit ~0. To cope, we designate 1ULL << 63 - * to mean 33 bit ~0, and introduce a helper below to do the - * translation. + * this bit is ignored by release *unused* and not advertised by + * release *unadvertised* + */ +#define DEFINE_CEPH_FEATURE_RETIRED(bit, inc, name, unused, unadvertised) + + +/* + * test for a feature. this test is safer than a typical mask against + * the bit because it ensures that we have the bit AND the marker for the + * bit's incarnation. this must be used in any case where the features + * bits may include an old meaning of the bit. + */ +#define CEPH_HAVE_FEATURE(x, name) \ + (((x) & (CEPH_FEATUREMASK_##name)) == (CEPH_FEATUREMASK_##name)) + + +/* + * Notes on deprecation: + * + * A *major* release is a release through which all upgrades must pass + * (e.g., jewel). For example, no pre-jewel server will ever talk to + * a post-jewel server (mon, osd, etc). + * + * For feature bits used *only* on the server-side: + * + * - In the first phase we indicate that a feature is DEPRECATED as of + * a particular release. This is the first major release X (say, + * jewel) that does not depend on its peers advertising the feature. + * That is, it safely assumes its peers all have the feature. We + * indicate this with the DEPRECATED macro. For example, + * + * DEFINE_CEPH_FEATURE_DEPRECATED( 2, 1, MONCLOCKCHECK, JEWEL) + * + * because 10.2.z (jewel) did not care if its peers advertised this + * feature bit. + * + * - In the second phase we stop advertising the the bit and call it + * RETIRED. This can normally be done in the *next* major release + * following the one in which we marked the feature DEPRECATED. In + * the above example, for 12.0.z (luminous) we can say: + * + * DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS) * - * This was introduced by ceph.git commit - * 9ea02b84104045c2ffd7e7f4e7af512953855ecd v0.58-657-g9ea02b8 - * and fixed by ceph.git commit - * 4255b5c2fb54ae40c53284b3ab700fdfc7e61748 v0.65-263-g4255b5c + * - The bit can be reused in the first post-luminous release, 13.0.z + * (m). + * + * This ensures that no two versions who have different meanings for + * the bit ever speak to each other. */ -#define CEPH_FEATURE_RESERVED (1ULL<<63) - -static inline u64 ceph_sanitize_features(u64 features) -{ - if (features & CEPH_FEATURE_RESERVED) { - /* everything through OSD_SNAPMAPPER */ - return 0x1ffffffffull; - } else { - return features; - } -} + +DEFINE_CEPH_FEATURE( 0, 1, UID) +DEFINE_CEPH_FEATURE( 1, 1, NOSRCADDR) +DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE( 3, 1, FLOCK) +DEFINE_CEPH_FEATURE( 4, 1, SUBSCRIBE2) +DEFINE_CEPH_FEATURE( 5, 1, MONNAMES) +DEFINE_CEPH_FEATURE( 6, 1, RECONNECT_SEQ) +DEFINE_CEPH_FEATURE( 7, 1, DIRLAYOUTHASH) +DEFINE_CEPH_FEATURE( 8, 1, OBJECTLOCATOR) +DEFINE_CEPH_FEATURE( 9, 1, PGID64) +DEFINE_CEPH_FEATURE(10, 1, INCSUBOSDMAP) +DEFINE_CEPH_FEATURE(11, 1, PGPOOL3) +DEFINE_CEPH_FEATURE(12, 1, OSDREPLYMUX) +DEFINE_CEPH_FEATURE(13, 1, OSDENC) +DEFINE_CEPH_FEATURE_RETIRED(14, 1, OMAP, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(14, 2, SERVER_KRAKEN) +DEFINE_CEPH_FEATURE(15, 1, MONENC) +DEFINE_CEPH_FEATURE_RETIRED(16, 1, QUERY_T, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(17, 1, INDEP_PG_MAP, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(18, 1, CRUSH_TUNABLES) +DEFINE_CEPH_FEATURE_RETIRED(19, 1, CHUNKY_SCRUB, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(20, 1, MON_NULLROUTE, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(21, 1, MON_GV, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(21, 2, SERVER_LUMINOUS) +DEFINE_CEPH_FEATURE(21, 2, RESEND_ON_SPLIT) // overlap +DEFINE_CEPH_FEATURE(21, 2, RADOS_BACKOFF) // overlap +DEFINE_CEPH_FEATURE(21, 2, OSDMAP_PG_UPMAP) // overlap +DEFINE_CEPH_FEATURE(21, 2, CRUSH_CHOOSE_ARGS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(22, 1, BACKFILL_RESERVATION, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(23, 1, MSG_AUTH) +DEFINE_CEPH_FEATURE_RETIRED(24, 1, RECOVERY_RESERVATION, JEWEL, LUNINOUS) + +DEFINE_CEPH_FEATURE(25, 1, CRUSH_TUNABLES2) +DEFINE_CEPH_FEATURE(26, 1, CREATEPOOLID) +DEFINE_CEPH_FEATURE(27, 1, REPLY_CREATE_INODE) +DEFINE_CEPH_FEATURE_RETIRED(28, 1, OSD_HBMSGS, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(28, 2, SERVER_M) +DEFINE_CEPH_FEATURE(29, 1, MDSENC) +DEFINE_CEPH_FEATURE(30, 1, OSDHASHPSPOOL) +DEFINE_CEPH_FEATURE(31, 1, MON_SINGLE_PAXOS) // deprecate me +DEFINE_CEPH_FEATURE_RETIRED(32, 1, OSD_SNAPMAPPER, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(33, 1, MON_SCRUB, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(34, 1, OSD_PACKED_RECOVERY, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(35, 1, OSD_CACHEPOOL) +DEFINE_CEPH_FEATURE(36, 1, CRUSH_V2) +DEFINE_CEPH_FEATURE(37, 1, EXPORT_PEER) +DEFINE_CEPH_FEATURE(38, 1, OSD_ERASURE_CODES) +DEFINE_CEPH_FEATURE(38, 1, OSD_OSD_TMAP2OMAP) // overlap +DEFINE_CEPH_FEATURE(39, 1, OSDMAP_ENC) +DEFINE_CEPH_FEATURE(40, 1, MDS_INLINE_DATA) +DEFINE_CEPH_FEATURE(41, 1, CRUSH_TUNABLES3) +DEFINE_CEPH_FEATURE(41, 1, OSD_PRIMARY_AFFINITY) // overlap +DEFINE_CEPH_FEATURE(42, 1, MSGR_KEEPALIVE2) +DEFINE_CEPH_FEATURE(43, 1, OSD_POOLRESEND) +DEFINE_CEPH_FEATURE(44, 1, ERASURE_CODE_PLUGINS_V2) +DEFINE_CEPH_FEATURE_RETIRED(45, 1, OSD_SET_ALLOC_HINT, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(46, 1, OSD_FADVISE_FLAGS) +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_REPOP, JEWEL, LUMINOUS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_OBJECT_DIGEST, JEWEL, LUMINOUS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_TRANSACTION_MAY_LAYOUT, JEWEL, LUMINOUS) // overlap + +DEFINE_CEPH_FEATURE(47, 1, MDS_QUOTA) +DEFINE_CEPH_FEATURE(48, 1, CRUSH_V4) +DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_MIN_SIZE_RECOVERY, JEWEL, LUMINOUS) +DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_PROXY_FEATURES, JEWEL, LUMINOUS) // overlap + +DEFINE_CEPH_FEATURE(50, 1, MON_METADATA) +DEFINE_CEPH_FEATURE(51, 1, OSD_BITWISE_HOBJ_SORT) +DEFINE_CEPH_FEATURE(52, 1, OSD_PROXY_WRITE_FEATURES) +DEFINE_CEPH_FEATURE(53, 1, ERASURE_CODE_PLUGINS_V3) +DEFINE_CEPH_FEATURE(54, 1, OSD_HITSET_GMT) +DEFINE_CEPH_FEATURE(55, 1, HAMMER_0_94_4) +DEFINE_CEPH_FEATURE(56, 1, NEW_OSDOP_ENCODING) +DEFINE_CEPH_FEATURE(57, 1, MON_STATEFUL_SUB) +DEFINE_CEPH_FEATURE(57, 1, MON_ROUTE_OSDMAP) // overlap +DEFINE_CEPH_FEATURE(57, 1, OSDSUBOP_NO_SNAPCONTEXT) // overlap +DEFINE_CEPH_FEATURE(57, 1, SERVER_JEWEL) // overlap +DEFINE_CEPH_FEATURE(58, 1, CRUSH_TUNABLES5) +DEFINE_CEPH_FEATURE(58, 1, NEW_OSDOPREPLY_ENCODING) // overlap +DEFINE_CEPH_FEATURE(58, 1, FS_FILE_LAYOUT_V2) // overlap +DEFINE_CEPH_FEATURE(59, 1, FS_BTIME) +DEFINE_CEPH_FEATURE(59, 1, FS_CHANGE_ATTR) // overlap +DEFINE_CEPH_FEATURE(59, 1, MSG_ADDR2) // overlap +DEFINE_CEPH_FEATURE(60, 1, BLKIN_TRACING) // *do not share this bit* + +DEFINE_CEPH_FEATURE(61, 1, RESERVED2) // unused, but slow down! +DEFINE_CEPH_FEATURE(62, 1, RESERVED) // do not use; used as a sentinal +DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facing + /* * Features supported. @@ -113,6 +184,11 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC | \ CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_SERVER_LUMINOUS | \ + CEPH_FEATURE_RESEND_ON_SPLIT | \ + CEPH_FEATURE_RADOS_BACKOFF | \ + CEPH_FEATURE_OSDMAP_PG_UPMAP | \ + CEPH_FEATURE_CRUSH_CHOOSE_ARGS | \ CEPH_FEATURE_MSG_AUTH | \ CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ @@ -126,7 +202,11 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ + CEPH_FEATURE_OSD_POOLRESEND | \ CEPH_FEATURE_CRUSH_V4 | \ + CEPH_FEATURE_NEW_OSDOP_ENCODING | \ + CEPH_FEATURE_SERVER_JEWEL | \ + CEPH_FEATURE_MON_STATEFUL_SUB | \ CEPH_FEATURE_CRUSH_TUNABLES5 | \ CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING) diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index ad078ebe25d6..b422170b791a 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -147,6 +147,7 @@ struct ceph_dir_layout { #define CEPH_MSG_OSD_OP 42 #define CEPH_MSG_OSD_OPREPLY 43 #define CEPH_MSG_WATCH_NOTIFY 44 +#define CEPH_MSG_OSD_BACKOFF 61 /* watch-notify operations */ @@ -166,6 +167,8 @@ struct ceph_mon_request_header { struct ceph_mon_statfs { struct ceph_mon_request_header monhdr; struct ceph_fsid fsid; + __u8 contains_data_pool; + __le64 data_pool; } __attribute__ ((packed)); struct ceph_statfs { @@ -668,7 +671,9 @@ enum { extern const char *ceph_cap_op_name(int op); /* flags field in client cap messages (version >= 10) */ -#define CEPH_CLIENT_CAPS_SYNC (0x1) +#define CEPH_CLIENT_CAPS_SYNC (1<<0) +#define CEPH_CLIENT_CAPS_NO_CAPSNAP (1<<1) +#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2); /* * caps message, used for capability callbacks, acks, requests, etc. diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index f990f2cc907a..14af9b70d301 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -133,6 +133,66 @@ bad: } /* + * skip helpers + */ +#define ceph_decode_skip_n(p, end, n, bad) \ + do { \ + ceph_decode_need(p, end, n, bad); \ + *p += n; \ + } while (0) + +#define ceph_decode_skip_64(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u64), bad) + +#define ceph_decode_skip_32(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u32), bad) + +#define ceph_decode_skip_16(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u16), bad) + +#define ceph_decode_skip_8(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u8), bad) + +#define ceph_decode_skip_string(p, end, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + ceph_decode_skip_n(p, end, len, bad); \ + } while (0) + +#define ceph_decode_skip_set(p, end, type, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) \ + ceph_decode_skip_##type(p, end, bad); \ + } while (0) + +#define ceph_decode_skip_map(p, end, ktype, vtype, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) { \ + ceph_decode_skip_##ktype(p, end, bad); \ + ceph_decode_skip_##vtype(p, end, bad); \ + } \ + } while (0) + +#define ceph_decode_skip_map_of_map(p, end, ktype1, ktype2, vtype2, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) { \ + ceph_decode_skip_##ktype1(p, end, bad); \ + ceph_decode_skip_map(p, end, ktype2, vtype2, bad); \ + } \ + } while (0) + +/* * struct ceph_timespec <-> struct timespec */ static inline void ceph_decode_timespec(struct timespec *ts, diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 3229ae6c7846..4c846aabd9f6 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -84,17 +84,6 @@ struct ceph_options { #define CEPH_AUTH_NAME_DEFAULT "guest" -/* - * Delay telling the MDS we no longer want caps, in case we reopen - * the file. Delay a minimum amount of time, even if we send a cap - * message for some other reason. Otherwise, take the oppotunity to - * update the mds to avoid sending another message later. - */ -#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ -#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ - -#define CEPH_CAP_RELEASE_SAFETY_DEFAULT (CEPH_CAPS_PER_RELEASE * 4) - /* mount state */ enum { CEPH_MOUNT_MOUNTING, @@ -184,10 +173,11 @@ static inline int calc_pages_for(u64 off, u64 len) (off >> PAGE_SHIFT); } -/* - * These are not meant to be generic - an integer key is assumed. - */ -#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ +#define RB_BYVAL(a) (a) +#define RB_BYPTR(a) (&(a)) +#define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b)) + +#define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ static void insert_##name(struct rb_root *root, type *t) \ { \ struct rb_node **n = &root->rb_node; \ @@ -197,11 +187,13 @@ static void insert_##name(struct rb_root *root, type *t) \ \ while (*n) { \ type *cur = rb_entry(*n, type, nodefld); \ + int cmp; \ \ parent = *n; \ - if (t->keyfld < cur->keyfld) \ + cmp = cmpexp(keyexp(t->keyfld), keyexp(cur->keyfld)); \ + if (cmp < 0) \ n = &(*n)->rb_left; \ - else if (t->keyfld > cur->keyfld) \ + else if (cmp > 0) \ n = &(*n)->rb_right; \ else \ BUG(); \ @@ -217,19 +209,24 @@ static void erase_##name(struct rb_root *root, type *t) \ RB_CLEAR_NODE(&t->nodefld); \ } -#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \ -extern type __lookup_##name##_key; \ -static type *lookup_##name(struct rb_root *root, \ - typeof(__lookup_##name##_key.keyfld) key) \ +/* + * @lookup_param_type is a parameter and not constructed from (@type, + * @keyfld) with typeof() because adding const is too unwieldy. + */ +#define DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) \ +static type *lookup_##name(struct rb_root *root, lookup_param_type key) \ { \ struct rb_node *n = root->rb_node; \ \ while (n) { \ type *cur = rb_entry(n, type, nodefld); \ + int cmp; \ \ - if (key < cur->keyfld) \ + cmp = cmpexp(key, keyexp(cur->keyfld)); \ + if (cmp < 0) \ n = n->rb_left; \ - else if (key > cur->keyfld) \ + else if (cmp > 0) \ n = n->rb_right; \ else \ return cur; \ @@ -238,6 +235,23 @@ static type *lookup_##name(struct rb_root *root, \ return NULL; \ } +#define DEFINE_RB_FUNCS2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) \ +DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ +DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) + +/* + * Shorthands for integer keys. + */ +#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ +DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL, nodefld) + +#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \ +extern type __lookup_##name##_key; \ +DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL, \ + typeof(__lookup_##name##_key.keyfld), nodefld) + #define DEFINE_RB_FUNCS(name, type, keyfld, nodefld) \ DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c5c4c713e00f..fbd94d9fa5dd 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -44,6 +44,8 @@ struct ceph_connection_operations { struct ceph_msg_header *hdr, int *skip); + void (*reencode_message) (struct ceph_msg *msg); + int (*sign_message) (struct ceph_msg *msg); int (*check_message_signature) (struct ceph_msg *msg); }; diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index d5a3ecea578d..0fa990bf867a 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -133,8 +133,8 @@ void ceph_monc_renew_subs(struct ceph_mon_client *monc); extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch, unsigned long timeout); -extern int ceph_monc_do_statfs(struct ceph_mon_client *monc, - struct ceph_statfs *buf); +int ceph_monc_do_statfs(struct ceph_mon_client *monc, u64 data_pool, + struct ceph_statfs *buf); int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what, u64 *newest); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 85650b415e73..adf670ecaf94 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -1,6 +1,7 @@ #ifndef _FS_CEPH_OSD_CLIENT_H #define _FS_CEPH_OSD_CLIENT_H +#include <linux/bitrev.h> #include <linux/completion.h> #include <linux/kref.h> #include <linux/mempool.h> @@ -36,6 +37,8 @@ struct ceph_osd { struct ceph_connection o_con; struct rb_root o_requests; struct rb_root o_linger_requests; + struct rb_root o_backoff_mappings; + struct rb_root o_backoffs_by_id; struct list_head o_osd_lru; struct ceph_auth_handshake o_auth; unsigned long lru_ttl; @@ -136,7 +139,8 @@ struct ceph_osd_request_target { struct ceph_object_id target_oid; struct ceph_object_locator target_oloc; - struct ceph_pg pgid; + struct ceph_pg pgid; /* last raw pg we mapped to */ + struct ceph_spg spgid; /* last actual spg we mapped to */ u32 pg_num; u32 pg_num_mask; struct ceph_osds acting; @@ -144,10 +148,14 @@ struct ceph_osd_request_target { int size; int min_size; bool sort_bitwise; + bool recovery_deletes; unsigned int flags; /* CEPH_OSD_FLAG_* */ bool paused; + u32 epoch; + u32 last_force_resend; + int osd; }; @@ -193,7 +201,6 @@ struct ceph_osd_request { unsigned long r_stamp; /* jiffies, send or check time */ unsigned long r_start_stamp; /* jiffies */ int r_attempts; - u32 r_last_force_resend; u32 r_map_dne_bound; struct ceph_osd_req_op r_ops[]; @@ -203,6 +210,23 @@ struct ceph_request_redirect { struct ceph_object_locator oloc; }; +/* + * osd request identifier + * + * caller name + incarnation# + tid to unique identify this request + */ +struct ceph_osd_reqid { + struct ceph_entity_name name; + __le64 tid; + __le32 inc; +} __packed; + +struct ceph_blkin_trace_info { + __le64 trace_id; + __le64 span_id; + __le64 parent_span_id; +} __packed; + typedef void (*rados_watchcb2_t)(void *arg, u64 notify_id, u64 cookie, u64 notifier_id, void *data, size_t data_len); typedef void (*rados_watcherrcb_t)(void *arg, u64 cookie, int err); @@ -221,7 +245,6 @@ struct ceph_osd_linger_request { struct list_head pending_lworks; struct ceph_osd_request_target t; - u32 last_force_resend; u32 map_dne_bound; struct timespec mtime; @@ -256,6 +279,48 @@ struct ceph_watch_item { struct ceph_entity_addr addr; }; +struct ceph_spg_mapping { + struct rb_node node; + struct ceph_spg spgid; + + struct rb_root backoffs; +}; + +struct ceph_hobject_id { + void *key; + size_t key_len; + void *oid; + size_t oid_len; + u64 snapid; + u32 hash; + u8 is_max; + void *nspace; + size_t nspace_len; + s64 pool; + + /* cache */ + u32 hash_reverse_bits; +}; + +static inline void ceph_hoid_build_hash_cache(struct ceph_hobject_id *hoid) +{ + hoid->hash_reverse_bits = bitrev32(hoid->hash); +} + +/* + * PG-wide backoff: [begin, end) + * per-object backoff: begin == end + */ +struct ceph_osd_backoff { + struct rb_node spg_node; + struct rb_node id_node; + + struct ceph_spg spgid; + u64 id; + struct ceph_hobject_id *begin; + struct ceph_hobject_id *end; +}; + #define CEPH_LINGER_ID_START 0xffff000000000000ULL struct ceph_osd_client { diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 938656f70807..af3444a5bfdd 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -24,7 +24,15 @@ struct ceph_pg { uint32_t seed; }; +#define CEPH_SPG_NOSHARD -1 + +struct ceph_spg { + struct ceph_pg pgid; + s8 shard; +}; + int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs); +int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs); #define CEPH_POOL_FLAG_HASHPSPOOL (1ULL << 0) /* hash pg seed and pool id together */ @@ -135,10 +143,14 @@ struct ceph_pg_mapping { struct { int len; int osds[]; - } pg_temp; + } pg_temp, pg_upmap; struct { int osd; } primary_temp; + struct { + int len; + int from_to[][2]; + } pg_upmap_items; }; }; @@ -150,13 +162,17 @@ struct ceph_osdmap { u32 flags; /* CEPH_OSDMAP_* */ u32 max_osd; /* size of osd_state, _offload, _addr arrays */ - u8 *osd_state; /* CEPH_OSD_* */ + u32 *osd_state; /* CEPH_OSD_* */ u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */ struct ceph_entity_addr *osd_addr; struct rb_root pg_temp; struct rb_root primary_temp; + /* remap (post-CRUSH, pre-up) */ + struct rb_root pg_upmap; /* PG := raw set */ + struct rb_root pg_upmap_items; /* from -> to within raw set */ + u32 *osd_primary_affinity; struct rb_root pg_pools; @@ -187,7 +203,7 @@ static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd) return !ceph_osd_is_up(map, osd); } -extern char *ceph_osdmap_state_str(char *str, int len, int state); +char *ceph_osdmap_state_str(char *str, int len, u32 state); extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd); static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, @@ -198,11 +214,13 @@ static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, return &map->osd_addr[osd]; } +#define CEPH_PGID_ENCODING_LEN (1 + 8 + 4 + 4) + static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid) { __u8 version; - if (!ceph_has_room(p, end, 1 + 8 + 4 + 4)) { + if (!ceph_has_room(p, end, CEPH_PGID_ENCODING_LEN)) { pr_warn("incomplete pg encoding\n"); return -EINVAL; } @@ -240,6 +258,8 @@ static inline void ceph_osds_init(struct ceph_osds *set) void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src); +bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num, + u32 new_pg_num); bool ceph_is_new_interval(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, const struct ceph_osds *old_up, @@ -252,6 +272,8 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting, u32 new_pg_num, bool old_sort_bitwise, bool new_sort_bitwise, + bool old_recovery_deletes, + bool new_recovery_deletes, const struct ceph_pg *pgid); bool ceph_osds_changed(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, @@ -262,15 +284,24 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 off, u64 len, u64 *bno, u64 *oxoff, u64 *oxlen); +int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid); int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, - struct ceph_object_id *oid, - struct ceph_object_locator *oloc, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, struct ceph_pg *raw_pgid); void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, const struct ceph_pg *raw_pgid, struct ceph_osds *up, struct ceph_osds *acting); +bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_spg *spgid); int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid); diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 5d0018782d50..01408841c9c4 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -158,6 +158,10 @@ extern const char *ceph_osd_state_name(int s); #define CEPH_OSDMAP_NOTIERAGENT (1<<13) /* disable tiering agent */ #define CEPH_OSDMAP_NOREBALANCE (1<<14) /* block osd backfill unless pg is degraded */ #define CEPH_OSDMAP_SORTBITWISE (1<<15) /* use bitwise hobject_t sort */ +#define CEPH_OSDMAP_REQUIRE_JEWEL (1<<16) /* require jewel for booting osds */ +#define CEPH_OSDMAP_REQUIRE_KRAKEN (1<<17) /* require kraken for booting osds */ +#define CEPH_OSDMAP_REQUIRE_LUMINOUS (1<<18) /* require l for booting osds */ +#define CEPH_OSDMAP_RECOVERY_DELETES (1<<19) /* deletes performed during recovery instead of peering */ /* * The error code to return when an OSD can't handle a write @@ -226,7 +230,6 @@ extern const char *ceph_osd_state_name(int s); \ /* fancy write */ \ f(APPEND, __CEPH_OSD_OP(WR, DATA, 6), "append") \ - f(STARTSYNC, __CEPH_OSD_OP(WR, DATA, 7), "startsync") \ f(SETTRUNC, __CEPH_OSD_OP(WR, DATA, 8), "settrunc") \ f(TRIMTRUNC, __CEPH_OSD_OP(WR, DATA, 9), "trimtrunc") \ \ @@ -439,6 +442,12 @@ enum { const char *ceph_osd_watch_op_name(int o); +enum { + CEPH_OSD_BACKOFF_OP_BLOCK = 1, + CEPH_OSD_BACKOFF_OP_ACK_BLOCK = 2, + CEPH_OSD_BACKOFF_OP_UNBLOCK = 3, +}; + /* * an individual object operation. each may be accompanied by some data * payload diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ec47101cb1bf..ade4a78a54c2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -67,12 +67,26 @@ enum { enum { CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ + + /* + * Consider namespaces as delegation boundaries. If this flag is + * set, controller specific interface files in a namespace root + * aren't writeable from inside the namespace. + */ + CGRP_ROOT_NS_DELEGATE = (1 << 3), + + /* + * Enable cpuset controller in v1 cgroup to use v2 behavior. + */ + CGRP_ROOT_CPUSET_V2_MODE = (1 << 4), }; /* cftype->flags */ enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ + CFTYPE_NS_DELEGATABLE = (1 << 2), /* writeable beyond delegation boundaries */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ @@ -163,9 +177,20 @@ struct css_set { /* reference count */ refcount_t refcount; + /* + * For a domain cgroup, the following points to self. If threaded, + * to the matching cset of the nearest domain ancestor. The + * dom_cset provides access to the domain cgroup and its csses to + * which domain level resource consumptions should be charged. + */ + struct css_set *dom_cset; + /* the default cgroup associated with this css_set */ struct cgroup *dfl_cgrp; + /* internal task count, protected by css_set_lock */ + int nr_tasks; + /* * Lists running through all tasks using this cgroup group. * mg_tasks lists tasks which belong to this cset but are in the @@ -188,6 +213,10 @@ struct css_set { */ struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; + /* all threaded csets whose ->dom_cset points to this cset */ + struct list_head threaded_csets; + struct list_head threaded_csets_node; + /* * List running through all cgroup groups in the same hash * slot. Protected by css_set_lock @@ -249,13 +278,35 @@ struct cgroup { */ int level; + /* Maximum allowed descent tree depth */ + int max_depth; + + /* + * Keep track of total numbers of visible and dying descent cgroups. + * Dying cgroups are cgroups which were deleted by a user, + * but are still existing because someone else is holding a reference. + * max_descendants is a maximum allowed number of descent cgroups. + */ + int nr_descendants; + int nr_dying_descendants; + int max_descendants; + /* * Each non-empty css_set associated with this cgroup contributes - * one to populated_cnt. All children with non-zero popuplated_cnt - * of their own contribute one. The count is zero iff there's no - * task in this cgroup or its subtree. + * one to nr_populated_csets. The counter is zero iff this cgroup + * doesn't have any tasks. + * + * All children which have non-zero nr_populated_csets and/or + * nr_populated_children of their own contribute one to either + * nr_populated_domain_children or nr_populated_threaded_children + * depending on their type. Each counter is zero iff all cgroups + * of the type in the subtree proper don't have any tasks. */ - int populated_cnt; + int nr_populated_csets; + int nr_populated_domain_children; + int nr_populated_threaded_children; + + int nr_threaded_children; /* # of live threaded child cgroups */ struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ @@ -294,6 +345,15 @@ struct cgroup { struct list_head e_csets[CGROUP_SUBSYS_COUNT]; /* + * If !threaded, self. If threaded, it points to the nearest + * domain ancestor. Inside a threaded subtree, cgroups are exempt + * from process granularity and no-internal-task constraint. + * Domain level resource consumptions which aren't tied to a + * specific task are charged to the dom_cgrp. + */ + struct cgroup *dom_cgrp; + + /* * list of pidlists, up to two for each namespace (one for procs, one * for tasks); created on demand. */ @@ -480,6 +540,18 @@ struct cgroup_subsys { bool implicit_on_dfl:1; /* + * If %true, the controller, supports threaded mode on the default + * hierarchy. In a threaded subtree, both process granularity and + * no-internal-process constraint are ignored and a threaded + * controllers should be able to handle that. + * + * Note that as an implicit controller is automatically enabled on + * all cgroups on the default hierarchy, it should also be + * threaded. implicit && !threaded is not supported. + */ + bool threaded:1; + + /* * If %false, this subsystem is properly hierarchical - * configuration, resource accounting and restriction on a parent * cgroup cover those of its children. If %true, hierarchy support diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 710a005c6b7a..d023ac5e377f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -36,18 +36,28 @@ #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 +/* walk only threadgroup leaders */ +#define CSS_TASK_ITER_PROCS (1U << 0) +/* walk all threaded css_sets in the domain */ +#define CSS_TASK_ITER_THREADED (1U << 1) + /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; + unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; + struct list_head *tcset_pos; + struct list_head *tcset_head; + struct list_head *task_pos; struct list_head *tasks_head; struct list_head *mg_tasks_head; struct css_set *cur_cset; + struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; @@ -129,7 +139,7 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); -void css_task_iter_start(struct cgroup_subsys_state *css, +void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); @@ -388,6 +398,16 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } +static inline void cgroup_get(struct cgroup *cgrp) +{ + css_get(&cgrp->self); +} + +static inline bool cgroup_tryget(struct cgroup *cgrp) +{ + return css_tryget(&cgrp->self); +} + static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); @@ -500,6 +520,20 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } +static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) +{ + return task_css_set(task)->dfl_cgrp; +} + +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + struct cgroup_subsys_state *parent_css = cgrp->self.parent; + + if (parent_css) + return container_of(parent_css, struct cgroup, self); + return NULL; +} + /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested @@ -537,13 +571,14 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { - return cgrp->populated_cnt; + return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { - return cgrp->kn->ino; + return cgrp->kn->id.ino; } /* cft/css accessors for cftype->write() operation */ @@ -609,6 +644,13 @@ static inline void cgroup_kthread_ready(void) current->no_cgroup_migration = 0; } +static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +{ + return &cgrp->kn->id; +} + +void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, + char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -631,12 +673,19 @@ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} +static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +{ + return NULL; +} static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { return true; } + +static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, + char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ /* diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index fccf7f44139d..bbb3712dd892 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -27,7 +27,7 @@ struct cleancache_filekey { struct cleancache_ops { int (*init_fs)(size_t); - int (*init_shared_fs)(char *uuid, size_t); + int (*init_shared_fs)(uuid_t *uuid, size_t); int (*get_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*put_page)(int, struct cleancache_filekey, diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index a428aec36ace..5100ec1b5d55 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -343,6 +343,7 @@ struct clk_hw *clk_hw_register_gate(struct device *dev, const char *name, u8 clk_gate_flags, spinlock_t *lock); void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); +int clk_gate_is_enabled(struct clk_hw *hw); struct clk_div_table { unsigned int val; @@ -412,9 +413,10 @@ extern const struct clk_ops clk_divider_ro_ops; unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate, unsigned int val, const struct clk_div_table *table, unsigned long flags); -long divider_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate, const struct clk_div_table *table, - u8 width, unsigned long flags); +long divider_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, + unsigned long rate, unsigned long *prate, + const struct clk_div_table *table, + u8 width, unsigned long flags); int divider_get_val(unsigned long rate, unsigned long parent_rate, const struct clk_div_table *table, u8 width, unsigned long flags); @@ -564,6 +566,9 @@ struct clk_fractional_divider { u8 nwidth; u32 nmask; u8 flags; + void (*approximation)(struct clk_hw *hw, + unsigned long rate, unsigned long *parent_rate, + unsigned long *m, unsigned long *n); spinlock_t *lock; }; @@ -757,6 +762,15 @@ static inline void __clk_hw_set_clk(struct clk_hw *dst, struct clk_hw *src) dst->core = src->core; } +static inline long divider_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate, + const struct clk_div_table *table, + u8 width, unsigned long flags) +{ + return divider_round_rate_parent(hw, clk_hw_get_parent(hw), + rate, prate, table, width, flags); +} + /* * FIXME clock api without lock protection */ diff --git a/include/linux/clk.h b/include/linux/clk.h index 024cd07870d0..12c96d94d1fa 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -77,6 +77,21 @@ struct clk_notifier_data { unsigned long new_rate; }; +/** + * struct clk_bulk_data - Data used for bulk clk operations. + * + * @id: clock consumer ID + * @clk: struct clk * to store the associated clock + * + * The CLK APIs provide a series of clk_bulk_() API calls as + * a convenience to consumers which require multiple clks. This + * structure is used to manage data for these calls. + */ +struct clk_bulk_data { + const char *id; + struct clk *clk; +}; + #ifdef CONFIG_COMMON_CLK /** @@ -185,12 +200,20 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) */ #ifdef CONFIG_HAVE_CLK_PREPARE int clk_prepare(struct clk *clk); +int __must_check clk_bulk_prepare(int num_clks, + const struct clk_bulk_data *clks); #else static inline int clk_prepare(struct clk *clk) { might_sleep(); return 0; } + +static inline int clk_bulk_prepare(int num_clks, struct clk_bulk_data *clks) +{ + might_sleep(); + return 0; +} #endif /** @@ -204,11 +227,16 @@ static inline int clk_prepare(struct clk *clk) */ #ifdef CONFIG_HAVE_CLK_PREPARE void clk_unprepare(struct clk *clk); +void clk_bulk_unprepare(int num_clks, const struct clk_bulk_data *clks); #else static inline void clk_unprepare(struct clk *clk) { might_sleep(); } +static inline void clk_bulk_unprepare(int num_clks, struct clk_bulk_data *clks) +{ + might_sleep(); +} #endif #ifdef CONFIG_HAVE_CLK @@ -230,6 +258,44 @@ static inline void clk_unprepare(struct clk *clk) struct clk *clk_get(struct device *dev, const char *id); /** + * clk_bulk_get - lookup and obtain a number of references to clock producer. + * @dev: device for clock "consumer" + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * This helper function allows drivers to get several clk consumers in one + * operation. If any of the clk cannot be acquired then any clks + * that were obtained will be freed before returning to the caller. + * + * Returns 0 if all clocks specified in clk_bulk_data table are obtained + * successfully, or valid IS_ERR() condition containing errno. + * The implementation uses @dev and @clk_bulk_data.id to determine the + * clock consumer, and thereby the clock producer. + * The clock returned is stored in each @clk_bulk_data.clk field. + * + * Drivers must assume that the clock source is not enabled. + * + * clk_bulk_get should not be called from within interrupt context. + */ +int __must_check clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks); + +/** + * devm_clk_bulk_get - managed get multiple clk consumers + * @dev: device for clock "consumer" + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Return 0 on success, an errno on failure. + * + * This helper function allows drivers to get several clk + * consumers in one operation with management, the clks will + * automatically be freed when the device is unbound. + */ +int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks); + +/** * devm_clk_get - lookup and obtain a managed reference to a clock producer. * @dev: device for clock "consumer" * @id: clock consumer ID @@ -279,6 +345,18 @@ struct clk *devm_get_clk_from_child(struct device *dev, int clk_enable(struct clk *clk); /** + * clk_bulk_enable - inform the system when the set of clks should be running. + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * May be called from atomic contexts. + * + * Returns success (0) or negative errno. + */ +int __must_check clk_bulk_enable(int num_clks, + const struct clk_bulk_data *clks); + +/** * clk_disable - inform the system when the clock source is no longer required. * @clk: clock source * @@ -295,6 +373,24 @@ int clk_enable(struct clk *clk); void clk_disable(struct clk *clk); /** + * clk_bulk_disable - inform the system when the set of clks is no + * longer required. + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Inform the system that a set of clks is no longer required by + * a driver and may be shut down. + * + * May be called from atomic contexts. + * + * Implementation detail: if the set of clks is shared between + * multiple drivers, clk_bulk_enable() calls must be balanced by the + * same number of clk_bulk_disable() calls for the clock source to be + * disabled. + */ +void clk_bulk_disable(int num_clks, const struct clk_bulk_data *clks); + +/** * clk_get_rate - obtain the current clock rate (in Hz) for a clock source. * This is only valid once the clock source has been enabled. * @clk: clock source @@ -314,6 +410,19 @@ unsigned long clk_get_rate(struct clk *clk); void clk_put(struct clk *clk); /** + * clk_bulk_put - "free" the clock source + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Note: drivers must ensure that all clk_bulk_enable calls made on this + * clock source are balanced by clk_bulk_disable calls prior to calling + * this function. + * + * clk_bulk_put should not be called from within interrupt context. + */ +void clk_bulk_put(int num_clks, struct clk_bulk_data *clks); + +/** * devm_clk_put - "free" a managed clock source * @dev: device used to acquire the clock * @clk: clock source acquired with devm_clk_get() @@ -445,11 +554,23 @@ static inline struct clk *clk_get(struct device *dev, const char *id) return NULL; } +static inline int clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks) +{ + return 0; +} + static inline struct clk *devm_clk_get(struct device *dev, const char *id) { return NULL; } +static inline int devm_clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks) +{ + return 0; +} + static inline struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { @@ -458,6 +579,8 @@ static inline struct clk *devm_get_clk_from_child(struct device *dev, static inline void clk_put(struct clk *clk) {} +static inline void clk_bulk_put(int num_clks, struct clk_bulk_data *clks) {} + static inline void devm_clk_put(struct device *dev, struct clk *clk) {} static inline int clk_enable(struct clk *clk) @@ -465,8 +588,17 @@ static inline int clk_enable(struct clk *clk) return 0; } +static inline int clk_bulk_enable(int num_clks, struct clk_bulk_data *clks) +{ + return 0; +} + static inline void clk_disable(struct clk *clk) {} + +static inline void clk_bulk_disable(int num_clks, + struct clk_bulk_data *clks) {} + static inline unsigned long clk_get_rate(struct clk *clk) { return 0; @@ -525,6 +657,28 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } +static inline int clk_bulk_prepare_enable(int num_clks, + struct clk_bulk_data *clks) +{ + int ret; + + ret = clk_bulk_prepare(num_clks, clks); + if (ret) + return ret; + ret = clk_bulk_enable(num_clks, clks); + if (ret) + clk_bulk_unprepare(num_clks, clks); + + return ret; +} + +static inline void clk_bulk_disable_unprepare(int num_clks, + struct clk_bulk_data *clks) +{ + clk_bulk_disable(num_clks, clks); + clk_bulk_unprepare(num_clks, clks); +} + #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) struct clk *of_clk_get(struct device_node *np, int index); struct clk *of_clk_get_by_name(struct device_node *np, const char *name); @@ -539,6 +693,10 @@ static inline struct clk *of_clk_get_by_name(struct device_node *np, { return ERR_PTR(-ENOENT); } +static inline struct clk *of_clk_get_from_provider(struct of_phandle_args *clkspec) +{ + return ERR_PTR(-ENOENT); +} #endif #endif diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 17f413bbbedf..6aca5ce8a99a 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -185,4 +185,29 @@ #define AT91_PMC_PCR_EN (0x1 << 28) /* Enable */ #define AT91_PMC_PCR_GCKEN (0x1 << 29) /* GCK Enable */ +#define AT91_PMC_AUDIO_PLL0 0x14c +#define AT91_PMC_AUDIO_PLL_PLLEN (1 << 0) +#define AT91_PMC_AUDIO_PLL_PADEN (1 << 1) +#define AT91_PMC_AUDIO_PLL_PMCEN (1 << 2) +#define AT91_PMC_AUDIO_PLL_RESETN (1 << 3) +#define AT91_PMC_AUDIO_PLL_ND_OFFSET 8 +#define AT91_PMC_AUDIO_PLL_ND_MASK (0x7f << AT91_PMC_AUDIO_PLL_ND_OFFSET) +#define AT91_PMC_AUDIO_PLL_ND(n) ((n) << AT91_PMC_AUDIO_PLL_ND_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPMC_OFFSET 16 +#define AT91_PMC_AUDIO_PLL_QDPMC_MASK (0x7f << AT91_PMC_AUDIO_PLL_QDPMC_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPMC(n) ((n) << AT91_PMC_AUDIO_PLL_QDPMC_OFFSET) + +#define AT91_PMC_AUDIO_PLL1 0x150 +#define AT91_PMC_AUDIO_PLL_FRACR_MASK 0x3fffff +#define AT91_PMC_AUDIO_PLL_QDPAD_OFFSET 24 +#define AT91_PMC_AUDIO_PLL_QDPAD_MASK (0x7f << AT91_PMC_AUDIO_PLL_QDPAD_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD(n) ((n) << AT91_PMC_AUDIO_PLL_QDPAD_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_DIV_OFFSET AT91_PMC_AUDIO_PLL_QDPAD_OFFSET +#define AT91_PMC_AUDIO_PLL_QDPAD_DIV_MASK (0x3 << AT91_PMC_AUDIO_PLL_QDPAD_DIV_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_DIV(n) ((n) << AT91_PMC_AUDIO_PLL_QDPAD_DIV_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_OFFSET 26 +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_MAX 0x1f +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_MASK (AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_MAX << AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV(n) ((n) << AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_OFFSET) + #endif diff --git a/include/linux/clk/sunxi-ng.h b/include/linux/clk/sunxi-ng.h new file mode 100644 index 000000000000..990f760f70e5 --- /dev/null +++ b/include/linux/clk/sunxi-ng.h @@ -0,0 +1,35 @@ +/* + * Copyright (c) 2017 Chen-Yu Tsai. All rights reserved. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_CLK_SUNXI_NG_H_ +#define _LINUX_CLK_SUNXI_NG_H_ + +#include <linux/errno.h> + +#ifdef CONFIG_SUNXI_CCU +int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode); +int sunxi_ccu_get_mmc_timing_mode(struct clk *clk); +#else +static inline int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, + bool new_mode) +{ + return -ENOTSUPP; +} + +static inline int sunxi_ccu_get_mmc_timing_mode(struct clk *clk) +{ + return -ENOTSUPP; +} +#endif + +#endif diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index acc9ce05e5f0..a116926598fd 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -223,13 +223,4 @@ static inline void tick_setup_hrtimer_broadcast(void) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -#define CLOCKEVENT_OF_DECLARE(name, compat, fn) \ - OF_DECLARE_1_RET(clkevt, name, compat, fn) - -#ifdef CONFIG_CLKEVT_PROBE -extern int clockevent_probe(void); -#else -static inline int clockevent_probe(void) { return 0; } -#endif - #endif /* _LINUX_CLOCKCHIPS_H */ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index f2b10d9ebd04..a78cb1848e65 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -96,6 +96,7 @@ struct clocksource { void (*suspend)(struct clocksource *cs); void (*resume)(struct clocksource *cs); void (*mark_unstable)(struct clocksource *cs); + void (*tick_stable)(struct clocksource *cs); /* private: */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG @@ -249,16 +250,19 @@ extern int clocksource_mmio_init(void __iomem *, const char *, extern int clocksource_i8253_init(void); +#define TIMER_OF_DECLARE(name, compat, fn) \ + OF_DECLARE_1_RET(timer, name, compat, fn) + #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ - OF_DECLARE_1_RET(clksrc, name, compat, fn) + TIMER_OF_DECLARE(name, compat, fn) -#ifdef CONFIG_CLKSRC_PROBE -extern void clocksource_probe(void); +#ifdef CONFIG_TIMER_PROBE +extern void timer_probe(void); #else -static inline void clocksource_probe(void) {} +static inline void timer_probe(void) {} #endif -#define CLOCKSOURCE_ACPI_DECLARE(name, table_id, fn) \ - ACPI_DECLARE_PROBE_ENTRY(clksrc, name, table_id, 0, NULL, 0, fn) +#define TIMER_ACPI_DECLARE(name, table_id, fn) \ + ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn) #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c5f3152cbb5..a5619de3437d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -27,7 +27,7 @@ #endif #ifndef __SC_DELOUSE -#define __SC_DELOUSE(t,v) ((t)(unsigned long)(v)) +#define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif #define COMPAT_SYSCALL_DEFINE0(name) \ @@ -94,6 +94,10 @@ struct compat_itimerval { struct compat_timeval it_value; }; +struct itimerval; +int get_compat_itimerval(struct itimerval *, const struct compat_itimerval __user *); +int put_compat_itimerval(struct compat_itimerval __user *, const struct itimerval *); + struct compat_tms { compat_clock_t tms_utime; compat_clock_t tms_stime; @@ -128,6 +132,10 @@ struct compat_timex { compat_int_t:32; compat_int_t:32; compat_int_t:32; }; +struct timex; +int compat_get_timex(struct timex *, const struct compat_timex __user *); +int compat_put_timex(struct compat_timex __user *, const struct timex *); + #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) typedef struct { @@ -156,15 +164,12 @@ extern int compat_get_timespec(struct timespec *, const void __user *); extern int compat_put_timespec(const struct timespec *, void __user *); extern int compat_get_timeval(struct timeval *, const void __user *); extern int compat_put_timeval(const struct timeval *, void __user *); - -/* - * This function convert a timespec if necessary and returns a *user - * space* pointer. If no conversion is necessary, it returns the - * initial pointer. NULL is a legitimate argument and will always - * output NULL. - */ -extern int compat_convert_timespec(struct timespec __user **, - const void __user *); +extern int compat_get_timespec64(struct timespec64 *, const void __user *); +extern int compat_put_timespec64(const struct timespec64 *, void __user *); +extern int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits); +extern int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits); struct compat_iovec { compat_uptr_t iov_base; @@ -351,10 +356,10 @@ asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, @@ -368,6 +373,18 @@ asmlinkage long compat_sys_pwritev64(unsigned long fd, unsigned long vlen, loff_t pos); #endif +#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 +asmlinkage long compat_sys_readv64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 +asmlinkage long compat_sys_pwritev64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, @@ -388,8 +405,7 @@ asmlinkage long compat_sys_wait4(compat_pid_t pid, #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) -#define BITS_TO_COMPAT_LONGS(bits) \ - (((bits)+BITS_PER_COMPAT_LONG-1)/BITS_PER_COMPAT_LONG) +#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d614c5ea1b5e..de179993e039 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -15,11 +15,3 @@ * with any version that can compile the kernel */ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) - -/* - * GCC does not warn about unused static inline functions for - * -Wunused-function. This turns out to avoid the need for complex #ifdef - * directives. Suppress the warning in clang as well. - */ -#undef inline -#define inline inline __attribute__((unused)) notrace diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 0efef9cf014f..16d41de92ee3 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,18 +66,22 @@ /* * Force always-inline if the user requests it so via the .config, - * or if gcc is too old: + * or if gcc is too old. + * GCC does not warn about unused static inline functions for + * -Wunused-function. This turns out to avoid the need for complex #ifdef + * directives. Suppress the warning in clang as well by using "unused" + * function attribute, which is redundant but not harmful for gcc. */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -#define inline inline __attribute__((always_inline)) notrace -#define __inline__ __inline__ __attribute__((always_inline)) notrace -#define __inline __inline __attribute__((always_inline)) notrace +#define inline inline __attribute__((always_inline,unused)) notrace +#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace +#define __inline __inline __attribute__((always_inline,unused)) notrace #else /* A lot of inline functions can cause havoc with function tracing */ -#define inline inline notrace -#define __inline__ __inline__ notrace -#define __inline __inline notrace +#define inline inline __attribute__((unused)) notrace +#define __inline__ __inline__ __attribute__((unused)) notrace +#define __inline __inline __attribute__((unused)) notrace #endif #define __always_inline inline __attribute__((always_inline)) @@ -162,6 +166,8 @@ #if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) + +#define __nostackprotector __attribute__((__optimize__("no-stack-protector"))) #endif #if GCC_VERSION >= 40300 @@ -197,17 +203,6 @@ #endif #endif -#ifdef CONFIG_STACK_VALIDATION -#define annotate_unreachable() ({ \ - asm("%c0:\t\n" \ - ".pushsection .discard.unreachable\t\n" \ - ".long %c0b - .\t\n" \ - ".popsection\t\n" : : "i" (__LINE__)); \ -}) -#else -#define annotate_unreachable() -#endif - /* * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer @@ -223,9 +218,15 @@ /* Mark a function definition as prohibited from being cloned. */ #define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) +#ifdef RANDSTRUCT_PLUGIN +#define __randomize_layout __attribute__((randomize_layout)) +#define __no_randomize_layout __attribute__((no_randomize_layout)) +#endif + #endif /* GCC_VERSION >= 40500 */ #if GCC_VERSION >= 40600 + /* * When used with Link Time Optimization, gcc can optimize away C functions or * variables which are referenced only from assembly code. __visible tells the @@ -233,7 +234,17 @@ * this. */ #define __visible __attribute__((externally_visible)) -#endif + +/* + * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only + * possible since GCC 4.6. To provide as much build testing coverage + * as possible, this is used for all GCC 4.6+ builds, and not just on + * RANDSTRUCT_PLUGIN builds. + */ +#define randomized_struct_fields_start struct { +#define randomized_struct_fields_end } __randomize_layout; + +#endif /* GCC_VERSION >= 40600 */ #if GCC_VERSION >= 40900 && !defined(__CHECKER__) @@ -294,6 +305,14 @@ #define __no_sanitize_address __attribute__((no_sanitize_address)) #endif +#if GCC_VERSION >= 50100 +/* + * Mark structures as requiring designated initializers. + * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html + */ +#define __designated_init __attribute__((designated_init)) +#endif + #endif /* gcc version >= 40000 specific checks */ #if !defined(__noclone) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index f8110051188f..e95a2631e545 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -17,11 +17,7 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) -#ifdef CONFIG_SPARSE_RCU_POINTER # define __rcu __attribute__((noderef, address_space(4))) -#else /* CONFIG_SPARSE_RCU_POINTER */ -# define __rcu -#endif /* CONFIG_SPARSE_RCU_POINTER */ # define __private __attribute__((noderef)) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); @@ -189,8 +185,34 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ +#ifdef CONFIG_STACK_VALIDATION +#define annotate_reachable() ({ \ + asm("%c0:\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__LINE__)); \ +}) +#define annotate_unreachable() ({ \ + asm("%c0:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__LINE__)); \ +}) +#define ASM_UNREACHABLE \ + "999:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" +#else +#define annotate_reachable() +#define annotate_unreachable() +#endif + +#ifndef ASM_UNREACHABLE +# define ASM_UNREACHABLE +#endif #ifndef unreachable -# define unreachable() do { } while (1) +# define unreachable() do { annotate_reachable(); do { } while (1); } while (0) #endif /* @@ -440,10 +462,27 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __attribute_const__ /* unimplemented */ #endif +#ifndef __designated_init +# define __designated_init +#endif + #ifndef __latent_entropy # define __latent_entropy #endif +#ifndef __randomize_layout +# define __randomize_layout __designated_init +#endif + +#ifndef __no_randomize_layout +# define __no_randomize_layout +#endif + +#ifndef randomized_struct_fields_start +# define randomized_struct_fields_start +# define randomized_struct_fields_end +#endif + /* * Tell gcc if a function is cold. The compiler will assume any path * directly leading to the call is unlikely. @@ -462,6 +501,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define __visible #endif +#ifndef __nostackprotector +# define __nostackprotector +#endif + /* * Assume alignment of return value. */ @@ -504,7 +547,8 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __compiletime_error_fallback(condition) do { } while (0) #endif -#define __compiletime_assert(condition, msg, prefix, suffix) \ +#ifdef __OPTIMIZE__ +# define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ bool __cond = !(condition); \ extern void prefix ## suffix(void) __compiletime_error(msg); \ @@ -512,6 +556,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s prefix ## suffix(); \ __compiletime_error_fallback(__cond); \ } while (0) +#else +# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) +#endif #define _compiletime_assert(condition, msg, prefix, suffix) \ __compiletime_assert(condition, msg, prefix, suffix) diff --git a/include/linux/completion.h b/include/linux/completion.h index 5d5aaae3af43..cae5400022a3 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -9,6 +9,9 @@ */ #include <linux/wait.h> +#ifdef CONFIG_LOCKDEP_COMPLETIONS +#include <linux/lockdep.h> +#endif /* * struct completion - structure used to maintain state for a "completion" @@ -25,13 +28,53 @@ struct completion { unsigned int done; wait_queue_head_t wait; +#ifdef CONFIG_LOCKDEP_COMPLETIONS + struct lockdep_map_cross map; +#endif }; +#ifdef CONFIG_LOCKDEP_COMPLETIONS +static inline void complete_acquire(struct completion *x) +{ + lock_acquire_exclusive((struct lockdep_map *)&x->map, 0, 0, NULL, _RET_IP_); +} + +static inline void complete_release(struct completion *x) +{ + lock_release((struct lockdep_map *)&x->map, 0, _RET_IP_); +} + +static inline void complete_release_commit(struct completion *x) +{ + lock_commit_crosslock((struct lockdep_map *)&x->map); +} + +#define init_completion(x) \ +do { \ + static struct lock_class_key __key; \ + lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map, \ + "(complete)" #x, \ + &__key, 0); \ + __init_completion(x); \ +} while (0) +#else +#define init_completion(x) __init_completion(x) +static inline void complete_acquire(struct completion *x) {} +static inline void complete_release(struct completion *x) {} +static inline void complete_release_commit(struct completion *x) {} +#endif + +#ifdef CONFIG_LOCKDEP_COMPLETIONS +#define COMPLETION_INITIALIZER(work) \ + { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \ + STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) } +#else #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } +#endif #define COMPLETION_INITIALIZER_ONSTACK(work) \ - ({ init_completion(&work); work; }) + (*({ init_completion(&work); &work; })) /** * DECLARE_COMPLETION - declare and initialize a completion structure @@ -70,7 +113,7 @@ struct completion { * This inline function will initialize a dynamically created completion * structure. */ -static inline void init_completion(struct completion *x) +static inline void __init_completion(struct completion *x) { x->done = 0; init_waitqueue_head(&x->wait); diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 7d410260661b..edfeaba95429 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -24,6 +24,12 @@ /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_TS 28 +#define ETM_OPT_RETSTK 29 + +/* ETMv4 CONFIGR programming bits for the ETM OPTs */ +#define ETM4_CFG_BIT_CYCACC 4 +#define ETM4_CFG_BIT_TS 11 +#define ETM4_CFG_BIT_RETSTK 12 static inline int coresight_get_trace_id(int cpu) { diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 035c16c9a505..d950dad5056a 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -263,11 +263,15 @@ static inline int coresight_timeout(void __iomem *addr, u32 offset, #endif #ifdef CONFIG_OF -extern struct coresight_platform_data *of_get_coresight_platform_data( - struct device *dev, struct device_node *node); +extern int of_coresight_get_cpu(const struct device_node *node); +extern struct coresight_platform_data * +of_get_coresight_platform_data(struct device *dev, + const struct device_node *node); #else +static inline int of_coresight_get_cpu(const struct device_node *node) +{ return 0; } static inline struct coresight_platform_data *of_get_coresight_platform_data( - struct device *dev, struct device_node *node) { return NULL; } + struct device *dev, const struct device_node *node) { return NULL; } #endif #ifdef CONFIG_PID_NS diff --git a/include/linux/cper.h b/include/linux/cper.h index dcacb1a72e26..723e952fde0d 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -74,36 +74,36 @@ enum { * Corrected Machine Check */ #define CPER_NOTIFY_CMC \ - UUID_LE(0x2DCE8BB1, 0xBDD7, 0x450e, 0xB9, 0xAD, 0x9C, 0xF4, \ - 0xEB, 0xD4, 0xF8, 0x90) + GUID_INIT(0x2DCE8BB1, 0xBDD7, 0x450e, 0xB9, 0xAD, 0x9C, 0xF4, \ + 0xEB, 0xD4, 0xF8, 0x90) /* Corrected Platform Error */ #define CPER_NOTIFY_CPE \ - UUID_LE(0x4E292F96, 0xD843, 0x4a55, 0xA8, 0xC2, 0xD4, 0x81, \ - 0xF2, 0x7E, 0xBE, 0xEE) + GUID_INIT(0x4E292F96, 0xD843, 0x4a55, 0xA8, 0xC2, 0xD4, 0x81, \ + 0xF2, 0x7E, 0xBE, 0xEE) /* Machine Check Exception */ #define CPER_NOTIFY_MCE \ - UUID_LE(0xE8F56FFE, 0x919C, 0x4cc5, 0xBA, 0x88, 0x65, 0xAB, \ - 0xE1, 0x49, 0x13, 0xBB) + GUID_INIT(0xE8F56FFE, 0x919C, 0x4cc5, 0xBA, 0x88, 0x65, 0xAB, \ + 0xE1, 0x49, 0x13, 0xBB) /* PCI Express Error */ #define CPER_NOTIFY_PCIE \ - UUID_LE(0xCF93C01F, 0x1A16, 0x4dfc, 0xB8, 0xBC, 0x9C, 0x4D, \ - 0xAF, 0x67, 0xC1, 0x04) + GUID_INIT(0xCF93C01F, 0x1A16, 0x4dfc, 0xB8, 0xBC, 0x9C, 0x4D, \ + 0xAF, 0x67, 0xC1, 0x04) /* INIT Record (for IPF) */ #define CPER_NOTIFY_INIT \ - UUID_LE(0xCC5263E8, 0x9308, 0x454a, 0x89, 0xD0, 0x34, 0x0B, \ - 0xD3, 0x9B, 0xC9, 0x8E) + GUID_INIT(0xCC5263E8, 0x9308, 0x454a, 0x89, 0xD0, 0x34, 0x0B, \ + 0xD3, 0x9B, 0xC9, 0x8E) /* Non-Maskable Interrupt */ #define CPER_NOTIFY_NMI \ - UUID_LE(0x5BAD89FF, 0xB7E6, 0x42c9, 0x81, 0x4A, 0xCF, 0x24, \ - 0x85, 0xD6, 0xE9, 0x8A) + GUID_INIT(0x5BAD89FF, 0xB7E6, 0x42c9, 0x81, 0x4A, 0xCF, 0x24, \ + 0x85, 0xD6, 0xE9, 0x8A) /* BOOT Error Record */ #define CPER_NOTIFY_BOOT \ - UUID_LE(0x3D61A466, 0xAB40, 0x409a, 0xA6, 0x98, 0xF3, 0x62, \ - 0xD4, 0x64, 0xB3, 0x8F) + GUID_INIT(0x3D61A466, 0xAB40, 0x409a, 0xA6, 0x98, 0xF3, 0x62, \ + 0xD4, 0x64, 0xB3, 0x8F) /* DMA Remapping Error */ #define CPER_NOTIFY_DMAR \ - UUID_LE(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ - 0x72, 0x2D, 0xEB, 0x41) + GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ + 0x72, 0x2D, 0xEB, 0x41) /* * Flags bits definitions for flags in struct cper_record_header @@ -170,46 +170,50 @@ enum { * Processor Generic */ #define CPER_SEC_PROC_GENERIC \ - UUID_LE(0x9876CCAD, 0x47B4, 0x4bdb, 0xB6, 0x5E, 0x16, 0xF1, \ - 0x93, 0xC4, 0xF3, 0xDB) + GUID_INIT(0x9876CCAD, 0x47B4, 0x4bdb, 0xB6, 0x5E, 0x16, 0xF1, \ + 0x93, 0xC4, 0xF3, 0xDB) /* Processor Specific: X86/X86_64 */ #define CPER_SEC_PROC_IA \ - UUID_LE(0xDC3EA0B0, 0xA144, 0x4797, 0xB9, 0x5B, 0x53, 0xFA, \ - 0x24, 0x2B, 0x6E, 0x1D) + GUID_INIT(0xDC3EA0B0, 0xA144, 0x4797, 0xB9, 0x5B, 0x53, 0xFA, \ + 0x24, 0x2B, 0x6E, 0x1D) /* Processor Specific: IA64 */ #define CPER_SEC_PROC_IPF \ - UUID_LE(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \ - 0x80, 0xC7, 0x3C, 0x88, 0x81) + GUID_INIT(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \ + 0x80, 0xC7, 0x3C, 0x88, 0x81) +/* Processor Specific: ARM */ +#define CPER_SEC_PROC_ARM \ + GUID_INIT(0xE19E3D16, 0xBC11, 0x11E4, 0x9C, 0xAA, 0xC2, 0x05, \ + 0x1D, 0x5D, 0x46, 0xB0) /* Platform Memory */ #define CPER_SEC_PLATFORM_MEM \ - UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ - 0xED, 0x7C, 0x83, 0xB1) + GUID_INIT(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ + 0xED, 0x7C, 0x83, 0xB1) #define CPER_SEC_PCIE \ - UUID_LE(0xD995E954, 0xBBC1, 0x430F, 0xAD, 0x91, 0xB4, 0x4D, \ - 0xCB, 0x3C, 0x6F, 0x35) + GUID_INIT(0xD995E954, 0xBBC1, 0x430F, 0xAD, 0x91, 0xB4, 0x4D, \ + 0xCB, 0x3C, 0x6F, 0x35) /* Firmware Error Record Reference */ #define CPER_SEC_FW_ERR_REC_REF \ - UUID_LE(0x81212A96, 0x09ED, 0x4996, 0x94, 0x71, 0x8D, 0x72, \ - 0x9C, 0x8E, 0x69, 0xED) + GUID_INIT(0x81212A96, 0x09ED, 0x4996, 0x94, 0x71, 0x8D, 0x72, \ + 0x9C, 0x8E, 0x69, 0xED) /* PCI/PCI-X Bus */ #define CPER_SEC_PCI_X_BUS \ - UUID_LE(0xC5753963, 0x3B84, 0x4095, 0xBF, 0x78, 0xED, 0xDA, \ - 0xD3, 0xF9, 0xC9, 0xDD) + GUID_INIT(0xC5753963, 0x3B84, 0x4095, 0xBF, 0x78, 0xED, 0xDA, \ + 0xD3, 0xF9, 0xC9, 0xDD) /* PCI Component/Device */ #define CPER_SEC_PCI_DEV \ - UUID_LE(0xEB5E4685, 0xCA66, 0x4769, 0xB6, 0xA2, 0x26, 0x06, \ - 0x8B, 0x00, 0x13, 0x26) + GUID_INIT(0xEB5E4685, 0xCA66, 0x4769, 0xB6, 0xA2, 0x26, 0x06, \ + 0x8B, 0x00, 0x13, 0x26) #define CPER_SEC_DMAR_GENERIC \ - UUID_LE(0x5B51FEF7, 0xC79D, 0x4434, 0x8F, 0x1B, 0xAA, 0x62, \ - 0xDE, 0x3E, 0x2C, 0x64) + GUID_INIT(0x5B51FEF7, 0xC79D, 0x4434, 0x8F, 0x1B, 0xAA, 0x62, \ + 0xDE, 0x3E, 0x2C, 0x64) /* Intel VT for Directed I/O specific DMAr */ #define CPER_SEC_DMAR_VT \ - UUID_LE(0x71761D37, 0x32B2, 0x45cd, 0xA7, 0xD0, 0xB0, 0xFE, \ - 0xDD, 0x93, 0xE8, 0xCF) + GUID_INIT(0x71761D37, 0x32B2, 0x45cd, 0xA7, 0xD0, 0xB0, 0xFE, \ + 0xDD, 0x93, 0xE8, 0xCF) /* IOMMU specific DMAr */ #define CPER_SEC_DMAR_IOMMU \ - UUID_LE(0x036F84E1, 0x7F37, 0x428c, 0xA7, 0x9E, 0x57, 0x5F, \ - 0xDF, 0xAA, 0x84, 0xEC) + GUID_INIT(0x036F84E1, 0x7F37, 0x428c, 0xA7, 0x9E, 0x57, 0x5F, \ + 0xDF, 0xAA, 0x84, 0xEC) #define CPER_PROC_VALID_TYPE 0x0001 #define CPER_PROC_VALID_ISA 0x0002 @@ -255,6 +259,22 @@ enum { #define CPER_PCIE_SLOT_SHIFT 3 +#define CPER_ARM_VALID_MPIDR BIT(0) +#define CPER_ARM_VALID_AFFINITY_LEVEL BIT(1) +#define CPER_ARM_VALID_RUNNING_STATE BIT(2) +#define CPER_ARM_VALID_VENDOR_INFO BIT(3) + +#define CPER_ARM_INFO_VALID_MULTI_ERR BIT(0) +#define CPER_ARM_INFO_VALID_FLAGS BIT(1) +#define CPER_ARM_INFO_VALID_ERR_INFO BIT(2) +#define CPER_ARM_INFO_VALID_VIRT_ADDR BIT(3) +#define CPER_ARM_INFO_VALID_PHYSICAL_ADDR BIT(4) + +#define CPER_ARM_INFO_FLAGS_FIRST BIT(0) +#define CPER_ARM_INFO_FLAGS_LAST BIT(1) +#define CPER_ARM_INFO_FLAGS_PROPAGATED BIT(2) +#define CPER_ARM_INFO_FLAGS_OVERFLOW BIT(3) + /* * All tables and structs must be byte-packed to match CPER * specification, since the tables are provided by the system BIOS @@ -270,10 +290,10 @@ struct cper_record_header { __u32 validation_bits; __u32 record_length; __u64 timestamp; - uuid_le platform_id; - uuid_le partition_id; - uuid_le creator_id; - uuid_le notification_type; + guid_t platform_id; + guid_t partition_id; + guid_t creator_id; + guid_t notification_type; __u64 record_id; __u32 flags; __u64 persistence_information; @@ -289,8 +309,8 @@ struct cper_section_descriptor { __u8 validation_bits; __u8 reserved; /* must be zero */ __u32 flags; - uuid_le section_type; - uuid_le fru_id; + guid_t section_type; + guid_t fru_id; __u32 section_severity; __u8 fru_text[20]; }; @@ -323,7 +343,7 @@ struct cper_sec_proc_ia { /* IA32/X64 Processor Error Information Structure */ struct cper_ia_err_info { - uuid_le err_type; + guid_t err_type; __u64 validation_bits; __u64 check_info; __u64 target_id; @@ -340,6 +360,40 @@ struct cper_ia_proc_ctx { __u64 mm_reg_addr; }; +/* ARM Processor Error Section */ +struct cper_sec_proc_arm { + __u32 validation_bits; + __u16 err_info_num; /* Number of Processor Error Info */ + __u16 context_info_num; /* Number of Processor Context Info Records*/ + __u32 section_length; + __u8 affinity_level; + __u8 reserved[3]; /* must be zero */ + __u64 mpidr; + __u64 midr; + __u32 running_state; /* Bit 0 set - Processor running. PSCI = 0 */ + __u32 psci_state; +}; + +/* ARM Processor Error Information Structure */ +struct cper_arm_err_info { + __u8 version; + __u8 length; + __u16 validation_bits; + __u8 type; + __u16 multiple_error; + __u8 flags; + __u64 error_info; + __u64 virt_fault_addr; + __u64 physical_fault_addr; +}; + +/* ARM Processor Context Information Structure */ +struct cper_arm_ctx_info { + __u16 version; + __u16 type; + __u32 size; +}; + /* Old Memory Error Section UEFI 2.1, 2.2 */ struct cper_sec_mem_err_old { __u64 validation_bits; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f92081234afd..ca73bc1563f4 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -99,26 +99,32 @@ static inline void cpu_maps_update_done(void) extern struct bus_type cpu_subsys; #ifdef CONFIG_HOTPLUG_CPU -/* Stop CPUs going up and down. */ - -extern void cpu_hotplug_begin(void); -extern void cpu_hotplug_done(void); -extern void get_online_cpus(void); -extern void put_online_cpus(void); +extern void cpus_write_lock(void); +extern void cpus_write_unlock(void); +extern void cpus_read_lock(void); +extern void cpus_read_unlock(void); +extern void lockdep_assert_cpus_held(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); void clear_tasks_mm_cpumask(int cpu); int cpu_down(unsigned int cpu); -#else /* CONFIG_HOTPLUG_CPU */ - -static inline void cpu_hotplug_begin(void) {} -static inline void cpu_hotplug_done(void) {} -#define get_online_cpus() do { } while (0) -#define put_online_cpus() do { } while (0) -#define cpu_hotplug_disable() do { } while (0) -#define cpu_hotplug_enable() do { } while (0) -#endif /* CONFIG_HOTPLUG_CPU */ +#else /* CONFIG_HOTPLUG_CPU */ + +static inline void cpus_write_lock(void) { } +static inline void cpus_write_unlock(void) { } +static inline void cpus_read_lock(void) { } +static inline void cpus_read_unlock(void) { } +static inline void lockdep_assert_cpus_held(void) { } +static inline void cpu_hotplug_disable(void) { } +static inline void cpu_hotplug_enable(void) { } +#endif /* !CONFIG_HOTPLUG_CPU */ + +/* Wrappers which go away once all code is converted */ +static inline void cpu_hotplug_begin(void) { cpus_write_lock(); } +static inline void cpu_hotplug_done(void) { cpus_write_unlock(); } +static inline void get_online_cpus(void) { cpus_read_lock(); } +static inline void put_online_cpus(void) { cpus_read_unlock(); } #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index c156f5082758..d4292ebc5c8b 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -28,47 +28,49 @@ #include <linux/thermal.h> #include <linux/cpumask.h> +struct cpufreq_policy; + typedef int (*get_static_t)(cpumask_t *cpumask, int interval, unsigned long voltage, u32 *power); #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus); +cpufreq_cooling_register(struct cpufreq_policy *policy); struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @np: a valid struct device_node to the cooling device device tree node. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ #ifdef CONFIG_THERMAL_OF struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus); + struct cpufreq_policy *policy); struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); #else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -82,15 +84,14 @@ of_cpufreq_power_cooling_register(struct device_node *np, */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus) +cpufreq_cooling_register(struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { return NULL; @@ -98,14 +99,14 @@ cpufreq_power_cooling_register(const struct cpumask *clip_cpus, static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -117,11 +118,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -static inline -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) -{ - return THERMAL_CSTATE_INVALID; -} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a5ce0bbeadb5..537ff842ff73 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -127,6 +127,15 @@ struct cpufreq_policy { */ unsigned int transition_delay_us; + /* + * Remote DVFS flag (Not added to the driver structure as we don't want + * to access another structure from scheduler hotpath). + * + * Should be set if CPUs can do DVFS on behalf of other CPUs from + * different cpufreq policies. + */ + bool dvfs_possible_from_any_cpu; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; int cached_resolved_idx; @@ -370,6 +379,12 @@ struct cpufreq_driver { */ #define CPUFREQ_NEED_INITIAL_FREQ_CHECK (1 << 5) +/* + * Set by drivers to disallow use of governors with "dynamic_switching" flag + * set. + */ +#define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING (1 << 6) + int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); @@ -487,14 +502,8 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, * polling frequency is 1000 times the transition latency of the processor. The * ondemand governor will work on any processor with transition latency <= 10ms, * using appropriate sampling rate. - * - * For CPUs with transition latency > 10ms (mostly drivers with CPUFREQ_ETERNAL) - * the ondemand governor will not work. All times here are in us (microseconds). */ -#define MIN_SAMPLING_RATE_RATIO (2) #define LATENCY_MULTIPLIER (1000) -#define MIN_LATENCY_MULTIPLIER (20) -#define TRANSITION_LATENCY_LIMIT (10 * 1000 * 1000) struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; @@ -507,9 +516,8 @@ struct cpufreq_governor { char *buf); int (*store_setspeed) (struct cpufreq_policy *policy, unsigned int freq); - unsigned int max_transition_latency; /* HW must be able to switch to - next freq faster than this value in nano secs or we - will fallback to performance governor */ + /* For governors which change frequency dynamically by themselves */ + bool dynamic_switching; struct list_head governor_list; struct module *owner; }; @@ -525,6 +533,7 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation); unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, unsigned int target_freq); +unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy); int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); @@ -562,6 +571,17 @@ struct governor_attr { size_t count); }; +static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy) +{ + /* + * Allow remote callbacks if: + * - dvfs_possible_from_any_cpu flag is set + * - the local and remote CPUs share cpufreq policy + */ + return policy->dvfs_possible_from_any_cpu || + cpumask_test_cpu(smp_processor_id(), policy->cpus); +} + /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ @@ -862,6 +882,20 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, return -EINVAL; } } + +static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *pos; + int count = 0; + + if (unlikely(!policy->freq_table)) + return 0; + + cpufreq_for_each_valid_entry(pos, policy->freq_table) + count++; + + return count; +} #else static inline int cpufreq_boost_trigger_state(int state) { @@ -883,6 +917,8 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) } #endif +extern unsigned int arch_freq_get_on_cpu(int cpu); + /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0f2a80377520..f24bfb2b9a2d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -39,8 +39,6 @@ enum cpuhp_state { CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_INTEL_DEAD, CPUHP_LUSTRE_CFS_DEAD, - CPUHP_SCSI_BNX2FC_DEAD, - CPUHP_SCSI_BNX2I_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, @@ -58,7 +56,6 @@ enum cpuhp_state { CPUHP_XEN_EVTCHN_PREPARE, CPUHP_ARM_SHMOBILE_SCU_PREPARE, CPUHP_SH_SH3X_PREPARE, - CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, CPUHP_NET_IUCV_PREPARE, @@ -124,6 +121,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE_IDLE, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, + CPUHP_AP_IRQ_AFFINITY_ONLINE, CPUHP_AP_PERF_ONLINE, CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_PERF_X86_UNCORE_ONLINE, @@ -139,6 +137,9 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, + CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, + CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, + CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, @@ -153,6 +154,11 @@ int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance); +int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, + bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu), + bool multi_instance); /** * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks * @state: The state for which the calls are installed @@ -171,6 +177,15 @@ static inline int cpuhp_setup_state(enum cpuhp_state state, return __cpuhp_setup_state(state, name, true, startup, teardown, false); } +static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state_cpuslocked(state, name, true, startup, + teardown, false); +} + /** * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the * callbacks @@ -191,6 +206,15 @@ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state, false); } +static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state_cpuslocked(state, name, false, startup, + teardown, false); +} + /** * cpuhp_setup_state_multi - Add callbacks for multi state * @state: The state for which the calls are installed @@ -217,6 +241,8 @@ static inline int cpuhp_setup_state_multi(enum cpuhp_state state, int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke); +int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, + struct hlist_node *node, bool invoke); /** * cpuhp_state_add_instance - Add an instance for a state and invoke startup @@ -249,7 +275,15 @@ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state, return __cpuhp_state_add_instance(state, node, false); } +static inline int +cpuhp_state_add_instance_nocalls_cpuslocked(enum cpuhp_state state, + struct hlist_node *node) +{ + return __cpuhp_state_add_instance_cpuslocked(state, node, false); +} + void __cpuhp_remove_state(enum cpuhp_state state, bool invoke); +void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke); /** * cpuhp_remove_state - Remove hotplug state callbacks and invoke the teardown @@ -273,6 +307,11 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state) __cpuhp_remove_state(state, false); } +static inline void cpuhp_remove_state_nocalls_cpuslocked(enum cpuhp_state state) +{ + __cpuhp_remove_state_cpuslocked(state, false); +} + /** * cpuhp_remove_multi_state - Remove hotplug multi state callback * @state: The state for which the calls are removed diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index fc1e5d7fc1c7..8f7788d23b57 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -52,17 +52,18 @@ struct cpuidle_state { int (*enter_dead) (struct cpuidle_device *dev, int index); /* - * CPUs execute ->enter_freeze with the local tick or entire timekeeping + * CPUs execute ->enter_s2idle with the local tick or entire timekeeping * suspended, so it must not re-enable interrupts at any point (even * temporarily) or attempt to change states of clock event devices. */ - void (*enter_freeze) (struct cpuidle_device *dev, + void (*enter_s2idle) (struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); }; /* Idle State Flags */ #define CPUIDLE_FLAG_NONE (0x00) +#define CPUIDLE_FLAG_POLLING (0x01) /* polling state */ #define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP (0x04) /* timer is stopped on this state */ @@ -197,14 +198,14 @@ static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; } #ifdef CONFIG_CPU_IDLE extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev); -extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, +extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern void cpuidle_use_deepest_state(bool enable); #else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } -static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, +static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_use_deepest_state(bool enable) @@ -224,6 +225,12 @@ static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, } #endif +#ifdef CONFIG_ARCH_HAS_CPU_RELAX +void cpuidle_poll_state_init(struct cpuidle_driver *drv); +#else +static inline void cpuidle_poll_state_init(struct cpuidle_driver *drv) {} +#endif + /****************************** * CPUIDLE GOVERNOR INTERFACE * ******************************/ @@ -250,12 +257,6 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov) {return 0;} #endif -#ifdef CONFIG_ARCH_HAS_CPU_RELAX -#define CPUIDLE_DRIVER_STATE_START 1 -#else -#define CPUIDLE_DRIVER_STATE_START 0 -#endif - #define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx) \ ({ \ int __ret; \ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2404ad238c0b..cd415b733c2a 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -32,15 +32,15 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if NR_CPUS == 1 -#define nr_cpu_ids 1 +#define nr_cpu_ids 1U #else -extern int nr_cpu_ids; +extern unsigned int nr_cpu_ids; #endif #ifdef CONFIG_CPUMASK_OFFSTACK /* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, * not all bits may be allocated. */ -#define nr_cpumask_bits ((unsigned int)nr_cpu_ids) +#define nr_cpumask_bits nr_cpu_ids #else #define nr_cpumask_bits ((unsigned int)NR_CPUS) #endif @@ -178,20 +178,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } -/** - * cpumask_next - get the next cpu in a cpumask - * @n: the cpu prior to the place to search (ie. return will be > @n) - * @srcp: the cpumask pointer - * - * Returns >= nr_cpu_ids if no further cpus set. - */ -static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) -{ - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); - return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); -} +unsigned int cpumask_next(int n, const struct cpumask *srcp); /** * cpumask_next_zero - get the next unset cpu in a cpumask @@ -236,6 +223,23 @@ unsigned int cpumask_local_spread(unsigned int i, int node); (cpu) = cpumask_next_zero((cpu), (mask)), \ (cpu) < nr_cpu_ids;) +extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); + +/** + * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location + * @cpu: the (optionally unsigned) integer iterator + * @mask: the cpumask poiter + * @start: the start location + * + * The implementation does not assume any bit in @mask is set (including @start). + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_wrap(cpu, mask, start) \ + for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ + (cpu) < nr_cpumask_bits; \ + (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) + /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator @@ -276,6 +280,12 @@ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } +static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +{ + __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + + /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) @@ -286,6 +296,11 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } +static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) +{ + __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 119a3f9604b0..a1e6a33a4b03 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -18,31 +18,42 @@ #ifdef CONFIG_CPUSETS +/* + * Static branch rewrites can happen in an arbitrary order for a given + * key. In code paths where we need to loop with read_mems_allowed_begin() and + * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need + * to ensure that begin() always gets rewritten before retry() in the + * disabled -> enabled transition. If not, then if local irqs are disabled + * around the loop, we can deadlock since retry() would always be + * comparing the latest value of the mems_allowed seqcount against 0 as + * begin() still would see cpusets_enabled() as false. The enabled -> disabled + * transition should happen in reverse order for the same reasons (want to stop + * looking at real value of mems_allowed.sequence in retry() first). + */ +extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } -static inline int nr_cpusets(void) -{ - /* jump label reference count + the top-level cpuset */ - return static_key_count(&cpusets_enabled_key.key) + 1; -} - static inline void cpuset_inc(void) { + static_branch_inc(&cpusets_pre_enable_key); static_branch_inc(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec(&cpusets_enabled_key); + static_branch_dec(&cpusets_pre_enable_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); +extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); +extern void cpuset_wait_for_hotplug(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -115,7 +126,7 @@ extern void cpuset_print_current_mems_allowed(void); */ static inline unsigned int read_mems_allowed_begin(void) { - if (!cpusets_enabled()) + if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); @@ -129,7 +140,7 @@ static inline unsigned int read_mems_allowed_begin(void) */ static inline bool read_mems_allowed_retry(unsigned int seq) { - if (!cpusets_enabled()) + if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); @@ -155,11 +166,15 @@ static inline bool cpusets_enabled(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} +static inline void cpuset_force_rebuild(void) { } + static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } +static inline void cpuset_wait_for_hotplug(void) { } + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 541a197ba4a2..2df2118fbe13 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -10,11 +10,16 @@ #define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) #define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) +/* + * The per-cpu notes area is a list of notes terminated by a "NULL" + * note header. For kdump, the code in vmcore.c runs in the context + * of the second kernel to combine them into one note. + */ #define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ CRASH_CORE_NOTE_NAME_BYTES + \ CRASH_CORE_NOTE_DESC_BYTES) -#define VMCOREINFO_BYTES (4096) +#define VMCOREINFO_BYTES PAGE_SIZE #define VMCOREINFO_NOTE_NAME "VMCOREINFO" #define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) #define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ @@ -23,6 +28,7 @@ typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; +void crash_update_vmcoreinfo_safecopy(void *ptr); void crash_save_vmcoreinfo(void); void arch_crash_save_vmcoreinfo(void); __printf(1, 2) @@ -51,9 +57,7 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) -extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; -extern size_t vmcoreinfo_size; -extern size_t vmcoreinfo_max_size; +extern u32 *vmcoreinfo_note; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); diff --git a/include/linux/crc4.h b/include/linux/crc4.h new file mode 100644 index 000000000000..8f739f1d794f --- /dev/null +++ b/include/linux/crc4.h @@ -0,0 +1,8 @@ +#ifndef _LINUX_CRC4_H +#define _LINUX_CRC4_H + +#include <linux/types.h> + +extern uint8_t crc4(uint8_t c, uint64_t x, int bits); + +#endif /* _LINUX_CRC4_H */ diff --git a/include/linux/cred.h b/include/linux/cred.h index b03e7d049a64..099058e1178b 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -1,4 +1,4 @@ -/* Credentials management - see Documentation/security/credentials.txt +/* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) @@ -31,7 +31,7 @@ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; -}; +} __randomize_layout; /** * get_group_info - Get a reference to a group info structure @@ -145,7 +145,7 @@ struct cred { struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ -}; +} __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index fbecbd089d75..07eed95e10c7 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -2,6 +2,7 @@ #define CEPH_CRUSH_CRUSH_H #ifdef __KERNEL__ +# include <linux/rbtree.h> # include <linux/types.h> #else # include "crush_compat.h" @@ -137,6 +138,68 @@ struct crush_bucket { }; +/** @ingroup API + * + * Replacement weights for each item in a bucket. The size of the + * array must be exactly the size of the straw2 bucket, just as the + * item_weights array. + * + */ +struct crush_weight_set { + __u32 *weights; /*!< 16.16 fixed point weights + in the same order as items */ + __u32 size; /*!< size of the __weights__ array */ +}; + +/** @ingroup API + * + * Replacement weights and ids for a given straw2 bucket, for + * placement purposes. + * + * When crush_do_rule() chooses the Nth item from a straw2 bucket, the + * replacement weights found at __weight_set[N]__ are used instead of + * the weights from __item_weights__. If __N__ is greater than + * __weight_set_size__, the weights found at __weight_set_size-1__ are + * used instead. For instance if __weight_set__ is: + * + * [ [ 0x10000, 0x20000 ], // position 0 + * [ 0x20000, 0x40000 ] ] // position 1 + * + * choosing the 0th item will use position 0 weights [ 0x10000, 0x20000 ] + * choosing the 1th item will use position 1 weights [ 0x20000, 0x40000 ] + * choosing the 2th item will use position 1 weights [ 0x20000, 0x40000 ] + * etc. + * + */ +struct crush_choose_arg { + __s32 *ids; /*!< values to use instead of items */ + __u32 ids_size; /*!< size of the __ids__ array */ + struct crush_weight_set *weight_set; /*!< weight replacements for + a given position */ + __u32 weight_set_size; /*!< size of the __weight_set__ array */ +}; + +/** @ingroup API + * + * Replacement weights and ids for each bucket in the crushmap. The + * __size__ of the __args__ array must be exactly the same as the + * __map->max_buckets__. + * + * The __crush_choose_arg__ at index N will be used when choosing + * an item from the bucket __map->buckets[N]__ bucket, provided it + * is a straw2 bucket. + * + */ +struct crush_choose_arg_map { +#ifdef __KERNEL__ + struct rb_node node; + s64 choose_args_index; +#endif + struct crush_choose_arg *args; /*!< replacement for each bucket + in the crushmap */ + __u32 size; /*!< size of the __args__ array */ +}; + struct crush_bucket_uniform { struct crush_bucket h; __u32 item_weight; /* 16-bit fixed point; all items equally weighted */ @@ -236,6 +299,9 @@ struct crush_map { __u32 allowed_bucket_algs; __u32 *choose_tries; +#else + /* CrushWrapper::choose_args */ + struct rb_root choose_args; #endif }; diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h index c95e19e1ff11..141edabb947e 100644 --- a/include/linux/crush/mapper.h +++ b/include/linux/crush/mapper.h @@ -11,11 +11,10 @@ #include "crush.h" extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size); -extern int crush_do_rule(const struct crush_map *map, - int ruleno, - int x, int *result, int result_max, - const __u32 *weights, int weight_max, - void *cwin); +int crush_do_rule(const struct crush_map *map, + int ruleno, int x, int *result, int result_max, + const __u32 *weight, int weight_max, + void *cwin, const struct crush_choose_arg *choose_args); /* * Returns the exact amount of workspace that will need to be used diff --git a/include/linux/dax.h b/include/linux/dax.h index 5ec1f6c47716..122197124b9d 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -16,8 +16,13 @@ struct dax_operations { */ long (*direct_access)(struct dax_device *, pgoff_t, long, void **, pfn_t *); + /* copy_from_iter: required operation for fs-dax direct-i/o */ + size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, + struct iov_iter *); }; +extern struct attribute_group dax_attribute_group; + #if IS_ENABLED(CONFIG_DAX) struct dax_device *dax_get_by_host(const char *host); void put_dax(struct dax_device *dax_dev); @@ -50,6 +55,7 @@ static inline void fs_put_dax(struct dax_device *dax_dev) put_dax(dax_dev); } +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); #else static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { @@ -64,6 +70,11 @@ static inline struct dax_device *fs_dax_get_by_host(const char *host) static inline void fs_put_dax(struct dax_device *dax_dev) { } + +static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) +{ + return NULL; +} #endif int dax_read_lock(void); @@ -75,34 +86,11 @@ void kill_dax(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); - -/* - * We use lowest available bit in exceptional entry for locking, one bit for - * the entry size (PMD) and two more to tell us if the entry is a huge zero - * page (HZP) or an empty entry that is just used for locking. In total four - * special bits. - * - * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and - * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem - * block allocation. - */ -#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) -#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) -#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) -#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) - -static inline unsigned long dax_radix_sector(void *entry) -{ - return (unsigned long)entry >> RADIX_DAX_SHIFT; -} - -static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags) -{ - return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | - ((unsigned long)sector << RADIX_DAX_SHIFT) | - RADIX_DAX_ENTRY_LOCK); -} +size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t bytes, struct iov_iter *i); +void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); +void dax_write_cache(struct dax_device *dax_dev, bool wc); +bool dax_write_cache_enabled(struct dax_device *dax_dev); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); @@ -111,8 +99,6 @@ int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, void *entry, bool wake_all); #ifdef CONFIG_FS_DAX int __dax_zero_page_range(struct block_device *bdev, @@ -127,26 +113,6 @@ static inline int __dax_zero_page_range(struct block_device *bdev, } #endif -#ifdef CONFIG_FS_DAX_PMD -static inline unsigned int dax_radix_order(void *entry) -{ - if ((unsigned long)entry & RADIX_DAX_PMD) - return PMD_SHIFT - PAGE_SHIFT; - return 0; -} -#else -static inline unsigned int dax_radix_order(void *entry) -{ - return 0; -} -#endif -int dax_pfn_mkwrite(struct vm_fault *vmf); - -static inline bool vma_is_dax(struct vm_area_struct *vma) -{ - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); -} - static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d2e38dc6172c..ed1a7cf6923a 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -55,6 +55,11 @@ struct qstr { #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } +extern const char empty_string[]; +extern const struct qstr empty_name; +extern const char slash_string[]; +extern const struct qstr slash_name; + struct dentry_stat_t { long nr_dentry; long nr_unused; @@ -113,7 +118,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -}; +} __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: @@ -142,7 +147,7 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, const struct inode *, - unsigned int); + unsigned int, unsigned int); } ____cacheline_aligned; /* @@ -557,11 +562,15 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) return upper; } +/* d_real() flags */ +#define D_REAL_UPPER 0x2 /* return upper dentry or NULL if non-upper */ + /** * d_real - Return the real dentry * @dentry: the dentry to query * @inode: inode to select the dentry from multiple layers (can be NULL) - * @flags: open flags to control copy-up behavior + * @open_flags: open flags to control copy-up behavior + * @flags: flags to control what is returned by this function * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. @@ -570,10 +579,10 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) */ static inline struct dentry *d_real(struct dentry *dentry, const struct inode *inode, - unsigned int flags) + unsigned int open_flags, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, inode, flags); + return dentry->d_op->d_real(dentry, inode, open_flags, flags); else return dentry; } @@ -588,8 +597,14 @@ static inline struct dentry *d_real(struct dentry *dentry, static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ - return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0)); + return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0, 0)); } +struct name_snapshot { + const unsigned char *name; + unsigned char inline_name[DNAME_INLINE_LEN]; +}; +void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); +void release_dentry_name_snapshot(struct name_snapshot *); #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 9174b0d28582..b93efc8feecd 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/filesystems for more details. + * See Documentation/filesystems/ for more details. */ #ifndef _DEBUGFS_H_ @@ -196,6 +196,14 @@ static inline struct dentry *debugfs_create_file(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_file_unsafe(const char *name, + umode_t mode, struct dentry *parent, + void *data, + const struct file_operations *fops) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_file_size(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops, @@ -289,6 +297,14 @@ static inline struct dentry *debugfs_create_u64(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_ulong(const char *name, + umode_t mode, + struct dentry *parent, + unsigned long *value) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 6c220e4ebb6b..597294e0cc40 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -214,19 +214,6 @@ extern void devm_devfreq_unregister_notifier(struct device *dev, extern struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index); -/** - * devfreq_update_stats() - update the last_status pointer in struct devfreq - * @df: the devfreq instance whose status needs updating - * - * Governors are recommended to use this function along with last_status, - * which allows other entities to reuse the last_status without affecting - * the values fetched later by governors. - */ -static inline int devfreq_update_stats(struct devfreq *df) -{ - return df->profile->get_dev_status(df->dev.parent, &df->last_status); -} - #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index f4c639c0c362..a5538433c927 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -72,9 +72,9 @@ typedef void (*dm_release_clone_request_fn) (struct request *clone); * 2 : The target wants to push back the io */ typedef int (*dm_endio_fn) (struct dm_target *ti, - struct bio *bio, int error); + struct bio *bio, blk_status_t *error); typedef int (*dm_request_endio_fn) (struct dm_target *ti, - struct request *clone, int error, + struct request *clone, blk_status_t error, union map_info *map_context); typedef void (*dm_presuspend_fn) (struct dm_target *ti); @@ -132,6 +132,8 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); +typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); #define PAGE_SECTORS (PAGE_SIZE / 512) void dm_error(const char *message); @@ -181,6 +183,7 @@ struct target_type { dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; + dm_dax_copy_from_iter_fn dax_copy_from_iter; /* For internal device-mapper use. */ struct list_head list; @@ -237,6 +240,12 @@ typedef unsigned (*dm_num_write_bios_fn) (struct dm_target *ti, struct bio *bio) #define DM_TARGET_PASSES_INTEGRITY 0x00000020 #define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY) +/* + * Indicates that a target supports host-managed zoned block devices. + */ +#define DM_TARGET_ZONED_HM 0x00000040 +#define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM) + struct dm_target { struct dm_table *table; struct target_type *type; @@ -375,7 +384,7 @@ struct dm_arg { * Validate the next argument, either returning it as *value or, if invalid, * returning -EINVAL and setting *error. */ -int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, +int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, unsigned *value, char **error); /* @@ -383,7 +392,7 @@ int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, * arg->min and arg->max further arguments. Either return the size as * *num_args or, if invalid, return -EINVAL and set *error. */ -int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set, +int dm_read_arg_group(const struct dm_arg *arg, struct dm_arg_set *arg_set, unsigned *num_args, char **error); /* @@ -444,6 +453,8 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); +void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, + sector_t start); union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); @@ -535,56 +546,32 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); *---------------------------------------------------------------*/ #define DM_NAME "device-mapper" -#ifdef CONFIG_PRINTK -extern struct ratelimit_state dm_ratelimit_state; +#define DM_RATELIMIT(pr_func, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + \ + if (__ratelimit(&rs)) \ + pr_func(DM_FMT(fmt), ##__VA_ARGS__); \ +} while (0) -#define dm_ratelimit() __ratelimit(&dm_ratelimit_state) -#else -#define dm_ratelimit() 0 -#endif +#define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n" + +#define DMCRIT(fmt, ...) pr_crit(DM_FMT(fmt), ##__VA_ARGS__) -#define DMCRIT(f, arg...) \ - printk(KERN_CRIT DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) - -#define DMERR(f, arg...) \ - printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) -#define DMERR_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " \ - f "\n", ## arg); \ - } while (0) - -#define DMWARN(f, arg...) \ - printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) -#define DMWARN_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " \ - f "\n", ## arg); \ - } while (0) - -#define DMINFO(f, arg...) \ - printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) -#define DMINFO_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f \ - "\n", ## arg); \ - } while (0) +#define DMERR(fmt, ...) pr_err(DM_FMT(fmt), ##__VA_ARGS__) +#define DMERR_LIMIT(fmt, ...) DM_RATELIMIT(pr_err, fmt, ##__VA_ARGS__) +#define DMWARN(fmt, ...) pr_warn(DM_FMT(fmt), ##__VA_ARGS__) +#define DMWARN_LIMIT(fmt, ...) DM_RATELIMIT(pr_warn, fmt, ##__VA_ARGS__) +#define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__) +#define DMINFO_LIMIT(fmt, ...) DM_RATELIMIT(pr_info, fmt, ##__VA_ARGS__) #ifdef CONFIG_DM_DEBUG -# define DMDEBUG(f, arg...) \ - printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX " DEBUG: " f "\n", ## arg) -# define DMDEBUG_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX ": " f \ - "\n", ## arg); \ - } while (0) +#define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__) +#define DMDEBUG_LIMIT(fmt, ...) DM_RATELIMIT(pr_debug, fmt, ##__VA_ARGS__) #else -# define DMDEBUG(f, arg...) do {} while (0) -# define DMDEBUG_LIMIT(f, arg...) do {} while (0) +#define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif #define DMEMIT(x...) sz += ((sz >= maxlen) ? \ diff --git a/include/linux/device.h b/include/linux/device.h index 9ef518af5515..c6f27207dbe8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,7 +66,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @name: The name of the bus. * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). * @dev_root: Default device to use as the parent. - * @dev_attrs: Default attributes of the devices on the bus. * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. @@ -112,7 +111,6 @@ struct bus_type { const char *name; const char *dev_name; struct device *dev_root; - struct device_attribute *dev_attrs; /* use dev_groups instead */ const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; @@ -365,7 +363,6 @@ int subsys_virtual_register(struct bus_type *subsys, * struct class - device classes * @name: Name of the class. * @owner: The module owner. - * @class_attrs: Default attributes of this class. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. * @dev_kobj: The kobject that represents this class and links it into the hierarchy. @@ -378,6 +375,7 @@ int subsys_virtual_register(struct bus_type *subsys, * @suspend: Used to put the device to sleep mode, usually to a low power * state. * @resume: Used to bring the device from the sleep mode. + * @shutdown_pre: Called at shut-down time before driver shutdown. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. * @pm: The default device power management operations of this class. @@ -394,7 +392,6 @@ struct class { const char *name; struct module *owner; - struct class_attribute *class_attrs; const struct attribute_group **class_groups; const struct attribute_group **dev_groups; struct kobject *dev_kobj; @@ -407,6 +404,7 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + int (*shutdown_pre)(struct device *dev); const struct kobj_ns_type_operations *ns_type; const void *(*namespace)(struct device *dev); @@ -465,8 +463,6 @@ struct class_attribute { const char *buf, size_t count); }; -#define CLASS_ATTR(_name, _mode, _show, _store) \ - struct class_attribute class_attr_##_name = __ATTR(_name, _mode, _show, _store) #define CLASS_ATTR_RW(_name) \ struct class_attribute class_attr_##_name = __ATTR_RW(_name) #define CLASS_ATTR_RO(_name) \ @@ -847,10 +843,11 @@ struct dev_links_info { * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @pins: For device pin management. - * See Documentation/pinctrl.txt for details. + * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. + * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations @@ -879,6 +876,8 @@ struct dev_links_info { * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). + * @of_node_reused: Set if the device-tree node is shared with an ancestor + * device. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -966,6 +965,7 @@ struct device { bool offline_disabled:1; bool offline:1; + bool of_node_reused:1; }; static inline struct device *kobj_to_dev(struct kobject *kobj) @@ -1144,6 +1144,7 @@ extern int device_offline(struct device *dev); extern int device_online(struct device *dev); extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); extern void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); +void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); static inline int dev_num_vf(struct device *dev) { @@ -1200,6 +1201,36 @@ struct device *device_create_with_groups(struct class *cls, const char *fmt, ...); extern void device_destroy(struct class *cls, dev_t devt); +extern int __must_check device_add_groups(struct device *dev, + const struct attribute_group **groups); +extern void device_remove_groups(struct device *dev, + const struct attribute_group **groups); + +static inline int __must_check device_add_group(struct device *dev, + const struct attribute_group *grp) +{ + const struct attribute_group *groups[] = { grp, NULL }; + + return device_add_groups(dev, groups); +} + +static inline void device_remove_group(struct device *dev, + const struct attribute_group *grp) +{ + const struct attribute_group *groups[] = { grp, NULL }; + + return device_remove_groups(dev, groups); +} + +extern int __must_check devm_device_add_groups(struct device *dev, + const struct attribute_group **groups); +extern void devm_device_remove_groups(struct device *dev, + const struct attribute_group **groups); +extern int __must_check devm_device_add_group(struct device *dev, + const struct attribute_group *grp); +extern void devm_device_remove_group(struct device *dev, + const struct attribute_group *grp); + /* * Platform "fixup" functions - allow the platform to have their say * about devices and actions that the general device layer doesn't diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 277ab9af9ac2..100cb4343763 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,7 @@ struct pts_fs_info; +struct vfsmount *devpts_mntget(struct file *, struct pts_fs_info *); struct pts_fs_info *devpts_acquire(struct file *); void devpts_release(struct pts_fs_info *); @@ -32,6 +33,15 @@ void *devpts_get_priv(struct dentry *); /* unlink */ void devpts_pty_kill(struct dentry *); +/* in pty.c */ +int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags); + +#else +static inline int +ptm_open_peer(struct file *master, struct tty_struct *tty, int flags) +{ + return -EIO; +} #endif diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index f486d636b82e..cfac8588ed56 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -20,6 +20,7 @@ #define DM_KCOPYD_MAX_REGIONS 8 #define DM_KCOPYD_IGNORE_ERROR 1 +#define DM_KCOPYD_WRITE_SEQ 2 struct dm_kcopyd_throttle { unsigned throttle; diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index a5195a7d6f77..171895072435 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -55,6 +55,7 @@ struct dma_fence_cb; * of the time. * * DMA_FENCE_FLAG_SIGNALED_BIT - fence is already signaled + * DMA_FENCE_FLAG_TIMESTAMP_BIT - timestamp recorded for fence signaling * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called * DMA_FENCE_FLAG_USER_BITS - start of the unused bits, can be used by the * implementer of the fence for its own purposes. Can be used in different @@ -84,6 +85,7 @@ struct dma_fence { enum dma_fence_flag_bits { DMA_FENCE_FLAG_SIGNALED_BIT, + DMA_FENCE_FLAG_TIMESTAMP_BIT, DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, DMA_FENCE_FLAG_USER_BITS, /* must always be last member */ }; @@ -336,6 +338,19 @@ dma_fence_is_signaled(struct dma_fence *fence) } /** + * __dma_fence_is_later - return if f1 is chronologically later than f2 + * @f1: [in] the first fence's seqno + * @f2: [in] the second fence's seqno from the same context + * + * Returns true if f1 is chronologically later than f2. Both fences must be + * from the same context, since a seqno is not common across contexts. + */ +static inline bool __dma_fence_is_later(u32 f1, u32 f2) +{ + return (int)(f1 - f2) > 0; +} + +/** * dma_fence_is_later - return if f1 is chronologically later than f2 * @f1: [in] the first fence from the same context * @f2: [in] the second fence from the same context @@ -349,7 +364,7 @@ static inline bool dma_fence_is_later(struct dma_fence *f1, if (WARN_ON(f1->context != f2->context)) return false; - return (int)(f1->seqno - f2->seqno) > 0; + return __dma_fence_is_later(f1->seqno, f2->seqno); } /** @@ -416,8 +431,8 @@ int dma_fence_get_status(struct dma_fence *fence); static inline void dma_fence_set_error(struct dma_fence *fence, int error) { - BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); - BUG_ON(error >= 0 || error < -MAX_ERRNO); + WARN_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); + WARN_ON(error >= 0 || error < -MAX_ERRNO); fence->error = error; } diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4f3eecedca2d..29ce9815da87 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -10,6 +10,7 @@ #include <linux/scatterlist.h> #include <linux/kmemcheck.h> #include <linux/bug.h> +#include <linux/mem_encrypt.h> /** * List of possible attributes associated with a DMA mapping. The semantics @@ -127,7 +128,6 @@ struct dma_map_ops { enum dma_data_direction dir); int (*mapping_error)(struct device *dev, dma_addr_t dma_addr); int (*dma_supported)(struct device *dev, u64 mask); - int (*set_dma_mask)(struct device *dev, u64 mask); #ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK u64 (*get_required_mask)(struct device *dev); #endif @@ -158,16 +158,40 @@ static inline int is_device_dma_capable(struct device *dev) * These three functions are only for dma allocator. * Don't use them in device drivers. */ -int dma_alloc_from_coherent(struct device *dev, ssize_t size, +int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle, void **ret); -int dma_release_from_coherent(struct device *dev, int order, void *vaddr); +int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr); -int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, +int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, size_t size, int *ret); + +void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle); +int dma_release_from_global_coherent(int order, void *vaddr); +int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, + size_t size, int *ret); + #else -#define dma_alloc_from_coherent(dev, size, handle, ret) (0) -#define dma_release_from_coherent(dev, order, vaddr) (0) -#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0) +#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0) +#define dma_release_from_dev_coherent(dev, order, vaddr) (0) +#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0) + +static inline void *dma_alloc_from_global_coherent(ssize_t size, + dma_addr_t *dma_handle) +{ + return NULL; +} + +static inline int dma_release_from_global_coherent(int order, void *vaddr) +{ + return 0; +} + +static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, + void *cpu_addr, size_t size, + int *ret) +{ + return 0; +} #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ #ifdef CONFIG_HAS_DMA @@ -482,7 +506,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, BUG_ON(!ops); - if (dma_alloc_from_coherent(dev, size, dma_handle, &cpu_addr)) + if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) return cpu_addr; if (!arch_dma_alloc_attrs(&dev, &flag)) @@ -504,7 +528,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size, BUG_ON(!ops); WARN_ON(irqs_disabled()); - if (dma_release_from_coherent(dev, get_order(size), cpu_addr)) + if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr)) return; if (!ops->free || !cpu_addr) @@ -526,35 +550,22 @@ static inline void dma_free_coherent(struct device *dev, size_t size, return dma_free_attrs(dev, size, cpu_addr, dma_handle, 0); } -static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - return dma_alloc_attrs(dev, size, dma_handle, gfp, - DMA_ATTR_NON_CONSISTENT); -} + const struct dma_map_ops *ops = get_dma_ops(dev); -static inline void dma_free_noncoherent(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t dma_handle) -{ - dma_free_attrs(dev, size, cpu_addr, dma_handle, - DMA_ATTR_NON_CONSISTENT); + debug_dma_mapping_error(dev, dma_addr); + if (ops->mapping_error) + return ops->mapping_error(dev, dma_addr); + return 0; } -static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +static inline void dma_check_mask(struct device *dev, u64 mask) { - debug_dma_mapping_error(dev, dma_addr); - - if (get_dma_ops(dev)->mapping_error) - return get_dma_ops(dev)->mapping_error(dev, dma_addr); - -#ifdef DMA_ERROR_CODE - return dma_addr == DMA_ERROR_CODE; -#else - return 0; -#endif + if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1))) + dev_warn(dev, "SME is active, device will require DMA bounce buffers\n"); } -#ifndef HAVE_ARCH_DMA_SUPPORTED static inline int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -565,18 +576,15 @@ static inline int dma_supported(struct device *dev, u64 mask) return 1; return ops->dma_supported(dev, mask); } -#endif #ifndef HAVE_ARCH_DMA_SET_MASK static inline int dma_set_mask(struct device *dev, u64 mask) { - const struct dma_map_ops *ops = get_dma_ops(dev); - - if (ops->set_dma_mask) - return ops->set_dma_mask(dev, mask); - if (!dev->dma_mask || !dma_supported(dev, mask)) return -EIO; + + dma_check_mask(dev, mask); + *dev->dma_mask = mask; return 0; } @@ -596,6 +604,9 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask) { if (!dma_supported(dev, mask)) return -EIO; + + dma_check_mask(dev, mask); + dev->coherent_dma_mask = mask; return 0; } @@ -696,10 +707,7 @@ static inline int dma_get_cache_alignment(void) #endif /* flags for the coherent memory api */ -#define DMA_MEMORY_MAP 0x01 -#define DMA_MEMORY_IO 0x02 -#define DMA_MEMORY_INCLUDES_CHILDREN 0x04 -#define DMA_MEMORY_EXCLUSIVE 0x08 +#define DMA_MEMORY_EXCLUSIVE 0x01 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, @@ -712,7 +720,7 @@ static inline int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags) { - return 0; + return -ENOSYS; } static inline void @@ -747,10 +755,9 @@ extern void *dmam_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp); extern void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle); -extern void *dmam_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); -extern void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle); +extern void *dmam_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + unsigned long attrs); #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT extern int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, diff --git a/include/linux/dma/dw.h b/include/linux/dma/dw.h index b63b25814d77..e166cac8e870 100644 --- a/include/linux/dma/dw.h +++ b/include/linux/dma/dw.h @@ -50,25 +50,4 @@ static inline int dw_dma_probe(struct dw_dma_chip *chip) { return -ENODEV; } static inline int dw_dma_remove(struct dw_dma_chip *chip) { return 0; } #endif /* CONFIG_DW_DMAC_CORE */ -/* DMA API extensions */ -struct dw_desc; - -struct dw_cyclic_desc { - struct dw_desc **desc; - unsigned long periods; - void (*period_callback)(void *param); - void *period_callback_param; -}; - -struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan, - dma_addr_t buf_addr, size_t buf_len, size_t period_len, - enum dma_transfer_direction direction); -void dw_dma_cyclic_free(struct dma_chan *chan); -int dw_dma_cyclic_start(struct dma_chan *chan); -void dw_dma_cyclic_stop(struct dma_chan *chan); - -dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan); - -dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan); - #endif /* _DMA_DW_H */ diff --git a/include/linux/dma/qcom_bam_dma.h b/include/linux/dma/qcom_bam_dma.h new file mode 100644 index 000000000000..077d43a358e5 --- /dev/null +++ b/include/linux/dma/qcom_bam_dma.h @@ -0,0 +1,79 @@ +/* + * Copyright (c) 2016-2017, The Linux Foundation. All rights reserved. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _QCOM_BAM_DMA_H +#define _QCOM_BAM_DMA_H + +#include <asm/byteorder.h> + +/* + * This data type corresponds to the native Command Element + * supported by BAM DMA Engine. + * + * @cmd_and_addr - upper 8 bits command and lower 24 bits register address. + * @data - for write command: content to be written into peripheral register. + * for read command: dest addr to write peripheral register value. + * @mask - register mask. + * @reserved - for future usage. + * + */ +struct bam_cmd_element { + __le32 cmd_and_addr; + __le32 data; + __le32 mask; + __le32 reserved; +}; + +/* + * This enum indicates the command type in a command element + */ +enum bam_command_type { + BAM_WRITE_COMMAND = 0, + BAM_READ_COMMAND, +}; + +/* + * prep_bam_ce_le32 - Wrapper function to prepare a single BAM command + * element with the data already in le32 format. + * + * @bam_ce: bam command element + * @addr: target address + * @cmd: BAM command + * @data: actual data for write and dest addr for read in le32 + */ +static inline void +bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, + enum bam_command_type cmd, __le32 data) +{ + bam_ce->cmd_and_addr = + cpu_to_le32((addr & 0xffffff) | ((cmd & 0xff) << 24)); + bam_ce->data = data; + bam_ce->mask = cpu_to_le32(0xffffffff); +} + +/* + * bam_prep_ce - Wrapper function to prepare a single BAM command element + * with the data. + * + * @bam_ce: BAM command element + * @addr: target address + * @cmd: BAM command + * @data: actual data for write and dest addr for read + */ +static inline void +bam_prep_ce(struct bam_cmd_element *bam_ce, u32 addr, + enum bam_command_type cmd, u32 data) +{ + bam_prep_ce_le32(bam_ce, addr, cmd, cpu_to_le32(data)); +} +#endif diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 533680860865..8319101170fc 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -68,7 +68,6 @@ enum dma_transaction_type { DMA_MEMSET, DMA_MEMSET_SG, DMA_INTERRUPT, - DMA_SG, DMA_PRIVATE, DMA_ASYNC_TX, DMA_SLAVE, @@ -186,6 +185,9 @@ struct dma_interleaved_template { * on the result of this operation * @DMA_CTRL_REUSE: client can reuse the descriptor and submit again till * cleared or freed + * @DMA_PREP_CMD: tell the driver that the data passed to DMA API is command + * data and the descriptor should be in different format from normal + * data descriptors. */ enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), @@ -195,6 +197,7 @@ enum dma_ctrl_flags { DMA_PREP_CONTINUE = (1 << 4), DMA_PREP_FENCE = (1 << 5), DMA_CTRL_REUSE = (1 << 6), + DMA_PREP_CMD = (1 << 7), }; /** @@ -771,11 +774,6 @@ struct dma_device { unsigned int nents, int value, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)( struct dma_chan *chan, unsigned long flags); - struct dma_async_tx_descriptor *(*device_prep_dma_sg)( - struct dma_chan *chan, - struct scatterlist *dst_sg, unsigned int dst_nents, - struct scatterlist *src_sg, unsigned int src_nents, - unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_slave_sg)( struct dma_chan *chan, struct scatterlist *sgl, @@ -905,19 +903,6 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( len, flags); } -static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( - struct dma_chan *chan, - struct scatterlist *dst_sg, unsigned int dst_nents, - struct scatterlist *src_sg, unsigned int src_nents, - unsigned long flags) -{ - if (!chan || !chan->device || !chan->device->device_prep_dma_sg) - return NULL; - - return chan->device->device_prep_dma_sg(chan, dst_sg, dst_nents, - src_sg, src_nents, flags); -} - /** * dmaengine_terminate_all() - Terminate all active DMA transfers * @chan: The channel for which to terminate the transfers diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 002611c85318..2d0259327721 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -51,7 +51,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.7" +#define REL_VERSION "8.4.10" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h index 2896f93808ae..4e6d4d4c7056 100644 --- a/include/linux/drbd_genl.h +++ b/include/linux/drbd_genl.h @@ -132,7 +132,8 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf, __flg_field_def(18, DRBD_GENLA_F_MANDATORY, disk_drain, DRBD_DISK_DRAIN_DEF) __flg_field_def(19, DRBD_GENLA_F_MANDATORY, md_flushes, DRBD_MD_FLUSHES_DEF) __flg_field_def(23, 0 /* OPTIONAL */, al_updates, DRBD_AL_UPDATES_DEF) - __flg_field_def(24, 0 /* OPTIONAL */, discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED) + __flg_field_def(24, 0 /* OPTIONAL */, discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF) + __flg_field_def(26, 0 /* OPTIONAL */, disable_write_same, DRBD_DISABLE_WRITE_SAME_DEF) ) GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts, diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index ddac68422a96..24ae1b9b76c7 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -209,12 +209,18 @@ #define DRBD_MD_FLUSHES_DEF 1 #define DRBD_TCP_CORK_DEF 1 #define DRBD_AL_UPDATES_DEF 1 + /* We used to ignore the discard_zeroes_data setting. * To not change established (and expected) behaviour, * by default assume that, for discard_zeroes_data=0, * we can make that an effective discard_zeroes_data=1, * if we only explicitly zero-out unaligned partial chunks. */ -#define DRBD_DISCARD_ZEROES_IF_ALIGNED 1 +#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1 + +/* Some backends pretend to support WRITE SAME, + * but fail such requests when they are actually submitted. + * This is to tell DRBD to not even try. */ +#define DRBD_DISABLE_WRITE_SAME_DEF 0 #define DRBD_ALLOW_TWO_PRIMARIES_DEF 0 #define DRBD_ALWAYS_ASBP_DEF 0 diff --git a/include/linux/edac.h b/include/linux/edac.h index 8ae0f45fafd6..cd75c173fd00 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -619,7 +619,6 @@ struct mem_ctl_info { */ struct device *pdev; const char *mod_name; - const char *mod_ver; const char *ctl_name; const char *dev_name; void *pvt_info; diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h index 885f587a3555..915898759280 100644 --- a/include/linux/eeprom_93xx46.h +++ b/include/linux/eeprom_93xx46.h @@ -2,8 +2,7 @@ * Module: eeprom_93xx46 * platform description for 93xx46 EEPROMs. */ - -struct gpio_desc; +#include <linux/gpio/consumer.h> struct eeprom_93xx46_platform_data { unsigned char flags; diff --git a/include/linux/efi.h b/include/linux/efi.h index ec36f42a2add..66f4a4e79f4b 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -47,10 +47,10 @@ typedef u16 efi_char16_t; /* UNICODE character */ typedef u64 efi_physical_addr_t; typedef void *efi_handle_t; -typedef uuid_le efi_guid_t; +typedef guid_t efi_guid_t; #define EFI_GUID(a,b,c,d0,d1,d2,d3,d4,d5,d6,d7) \ - UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) + GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) /* * Generic EFI table header @@ -137,6 +137,18 @@ struct efi_boot_memmap { #define EFI_CAPSULE_POPULATE_SYSTEM_TABLE 0x00020000 #define EFI_CAPSULE_INITIATE_RESET 0x00040000 +struct capsule_info { + efi_capsule_header_t header; + int reset_type; + long index; + size_t count; + size_t total_size; + phys_addr_t *pages; + size_t page_bytes_remain; +}; + +int __efi_capsule_setup_info(struct capsule_info *cap_info); + /* * Allocation types for calls to boottime->allocate_pages. */ @@ -973,7 +985,7 @@ static inline void efi_esrt_init(void) { } extern int efi_config_parse_tables(void *config_tables, int count, int sz, efi_config_table_type_t *arch_tables); extern u64 efi_get_iobase (void); -extern u32 efi_mem_type (unsigned long phys_addr); +extern int efi_mem_type(unsigned long phys_addr); extern u64 efi_mem_attributes (unsigned long phys_addr); extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); @@ -1008,6 +1020,28 @@ extern int efi_memattr_init(void); extern int efi_memattr_apply_permissions(struct mm_struct *mm, efi_memattr_perm_setter fn); +/* + * efi_early_memdesc_ptr - get the n-th EFI memmap descriptor + * @map: the start of efi memmap + * @desc_size: the size of space for each EFI memmap descriptor + * @n: the index of efi memmap descriptor + * + * EFI boot service provides the GetMemoryMap() function to get a copy of the + * current memory map which is an array of memory descriptors, each of + * which describes a contiguous block of memory. It also gets the size of the + * map, and the size of each descriptor, etc. + * + * Note that per section 6.2 of UEFI Spec 2.6 Errata A, the returned size of + * each descriptor might not be equal to sizeof(efi_memory_memdesc_t), + * since efi_memory_memdesc_t may be extended in the future. Thus the OS + * MUST use the returned size of the descriptor to find the start of each + * efi_memory_memdesc_t in the memory map array. This should only be used + * during bootup since for_each_efi_memory_desc_xxx() is available after the + * kernel initializes the EFI subsystem to set up struct efi_memory_map. + */ +#define efi_early_memdesc_ptr(map, desc_size, n) \ + (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size))) + /* Iterate through an efi_memory_map */ #define for_each_efi_memory_desc_in_map(m, md) \ for ((md) = (m)->map; \ @@ -1079,6 +1113,8 @@ static inline bool efi_enabled(int feature) return test_bit(feature, &efi.flags) != 0; } extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); + +extern bool efi_is_table_address(unsigned long phys_addr); #else static inline bool efi_enabled(int feature) { @@ -1092,6 +1128,11 @@ efi_capsule_pending(int *reset_type) { return false; } + +static inline bool efi_is_table_address(unsigned long phys_addr) +{ + return false; +} #endif extern int efi_status_to_err(efi_status_t status); @@ -1403,7 +1444,7 @@ extern int efi_capsule_supported(efi_guid_t guid, u32 flags, size_t size, int *reset); extern int efi_capsule_update(efi_capsule_header_t *capsule, - struct page **pages); + phys_addr_t *pages); #ifdef CONFIG_EFI_RUNTIME_MAP int efi_runtime_map_init(struct kobject *); @@ -1485,6 +1526,13 @@ enum efi_secureboot_mode { }; enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table); +#ifdef CONFIG_RESET_ATTACK_MITIGATION +void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg); +#else +static inline void +efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg) { } +#endif + /* * Arch code can implement the following three template macros, avoiding * reptition for the void/non-void return cases of {__,}efi_call_virt(): @@ -1545,6 +1593,8 @@ efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table, void *priv, efi_exit_boot_map_processing priv_func); +#define EFI_RANDOM_SEED_SIZE 64U + struct linux_efi_random_seed { u32 size; u8 bits[]; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 0e306c5a86d6..5bc8f8682a3e 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -104,8 +104,9 @@ struct elevator_mq_ops { int (*request_merge)(struct request_queue *q, struct request **, struct bio *); void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); - struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *); - void (*put_request)(struct request *); + void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); + void (*prepare_request)(struct request *, struct bio *bio); + void (*finish_request)(struct request *); void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); bool (*has_work)(struct blk_mq_hw_ctx *); @@ -114,8 +115,6 @@ struct elevator_mq_ops { void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); struct request *(*next_request)(struct request_queue *, struct request *); - int (*get_rq_priv)(struct request_queue *, struct request *, struct bio *); - void (*put_rq_priv)(struct request_queue *, struct request *); void (*init_icq)(struct io_cq *); void (*exit_icq)(struct io_cq *); }; diff --git a/include/linux/errseq.h b/include/linux/errseq.h new file mode 100644 index 000000000000..f746bd8fe4d0 --- /dev/null +++ b/include/linux/errseq.h @@ -0,0 +1,13 @@ +/* + * See Documentation/errseq.rst and lib/errseq.c + */ +#ifndef _LINUX_ERRSEQ_H +#define _LINUX_ERRSEQ_H + +typedef u32 errseq_t; + +errseq_t errseq_set(errseq_t *eseq, int err); +errseq_t errseq_sample(errseq_t *eseq); +int errseq_check(errseq_t *eseq, errseq_t since); +int errseq_check_and_advance(errseq_t *eseq, errseq_t *since); +#endif diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 83cc9863444b..4587a4c36923 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -137,6 +137,17 @@ struct ethtool_link_ksettings { __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) /** + * ethtool_link_ksettings_del_link_mode - clear bit in link_ksettings + * link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + */ +#define ethtool_link_ksettings_del_link_mode(ptr, name, mode) \ + __clear_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +/** * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask * @ptr : pointer to struct ethtool_link_ksettings * @name : one of supported/advertising/lp_advertising @@ -374,5 +385,9 @@ struct ethtool_ops { struct ethtool_link_ksettings *); int (*set_link_ksettings)(struct net_device *, const struct ethtool_link_ksettings *); + int (*get_fecparam)(struct net_device *, + struct ethtool_fecparam *); + int (*set_fecparam)(struct net_device *, + struct ethtool_fecparam *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index ff0b981f078e..9e4befd95bc7 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -37,7 +37,7 @@ struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt); -int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait, +int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); #else /* CONFIG_EVENTFD */ @@ -73,7 +73,7 @@ static inline ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, } static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, - wait_queue_t *wait, __u64 *cnt) + wait_queue_entry_t *wait, __u64 *cnt) { return -ENOSYS; } diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 6daf6d4971f6..2f14ac73d01d 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,6 +14,7 @@ #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> +#include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ @@ -22,6 +23,10 @@ struct file; #ifdef CONFIG_EPOLL +#ifdef CONFIG_CHECKPOINT_RESTORE +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); +#endif + /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { diff --git a/include/linux/extable.h b/include/linux/extable.h index 7effea4b257d..28addad0dda7 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -2,13 +2,14 @@ #define _LINUX_EXTABLE_H #include <linux/stddef.h> /* for NULL */ +#include <linux/types.h> struct module; struct exception_table_entry; const struct exception_table_entry * -search_extable(const struct exception_table_entry *first, - const struct exception_table_entry *last, +search_extable(const struct exception_table_entry *base, + const size_t num, unsigned long value); void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish); diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 7e206a9f88db..744d60ca80c3 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -1,5 +1,5 @@ /* - * External connector (extcon) class driver + * External Connector (extcon) framework * * Copyright (C) 2015 Samsung Electronics * Author: Chanwoo Choi <cw00.choi@samsung.com> @@ -20,8 +20,7 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * -*/ + */ #ifndef __LINUX_EXTCON_H__ #define __LINUX_EXTCON_H__ @@ -93,7 +92,7 @@ #define EXTCON_NUM 63 /* - * Define the property of supported external connectors. + * Define the properties of supported external connectors. * * When adding the new extcon property, they *must* have * the type/value/default information. Also, you *have to* @@ -176,44 +175,42 @@ struct extcon_dev; #if IS_ENABLED(CONFIG_EXTCON) -/* - * Following APIs are for notifiers or configurations. - * Notifiers are the external port and connection devices. - */ +/* Following APIs register/unregister the extcon device. */ extern int extcon_dev_register(struct extcon_dev *edev); extern void extcon_dev_unregister(struct extcon_dev *edev); extern int devm_extcon_dev_register(struct device *dev, - struct extcon_dev *edev); + struct extcon_dev *edev); extern void devm_extcon_dev_unregister(struct device *dev, - struct extcon_dev *edev); -extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); + struct extcon_dev *edev); -/* - * Following APIs control the memory of extcon device. - */ +/* Following APIs allocate/free the memory of the extcon device. */ extern struct extcon_dev *extcon_dev_allocate(const unsigned int *cable); extern void extcon_dev_free(struct extcon_dev *edev); extern struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const unsigned int *cable); + const unsigned int *cable); extern void devm_extcon_dev_free(struct device *dev, struct extcon_dev *edev); +/* Synchronize the state and property value for each external connector. */ +extern int extcon_sync(struct extcon_dev *edev, unsigned int id); + /* - * get/set_state access each bit of the 32b encoded state value. - * They are used to access the status of each cable based on the cable id. + * Following APIs get/set the connected state of each external connector. + * The 'id' argument indicates the defined external connector. */ extern int extcon_get_state(struct extcon_dev *edev, unsigned int id); extern int extcon_set_state(struct extcon_dev *edev, unsigned int id, - bool cable_state); + bool state); extern int extcon_set_state_sync(struct extcon_dev *edev, unsigned int id, - bool cable_state); -/* - * Synchronize the state and property data for a specific external connector. - */ -extern int extcon_sync(struct extcon_dev *edev, unsigned int id); + bool state); /* - * get/set_property access the property value of each external connector. - * They are used to access the property of each cable based on the property id. + * Following APIs get/set the property of each external connector. + * The 'id' argument indicates the defined external connector + * and the 'prop' indicates the extcon property. + * + * And extcon_get/set_property_capability() set the capability of the property + * for each external connector. They are used to set the capability of the + * property of each external connector based on the id and property. */ extern int extcon_get_property(struct extcon_dev *edev, unsigned int id, unsigned int prop, @@ -224,28 +221,24 @@ extern int extcon_set_property(struct extcon_dev *edev, unsigned int id, extern int extcon_set_property_sync(struct extcon_dev *edev, unsigned int id, unsigned int prop, union extcon_property_value prop_val); - -/* - * get/set_property_capability set the capability of the property for each - * external connector. They are used to set the capability of the property - * of each external connector based on the id and property. - */ extern int extcon_get_property_capability(struct extcon_dev *edev, unsigned int id, unsigned int prop); extern int extcon_set_property_capability(struct extcon_dev *edev, unsigned int id, unsigned int prop); /* - * Following APIs are to monitor the status change of the external connectors. + * Following APIs register the notifier block in order to detect + * the change of both state and property value for each external connector. + * * extcon_register_notifier(*edev, id, *nb) : Register a notifier block * for specific external connector of the extcon. * extcon_register_notifier_all(*edev, *nb) : Register a notifier block * for all supported external connectors of the extcon. */ extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, - struct notifier_block *nb); + struct notifier_block *nb); extern int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id, - struct notifier_block *nb); + struct notifier_block *nb); extern int devm_extcon_register_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); @@ -265,16 +258,15 @@ extern void devm_extcon_unregister_notifier_all(struct device *dev, struct notifier_block *nb); /* - * Following API get the extcon device from devicetree. - * This function use phandle of devicetree to get extcon device directly. + * Following APIs get the extcon_dev from devicetree or by through extcon name. */ +extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index); -/* Following API to get information of extcon device */ +/* Following API get the name of extcon device. */ extern const char *extcon_get_edev_name(struct extcon_dev *edev); - #else /* CONFIG_EXTCON */ static inline int extcon_dev_register(struct extcon_dev *edev) { @@ -284,13 +276,13 @@ static inline int extcon_dev_register(struct extcon_dev *edev) static inline void extcon_dev_unregister(struct extcon_dev *edev) { } static inline int devm_extcon_dev_register(struct device *dev, - struct extcon_dev *edev) + struct extcon_dev *edev) { return -EINVAL; } static inline void devm_extcon_dev_unregister(struct device *dev, - struct extcon_dev *edev) { } + struct extcon_dev *edev) { } static inline struct extcon_dev *extcon_dev_allocate(const unsigned int *cable) { @@ -300,7 +292,7 @@ static inline struct extcon_dev *extcon_dev_allocate(const unsigned int *cable) static inline void extcon_dev_free(struct extcon_dev *edev) { } static inline struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const unsigned int *cable) + const unsigned int *cable) { return ERR_PTR(-ENOSYS); } @@ -314,13 +306,13 @@ static inline int extcon_get_state(struct extcon_dev *edev, unsigned int id) } static inline int extcon_set_state(struct extcon_dev *edev, unsigned int id, - bool cable_state) + bool state) { return 0; } static inline int extcon_set_state_sync(struct extcon_dev *edev, unsigned int id, - bool cable_state) + bool state) { return 0; } @@ -331,52 +323,45 @@ static inline int extcon_sync(struct extcon_dev *edev, unsigned int id) } static inline int extcon_get_property(struct extcon_dev *edev, unsigned int id, - unsigned int prop, - union extcon_property_value *prop_val) + unsigned int prop, + union extcon_property_value *prop_val) { return 0; } static inline int extcon_set_property(struct extcon_dev *edev, unsigned int id, - unsigned int prop, - union extcon_property_value prop_val) + unsigned int prop, + union extcon_property_value prop_val) { return 0; } static inline int extcon_set_property_sync(struct extcon_dev *edev, - unsigned int id, unsigned int prop, - union extcon_property_value prop_val) + unsigned int id, unsigned int prop, + union extcon_property_value prop_val) { return 0; } static inline int extcon_get_property_capability(struct extcon_dev *edev, - unsigned int id, unsigned int prop) + unsigned int id, unsigned int prop) { return 0; } static inline int extcon_set_property_capability(struct extcon_dev *edev, - unsigned int id, unsigned int prop) + unsigned int id, unsigned int prop) { return 0; } -static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) -{ - return NULL; -} - static inline int extcon_register_notifier(struct extcon_dev *edev, - unsigned int id, - struct notifier_block *nb) + unsigned int id, struct notifier_block *nb) { return 0; } static inline int extcon_unregister_notifier(struct extcon_dev *edev, - unsigned int id, - struct notifier_block *nb) + unsigned int id, struct notifier_block *nb) { return 0; } @@ -392,8 +377,13 @@ static inline void devm_extcon_unregister_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb) { } +static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) +{ + return ERR_PTR(-ENODEV); +} + static inline struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, - int index) + int index) { return ERR_PTR(-ENODEV); } @@ -411,26 +401,14 @@ struct extcon_specific_cable_nb { }; static inline int extcon_register_interest(struct extcon_specific_cable_nb *obj, - const char *extcon_name, const char *cable_name, - struct notifier_block *nb) + const char *extcon_name, const char *cable_name, + struct notifier_block *nb) { return -EINVAL; } -static inline int extcon_unregister_interest(struct extcon_specific_cable_nb - *obj) +static inline int extcon_unregister_interest(struct extcon_specific_cable_nb *obj) { return -EINVAL; } - -static inline int extcon_get_cable_state_(struct extcon_dev *edev, unsigned int id) -{ - return extcon_get_state(edev, id); -} - -static inline int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id, - bool cable_state) -{ - return extcon_set_state_sync(edev, id, cable_state); -} #endif /* __LINUX_EXTCON_H__ */ diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index b6feed6547ce..2a0c453d7235 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -186,6 +186,8 @@ struct f2fs_extent { #define F2FS_NAME_LEN 255 #define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */ #define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ +#define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \ + get_extra_isize(inode)) #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ #define ADDRS_PER_INODE(inode) addrs_per_inode(inode) #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ @@ -205,9 +207,7 @@ struct f2fs_extent { #define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */ #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ #define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ - -#define MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \ - F2FS_INLINE_XATTR_ADDRS - 1)) +#define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */ struct f2fs_inode { __le16 i_mode; /* file mode */ @@ -235,8 +235,16 @@ struct f2fs_inode { struct f2fs_extent i_ext; /* caching a largest extent */ - __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ - + union { + struct { + __le16 i_extra_isize; /* extra inode attribute size */ + __le16 i_padding; /* padding */ + __le32 i_projid; /* project id */ + __le32 i_inode_checksum;/* inode meta checksum */ + __le32 i_extra_end[0]; /* for attribute size calculation */ + }; + __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ + }; __le32 i_nid[DEF_NIDS_PER_INODE]; /* direct(2), indirect(2), double_indirect(1) node id */ } __packed; @@ -465,7 +473,7 @@ typedef __le32 f2fs_hash_t; #define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) /* - * space utilization of regular dentry and inline dentry + * space utilization of regular dentry and inline dentry (w/o extra reservation) * regular dentry inline dentry * bitmap 1 * 27 = 27 1 * 23 = 23 * reserved 1 * 3 = 3 1 * 7 = 7 @@ -501,24 +509,6 @@ struct f2fs_dentry_block { __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; -/* for inline dir */ -#define NR_INLINE_DENTRY (MAX_INLINE_DATA * BITS_PER_BYTE / \ - ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ - BITS_PER_BYTE + 1)) -#define INLINE_DENTRY_BITMAP_SIZE ((NR_INLINE_DENTRY + \ - BITS_PER_BYTE - 1) / BITS_PER_BYTE) -#define INLINE_RESERVED_SIZE (MAX_INLINE_DATA - \ - ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ - NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE)) - -/* inline directory entry structure */ -struct f2fs_inline_dentry { - __u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE]; - __u8 reserved[INLINE_RESERVED_SIZE]; - struct f2fs_dir_entry dentry[NR_INLINE_DENTRY]; - __u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN]; -} __packed; - /* file types used in inode_info->flags */ enum { F2FS_FT_UNKNOWN, @@ -534,4 +524,6 @@ enum { #define S_SHIFT 12 +#define F2FS_DEF_PROJID 0 /* default project ID */ + #endif /* _LINUX_F2FS_FS_H */ diff --git a/include/linux/fb.h b/include/linux/fb.h index a964d076b4dc..f4386b0ccf40 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -400,7 +400,7 @@ struct fb_tile_ops { #endif /* CONFIG_FB_TILEBLITTING */ /* FBINFO_* = fb_info.flags bit flags */ -#define FBINFO_MODULE 0x0001 /* Low-level driver is a module */ +#define FBINFO_DEFAULT 0 #define FBINFO_HWACCEL_DISABLED 0x0002 /* When FBINFO_HWACCEL_DISABLED is set: * Hardware acceleration is turned off. Software implementations @@ -533,14 +533,6 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { return a; } -#ifdef MODULE -#define FBINFO_DEFAULT FBINFO_MODULE -#else -#define FBINFO_DEFAULT 0 -#endif - -// This will go away -#define FBINFO_FLAG_MODULE FBINFO_MODULE #define FBINFO_FLAG_DEFAULT FBINFO_DEFAULT /* This will go away diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h new file mode 100644 index 000000000000..f68a7db14165 --- /dev/null +++ b/include/linux/fbcon.h @@ -0,0 +1,12 @@ +#ifndef _LINUX_FBCON_H +#define _LINUX_FBCON_H + +#ifdef CONFIG_FRAMEBUFFER_CONSOLE +void __init fb_console_init(void); +void __exit fb_console_exit(void); +#else +static inline void fb_console_init(void) {} +static inline void fb_console_exit(void) {} +#endif + +#endif /* _LINUX_FBCON_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 62d948f80730..d29e58fde364 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -16,13 +16,10 @@ #include <linux/sched.h> #include <linux/capability.h> #include <linux/cryptohash.h> +#include <linux/set_memory.h> #include <net/sch_generic.h> -#ifdef CONFIG_ARCH_HAS_SET_MEMORY -#include <asm/set_memory.h> -#endif - #include <uapi/linux/filter.h> #include <uapi/linux/bpf.h> @@ -57,6 +54,9 @@ struct bpf_prog_aux; #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_JIT_REG (MAX_BPF_REG + 1) +/* unused opcode to mark special call to bpf_tail_call() helper */ +#define BPF_TAIL_CALL 0xf0 + /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. @@ -66,8 +66,6 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 -#define BPF_TAG_SIZE 8 - /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -336,6 +334,22 @@ struct bpf_prog_aux; bpf_size; \ }) +#define bpf_size_to_bytes(bpf_size) \ +({ \ + int bytes = -EINVAL; \ + \ + if (bpf_size == BPF_B) \ + bytes = sizeof(u8); \ + else if (bpf_size == BPF_H) \ + bytes = sizeof(u16); \ + else if (bpf_size == BPF_W) \ + bytes = sizeof(u32); \ + else if (bpf_size == BPF_DW) \ + bytes = sizeof(u64); \ + \ + bytes; \ +}) + #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ @@ -350,6 +364,13 @@ struct bpf_prog_aux; __size; \ }) +#define BPF_LDST_BYTES(insn) \ + ({ \ + const int __size = bpf_size_to_bytes(BPF_SIZE(insn->code)); \ + WARN_ON(__size < 0); \ + __size; \ + }) + #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) @@ -400,6 +421,18 @@ struct bpf_prog_aux; #define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) +#define bpf_ctx_range(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 +#define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ + offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 + +#define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ + ({ \ + BUILD_BUG_ON(FIELD_SIZEOF(TYPE, MEMBER) != (SIZE)); \ + *(PTR_SIZE) = (SIZE); \ + offsetof(TYPE, MEMBER); \ + }) + #ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { @@ -429,6 +462,7 @@ struct bpf_prog { kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ + u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ @@ -562,6 +596,18 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) return prog->type == BPF_PROG_TYPE_UNSPEC; } +static inline bool +bpf_ctx_narrow_access_ok(u32 off, u32 size, const u32 size_default) +{ + bool off_ok; +#ifdef __LITTLE_ENDIAN + off_ok = (off & (size_default - 1)) == 0; +#else + off_ok = (off & (size_default - 1)) + size == size_default; +#endif + return off_ok && size <= size_default && (size & (size - 1)) == 0; +} + #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) #ifdef CONFIG_ARCH_HAS_SET_MEMORY @@ -665,7 +711,24 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); + +/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the + * same cpu context. Further for best results no more than a single map + * for the do_redirect/do_flush pair should be used. This limitation is + * because we only track one map and force a flush when the map changes. + * This does not appear to be a real limitation for existing software. + */ +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *prog); +int xdp_do_redirect(struct net_device *dev, + struct xdp_buff *xdp, + struct bpf_prog *prog); +void xdp_do_flush_map(void); + void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_redirect(u32 ifindex); + +struct sock *do_sk_redirect_map(void); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; @@ -896,4 +959,13 @@ static inline int bpf_tell_extensions(void) return SKF_AD_MAX; } +struct bpf_sock_ops_kern { + struct sock *sk; + u32 op; + union { + u32 reply; + u32 replylong[4]; + }; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/flat.h b/include/linux/flat.h index 2c1eb15c4ba4..7d542dfd0def 100644 --- a/include/linux/flat.h +++ b/include/linux/flat.h @@ -9,8 +9,8 @@ #ifndef _LINUX_FLAT_H #define _LINUX_FLAT_H -#include <asm/flat.h> #include <uapi/linux/flat.h> +#include <asm/flat.h> /* * While it would be nice to keep this header clean, users of older diff --git a/include/linux/fmc.h b/include/linux/fmc.h index a5f0aa5c2a8d..3dc8a1b2db7b 100644 --- a/include/linux/fmc.h +++ b/include/linux/fmc.h @@ -132,6 +132,8 @@ struct fmc_operations { uint32_t (*read32)(struct fmc_device *fmc, int offset); void (*write32)(struct fmc_device *fmc, uint32_t value, int offset); int (*validate)(struct fmc_device *fmc, struct fmc_driver *drv); + int (*reprogram_raw)(struct fmc_device *f, struct fmc_driver *d, + void *gw, unsigned long len); int (*reprogram)(struct fmc_device *f, struct fmc_driver *d, char *gw); int (*irq_request)(struct fmc_device *fmc, irq_handler_t h, char *name, int flags); @@ -144,6 +146,8 @@ struct fmc_operations { }; /* Prefer this helper rather than calling of fmc->reprogram directly */ +int fmc_reprogram_raw(struct fmc_device *fmc, struct fmc_driver *d, + void *gw, unsigned long len, int sdb_entry); extern int fmc_reprogram(struct fmc_device *f, struct fmc_driver *d, char *gw, int sdb_entry); @@ -180,6 +184,9 @@ struct fmc_device { uint32_t device_id; /* Filled by the device */ char *mezzanine_name; /* Defaults to ``fmc'' */ void *mezzanine_data; + + struct dentry *dbg_dir; + struct dentry *dbg_sdb_dump; }; #define to_fmc_device(x) container_of((x), struct fmc_device, dev) @@ -217,14 +224,23 @@ static inline void fmc_set_drvdata(struct fmc_device *fmc, void *data) dev_set_drvdata(&fmc->dev, data); } -/* The 4 access points */ +struct fmc_gateware { + void *bitstream; + unsigned long len; +}; + +/* The 5 access points */ extern int fmc_driver_register(struct fmc_driver *drv); extern void fmc_driver_unregister(struct fmc_driver *drv); extern int fmc_device_register(struct fmc_device *tdev); +extern int fmc_device_register_gw(struct fmc_device *tdev, + struct fmc_gateware *gw); extern void fmc_device_unregister(struct fmc_device *tdev); -/* Two more for device sets, all driven by the same FPGA */ +/* Three more for device sets, all driven by the same FPGA */ extern int fmc_device_register_n(struct fmc_device **devs, int n); +extern int fmc_device_register_n_gw(struct fmc_device **devs, int n, + struct fmc_gateware *gw); extern void fmc_device_unregister_n(struct fmc_device **devs, int n); /* Internal cross-calls between files; not exported to other modules */ @@ -232,6 +248,23 @@ extern int fmc_match(struct device *dev, struct device_driver *drv); extern int fmc_fill_id_info(struct fmc_device *fmc); extern void fmc_free_id_info(struct fmc_device *fmc); extern void fmc_dump_eeprom(const struct fmc_device *fmc); -extern void fmc_dump_sdb(const struct fmc_device *fmc); + +/* helpers for FMC operations */ +extern int fmc_irq_request(struct fmc_device *fmc, irq_handler_t h, + char *name, int flags); +extern void fmc_irq_free(struct fmc_device *fmc); +extern void fmc_irq_ack(struct fmc_device *fmc); +extern int fmc_validate(struct fmc_device *fmc, struct fmc_driver *drv); +extern int fmc_gpio_config(struct fmc_device *fmc, struct fmc_gpio *gpio, + int ngpio); +extern int fmc_read_ee(struct fmc_device *fmc, int pos, void *d, int l); +extern int fmc_write_ee(struct fmc_device *fmc, int pos, const void *d, int l); + +/* helpers for FMC operations */ +extern int fmc_irq_request(struct fmc_device *fmc, irq_handler_t h, + char *name, int flags); +extern void fmc_irq_free(struct fmc_device *fmc); +extern void fmc_irq_ack(struct fmc_device *fmc); +extern int fmc_validate(struct fmc_device *fmc, struct fmc_driver *drv); #endif /* __LINUX_FMC_H__ */ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index b4ac24c4411d..bfa14bc023fb 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -67,10 +67,14 @@ enum fpga_mgr_states { * FPGA Manager flags * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported * FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting + * FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first + * FPGA_MGR_COMPRESSED_BITSTREAM: FPGA bitstream is compressed */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) #define FPGA_MGR_EXTERNAL_CONFIG BIT(1) #define FPGA_MGR_ENCRYPTED_BITSTREAM BIT(2) +#define FPGA_MGR_BITSTREAM_LSB_FIRST BIT(3) +#define FPGA_MGR_COMPRESSED_BITSTREAM BIT(4) /** * struct fpga_image_info - information specific to a FPGA image diff --git a/include/linux/fs.h b/include/linux/fs.h index 803e5a9b2654..339e73742e73 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,7 +2,7 @@ #define _LINUX_FS_H #include <linux/linkage.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> @@ -18,8 +18,10 @@ #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> +#include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> +#include <linux/fcntl.h> #include <linux/fiemap.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> @@ -30,6 +32,8 @@ #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> +#include <linux/uuid.h> +#include <linux/errseq.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -68,6 +72,8 @@ extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; +typedef __kernel_rwf_t rwf_t; + struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); @@ -142,6 +148,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +/* File is capable of returning -EAGAIN if I/O will block */ +#define FMODE_NOWAIT ((__force fmode_t)0x8000000) + /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are @@ -261,6 +270,18 @@ struct page; struct address_space; struct writeback_control; +/* + * Write life time hint values. + */ +enum rw_hint { + WRITE_LIFE_NOT_SET = 0, + WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, + WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, + WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, + WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, + WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, +}; + #define IOCB_EVENTFD (1 << 0) #define IOCB_APPEND (1 << 1) #define IOCB_DIRECT (1 << 2) @@ -268,6 +289,7 @@ struct writeback_control; #define IOCB_DSYNC (1 << 4) #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) +#define IOCB_NOWAIT (1 << 7) struct kiocb { struct file *ki_filp; @@ -275,23 +297,14 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; -}; + enum rw_hint ki_hint; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } -static inline int iocb_flags(struct file *file); - -static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) -{ - *kiocb = (struct kiocb) { - .ki_filp = filp, - .ki_flags = iocb_flags(filp), - }; -} - /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet @@ -379,7 +392,7 @@ struct address_space { struct radix_tree_root page_tree; /* radix tree of all pages */ spinlock_t tree_lock; /* and lock protecting it */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ - struct rb_root i_mmap; /* tree of private and shared mappings */ + struct rb_root_cached i_mmap; /* tree of private and shared mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ @@ -392,7 +405,8 @@ struct address_space { gfp_t gfp_mask; /* implicit gfp mask for allocations */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ -} __attribute__((aligned(sizeof(long)))); + errseq_t wb_err; +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -415,6 +429,7 @@ struct block_device { #endif struct block_device * bd_contains; unsigned bd_block_size; + u8 bd_partno; struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; @@ -435,7 +450,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -472,7 +487,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) */ static inline int mapping_mapped(struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap); + return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* @@ -592,6 +607,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; unsigned int i_blkbits; + enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED @@ -653,7 +669,7 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { @@ -846,6 +862,7 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; + enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -868,7 +885,9 @@ struct file { struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ + errseq_t f_wb_err; +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -891,9 +910,9 @@ static inline struct file *get_file(struct file *f) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 -#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) +#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 @@ -984,7 +1003,6 @@ struct file_lock { unsigned char fl_type; unsigned int fl_pid; int fl_link_cpu; /* what cpu's list is this on? */ - struct pid *fl_nspid; wait_queue_head_t fl_wait; struct file *fl_file; loff_t fl_start; @@ -1005,7 +1023,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1021,8 +1039,6 @@ struct file_lock_context { #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif -#include <linux/fcntl.h> - extern void send_sigio(struct fown_struct *fown, int fd, int band); /* @@ -1038,14 +1054,14 @@ static inline struct inode *locks_inode(const struct file *f) } #ifdef CONFIG_FILE_LOCKING -extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *); +extern int fcntl_getlk(struct file *, unsigned int, struct flock *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, - struct flock __user *); + struct flock *); #if BITS_PER_LONG == 32 -extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *); +extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, - struct flock64 __user *); + struct flock64 *); #endif extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); @@ -1219,7 +1235,7 @@ static inline struct inode *file_inode(const struct file *f) static inline struct dentry *file_dentry(const struct file *file) { - return d_real(file->f_path.dentry, file_inode(file), 0); + return d_real(file->f_path.dentry, file_inode(file), 0, 0); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) @@ -1249,12 +1265,37 @@ extern void fasync_free(struct fasync_struct *); extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); -extern void f_setown(struct file *filp, unsigned long arg, int force); +extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); -struct mm_struct; +/* + * sb->s_flags. Note that these mirror the equivalent MS_* flags where + * represented in both. + */ +#define SB_RDONLY 1 /* Mount read-only */ +#define SB_NOSUID 2 /* Ignore suid and sgid bits */ +#define SB_NODEV 4 /* Disallow access to device special files */ +#define SB_NOEXEC 8 /* Disallow program execution */ +#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ +#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ +#define SB_NOATIME 1024 /* Do not update access times. */ +#define SB_NODIRATIME 2048 /* Do not update directory access times */ +#define SB_SILENT 32768 +#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define SB_I_VERSION (1<<23) /* Update inode I_version field */ +#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define SB_SUBMOUNT (1<<26) +#define SB_NOREMOTELOCK (1<<27) +#define SB_NOSEC (1<<28) +#define SB_BORN (1<<29) +#define SB_ACTIVE (1<<30) +#define SB_NOUSER (1<<31) /* * Umount options @@ -1328,8 +1369,8 @@ struct super_block { struct sb_writers s_writers; - char s_id[32]; /* Informational name */ - u8 s_uuid[16]; /* UUID */ + char s_id[32]; /* Informational name */ + uuid_t s_uuid; /* UUID */ void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; @@ -1351,11 +1392,6 @@ struct super_block { */ char *s_subtype; - /* - * Saved mount options for lazy filesystems using - * generic_show_options() - */ - char __rcu *s_options; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* @@ -1404,7 +1440,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1690,7 +1726,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); @@ -1739,25 +1775,16 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma) return file->f_op->mmap(file, vma); } -static inline int call_fsync(struct file *file, loff_t start, loff_t end, - int datasync) -{ - return file->f_op->fsync(file, start, end, datasync); -} - ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, struct iovec **ret_pointer); extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); -extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); -extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, @@ -1833,7 +1860,7 @@ struct super_operations { * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * - * Exception: MS_RDONLY is always applied to the entire file system. + * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their @@ -1842,19 +1869,20 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY) -#define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \ +static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & MS_RDONLY; } +#define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) +#define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) -#define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \ +#define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) -#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK) -#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME) -#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION) +#define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) +#define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) +#define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) -#define IS_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL) +#define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) @@ -1873,6 +1901,25 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); } +static inline enum rw_hint file_write_hint(struct file *file) +{ + if (file->f_write_hint != WRITE_LIFE_NOT_SET) + return file->f_write_hint; + + return file_inode(file)->i_write_hint; +} + +static inline int iocb_flags(struct file *file); + +static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + .ki_flags = iocb_flags(filp), + .ki_hint = file_write_hint(filp), + }; +} + /* * Inode state bits. Protected by inode->i_lock * @@ -1929,6 +1976,9 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) * wb stat updates to grab mapping->tree_lock. See * inode_switch_wb_work_fn() for details. * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1949,6 +1999,7 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) +#define I_OVL_INUSE (1 << 14) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) @@ -2152,7 +2203,7 @@ static inline int __mandatory_lock(struct inode *ino) } /* - * ... and these candidates should be on MS_MANDLOCK mounted fs, + * ... and these candidates should be on SB_MANDLOCK mounted fs, * otherwise these will be advisory locks */ @@ -2445,9 +2496,13 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, #endif /* fs/char_dev.c */ -#define CHRDEV_MAJOR_HASH_SIZE 255 +#define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 +/* Marks the top and bottom of the second segment of free char majors */ +#define CHRDEV_MAJOR_DYN_EXT_START 511 +#define CHRDEV_MAJOR_DYN_EXT_END 384 + extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, @@ -2474,14 +2529,14 @@ static inline void unregister_chrdev(unsigned int major, const char *name) #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_HASH_SIZE 255 +#define BLKDEV_MAJOR_MAX 512 extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern void blkdev_show(struct seq_file *,off_t); #else -#define BLKDEV_MAJOR_HASH_SIZE 0 +#define BLKDEV_MAJOR_MAX 0 #endif extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -2513,10 +2568,19 @@ extern int invalidate_inode_pages2_range(struct address_space *mapping, extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait(struct address_space *); -extern void filemap_fdatawait_keep_errors(struct address_space *); +extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); + +static inline int filemap_fdatawait(struct address_space *mapping) +{ + return filemap_fdatawait_range(mapping, 0, LLONG_MAX); +} + +extern bool filemap_range_has_page(struct address_space *, loff_t lstart, + loff_t lend); +extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, + loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); @@ -2525,6 +2589,67 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); extern int filemap_check_errors(struct address_space *mapping); +extern void __filemap_set_wb_err(struct address_space *mapping, int err); + +extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, + loff_t lend); +extern int __must_check file_check_and_advance_wb_err(struct file *file); +extern int __must_check file_write_and_wait_range(struct file *file, + loff_t start, loff_t end); + +static inline int file_write_and_wait(struct file *file) +{ + return file_write_and_wait_range(file, 0, LLONG_MAX); +} + +/** + * filemap_set_wb_err - set a writeback error on an address_space + * @mapping: mapping in which to set writeback error + * @err: error to be set in mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * filemap_set_wb_err to record the error in the mapping so that it will be + * automatically reported whenever fsync is called on the file. + */ +static inline void filemap_set_wb_err(struct address_space *mapping, int err) +{ + /* Fastpath for common case of no error */ + if (unlikely(err)) + __filemap_set_wb_err(mapping, err); +} + +/** + * filemap_check_wb_error - has an error occurred since the mark was sampled? + * @mapping: mapping to check for writeback errors + * @since: previously-sampled errseq_t + * + * Grab the errseq_t value from the mapping, and see if it has changed "since" + * the given value was sampled. + * + * If it has then report the latest error set, otherwise return 0. + */ +static inline int filemap_check_wb_err(struct address_space *mapping, + errseq_t since) +{ + return errseq_check(&mapping->wb_err, since); +} + +/** + * filemap_sample_wb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Writeback errors are always reported relative to a particular sample point + * in the past. This function provides those sample points. + */ +static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) +{ + return errseq_sample(&mapping->wb_err); +} extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); @@ -2688,15 +2813,15 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) return kernel_read_file_str[id]; } -extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, enum kernel_read_file_id); -extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t, +extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t, enum kernel_read_file_id); extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); -extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); -extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); +extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); +extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); +extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ @@ -2747,6 +2872,7 @@ static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern unsigned int get_next_ino(void); +extern void evict_inodes(struct super_block *sb); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); @@ -2789,8 +2915,10 @@ extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); -ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos); -ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos); +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags); +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); @@ -2843,7 +2971,7 @@ enum { DIO_SKIP_DIO_COUNT = 0x08, }; -void dio_end_io(struct bio *bio, int error); +void dio_end_io(struct bio *bio); ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, @@ -2912,6 +3040,10 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); +static inline loff_t __inode_get_bytes(struct inode *inode) +{ + return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; +} loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, @@ -2936,8 +3068,7 @@ static inline int vfs_lstat(const char __user *name, struct kstat *stat) static inline int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags) { - return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); + return vfs_statx(dfd, filename, flags, stat, STATX_BASIC_STATS); } static inline int vfs_fstat(int fd, struct kstat *stat) { @@ -2956,7 +3087,7 @@ extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); -extern void get_filesystem(struct file_system_type *fs); +extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); @@ -3033,15 +3164,16 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -extern int generic_show_options(struct seq_file *m, struct dentry *root); -extern void save_mount_options(struct super_block *sb, char *options); -extern void replace_mount_options(struct super_block *sb, char *options); - static inline bool io_is_direct(struct file *filp) { return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} + static inline int iocb_flags(struct file *file) { int res = 0; @@ -3056,6 +3188,25 @@ static inline int iocb_flags(struct file *file) return res; } +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +{ + if (unlikely(flags & ~RWF_SUPPORTED)) + return -EOPNOTSUPP; + + if (flags & RWF_NOWAIT) { + if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) + return -EOPNOTSUPP; + ki->ki_flags |= IOCB_NOWAIT; + } + if (flags & RWF_HIPRI) + ki->ki_flags |= IOCB_HIPRI; + if (flags & RWF_DSYNC) + ki->ki_flags |= IOCB_DSYNC; + if (flags & RWF_SYNC) + ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC); + return 0; +} + static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; @@ -3168,7 +3319,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode) static inline void inode_has_no_xattr(struct inode *inode) { - if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) + if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 0efc3e62843a..7a026240cbb1 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -12,7 +12,7 @@ struct fs_struct { int umask; int in_exec; struct path root, pwd; -}; +} __randomize_layout; extern struct kmem_cache *fs_cachep; diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 115bb81912cc..f4ff47d4a893 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -143,15 +143,6 @@ struct fscache_cookie_def { void (*mark_page_cached)(void *cookie_netfs_data, struct address_space *mapping, struct page *page); - - /* indicate the cookie is no longer cached - * - this function is called when the backing store currently caching - * a cookie is removed - * - the netfs should use this to clean up any markers indicating - * cached pages - * - this is mandatory for any object that may have data - */ - void (*now_uncached)(void *cookie_netfs_data); }; /* diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h index 0a30c106c1e5..97f738628b36 100644 --- a/include/linux/fscrypt_common.h +++ b/include/linux/fscrypt_common.h @@ -77,12 +77,15 @@ struct fscrypt_operations { const char *key_prefix; int (*get_context)(struct inode *, void *, size_t); int (*set_context)(struct inode *, const void *, size_t, void *); - int (*dummy_context)(struct inode *); + bool (*dummy_context)(struct inode *); bool (*is_encrypted)(struct inode *); bool (*empty_dir)(struct inode *); unsigned (*max_namelen)(struct inode *); }; +/* Maximum value for the third parameter of fscrypt_operations.set_context(). */ +#define FSCRYPT_SET_CONTEXT_MAX_SIZE 28 + static inline bool fscrypt_dummy_context_enabled(struct inode *inode) { if (inode->i_sb->s_cop->dummy_context && @@ -91,14 +94,18 @@ static inline bool fscrypt_dummy_context_enabled(struct inode *inode) return false; } -static inline bool fscrypt_valid_contents_enc_mode(u32 mode) +static inline bool fscrypt_valid_enc_modes(u32 contents_mode, + u32 filenames_mode) { - return (mode == FS_ENCRYPTION_MODE_AES_256_XTS); -} + if (contents_mode == FS_ENCRYPTION_MODE_AES_128_CBC && + filenames_mode == FS_ENCRYPTION_MODE_AES_128_CTS) + return true; -static inline bool fscrypt_valid_filenames_enc_mode(u32 mode) -{ - return (mode == FS_ENCRYPTION_MODE_AES_256_CTS); + if (contents_mode == FS_ENCRYPTION_MODE_AES_256_XTS && + filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) + return true; + + return false; } static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h index cd4e82c17304..32e2fcf13b01 100644 --- a/include/linux/fscrypt_supp.h +++ b/include/linux/fscrypt_supp.h @@ -47,7 +47,12 @@ extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); /* fname.c */ extern int fscrypt_setup_filename(struct inode *, const struct qstr *, int lookup, struct fscrypt_name *); -extern void fscrypt_free_filename(struct fscrypt_name *); + +static inline void fscrypt_free_filename(struct fscrypt_name *fname) +{ + kfree(fname->crypto_buf.name); +} + extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32); extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, struct fscrypt_str *); diff --git a/include/linux/fsi.h b/include/linux/fsi.h index 273cbf6400ea..141fd38d061f 100644 --- a/include/linux/fsi.h +++ b/include/linux/fsi.h @@ -21,8 +21,18 @@ struct fsi_device { struct device dev; u8 engine_type; u8 version; + u8 unit; + struct fsi_slave *slave; + uint32_t addr; + uint32_t size; }; +extern int fsi_device_read(struct fsi_device *dev, uint32_t addr, + void *val, size_t size); +extern int fsi_device_write(struct fsi_device *dev, uint32_t addr, + const void *val, size_t size); +extern int fsi_device_peek(struct fsi_device *dev, void *val); + struct fsi_device_id { u8 engine_type; u8 version; @@ -36,7 +46,6 @@ struct fsi_device_id { #define FSI_DEVICE_VERSIONED(t, v) \ .engine_type = (t), .version = (v), - struct fsi_driver { struct device_driver drv; const struct fsi_device_id *id_table; @@ -45,6 +54,30 @@ struct fsi_driver { #define to_fsi_dev(devp) container_of(devp, struct fsi_device, dev) #define to_fsi_drv(drvp) container_of(drvp, struct fsi_driver, drv) +extern int fsi_driver_register(struct fsi_driver *fsi_drv); +extern void fsi_driver_unregister(struct fsi_driver *fsi_drv); + +/* module_fsi_driver() - Helper macro for drivers that don't do + * anything special in module init/exit. This eliminates a lot of + * boilerplate. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit() + */ +#define module_fsi_driver(__fsi_driver) \ + module_driver(__fsi_driver, fsi_driver_register, \ + fsi_driver_unregister) + +/* direct slave API */ +extern int fsi_slave_claim_range(struct fsi_slave *slave, + uint32_t addr, uint32_t size); +extern void fsi_slave_release_range(struct fsi_slave *slave, + uint32_t addr, uint32_t size); +extern int fsi_slave_read(struct fsi_slave *slave, uint32_t addr, + void *val, size_t size); +extern int fsi_slave_write(struct fsi_slave *slave, uint32_t addr, + const void *val, size_t size); + + + extern struct bus_type fsi_bus_type; #endif /* LINUX_FSI_H */ diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index b43d3f5bd9ea..b78aa7ac77ce 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -293,35 +293,4 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) } } -#if defined(CONFIG_FSNOTIFY) /* notify helpers */ - -/* - * fsnotify_oldname_init - save off the old filename before we change it - */ -static inline const unsigned char *fsnotify_oldname_init(const unsigned char *name) -{ - return kstrdup(name, GFP_KERNEL); -} - -/* - * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init - */ -static inline void fsnotify_oldname_free(const unsigned char *old_name) -{ - kfree(old_name); -} - -#else /* CONFIG_FSNOTIFY */ - -static inline const char *fsnotify_oldname_init(const unsigned char *name) -{ - return NULL; -} - -static inline void fsnotify_oldname_free(const unsigned char *old_name) -{ -} - -#endif /* CONFIG_FSNOTIFY */ - #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 473f088aabea..2e028854bac7 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -119,6 +119,8 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * for any of the functions that this ops will be registered for, then * this ops will fail to register or set_filter_ip. * PID - Is affected by set_ftrace_pid (allows filtering on those pids) + * RCU - Set when the ops can only be called when RCU is watching. + * TRACE_ARRAY - The ops->private points to a trace_array descriptor. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -137,13 +139,14 @@ enum { FTRACE_OPS_FL_IPMODIFY = 1 << 13, FTRACE_OPS_FL_PID = 1 << 14, FTRACE_OPS_FL_RCU = 1 << 15, + FTRACE_OPS_FL_TRACE_ARRAY = 1 << 16, }; #ifdef CONFIG_DYNAMIC_FTRACE /* The hash used to know what functions callbacks trace */ struct ftrace_ops_hash { - struct ftrace_hash *notrace_hash; - struct ftrace_hash *filter_hash; + struct ftrace_hash __rcu *notrace_hash; + struct ftrace_hash __rcu *filter_hash; struct mutex regex_lock; }; @@ -165,7 +168,7 @@ static inline void ftrace_free_init_mem(void) { } */ struct ftrace_ops { ftrace_func_t func; - struct ftrace_ops *next; + struct ftrace_ops __rcu *next; unsigned long flags; void *private; ftrace_func_t saved_func; @@ -304,7 +307,7 @@ DECLARE_PER_CPU(int, disable_stack_tracer); static inline void stack_tracer_disable(void) { /* Preemption or interupts must be disabled */ - if (IS_ENABLED(CONFIG_PREEMPT_DEBUG)) + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); this_cpu_inc(disable_stack_tracer); } @@ -317,7 +320,7 @@ static inline void stack_tracer_disable(void) */ static inline void stack_tracer_enable(void) { - if (IS_ENABLED(CONFIG_PREEMPT_DEBUG)) + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); this_cpu_dec(disable_stack_tracer); } @@ -445,7 +448,8 @@ enum { FTRACE_ITER_PRINTALL = (1 << 2), FTRACE_ITER_DO_PROBES = (1 << 3), FTRACE_ITER_PROBE = (1 << 4), - FTRACE_ITER_ENABLED = (1 << 5), + FTRACE_ITER_MOD = (1 << 5), + FTRACE_ITER_ENABLED = (1 << 6), }; void arch_ftrace_update_code(int command); diff --git a/include/linux/futex.h b/include/linux/futex.h index 7c5b694864cd..f36bfd26f998 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -54,7 +54,6 @@ union futex_key { #ifdef CONFIG_FUTEX extern void exit_robust_list(struct task_struct *curr); -extern void exit_pi_state_list(struct task_struct *curr); #ifdef CONFIG_HAVE_FUTEX_CMPXCHG #define futex_cmpxchg_enabled 1 #else @@ -64,8 +63,14 @@ extern int futex_cmpxchg_enabled; static inline void exit_robust_list(struct task_struct *curr) { } +#endif + +#ifdef CONFIG_FUTEX_PI +extern void exit_pi_state_list(struct task_struct *curr); +#else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif + #endif diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 3dff2398a5f0..0c35b6caf0f6 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -12,19 +12,13 @@ #ifndef _LINUX_FWNODE_H_ #define _LINUX_FWNODE_H_ -enum fwnode_type { - FWNODE_INVALID = 0, - FWNODE_OF, - FWNODE_ACPI, - FWNODE_ACPI_DATA, - FWNODE_ACPI_STATIC, - FWNODE_PDATA, - FWNODE_IRQCHIP -}; +#include <linux/types.h> + +struct fwnode_operations; struct fwnode_handle { - enum fwnode_type type; struct fwnode_handle *secondary; + const struct fwnode_operations *ops; }; /** @@ -39,4 +33,93 @@ struct fwnode_endpoint { const struct fwnode_handle *local_fwnode; }; +#define NR_FWNODE_REFERENCE_ARGS 8 + +/** + * struct fwnode_reference_args - Fwnode reference with additional arguments + * @fwnode:- A reference to the base fwnode + * @nargs: Number of elements in @args array + * @args: Integer arguments on the fwnode + */ +struct fwnode_reference_args { + struct fwnode_handle *fwnode; + unsigned int nargs; + unsigned int args[NR_FWNODE_REFERENCE_ARGS]; +}; + +/** + * struct fwnode_operations - Operations for fwnode interface + * @get: Get a reference to an fwnode. + * @put: Put a reference to an fwnode. + * @property_present: Return true if a property is present. + * @property_read_integer_array: Read an array of integer properties. Return + * zero on success, a negative error code + * otherwise. + * @property_read_string_array: Read an array of string properties. Return zero + * on success, a negative error code otherwise. + * @get_parent: Return the parent of an fwnode. + * @get_next_child_node: Return the next child node in an iteration. + * @get_named_child_node: Return a child node with a given name. + * @get_reference_args: Return a reference pointed to by a property, with args + * @graph_get_next_endpoint: Return an endpoint node in an iteration. + * @graph_get_remote_endpoint: Return the remote endpoint node of a local + * endpoint node. + * @graph_get_port_parent: Return the parent node of a port node. + * @graph_parse_endpoint: Parse endpoint for port and endpoint id. + */ +struct fwnode_operations { + void (*get)(struct fwnode_handle *fwnode); + void (*put)(struct fwnode_handle *fwnode); + bool (*device_is_available)(const struct fwnode_handle *fwnode); + bool (*property_present)(const struct fwnode_handle *fwnode, + const char *propname); + int (*property_read_int_array)(const struct fwnode_handle *fwnode, + const char *propname, + unsigned int elem_size, void *val, + size_t nval); + int + (*property_read_string_array)(const struct fwnode_handle *fwnode_handle, + const char *propname, const char **val, + size_t nval); + struct fwnode_handle *(*get_parent)(const struct fwnode_handle *fwnode); + struct fwnode_handle * + (*get_next_child_node)(const struct fwnode_handle *fwnode, + struct fwnode_handle *child); + struct fwnode_handle * + (*get_named_child_node)(const struct fwnode_handle *fwnode, + const char *name); + int (*get_reference_args)(const struct fwnode_handle *fwnode, + const char *prop, const char *nargs_prop, + unsigned int nargs, unsigned int index, + struct fwnode_reference_args *args); + struct fwnode_handle * + (*graph_get_next_endpoint)(const struct fwnode_handle *fwnode, + struct fwnode_handle *prev); + struct fwnode_handle * + (*graph_get_remote_endpoint)(const struct fwnode_handle *fwnode); + struct fwnode_handle * + (*graph_get_port_parent)(struct fwnode_handle *fwnode); + int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, + struct fwnode_endpoint *endpoint); +}; + +#define fwnode_has_op(fwnode, op) \ + ((fwnode) && (fwnode)->ops && (fwnode)->ops->op) +#define fwnode_call_int_op(fwnode, op, ...) \ + (fwnode ? (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ + -EINVAL) +#define fwnode_call_bool_op(fwnode, op, ...) \ + (fwnode ? (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : false) : \ + false) +#define fwnode_call_ptr_op(fwnode, op, ...) \ + (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : NULL) +#define fwnode_call_void_op(fwnode, op, ...) \ + do { \ + if (fwnode_has_op(fwnode, op)) \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__); \ + } while (false) + #endif diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 29d4385903d4..6dfec4d638df 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -38,12 +38,13 @@ struct device_node; struct gen_pool; /** - * Allocation callback function type definition + * typedef genpool_algo_t: Allocation callback function type definition * @map: Pointer to bitmap * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for - * @data: optional additional data used by @genpool_algo_t + * @data: optional additional data used by the callback + * @pool: the pool being allocated from */ typedef unsigned long (*genpool_algo_t)(unsigned long *map, unsigned long size, diff --git a/include/linux/genhd.h b/include/linux/genhd.h index acff9437e5c3..ea652bfcd675 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -219,12 +219,6 @@ static inline struct gendisk *part_to_disk(struct hd_struct *part) return NULL; } -static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) -{ - uuid_be_to_bin(uuid_str, (uuid_be *)to); - return 0; -} - static inline int disk_max_parts(struct gendisk *disk) { if (disk->flags & GENHD_FL_EXT_DEVT) @@ -368,24 +362,12 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part, int rw) -{ - atomic_inc(&part->in_flight[rw]); - if (part->partno) - atomic_inc(&part_to_disk(part)->part0.in_flight[rw]); -} - -static inline void part_dec_in_flight(struct hd_struct *part, int rw) -{ - atomic_dec(&part->in_flight[rw]); - if (part->partno) - atomic_dec(&part_to_disk(part)->part0.in_flight[rw]); -} - -static inline int part_in_flight(struct hd_struct *part) -{ - return atomic_read(&part->in_flight[0]) + atomic_read(&part->in_flight[1]); -} +void part_in_flight(struct request_queue *q, struct hd_struct *part, + unsigned int inflight[2]); +void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, + int rw); +void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, + int rw); static inline struct partition_meta_info *alloc_part_info(struct gendisk *disk) { @@ -401,7 +383,7 @@ static inline void free_part_info(struct hd_struct *part) } /* block/blk-core.c */ -extern void part_round_stats(int cpu, struct hd_struct *part); +extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part); /* block/genhd.c */ extern void device_add_disk(struct device *parent, struct gendisk *disk); @@ -736,11 +718,6 @@ static inline dev_t blk_lookup_devt(const char *name, int partno) dev_t devt = MKDEV(0, 0); return devt; } - -static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) -{ - return -EINVAL; -} #endif /* CONFIG_BLOCK */ #endif /* _LINUX_GENHD_H */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index a89d37e8b387..f780718b7391 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -25,7 +25,7 @@ struct vm_area_struct; #define ___GFP_FS 0x80u #define ___GFP_COLD 0x100u #define ___GFP_NOWARN 0x200u -#define ___GFP_REPEAT 0x400u +#define ___GFP_RETRY_MAYFAIL 0x400u #define ___GFP_NOFAIL 0x800u #define ___GFP_NORETRY 0x1000u #define ___GFP_MEMALLOC 0x2000u @@ -136,26 +136,56 @@ struct vm_area_struct; * * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * - * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt - * _might_ fail. This depends upon the particular VM implementation. + * The default allocator behavior depends on the request size. We have a concept + * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER). + * !costly allocations are too essential to fail so they are implicitly + * non-failing by default (with some exceptions like OOM victims might fail so + * the caller still has to check for failures) while costly requests try to be + * not disruptive and back off even without invoking the OOM killer. + * The following three modifiers might be used to override some of these + * implicit rules + * + * __GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with __GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. * * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. New users should be evaluated carefully - * (and the flag should be used only when there is no reasonable failure - * policy) but it is definitely preferable to use the flag rather than - * opencode endless loop around allocator. - * - * __GFP_NORETRY: The VM implementation must not retry indefinitely and will - * return NULL when direct reclaim and memory compaction have failed to allow - * the allocation to succeed. The OOM killer is not called with the current - * implementation. + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) +#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) @@ -258,8 +288,6 @@ struct vm_area_struct; #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) -#define GFP_TEMPORARY (__GFP_RECLAIM | __GFP_IO | __GFP_FS | \ - __GFP_RECLAIMABLE) #define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 @@ -432,14 +460,13 @@ static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, nodemask_t *nodemask); +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, + nodemask_t *nodemask); static inline struct page * -__alloc_pages(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist) +__alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) { - return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL); + return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); } /* @@ -452,7 +479,7 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); VM_WARN_ON(!node_online(nid)); - return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); + return __alloc_pages(gfp_mask, order, nid); } /* diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 393582867afd..c97f8325e8bf 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -180,8 +180,27 @@ struct gpio_chip { * If CONFIG_OF is enabled, then all GPIO controllers described in the * device tree automatically may have an OF translation */ + + /** + * @of_node: + * + * Pointer to a device tree node representing this GPIO controller. + */ struct device_node *of_node; - int of_gpio_n_cells; + + /** + * @of_gpio_n_cells: + * + * Number of cells used to form the GPIO specifier. + */ + unsigned int of_gpio_n_cells; + + /** + * @of_xlate: + * + * Callback to translate a device tree GPIO specifier into a chip- + * relative GPIO number and flags. + */ int (*of_xlate)(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags); #endif @@ -213,6 +232,9 @@ bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_open_drain(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *chip, unsigned int offset); +/* Sleep persistence inquiry for drivers */ +bool gpiochip_line_is_persistent(struct gpio_chip *chip, unsigned int offset); + /* get driver data */ void *gpiochip_get_data(struct gpio_chip *chip); @@ -324,11 +346,10 @@ int gpiochip_generic_config(struct gpio_chip *chip, unsigned offset, /** * struct gpio_pin_range - pin range controlled by a gpio chip - * @head: list for maintaining set of pin ranges, used internally + * @node: list for maintaining set of pin ranges, used internally * @pctldev: pinctrl device which handles corresponding pins * @range: actual range of pins controlled by a gpio controller */ - struct gpio_pin_range { struct list_head node; struct pinctrl_dev *pctldev; diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index f738d50cc17d..ba4ccfd900f9 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -9,6 +9,8 @@ enum gpio_lookup_flags { GPIO_ACTIVE_LOW = (1 << 0), GPIO_OPEN_DRAIN = (1 << 1), GPIO_OPEN_SOURCE = (1 << 2), + GPIO_SLEEP_MAINTAIN_VALUE = (0 << 3), + GPIO_SLEEP_MAY_LOOSE_VALUE = (1 << 3), }; /** @@ -58,11 +60,14 @@ struct gpiod_lookup_table { #ifdef CONFIG_GPIOLIB void gpiod_add_lookup_table(struct gpiod_lookup_table *table); +void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n); void gpiod_remove_lookup_table(struct gpiod_lookup_table *table); #else static inline void gpiod_add_lookup_table(struct gpiod_lookup_table *table) {} static inline +void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n) {} +static inline void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) {} #endif diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index f32d7c392c1e..fc7aae64dcde 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -233,12 +233,14 @@ struct hid_sensor_common { atomic_t user_requested_state; int poll_interval; int raw_hystersis; + int latency_ms; struct iio_trigger *trigger; int timestamp_ns_scale; struct hid_sensor_hub_attribute_info poll; struct hid_sensor_hub_attribute_info report_state; struct hid_sensor_hub_attribute_info power_state; struct hid_sensor_hub_attribute_info sensitivity; + struct hid_sensor_hub_attribute_info report_latency; struct work_struct work; }; @@ -276,5 +278,8 @@ s32 hid_sensor_read_poll_value(struct hid_sensor_common *st); int64_t hid_sensor_convert_timestamp(struct hid_sensor_common *st, int64_t raw_value); +bool hid_sensor_batch_mode_supported(struct hid_sensor_common *st); +int hid_sensor_set_report_latency(struct hid_sensor_common *st, int latency); +int hid_sensor_get_report_latency(struct hid_sensor_common *st); #endif diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index 761f86242473..76033e0420a7 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -90,6 +90,8 @@ #define HID_USAGE_SENSOR_ORIENT_TILT_Z 0x200481 #define HID_USAGE_SENSOR_DEVICE_ORIENTATION 0x20008A +#define HID_USAGE_SENSOR_RELATIVE_ORIENTATION 0x20008E +#define HID_USAGE_SENSOR_GEOMAGNETIC_ORIENTATION 0x2000C1 #define HID_USAGE_SENSOR_ORIENT_ROTATION_MATRIX 0x200482 #define HID_USAGE_SENSOR_ORIENT_QUATERNION 0x200483 #define HID_USAGE_SENSOR_ORIENT_MAGN_FLUX 0x200484 @@ -150,6 +152,9 @@ #define HID_USAGE_SENSOR_PROP_REPORT_STATE 0x200316 #define HID_USAGE_SENSOR_PROY_POWER_STATE 0x200319 +/* Batch mode selectors */ +#define HID_USAGE_SENSOR_PROP_REPORT_LATENCY 0x20031B + /* Per data field properties */ #define HID_USAGE_SENSOR_DATA_MOD_NONE 0x00 #define HID_USAGE_SENSOR_DATA_MOD_CHANGE_SENSITIVITY_ABS 0x1000 diff --git a/include/linux/hid.h b/include/linux/hid.h index 5be325d890d9..ab05a86269dc 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -34,6 +34,7 @@ #include <linux/workqueue.h> #include <linux/input.h> #include <linux/semaphore.h> +#include <linux/mutex.h> #include <linux/power_supply.h> #include <uapi/linux/hid.h> @@ -172,6 +173,7 @@ struct hid_item { #define HID_UP_LOGIVENDOR3 0xff430000 #define HID_UP_LNVENDOR 0xffa00000 #define HID_UP_SENSOR 0x00200000 +#define HID_UP_ASUSVENDOR 0xff310000 #define HID_USAGE 0x0000ffff @@ -182,6 +184,11 @@ struct hid_item { #define HID_GD_KEYBOARD 0x00010006 #define HID_GD_KEYPAD 0x00010007 #define HID_GD_MULTIAXIS 0x00010008 +/* + * Microsoft Win8 Wireless Radio Controls extensions CA, see: + * http://www.usb.org/developers/hidpage/HUTRR40RadioHIDUsagesFinal.pdf + */ +#define HID_GD_WIRELESS_RADIO_CTLS 0x0001000c #define HID_GD_X 0x00010030 #define HID_GD_Y 0x00010031 #define HID_GD_Z 0x00010032 @@ -210,6 +217,10 @@ struct hid_item { #define HID_GD_DOWN 0x00010091 #define HID_GD_RIGHT 0x00010092 #define HID_GD_LEFT 0x00010093 +/* Microsoft Win8 Wireless Radio Controls CA usage codes */ +#define HID_GD_RFKILL_BTN 0x000100c6 +#define HID_GD_RFKILL_LED 0x000100c7 +#define HID_GD_RFKILL_SWITCH 0x000100c8 #define HID_DC_BATTERYSTRENGTH 0x00060020 @@ -282,6 +293,7 @@ struct hid_item { #define HID_DG_BARRELSWITCH2 0x000d005a #define HID_DG_TOOLSERIALNUMBER 0x000d005b +#define HID_VD_ASUS_CUSTOM_MEDIA_KEYS 0xff310076 /* * HID report types --- Ouch! HID spec says 1 2 3! */ @@ -353,6 +365,12 @@ struct hid_item { #define HID_GROUP_LOGITECH_DJ_DEVICE 0x0102 /* + * HID protocol status + */ +#define HID_REPORT_PROTOCOL 1 +#define HID_BOOT_PROTOCOL 0 + +/* * This is the global environment of the parser. This information is * persistent for main-items. The global environment can be saved and * restored with PUSH/POP statements. @@ -516,11 +534,13 @@ struct hid_device { /* device report descriptor */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; struct work_struct led_work; /* delayed LED worker */ - struct semaphore driver_lock; /* protects the current driver, except during input */ struct semaphore driver_input_lock; /* protects the current driver */ struct device dev; /* device */ struct hid_driver *driver; + struct hid_ll_driver *ll_driver; + struct mutex ll_open_lock; + unsigned int ll_open_count; #ifdef CONFIG_HID_BATTERY_STRENGTH /* @@ -529,22 +549,23 @@ struct hid_device { /* device report descriptor */ * battery is non-NULL. */ struct power_supply *battery; + __s32 battery_capacity; __s32 battery_min; __s32 battery_max; __s32 battery_report_type; __s32 battery_report_id; + bool battery_reported; #endif unsigned int status; /* see STAT flags above */ unsigned claimed; /* Claimed by hidinput, hiddev? */ unsigned quirks; /* Various quirks the device can pull on us */ - bool io_started; /* Protected by driver_lock. If IO has started */ + bool io_started; /* If IO has started */ struct list_head inputs; /* The list of inputs */ void *hiddev; /* The hiddev structure */ void *hidraw; - int open; /* is the device open by anyone? */ char name[128]; /* Device name */ char phys[64]; /* Device physical location */ char uniq[64]; /* Device unique identifier (serial #) */ @@ -765,6 +786,17 @@ struct hid_ll_driver { int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); }; +extern struct hid_ll_driver i2c_hid_ll_driver; +extern struct hid_ll_driver hidp_hid_driver; +extern struct hid_ll_driver uhid_hid_driver; +extern struct hid_ll_driver usb_hid_driver; + +static inline bool hid_is_using_ll_driver(struct hid_device *hdev, + struct hid_ll_driver *driver) +{ + return hdev->ll_driver == driver; +} + #define PM_HINT_FULLON 1<<5 #define PM_HINT_NORMAL 1<<1 @@ -937,69 +969,11 @@ static inline int __must_check hid_parse(struct hid_device *hdev) return hid_open_report(hdev); } -/** - * hid_hw_start - start underlaying HW - * - * @hdev: hid device - * @connect_mask: which outputs to connect, see HID_CONNECT_* - * - * Call this in probe function *after* hid_parse. This will setup HW buffers - * and start the device (if not deffered to device open). hid_hw_stop must be - * called if this was successful. - */ -static inline int __must_check hid_hw_start(struct hid_device *hdev, - unsigned int connect_mask) -{ - int ret = hdev->ll_driver->start(hdev); - if (ret || !connect_mask) - return ret; - ret = hid_connect(hdev, connect_mask); - if (ret) - hdev->ll_driver->stop(hdev); - return ret; -} - -/** - * hid_hw_stop - stop underlaying HW - * - * @hdev: hid device - * - * This is usually called from remove function or from probe when something - * failed and hid_hw_start was called already. - */ -static inline void hid_hw_stop(struct hid_device *hdev) -{ - hid_disconnect(hdev); - hdev->ll_driver->stop(hdev); -} - -/** - * hid_hw_open - signal underlaying HW to start delivering events - * - * @hdev: hid device - * - * Tell underlying HW to start delivering events from the device. - * This function should be called sometime after successful call - * to hid_hiw_start(). - */ -static inline int __must_check hid_hw_open(struct hid_device *hdev) -{ - return hdev->ll_driver->open(hdev); -} - -/** - * hid_hw_close - signal underlaying HW to stop delivering events - * - * @hdev: hid device - * - * This function indicates that we are not interested in the events - * from this device anymore. Delivery of events may or may not stop, - * depending on the number of users still outstanding. - */ -static inline void hid_hw_close(struct hid_device *hdev) -{ - hdev->ll_driver->close(hdev); -} +int __must_check hid_hw_start(struct hid_device *hdev, + unsigned int connect_mask); +void hid_hw_stop(struct hid_device *hdev); +int __must_check hid_hw_open(struct hid_device *hdev); +void hid_hw_close(struct hid_device *hdev); /** * hid_hw_power - requests underlying HW to go into given power mode diff --git a/include/linux/hmm.h b/include/linux/hmm.h new file mode 100644 index 000000000000..96e69979f84d --- /dev/null +++ b/include/linux/hmm.h @@ -0,0 +1,520 @@ +/* + * Copyright 2013 Red Hat Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Jérôme Glisse <jglisse@redhat.com> + */ +/* + * Heterogeneous Memory Management (HMM) + * + * See Documentation/vm/hmm.txt for reasons and overview of what HMM is and it + * is for. Here we focus on the HMM API description, with some explanation of + * the underlying implementation. + * + * Short description: HMM provides a set of helpers to share a virtual address + * space between CPU and a device, so that the device can access any valid + * address of the process (while still obeying memory protection). HMM also + * provides helpers to migrate process memory to device memory, and back. Each + * set of functionality (address space mirroring, and migration to and from + * device memory) can be used independently of the other. + * + * + * HMM address space mirroring API: + * + * Use HMM address space mirroring if you want to mirror range of the CPU page + * table of a process into a device page table. Here, "mirror" means "keep + * synchronized". Prerequisites: the device must provide the ability to write- + * protect its page tables (at PAGE_SIZE granularity), and must be able to + * recover from the resulting potential page faults. + * + * HMM guarantees that at any point in time, a given virtual address points to + * either the same memory in both CPU and device page tables (that is: CPU and + * device page tables each point to the same pages), or that one page table (CPU + * or device) points to no entry, while the other still points to the old page + * for the address. The latter case happens when the CPU page table update + * happens first, and then the update is mirrored over to the device page table. + * This does not cause any issue, because the CPU page table cannot start + * pointing to a new page until the device page table is invalidated. + * + * HMM uses mmu_notifiers to monitor the CPU page tables, and forwards any + * updates to each device driver that has registered a mirror. It also provides + * some API calls to help with taking a snapshot of the CPU page table, and to + * synchronize with any updates that might happen concurrently. + * + * + * HMM migration to and from device memory: + * + * HMM provides a set of helpers to hotplug device memory as ZONE_DEVICE, with + * a new MEMORY_DEVICE_PRIVATE type. This provides a struct page for each page + * of the device memory, and allows the device driver to manage its memory + * using those struct pages. Having struct pages for device memory makes + * migration easier. Because that memory is not addressable by the CPU it must + * never be pinned to the device; in other words, any CPU page fault can always + * cause the device memory to be migrated (copied/moved) back to regular memory. + * + * A new migrate helper (migrate_vma()) has been added (see mm/migrate.c) that + * allows use of a device DMA engine to perform the copy operation between + * regular system memory and device memory. + */ +#ifndef LINUX_HMM_H +#define LINUX_HMM_H + +#include <linux/kconfig.h> + +#if IS_ENABLED(CONFIG_HMM) + +#include <linux/device.h> +#include <linux/migrate.h> +#include <linux/memremap.h> +#include <linux/completion.h> + +struct hmm; + +/* + * hmm_pfn_t - HMM uses its own pfn type to keep several flags per page + * + * Flags: + * HMM_PFN_VALID: pfn is valid + * HMM_PFN_READ: CPU page table has read permission set + * HMM_PFN_WRITE: CPU page table has write permission set + * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory + * HMM_PFN_EMPTY: corresponding CPU page table entry is pte_none() + * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the + * result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not + * be mirrored by a device, because the entry will never have HMM_PFN_VALID + * set and the pfn value is undefined. + * HMM_PFN_DEVICE_UNADDRESSABLE: unaddressable device memory (ZONE_DEVICE) + */ +typedef unsigned long hmm_pfn_t; + +#define HMM_PFN_VALID (1 << 0) +#define HMM_PFN_READ (1 << 1) +#define HMM_PFN_WRITE (1 << 2) +#define HMM_PFN_ERROR (1 << 3) +#define HMM_PFN_EMPTY (1 << 4) +#define HMM_PFN_SPECIAL (1 << 5) +#define HMM_PFN_DEVICE_UNADDRESSABLE (1 << 6) +#define HMM_PFN_SHIFT 7 + +/* + * hmm_pfn_t_to_page() - return struct page pointed to by a valid hmm_pfn_t + * @pfn: hmm_pfn_t to convert to struct page + * Returns: struct page pointer if pfn is a valid hmm_pfn_t, NULL otherwise + * + * If the hmm_pfn_t is valid (ie valid flag set) then return the struct page + * matching the pfn value stored in the hmm_pfn_t. Otherwise return NULL. + */ +static inline struct page *hmm_pfn_t_to_page(hmm_pfn_t pfn) +{ + if (!(pfn & HMM_PFN_VALID)) + return NULL; + return pfn_to_page(pfn >> HMM_PFN_SHIFT); +} + +/* + * hmm_pfn_t_to_pfn() - return pfn value store in a hmm_pfn_t + * @pfn: hmm_pfn_t to extract pfn from + * Returns: pfn value if hmm_pfn_t is valid, -1UL otherwise + */ +static inline unsigned long hmm_pfn_t_to_pfn(hmm_pfn_t pfn) +{ + if (!(pfn & HMM_PFN_VALID)) + return -1UL; + return (pfn >> HMM_PFN_SHIFT); +} + +/* + * hmm_pfn_t_from_page() - create a valid hmm_pfn_t value from struct page + * @page: struct page pointer for which to create the hmm_pfn_t + * Returns: valid hmm_pfn_t for the page + */ +static inline hmm_pfn_t hmm_pfn_t_from_page(struct page *page) +{ + return (page_to_pfn(page) << HMM_PFN_SHIFT) | HMM_PFN_VALID; +} + +/* + * hmm_pfn_t_from_pfn() - create a valid hmm_pfn_t value from pfn + * @pfn: pfn value for which to create the hmm_pfn_t + * Returns: valid hmm_pfn_t for the pfn + */ +static inline hmm_pfn_t hmm_pfn_t_from_pfn(unsigned long pfn) +{ + return (pfn << HMM_PFN_SHIFT) | HMM_PFN_VALID; +} + + +#if IS_ENABLED(CONFIG_HMM_MIRROR) +/* + * Mirroring: how to synchronize device page table with CPU page table. + * + * A device driver that is participating in HMM mirroring must always + * synchronize with CPU page table updates. For this, device drivers can either + * directly use mmu_notifier APIs or they can use the hmm_mirror API. Device + * drivers can decide to register one mirror per device per process, or just + * one mirror per process for a group of devices. The pattern is: + * + * int device_bind_address_space(..., struct mm_struct *mm, ...) + * { + * struct device_address_space *das; + * + * // Device driver specific initialization, and allocation of das + * // which contains an hmm_mirror struct as one of its fields. + * ... + * + * ret = hmm_mirror_register(&das->mirror, mm, &device_mirror_ops); + * if (ret) { + * // Cleanup on error + * return ret; + * } + * + * // Other device driver specific initialization + * ... + * } + * + * Once an hmm_mirror is registered for an address space, the device driver + * will get callbacks through sync_cpu_device_pagetables() operation (see + * hmm_mirror_ops struct). + * + * Device driver must not free the struct containing the hmm_mirror struct + * before calling hmm_mirror_unregister(). The expected usage is to do that when + * the device driver is unbinding from an address space. + * + * + * void device_unbind_address_space(struct device_address_space *das) + * { + * // Device driver specific cleanup + * ... + * + * hmm_mirror_unregister(&das->mirror); + * + * // Other device driver specific cleanup, and now das can be freed + * ... + * } + */ + +struct hmm_mirror; + +/* + * enum hmm_update_type - type of update + * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) + */ +enum hmm_update_type { + HMM_UPDATE_INVALIDATE, +}; + +/* + * struct hmm_mirror_ops - HMM mirror device operations callback + * + * @update: callback to update range on a device + */ +struct hmm_mirror_ops { + /* sync_cpu_device_pagetables() - synchronize page tables + * + * @mirror: pointer to struct hmm_mirror + * @update_type: type of update that occurred to the CPU page table + * @start: virtual start address of the range to update + * @end: virtual end address of the range to update + * + * This callback ultimately originates from mmu_notifiers when the CPU + * page table is updated. The device driver must update its page table + * in response to this callback. The update argument tells what action + * to perform. + * + * The device driver must not return from this callback until the device + * page tables are completely updated (TLBs flushed, etc); this is a + * synchronous call. + */ + void (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, + enum hmm_update_type update_type, + unsigned long start, + unsigned long end); +}; + +/* + * struct hmm_mirror - mirror struct for a device driver + * + * @hmm: pointer to struct hmm (which is unique per mm_struct) + * @ops: device driver callback for HMM mirror operations + * @list: for list of mirrors of a given mm + * + * Each address space (mm_struct) being mirrored by a device must register one + * instance of an hmm_mirror struct with HMM. HMM will track the list of all + * mirrors for each mm_struct. + */ +struct hmm_mirror { + struct hmm *hmm; + const struct hmm_mirror_ops *ops; + struct list_head list; +}; + +int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); +void hmm_mirror_unregister(struct hmm_mirror *mirror); + + +/* + * struct hmm_range - track invalidation lock on virtual address range + * + * @list: all range lock are on a list + * @start: range virtual start address (inclusive) + * @end: range virtual end address (exclusive) + * @pfns: array of pfns (big enough for the range) + * @valid: pfns array did not change since it has been fill by an HMM function + */ +struct hmm_range { + struct list_head list; + unsigned long start; + unsigned long end; + hmm_pfn_t *pfns; + bool valid; +}; + +/* + * To snapshot the CPU page table, call hmm_vma_get_pfns(), then take a device + * driver lock that serializes device page table updates, then call + * hmm_vma_range_done(), to check if the snapshot is still valid. The same + * device driver page table update lock must also be used in the + * hmm_mirror_ops.sync_cpu_device_pagetables() callback, so that CPU page + * table invalidation serializes on it. + * + * YOU MUST CALL hmm_vma_range_done() ONCE AND ONLY ONCE EACH TIME YOU CALL + * hmm_vma_get_pfns() WITHOUT ERROR ! + * + * IF YOU DO NOT FOLLOW THE ABOVE RULE THE SNAPSHOT CONTENT MIGHT BE INVALID ! + */ +int hmm_vma_get_pfns(struct vm_area_struct *vma, + struct hmm_range *range, + unsigned long start, + unsigned long end, + hmm_pfn_t *pfns); +bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range); + + +/* + * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will + * not migrate any device memory back to system memory. The hmm_pfn_t array will + * be updated with the fault result and current snapshot of the CPU page table + * for the range. + * + * The mmap_sem must be taken in read mode before entering and it might be + * dropped by the function if the block argument is false. In that case, the + * function returns -EAGAIN. + * + * Return value does not reflect if the fault was successful for every single + * address or not. Therefore, the caller must to inspect the hmm_pfn_t array to + * determine fault status for each address. + * + * Trying to fault inside an invalid vma will result in -EINVAL. + * + * See the function description in mm/hmm.c for further documentation. + */ +int hmm_vma_fault(struct vm_area_struct *vma, + struct hmm_range *range, + unsigned long start, + unsigned long end, + hmm_pfn_t *pfns, + bool write, + bool block); +#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ + + +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) +struct hmm_devmem; + +struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, + unsigned long addr); + +/* + * struct hmm_devmem_ops - callback for ZONE_DEVICE memory events + * + * @free: call when refcount on page reach 1 and thus is no longer use + * @fault: call when there is a page fault to unaddressable memory + * + * Both callback happens from page_free() and page_fault() callback of struct + * dev_pagemap respectively. See include/linux/memremap.h for more details on + * those. + * + * The hmm_devmem_ops callback are just here to provide a coherent and + * uniq API to device driver and device driver should not register their + * own page_free() or page_fault() but rely on the hmm_devmem_ops call- + * back. + */ +struct hmm_devmem_ops { + /* + * free() - free a device page + * @devmem: device memory structure (see struct hmm_devmem) + * @page: pointer to struct page being freed + * + * Call back occurs whenever a device page refcount reach 1 which + * means that no one is holding any reference on the page anymore + * (ZONE_DEVICE page have an elevated refcount of 1 as default so + * that they are not release to the general page allocator). + * + * Note that callback has exclusive ownership of the page (as no + * one is holding any reference). + */ + void (*free)(struct hmm_devmem *devmem, struct page *page); + /* + * fault() - CPU page fault or get user page (GUP) + * @devmem: device memory structure (see struct hmm_devmem) + * @vma: virtual memory area containing the virtual address + * @addr: virtual address that faulted or for which there is a GUP + * @page: pointer to struct page backing virtual address (unreliable) + * @flags: FAULT_FLAG_* (see include/linux/mm.h) + * @pmdp: page middle directory + * Returns: VM_FAULT_MINOR/MAJOR on success or one of VM_FAULT_ERROR + * on error + * + * The callback occurs whenever there is a CPU page fault or GUP on a + * virtual address. This means that the device driver must migrate the + * page back to regular memory (CPU accessible). + * + * The device driver is free to migrate more than one page from the + * fault() callback as an optimization. However if device decide to + * migrate more than one page it must always priotirize the faulting + * address over the others. + * + * The struct page pointer is only given as an hint to allow quick + * lookup of internal device driver data. A concurrent migration + * might have already free that page and the virtual address might + * not longer be back by it. So it should not be modified by the + * callback. + * + * Note that mmap semaphore is held in read mode at least when this + * callback occurs, hence the vma is valid upon callback entry. + */ + int (*fault)(struct hmm_devmem *devmem, + struct vm_area_struct *vma, + unsigned long addr, + const struct page *page, + unsigned int flags, + pmd_t *pmdp); +}; + +/* + * struct hmm_devmem - track device memory + * + * @completion: completion object for device memory + * @pfn_first: first pfn for this resource (set by hmm_devmem_add()) + * @pfn_last: last pfn for this resource (set by hmm_devmem_add()) + * @resource: IO resource reserved for this chunk of memory + * @pagemap: device page map for that chunk + * @device: device to bind resource to + * @ops: memory operations callback + * @ref: per CPU refcount + * + * This an helper structure for device drivers that do not wish to implement + * the gory details related to hotplugging new memoy and allocating struct + * pages. + * + * Device drivers can directly use ZONE_DEVICE memory on their own if they + * wish to do so. + */ +struct hmm_devmem { + struct completion completion; + unsigned long pfn_first; + unsigned long pfn_last; + struct resource *resource; + struct device *device; + struct dev_pagemap pagemap; + const struct hmm_devmem_ops *ops; + struct percpu_ref ref; +}; + +/* + * To add (hotplug) device memory, HMM assumes that there is no real resource + * that reserves a range in the physical address space (this is intended to be + * use by unaddressable device memory). It will reserve a physical range big + * enough and allocate struct page for it. + * + * The device driver can wrap the hmm_devmem struct inside a private device + * driver struct. The device driver must call hmm_devmem_remove() before the + * device goes away and before freeing the hmm_devmem struct memory. + */ +struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, + struct device *device, + unsigned long size); +struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, + struct device *device, + struct resource *res); +void hmm_devmem_remove(struct hmm_devmem *devmem); + +/* + * hmm_devmem_page_set_drvdata - set per-page driver data field + * + * @page: pointer to struct page + * @data: driver data value to set + * + * Because page can not be on lru we have an unsigned long that driver can use + * to store a per page field. This just a simple helper to do that. + */ +static inline void hmm_devmem_page_set_drvdata(struct page *page, + unsigned long data) +{ + unsigned long *drvdata = (unsigned long *)&page->pgmap; + + drvdata[1] = data; +} + +/* + * hmm_devmem_page_get_drvdata - get per page driver data field + * + * @page: pointer to struct page + * Return: driver data value + */ +static inline unsigned long hmm_devmem_page_get_drvdata(struct page *page) +{ + unsigned long *drvdata = (unsigned long *)&page->pgmap; + + return drvdata[1]; +} + + +/* + * struct hmm_device - fake device to hang device memory onto + * + * @device: device struct + * @minor: device minor number + */ +struct hmm_device { + struct device device; + unsigned int minor; +}; + +/* + * A device driver that wants to handle multiple devices memory through a + * single fake device can use hmm_device to do so. This is purely a helper and + * it is not strictly needed, in order to make use of any HMM functionality. + */ +struct hmm_device *hmm_device_new(void *drvdata); +void hmm_device_put(struct hmm_device *hmm_device); +#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ +#endif /* IS_ENABLED(CONFIG_HMM) */ + +/* Below are for HMM internal use only! Not to be used by device driver! */ +#if IS_ENABLED(CONFIG_HMM_MIRROR) +void hmm_mm_destroy(struct mm_struct *mm); + +static inline void hmm_mm_init(struct mm_struct *mm) +{ + mm->hmm = NULL; +} +#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ +static inline void hmm_mm_destroy(struct mm_struct *mm) {} +static inline void hmm_mm_init(struct mm_struct *mm) {} +#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ + + +#else /* IS_ENABLED(CONFIG_HMM) */ +static inline void hmm_mm_destroy(struct mm_struct *mm) {} +static inline void hmm_mm_init(struct mm_struct *mm) {} +#endif /* LINUX_HMM_H */ diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 3d04aa1dc83e..630b1a98ab58 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -32,11 +32,27 @@ enum host1x_class { struct host1x_client; +/** + * struct host1x_client_ops - host1x client operations + * @init: host1x client initialization code + * @exit: host1x client tear down code + */ struct host1x_client_ops { int (*init)(struct host1x_client *client); int (*exit)(struct host1x_client *client); }; +/** + * struct host1x_client - host1x client structure + * @list: list node for the host1x client + * @parent: pointer to struct device representing the host1x controller + * @dev: pointer to struct device backing this host1x client + * @ops: host1x client operations + * @class: host1x class represented by this client + * @channel: host1x channel associated with this client + * @syncpts: array of syncpoints requested for this client + * @num_syncpts: number of syncpoints requested for this client + */ struct host1x_client { struct list_head list; struct device *parent; @@ -156,7 +172,6 @@ struct host1x_channel; struct host1x_job; struct host1x_channel *host1x_channel_request(struct device *dev); -void host1x_channel_free(struct host1x_channel *channel); struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); void host1x_channel_put(struct host1x_channel *channel); int host1x_job_submit(struct host1x_job *job); @@ -177,6 +192,13 @@ struct host1x_reloc { unsigned long shift; }; +struct host1x_waitchk { + struct host1x_bo *bo; + u32 offset; + u32 syncpt_id; + u32 thresh; +}; + struct host1x_job { /* When refcount goes to zero, job can be freed */ struct kref ref; @@ -226,7 +248,10 @@ struct host1x_job { u8 *gather_copy_mapped; /* Check if register is marked as an address reg */ - int (*is_addr_reg)(struct device *dev, u32 reg, u32 class); + int (*is_addr_reg)(struct device *dev, u32 class, u32 reg); + + /* Check if class belongs to the unit */ + int (*is_valid_class)(u32 class); /* Request a SETCLASS to this class */ u32 class; @@ -251,6 +276,15 @@ void host1x_job_unpin(struct host1x_job *job); struct host1x_device; +/** + * struct host1x_driver - host1x logical device driver + * @driver: core driver + * @subdevs: table of OF device IDs matching subdevices for this driver + * @list: list node for the driver + * @probe: called when the host1x logical device is probed + * @remove: called when the host1x logical device is removed + * @shutdown: called when the host1x logical device is shut down + */ struct host1x_driver { struct device_driver driver; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 8c5b10eb7265..012c37fdb688 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -452,11 +452,11 @@ static inline u64 hrtimer_forward_now(struct hrtimer *timer, } /* Precise sleep: */ -extern long hrtimer_nanosleep(struct timespec64 *rqtp, - struct timespec __user *rmtp, + +extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); +extern long hrtimer_nanosleep(const struct timespec64 *rqtp, const enum hrtimer_mode mode, const clockid_t clockid); -extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a3762d49ba39..14bc21c2ee7f 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -1,6 +1,10 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H +#include <linux/sched/coredump.h> + +#include <linux/fs.h> /* only for vma_is_dax() */ + extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, @@ -85,14 +89,32 @@ extern struct kobj_attribute shmem_enabled_attr; extern bool is_vma_temporary_stack(struct vm_area_struct *vma); -#define transparent_hugepage_enabled(__vma) \ - ((transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_FLAG) || \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \ - ((__vma)->vm_flags & VM_HUGEPAGE))) && \ - !((__vma)->vm_flags & VM_NOHUGEPAGE) && \ - !is_vma_temporary_stack(__vma)) +extern unsigned long transparent_hugepage_flags; + +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_NOHUGEPAGE) + return false; + + if (is_vma_temporary_stack(vma)) + return false; + + if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) + return true; + + if (vma_is_dax(vma)) + return true; + + if (transparent_hugepage_flags & + (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) + return !!(vma->vm_flags & VM_HUGEPAGE); + + return false; +} + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) @@ -104,8 +126,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #define transparent_hugepage_debug_cow() 0 #endif /* CONFIG_DEBUG_VM */ -extern unsigned long transparent_hugepage_flags; - extern unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); @@ -113,6 +133,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp, extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); +bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { @@ -126,7 +147,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ - if (pmd_trans_huge(*____pmd) \ + if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false, NULL); \ @@ -157,12 +178,18 @@ extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); extern spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); + +static inline int is_swap_pmd(pmd_t pmd) +{ + return !pmd_none(pmd) && !pmd_present(pmd); +} + /* mmap_sem must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); - if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) + if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else return NULL; @@ -212,6 +239,11 @@ void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) +static inline bool thp_migration_supported(void) +{ + return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); +} + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -223,7 +255,10 @@ void mm_put_huge_zero_page(struct mm_struct *mm); #define hpage_nr_pages(x) 1 -#define transparent_hugepage_enabled(__vma) 0 +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + return false; +} static inline void prep_transhuge_page(struct page *page) {} @@ -231,6 +266,12 @@ static inline void prep_transhuge_page(struct page *page) {} #define thp_get_unmapped_area NULL +static inline bool +can_split_huge_page(struct page *page, int *pextra_pins) +{ + BUILD_BUG(); + return false; +} static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { @@ -264,6 +305,10 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, long adjust_next) { } +static inline int is_swap_pmd(pmd_t pmd) +{ + return 0; +} static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { @@ -306,6 +351,11 @@ static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, { return NULL; } + +static inline bool thp_migration_supported(void) +{ + return false; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b857fc8cc2ec..8bbbd37ab105 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -14,6 +14,30 @@ struct ctl_table; struct user_struct; struct mmu_gather; +#ifndef is_hugepd +/* + * Some architectures requires a hugepage directory format that is + * required to support multiple hugepage sizes. For example + * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables" + * introduced the same on powerpc. This allows for a more flexible hugepage + * pagetable layout. + */ +typedef struct { unsigned long pd; } hugepd_t; +#define is_hugepd(hugepd) (0) +#define __hugepd(x) ((hugepd_t) { (x) }) +static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned pdshift, unsigned long end, + int write, struct page **pages, int *nr) +{ + return 0; +} +#else +extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned pdshift, unsigned long end, + int write, struct page **pages, int *nr); +#endif + + #ifdef CONFIG_HUGETLB_PAGE #include <linux/mempolicy.h> @@ -92,7 +116,6 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void free_huge_page(struct page *page); @@ -113,19 +136,27 @@ extern struct list_head huge_boot_pages; pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz); -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); +pte_t *huge_pte_offset(struct mm_struct *mm, + unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); +struct page *follow_huge_pd(struct vm_area_struct *vma, + unsigned long address, hugepd_t hpd, + int flags, int pdshift); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); +struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, + pgd_t *pgd, int flags); + int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); +bool is_hugetlb_entry_migration(pte_t pte); #else /* !CONFIG_HUGETLB_PAGE */ static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) @@ -147,8 +178,10 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) static inline void hugetlb_show_meminfo(void) { } +#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL #define follow_huge_pmd(mm, addr, pmd, flags) NULL #define follow_huge_pud(mm, addr, pud, flags) NULL +#define follow_huge_pgd(mm, addr, pgd, flags) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define pud_huge(x) 0 @@ -157,11 +190,7 @@ static inline void hugetlb_show_meminfo(void) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) -#define huge_pte_offset(mm, address) 0 -static inline int dequeue_hwpoisoned_huge_page(struct page *page) -{ - return 0; -} +#define huge_pte_offset(mm, address, sz) 0 static inline bool isolate_huge_page(struct page *page, struct list_head *list) { @@ -217,29 +246,6 @@ static inline int pud_write(pud_t pud) } #endif -#ifndef is_hugepd -/* - * Some architectures requires a hugepage directory format that is - * required to support multiple hugepage sizes. For example - * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables" - * introduced the same on powerpc. This allows for a more flexible hugepage - * pagetable layout. - */ -typedef struct { unsigned long pd; } hugepd_t; -#define is_hugepd(hugepd) (0) -#define __hugepd(x) ((hugepd_t) { (x) }) -static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr) -{ - return 0; -} -#else -extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr); -#endif - #define HUGETLB_ANON_FILE "anon_hugepage" enum { @@ -262,6 +268,9 @@ struct hugetlbfs_sb_info { spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; + kuid_t uid; + kgid_t gid; + umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) @@ -343,10 +352,13 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); +struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); /* arch callback */ +int __init __alloc_bootmem_huge_page(struct hstate *h); int __init alloc_bootmem_huge_page(struct hstate *h); void __init hugetlb_bad_size(void); @@ -461,12 +473,17 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } +extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); static inline bool hugepage_migration_supported(struct hstate *h) { #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION - return huge_page_shift(h) == PMD_SHIFT; + if ((huge_page_shift(h) == PMD_SHIFT) || + (huge_page_shift(h) == PGDIR_SHIFT)) + return true; + else + return false; #else return false; #endif @@ -501,10 +518,19 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } + +#ifndef set_huge_swap_pte_at +static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz) +{ + set_huge_pte_at(mm, addr, ptep, pte); +} +#endif #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page(v, a, r) NULL #define alloc_huge_page_node(h, nid) NULL +#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL #define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL @@ -518,19 +544,46 @@ struct hstate {}; #define vma_mmu_pagesize(v) PAGE_SIZE #define huge_page_order(h) 0 #define huge_page_shift(h) PAGE_SHIFT +static inline bool hstate_is_gigantic(struct hstate *h) +{ + return false; +} + static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } -#define hstate_index_to_shift(index) 0 -#define hstate_index(h) 0 + +static inline unsigned hstate_index_to_shift(unsigned index) +{ + return 0; +} + +static inline int hstate_index(struct hstate *h) +{ + return 0; +} static inline pgoff_t basepage_index(struct page *page) { return page->index; } -#define dissolve_free_huge_pages(s, e) 0 -#define hugepage_migration_supported(h) false + +static inline int dissolve_free_huge_page(struct page *page) +{ + return 0; +} + +static inline int dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn) +{ + return 0; +} + +static inline bool hugepage_migration_supported(struct hstate *h) +{ + return false; +} static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) @@ -545,6 +598,11 @@ static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } + +static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index e09fc8290c2f..c458d7b7ad19 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -124,10 +124,7 @@ struct hv_ring_buffer_info { spinlock_t ring_lock; u32 ring_datasize; /* < ring_size */ - u32 ring_data_startoffset; - u32 priv_write_index; u32 priv_read_index; - u32 cached_read_index; }; /* @@ -180,19 +177,6 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) return write; } -static inline u32 hv_get_cached_bytes_to_write( - const struct hv_ring_buffer_info *rbi) -{ - u32 read_loc, write_loc, dsize, write; - - dsize = rbi->ring_datasize; - read_loc = rbi->cached_read_index; - write_loc = rbi->ring_buffer->write_index; - - write = write_loc >= read_loc ? dsize - (write_loc - read_loc) : - read_loc - write_loc; - return write; -} /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. @@ -677,18 +661,6 @@ union hv_connection_id { } u; }; -/* Definition of the hv_signal_event hypercall input structure. */ -struct hv_input_signal_event { - union hv_connection_id connectionid; - u16 flag_number; - u16 rsvdz; -}; - -struct hv_input_signal_event_buffer { - u64 align8; - struct hv_input_signal_event event; -}; - enum hv_numa_policy { HV_BALANCED = 0, HV_LOCALIZED, @@ -744,7 +716,6 @@ struct vmbus_channel { u32 ringbuffer_pagecount; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ - spinlock_t inbound_lock; struct vmbus_close_msg close_msg; @@ -771,8 +742,7 @@ struct vmbus_channel { } callback_mode; bool is_dedicated_interrupt; - struct hv_input_signal_event_buffer sig_buf; - struct hv_input_signal_event *sig_event; + u64 sig_event; /* * Starting with win8, this field will be used to specify @@ -896,6 +866,8 @@ struct vmbus_channel { */ enum hv_numa_policy affinity_policy; + bool probe_done; + }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) @@ -1031,13 +1003,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -extern int vmbus_sendpacket_ctl(struct vmbus_channel *channel, - void *buffer, - u32 bufferLen, - u64 requestid, - enum vmbus_packet_type type, - u32 flags); - extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, struct hv_page_buffer pagebuffers[], u32 pagecount, @@ -1045,20 +1010,6 @@ extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, u32 bufferlen, u64 requestid); -extern int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, - void *buffer, - u32 bufferlen, - u64 requestid, - u32 flags); - -extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, - struct hv_multipage_buffer *mpb, - void *buffer, - u32 bufferlen, - u64 requestid); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, @@ -1187,8 +1138,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, resource_size_t size, resource_size_t align, bool fb_overlap_ok); void vmbus_free_mmio(resource_size_t start, resource_size_t size); -int vmbus_cpu_number_to_vp_number(int cpu_number); -u64 hv_do_hypercall(u64 control, void *input, void *output); /* * GUID definitions of various offer types - services offered to the guest. @@ -1475,55 +1424,6 @@ hv_get_ring_buffer(const struct hv_ring_buffer_info *ring_info) } /* - * To optimize the flow management on the send-side, - * when the sender is blocked because of lack of - * sufficient space in the ring buffer, potential the - * consumer of the ring buffer can signal the producer. - * This is controlled by the following parameters: - * - * 1. pending_send_sz: This is the size in bytes that the - * producer is trying to send. - * 2. The feature bit feat_pending_send_sz set to indicate if - * the consumer of the ring will signal when the ring - * state transitions from being full to a state where - * there is room for the producer to send the pending packet. - */ - -static inline void hv_signal_on_read(struct vmbus_channel *channel) -{ - u32 cur_write_sz, cached_write_sz; - u32 pending_sz; - struct hv_ring_buffer_info *rbi = &channel->inbound; - - /* - * Issue a full memory barrier before making the signaling decision. - * Here is the reason for having this barrier: - * If the reading of the pend_sz (in this function) - * were to be reordered and read before we commit the new read - * index (in the calling function) we could - * have a problem. If the host were to set the pending_sz after we - * have sampled pending_sz and go to sleep before we commit the - * read index, we could miss sending the interrupt. Issue a full - * memory barrier to address this. - */ - virt_mb(); - - pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); - /* If the other end is not blocked on write don't bother. */ - if (pending_sz == 0) - return; - - cur_write_sz = hv_get_bytes_to_write(rbi); - - if (cur_write_sz < pending_sz) - return; - - cached_write_sz = hv_get_cached_bytes_to_write(rbi); - if (cached_write_sz < pending_sz) - vmbus_setevent(channel); -} - -/* * Mask off host interrupt callback notifications */ static inline void hv_begin_read(struct hv_ring_buffer_info *rbi) diff --git a/include/linux/i2c-mux-pinctrl.h b/include/linux/i2c-mux-pinctrl.h deleted file mode 100644 index a65c86429e84..000000000000 --- a/include/linux/i2c-mux-pinctrl.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * i2c-mux-pinctrl platform data - * - * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef _LINUX_I2C_MUX_PINCTRL_H -#define _LINUX_I2C_MUX_PINCTRL_H - -/** - * struct i2c_mux_pinctrl_platform_data - Platform data for i2c-mux-pinctrl - * @parent_bus_num: Parent I2C bus number - * @base_bus_num: Base I2C bus number for the child busses. 0 for dynamic. - * @bus_count: Number of child busses. Also the number of elements in - * @pinctrl_states - * @pinctrl_states: The names of the pinctrl state to select for each child bus - * @pinctrl_state_idle: The pinctrl state to select when no child bus is being - * accessed. If NULL, the most recently used pinctrl state will be left - * selected. - */ -struct i2c_mux_pinctrl_platform_data { - int parent_bus_num; - int base_bus_num; - int bus_count; - const char **pinctrl_states; - const char *pinctrl_state_idle; -}; - -#endif diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 72d0ece70ed3..d501d3956f13 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -295,6 +295,8 @@ static inline int i2c_slave_event(struct i2c_client *client, { return client->slave_cb(client, event, val); } +#else +static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif /** @@ -687,7 +689,8 @@ i2c_unlock_adapter(struct i2c_adapter *adapter) #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ #define I2C_CLASS_DDC (1<<3) /* DDC bus on graphics adapters */ #define I2C_CLASS_SPD (1<<7) /* Memory modules */ -#define I2C_CLASS_DEPRECATED (1<<8) /* Warn users that adapter will stop using classes */ +/* Warn users that the adapter doesn't support classes anymore */ +#define I2C_CLASS_DEPRECATED (1<<8) /* Internal numbers to terminate lists */ #define I2C_CLIENT_END 0xfffeU diff --git a/include/linux/i2c/bfin_twi.h b/include/linux/i2c/bfin_twi.h deleted file mode 100644 index 135a4e0876ae..000000000000 --- a/include/linux/i2c/bfin_twi.h +++ /dev/null @@ -1,145 +0,0 @@ -/* - * i2c-bfin-twi.h - interface to ADI TWI controller - * - * Copyright 2005-2014 Analog Devices Inc. - * - * Licensed under the GPL-2 or later. - */ - -#ifndef __I2C_BFIN_TWI_H__ -#define __I2C_BFIN_TWI_H__ - -#include <linux/types.h> -#include <linux/i2c.h> - -/* - * ADI twi registers layout - */ -struct bfin_twi_regs { - u16 clkdiv; - u16 dummy1; - u16 control; - u16 dummy2; - u16 slave_ctl; - u16 dummy3; - u16 slave_stat; - u16 dummy4; - u16 slave_addr; - u16 dummy5; - u16 master_ctl; - u16 dummy6; - u16 master_stat; - u16 dummy7; - u16 master_addr; - u16 dummy8; - u16 int_stat; - u16 dummy9; - u16 int_mask; - u16 dummy10; - u16 fifo_ctl; - u16 dummy11; - u16 fifo_stat; - u16 dummy12; - u32 __pad[20]; - u16 xmt_data8; - u16 dummy13; - u16 xmt_data16; - u16 dummy14; - u16 rcv_data8; - u16 dummy15; - u16 rcv_data16; - u16 dummy16; -}; - -struct bfin_twi_iface { - int irq; - spinlock_t lock; - char read_write; - u8 command; - u8 *transPtr; - int readNum; - int writeNum; - int cur_mode; - int manual_stop; - int result; - struct i2c_adapter adap; - struct completion complete; - struct i2c_msg *pmsg; - int msg_num; - int cur_msg; - u16 saved_clkdiv; - u16 saved_control; - struct bfin_twi_regs __iomem *regs_base; -}; - -/* ******************** TWO-WIRE INTERFACE (TWI) MASKS ********************/ -/* TWI_CLKDIV Macros (Use: *pTWI_CLKDIV = CLKLOW(x)|CLKHI(y); ) */ -#define CLKLOW(x) ((x) & 0xFF) /* Periods Clock Is Held Low */ -#define CLKHI(y) (((y)&0xFF)<<0x8) /* Periods Before New Clock Low */ - -/* TWI_PRESCALE Masks */ -#define PRESCALE 0x007F /* SCLKs Per Internal Time Reference (10MHz) */ -#define TWI_ENA 0x0080 /* TWI Enable */ -#define SCCB 0x0200 /* SCCB Compatibility Enable */ - -/* TWI_SLAVE_CTL Masks */ -#define SEN 0x0001 /* Slave Enable */ -#define SADD_LEN 0x0002 /* Slave Address Length */ -#define STDVAL 0x0004 /* Slave Transmit Data Valid */ -#define NAK 0x0008 /* NAK Generated At Conclusion Of Transfer */ -#define GEN 0x0010 /* General Call Address Matching Enabled */ - -/* TWI_SLAVE_STAT Masks */ -#define SDIR 0x0001 /* Slave Transfer Direction (RX/TX*) */ -#define GCALL 0x0002 /* General Call Indicator */ - -/* TWI_MASTER_CTL Masks */ -#define MEN 0x0001 /* Master Mode Enable */ -#define MADD_LEN 0x0002 /* Master Address Length */ -#define MDIR 0x0004 /* Master Transmit Direction (RX/TX*) */ -#define FAST 0x0008 /* Use Fast Mode Timing Specs */ -#define STOP 0x0010 /* Issue Stop Condition */ -#define RSTART 0x0020 /* Repeat Start or Stop* At End Of Transfer */ -#define DCNT 0x3FC0 /* Data Bytes To Transfer */ -#define SDAOVR 0x4000 /* Serial Data Override */ -#define SCLOVR 0x8000 /* Serial Clock Override */ - -/* TWI_MASTER_STAT Masks */ -#define MPROG 0x0001 /* Master Transfer In Progress */ -#define LOSTARB 0x0002 /* Lost Arbitration Indicator (Xfer Aborted) */ -#define ANAK 0x0004 /* Address Not Acknowledged */ -#define DNAK 0x0008 /* Data Not Acknowledged */ -#define BUFRDERR 0x0010 /* Buffer Read Error */ -#define BUFWRERR 0x0020 /* Buffer Write Error */ -#define SDASEN 0x0040 /* Serial Data Sense */ -#define SCLSEN 0x0080 /* Serial Clock Sense */ -#define BUSBUSY 0x0100 /* Bus Busy Indicator */ - -/* TWI_INT_SRC and TWI_INT_ENABLE Masks */ -#define SINIT 0x0001 /* Slave Transfer Initiated */ -#define SCOMP 0x0002 /* Slave Transfer Complete */ -#define SERR 0x0004 /* Slave Transfer Error */ -#define SOVF 0x0008 /* Slave Overflow */ -#define MCOMP 0x0010 /* Master Transfer Complete */ -#define MERR 0x0020 /* Master Transfer Error */ -#define XMTSERV 0x0040 /* Transmit FIFO Service */ -#define RCVSERV 0x0080 /* Receive FIFO Service */ - -/* TWI_FIFO_CTRL Masks */ -#define XMTFLUSH 0x0001 /* Transmit Buffer Flush */ -#define RCVFLUSH 0x0002 /* Receive Buffer Flush */ -#define XMTINTLEN 0x0004 /* Transmit Buffer Interrupt Length */ -#define RCVINTLEN 0x0008 /* Receive Buffer Interrupt Length */ - -/* TWI_FIFO_STAT Masks */ -#define XMTSTAT 0x0003 /* Transmit FIFO Status */ -#define XMT_EMPTY 0x0000 /* Transmit FIFO Empty */ -#define XMT_HALF 0x0001 /* Transmit FIFO Has 1 Byte To Write */ -#define XMT_FULL 0x0003 /* Transmit FIFO Full (2 Bytes To Write) */ - -#define RCVSTAT 0x000C /* Receive FIFO Status */ -#define RCV_EMPTY 0x0000 /* Receive FIFO Empty */ -#define RCV_HALF 0x0004 /* Receive FIFO Has 1 Byte To Read */ -#define RCV_FULL 0x000C /* Receive FIFO Full (2 Bytes To Read) */ - -#endif diff --git a/include/linux/i2c/i2c-sh_mobile.h b/include/linux/i2c/i2c-sh_mobile.h deleted file mode 100644 index 06e3089795fb..000000000000 --- a/include/linux/i2c/i2c-sh_mobile.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __I2C_SH_MOBILE_H__ -#define __I2C_SH_MOBILE_H__ - -#include <linux/platform_device.h> - -struct i2c_sh_mobile_platform_data { - unsigned long bus_speed; - unsigned int clks_per_count; -}; - -#endif /* __I2C_SH_MOBILE_H__ */ diff --git a/include/linux/i2c/twl4030-madc.h b/include/linux/i2c/twl4030-madc.h deleted file mode 100644 index 1c0134dd3271..000000000000 --- a/include/linux/i2c/twl4030-madc.h +++ /dev/null @@ -1,147 +0,0 @@ -/* - * twl4030_madc.h - Header for TWL4030 MADC - * - * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/ - * J Keerthy <j-keerthy@ti.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - * - */ - -#ifndef _TWL4030_MADC_H -#define _TWL4030_MADC_H - -struct twl4030_madc_conversion_method { - u8 sel; - u8 avg; - u8 rbase; - u8 ctrl; -}; - -#define TWL4030_MADC_MAX_CHANNELS 16 - - -/* - * twl4030_madc_request- madc request packet for channel conversion - * @channels: 16 bit bitmap for individual channels - * @do_avgP: sample the input channel for 4 consecutive cycles - * @method: RT, SW1, SW2 - * @type: Polling or interrupt based method - * @raw: Return raw value, do not convert it - */ - -struct twl4030_madc_request { - unsigned long channels; - bool do_avg; - u16 method; - u16 type; - bool active; - bool result_pending; - bool raw; - int rbuf[TWL4030_MADC_MAX_CHANNELS]; - void (*func_cb)(int len, int channels, int *buf); -}; - -enum conversion_methods { - TWL4030_MADC_RT, - TWL4030_MADC_SW1, - TWL4030_MADC_SW2, - TWL4030_MADC_NUM_METHODS -}; - -enum sample_type { - TWL4030_MADC_WAIT, - TWL4030_MADC_IRQ_ONESHOT, - TWL4030_MADC_IRQ_REARM -}; - -#define TWL4030_MADC_CTRL1 0x00 -#define TWL4030_MADC_CTRL2 0x01 - -#define TWL4030_MADC_RTSELECT_LSB 0x02 -#define TWL4030_MADC_SW1SELECT_LSB 0x06 -#define TWL4030_MADC_SW2SELECT_LSB 0x0A - -#define TWL4030_MADC_RTAVERAGE_LSB 0x04 -#define TWL4030_MADC_SW1AVERAGE_LSB 0x08 -#define TWL4030_MADC_SW2AVERAGE_LSB 0x0C - -#define TWL4030_MADC_CTRL_SW1 0x12 -#define TWL4030_MADC_CTRL_SW2 0x13 - -#define TWL4030_MADC_RTCH0_LSB 0x17 -#define TWL4030_MADC_GPCH0_LSB 0x37 - -#define TWL4030_MADC_MADCON (1 << 0) /* MADC power on */ -#define TWL4030_MADC_BUSY (1 << 0) /* MADC busy */ -/* MADC conversion completion */ -#define TWL4030_MADC_EOC_SW (1 << 1) -/* MADC SWx start conversion */ -#define TWL4030_MADC_SW_START (1 << 5) -#define TWL4030_MADC_ADCIN0 (1 << 0) -#define TWL4030_MADC_ADCIN1 (1 << 1) -#define TWL4030_MADC_ADCIN2 (1 << 2) -#define TWL4030_MADC_ADCIN3 (1 << 3) -#define TWL4030_MADC_ADCIN4 (1 << 4) -#define TWL4030_MADC_ADCIN5 (1 << 5) -#define TWL4030_MADC_ADCIN6 (1 << 6) -#define TWL4030_MADC_ADCIN7 (1 << 7) -#define TWL4030_MADC_ADCIN8 (1 << 8) -#define TWL4030_MADC_ADCIN9 (1 << 9) -#define TWL4030_MADC_ADCIN10 (1 << 10) -#define TWL4030_MADC_ADCIN11 (1 << 11) -#define TWL4030_MADC_ADCIN12 (1 << 12) -#define TWL4030_MADC_ADCIN13 (1 << 13) -#define TWL4030_MADC_ADCIN14 (1 << 14) -#define TWL4030_MADC_ADCIN15 (1 << 15) - -/* Fixed channels */ -#define TWL4030_MADC_BTEMP TWL4030_MADC_ADCIN1 -#define TWL4030_MADC_VBUS TWL4030_MADC_ADCIN8 -#define TWL4030_MADC_VBKB TWL4030_MADC_ADCIN9 -#define TWL4030_MADC_ICHG TWL4030_MADC_ADCIN10 -#define TWL4030_MADC_VCHG TWL4030_MADC_ADCIN11 -#define TWL4030_MADC_VBAT TWL4030_MADC_ADCIN12 - -/* Step size and prescaler ratio */ -#define TEMP_STEP_SIZE 147 -#define TEMP_PSR_R 100 -#define CURR_STEP_SIZE 147 -#define CURR_PSR_R1 44 -#define CURR_PSR_R2 88 - -#define TWL4030_BCI_BCICTL1 0x23 -#define TWL4030_BCI_CGAIN 0x020 -#define TWL4030_BCI_MESBAT (1 << 1) -#define TWL4030_BCI_TYPEN (1 << 4) -#define TWL4030_BCI_ITHEN (1 << 3) - -#define REG_BCICTL2 0x024 -#define TWL4030_BCI_ITHSENS 0x007 - -/* Register and bits for GPBR1 register */ -#define TWL4030_REG_GPBR1 0x0c -#define TWL4030_GPBR1_MADC_HFCLK_EN (1 << 7) - -struct twl4030_madc_user_parms { - int channel; - int average; - int status; - u16 result; -}; - -int twl4030_madc_conversion(struct twl4030_madc_request *conv); -int twl4030_get_madc_conversion(int channel_no); -#endif diff --git a/include/linux/ide.h b/include/linux/ide.h index 6980ca322074..dc152e4b7f73 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -671,7 +671,7 @@ struct ide_port_ops { void (*init_dev)(ide_drive_t *); void (*set_pio_mode)(struct hwif_s *, ide_drive_t *); void (*set_dma_mode)(struct hwif_s *, ide_drive_t *); - int (*reset_poll)(ide_drive_t *); + blk_status_t (*reset_poll)(ide_drive_t *); void (*pre_reset)(ide_drive_t *); void (*resetproc)(ide_drive_t *); void (*maskproc)(ide_drive_t *, int); @@ -1092,7 +1092,7 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l extern int ide_vlb_clk; extern int ide_pci_clk; -int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int); +int ide_end_rq(ide_drive_t *, struct request *, blk_status_t, unsigned int); void ide_kill_rq(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); @@ -1123,7 +1123,7 @@ extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); -int ide_complete_rq(ide_drive_t *, int, unsigned int); +int ide_complete_rq(ide_drive_t *, blk_status_t, unsigned int); void ide_tf_readback(ide_drive_t *drive, struct ide_cmd *cmd); void ide_tf_dump(const char *, struct ide_cmd *); diff --git a/include/linux/idr.h b/include/linux/idr.h index bf70b3ef0a07..7c3a365f7e12 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -80,19 +80,75 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) */ void idr_preload(gfp_t gfp_mask); -int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t); + +int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index, + unsigned long start, unsigned long end, gfp_t gfp, + bool ext); + +/** + * idr_alloc - allocate an id + * @idr: idr handle + * @ptr: pointer to be associated with the new id + * @start: the minimum id (inclusive) + * @end: the maximum id (exclusive) + * @gfp: memory allocation flags + * + * Allocates an unused ID in the range [start, end). Returns -ENOSPC + * if there are no unused IDs in that range. + * + * Note that @end is treated as max when <= 0. This is to always allow + * using @start + N as @end as long as N is inside integer range. + * + * Simultaneous modifications to the @idr are not allowed and should be + * prevented by the user, usually with a lock. idr_alloc() may be called + * concurrently with read-only accesses to the @idr, such as idr_find() and + * idr_for_each_entry(). + */ +static inline int idr_alloc(struct idr *idr, void *ptr, + int start, int end, gfp_t gfp) +{ + unsigned long id; + int ret; + + if (WARN_ON_ONCE(start < 0)) + return -EINVAL; + + ret = idr_alloc_cmn(idr, ptr, &id, start, end, gfp, false); + + if (ret) + return ret; + + return id; +} + +static inline int idr_alloc_ext(struct idr *idr, void *ptr, + unsigned long *index, + unsigned long start, + unsigned long end, + gfp_t gfp) +{ + return idr_alloc_cmn(idr, ptr, index, start, end, gfp, true); +} + int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); +void *idr_get_next_ext(struct idr *idr, unsigned long *nextid); void *idr_replace(struct idr *, void *, int id); +void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id); void idr_destroy(struct idr *); -static inline void *idr_remove(struct idr *idr, int id) +static inline void *idr_remove_ext(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id, NULL); } +static inline void *idr_remove(struct idr *idr, int id) +{ + return idr_remove_ext(idr, id); +} + static inline void idr_init(struct idr *idr) { INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); @@ -128,11 +184,16 @@ static inline void idr_preload_end(void) * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. */ -static inline void *idr_find(const struct idr *idr, int id) +static inline void *idr_find_ext(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id); } +static inline void *idr_find(const struct idr *idr, int id) +{ + return idr_find_ext(idr, id); +} + /** * idr_for_each_entry - iterate over an idr's elements of a given type * @idr: idr handle @@ -145,6 +206,8 @@ static inline void *idr_find(const struct idr *idr, int id) */ #define idr_for_each_entry(idr, entry, id) \ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) +#define idr_for_each_entry_ext(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next_ext(idr, &(id))) != NULL; ++id) /** * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 69033353d0d1..55a604ad459f 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2113,10 +2113,43 @@ enum ieee80211_key_len { #define PMK_MAX_LEN 48 -/* Public action codes */ +/* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { + WLAN_PUB_ACTION_20_40_BSS_COEX = 0, + WLAN_PUB_ACTION_DSE_ENABLEMENT = 1, + WLAN_PUB_ACTION_DSE_DEENABLEMENT = 2, + WLAN_PUB_ACTION_DSE_REG_LOC_ANN = 3, WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, + WLAN_PUB_ACTION_DSE_MSMT_REQ = 5, + WLAN_PUB_ACTION_DSE_MSMT_RESP = 6, + WLAN_PUB_ACTION_MSMT_PILOT = 7, + WLAN_PUB_ACTION_DSE_PC = 8, + WLAN_PUB_ACTION_VENDOR_SPECIFIC = 9, + WLAN_PUB_ACTION_GAS_INITIAL_REQ = 10, + WLAN_PUB_ACTION_GAS_INITIAL_RESP = 11, + WLAN_PUB_ACTION_GAS_COMEBACK_REQ = 12, + WLAN_PUB_ACTION_GAS_COMEBACK_RESP = 13, WLAN_PUB_ACTION_TDLS_DISCOVER_RES = 14, + WLAN_PUB_ACTION_LOC_TRACK_NOTI = 15, + WLAN_PUB_ACTION_QAB_REQUEST_FRAME = 16, + WLAN_PUB_ACTION_QAB_RESPONSE_FRAME = 17, + WLAN_PUB_ACTION_QMF_POLICY = 18, + WLAN_PUB_ACTION_QMF_POLICY_CHANGE = 19, + WLAN_PUB_ACTION_QLOAD_REQUEST = 20, + WLAN_PUB_ACTION_QLOAD_REPORT = 21, + WLAN_PUB_ACTION_HCCA_TXOP_ADVERT = 22, + WLAN_PUB_ACTION_HCCA_TXOP_RESPONSE = 23, + WLAN_PUB_ACTION_PUBLIC_KEY = 24, + WLAN_PUB_ACTION_CHANNEL_AVAIL_QUERY = 25, + WLAN_PUB_ACTION_CHANNEL_SCHEDULE_MGMT = 26, + WLAN_PUB_ACTION_CONTACT_VERI_SIGNAL = 27, + WLAN_PUB_ACTION_GDD_ENABLEMENT_REQ = 28, + WLAN_PUB_ACTION_GDD_ENABLEMENT_RESP = 29, + WLAN_PUB_ACTION_NETWORK_CHANNEL_CONTROL = 30, + WLAN_PUB_ACTION_WHITE_SPACE_MAP_ANN = 31, + WLAN_PUB_ACTION_FTM_REQUEST = 32, + WLAN_PUB_ACTION_FTM = 33, + WLAN_PUB_ACTION_FILS_DISCOVERY = 34, }; /* TDLS action codes */ @@ -2400,7 +2433,11 @@ enum ieee80211_sa_query_action { #define WLAN_MAX_KEY_LEN 32 +#define WLAN_PMK_NAME_LEN 16 #define WLAN_PMKID_LEN 16 +#define WLAN_PMK_LEN_EAP_LEAP 16 +#define WLAN_PMK_LEN 32 +#define WLAN_PMK_LEN_SUITE_B_192 48 #define WLAN_OUI_WFA 0x506f9a #define WLAN_OUI_TYPE_WFA_P2P 9 diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 0c16866a7aac..3cd18ac0697f 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -62,6 +62,7 @@ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); +bool br_multicast_enabled(const struct net_device *dev); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -78,6 +79,19 @@ static inline bool br_multicast_has_querier_adjacent(struct net_device *dev, { return false; } +static inline bool br_multicast_enabled(const struct net_device *dev) +{ + return false; +} +#endif + +#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) +bool br_vlan_enabled(const struct net_device *dev); +#else +static inline bool br_vlan_enabled(const struct net_device *dev) +{ + return false; +} #endif #endif diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h index 3482c3c2037d..4837157da0dc 100644 --- a/include/linux/if_tap.h +++ b/include/linux/if_tap.h @@ -3,6 +3,7 @@ #if IS_ENABLED(CONFIG_TAP) struct socket *tap_get_socket(struct file *); +struct skb_array *tap_get_skb_array(struct file *file); #else #include <linux/err.h> #include <linux/errno.h> @@ -12,6 +13,10 @@ static inline struct socket *tap_get_socket(struct file *f) { return ERR_PTR(-EINVAL); } +static inline struct skb_array *tap_get_skb_array(struct file *f) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_TAP */ #include <net/sock.h> diff --git a/include/linux/if_team.h b/include/linux/if_team.h index c05216a8fbac..30294603526f 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -298,4 +298,6 @@ extern void team_mode_unregister(const struct team_mode *mode); #define TEAM_DEFAULT_NUM_TX_QUEUES 16 #define TEAM_DEFAULT_NUM_RX_QUEUES 16 +#define MODULE_ALIAS_TEAM_MODE(kind) MODULE_ALIAS("team-mode-" kind) + #endif /* _LINUX_IF_TEAM_H_ */ diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index ed6da2e6df90..bf9bdf42d577 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -19,6 +19,7 @@ #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); +struct skb_array *tun_get_skb_array(struct file *file); #else #include <linux/err.h> #include <linux/errno.h> @@ -28,5 +29,9 @@ static inline struct socket *tun_get_socket(struct file *f) { return ERR_PTR(-EINVAL); } +static inline struct skb_array *tun_get_skb_array(struct file *f) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_TUN */ #endif /* __IF_TUN_H */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 283dc2f5364d..5e6a2d4dc366 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -318,7 +318,7 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; - veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN); + veth = skb_push(skb, VLAN_HLEN); /* Move the mac addresses to the beginning of the new header. */ memmove(skb->data, skb->data + VLAN_HLEN, 2 * ETH_ALEN); diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 12f6fba6d21a..f8231854b5d6 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -18,6 +18,7 @@ #include <linux/skbuff.h> #include <linux/timer.h> #include <linux/in.h> +#include <linux/refcount.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) @@ -84,7 +85,7 @@ struct ip_mc_list { struct ip_mc_list __rcu *next_hash; struct timer_list timer; int users; - atomic_t refcnt; + refcount_t refcnt; spinlock_t lock; char tm_running; char reporter; @@ -117,7 +118,8 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen); -extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif); +extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, + int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 497f2b3a5a62..7b0fa8b5c120 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -105,6 +105,11 @@ struct st_sensor_fullscale { struct st_sensor_fullscale_avl fs_avl[ST_SENSORS_FULLSCALE_AVL_MAX]; }; +struct st_sensor_sim { + u8 addr; + u8 value; +}; + /** * struct st_sensor_bdu - ST sensor device block data update * @addr: address of the register. @@ -197,6 +202,7 @@ struct st_sensor_transfer_function { * @bdu: Block data update register. * @das: Data Alignment Selection register. * @drdy_irq: Data ready register of the sensor. + * @sim: SPI serial interface mode register of the sensor. * @multi_read_bit: Use or not particular bit for [I2C/SPI] multi-read. * @bootime: samples to discard when sensor passing from power-down to power-up. */ @@ -213,6 +219,7 @@ struct st_sensor_settings { struct st_sensor_bdu bdu; struct st_sensor_das das; struct st_sensor_data_ready_irq drdy_irq; + struct st_sensor_sim sim; bool multi_read_bit; unsigned int bootime; }; @@ -325,4 +332,16 @@ ssize_t st_sensors_sysfs_sampling_frequency_avail(struct device *dev, ssize_t st_sensors_sysfs_scale_avail(struct device *dev, struct device_attribute *attr, char *buf); +#ifdef CONFIG_OF +void st_sensors_of_name_probe(struct device *dev, + const struct of_device_id *match, + char *name, int len); +#else +static inline void st_sensors_of_name_probe(struct device *dev, + const struct of_device_id *match, + char *name, int len) +{ +} +#endif + #endif /* ST_SENSORS_H */ diff --git a/include/linux/iio/common/st_sensors_i2c.h b/include/linux/iio/common/st_sensors_i2c.h index 254de3c7dde8..0a2c25e06d1f 100644 --- a/include/linux/iio/common/st_sensors_i2c.h +++ b/include/linux/iio/common/st_sensors_i2c.h @@ -18,16 +18,6 @@ void st_sensors_i2c_configure(struct iio_dev *indio_dev, struct i2c_client *client, struct st_sensor_data *sdata); -#ifdef CONFIG_OF -void st_sensors_of_i2c_probe(struct i2c_client *client, - const struct of_device_id *match); -#else -static inline void st_sensors_of_i2c_probe(struct i2c_client *client, - const struct of_device_id *match) -{ -} -#endif - #ifdef CONFIG_ACPI int st_sensors_match_acpi_device(struct device *dev); #else diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 47eeec3218b5..5e347a9805fd 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -312,4 +312,41 @@ int iio_read_channel_scale(struct iio_channel *chan, int *val, int iio_convert_raw_to_processed(struct iio_channel *chan, int raw, int *processed, unsigned int scale); +/** + * iio_get_channel_ext_info_count() - get number of ext_info attributes + * connected to the channel. + * @chan: The channel being queried + * + * Returns the number of ext_info attributes + */ +unsigned int iio_get_channel_ext_info_count(struct iio_channel *chan); + +/** + * iio_read_channel_ext_info() - read ext_info attribute from a given channel + * @chan: The channel being queried. + * @attr: The ext_info attribute to read. + * @buf: Where to store the attribute value. Assumed to hold + * at least PAGE_SIZE bytes. + * + * Returns the number of bytes written to buf (perhaps w/o zero termination; + * it need not even be a string), or an error code. + */ +ssize_t iio_read_channel_ext_info(struct iio_channel *chan, + const char *attr, char *buf); + +/** + * iio_write_channel_ext_info() - write ext_info attribute from a given channel + * @chan: The channel being queried. + * @attr: The ext_info attribute to read. + * @buf: The new attribute value. Strings needs to be zero- + * terminated, but the terminator should not be included + * in the below len. + * @len: The size of the new attribute value. + * + * Returns the number of accepted bytes, which should be the same as len. + * An error code can also be returned. + */ +ssize_t iio_write_channel_ext_info(struct iio_channel *chan, const char *attr, + const char *buf, size_t len); + #endif diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 3f5ea2e9a39e..c380daa40c0e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -352,10 +352,16 @@ unsigned int iio_get_time_res(const struct iio_dev *indio_dev); #define INDIO_BUFFER_SOFTWARE 0x04 #define INDIO_BUFFER_HARDWARE 0x08 #define INDIO_EVENT_TRIGGERED 0x10 +#define INDIO_HARDWARE_TRIGGERED 0x20 #define INDIO_ALL_BUFFER_MODES \ (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | INDIO_BUFFER_SOFTWARE) +#define INDIO_ALL_TRIGGERED_MODES \ + (INDIO_BUFFER_TRIGGERED \ + | INDIO_EVENT_TRIGGERED \ + | INDIO_HARDWARE_TRIGGERED) + #define INDIO_MAX_RAW_ELEMENTS 4 struct iio_trigger; /* forward declaration */ @@ -529,7 +535,7 @@ struct iio_buffer_setup_ops { * @scan_timestamp: [INTERN] set if any buffers have requested timestamp * @scan_index_timestamp:[INTERN] cache of the index to the timestamp * @trig: [INTERN] current device trigger (buffer modes) - * @trig_readonly [INTERN] mark the current trigger immutable + * @trig_readonly: [INTERN] mark the current trigger immutable * @pollfunc: [DRIVER] function run on trigger being received * @pollfunc_event: [DRIVER] function run on events trigger being received * @channels: [DRIVER] channel specification structure table diff --git a/include/linux/iio/timer/stm32-lptim-trigger.h b/include/linux/iio/timer/stm32-lptim-trigger.h new file mode 100644 index 000000000000..34d59bfdce2d --- /dev/null +++ b/include/linux/iio/timer/stm32-lptim-trigger.h @@ -0,0 +1,27 @@ +/* + * Copyright (C) STMicroelectronics 2017 + * + * Author: Fabrice Gasnier <fabrice.gasnier@st.com> + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#ifndef _STM32_LPTIM_TRIGGER_H_ +#define _STM32_LPTIM_TRIGGER_H_ + +#include <linux/iio/iio.h> +#include <linux/iio/trigger.h> + +#define LPTIM1_OUT "lptim1_out" +#define LPTIM2_OUT "lptim2_out" +#define LPTIM3_OUT "lptim3_out" + +#if IS_ENABLED(CONFIG_IIO_STM32_LPTIMER_TRIGGER) +bool is_stm32_lptim_trigger(struct iio_trigger *trig); +#else +static inline bool is_stm32_lptim_trigger(struct iio_trigger *trig) +{ + return false; +} +#endif +#endif diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h index 55535aef2e6c..d68add80ab86 100644 --- a/include/linux/iio/timer/stm32-timer-trigger.h +++ b/include/linux/iio/timer/stm32-timer-trigger.h @@ -10,6 +10,7 @@ #define _STM32_TIMER_TRIGGER_H_ #define TIM1_TRGO "tim1_trgo" +#define TIM1_TRGO2 "tim1_trgo2" #define TIM1_CH1 "tim1_ch1" #define TIM1_CH2 "tim1_ch2" #define TIM1_CH3 "tim1_ch3" @@ -44,6 +45,7 @@ #define TIM7_TRGO "tim7_trgo" #define TIM8_TRGO "tim8_trgo" +#define TIM8_TRGO2 "tim8_trgo2" #define TIM8_CH1 "tim8_ch1" #define TIM8_CH2 "tim8_ch2" #define TIM8_CH3 "tim8_ch3" @@ -53,10 +55,24 @@ #define TIM9_CH1 "tim9_ch1" #define TIM9_CH2 "tim9_ch2" +#define TIM10_OC1 "tim10_oc1" + +#define TIM11_OC1 "tim11_oc1" + #define TIM12_TRGO "tim12_trgo" #define TIM12_CH1 "tim12_ch1" #define TIM12_CH2 "tim12_ch2" +#define TIM13_OC1 "tim13_oc1" + +#define TIM14_OC1 "tim14_oc1" + +#define TIM15_TRGO "tim15_trgo" + +#define TIM16_OC1 "tim16_oc1" + +#define TIM17_OC1 "tim17_oc1" + bool is_stm32_timer_trigger(struct iio_trigger *trig); #endif diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index ea08302f2d7b..7142d8d6e470 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -144,8 +144,8 @@ void devm_iio_trigger_unregister(struct device *dev, /** * iio_trigger_set_immutable() - set an immutable trigger on destination * - * @indio_dev - IIO device structure containing the device - * @trig - trigger to assign to device + * @indio_dev: IIO device structure containing the device + * @trig: trigger to assign to device * **/ int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); diff --git a/include/linux/ima.h b/include/linux/ima.h index 7f6952f8d6aa..0e4647e0eb60 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -75,11 +75,17 @@ static inline void ima_add_kexec_buffer(struct kimage *image) #endif #ifdef CONFIG_IMA_APPRAISE +extern bool is_ima_appraise_enabled(void); extern void ima_inode_post_setattr(struct dentry *dentry); extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name); #else +static inline bool is_ima_appraise_enabled(void) +{ + return 0; +} + static inline void ima_inode_post_setattr(struct dentry *dentry) { return; diff --git a/include/linux/imx-media.h b/include/linux/imx-media.h new file mode 100644 index 000000000000..77221ecad6fc --- /dev/null +++ b/include/linux/imx-media.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2014-2017 Mentor Graphics Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the + * License, or (at your option) any later version + */ + +#ifndef __LINUX_IMX_MEDIA_H__ +#define __LINUX_IMX_MEDIA_H__ + +/* + * events from the subdevs + */ +#define V4L2_EVENT_IMX_CLASS V4L2_EVENT_PRIVATE_START +#define V4L2_EVENT_IMX_FRAME_INTERVAL_ERROR (V4L2_EVENT_IMX_CLASS + 1) + +enum imx_ctrl_id { + V4L2_CID_IMX_FIM_ENABLE = (V4L2_CID_USER_IMX_BASE + 0), + V4L2_CID_IMX_FIM_NUM, + V4L2_CID_IMX_FIM_TOLERANCE_MIN, + V4L2_CID_IMX_FIM_TOLERANCE_MAX, + V4L2_CID_IMX_FIM_NUM_SKIP, + V4L2_CID_IMX_FIM_ICAP_EDGE, + V4L2_CID_IMX_FIM_ICAP_CHANNEL, +}; + +#endif diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 65da430e260f..ee251c585854 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -25,6 +25,13 @@ struct inet_diag_handler { struct inet_diag_msg *r, void *info); + int (*idiag_get_aux)(struct sock *sk, + bool net_admin, + struct sk_buff *skb); + + size_t (*idiag_get_aux_size)(struct sock *sk, + bool net_admin); + int (*destroy)(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a2e9d6ea1349..fb3f809e34e4 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -11,6 +11,7 @@ #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> +#include <linux/refcount.h> struct ipv4_devconf { void *sysctl; @@ -22,7 +23,7 @@ struct ipv4_devconf { struct in_device { struct net_device *dev; - atomic_t refcnt; + refcount_t refcnt; int dead; struct in_ifaddr *ifa_list; /* IP ifaddr chain */ @@ -150,8 +151,15 @@ struct in_ifaddr { unsigned long ifa_tstamp; /* updated timestamp */ }; +struct in_validator_info { + __be32 ivi_addr; + struct in_device *ivi_dev; +}; + int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); +int register_inetaddr_validator_notifier(struct notifier_block *nb); +int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); @@ -212,7 +220,7 @@ static inline struct in_device *in_dev_get(const struct net_device *dev) rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) - atomic_inc(&in_dev->refcnt); + refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } @@ -233,12 +241,12 @@ void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { - if (atomic_dec_and_test(&idev->refcnt)) + if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } -#define __in_dev_put(idev) atomic_dec(&(idev)->refcnt) -#define in_dev_hold(idev) atomic_inc(&(idev)->refcnt) +#define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) +#define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index e049526bc188..3c07ace5b431 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -126,17 +126,11 @@ extern struct group_info init_groups; #endif #ifdef CONFIG_PREEMPT_RCU -#define INIT_TASK_RCU_TREE_PREEMPT() \ - .rcu_blocked_node = NULL, -#else -#define INIT_TASK_RCU_TREE_PREEMPT(tsk) -#endif -#ifdef CONFIG_PREEMPT_RCU #define INIT_TASK_RCU_PREEMPT(tsk) \ .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special.s = 0, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ - INIT_TASK_RCU_TREE_PREEMPT() + .rcu_blocked_node = NULL, #else #define INIT_TASK_RCU_PREEMPT(tsk) #endif @@ -170,9 +164,9 @@ extern struct cred init_cred; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN # define INIT_VTIME(tsk) \ - .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ - .vtime_snap = 0, \ - .vtime_snap_whence = VTIME_SYS, + .vtime.seqcount = SEQCNT_ZERO(tsk.vtime.seqcount), \ + .vtime.starttime = 0, \ + .vtime.state = VTIME_SYS, #else # define INIT_VTIME(tsk) #endif @@ -181,9 +175,8 @@ extern struct cred init_cred; #ifdef CONFIG_RT_MUTEXES # define INIT_RT_MUTEXES(tsk) \ - .pi_waiters = RB_ROOT, \ - .pi_top_task = NULL, \ - .pi_waiters_leftmost = NULL, + .pi_waiters = RB_ROOT_CACHED, \ + .pi_top_task = NULL, #else # define INIT_RT_MUTEXES(tsk) #endif diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 55289d261b4f..bc67b767f9ce 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -10,6 +10,9 @@ extern int rd_prompt; /* starting block # of image */ extern int rd_image_start; +/* size of a single RAM disk */ +extern unsigned long rd_size; + /* 1 if it is not an error if initrd_start < memory_start */ extern int initrd_below_start_ok; diff --git a/include/linux/input/sparse-keymap.h b/include/linux/input/sparse-keymap.h index 52db62064c6e..c7346e33d958 100644 --- a/include/linux/input/sparse-keymap.h +++ b/include/linux/input/sparse-keymap.h @@ -51,7 +51,6 @@ struct key_entry *sparse_keymap_entry_from_keycode(struct input_dev *dev, int sparse_keymap_setup(struct input_dev *dev, const struct key_entry *keymap, int (*setup)(struct input_dev *, struct key_entry *)); -void sparse_keymap_free(struct input_dev *dev); void sparse_keymap_report_entry(struct input_dev *dev, const struct key_entry *ke, unsigned int value, bool autorelease); diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 3c25794042f9..99bc5b3ae26e 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -102,6 +102,21 @@ extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, */ extern int intel_svm_unbind_mm(struct device *dev, int pasid); +/** + * intel_svm_is_pasid_valid() - check if pasid is valid + * @dev: Device for which PASID was allocated + * @pasid: PASID value to be checked + * + * This function checks if the specified pasid is still valid. A + * valid pasid means the backing mm is still having a valid user. + * For kernel callers init_mm is always valid. for other mm, if mm->mm_users + * is non-zero, it is valid. + * + * returns -EINVAL if invalid pasid, 0 if pasid ref count is invalid + * 1 if pasid is valid. + */ +extern int intel_svm_is_pasid_valid(struct device *dev, int pasid); + #else /* CONFIG_INTEL_IOMMU_SVM */ static inline int intel_svm_bind_mm(struct device *dev, int *pasid, @@ -114,6 +129,11 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid) { BUG(); } + +static int intel_svm_is_pasid_valid(struct device *dev, int pasid) +{ + return -EINVAL; +} #endif /* CONFIG_INTEL_IOMMU_SVM */ #define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL)) diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a6fba4804672..59ba11661b6e 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -18,6 +18,7 @@ #include <linux/atomic.h> #include <asm/ptrace.h> #include <asm/irq.h> +#include <asm/sections.h> /* * These correspond to the IORESOURCE_IRQ_* defines in @@ -152,8 +153,17 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id); extern int __must_check +__request_percpu_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, const char *devname, + void __percpu *percpu_dev_id); + +static inline int __must_check request_percpu_irq(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *percpu_dev_id); + const char *devname, void __percpu *percpu_dev_id) +{ + return __request_percpu_irq(irq, handler, 0, + devname, percpu_dev_id); +} extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); @@ -291,7 +301,7 @@ extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); struct cpumask *irq_create_affinity_masks(int nvec, const struct irq_affinity *affd); -int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd); +int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd); #else /* CONFIG_SMP */ @@ -331,7 +341,7 @@ irq_create_affinity_masks(int nvec, const struct irq_affinity *affd) } static inline int -irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd) +irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd) { return maxvec; } @@ -703,6 +713,12 @@ static inline void init_irq_proc(void) } #endif +#ifdef CONFIG_IRQ_TIMINGS +void irq_timings_enable(void); +void irq_timings_disable(void); +u64 irq_timings_next_event(u64 now); +#endif + struct seq_file; int show_interrupts(struct seq_file *p, void *v); int arch_show_interrupts(struct seq_file *p, int prec); @@ -711,7 +727,6 @@ extern int early_irq_init(void); extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) /* * We want to know which function is an entrypoint of a hardirq or a softirq. */ @@ -719,16 +734,4 @@ extern int arch_early_irq_init(void); #define __softirq_entry \ __attribute__((__section__(".softirqentry.text"))) -/* Limits of hardirq entrypoints */ -extern char __irqentry_text_start[]; -extern char __irqentry_text_end[]; -/* Limits of softirq entrypoints */ -extern char __softirqentry_text_start[]; -extern char __softirqentry_text_end[]; - -#else -#define __irq_entry -#define __softirq_entry -#endif - #endif diff --git a/include/linux/interval_tree.h b/include/linux/interval_tree.h index 724556aa3c95..202ee1283f4b 100644 --- a/include/linux/interval_tree.h +++ b/include/linux/interval_tree.h @@ -11,13 +11,15 @@ struct interval_tree_node { }; extern void -interval_tree_insert(struct interval_tree_node *node, struct rb_root *root); +interval_tree_insert(struct interval_tree_node *node, + struct rb_root_cached *root); extern void -interval_tree_remove(struct interval_tree_node *node, struct rb_root *root); +interval_tree_remove(struct interval_tree_node *node, + struct rb_root_cached *root); extern struct interval_tree_node * -interval_tree_iter_first(struct rb_root *root, +interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); extern struct interval_tree_node * diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h index 58370e1862ad..1f97ce26cccc 100644 --- a/include/linux/interval_tree_generic.h +++ b/include/linux/interval_tree_generic.h @@ -33,7 +33,7 @@ * ITSTATIC: 'static' or empty * ITPREFIX: prefix to use for the inline tree definitions * - * Note - before using this, please consider if non-generic version + * Note - before using this, please consider if generic version * (interval_tree.h) would work for you... */ @@ -65,11 +65,13 @@ RB_DECLARE_CALLBACKS(static, ITPREFIX ## _augment, ITSTRUCT, ITRB, \ \ /* Insert / remove interval nodes from the tree */ \ \ -ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, struct rb_root *root) \ +ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, \ + struct rb_root_cached *root) \ { \ - struct rb_node **link = &root->rb_node, *rb_parent = NULL; \ + struct rb_node **link = &root->rb_root.rb_node, *rb_parent = NULL; \ ITTYPE start = ITSTART(node), last = ITLAST(node); \ ITSTRUCT *parent; \ + bool leftmost = true; \ \ while (*link) { \ rb_parent = *link; \ @@ -78,18 +80,22 @@ ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, struct rb_root *root) \ parent->ITSUBTREE = last; \ if (start < ITSTART(parent)) \ link = &parent->ITRB.rb_left; \ - else \ + else { \ link = &parent->ITRB.rb_right; \ + leftmost = false; \ + } \ } \ \ node->ITSUBTREE = last; \ rb_link_node(&node->ITRB, rb_parent, link); \ - rb_insert_augmented(&node->ITRB, root, &ITPREFIX ## _augment); \ + rb_insert_augmented_cached(&node->ITRB, root, \ + leftmost, &ITPREFIX ## _augment); \ } \ \ -ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, struct rb_root *root) \ +ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, \ + struct rb_root_cached *root) \ { \ - rb_erase_augmented(&node->ITRB, root, &ITPREFIX ## _augment); \ + rb_erase_augmented_cached(&node->ITRB, root, &ITPREFIX ## _augment); \ } \ \ /* \ @@ -140,15 +146,35 @@ ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last) \ } \ \ ITSTATIC ITSTRUCT * \ -ITPREFIX ## _iter_first(struct rb_root *root, ITTYPE start, ITTYPE last) \ +ITPREFIX ## _iter_first(struct rb_root_cached *root, \ + ITTYPE start, ITTYPE last) \ { \ - ITSTRUCT *node; \ + ITSTRUCT *node, *leftmost; \ \ - if (!root->rb_node) \ + if (!root->rb_root.rb_node) \ return NULL; \ - node = rb_entry(root->rb_node, ITSTRUCT, ITRB); \ + \ + /* \ + * Fastpath range intersection/overlap between A: [a0, a1] and \ + * B: [b0, b1] is given by: \ + * \ + * a0 <= b1 && b0 <= a1 \ + * \ + * ... where A holds the lock range and B holds the smallest \ + * 'start' and largest 'last' in the tree. For the later, we \ + * rely on the root node, which by augmented interval tree \ + * property, holds the largest value in its last-in-subtree. \ + * This allows mitigating some of the tree walk overhead for \ + * for non-intersecting ranges, maintained and consulted in O(1). \ + */ \ + node = rb_entry(root->rb_root.rb_node, ITSTRUCT, ITRB); \ if (node->ITSUBTREE < start) \ return NULL; \ + \ + leftmost = rb_entry(root->rb_leftmost, ITSTRUCT, ITRB); \ + if (ITSTART(leftmost) > last) \ + return NULL; \ + \ return ITPREFIX ## _subtree_search(node, start, last); \ } \ \ diff --git a/include/linux/io.h b/include/linux/io.h index 2195d9ea4aaa..32e30e8fb9db 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -157,6 +157,8 @@ enum { MEMREMAP_WB = 1 << 0, MEMREMAP_WT = 1 << 1, MEMREMAP_WC = 1 << 2, + MEMREMAP_ENC = 1 << 3, + MEMREMAP_DEC = 1 << 4, }; void *memremap(resource_size_t offset, size_t size, unsigned long flags); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index f753e788da31..f64dc6ce5161 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -52,6 +52,7 @@ struct iomap { #define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ #define IOMAP_FAULT (1 << 3) /* mapping for page fault */ #define IOMAP_DIRECT (1 << 4) /* direct I/O */ +#define IOMAP_NOWAIT (1 << 5) /* Don't wait for writeback */ struct iomap_ops { /* @@ -83,6 +84,10 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, const struct iomap_ops *ops); +loff_t iomap_seek_hole(struct inode *inode, loff_t offset, + const struct iomap_ops *ops); +loff_t iomap_seek_data(struct inode *inode, loff_t offset, + const struct iomap_ops *ops); /* * Flags for direct I/O ->end_io: diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2cb54adc4a33..a7f2ac689d29 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,6 +167,10 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain + * @tlb_range_add: Add a given iova range to the flush queue for this domain + * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush + * queue * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping @@ -199,6 +203,10 @@ struct iommu_ops { size_t size); size_t (*map_sg)(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot); + void (*flush_iotlb_all)(struct iommu_domain *domain); + void (*iotlb_range_add)(struct iommu_domain *domain, + unsigned long iova, size_t size); + void (*iotlb_sync)(struct iommu_domain *domain); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); void (*remove_device)(struct device *dev); @@ -225,6 +233,7 @@ struct iommu_ops { u32 (*domain_get_windows)(struct iommu_domain *domain); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); + bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); unsigned long pgsize_bitmap; }; @@ -240,7 +249,7 @@ struct iommu_device { struct list_head list; const struct iommu_ops *ops; struct fwnode_handle *fwnode; - struct device dev; + struct device *dev; }; int iommu_device_register(struct iommu_device *iommu); @@ -265,6 +274,11 @@ static inline void iommu_device_set_fwnode(struct iommu_device *iommu, iommu->fwnode = fwnode; } +static inline struct iommu_device *dev_to_iommu_device(struct device *dev) +{ + return (struct iommu_device *)dev_get_drvdata(dev); +} + #define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ #define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ #define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ @@ -286,7 +300,9 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size); + size_t size); +extern size_t iommu_unmap_fast(struct iommu_domain *domain, + unsigned long iova, size_t size); extern size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg,unsigned int nents, int prot); @@ -343,6 +359,25 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); +static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +{ + if (domain->ops->flush_iotlb_all) + domain->ops->flush_iotlb_all(domain); +} + +static inline void iommu_tlb_range_add(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + if (domain->ops->iotlb_range_add) + domain->ops->iotlb_range_add(domain, iova, size); +} + +static inline void iommu_tlb_sync(struct iommu_domain *domain) +{ + if (domain->ops->iotlb_sync) + domain->ops->iotlb_sync(domain); +} + static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) @@ -425,13 +460,19 @@ static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) } static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, int gfp_order, int prot) + phys_addr_t paddr, size_t size, int prot) { return -ENODEV; } static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, - int gfp_order) + size_t size) +{ + return -ENODEV; +} + +static inline int iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, + int gfp_order) { return -ENODEV; } @@ -443,6 +484,19 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain, return -ENODEV; } +static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +{ +} + +static inline void iommu_tlb_range_add(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ +} + +static inline void iommu_tlb_sync(struct iommu_domain *domain) +{ +} + static inline int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) @@ -589,6 +643,11 @@ static inline void iommu_device_set_fwnode(struct iommu_device *iommu, { } +static inline struct iommu_device *dev_to_iommu_device(struct device *dev) +{ + return NULL; +} + static inline void iommu_device_unregister(struct iommu_device *iommu) { } diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 6230064d7f95..f5cf32e80041 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -130,6 +130,8 @@ enum { IORES_DESC_ACPI_NV_STORAGE = 3, IORES_DESC_PERSISTENT_MEMORY = 4, IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, + IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, + IORES_DESC_DEVICE_PUBLIC_MEMORY = 7, }; /* helpers to define resources */ diff --git a/include/linux/iova.h b/include/linux/iova.h index e0a892ae45c0..d179b9bf7814 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/rbtree.h> +#include <linux/atomic.h> #include <linux/dma-mapping.h> /* iova structure */ @@ -36,6 +37,35 @@ struct iova_rcache { struct iova_cpu_rcache __percpu *cpu_rcaches; }; +struct iova_domain; + +/* Call-Back from IOVA code into IOMMU drivers */ +typedef void (* iova_flush_cb)(struct iova_domain *domain); + +/* Destructor for per-entry data */ +typedef void (* iova_entry_dtor)(unsigned long data); + +/* Number of entries per Flush Queue */ +#define IOVA_FQ_SIZE 256 + +/* Timeout (in ms) after which entries are flushed from the Flush-Queue */ +#define IOVA_FQ_TIMEOUT 10 + +/* Flush Queue entry for defered flushing */ +struct iova_fq_entry { + unsigned long iova_pfn; + unsigned long pages; + unsigned long data; + u64 counter; /* Flush counter when this entrie was added */ +}; + +/* Per-CPU Flush Queue structure */ +struct iova_fq { + struct iova_fq_entry entries[IOVA_FQ_SIZE]; + unsigned head, tail; + spinlock_t lock; +}; + /* holds all the iova translations for a domain */ struct iova_domain { spinlock_t iova_rbtree_lock; /* Lock to protect update of rbtree */ @@ -45,6 +75,25 @@ struct iova_domain { unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ + + iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU + TLBs */ + + iova_entry_dtor entry_dtor; /* IOMMU driver specific destructor for + iova entry */ + + struct iova_fq __percpu *fq; /* Flush Queue */ + + atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that + have been started */ + + atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that + have been finished */ + + struct timer_list fq_timer; /* Timer to regularily empty the + flush-queues */ + atomic_t fq_timer_on; /* 1 when timer is active, 0 + when not */ }; static inline unsigned long iova_size(struct iova *iova) @@ -95,6 +144,9 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, bool size_aligned); void free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size); +void queue_iova(struct iova_domain *iovad, + unsigned long pfn, unsigned long pages, + unsigned long data); unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, @@ -102,6 +154,8 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn, unsigned long pfn_32bit); +int init_iova_flush_queue(struct iova_domain *iovad, + iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); struct iova *split_and_remove_iova(struct iova_domain *iovad, @@ -148,6 +202,12 @@ static inline void free_iova_fast(struct iova_domain *iovad, { } +static inline void queue_iova(struct iova_domain *iovad, + unsigned long pfn, unsigned long pages, + unsigned long data) +{ +} + static inline unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn) @@ -174,6 +234,13 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } +static inline int init_iova_flush_queue(struct iova_domain *iovad, + iova_flush_cb flush_cb, + iova_entry_dtor entry_dtor) +{ + return -ENODEV; +} + static inline struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn) { diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 71fd92d81b26..92a2ccff80c5 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -3,7 +3,9 @@ #include <linux/spinlock.h> #include <linux/uidgid.h> +#include <linux/rhashtable.h> #include <uapi/linux/ipc.h> +#include <linux/refcount.h> #define IPCMNI 32768 /* <= MAX_INT limit for ipc arrays (including sysctl changes) */ @@ -20,6 +22,11 @@ struct kern_ipc_perm { umode_t mode; unsigned long seq; void *security; -} ____cacheline_aligned_in_smp; + + struct rhash_head khtnode; + + struct rcu_head rcu; + refcount_t refcount; +} ____cacheline_aligned_in_smp __randomize_layout; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 848e5796400e..83f0bf7a587d 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -7,19 +7,23 @@ #include <linux/notifier.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> +#include <linux/refcount.h> +#include <linux/rhashtable.h> struct user_namespace; struct ipc_ids { int in_use; unsigned short seq; + bool tables_initialized; struct rw_semaphore rwsem; struct idr ipcs_idr; int next_id; + struct rhashtable key_ht; }; struct ipc_namespace { - atomic_t count; + refcount_t count; struct ipc_ids ids[3]; int sem_ctls[4]; @@ -61,7 +65,7 @@ struct ipc_namespace { struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct ipc_namespace init_ipc_ns; extern spinlock_t mq_lock; @@ -118,7 +122,7 @@ extern struct ipc_namespace *copy_ipcs(unsigned long flags, static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) - atomic_inc(&ns->count); + refcount_inc(&ns->count); return ns; } diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index e1b442996f81..ac2da4e11d5e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -128,6 +128,7 @@ struct inet6_skb_parm { #define IP6SKB_FRAGMENTED 16 #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 +#define IP6SKB_JUMBOGRAM 128 }; #if defined(CONFIG_NET_L3_MASTER_DEV) @@ -152,6 +153,21 @@ static inline int inet6_iif(const struct sk_buff *skb) return l3_slave ? skb->skb_iif : IP6CB(skb)->iif; } +static inline bool inet6_is_jumbogram(const struct sk_buff *skb) +{ + return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM); +} + +/* can not be used in TCP layer after tcp_v6_fill_cb */ +static inline int inet6_sdif(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) + return IP6CB(skb)->iif; +#endif + return 0; +} + /* can not be used in TCP layer after tcp_v6_fill_cb */ static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) { diff --git a/include/linux/irq.h b/include/linux/irq.h index f887351aa80e..b99a784635ff 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -22,6 +22,7 @@ #include <linux/topology.h> #include <linux/wait.h> #include <linux/io.h> +#include <linux/slab.h> #include <asm/irq.h> #include <asm/ptrace.h> @@ -136,6 +137,9 @@ struct irq_domain; * @affinity: IRQ affinity on SMP. If this is an IPI * related irq, then this is the mask of the * CPUs to which an IPI can be sent. + * @effective_affinity: The effective IRQ affinity on SMP as some irq + * chips do not allow multi CPU destinations. + * A subset of @affinity. * @msi_desc: MSI descriptor * @ipi_offset: Offset of first IPI target cpu in @affinity. Optional. */ @@ -147,6 +151,9 @@ struct irq_common_data { void *handler_data; struct msi_desc *msi_desc; cpumask_var_t affinity; +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + cpumask_var_t effective_affinity; +#endif #ifdef CONFIG_GENERIC_IRQ_IPI unsigned int ipi_offset; #endif @@ -199,6 +206,10 @@ struct irq_data { * IRQD_WAKEUP_ARMED - Wakeup mode armed * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU * IRQD_AFFINITY_MANAGED - Affinity is auto-managed by the kernel + * IRQD_IRQ_STARTED - Startup state of the interrupt + * IRQD_MANAGED_SHUTDOWN - Interrupt was shutdown due to empty affinity + * mask. Applies only to affinity managed irqs. + * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -216,6 +227,9 @@ enum { IRQD_WAKEUP_ARMED = (1 << 19), IRQD_FORWARDED_TO_VCPU = (1 << 20), IRQD_AFFINITY_MANAGED = (1 << 21), + IRQD_IRQ_STARTED = (1 << 22), + IRQD_MANAGED_SHUTDOWN = (1 << 23), + IRQD_SINGLE_TARGET = (1 << 24), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -264,6 +278,20 @@ static inline bool irqd_is_level_type(struct irq_data *d) return __irqd_to_state(d) & IRQD_LEVEL; } +/* + * Must only be called of irqchip.irq_set_affinity() or low level + * hieararchy domain allocation functions. + */ +static inline void irqd_set_single_target(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_SINGLE_TARGET; +} + +static inline bool irqd_is_single_target(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_SINGLE_TARGET; +} + static inline bool irqd_is_wakeup_set(struct irq_data *d) { return __irqd_to_state(d) & IRQD_WAKEUP_STATE; @@ -329,6 +357,16 @@ static inline void irqd_clr_activated(struct irq_data *d) __irqd_to_state(d) &= ~IRQD_ACTIVATED; } +static inline bool irqd_is_started(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_IRQ_STARTED; +} + +static inline bool irqd_is_managed_and_shutdown(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_MANAGED_SHUTDOWN; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) @@ -350,7 +388,12 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_mask_ack: ack and mask an interrupt source * @irq_unmask: unmask an interrupt source * @irq_eoi: end of interrupt - * @irq_set_affinity: set the CPU affinity on SMP machines + * @irq_set_affinity: Set the CPU affinity on SMP machines. If the force + * argument is true, it tells the driver to + * unconditionally apply the affinity setting. Sanity + * checks against the supplied affinity mask are not + * required. This is used for CPU hotplug where the + * target CPU is not yet set in the cpu_online_mask. * @irq_retrigger: resend an IRQ to the CPU * @irq_set_type: set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ * @irq_set_wake: enable/disable power-management wake-on of an IRQ @@ -478,14 +521,21 @@ extern int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask, bool force); extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info); +#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_IRQ_MIGRATION) extern void irq_migrate_all_off_this_cpu(void); +extern int irq_affinity_online_cpu(unsigned int cpu); +#else +# define irq_affinity_online_cpu NULL +#endif #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) void irq_move_irq(struct irq_data *data); void irq_move_masked_irq(struct irq_data *data); +void irq_force_complete_move(struct irq_desc *desc); #else static inline void irq_move_irq(struct irq_data *data) { } static inline void irq_move_masked_irq(struct irq_data *data) { } +static inline void irq_force_complete_move(struct irq_desc *desc) { } #endif extern int no_irq_affinity; @@ -518,6 +568,8 @@ extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); extern int irq_chip_pm_get(struct irq_data *data); extern int irq_chip_pm_put(struct irq_data *data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +extern void handle_fasteoi_ack_irq(struct irq_desc *desc); +extern void handle_fasteoi_mask_irq(struct irq_desc *desc); extern void irq_chip_enable_parent(struct irq_data *data); extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); @@ -727,6 +779,32 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) return d->common->affinity; } +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK +static inline +struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) +{ + if (!cpumask_empty(d->common->effective_affinity)) + return d->common->effective_affinity; + + return d->common->affinity; +} +static inline void irq_data_update_effective_affinity(struct irq_data *d, + const struct cpumask *m) +{ + cpumask_copy(d->common->effective_affinity, m); +} +#else +static inline void irq_data_update_effective_affinity(struct irq_data *d, + const struct cpumask *m) +{ +} +static inline +struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) +{ + return d->common->affinity; +} +#endif + unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, @@ -951,6 +1029,14 @@ int irq_setup_alt_chip(struct irq_data *d, unsigned int type); void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, unsigned int clr, unsigned int set); +struct irq_chip_generic * +devm_irq_alloc_generic_chip(struct device *dev, const char *name, int num_ct, + unsigned int irq_base, void __iomem *reg_base, + irq_flow_handler_t handler); +int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc, + u32 msk, enum irq_gc_flags flags, + unsigned int clr, unsigned int set); + struct irq_chip_generic *irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq); int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, @@ -967,6 +1053,19 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, handler, clr, set, flags); \ }) +static inline void irq_free_generic_chip(struct irq_chip_generic *gc) +{ + kfree(gc); +} + +static inline void irq_destroy_generic_chip(struct irq_chip_generic *gc, + u32 msk, unsigned int clr, + unsigned int set) +{ + irq_remove_generic_chip(gc, msk, clr, set); + irq_free_generic_chip(gc); +} + static inline struct irq_chip_type *irq_data_get_chip_type(struct irq_data *d) { return container_of(d->chip, struct irq_chip_type, chip); diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h new file mode 100644 index 000000000000..0380d899b955 --- /dev/null +++ b/include/linux/irq_sim.h @@ -0,0 +1,44 @@ +#ifndef _LINUX_IRQ_SIM_H +#define _LINUX_IRQ_SIM_H +/* + * Copyright (C) 2017 Bartosz Golaszewski <brgl@bgdev.pl> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/irq_work.h> +#include <linux/device.h> + +/* + * Provides a framework for allocating simulated interrupts which can be + * requested like normal irqs and enqueued from process context. + */ + +struct irq_sim_work_ctx { + struct irq_work work; + int irq; +}; + +struct irq_sim_irq_ctx { + int irqnum; + bool enabled; +}; + +struct irq_sim { + struct irq_sim_work_ctx work_ctx; + int irq_base; + unsigned int irq_count; + struct irq_sim_irq_ctx *irqs; +}; + +int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs); +int devm_irq_sim_init(struct device *dev, struct irq_sim *sim, + unsigned int num_irqs); +void irq_sim_fini(struct irq_sim *sim); +void irq_sim_fire(struct irq_sim *sim, unsigned int offset); +int irq_sim_irqnum(struct irq_sim *sim, unsigned int offset); + +#endif /* _LINUX_IRQ_SIM_H */ diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index c647b0547bcd..0a83b4379f34 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -27,6 +27,8 @@ struct gic_kvm_info { unsigned int maint_irq; /* Virtual control interface */ struct resource vctrl; + /* vlpi support */ + bool has_v4; }; const struct gic_kvm_info *gic_get_kvm_info(void); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 1fa293a37f4a..1ea576c8126f 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -204,6 +204,7 @@ #define GICR_TYPER_PLPIS (1U << 0) #define GICR_TYPER_VLPIS (1U << 1) +#define GICR_TYPER_DirectLPIS (1U << 3) #define GICR_TYPER_LAST (1U << 4) #define GIC_V3_REDIST_SIZE 0x20000 @@ -212,6 +213,69 @@ #define LPI_PROP_ENABLED (1 << 0) /* + * Re-Distributor registers, offsets from VLPI_base + */ +#define GICR_VPROPBASER 0x0070 + +#define GICR_VPROPBASER_IDBITS_MASK 0x1f + +#define GICR_VPROPBASER_SHAREABILITY_SHIFT (10) +#define GICR_VPROPBASER_INNER_CACHEABILITY_SHIFT (7) +#define GICR_VPROPBASER_OUTER_CACHEABILITY_SHIFT (56) + +#define GICR_VPROPBASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GICR_VPROPBASER, SHAREABILITY_MASK) +#define GICR_VPROPBASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, MASK) +#define GICR_VPROPBASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPROPBASER, OUTER, MASK) +#define GICR_VPROPBASER_CACHEABILITY_MASK \ + GICR_VPROPBASER_INNER_CACHEABILITY_MASK + +#define GICR_VPROPBASER_InnerShareable \ + GIC_BASER_SHAREABILITY(GICR_VPROPBASER, InnerShareable) + +#define GICR_VPROPBASER_nCnB GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nCnB) +#define GICR_VPROPBASER_nC GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nC) +#define GICR_VPROPBASER_RaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWt) +#define GICR_VPROPBASER_RaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWt) +#define GICR_VPROPBASER_WaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWt) +#define GICR_VPROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWb) +#define GICR_VPROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt) +#define GICR_VPROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb) + +#define GICR_VPENDBASER 0x0078 + +#define GICR_VPENDBASER_SHAREABILITY_SHIFT (10) +#define GICR_VPENDBASER_INNER_CACHEABILITY_SHIFT (7) +#define GICR_VPENDBASER_OUTER_CACHEABILITY_SHIFT (56) +#define GICR_VPENDBASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GICR_VPENDBASER, SHAREABILITY_MASK) +#define GICR_VPENDBASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, MASK) +#define GICR_VPENDBASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPENDBASER, OUTER, MASK) +#define GICR_VPENDBASER_CACHEABILITY_MASK \ + GICR_VPENDBASER_INNER_CACHEABILITY_MASK + +#define GICR_VPENDBASER_NonShareable \ + GIC_BASER_SHAREABILITY(GICR_VPENDBASER, NonShareable) + +#define GICR_VPENDBASER_nCnB GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nCnB) +#define GICR_VPENDBASER_nC GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nC) +#define GICR_VPENDBASER_RaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt) +#define GICR_VPENDBASER_RaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt) +#define GICR_VPENDBASER_WaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWt) +#define GICR_VPENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWb) +#define GICR_VPENDBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWt) +#define GICR_VPENDBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWb) + +#define GICR_VPENDBASER_Dirty (1ULL << 60) +#define GICR_VPENDBASER_PendingLast (1ULL << 61) +#define GICR_VPENDBASER_IDAI (1ULL << 62) +#define GICR_VPENDBASER_Valid (1ULL << 63) + +/* * ITS registers, offsets from ITS_base */ #define GITS_CTLR 0x0000 @@ -234,15 +298,21 @@ #define GITS_TRANSLATER 0x10040 #define GITS_CTLR_ENABLE (1U << 0) +#define GITS_CTLR_ImDe (1U << 1) +#define GITS_CTLR_ITS_NUMBER_SHIFT 4 +#define GITS_CTLR_ITS_NUMBER (0xFU << GITS_CTLR_ITS_NUMBER_SHIFT) #define GITS_CTLR_QUIESCENT (1U << 31) #define GITS_TYPER_PLPIS (1UL << 0) +#define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) #define GITS_TYPER_PTA (1UL << 19) #define GITS_TYPER_HWCOLLCNT_SHIFT 24 +#define GITS_TYPER_VMOVP (1ULL << 37) #define GITS_IIDR_REV_SHIFT 12 #define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT) @@ -342,6 +412,18 @@ #define GITS_CMD_SYNC 0x05 /* + * GICv4 ITS specific commands + */ +#define GITS_CMD_GICv4(x) ((x) | 0x20) +#define GITS_CMD_VINVALL GITS_CMD_GICv4(GITS_CMD_INVALL) +#define GITS_CMD_VMAPP GITS_CMD_GICv4(GITS_CMD_MAPC) +#define GITS_CMD_VMAPTI GITS_CMD_GICv4(GITS_CMD_MAPTI) +#define GITS_CMD_VMOVI GITS_CMD_GICv4(GITS_CMD_MOVI) +#define GITS_CMD_VSYNC GITS_CMD_GICv4(GITS_CMD_SYNC) +/* VMOVP is the odd one, as it doesn't have a physical counterpart */ +#define GITS_CMD_VMOVP GITS_CMD_GICv4(2) + +/* * ITS error numbers */ #define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107 @@ -405,6 +487,7 @@ #define ICH_LR_PHYS_ID_SHIFT 32 #define ICH_LR_PHYS_ID_MASK (0x3ffULL << ICH_LR_PHYS_ID_SHIFT) #define ICH_LR_PRIORITY_SHIFT 48 +#define ICH_LR_PRIORITY_MASK (0xffULL << ICH_LR_PRIORITY_SHIFT) /* These are for GICv2 emulation only */ #define GICH_LR_VIRTUALID (0x3ffUL << 0) @@ -416,6 +499,11 @@ #define ICH_HCR_EN (1 << 0) #define ICH_HCR_UIE (1 << 1) +#define ICH_HCR_TC (1 << 10) +#define ICH_HCR_TALL0 (1 << 11) +#define ICH_HCR_TALL1 (1 << 12) +#define ICH_HCR_EOIcount_SHIFT 27 +#define ICH_HCR_EOIcount_MASK (0x1f << ICH_HCR_EOIcount_SHIFT) #define ICH_VMCR_ACK_CTL_SHIFT 2 #define ICH_VMCR_ACK_CTL_MASK (1 << ICH_VMCR_ACK_CTL_SHIFT) @@ -481,6 +569,8 @@ struct rdists { struct page *prop_page; int id_bits; u64 flags; + bool has_vlpis; + bool has_direct_lpi; }; struct irq_domain; diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h new file mode 100644 index 000000000000..58a4d89aa82c --- /dev/null +++ b/include/linux/irqchip/arm-gic-v4.h @@ -0,0 +1,105 @@ +/* + * Copyright (C) 2016,2017 ARM Limited, All Rights Reserved. + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __LINUX_IRQCHIP_ARM_GIC_V4_H +#define __LINUX_IRQCHIP_ARM_GIC_V4_H + +struct its_vpe; + +/* Embedded in kvm.arch */ +struct its_vm { + struct fwnode_handle *fwnode; + struct irq_domain *domain; + struct page *vprop_page; + struct its_vpe **vpes; + int nr_vpes; + irq_hw_number_t db_lpi_base; + unsigned long *db_bitmap; + int nr_db_lpis; +}; + +/* Embedded in kvm_vcpu.arch */ +struct its_vpe { + struct page *vpt_page; + struct its_vm *its_vm; + /* Doorbell interrupt */ + int irq; + irq_hw_number_t vpe_db_lpi; + /* VPE proxy mapping */ + int vpe_proxy_event; + /* + * This collection ID is used to indirect the target + * redistributor for this VPE. The ID itself isn't involved in + * programming of the ITS. + */ + u16 col_idx; + /* Unique (system-wide) VPE identifier */ + u16 vpe_id; + /* Implementation Defined Area Invalid */ + bool idai; + /* Pending VLPIs on schedule out? */ + bool pending_last; +}; + +/* + * struct its_vlpi_map: structure describing the mapping of a + * VLPI. Only to be interpreted in the context of a physical interrupt + * it complements. To be used as the vcpu_info passed to + * irq_set_vcpu_affinity(). + * + * @vm: Pointer to the GICv4 notion of a VM + * @vpe: Pointer to the GICv4 notion of a virtual CPU (VPE) + * @vintid: Virtual LPI number + * @db_enabled: Is the VPE doorbell to be generated? + */ +struct its_vlpi_map { + struct its_vm *vm; + struct its_vpe *vpe; + u32 vintid; + bool db_enabled; +}; + +enum its_vcpu_info_cmd_type { + MAP_VLPI, + GET_VLPI, + PROP_UPDATE_VLPI, + PROP_UPDATE_AND_INV_VLPI, + SCHEDULE_VPE, + DESCHEDULE_VPE, + INVALL_VPE, +}; + +struct its_cmd_info { + enum its_vcpu_info_cmd_type cmd_type; + union { + struct its_vlpi_map *map; + u8 config; + }; +}; + +int its_alloc_vcpu_irqs(struct its_vm *vm); +void its_free_vcpu_irqs(struct its_vm *vm); +int its_schedule_vpe(struct its_vpe *vpe, bool on); +int its_invall_vpe(struct its_vpe *vpe); +int its_map_vlpi(int irq, struct its_vlpi_map *map); +int its_get_vlpi(int irq, struct its_vlpi_map *map); +int its_unmap_vlpi(int irq); +int its_prop_update_vlpi(int irq, u8 config, bool inv); + +int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops); + +#endif diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h deleted file mode 100644 index 2b0e56619e53..000000000000 --- a/include/linux/irqchip/mips-gic.h +++ /dev/null @@ -1,297 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2000, 07 MIPS Technologies, Inc. - */ -#ifndef __LINUX_IRQCHIP_MIPS_GIC_H -#define __LINUX_IRQCHIP_MIPS_GIC_H - -#include <linux/clocksource.h> -#include <linux/ioport.h> - -#define GIC_MAX_INTRS 256 - -/* Constants */ -#define GIC_POL_POS 1 -#define GIC_POL_NEG 0 -#define GIC_TRIG_EDGE 1 -#define GIC_TRIG_LEVEL 0 -#define GIC_TRIG_DUAL_ENABLE 1 -#define GIC_TRIG_DUAL_DISABLE 0 - -#define MSK(n) ((1 << (n)) - 1) - -/* Accessors */ -#define GIC_REG(segment, offset) (segment##_##SECTION_OFS + offset##_##OFS) - -/* GIC Address Space */ -#define SHARED_SECTION_OFS 0x0000 -#define SHARED_SECTION_SIZE 0x8000 -#define VPE_LOCAL_SECTION_OFS 0x8000 -#define VPE_LOCAL_SECTION_SIZE 0x4000 -#define VPE_OTHER_SECTION_OFS 0xc000 -#define VPE_OTHER_SECTION_SIZE 0x4000 -#define USM_VISIBLE_SECTION_OFS 0x10000 -#define USM_VISIBLE_SECTION_SIZE 0x10000 - -/* Register Map for Shared Section */ - -#define GIC_SH_CONFIG_OFS 0x0000 - -/* Shared Global Counter */ -#define GIC_SH_COUNTER_31_00_OFS 0x0010 -/* 64-bit counter register for CM3 */ -#define GIC_SH_COUNTER_OFS GIC_SH_COUNTER_31_00_OFS -#define GIC_SH_COUNTER_63_32_OFS 0x0014 -#define GIC_SH_REVISIONID_OFS 0x0020 - -/* Convert an interrupt number to a byte offset/bit for multi-word registers */ -#define GIC_INTR_OFS(intr) ({ \ - unsigned bits = mips_cm_is64 ? 64 : 32; \ - unsigned reg_idx = (intr) / bits; \ - unsigned reg_width = bits / 8; \ - \ - reg_idx * reg_width; \ -}) -#define GIC_INTR_BIT(intr) ((intr) % (mips_cm_is64 ? 64 : 32)) - -/* Polarity : Reset Value is always 0 */ -#define GIC_SH_SET_POLARITY_OFS 0x0100 - -/* Triggering : Reset Value is always 0 */ -#define GIC_SH_SET_TRIGGER_OFS 0x0180 - -/* Dual edge triggering : Reset Value is always 0 */ -#define GIC_SH_SET_DUAL_OFS 0x0200 - -/* Set/Clear corresponding bit in Edge Detect Register */ -#define GIC_SH_WEDGE_OFS 0x0280 - -/* Mask manipulation */ -#define GIC_SH_RMASK_OFS 0x0300 -#define GIC_SH_SMASK_OFS 0x0380 - -/* Global Interrupt Mask Register (RO) - Bit Set == Interrupt enabled */ -#define GIC_SH_MASK_OFS 0x0400 - -/* Pending Global Interrupts (RO) */ -#define GIC_SH_PEND_OFS 0x0480 - -/* Maps Interrupt X to a Pin */ -#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500 -#define GIC_SH_MAP_TO_PIN(intr) (4 * (intr)) - -/* Maps Interrupt X to a VPE */ -#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS 0x2000 -#define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \ - ((32 * (intr)) + (((vpe) / 32) * 4)) -#define GIC_SH_MAP_TO_VPE_REG_BIT(vpe) (1 << ((vpe) % 32)) - -/* Register Map for Local Section */ -#define GIC_VPE_CTL_OFS 0x0000 -#define GIC_VPE_PEND_OFS 0x0004 -#define GIC_VPE_MASK_OFS 0x0008 -#define GIC_VPE_RMASK_OFS 0x000c -#define GIC_VPE_SMASK_OFS 0x0010 -#define GIC_VPE_WD_MAP_OFS 0x0040 -#define GIC_VPE_COMPARE_MAP_OFS 0x0044 -#define GIC_VPE_TIMER_MAP_OFS 0x0048 -#define GIC_VPE_FDC_MAP_OFS 0x004c -#define GIC_VPE_PERFCTR_MAP_OFS 0x0050 -#define GIC_VPE_SWINT0_MAP_OFS 0x0054 -#define GIC_VPE_SWINT1_MAP_OFS 0x0058 -#define GIC_VPE_OTHER_ADDR_OFS 0x0080 -#define GIC_VP_IDENT_OFS 0x0088 -#define GIC_VPE_WD_CONFIG0_OFS 0x0090 -#define GIC_VPE_WD_COUNT0_OFS 0x0094 -#define GIC_VPE_WD_INITIAL0_OFS 0x0098 -#define GIC_VPE_COMPARE_LO_OFS 0x00a0 -/* 64-bit Compare register on CM3 */ -#define GIC_VPE_COMPARE_OFS GIC_VPE_COMPARE_LO_OFS -#define GIC_VPE_COMPARE_HI_OFS 0x00a4 - -#define GIC_VPE_EIC_SHADOW_SET_BASE_OFS 0x0100 -#define GIC_VPE_EIC_SS(intr) (4 * (intr)) - -#define GIC_VPE_EIC_VEC_BASE_OFS 0x0800 -#define GIC_VPE_EIC_VEC(intr) (4 * (intr)) - -#define GIC_VPE_TENABLE_NMI_OFS 0x1000 -#define GIC_VPE_TENABLE_YQ_OFS 0x1004 -#define GIC_VPE_TENABLE_INT_31_0_OFS 0x1080 -#define GIC_VPE_TENABLE_INT_63_32_OFS 0x1084 - -/* User Mode Visible Section Register Map */ -#define GIC_UMV_SH_COUNTER_31_00_OFS 0x0000 -#define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 - -/* Masks */ -#define GIC_SH_CONFIG_COUNTSTOP_SHF 28 -#define GIC_SH_CONFIG_COUNTSTOP_MSK (MSK(1) << GIC_SH_CONFIG_COUNTSTOP_SHF) - -#define GIC_SH_CONFIG_COUNTBITS_SHF 24 -#define GIC_SH_CONFIG_COUNTBITS_MSK (MSK(4) << GIC_SH_CONFIG_COUNTBITS_SHF) - -#define GIC_SH_CONFIG_NUMINTRS_SHF 16 -#define GIC_SH_CONFIG_NUMINTRS_MSK (MSK(8) << GIC_SH_CONFIG_NUMINTRS_SHF) - -#define GIC_SH_CONFIG_NUMVPES_SHF 0 -#define GIC_SH_CONFIG_NUMVPES_MSK (MSK(8) << GIC_SH_CONFIG_NUMVPES_SHF) - -#define GIC_SH_WEDGE_SET(intr) ((intr) | (0x1 << 31)) -#define GIC_SH_WEDGE_CLR(intr) ((intr) & ~(0x1 << 31)) - -#define GIC_MAP_TO_PIN_SHF 31 -#define GIC_MAP_TO_PIN_MSK (MSK(1) << GIC_MAP_TO_PIN_SHF) -#define GIC_MAP_TO_NMI_SHF 30 -#define GIC_MAP_TO_NMI_MSK (MSK(1) << GIC_MAP_TO_NMI_SHF) -#define GIC_MAP_TO_YQ_SHF 29 -#define GIC_MAP_TO_YQ_MSK (MSK(1) << GIC_MAP_TO_YQ_SHF) -#define GIC_MAP_SHF 0 -#define GIC_MAP_MSK (MSK(6) << GIC_MAP_SHF) - -/* GIC_VPE_CTL Masks */ -#define GIC_VPE_CTL_FDC_RTBL_SHF 4 -#define GIC_VPE_CTL_FDC_RTBL_MSK (MSK(1) << GIC_VPE_CTL_FDC_RTBL_SHF) -#define GIC_VPE_CTL_SWINT_RTBL_SHF 3 -#define GIC_VPE_CTL_SWINT_RTBL_MSK (MSK(1) << GIC_VPE_CTL_SWINT_RTBL_SHF) -#define GIC_VPE_CTL_PERFCNT_RTBL_SHF 2 -#define GIC_VPE_CTL_PERFCNT_RTBL_MSK (MSK(1) << GIC_VPE_CTL_PERFCNT_RTBL_SHF) -#define GIC_VPE_CTL_TIMER_RTBL_SHF 1 -#define GIC_VPE_CTL_TIMER_RTBL_MSK (MSK(1) << GIC_VPE_CTL_TIMER_RTBL_SHF) -#define GIC_VPE_CTL_EIC_MODE_SHF 0 -#define GIC_VPE_CTL_EIC_MODE_MSK (MSK(1) << GIC_VPE_CTL_EIC_MODE_SHF) - -/* GIC_VPE_PEND Masks */ -#define GIC_VPE_PEND_WD_SHF 0 -#define GIC_VPE_PEND_WD_MSK (MSK(1) << GIC_VPE_PEND_WD_SHF) -#define GIC_VPE_PEND_CMP_SHF 1 -#define GIC_VPE_PEND_CMP_MSK (MSK(1) << GIC_VPE_PEND_CMP_SHF) -#define GIC_VPE_PEND_TIMER_SHF 2 -#define GIC_VPE_PEND_TIMER_MSK (MSK(1) << GIC_VPE_PEND_TIMER_SHF) -#define GIC_VPE_PEND_PERFCOUNT_SHF 3 -#define GIC_VPE_PEND_PERFCOUNT_MSK (MSK(1) << GIC_VPE_PEND_PERFCOUNT_SHF) -#define GIC_VPE_PEND_SWINT0_SHF 4 -#define GIC_VPE_PEND_SWINT0_MSK (MSK(1) << GIC_VPE_PEND_SWINT0_SHF) -#define GIC_VPE_PEND_SWINT1_SHF 5 -#define GIC_VPE_PEND_SWINT1_MSK (MSK(1) << GIC_VPE_PEND_SWINT1_SHF) -#define GIC_VPE_PEND_FDC_SHF 6 -#define GIC_VPE_PEND_FDC_MSK (MSK(1) << GIC_VPE_PEND_FDC_SHF) - -/* GIC_VPE_RMASK Masks */ -#define GIC_VPE_RMASK_WD_SHF 0 -#define GIC_VPE_RMASK_WD_MSK (MSK(1) << GIC_VPE_RMASK_WD_SHF) -#define GIC_VPE_RMASK_CMP_SHF 1 -#define GIC_VPE_RMASK_CMP_MSK (MSK(1) << GIC_VPE_RMASK_CMP_SHF) -#define GIC_VPE_RMASK_TIMER_SHF 2 -#define GIC_VPE_RMASK_TIMER_MSK (MSK(1) << GIC_VPE_RMASK_TIMER_SHF) -#define GIC_VPE_RMASK_PERFCNT_SHF 3 -#define GIC_VPE_RMASK_PERFCNT_MSK (MSK(1) << GIC_VPE_RMASK_PERFCNT_SHF) -#define GIC_VPE_RMASK_SWINT0_SHF 4 -#define GIC_VPE_RMASK_SWINT0_MSK (MSK(1) << GIC_VPE_RMASK_SWINT0_SHF) -#define GIC_VPE_RMASK_SWINT1_SHF 5 -#define GIC_VPE_RMASK_SWINT1_MSK (MSK(1) << GIC_VPE_RMASK_SWINT1_SHF) -#define GIC_VPE_RMASK_FDC_SHF 6 -#define GIC_VPE_RMASK_FDC_MSK (MSK(1) << GIC_VPE_RMASK_FDC_SHF) - -/* GIC_VPE_SMASK Masks */ -#define GIC_VPE_SMASK_WD_SHF 0 -#define GIC_VPE_SMASK_WD_MSK (MSK(1) << GIC_VPE_SMASK_WD_SHF) -#define GIC_VPE_SMASK_CMP_SHF 1 -#define GIC_VPE_SMASK_CMP_MSK (MSK(1) << GIC_VPE_SMASK_CMP_SHF) -#define GIC_VPE_SMASK_TIMER_SHF 2 -#define GIC_VPE_SMASK_TIMER_MSK (MSK(1) << GIC_VPE_SMASK_TIMER_SHF) -#define GIC_VPE_SMASK_PERFCNT_SHF 3 -#define GIC_VPE_SMASK_PERFCNT_MSK (MSK(1) << GIC_VPE_SMASK_PERFCNT_SHF) -#define GIC_VPE_SMASK_SWINT0_SHF 4 -#define GIC_VPE_SMASK_SWINT0_MSK (MSK(1) << GIC_VPE_SMASK_SWINT0_SHF) -#define GIC_VPE_SMASK_SWINT1_SHF 5 -#define GIC_VPE_SMASK_SWINT1_MSK (MSK(1) << GIC_VPE_SMASK_SWINT1_SHF) -#define GIC_VPE_SMASK_FDC_SHF 6 -#define GIC_VPE_SMASK_FDC_MSK (MSK(1) << GIC_VPE_SMASK_FDC_SHF) - -/* GIC_VP_IDENT fields */ -#define GIC_VP_IDENT_VCNUM_SHF 0 -#define GIC_VP_IDENT_VCNUM_MSK (MSK(6) << GIC_VP_IDENT_VCNUM_SHF) - -/* GIC nomenclature for Core Interrupt Pins. */ -#define GIC_CPU_INT0 0 /* Core Interrupt 2 */ -#define GIC_CPU_INT1 1 /* . */ -#define GIC_CPU_INT2 2 /* . */ -#define GIC_CPU_INT3 3 /* . */ -#define GIC_CPU_INT4 4 /* . */ -#define GIC_CPU_INT5 5 /* Core Interrupt 7 */ - -/* Add 2 to convert GIC CPU pin to core interrupt */ -#define GIC_CPU_PIN_OFFSET 2 - -/* Add 2 to convert non-EIC hardware interrupt to EIC vector number. */ -#define GIC_CPU_TO_VEC_OFFSET 2 - -/* Mapped interrupt to pin X, then GIC will generate the vector (X+1). */ -#define GIC_PIN_TO_VEC_OFFSET 1 - -/* Local GIC interrupts. */ -#define GIC_LOCAL_INT_WD 0 /* GIC watchdog */ -#define GIC_LOCAL_INT_COMPARE 1 /* GIC count and compare timer */ -#define GIC_LOCAL_INT_TIMER 2 /* CPU timer interrupt */ -#define GIC_LOCAL_INT_PERFCTR 3 /* CPU performance counter */ -#define GIC_LOCAL_INT_SWINT0 4 /* CPU software interrupt 0 */ -#define GIC_LOCAL_INT_SWINT1 5 /* CPU software interrupt 1 */ -#define GIC_LOCAL_INT_FDC 6 /* CPU fast debug channel */ -#define GIC_NUM_LOCAL_INTRS 7 - -/* Convert between local/shared IRQ number and GIC HW IRQ number. */ -#define GIC_LOCAL_HWIRQ_BASE 0 -#define GIC_LOCAL_TO_HWIRQ(x) (GIC_LOCAL_HWIRQ_BASE + (x)) -#define GIC_HWIRQ_TO_LOCAL(x) ((x) - GIC_LOCAL_HWIRQ_BASE) -#define GIC_SHARED_HWIRQ_BASE GIC_NUM_LOCAL_INTRS -#define GIC_SHARED_TO_HWIRQ(x) (GIC_SHARED_HWIRQ_BASE + (x)) -#define GIC_HWIRQ_TO_SHARED(x) ((x) - GIC_SHARED_HWIRQ_BASE) - -#ifdef CONFIG_MIPS_GIC - -extern unsigned int gic_present; - -extern void gic_init(unsigned long gic_base_addr, - unsigned long gic_addrspace_size, unsigned int cpu_vec, - unsigned int irqbase); -extern u64 gic_read_count(void); -extern unsigned int gic_get_count_width(void); -extern u64 gic_read_compare(void); -extern void gic_write_compare(u64 cnt); -extern void gic_write_cpu_compare(u64 cnt, int cpu); -extern void gic_start_count(void); -extern void gic_stop_count(void); -extern int gic_get_c0_compare_int(void); -extern int gic_get_c0_perfcount_int(void); -extern int gic_get_c0_fdc_int(void); -extern int gic_get_usm_range(struct resource *gic_usm_res); - -#else /* CONFIG_MIPS_GIC */ - -#define gic_present 0 - -static inline int gic_get_usm_range(struct resource *gic_usm_res) -{ - /* Shouldn't be called. */ - return -1; -} - -#endif /* CONFIG_MIPS_GIC */ - -/** - * gic_read_local_vp_id() - read the local VPs VCNUM - * - * Read the VCNUM of the local VP from the GIC_VP_IDENT register and - * return it to the caller. This ID should be used to refer to the VP - * via the GICs VP-other region, or when calculating an offset to a - * bit representing the VP in interrupt masks. - * - * Return: The VCNUM value for the local VP. - */ -extern unsigned gic_read_local_vp_id(void); - -#endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c9be57931b58..3e90a094798d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -3,6 +3,7 @@ #include <linux/rcupdate.h> #include <linux/kobject.h> +#include <linux/mutex.h> /* * Core internal functions to deal with irq descriptors @@ -45,7 +46,9 @@ struct pt_regs; * IRQF_FORCE_RESUME set * @rcu: rcu head for delayed free * @kobj: kobject used to represent this struct in sysfs + * @request_mutex: mutex to protect request/free before locking desc->lock * @dir: /proc/irq/ procfs entry + * @debugfs_file: dentry for the debugfs file * @name: flow handler name for /proc/interrupts output */ struct irq_desc { @@ -88,10 +91,14 @@ struct irq_desc { #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; #endif +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + struct dentry *debugfs_file; +#endif #ifdef CONFIG_SPARSE_IRQ struct rcu_head rcu; struct kobject kobj; #endif + struct mutex request_mutex; int parent_irq; struct module *owner; const char *name; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 9f3616085423..81e4889ca6dd 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -130,6 +130,7 @@ struct irq_domain_chip_generic; * @host_data: private data pointer for use by owner. Not touched by irq_domain * core code. * @flags: host per irq_domain flags + * @mapcount: The number of mapped interrupts * * Optional elements * @of_node: Pointer to device tree nodes associated with the irq_domain. Used @@ -138,6 +139,7 @@ struct irq_domain_chip_generic; * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains + * @debugfs_file: dentry for the domain debugfs file * * Revmap data, used internally by irq_domain * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that @@ -152,6 +154,7 @@ struct irq_domain { const struct irq_domain_ops *ops; void *host_data; unsigned int flags; + unsigned int mapcount; /* Optional data */ struct fwnode_handle *fwnode; @@ -160,6 +163,9 @@ struct irq_domain { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; #endif +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + struct dentry *debugfs_file; +#endif /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; @@ -174,8 +180,8 @@ enum { /* Irq domain is hierarchical */ IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), - /* Core calls alloc/free recursive through the domain hierarchy. */ - IRQ_DOMAIN_FLAG_AUTO_RECURSIVE = (1 << 1), + /* Irq domain name was allocated in __irq_domain_add() */ + IRQ_DOMAIN_NAME_ALLOCATED = (1 << 6), /* Irq domain is an IPI domain with virq per cpu */ IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2), @@ -203,7 +209,33 @@ static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) } #ifdef CONFIG_IRQ_DOMAIN -struct fwnode_handle *irq_domain_alloc_fwnode(void *data); +struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, + const char *name, void *data); + +enum { + IRQCHIP_FWNODE_REAL, + IRQCHIP_FWNODE_NAMED, + IRQCHIP_FWNODE_NAMED_ID, +}; + +static inline +struct fwnode_handle *irq_domain_alloc_named_fwnode(const char *name) +{ + return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_NAMED, 0, name, NULL); +} + +static inline +struct fwnode_handle *irq_domain_alloc_named_id_fwnode(const char *name, int id) +{ + return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_NAMED_ID, id, name, + NULL); +} + +static inline struct fwnode_handle *irq_domain_alloc_fwnode(void *data) +{ + return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_REAL, 0, NULL, data); +} + void irq_domain_free_fwnode(struct fwnode_handle *fwnode); struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, @@ -233,11 +265,16 @@ static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) return node ? &node->fwnode : NULL; } +extern const struct fwnode_operations irqchip_fwnode_ops; + static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_IRQCHIP; + return fwnode && fwnode->ops == &irqchip_fwnode_ops; } +extern void irq_domain_update_bus_token(struct irq_domain *domain, + enum irq_domain_bus_token bus_token); + static inline struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token) @@ -410,7 +447,7 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain, NULL); } -extern int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, +extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs, void *arg); extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, @@ -425,6 +462,9 @@ extern void irq_domain_free_irqs_common(struct irq_domain *domain, extern void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); +extern int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg); +extern int irq_domain_pop_irq(struct irq_domain *domain, int virq); + extern int irq_domain_alloc_irqs_parent(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs, void *arg); diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 5dd1272d1ab2..5fdd93bb9300 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -23,10 +23,26 @@ # define trace_softirq_context(p) ((p)->softirq_context) # define trace_hardirqs_enabled(p) ((p)->hardirqs_enabled) # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) -# define trace_hardirq_enter() do { current->hardirq_context++; } while (0) -# define trace_hardirq_exit() do { current->hardirq_context--; } while (0) -# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) -# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) +# define trace_hardirq_enter() \ +do { \ + current->hardirq_context++; \ + crossrelease_hist_start(XHLOCK_HARD); \ +} while (0) +# define trace_hardirq_exit() \ +do { \ + current->hardirq_context--; \ + crossrelease_hist_end(XHLOCK_HARD); \ +} while (0) +# define lockdep_softirq_enter() \ +do { \ + current->softirq_context++; \ + crossrelease_hist_start(XHLOCK_SOFT); \ +} while (0) +# define lockdep_softirq_exit() \ +do { \ + current->softirq_context--; \ + crossrelease_hist_end(XHLOCK_SOFT); \ +} while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else # define trace_hardirqs_on() do { } while (0) diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 348c6f47e4cc..8037850f3104 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -85,19 +85,18 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) k += 12; } /* Last block: affect all 32 bits of (c) */ - /* All the case statements fall through */ switch (length) { - case 12: c += (u32)k[11]<<24; - case 11: c += (u32)k[10]<<16; - case 10: c += (u32)k[9]<<8; - case 9: c += k[8]; - case 8: b += (u32)k[7]<<24; - case 7: b += (u32)k[6]<<16; - case 6: b += (u32)k[5]<<8; - case 5: b += k[4]; - case 4: a += (u32)k[3]<<24; - case 3: a += (u32)k[2]<<16; - case 2: a += (u32)k[1]<<8; + case 12: c += (u32)k[11]<<24; /* fall through */ + case 11: c += (u32)k[10]<<16; /* fall through */ + case 10: c += (u32)k[9]<<8; /* fall through */ + case 9: c += k[8]; /* fall through */ + case 8: b += (u32)k[7]<<24; /* fall through */ + case 7: b += (u32)k[6]<<16; /* fall through */ + case 6: b += (u32)k[5]<<8; /* fall through */ + case 5: b += k[4]; /* fall through */ + case 4: a += (u32)k[3]<<24; /* fall through */ + case 3: a += (u32)k[2]<<16; /* fall through */ + case 2: a += (u32)k[1]<<8; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ @@ -131,10 +130,10 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) k += 3; } - /* Handle the last 3 u32's: all the case statements fall through */ + /* Handle the last 3 u32's */ switch (length) { - case 3: c += k[2]; - case 2: b += k[1]; + case 3: c += k[2]; /* fall through */ + case 2: b += k[1]; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 2afd74b9d844..cd5861651b17 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -163,6 +163,8 @@ extern void jump_label_apply_nops(struct module *mod); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); +extern void static_key_enable_cpuslocked(struct static_key *key); +extern void static_key_disable_cpuslocked(struct static_key *key); /* * We should be using ATOMIC_INIT() for initializing .enabled, but @@ -234,24 +236,29 @@ static inline int jump_label_apply_nops(struct module *mod) static inline void static_key_enable(struct static_key *key) { - int count = static_key_count(key); - - WARN_ON_ONCE(count < 0 || count > 1); + STATIC_KEY_CHECK_USE(); - if (!count) - static_key_slow_inc(key); + if (atomic_read(&key->enabled) != 0) { + WARN_ON_ONCE(atomic_read(&key->enabled) != 1); + return; + } + atomic_set(&key->enabled, 1); } static inline void static_key_disable(struct static_key *key) { - int count = static_key_count(key); - - WARN_ON_ONCE(count < 0 || count > 1); + STATIC_KEY_CHECK_USE(); - if (count) - static_key_slow_dec(key); + if (atomic_read(&key->enabled) != 1) { + WARN_ON_ONCE(atomic_read(&key->enabled) != 0); + return; + } + atomic_set(&key->enabled, 0); } +#define static_key_enable_cpuslocked(k) static_key_enable((k)) +#define static_key_disable_cpuslocked(k) static_key_disable((k)) + #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } #define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } @@ -413,8 +420,10 @@ extern bool ____wrong_branch_error(void); * Normal usage; boolean enable/disable. */ -#define static_branch_enable(x) static_key_enable(&(x)->key) -#define static_branch_disable(x) static_key_disable(&(x)->key) +#define static_branch_enable(x) static_key_enable(&(x)->key) +#define static_branch_disable(x) static_key_disable(&(x)->key) +#define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) +#define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) #endif /* __ASSEMBLY__ */ diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h index b7f8aced7870..41960fecf783 100644 --- a/include/linux/kasan-checks.h +++ b/include/linux/kasan-checks.h @@ -2,11 +2,13 @@ #define _LINUX_KASAN_CHECKS_H #ifdef CONFIG_KASAN -void kasan_check_read(const void *p, unsigned int size); -void kasan_check_write(const void *p, unsigned int size); +void kasan_check_read(const volatile void *p, unsigned int size); +void kasan_check_write(const volatile void *p, unsigned int size); #else -static inline void kasan_check_read(const void *p, unsigned int size) { } -static inline void kasan_check_write(const void *p, unsigned int size) { } +static inline void kasan_check_read(const volatile void *p, unsigned int size) +{ } +static inline void kasan_check_write(const volatile void *p, unsigned int size) +{ } #endif #endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 13bc08aba704..0ad4c3044cf9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -11,6 +11,7 @@ #include <linux/log2.h> #include <linux/typecheck.h> #include <linux/printk.h> +#include <linux/build_bug.h> #include <asm/byteorder.h> #include <uapi/linux/kernel.h> @@ -77,8 +78,11 @@ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP -#define DIV_ROUND_UP_ULL(ll,d) \ - ({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; }) + +#define DIV_ROUND_DOWN_ULL(ll, d) \ + ({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; }) + +#define DIV_ROUND_UP_ULL(ll, d) DIV_ROUND_DOWN_ULL((ll) + (d) - 1, (d)) #if BITS_PER_LONG == 32 # define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d) @@ -276,6 +280,13 @@ extern int oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; +#ifdef CONFIG_ARCH_HAS_REFCOUNT +void refcount_error_report(struct pt_regs *regs, const char *err); +#else +static inline void refcount_error_report(struct pt_regs *regs, const char *err) +{ } +#endif + /* Internal, do not use. */ int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); int __must_check _kstrtol(const char *s, unsigned int base, long *res); @@ -490,9 +501,13 @@ extern int root_mountflags; extern bool early_boot_irqs_disabled; -/* Values used for system_state */ +/* + * Values used for system_state. Ordering of the states must not be changed + * as code checks for <, <=, >, >= STATE. + */ extern enum system_states { SYSTEM_BOOTING, + SYSTEM_SCHEDULING, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, @@ -850,9 +865,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @member: the name of the member within the struct. * */ -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index a9b11b8d06f2..ab25c8b6d9e3 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -69,6 +69,12 @@ enum kernfs_root_flag { * following flag enables that behavior. */ KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, + + /* + * The filesystem supports exportfs operation, so userspace can use + * fhandle to access nodes of the fs. + */ + KERNFS_ROOT_SUPPORT_EXPORTOP = 0x0004, }; /* type-specific structures for kernfs_node union members */ @@ -95,6 +101,21 @@ struct kernfs_elem_attr { struct kernfs_node *notify_next; /* for kernfs_notify() */ }; +/* represent a kernfs node */ +union kernfs_node_id { + struct { + /* + * blktrace will export this struct as a simplified 'struct + * fid' (which is a big data struction), so userspace can use + * it to find kernfs node. The layout must match the first two + * fields of 'struct fid' exactly. + */ + u32 ino; + u32 generation; + }; + u64 id; +}; + /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are @@ -131,9 +152,9 @@ struct kernfs_node { void *priv; + union kernfs_node_id id; unsigned short flags; umode_t mode; - unsigned int ino; struct kernfs_iattrs *iattr; }; @@ -163,7 +184,8 @@ struct kernfs_root { unsigned int flags; /* KERNFS_ROOT_* flags */ /* private fields, do not use outside kernfs proper */ - struct ida ino_ida; + struct idr ino_idr; + u32 next_generation; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_mutex */ @@ -336,6 +358,8 @@ struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns); void kernfs_init(void); +struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, + const union kernfs_node_id *id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index c9481ebcbc0c..2b7590f5483a 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -63,15 +63,6 @@ #define KEXEC_CORE_NOTE_NAME CRASH_CORE_NOTE_NAME /* - * The per-cpu notes area is a list of notes terminated by a "NULL" - * note header. For kdump, the code in vmcore.c runs in the context - * of the second kernel to combine them into one note. - */ -#ifndef KEXEC_NOTE_BYTES -#define KEXEC_NOTE_BYTES CRASH_CORE_NOTE_BYTES -#endif - -/* * This structure is used to hold the arguments that are used when loading * kernel binaries. */ @@ -181,6 +172,7 @@ struct kimage { unsigned long start; struct page *control_code_page; struct page *swap_page; + void *vmcoreinfo_data_copy; /* locates in the crash memory */ unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -250,6 +242,7 @@ extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); +extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; @@ -334,6 +327,14 @@ static inline void *boot_phys_to_virt(unsigned long entry) return phys_to_virt(boot_phys_to_phys(entry)); } +#ifndef arch_kexec_post_alloc_pages +static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) { return 0; } +#endif + +#ifndef arch_kexec_pre_free_pages +static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { } +#endif + #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 8496cf64575c..9520fc3c3b9a 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -45,7 +45,7 @@ struct key_preparsed_payload { size_t datalen; /* Raw datalen */ size_t quotalen; /* Quota length for proposed payload */ time_t expiry; /* Expiry time of key */ -}; +} __randomize_layout; typedef int (*request_key_actor_t)(struct key_construction *key, const char *op, void *aux); @@ -158,7 +158,7 @@ struct key_type { /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ -}; +} __randomize_layout; extern struct key_type key_type_keyring; diff --git a/include/linux/key.h b/include/linux/key.h index 78e25aabedaf..044114185120 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -9,7 +9,7 @@ * 2 of the License, or (at your option) any later version. * * - * See Documentation/security/keys.txt for information on keys/keyrings. + * See Documentation/security/keys/core.rst for information on keys/keyrings. */ #ifndef _LINUX_KEY_H diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 5d9a400af509..f0d7335336cd 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -48,7 +48,8 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE)) + !(vm_flags & VM_NOHUGEPAGE) && + !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) if (__khugepaged_enter(vma->vm_mm)) return -ENOMEM; return 0; diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 1c2a32829620..590343f6c1b1 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -22,6 +22,7 @@ #define __KMEMLEAK_H #include <linux/slab.h> +#include <linux/vmalloc.h> #ifdef CONFIG_DEBUG_KMEMLEAK @@ -30,6 +31,8 @@ extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, gfp_t gfp) __ref; +extern void kmemleak_vmalloc(const struct vm_struct *area, size_t size, + gfp_t gfp) __ref; extern void kmemleak_free(const void *ptr) __ref; extern void kmemleak_free_part(const void *ptr, size_t size) __ref; extern void kmemleak_free_percpu(const void __percpu *ptr) __ref; @@ -81,6 +84,10 @@ static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, gfp_t gfp) { } +static inline void kmemleak_vmalloc(const struct vm_struct *area, size_t size, + gfp_t gfp) +{ +} static inline void kmemleak_free(const void *ptr) { } diff --git a/include/linux/kmod.h b/include/linux/kmod.h index c4e441e00db5..40c89ad4bea6 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -19,6 +19,7 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include <linux/umh.h> #include <linux/gfp.h> #include <linux/stddef.h> #include <linux/errno.h> @@ -44,63 +45,4 @@ static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; #define try_then_request_module(x, mod...) (x) #endif - -struct cred; -struct file; - -#define UMH_NO_WAIT 0 /* don't wait at all */ -#define UMH_WAIT_EXEC 1 /* wait for the exec, but not the process */ -#define UMH_WAIT_PROC 2 /* wait for the process to complete */ -#define UMH_KILLABLE 4 /* wait for EXEC/PROC killable */ - -struct subprocess_info { - struct work_struct work; - struct completion *complete; - const char *path; - char **argv; - char **envp; - int wait; - int retval; - int (*init)(struct subprocess_info *info, struct cred *new); - void (*cleanup)(struct subprocess_info *info); - void *data; -}; - -extern int -call_usermodehelper(const char *path, char **argv, char **envp, int wait); - -extern struct subprocess_info * -call_usermodehelper_setup(const char *path, char **argv, char **envp, - gfp_t gfp_mask, - int (*init)(struct subprocess_info *info, struct cred *new), - void (*cleanup)(struct subprocess_info *), void *data); - -extern int -call_usermodehelper_exec(struct subprocess_info *info, int wait); - -extern struct ctl_table usermodehelper_table[]; - -enum umh_disable_depth { - UMH_ENABLED = 0, - UMH_FREEZING, - UMH_DISABLED, -}; - -extern int __usermodehelper_disable(enum umh_disable_depth depth); -extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth); - -static inline int usermodehelper_disable(void) -{ - return __usermodehelper_disable(UMH_DISABLED); -} - -static inline void usermodehelper_enable(void) -{ - __usermodehelper_set_disable_depth(UMH_ENABLED); -} - -extern int usermodehelper_read_trylock(void); -extern long usermodehelper_read_lock_wait(long timeout); -extern void usermodehelper_read_unlock(void); - #endif /* __LINUX_KMOD_H__ */ diff --git a/include/linux/kobject.h b/include/linux/kobject.h index ca85cb80e99a..e0a6205caa71 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -57,6 +57,8 @@ enum kobject_action { KOBJ_MOVE, KOBJ_ONLINE, KOBJ_OFFLINE, + KOBJ_BIND, + KOBJ_UNBIND, KOBJ_MAX }; @@ -172,7 +174,7 @@ struct kset { spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; -}; +} __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); @@ -217,11 +219,9 @@ extern struct kobject *firmware_kobj; int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]); +int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count); __printf(2, 3) int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...); -int kobject_action_type(const char *buf, size_t count, - enum kobject_action *type); - #endif /* _KOBJECT_H_ */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 541df0b5b815..bd2684700b74 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -267,8 +267,8 @@ extern int arch_init_kprobes(void); extern void show_registers(struct pt_regs *regs); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); -extern bool arch_function_offset_within_entry(unsigned long offset); -extern bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); +extern bool arch_kprobe_on_func_entry(unsigned long offset); +extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 4fec8b775895..82e197eeac91 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -15,7 +15,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), * @threadfn: the function to run in the thread * @data: data pointer for @threadfn() * @namefmt: printf-style format string for the thread name - * @...: arguments for @namefmt. + * @arg...: arguments for @namefmt. * * This macro will create a kthread on the current node, leaving it in * the stopped state. This is just a helper for kthread_create_on_node(); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8c0664309815..6882538eda32 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -126,6 +126,13 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_PENDING_TIMER 2 #define KVM_REQ_UNHALT 3 +#define KVM_REQUEST_ARCH_BASE 8 + +#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ + BUILD_BUG_ON((unsigned)(nr) >= 32 - KVM_REQUEST_ARCH_BASE); \ + (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ +}) +#define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -227,7 +234,7 @@ struct kvm_vcpu { int guest_fpu_loaded, guest_xcr0_loaded; struct swait_queue_head wq; - struct pid *pid; + struct pid __rcu *pid; int sigset_active; sigset_t sigset; struct kvm_vcpu_stat stat; @@ -383,7 +390,7 @@ struct kvm { spinlock_t mmu_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM]; + struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; /* @@ -397,7 +404,7 @@ struct kvm { int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; - struct kvm_io_bus *buses[KVM_NR_BUSES]; + struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_EVENTFD struct { spinlock_t lock; @@ -438,6 +445,7 @@ struct kvm { struct kvm_stat_data **debugfs_stat_data; struct srcu_struct srcu; struct srcu_struct irq_srcu; + pid_t userspace_pid; }; #define kvm_err(fmt, ...) \ @@ -466,6 +474,13 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) +{ + return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock) || + !refcount_read(&kvm->users_count)); +} + static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case @@ -555,9 +570,9 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - return rcu_dereference_check(kvm->memslots[as_id], - srcu_read_lock_held(&kvm->srcu) - || lockdep_is_held(&kvm->slots_lock)); + return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock) || + !refcount_read(&kvm->users_count)); } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) @@ -705,7 +720,7 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); -void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); @@ -785,6 +800,7 @@ int kvm_arch_hardware_setup(void); void kvm_arch_hardware_unsetup(void); void kvm_arch_check_processor_compat(void *rtn); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); +bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); #ifndef __KVM_HAVE_ARCH_VM_ALLOC @@ -970,6 +986,12 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) return (hpa_t)pfn << PAGE_SHIFT; } +static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu, + gpa_t gpa) +{ + return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa)); +} + static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); @@ -1098,6 +1120,11 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) set_bit(req & KVM_REQUEST_MASK, &vcpu->requests); } +static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) +{ + return READ_ONCE(vcpu->requests); +} + static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu) { return test_bit(req & KVM_REQUEST_MASK, &vcpu->requests); diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index 0c1de05098c8..76c2fbc59f35 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -46,7 +46,7 @@ struct kvm_kernel_irqfd_resampler { struct kvm_kernel_irqfd { /* Used for MSI fast-path */ struct kvm *kvm; - wait_queue_t wait; + wait_queue_entry_t wait; /* Update side is protected by irqfds.lock */ struct kvm_kernel_irq_routing_entry irq_entry; seqcount_t irq_entry_sc; diff --git a/include/linux/leds.h b/include/linux/leds.h index 64c56d454f7d..bf6db4fe895b 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -49,6 +49,7 @@ struct led_classdev { #define LED_HW_PLUGGABLE (1 << 19) #define LED_PANIC_INDICATOR (1 << 20) #define LED_BRIGHT_HW_CHANGED (1 << 21) +#define LED_RETAIN_AT_SHUTDOWN (1 << 22) /* set_brightness_work / blink_timer flags, atomic, private. */ unsigned long work_flags; @@ -392,6 +393,7 @@ struct gpio_led { unsigned retain_state_suspended : 1; unsigned panic_indicator : 1; unsigned default_state : 2; + unsigned retain_state_shutdown : 1; /* default_state should be one of LEDS_GPIO_DEFSTATE_(ON|OFF|KEEP) */ struct gpio_desc *gpiod; }; diff --git a/include/linux/lguest.h b/include/linux/lguest.h deleted file mode 100644 index 6db19f35f7c5..000000000000 --- a/include/linux/lguest.h +++ /dev/null @@ -1,73 +0,0 @@ -/* - * Things the lguest guest needs to know. Note: like all lguest interfaces, - * this is subject to wild and random change between versions. - */ -#ifndef _LINUX_LGUEST_H -#define _LINUX_LGUEST_H - -#ifndef __ASSEMBLY__ -#include <linux/time.h> -#include <asm/irq.h> -#include <asm/lguest_hcall.h> - -#define LG_CLOCK_MIN_DELTA 100UL -#define LG_CLOCK_MAX_DELTA ULONG_MAX - -/*G:031 - * The second method of communicating with the Host is to via "struct - * lguest_data". Once the Guest's initialization hypercall tells the Host where - * this is, the Guest and Host both publish information in it. -:*/ -struct lguest_data { - /* - * 512 == enabled (same as eflags in normal hardware). The Guest - * changes interrupts so often that a hypercall is too slow. - */ - unsigned int irq_enabled; - /* Fine-grained interrupt disabling by the Guest */ - DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS); - - /* - * The Host writes the virtual address of the last page fault here, - * which saves the Guest a hypercall. CR2 is the native register where - * this address would normally be found. - */ - unsigned long cr2; - - /* Wallclock time set by the Host. */ - struct timespec time; - - /* - * Interrupt pending set by the Host. The Guest should do a hypercall - * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF). - */ - int irq_pending; - - /* - * Async hypercall ring. Instead of directly making hypercalls, we can - * place them in here for processing the next time the Host wants. - * This batching can be quite efficient. - */ - - /* 0xFF == done (set by Host), 0 == pending (set by Guest). */ - u8 hcall_status[LHCALL_RING_SIZE]; - /* The actual registers for the hypercalls. */ - struct hcall_args hcalls[LHCALL_RING_SIZE]; - -/* Fields initialized by the Host at boot: */ - /* Memory not to try to access */ - unsigned long reserve_mem; - /* KHz for the TSC clock. */ - u32 tsc_khz; - -/* Fields initialized by the Guest at boot: */ - /* Instruction to suppress interrupts even if enabled */ - unsigned long noirq_iret; - /* Address above which page tables are all identical. */ - unsigned long kernel_address; - /* The vector to try to use for system calls (0x40 or 0x80). */ - unsigned int syscall_vec; -}; -extern struct lguest_data lguest_data; -#endif /* __ASSEMBLY__ */ -#endif /* _LINUX_LGUEST_H */ diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h deleted file mode 100644 index acd5b12565cc..000000000000 --- a/include/linux/lguest_launcher.h +++ /dev/null @@ -1,44 +0,0 @@ -#ifndef _LINUX_LGUEST_LAUNCHER -#define _LINUX_LGUEST_LAUNCHER -/* Everything the "lguest" userspace program needs to know. */ -#include <linux/types.h> - -/*D:010 - * Drivers - * - * The Guest needs devices to do anything useful. Since we don't let it touch - * real devices (think of the damage it could do!) we provide virtual devices. - * We emulate a PCI bus with virtio devices on it; we used to have our own - * lguest bus which was far simpler, but this tests the virtio 1.0 standard. - * - * Virtio devices are also used by kvm, so we can simply reuse their optimized - * device drivers. And one day when everyone uses virtio, my plan will be - * complete. Bwahahahah! - */ - -/* Write command first word is a request. */ -enum lguest_req -{ - LHREQ_INITIALIZE, /* + base, pfnlimit, start */ - LHREQ_GETDMA, /* No longer used */ - LHREQ_IRQ, /* + irq */ - LHREQ_BREAK, /* No longer used */ - LHREQ_EVENTFD, /* No longer used. */ - LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */ - LHREQ_SETREG, /* + offset within struct pt_regs, value. */ - LHREQ_TRAP, /* + trap number to deliver to guest. */ -}; - -/* - * This is what read() of the lguest fd populates. trap == - * LGUEST_TRAP_ENTRY for an LHCALL_NOTIFY (addr is the - * argument), 14 for a page fault in the MMIO region (addr is - * the trap address, insn is the instruction), or 13 for a GPF - * (insn is the instruction). - */ -struct lguest_pending { - __u8 trap; - __u8 insn[7]; - __u32 addr; -}; -#endif /* _LINUX_LGUEST_LAUNCHER */ diff --git a/include/linux/libata.h b/include/linux/libata.h index c9a69fc8821e..931c32f1f18d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -19,7 +19,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * */ @@ -156,6 +156,7 @@ enum { ATA_DFLAG_ACPI_PENDING = (1 << 5), /* ACPI resume action pending */ ATA_DFLAG_ACPI_FAILED = (1 << 6), /* ACPI on devcfg has failed */ ATA_DFLAG_AN = (1 << 7), /* AN configured */ + ATA_DFLAG_TRUSTED = (1 << 8), /* device supports trusted send/recv */ ATA_DFLAG_DMADIR = (1 << 10), /* device requires DMADIR */ ATA_DFLAG_CFG_MASK = (1 << 12) - 1, @@ -434,7 +435,7 @@ enum { ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ - ATA_HORKAGE_NO_NCQ_LOG = (1 << 23), /* don't use NCQ for log read */ + ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 6c807017128d..3eaad2fbf284 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/sizes.h> #include <linux/types.h> +#include <linux/uuid.h> enum { /* when a dimm supports both PMEM and BLK access a label is required */ @@ -54,6 +55,7 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; + unsigned long bus_dsm_mask; unsigned long cmd_mask; struct module *module; char *provider_name; @@ -71,15 +73,21 @@ struct nd_cmd_desc { }; struct nd_interleave_set { - u64 cookie; + /* v1.1 definition of the interleave-set-cookie algorithm */ + u64 cookie1; + /* v1.2 definition of the interleave-set-cookie algorithm */ + u64 cookie2; /* compatibility with initial buggy Linux implementation */ u64 altcookie; + + guid_t type_guid; }; struct nd_mapping_desc { struct nvdimm *nvdimm; u64 start; u64 size; + int position; }; struct nd_region_desc { @@ -159,9 +167,26 @@ void *nd_region_provider_data(struct nd_region *nd_region); void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); +unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); void nvdimm_flush(struct nd_region *nd_region); int nvdimm_has_flush(struct nd_region *nd_region); +int nvdimm_has_cache(struct nd_region *nd_region); + +#ifdef CONFIG_ARCH_HAS_PMEM_API +#define ARCH_MEMREMAP_PMEM MEMREMAP_WB +void arch_wb_cache_pmem(void *addr, size_t size); +void arch_invalidate_pmem(void *addr, size_t size); +#else +#define ARCH_MEMREMAP_PMEM MEMREMAP_WT +static inline void arch_wb_cache_pmem(void *addr, size_t size) +{ +} +static inline void arch_invalidate_pmem(void *addr, size_t size) +{ +} +#endif + #endif /* __LIBNVDIMM_H__ */ diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index cb0ba9f2a9a2..fa7fd03cb5f9 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -44,6 +44,7 @@ struct list_lru_node { /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg *memcg_lrus; #endif + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { diff --git a/include/linux/llist.h b/include/linux/llist.h index 171baa90f6f6..1957635e6d5f 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -93,6 +93,23 @@ static inline void init_llist_head(struct llist_head *list) container_of(ptr, type, member) /** + * member_address_is_nonnull - check whether the member address is not NULL + * @ptr: the object pointer (struct type * that contains the llist_node) + * @member: the name of the llist_node within the struct. + * + * This macro is conceptually the same as + * &ptr->member != NULL + * but it works around the fact that compilers can decide that taking a member + * address is never a NULL pointer. + * + * Real objects that start at a high address and have a member at NULL are + * unlikely to exist, but such pointers may be returned e.g. by the + * container_of() macro. + */ +#define member_address_is_nonnull(ptr, member) \ + ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) + +/** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries @@ -110,6 +127,25 @@ static inline void init_llist_head(struct llist_head *list) for ((pos) = (node); pos; (pos) = (pos)->next) /** + * llist_for_each_safe - iterate over some deleted entries of a lock-less list + * safe against removal of list entry + * @pos: the &struct llist_node to use as a loop cursor + * @n: another &struct llist_node to use as temporary storage + * @node: the first entry of deleted list entries + * + * In general, some entries of the lock-less list can be traversed + * safely only after being deleted from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_safe(pos, n, node) \ + for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) + +/** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. @@ -126,7 +162,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ - &(pos)->member != NULL; \ + member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** @@ -148,7 +184,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ - &pos->member != NULL && \ + member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 41f7b6a04d69..3eca67728366 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -192,9 +192,9 @@ struct nlm_block { * Global variables */ extern const struct rpc_program nlm_program; -extern struct svc_procedure nlmsvc_procedures[]; +extern const struct svc_procedure nlmsvc_procedures[]; #ifdef CONFIG_LOCKD_V4 -extern struct svc_procedure nlmsvc_procedures4[]; +extern const struct svc_procedure nlmsvc_procedures4[]; #endif extern int nlmsvc_grace_period; extern unsigned long nlmsvc_timeout; diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index d39ed1cc5fbf..7acbecc21a40 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -95,19 +95,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); +int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_res(struct svc_rqst *, __be32 *); +int nlmsvc_decode_res(struct svc_rqst *, __be32 *); +int nlmsvc_encode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); +int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); +int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index e58c88b52ce1..bf1645609225 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -23,19 +23,19 @@ -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); +int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_res(struct svc_rqst *, __be32 *); +int nlm4svc_decode_res(struct svc_rqst *, __be32 *); +int nlm4svc_encode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); +int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); +int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index fffe49f188e6..bfa8e0b0d6f1 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -18,6 +18,8 @@ extern int lock_stat; #define MAX_LOCKDEP_SUBCLASSES 8UL +#include <linux/types.h> + #ifdef CONFIG_LOCKDEP #include <linux/linkage.h> @@ -29,7 +31,7 @@ extern int lock_stat; * We'd rather not expose kernel/lockdep_states.h this wide, but we do need * the total number of states... :-( */ -#define XXX_LOCK_USAGE_STATES (1+3*4) +#define XXX_LOCK_USAGE_STATES (1+2*4) /* * NR_LOCKDEP_CACHING_CLASSES ... Number of classes @@ -155,6 +157,12 @@ struct lockdep_map { int cpu; unsigned long ip; #endif +#ifdef CONFIG_LOCKDEP_CROSSRELEASE + /* + * Whether it's a crosslock. + */ + int cross; +#endif }; static inline void lockdep_copy_map(struct lockdep_map *to, @@ -258,8 +266,95 @@ struct held_lock { unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ unsigned int pin_count; +#ifdef CONFIG_LOCKDEP_CROSSRELEASE + /* + * Generation id. + * + * A value of cross_gen_id will be stored when holding this, + * which is globally increased whenever each crosslock is held. + */ + unsigned int gen_id; +#endif +}; + +#ifdef CONFIG_LOCKDEP_CROSSRELEASE +#define MAX_XHLOCK_TRACE_ENTRIES 5 + +/* + * This is for keeping locks waiting for commit so that true dependencies + * can be added at commit step. + */ +struct hist_lock { + /* + * Id for each entry in the ring buffer. This is used to + * decide whether the ring buffer was overwritten or not. + * + * For example, + * + * |<----------- hist_lock ring buffer size ------->| + * pppppppppppppppppppppiiiiiiiiiiiiiiiiiiiiiiiiiiiii + * wrapped > iiiiiiiiiiiiiiiiiiiiiiiiiii....................... + * + * where 'p' represents an acquisition in process + * context, 'i' represents an acquisition in irq + * context. + * + * In this example, the ring buffer was overwritten by + * acquisitions in irq context, that should be detected on + * rollback or commit. + */ + unsigned int hist_id; + + /* + * Seperate stack_trace data. This will be used at commit step. + */ + struct stack_trace trace; + unsigned long trace_entries[MAX_XHLOCK_TRACE_ENTRIES]; + + /* + * Seperate hlock instance. This will be used at commit step. + * + * TODO: Use a smaller data structure containing only necessary + * data. However, we should make lockdep code able to handle the + * smaller one first. + */ + struct held_lock hlock; +}; + +/* + * To initialize a lock as crosslock, lockdep_init_map_crosslock() should + * be called instead of lockdep_init_map(). + */ +struct cross_lock { + /* + * When more than one acquisition of crosslocks are overlapped, + * we have to perform commit for them based on cross_gen_id of + * the first acquisition, which allows us to add more true + * dependencies. + * + * Moreover, when no acquisition of a crosslock is in progress, + * we should not perform commit because the lock might not exist + * any more, which might cause incorrect memory access. So we + * have to track the number of acquisitions of a crosslock. + */ + int nr_acquire; + + /* + * Seperate hlock instance. This will be used at commit step. + * + * TODO: Use a smaller data structure containing only necessary + * data. However, we should make lockdep code able to handle the + * smaller one first. + */ + struct held_lock hlock; }; +struct lockdep_map_cross { + struct lockdep_map map; + struct cross_lock xlock; +}; +#endif + /* * Initialization, self-test and debugging-output methods: */ @@ -282,13 +377,6 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass); /* - * To initialize a lockdep_map statically use this macro. - * Note that _name must not be NULL. - */ -#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ - { .name = (_name), .key = (void *)(_key), } - -/* * Reinitialize a lock key - for cases where there is special locking or * special initialization of locks so that the validator gets the scope * of dependencies wrong: they are either too broad (they need a class-split) @@ -363,10 +451,6 @@ static inline void lock_set_subclass(struct lockdep_map *lock, extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip); -extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask); -extern void lockdep_clear_current_reclaim_state(void); -extern void lockdep_trace_alloc(gfp_t mask); - struct pin_cookie { unsigned int val; }; #define NIL_COOKIE (struct pin_cookie){ .val = 0U, } @@ -375,7 +459,7 @@ extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie); extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); -# define INIT_LOCKDEP .lockdep_recursion = 0, .lockdep_reclaim_gfp = 0, +# define INIT_LOCKDEP .lockdep_recursion = 0, #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) @@ -416,9 +500,6 @@ static inline void lockdep_on(void) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) -# define lockdep_set_current_reclaim_state(g) do { } while (0) -# define lockdep_clear_current_reclaim_state() do { } while (0) -# define lockdep_trace_alloc(g) do { } while (0) # define lockdep_info() do { } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) @@ -467,6 +548,58 @@ struct pin_cookie { }; #endif /* !LOCKDEP */ +enum xhlock_context_t { + XHLOCK_HARD, + XHLOCK_SOFT, + XHLOCK_CTX_NR, +}; + +#ifdef CONFIG_LOCKDEP_CROSSRELEASE +extern void lockdep_init_map_crosslock(struct lockdep_map *lock, + const char *name, + struct lock_class_key *key, + int subclass); +extern void lock_commit_crosslock(struct lockdep_map *lock); + +/* + * What we essencially have to initialize is 'nr_acquire'. Other members + * will be initialized in add_xlock(). + */ +#define STATIC_CROSS_LOCK_INIT() \ + { .nr_acquire = 0,} + +#define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \ + { .map.name = (_name), .map.key = (void *)(_key), \ + .map.cross = 1, .xlock = STATIC_CROSS_LOCK_INIT(), } + +/* + * To initialize a lockdep_map statically use this macro. + * Note that _name must not be NULL. + */ +#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ + { .name = (_name), .key = (void *)(_key), .cross = 0, } + +extern void crossrelease_hist_start(enum xhlock_context_t c); +extern void crossrelease_hist_end(enum xhlock_context_t c); +extern void lockdep_invariant_state(bool force); +extern void lockdep_init_task(struct task_struct *task); +extern void lockdep_free_task(struct task_struct *task); +#else /* !CROSSRELEASE */ +#define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) +/* + * To initialize a lockdep_map statically use this macro. + * Note that _name must not be NULL. + */ +#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ + { .name = (_name), .key = (void *)(_key), } + +static inline void crossrelease_hist_start(enum xhlock_context_t c) {} +static inline void crossrelease_hist_end(enum xhlock_context_t c) {} +static inline void lockdep_invariant_state(bool force) {} +static inline void lockdep_init_task(struct task_struct *task) {} +static inline void lockdep_free_task(struct task_struct *task) {} +#endif /* CROSSRELEASE */ + #ifdef CONFIG_LOCK_STAT extern void lock_contended(struct lockdep_map *lock, unsigned long ip); diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index e58e577117b6..d1c2901f1542 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -4,7 +4,7 @@ * * Author : Etienne BASSET <etienne.basset@ensta.org> * - * All credits to : Stephen Smalley, <sds@epoch.ncsc.mil> + * All credits to : Stephen Smalley, <sds@tycho.nsa.gov> * All BUGS to : Etienne BASSET <etienne.basset@ensta.org> */ #ifndef _LSM_COMMON_LOGGING_ @@ -21,6 +21,7 @@ #include <linux/path.h> #include <linux/key.h> #include <linux/skbuff.h> +#include <rdma/ib_verbs.h> struct lsm_network_audit { int netif; @@ -45,6 +46,16 @@ struct lsm_ioctlop_audit { u16 cmd; }; +struct lsm_ibpkey_audit { + u64 subnet_prefix; + u16 pkey; +}; + +struct lsm_ibendport_audit { + char dev_name[IB_DEVICE_NAME_MAX]; + u8 port; +}; + /* Auxiliary data to use in generating the audit record. */ struct common_audit_data { char type; @@ -60,6 +71,8 @@ struct common_audit_data { #define LSM_AUDIT_DATA_DENTRY 10 #define LSM_AUDIT_DATA_IOCTL_OP 11 #define LSM_AUDIT_DATA_FILE 12 +#define LSM_AUDIT_DATA_IBPKEY 13 +#define LSM_AUDIT_DATA_IBENDPORT 14 union { struct path path; struct dentry *dentry; @@ -77,6 +90,8 @@ struct common_audit_data { char *kmod_name; struct lsm_ioctlop_audit *op; struct file *file; + struct lsm_ibpkey_audit *ibpkey; + struct lsm_ibendport_audit *ibendport; } u; /* this union contains LSM specific data */ union { diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 080f34e66017..c9258124e417 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -8,6 +8,7 @@ * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) * Copyright (C) 2015 Intel Corporation. * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> + * Copyright (C) 2016 Mellanox Techonologies * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -29,6 +30,8 @@ #include <linux/rculist.h> /** + * union security_list_options - Linux Security Module hook function list + * * Security hooks for program execution operations. * * @bprm_set_creds: @@ -40,7 +43,11 @@ * interpreters. The hook can tell whether it has already been called by * checking to see if @bprm->security is non-NULL. If so, then the hook * may decide either to retain the security information saved earlier or - * to replace it. + * to replace it. The hook must set @bprm->secureexec to 1 if a "secure + * exec" has happened as a result of this hook call. The flag is used to + * indicate the need for a sanitized execution environment, and is also + * passed in the ELF auxiliary table on the initial stack to indicate + * whether libc should enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: @@ -68,12 +75,6 @@ * linux_binprm structure. This hook is a good place to perform state * changes on the process such as clearing out non-inheritable signal * state. This is called immediately after commit_creds(). - * @bprm_secureexec: - * Return a boolean value (0 or 1) indicating whether a "secure exec" - * is required. The flag is passed in the auxiliary table - * on the initial stack to the ELF interpreter to indicate whether libc - * should enable secure mode. - * @bprm contains the linux_binprm structure. * * Security hooks for filesystem operations. * @@ -193,8 +194,8 @@ * @value will be set to the allocated attribute value. * @len will be set to the length of the value. * Returns 0 if @name and @value have been successfully set, - * -EOPNOTSUPP if no security attribute is needed, or - * -ENOMEM on memory allocation failure. + * -EOPNOTSUPP if no security attribute is needed, or + * -ENOMEM on memory allocation failure. * @inode_create: * Check permission to create a regular file. * @dir contains inode structure of the parent of the new file. @@ -510,8 +511,7 @@ * process @tsk. Note that this hook is sometimes called from interrupt. * Note that the fown_struct, @fown, is never outside the context of a * struct file, so the file structure (and associated security information) - * can always be obtained: - * container_of(fown, struct file, f_owner) + * can always be obtained: container_of(fown, struct file, f_owner) * @tsk contains the structure of task receiving signal. * @fown contains the file owner information. * @sig is the signal that will be sent. When 0, kernel sends SIGIO. @@ -521,18 +521,13 @@ * to receive an open file descriptor via socket IPC. * @file contains the file structure being received. * Return 0 if permission is granted. - * @file_open + * @file_open: * Save open-time permission checking state for later use upon * file_permission, and recheck access if anything has changed * since inode_permission. * * Security hooks for task operations. * - * @task_create: - * Check permission before creating a child process. See the clone(2) - * manual page for definitions of the @clone_flags. - * @clone_flags contains the flags indicating what should be shared. - * Return 0 if permission is granted. * @task_alloc: * @task task being allocated. * @clone_flags contains the flags indicating what should be shared. @@ -911,6 +906,26 @@ * associated with the TUN device's security structure. * @security pointer to the TUN devices's security structure. * + * Security hooks for Infiniband + * + * @ib_pkey_access: + * Check permission to access a pkey when modifing a QP. + * @subnet_prefix the subnet prefix of the port being used. + * @pkey the pkey to be accessed. + * @sec pointer to a security structure. + * @ib_endport_manage_subnet: + * Check permissions to send and receive SMPs on a end port. + * @dev_name the IB device name (i.e. mlx4_0). + * @port_num the port number. + * @sec pointer to a security structure. + * @ib_alloc_security: + * Allocate a security structure for Infiniband objects. + * @sec pointer to a security structure pointer. + * Returns 0 on success, non-zero on failure + * @ib_free_security: + * Deallocate an Infiniband security structure. + * @sec contains the security structure to be freed. + * * Security hooks for XFRM operations. * * @xfrm_policy_alloc_security: @@ -1143,7 +1158,7 @@ * @sma contains the semaphore structure. May be NULL. * @cmd contains the operation to be performed. * Return 0 if permission is granted. - * @sem_semop + * @sem_semop: * Check permissions before performing operations on members of the * semaphore set @sma. If the @alter flag is nonzero, the semaphore set * may be modified. @@ -1153,20 +1168,20 @@ * @alter contains the flag indicating whether changes are to be made. * Return 0 if permission is granted. * - * @binder_set_context_mgr + * @binder_set_context_mgr: * Check whether @mgr is allowed to be the binder context manager. * @mgr contains the task_struct for the task being registered. * Return 0 if permission is granted. - * @binder_transaction + * @binder_transaction: * Check whether @from is allowed to invoke a binder transaction call * to @to. * @from contains the task_struct for the sending task. * @to contains the task_struct for the receiving task. - * @binder_transfer_binder + * @binder_transfer_binder: * Check whether @from is allowed to transfer a binder reference to @to. * @from contains the task_struct for the sending task. * @to contains the task_struct for the receiving task. - * @binder_transfer_file + * @binder_transfer_file: * Check whether @from is allowed to transfer @file to @to. * @from contains the task_struct for the sending task. * @file contains the struct file being transferred. @@ -1214,7 +1229,7 @@ * @cred contains the credentials to use. * @ns contains the user namespace we want the capability in * @cap contains the capability <include/linux/capability.h>. - * @audit: Whether to write an audit message or not + * @audit contains whether to write an audit message or not * Return 0 if the capability is granted for @tsk. * @syslog: * Check permission before accessing the kernel message ring or changing @@ -1336,9 +1351,7 @@ * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. - * This is the main security structure. */ - union security_list_options { int (*binder_set_context_mgr)(struct task_struct *mgr); int (*binder_transaction)(struct task_struct *from, @@ -1368,7 +1381,6 @@ union security_list_options { int (*bprm_set_creds)(struct linux_binprm *bprm); int (*bprm_check_security)(struct linux_binprm *bprm); - int (*bprm_secureexec)(struct linux_binprm *bprm); void (*bprm_committing_creds)(struct linux_binprm *bprm); void (*bprm_committed_creds)(struct linux_binprm *bprm); @@ -1388,7 +1400,9 @@ union security_list_options { unsigned long kern_flags, unsigned long *set_kern_flags); int (*sb_clone_mnt_opts)(const struct super_block *oldsb, - struct super_block *newsb); + struct super_block *newsb, + unsigned long kern_flags, + unsigned long *set_kern_flags); int (*sb_parse_opts_str)(char *options, struct security_mnt_opts *opts); int (*dentry_init_security)(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, @@ -1486,7 +1500,6 @@ union security_list_options { int (*file_receive)(struct file *file); int (*file_open)(struct file *file, const struct cred *cred); - int (*task_create)(unsigned long clone_flags); int (*task_alloc)(struct task_struct *task, unsigned long clone_flags); void (*task_free)(struct task_struct *task); int (*cred_alloc_blank)(struct cred *cred, gfp_t gfp); @@ -1620,6 +1633,14 @@ union security_list_options { int (*tun_dev_open)(void *security); #endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_INFINIBAND + int (*ib_pkey_access)(void *sec, u64 subnet_prefix, u16 pkey); + int (*ib_endport_manage_subnet)(void *sec, const char *dev_name, + u8 port_num); + int (*ib_alloc_security)(void **sec); + void (*ib_free_security)(void *sec); +#endif /* CONFIG_SECURITY_INFINIBAND */ + #ifdef CONFIG_SECURITY_NETWORK_XFRM int (*xfrm_policy_alloc_security)(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, @@ -1680,7 +1701,6 @@ struct security_hook_heads { struct list_head vm_enough_memory; struct list_head bprm_set_creds; struct list_head bprm_check_security; - struct list_head bprm_secureexec; struct list_head bprm_committing_creds; struct list_head bprm_committed_creds; struct list_head sb_alloc_security; @@ -1753,7 +1773,6 @@ struct security_hook_heads { struct list_head file_send_sigiotask; struct list_head file_receive; struct list_head file_open; - struct list_head task_create; struct list_head task_alloc; struct list_head task_free; struct list_head cred_alloc_blank; @@ -1851,6 +1870,12 @@ struct security_hook_heads { struct list_head tun_dev_attach; struct list_head tun_dev_open; #endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_INFINIBAND + struct list_head ib_pkey_access; + struct list_head ib_endport_manage_subnet; + struct list_head ib_alloc_security; + struct list_head ib_free_security; +#endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM struct list_head xfrm_policy_alloc_security; struct list_head xfrm_policy_clone_security; @@ -1876,7 +1901,7 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ -}; +} __randomize_layout; /* * Security module hook list structure. @@ -1887,7 +1912,7 @@ struct security_hook_list { struct list_head *head; union security_list_options hook; char *lsm; -}; +} __randomize_layout; /* * Initializing a security_hook_list structure takes diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h index ac02c54520e9..a7330eb3ec64 100644 --- a/include/linux/mISDNif.h +++ b/include/linux/mISDNif.h @@ -554,7 +554,7 @@ _alloc_mISDN_skb(u_int prim, u_int id, u_int len, void *dp, gfp_t gfp_mask) if (!skb) return NULL; if (len) - memcpy(skb_put(skb, len), dp, len); + skb_put_data(skb, dp, len); hh = mISDN_HEAD_P(skb); hh->prim = prim; hh->id = id; diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 86c9a8b480c5..e1bc73414983 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -19,15 +19,15 @@ struct mb_cache_entry { u32 e_key; u32 e_referenced:1; u32 e_reusable:1; - /* Block number of hashed block - stable during lifetime of the entry */ - sector_t e_block; + /* User provided value - stable during lifetime of the entry */ + u64 e_value; }; struct mb_cache *mb_cache_create(int bucket_bits); void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, - sector_t block, bool reusable); + u64 value, bool reusable); void __mb_cache_entry_free(struct mb_cache_entry *entry); static inline int mb_cache_entry_put(struct mb_cache *cache, struct mb_cache_entry *entry) @@ -38,10 +38,9 @@ static inline int mb_cache_entry_put(struct mb_cache *cache, return 1; } -void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, - sector_t block); +void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, - sector_t block); + u64 value); struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, u32 key); struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, diff --git a/include/linux/mcb.h b/include/linux/mcb.h index 4097ac9ea13a..b1a0ad9d23b3 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -136,5 +136,7 @@ extern struct resource *mcb_request_mem(struct mcb_device *dev, const char *name); extern void mcb_release_mem(struct resource *mem); extern int mcb_get_irq(struct mcb_device *dev); +extern struct resource *mcb_get_resource(struct mcb_device *dev, + unsigned int type); #endif /* _LINUX_MCB_H */ diff --git a/include/linux/mdio-mux.h b/include/linux/mdio-mux.h index 61f5b21b31c7..a5d58f221939 100644 --- a/include/linux/mdio-mux.h +++ b/include/linux/mdio-mux.h @@ -12,7 +12,16 @@ #include <linux/device.h> #include <linux/phy.h> +/* mdio_mux_init() - Initialize a MDIO mux + * @dev The device owning the MDIO mux + * @mux_node The device node of the MDIO mux + * @switch_fn The function called for switching target MDIO child + * mux_handle A pointer to a (void *) used internaly by mdio-mux + * @data Private data used by switch_fn() + * @mux_bus An optional parent bus (Other case are to use parent_bus property) + */ int mdio_mux_init(struct device *dev, + struct device_node *mux_node, int (*switch_fn) (int cur, int desired, void *data), void **mux_handle, void *data, diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h new file mode 100644 index 000000000000..265a9cd21cb4 --- /dev/null +++ b/include/linux/mem_encrypt.h @@ -0,0 +1,53 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __MEM_ENCRYPT_H__ +#define __MEM_ENCRYPT_H__ + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_ARCH_HAS_MEM_ENCRYPT + +#include <asm/mem_encrypt.h> + +#else /* !CONFIG_ARCH_HAS_MEM_ENCRYPT */ + +#define sme_me_mask 0ULL + +#endif /* CONFIG_ARCH_HAS_MEM_ENCRYPT */ + +static inline bool sme_active(void) +{ + return !!sme_me_mask; +} + +static inline u64 sme_get_me_mask(void) +{ + return sme_me_mask; +} + +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* + * The __sme_set() and __sme_clr() macros are useful for adding or removing + * the encryption mask from a value (e.g. when dealing with pagetable + * entries). + */ +#define __sme_set(x) ((x) | sme_me_mask) +#define __sme_clr(x) ((x) & ~sme_me_mask) +#else +#define __sme_set(x) (x) +#define __sme_clr(x) (x) +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* __MEM_ENCRYPT_H__ */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8098695e5d8d..bae11c7e7bf3 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -57,14 +57,11 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; -#ifdef CONFIG_MOVABLE_NODE -/* If movable_node boot option specified */ -extern bool movable_node_enabled; -#endif /* CONFIG_MOVABLE_NODE */ #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit #define __initdata_memblock __meminitdata +void memblock_discard(void); #else #define __init_memblock #define __initdata_memblock @@ -78,8 +75,6 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, int nid, ulong flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); -phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); -phys_addr_t get_allocated_memblock_memory_regions_info(phys_addr_t *addr); void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); @@ -114,6 +109,9 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags, void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, phys_addr_t *out_end); +void __memblock_free_early(phys_addr_t base, phys_addr_t size); +void __memblock_free_late(phys_addr_t base, phys_addr_t size); + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. @@ -169,27 +167,11 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, i != (u64)ULLONG_MAX; \ __next_reserved_mem_region(&i, p_start, p_end)) -#ifdef CONFIG_MOVABLE_NODE static inline bool memblock_is_hotpluggable(struct memblock_region *m) { return m->flags & MEMBLOCK_HOTPLUG; } -static inline bool __init_memblock movable_node_is_enabled(void) -{ - return movable_node_enabled; -} -#else -static inline bool memblock_is_hotpluggable(struct memblock_region *m) -{ - return false; -} -static inline bool movable_node_is_enabled(void) -{ - return false; -} -#endif - static inline bool memblock_is_mirror(struct memblock_region *m) { return m->flags & MEMBLOCK_MIRROR; @@ -296,7 +278,6 @@ phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); -#ifdef CONFIG_MOVABLE_NODE /* * Set the allocation direction to bottom-up or top-down. */ @@ -314,10 +295,6 @@ static inline bool memblock_bottom_up(void) { return memblock.bottom_up; } -#else -static inline void __init memblock_set_bottom_up(bool enable) {} -static inline bool memblock_bottom_up(void) { return false; } -#endif /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 899949bbb2f9..69966c461d1c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -26,7 +26,8 @@ #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> -#include <linux/mmzone.h> +#include <linux/mm.h> +#include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> @@ -44,8 +45,6 @@ enum memcg_stat_item { MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ MEMCG_KERNEL_STACK_KB, - MEMCG_SLAB_RECLAIMABLE, - MEMCG_SLAB_UNRECLAIMABLE, MEMCG_NR_STAT, }; @@ -100,11 +99,16 @@ struct mem_cgroup_reclaim_iter { unsigned int generation; }; +struct lruvec_stat { + long count[NR_VM_NODE_STAT_ITEMS]; +}; + /* * per-zone information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; + struct lruvec_stat __percpu *lruvec_stat; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; @@ -357,6 +361,17 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); +static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) +{ + struct mem_cgroup_per_node *mz; + + if (mem_cgroup_disabled()) + return NULL; + + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + return mz->memcg; +} + /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find @@ -469,11 +484,13 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -void lock_page_memcg(struct page *page); +struct mem_cgroup *lock_page_memcg(struct page *page); +void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { long val = 0; int cpu; @@ -487,23 +504,20 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, return val; } -static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, int val) +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void __mod_memcg_state(struct mem_cgroup *memcg, + int idx, int val) { if (!mem_cgroup_disabled()) - this_cpu_add(memcg->stat->count[idx], val); -} - -static inline void inc_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) -{ - mod_memcg_state(memcg, idx, 1); + __this_cpu_add(memcg->stat->count[idx], val); } -static inline void dec_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void mod_memcg_state(struct mem_cgroup *memcg, + int idx, int val) { - mod_memcg_state(memcg, idx, -1); + if (!mem_cgroup_disabled()) + this_cpu_add(memcg->stat->count[idx], val); } /** @@ -523,31 +537,114 @@ static inline void dec_memcg_state(struct mem_cgroup *memcg, * * Kernel pages are an exception to this, since they'll never move. */ +static inline void __mod_memcg_page_state(struct page *page, + int idx, int val) +{ + if (page->mem_cgroup) + __mod_memcg_state(page->mem_cgroup, idx, val); +} + static inline void mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, int val) + int idx, int val) { if (page->mem_cgroup) mod_memcg_state(page->mem_cgroup, idx, val); } -static inline void inc_memcg_page_state(struct page *page, - enum memcg_stat_item idx) +static inline unsigned long lruvec_page_state(struct lruvec *lruvec, + enum node_stat_item idx) { - mod_memcg_page_state(page, idx, 1); + struct mem_cgroup_per_node *pn; + long val = 0; + int cpu; + + if (mem_cgroup_disabled()) + return node_page_state(lruvec_pgdat(lruvec), idx); + + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + for_each_possible_cpu(cpu) + val += per_cpu(pn->lruvec_stat->count[idx], cpu); + + if (val < 0) + val = 0; + + return val; } -static inline void dec_memcg_page_state(struct page *page, - enum memcg_stat_item idx) +static inline void __mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) { - mod_memcg_page_state(page, idx, -1); + struct mem_cgroup_per_node *pn; + + __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); + if (mem_cgroup_disabled()) + return; + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + __mod_memcg_state(pn->memcg, idx, val); + __this_cpu_add(pn->lruvec_stat->count[idx], val); +} + +static inline void mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) +{ + struct mem_cgroup_per_node *pn; + + mod_node_page_state(lruvec_pgdat(lruvec), idx, val); + if (mem_cgroup_disabled()) + return; + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + mod_memcg_state(pn->memcg, idx, val); + this_cpu_add(pn->lruvec_stat->count[idx], val); +} + +static inline void __mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) +{ + struct mem_cgroup_per_node *pn; + + __mod_node_page_state(page_pgdat(page), idx, val); + if (mem_cgroup_disabled() || !page->mem_cgroup) + return; + __mod_memcg_state(page->mem_cgroup, idx, val); + pn = page->mem_cgroup->nodeinfo[page_to_nid(page)]; + __this_cpu_add(pn->lruvec_stat->count[idx], val); +} + +static inline void mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) +{ + struct mem_cgroup_per_node *pn; + + mod_node_page_state(page_pgdat(page), idx, val); + if (mem_cgroup_disabled() || !page->mem_cgroup) + return; + mod_memcg_state(page->mem_cgroup, idx, val); + pn = page->mem_cgroup->nodeinfo[page_to_nid(page)]; + this_cpu_add(pn->lruvec_stat->count[idx], val); } unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); -static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, - enum vm_event_item idx) +static inline void count_memcg_events(struct mem_cgroup *memcg, + enum vm_event_item idx, + unsigned long count) +{ + if (!mem_cgroup_disabled()) + this_cpu_add(memcg->stat->events[idx], count); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void count_memcg_page_event(struct page *page, + int idx) +{ + if (page->mem_cgroup) + count_memcg_events(page->mem_cgroup, idx, 1); +} + +static inline void count_memcg_event_mm(struct mm_struct *mm, + enum vm_event_item idx) { struct mem_cgroup *memcg; @@ -556,8 +653,11 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (likely(memcg)) + if (likely(memcg)) { this_cpu_inc(memcg->stat->events[idx]); + if (idx == OOM_KILL) + cgroup_file_notify(&memcg->events_file); + } rcu_read_unlock(); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -675,6 +775,11 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return NULL; } +static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) +{ + return NULL; +} + static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; @@ -709,7 +814,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline void lock_page_memcg(struct page *page) +static inline struct mem_cgroup *lock_page_memcg(struct page *page) +{ + return NULL; +} + +static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } @@ -740,41 +850,63 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { return 0; } -static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, - int nr) +static inline void __mod_memcg_state(struct mem_cgroup *memcg, + int idx, + int nr) { } -static inline void inc_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) +static inline void mod_memcg_state(struct mem_cgroup *memcg, + int idx, + int nr) { } -static inline void dec_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) +static inline void __mod_memcg_page_state(struct page *page, + int idx, + int nr) { } static inline void mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, + int idx, int nr) { } -static inline void inc_memcg_page_state(struct page *page, - enum memcg_stat_item idx) +static inline unsigned long lruvec_page_state(struct lruvec *lruvec, + enum node_stat_item idx) { + return node_page_state(lruvec_pgdat(lruvec), idx); } -static inline void dec_memcg_page_state(struct page *page, - enum memcg_stat_item idx) +static inline void __mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) +{ + __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); +} + +static inline void mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) +{ + mod_node_page_state(lruvec_pgdat(lruvec), idx, val); +} + +static inline void __mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) +{ + __mod_node_page_state(page_pgdat(page), idx, val); +} + +static inline void mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) { + mod_node_page_state(page_pgdat(page), idx, val); } static inline @@ -789,12 +921,127 @@ static inline void mem_cgroup_split_huge_fixup(struct page *head) { } +static inline void count_memcg_events(struct mem_cgroup *memcg, + enum vm_event_item idx, + unsigned long count) +{ +} + +static inline void count_memcg_page_event(struct page *page, + int idx) +{ +} + static inline -void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) +void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } #endif /* CONFIG_MEMCG */ +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void __inc_memcg_state(struct mem_cgroup *memcg, + int idx) +{ + __mod_memcg_state(memcg, idx, 1); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void __dec_memcg_state(struct mem_cgroup *memcg, + int idx) +{ + __mod_memcg_state(memcg, idx, -1); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void __inc_memcg_page_state(struct page *page, + int idx) +{ + __mod_memcg_page_state(page, idx, 1); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void __dec_memcg_page_state(struct page *page, + int idx) +{ + __mod_memcg_page_state(page, idx, -1); +} + +static inline void __inc_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + __mod_lruvec_state(lruvec, idx, 1); +} + +static inline void __dec_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + __mod_lruvec_state(lruvec, idx, -1); +} + +static inline void __inc_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + __mod_lruvec_page_state(page, idx, 1); +} + +static inline void __dec_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + __mod_lruvec_page_state(page, idx, -1); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void inc_memcg_state(struct mem_cgroup *memcg, + int idx) +{ + mod_memcg_state(memcg, idx, 1); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void dec_memcg_state(struct mem_cgroup *memcg, + int idx) +{ + mod_memcg_state(memcg, idx, -1); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void inc_memcg_page_state(struct page *page, + int idx) +{ + mod_memcg_page_state(page, idx, 1); +} + +/* idx can be of type enum memcg_stat_item or node_stat_item */ +static inline void dec_memcg_page_state(struct page *page, + int idx) +{ + mod_memcg_page_state(page, idx, -1); +} + +static inline void inc_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + mod_lruvec_state(lruvec, idx, 1); +} + +static inline void dec_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + mod_lruvec_state(lruvec, idx, -1); +} + +static inline void inc_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + mod_lruvec_page_state(page, idx, 1); +} + +static inline void dec_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + mod_lruvec_page_state(page, idx, -1); +} + #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); @@ -886,19 +1133,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -/** - * memcg_kmem_update_page_stat - update kmem page state statistics - * @page: the page - * @idx: page state item to account - * @val: number of pages (positive or negative) - */ -static inline void memcg_kmem_update_page_stat(struct page *page, - enum memcg_stat_item idx, int val) -{ - if (memcg_kmem_enabled() && page->mem_cgroup) - this_cpu_add(page->mem_cgroup->stat->count[idx], val); -} - #else #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) @@ -921,10 +1155,6 @@ static inline void memcg_put_cache_ids(void) { } -static inline void memcg_kmem_update_page_stat(struct page *page, - enum memcg_stat_item idx, int val) -{ -} #endif /* CONFIG_MEMCG && !CONFIG_SLOB */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 134a2f69c21a..0995e1a2b458 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -14,6 +14,20 @@ struct memory_block; struct resource; #ifdef CONFIG_MEMORY_HOTPLUG +/* + * Return page for the valid pfn only if the page is online. All pfn + * walkers which rely on the fully initialized page->flags and others + * should use this rather than pfn_valid && pfn_to_page + */ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___nr = pfn_to_section_nr(pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ + ___page = pfn_to_page(pfn); \ + ___page; \ +}) /* * Types for free bootmem stored in page->lru.next. These have to be in @@ -101,6 +115,12 @@ extern void __online_page_free(struct page *page); extern int try_online_node(int nid); extern bool memhp_auto_online; +/* If movable_node boot option specified */ +extern bool movable_node_enabled; +static inline bool movable_node_is_enabled(void) +{ + return movable_node_enabled; +} #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); @@ -109,9 +129,20 @@ extern int __remove_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); #endif /* CONFIG_MEMORY_HOTREMOVE */ -/* reasonably generic interface to expand the physical pages in a zone */ -extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages); +/* reasonably generic interface to expand the physical pages */ +extern int __add_pages(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool want_memblock); + +#ifndef CONFIG_ARCH_HAS_ADD_PAGES +static inline int add_pages(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool want_memblock) +{ + return __add_pages(nid, start_pfn, nr_pages, want_memblock); +} +#else /* ARCH_HAS_ADD_PAGES */ +int add_pages(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool want_memblock); +#endif /* ARCH_HAS_ADD_PAGES */ #ifdef CONFIG_NUMA extern int memory_add_physaddr_to_nid(u64 start); @@ -203,6 +234,14 @@ extern void set_zone_contiguous(struct zone *zone); extern void clear_zone_contiguous(struct zone *zone); #else /* ! CONFIG_MEMORY_HOTPLUG */ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + if (pfn_valid(pfn)) \ + ___page = pfn_to_page(pfn); \ + ___page; \ + }) + /* * Stub functions for when hotplug is off */ @@ -244,6 +283,10 @@ static inline void put_online_mems(void) {} static inline void mem_hotplug_begin(void) {} static inline void mem_hotplug_done(void) {} +static inline bool movable_node_is_enabled(void) +{ + return false; +} #endif /* ! CONFIG_MEMORY_HOTPLUG */ #ifdef CONFIG_MEMORY_HOTREMOVE @@ -274,18 +317,19 @@ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource, bool online); -extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default, - bool for_device); -extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device); +extern int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock); +extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); -extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn); +extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages, - enum zone_type target, int *zone_shift); - +extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, + int online_type); +extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, + unsigned long nr_pages); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5f4d8281832b..3a58b4be1b0c 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -142,11 +142,10 @@ bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); -extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new, - enum mpol_rebind_step step); +extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); -extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, +extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); @@ -260,8 +259,7 @@ static inline void numa_default_policy(void) } static inline void mpol_rebind_task(struct task_struct *tsk, - const nodemask_t *new, - enum mpol_rebind_step step) + const nodemask_t *new) { } @@ -269,13 +267,13 @@ static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } -static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, +static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; - return node_zonelist(0, gfp_flags); + return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 93416196ba64..79f8ba7c3894 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -4,6 +4,8 @@ #include <linux/ioport.h> #include <linux/percpu-refcount.h> +#include <asm/pgtable.h> + struct resource; struct device; @@ -35,24 +37,107 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) } #endif +/* + * Specialize ZONE_DEVICE memory into multiple types each having differents + * usage. + * + * MEMORY_DEVICE_HOST: + * Persistent device memory (pmem): struct page might be allocated in different + * memory and architecture might want to perform special actions. It is similar + * to regular memory, in that the CPU can access it transparently. However, + * it is likely to have different bandwidth and latency than regular memory. + * See Documentation/nvdimm/nvdimm.txt for more information. + * + * MEMORY_DEVICE_PRIVATE: + * Device memory that is not directly addressable by the CPU: CPU can neither + * read nor write private memory. In this case, we do still have struct pages + * backing the device memory. Doing so simplifies the implementation, but it is + * important to remember that there are certain points at which the struct page + * must be treated as an opaque object, rather than a "normal" struct page. + * + * A more complete discussion of unaddressable memory may be found in + * include/linux/hmm.h and Documentation/vm/hmm.txt. + * + * MEMORY_DEVICE_PUBLIC: + * Device memory that is cache coherent from device and CPU point of view. This + * is use on platform that have an advance system bus (like CAPI or CCIX). A + * driver can hotplug the device memory using ZONE_DEVICE and with that memory + * type. Any page of a process can be migrated to such memory. However no one + * should be allow to pin such memory so that it can always be evicted. + */ +enum memory_type { + MEMORY_DEVICE_HOST = 0, + MEMORY_DEVICE_PRIVATE, + MEMORY_DEVICE_PUBLIC, +}; + +/* + * For MEMORY_DEVICE_PRIVATE we use ZONE_DEVICE and extend it with two + * callbacks: + * page_fault() + * page_free() + * + * Additional notes about MEMORY_DEVICE_PRIVATE may be found in + * include/linux/hmm.h and Documentation/vm/hmm.txt. There is also a brief + * explanation in include/linux/memory_hotplug.h. + * + * The page_fault() callback must migrate page back, from device memory to + * system memory, so that the CPU can access it. This might fail for various + * reasons (device issues, device have been unplugged, ...). When such error + * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and + * set the CPU page table entry to "poisoned". + * + * Note that because memory cgroup charges are transferred to the device memory, + * this should never fail due to memory restrictions. However, allocation + * of a regular system page might still fail because we are out of memory. If + * that happens, the page_fault() callback must return VM_FAULT_OOM. + * + * The page_fault() callback can also try to migrate back multiple pages in one + * chunk, as an optimization. It must, however, prioritize the faulting address + * over all the others. + * + * + * The page_free() callback is called once the page refcount reaches 1 + * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. + * This allows the device driver to implement its own memory management.) + * + * For MEMORY_DEVICE_PUBLIC only the page_free() callback matter. + */ +typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, + unsigned long addr, + const struct page *page, + unsigned int flags, + pmd_t *pmdp); +typedef void (*dev_page_free_t)(struct page *page, void *data); + /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings + * @page_fault: callback when CPU fault on an unaddressable device page + * @page_free: free page callback when page refcount reaches 1 * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping * @dev: host device of the mapping for debug + * @data: private data pointer for page_free() + * @type: memory type: see MEMORY_* in memory_hotplug.h */ struct dev_pagemap { + dev_page_fault_t page_fault; + dev_page_free_t page_free; struct vmem_altmap *altmap; const struct resource *res; struct percpu_ref *ref; struct device *dev; + void *data; + enum memory_type type; }; #ifdef CONFIG_ZONE_DEVICE void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap); struct dev_pagemap *find_dev_pagemap(resource_size_t phys); + +static inline bool is_zone_device_page(const struct page *page); #else static inline void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, @@ -73,6 +158,20 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) } #endif +#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) +static inline bool is_device_private_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; +} + +static inline bool is_device_public_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PUBLIC; +} +#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ + /** * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn * @pfn: page frame number to lookup page_map diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index cde56cfe8446..e9c908c4fba8 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -23,6 +23,7 @@ enum axp20x_variants { AXP803_ID, AXP806_ID, AXP809_ID, + AXP813_ID, NR_AXP20X_VARIANTS, }; @@ -119,6 +120,17 @@ enum axp20x_variants { #define AXP806_BUS_ADDR_EXT 0xfe #define AXP806_REG_ADDR_EXT 0xff +#define AXP803_POLYPHASE_CTRL 0x14 +#define AXP803_FLDO1_V_OUT 0x1c +#define AXP803_FLDO2_V_OUT 0x1d +#define AXP803_DCDC1_V_OUT 0x20 +#define AXP803_DCDC2_V_OUT 0x21 +#define AXP803_DCDC3_V_OUT 0x22 +#define AXP803_DCDC4_V_OUT 0x23 +#define AXP803_DCDC5_V_OUT 0x24 +#define AXP803_DCDC6_V_OUT 0x25 +#define AXP803_DCDC_FREQ_CTRL 0x3b + /* Interrupt */ #define AXP152_IRQ1_EN 0x40 #define AXP152_IRQ2_EN 0x41 @@ -350,6 +362,60 @@ enum { AXP809_REG_ID_MAX, }; +enum { + AXP803_DCDC1 = 0, + AXP803_DCDC2, + AXP803_DCDC3, + AXP803_DCDC4, + AXP803_DCDC5, + AXP803_DCDC6, + AXP803_DC1SW, + AXP803_ALDO1, + AXP803_ALDO2, + AXP803_ALDO3, + AXP803_DLDO1, + AXP803_DLDO2, + AXP803_DLDO3, + AXP803_DLDO4, + AXP803_ELDO1, + AXP803_ELDO2, + AXP803_ELDO3, + AXP803_FLDO1, + AXP803_FLDO2, + AXP803_RTC_LDO, + AXP803_LDO_IO0, + AXP803_LDO_IO1, + AXP803_REG_ID_MAX, +}; + +enum { + AXP813_DCDC1 = 0, + AXP813_DCDC2, + AXP813_DCDC3, + AXP813_DCDC4, + AXP813_DCDC5, + AXP813_DCDC6, + AXP813_DCDC7, + AXP813_ALDO1, + AXP813_ALDO2, + AXP813_ALDO3, + AXP813_DLDO1, + AXP813_DLDO2, + AXP813_DLDO3, + AXP813_DLDO4, + AXP813_ELDO1, + AXP813_ELDO2, + AXP813_ELDO3, + AXP813_FLDO1, + AXP813_FLDO2, + AXP813_FLDO3, + AXP813_RTC_LDO, + AXP813_LDO_IO0, + AXP813_LDO_IO1, + AXP813_SW, + AXP813_REG_ID_MAX, +}; + /* IRQs */ enum { AXP152_IRQ_LDO0IN_CONNECT = 1, diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h new file mode 100644 index 000000000000..f0708ba4cbba --- /dev/null +++ b/include/linux/mfd/bd9571mwv.h @@ -0,0 +1,115 @@ +/* + * ROHM BD9571MWV-M driver + * + * Copyright (C) 2017 Marek Vasut <marek.vasut+renesas@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether expressed or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License version 2 for more details. + * + * Based on the TPS65086 driver + */ + +#ifndef __LINUX_MFD_BD9571MWV_H +#define __LINUX_MFD_BD9571MWV_H + +#include <linux/device.h> +#include <linux/regmap.h> + +/* List of registers for BD9571MWV */ +#define BD9571MWV_VENDOR_CODE 0x00 +#define BD9571MWV_VENDOR_CODE_VAL 0xdb +#define BD9571MWV_PRODUCT_CODE 0x01 +#define BD9571MWV_PRODUCT_CODE_VAL 0x60 +#define BD9571MWV_PRODUCT_REVISION 0x02 + +#define BD9571MWV_I2C_FUSA_MODE 0x10 +#define BD9571MWV_I2C_MD2_E1_BIT_1 0x11 +#define BD9571MWV_I2C_MD2_E1_BIT_2 0x12 + +#define BD9571MWV_BKUP_MODE_CNT 0x20 +#define BD9571MWV_BKUP_MODE_STATUS 0x21 +#define BD9571MWV_BKUP_RECOVERY_CNT 0x22 +#define BD9571MWV_BKUP_CTRL_TIM_CNT 0x23 +#define BD9571MWV_WAITBKUP_WDT_CNT 0x24 +#define BD9571MWV_128H_TIM_CNT 0x26 +#define BD9571MWV_QLLM_CNT 0x27 + +#define BD9571MWV_AVS_SET_MONI 0x31 +#define BD9571MWV_AVS_SET_MONI_MASK 0x3 +#define BD9571MWV_AVS_VD09_VID(n) (0x32 + (n)) +#define BD9571MWV_AVS_DVFS_VID(n) (0x36 + (n)) + +#define BD9571MWV_VD18_VID 0x42 +#define BD9571MWV_VD25_VID 0x43 +#define BD9571MWV_VD33_VID 0x44 + +#define BD9571MWV_DVFS_VINIT 0x50 +#define BD9571MWV_DVFS_SETVMAX 0x52 +#define BD9571MWV_DVFS_BOOSTVID 0x53 +#define BD9571MWV_DVFS_SETVID 0x54 +#define BD9571MWV_DVFS_MONIVDAC 0x55 +#define BD9571MWV_DVFS_PGD_CNT 0x56 + +#define BD9571MWV_GPIO_DIR 0x60 +#define BD9571MWV_GPIO_OUT 0x61 +#define BD9571MWV_GPIO_IN 0x62 +#define BD9571MWV_GPIO_DEB 0x63 +#define BD9571MWV_GPIO_INT_SET 0x64 +#define BD9571MWV_GPIO_INT 0x65 +#define BD9571MWV_GPIO_INTMASK 0x66 + +#define BD9571MWV_REG_KEEP(n) (0x70 + (n)) + +#define BD9571MWV_PMIC_INTERNAL_STATUS 0x80 +#define BD9571MWV_PROT_ERROR_STATUS0 0x81 +#define BD9571MWV_PROT_ERROR_STATUS1 0x82 +#define BD9571MWV_PROT_ERROR_STATUS2 0x83 +#define BD9571MWV_PROT_ERROR_STATUS3 0x84 +#define BD9571MWV_PROT_ERROR_STATUS4 0x85 + +#define BD9571MWV_INT_INTREQ 0x90 +#define BD9571MWV_INT_INTREQ_MD1_INT BIT(0) +#define BD9571MWV_INT_INTREQ_MD2_E1_INT BIT(1) +#define BD9571MWV_INT_INTREQ_MD2_E2_INT BIT(2) +#define BD9571MWV_INT_INTREQ_PROT_ERR_INT BIT(3) +#define BD9571MWV_INT_INTREQ_GP_INT BIT(4) +#define BD9571MWV_INT_INTREQ_128H_OF_INT BIT(5) +#define BD9571MWV_INT_INTREQ_WDT_OF_INT BIT(6) +#define BD9571MWV_INT_INTREQ_BKUP_TRG_INT BIT(7) +#define BD9571MWV_INT_INTMASK 0x91 + +#define BD9571MWV_ACCESS_KEY 0xff + +/* Define the BD9571MWV IRQ numbers */ +enum bd9571mwv_irqs { + BD9571MWV_IRQ_MD1, + BD9571MWV_IRQ_MD2_E1, + BD9571MWV_IRQ_MD2_E2, + BD9571MWV_IRQ_PROT_ERR, + BD9571MWV_IRQ_GP, + BD9571MWV_IRQ_128H_OF, + BD9571MWV_IRQ_WDT_OF, + BD9571MWV_IRQ_BKUP_TRG, +}; + +/** + * struct bd9571mwv - state holder for the bd9571mwv driver + * + * Device data may be used to access the BD9571MWV chip + */ +struct bd9571mwv { + struct device *dev; + struct regmap *regmap; + + /* IRQ Data */ + int irq; + struct regmap_irq_chip_data *irq_data; +}; + +#endif /* __LINUX_MFD_BD9571MWV_H */ diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 28baee63eaf6..4e887ba22635 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -149,6 +149,7 @@ struct cros_ec_device { struct ec_response_get_next_event event_data; int event_size; + u32 host_event_wake_mask; }; /** @@ -172,6 +173,8 @@ struct cros_ec_platform { u16 cmd_offset; }; +struct cros_ec_debugfs; + /* * struct cros_ec_dev - ChromeOS EC device entry point * @@ -179,6 +182,7 @@ struct cros_ec_platform { * @cdev: Character device structure in /dev * @ec_dev: cros_ec_device structure to talk to the physical device * @dev: pointer to the platform device + * @debug_info: cros_ec_debugfs structure for debugging information * @cmd_offset: offset to apply for each command. */ struct cros_ec_dev { @@ -186,6 +190,7 @@ struct cros_ec_dev { struct cdev cdev; struct cros_ec_device *ec_dev; struct device *dev; + struct cros_ec_debugfs *debug_info; u16 cmd_offset; u32 features[2]; }; @@ -295,10 +300,22 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev); * cros_ec_get_next_event - Fetch next event from the ChromeOS EC * * @ec_dev: Device to fetch event from + * @wake_event: Pointer to a bool set to true upon return if the event might be + * treated as a wake event. Ignored if null. * * Returns: 0 on success, Linux error number on failure */ -int cros_ec_get_next_event(struct cros_ec_device *ec_dev); +int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); + +/** + * cros_ec_get_host_event - Return a mask of event set by the EC. + * + * When MKBP is supported, when the EC raises an interrupt, + * We collect the events raised and call the functions in the ec notifier. + * + * This function is a helper to know which events are raised. + */ +u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); /* sysfs stuff */ extern struct attribute_group cros_ec_attr_group; diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index c93e7e0300ef..2b16e95b9bb8 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -285,6 +285,11 @@ enum host_event_code { EC_HOST_EVENT_HANG_DETECT = 20, /* Hang detect logic detected a hang and warm rebooted the AP */ EC_HOST_EVENT_HANG_REBOOT = 21, + /* PD MCU triggering host event */ + EC_HOST_EVENT_PD_MCU = 22, + + /* EC desires to change state of host-controlled USB mux */ + EC_HOST_EVENT_USB_MUX = 28, /* * The high bit of the event mask is not used as a host event code. If @@ -625,6 +630,10 @@ struct ec_params_get_cmd_versions { uint8_t cmd; /* Command to check */ } __packed; +struct ec_params_get_cmd_versions_v1 { + uint16_t cmd; /* Command to check */ +} __packed; + struct ec_response_get_cmd_versions { /* * Mask of supported versions; use EC_VER_MASK() to compare with a @@ -1158,13 +1167,20 @@ struct lightbar_params_v1 { struct rgb_s color[8]; /* 0-3 are Google colors */ } __packed; +/* Lightbar program */ +#define EC_LB_PROG_LEN 192 +struct lightbar_program { + uint8_t size; + uint8_t data[EC_LB_PROG_LEN]; +}; + struct ec_params_lightbar { uint8_t cmd; /* Command (see enum lightbar_command) */ union { struct { /* no args */ } dump, off, on, init, get_seq, get_params_v0, get_params_v1, - version, get_brightness, get_demo; + version, get_brightness, get_demo, suspend, resume; struct { uint8_t num; @@ -1182,8 +1198,13 @@ struct ec_params_lightbar { uint8_t led; } get_rgb; + struct { + uint8_t enable; + } manual_suspend_ctrl; + struct lightbar_params_v0 set_params_v0; struct lightbar_params_v1 set_params_v1; + struct lightbar_program set_program; }; } __packed; @@ -1216,7 +1237,8 @@ struct ec_response_lightbar { struct { /* no return params */ } off, on, init, set_brightness, seq, reg, set_rgb, - demo, set_params_v0, set_params_v1; + demo, set_params_v0, set_params_v1, + set_program, manual_suspend_ctrl, suspend, resume; }; } __packed; @@ -1240,6 +1262,10 @@ enum lightbar_command { LIGHTBAR_CMD_GET_DEMO = 15, LIGHTBAR_CMD_GET_PARAMS_V1 = 16, LIGHTBAR_CMD_SET_PARAMS_V1 = 17, + LIGHTBAR_CMD_SET_PROGRAM = 18, + LIGHTBAR_CMD_MANUAL_SUSPEND_CTRL = 19, + LIGHTBAR_CMD_SUSPEND = 20, + LIGHTBAR_CMD_RESUME = 21, LIGHTBAR_NUM_CMDS }; @@ -2285,13 +2311,28 @@ struct ec_params_charge_control { #define EC_CMD_CONSOLE_SNAPSHOT 0x97 /* - * Read next chunk of data from saved snapshot. + * Read data from the saved snapshot. If the subcmd parameter is + * CONSOLE_READ_NEXT, this will return data starting from the beginning of + * the latest snapshot. If it is CONSOLE_READ_RECENT, it will start from the + * end of the previous snapshot. + * + * The params are only looked at in version >= 1 of this command. Prior + * versions will just default to CONSOLE_READ_NEXT behavior. * * Response is null-terminated string. Empty string, if there is no more * remaining output. */ #define EC_CMD_CONSOLE_READ 0x98 +enum ec_console_read_subcmd { + CONSOLE_READ_NEXT = 0, + CONSOLE_READ_RECENT +}; + +struct ec_params_console_read_v1 { + uint8_t subcmd; /* enum ec_console_read_subcmd */ +} __packed; + /*****************************************************************************/ /* @@ -2869,6 +2910,76 @@ struct ec_params_usb_pd_control { uint8_t mux; } __packed; +#define PD_CTRL_RESP_ENABLED_COMMS (1 << 0) /* Communication enabled */ +#define PD_CTRL_RESP_ENABLED_CONNECTED (1 << 1) /* Device connected */ +#define PD_CTRL_RESP_ENABLED_PD_CAPABLE (1 << 2) /* Partner is PD capable */ + +struct ec_response_usb_pd_control_v1 { + uint8_t enabled; + uint8_t role; + uint8_t polarity; + char state[32]; +} __packed; + +#define EC_CMD_USB_PD_PORTS 0x102 + +struct ec_response_usb_pd_ports { + uint8_t num_ports; +} __packed; + +#define EC_CMD_USB_PD_POWER_INFO 0x103 + +#define PD_POWER_CHARGING_PORT 0xff +struct ec_params_usb_pd_power_info { + uint8_t port; +} __packed; + +enum usb_chg_type { + USB_CHG_TYPE_NONE, + USB_CHG_TYPE_PD, + USB_CHG_TYPE_C, + USB_CHG_TYPE_PROPRIETARY, + USB_CHG_TYPE_BC12_DCP, + USB_CHG_TYPE_BC12_CDP, + USB_CHG_TYPE_BC12_SDP, + USB_CHG_TYPE_OTHER, + USB_CHG_TYPE_VBUS, + USB_CHG_TYPE_UNKNOWN, +}; + +struct usb_chg_measures { + uint16_t voltage_max; + uint16_t voltage_now; + uint16_t current_max; + uint16_t current_lim; +} __packed; + +struct ec_response_usb_pd_power_info { + uint8_t role; + uint8_t type; + uint8_t dualrole; + uint8_t reserved1; + struct usb_chg_measures meas; + uint32_t max_power; +} __packed; + +/* Get info about USB-C SS muxes */ +#define EC_CMD_USB_PD_MUX_INFO 0x11a + +struct ec_params_usb_pd_mux_info { + uint8_t port; /* USB-C port number */ +} __packed; + +/* Flags representing mux state */ +#define USB_PD_MUX_USB_ENABLED (1 << 0) +#define USB_PD_MUX_DP_ENABLED (1 << 1) +#define USB_PD_MUX_POLARITY_INVERTED (1 << 2) +#define USB_PD_MUX_HPD_IRQ (1 << 3) + +struct ec_response_usb_pd_mux_info { + uint8_t flags; /* USB_PD_MUX_*-encoded USB mux state */ +} __packed; + /*****************************************************************************/ /* * Passthru commands diff --git a/include/linux/mfd/cros_ec_lpc_mec.h b/include/linux/mfd/cros_ec_lpc_mec.h new file mode 100644 index 000000000000..176496ddc66c --- /dev/null +++ b/include/linux/mfd/cros_ec_lpc_mec.h @@ -0,0 +1,90 @@ +/* + * cros_ec_lpc_mec - LPC variant I/O for Microchip EC + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __LINUX_MFD_CROS_EC_MEC_H +#define __LINUX_MFD_CROS_EC_MEC_H + +#include <linux/mfd/cros_ec_commands.h> + +enum cros_ec_lpc_mec_emi_access_mode { + /* 8-bit access */ + ACCESS_TYPE_BYTE = 0x0, + /* 16-bit access */ + ACCESS_TYPE_WORD = 0x1, + /* 32-bit access */ + ACCESS_TYPE_LONG = 0x2, + /* + * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the + * EC data register to be incremented. + */ + ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3, +}; + +enum cros_ec_lpc_mec_io_type { + MEC_IO_READ, + MEC_IO_WRITE, +}; + +/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */ +#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0 +#define MEC_EMI_RANGE_END (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE) + +/* EMI registers are relative to base */ +#define MEC_EMI_BASE 0x800 +#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0) +#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1) +#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2) +#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3) +#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4) +#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5) +#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6) +#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7) + +/* + * cros_ec_lpc_mec_init + * + * Initialize MEC I/O. + */ +void cros_ec_lpc_mec_init(void); + +/* + * cros_ec_lpc_mec_destroy + * + * Cleanup MEC I/O. + */ +void cros_ec_lpc_mec_destroy(void); + +/** + * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port + * + * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request + * @offset: Base read / write address + * @length: Number of bytes to read / write + * @buf: Destination / source buffer + * + * @return 8-bit checksum of all bytes read / written + */ +u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type, + unsigned int offset, unsigned int length, u8 *buf); + +#endif /* __LINUX_MFD_CROS_EC_MEC_H */ diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h new file mode 100644 index 000000000000..5560bef63c2b --- /dev/null +++ b/include/linux/mfd/cros_ec_lpc_reg.h @@ -0,0 +1,61 @@ +/* + * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __LINUX_MFD_CROS_EC_REG_H +#define __LINUX_MFD_CROS_EC_REG_H + +/** + * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address. + * Returns 8-bit checksum of all bytes read. + * + * @offset: Base read address + * @length: Number of bytes to read + * @dest: Destination buffer + */ +u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest); + +/** + * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address. + * Returns 8-bit checksum of all bytes written. + * + * @offset: Base write address + * @length: Number of bytes to write + * @msg: Write data buffer + */ +u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg); + +/** + * cros_ec_lpc_reg_init + * + * Initialize register I/O. + */ +void cros_ec_lpc_reg_init(void); + +/** + * cros_ec_lpc_reg_destroy + * + * Cleanup reg I/O. + */ +void cros_ec_lpc_reg_destroy(void); + +#endif /* __LINUX_MFD_CROS_EC_REG_H */ diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h index ce9230af09c2..ae5b663836d0 100644 --- a/include/linux/mfd/da9052/da9052.h +++ b/include/linux/mfd/da9052/da9052.h @@ -45,6 +45,12 @@ #define DA9052_ADC_TJUNC 8 #define DA9052_ADC_VBBAT 9 +/* TSI channel has its own 4 channel mux */ +#define DA9052_ADC_TSI_XP 70 +#define DA9052_ADC_TSI_XN 71 +#define DA9052_ADC_TSI_YP 72 +#define DA9052_ADC_TSI_YN 73 + #define DA9052_IRQ_DCIN 0 #define DA9052_IRQ_VBUS 1 #define DA9052_IRQ_DCINREM 2 diff --git a/include/linux/mfd/da9052/reg.h b/include/linux/mfd/da9052/reg.h index 5010f978725c..76780ea8849c 100644 --- a/include/linux/mfd/da9052/reg.h +++ b/include/linux/mfd/da9052/reg.h @@ -690,7 +690,10 @@ /* TSI CONTROL REGISTER B BITS */ #define DA9052_TSICONTB_ADCREF 0X80 #define DA9052_TSICONTB_TSIMAN 0X40 -#define DA9052_TSICONTB_TSIMUX 0X30 +#define DA9052_TSICONTB_TSIMUX_XP 0X00 +#define DA9052_TSICONTB_TSIMUX_YP 0X10 +#define DA9052_TSICONTB_TSIMUX_XN 0X20 +#define DA9052_TSICONTB_TSIMUX_YN 0X30 #define DA9052_TSICONTB_TSISEL3 0X08 #define DA9052_TSICONTB_TSISEL2 0X04 #define DA9052_TSICONTB_TSISEL1 0X02 @@ -705,8 +708,14 @@ /* TSI CO-ORDINATE LSB RESULT REGISTER BITS */ #define DA9052_TSILSB_PENDOWN 0X40 #define DA9052_TSILSB_TSIZL 0X30 +#define DA9052_TSILSB_TSIZL_SHIFT 4 +#define DA9052_TSILSB_TSIZL_BITS 2 #define DA9052_TSILSB_TSIYL 0X0C +#define DA9052_TSILSB_TSIYL_SHIFT 2 +#define DA9052_TSILSB_TSIYL_BITS 2 #define DA9052_TSILSB_TSIXL 0X03 +#define DA9052_TSILSB_TSIXL_SHIFT 0 +#define DA9052_TSILSB_TSIXL_BITS 2 /* TSI Z MEASUREMENT MSB RESULT REGISTER BIT */ #define DA9052_TSIZMSB_TSIZM 0XFF diff --git a/include/linux/i2c/dm355evm_msp.h b/include/linux/mfd/dm355evm_msp.h index 372470350fab..372470350fab 100644 --- a/include/linux/i2c/dm355evm_msp.h +++ b/include/linux/mfd/dm355evm_msp.h diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h index 38a372a0e285..2227c6a75d84 100644 --- a/include/linux/mfd/ds1wm.h +++ b/include/linux/mfd/ds1wm.h @@ -1,13 +1,28 @@ -/* MFD cell driver data for the DS1WM driver */ +/* MFD cell driver data for the DS1WM driver + * + * to be defined in the MFD device that is + * using this driver for one of his sub devices + */ struct ds1wm_driver_data { int active_high; int clock_rate; - /* in milliseconds, the amount of time to */ - /* sleep following a reset pulse. Zero */ - /* should work if your bus devices recover*/ - /* time respects the 1-wire spec since the*/ - /* ds1wm implements the precise timings of*/ - /* a reset pulse/presence detect sequence.*/ + /* in milliseconds, the amount of time to + * sleep following a reset pulse. Zero + * should work if your bus devices recover + * time respects the 1-wire spec since the + * ds1wm implements the precise timings of + * a reset pulse/presence detect sequence. + */ unsigned int reset_recover_delay; + + /* Say 1 here for big endian Hardware + * (only relevant with bus-shift > 0 + */ + bool is_hw_big_endian; + + /* left shift of register number to get register address offsett. + * Only 0,1,2 allowed for 8,16 or 32 bit bus width respectively + */ + unsigned int bus_shift; }; diff --git a/include/linux/mfd/hi6421-pmic.h b/include/linux/mfd/hi6421-pmic.h index 587273e35acf..2580c08db7b1 100644 --- a/include/linux/mfd/hi6421-pmic.h +++ b/include/linux/mfd/hi6421-pmic.h @@ -38,4 +38,9 @@ struct hi6421_pmic { struct regmap *regmap; }; +enum hi6421_type { + HI6421 = 0, + HI6421_V530, +}; + #endif /* __HI6421_PMIC_H */ diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 956caa0628f5..5aacdb017a9f 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -25,8 +25,11 @@ struct intel_soc_pmic { int irq; struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; - struct regmap_irq_chip_data *irq_chip_data_level2; struct regmap_irq_chip_data *irq_chip_data_tmu; + struct regmap_irq_chip_data *irq_chip_data_bcu; + struct regmap_irq_chip_data *irq_chip_data_adc; + struct regmap_irq_chip_data *irq_chip_data_chgr; + struct regmap_irq_chip_data *irq_chip_data_crit; struct device *dev; }; diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h new file mode 100644 index 000000000000..d0c91ba65525 --- /dev/null +++ b/include/linux/mfd/lp87565.h @@ -0,0 +1,270 @@ +/* + * Functions to access LP87565 power management chip. + * + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + */ + +#ifndef __LINUX_MFD_LP87565_H +#define __LINUX_MFD_LP87565_H + +#include <linux/i2c.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> + +enum lp87565_device_type { + LP87565_DEVICE_TYPE_UNKNOWN = 0, + LP87565_DEVICE_TYPE_LP87565_Q1, +}; + +/* All register addresses */ +#define LP87565_REG_DEV_REV 0X00 +#define LP87565_REG_OTP_REV 0X01 +#define LP87565_REG_BUCK0_CTRL_1 0X02 +#define LP87565_REG_BUCK0_CTRL_2 0X03 + +#define LP87565_REG_BUCK1_CTRL_1 0X04 +#define LP87565_REG_BUCK1_CTRL_2 0X05 + +#define LP87565_REG_BUCK2_CTRL_1 0X06 +#define LP87565_REG_BUCK2_CTRL_2 0X07 + +#define LP87565_REG_BUCK3_CTRL_1 0X08 +#define LP87565_REG_BUCK3_CTRL_2 0X09 + +#define LP87565_REG_BUCK0_VOUT 0X0A +#define LP87565_REG_BUCK0_FLOOR_VOUT 0X0B + +#define LP87565_REG_BUCK1_VOUT 0X0C +#define LP87565_REG_BUCK1_FLOOR_VOUT 0X0D + +#define LP87565_REG_BUCK2_VOUT 0X0E +#define LP87565_REG_BUCK2_FLOOR_VOUT 0X0F + +#define LP87565_REG_BUCK3_VOUT 0X10 +#define LP87565_REG_BUCK3_FLOOR_VOUT 0X11 + +#define LP87565_REG_BUCK0_DELAY 0X12 +#define LP87565_REG_BUCK1_DELAY 0X13 + +#define LP87565_REG_BUCK2_DELAY 0X14 +#define LP87565_REG_BUCK3_DELAY 0X15 + +#define LP87565_REG_GPO2_DELAY 0X16 +#define LP87565_REG_GPO3_DELAY 0X17 +#define LP87565_REG_RESET 0X18 +#define LP87565_REG_CONFIG 0X19 + +#define LP87565_REG_INT_TOP_1 0X1A +#define LP87565_REG_INT_TOP_2 0X1B + +#define LP87565_REG_INT_BUCK_0_1 0X1C +#define LP87565_REG_INT_BUCK_2_3 0X1D +#define LP87565_REG_TOP_STAT 0X1E +#define LP87565_REG_BUCK_0_1_STAT 0X1F +#define LP87565_REG_BUCK_2_3_STAT 0x20 + +#define LP87565_REG_TOP_MASK_1 0x21 +#define LP87565_REG_TOP_MASK_2 0x22 + +#define LP87565_REG_BUCK_0_1_MASK 0x23 +#define LP87565_REG_BUCK_2_3_MASK 0x24 +#define LP87565_REG_SEL_I_LOAD 0x25 + +#define LP87565_REG_I_LOAD_2 0x26 +#define LP87565_REG_I_LOAD_1 0x27 + +#define LP87565_REG_PGOOD_CTRL1 0x28 +#define LP87565_REG_PGOOD_CTRL2 0x29 +#define LP87565_REG_PGOOD_FLT 0x2A +#define LP87565_REG_PLL_CTRL 0x2B +#define LP87565_REG_PIN_FUNCTION 0x2C +#define LP87565_REG_GPIO_CONFIG 0x2D +#define LP87565_REG_GPIO_IN 0x2E +#define LP87565_REG_GPIO_OUT 0x2F + +#define LP87565_REG_MAX LP87565_REG_GPIO_OUT + +/* Register field definitions */ +#define LP87565_DEV_REV_DEV_ID 0xC0 +#define LP87565_DEV_REV_ALL_LAYER 0x30 +#define LP87565_DEV_REV_METAL_LAYER 0x0F + +#define LP87565_OTP_REV_OTP_ID 0xFF + +#define LP87565_BUCK_CTRL_1_EN BIT(7) +#define LP87565_BUCK_CTRL_1_EN_PIN_CTRL BIT(6) +#define LP87565_BUCK_CTRL_1_PIN_SELECT_EN 0x30 + +#define LP87565_BUCK_CTRL_1_ROOF_FLOOR_EN BIT(3) +#define LP87565_BUCK_CTRL_1_RDIS_EN BIT(2) +#define LP87565_BUCK_CTRL_1_FPWM BIT(1) +/* Bit0 is reserved for BUCK1 and BUCK3 and valid only for BUCK0 and BUCK2 */ +#define LP87565_BUCK_CTRL_1_FPWM_MP_0_2 BIT(0) + +#define LP87565_BUCK_CTRL_2_ILIM 0x38 +#define LP87565_BUCK_CTRL_2_SLEW_RATE 0x07 + +#define LP87565_BUCK_VSET 0xFF +#define LP87565_BUCK_FLOOR_VSET 0xFF + +#define LP87565_BUCK_SHUTDOWN_DELAY 0xF0 +#define LP87565_BUCK_STARTUP_DELAY 0x0F + +#define LP87565_GPIO_SHUTDOWN_DELAY 0xF0 +#define LP87565_GPIO_STARTUP_DELAY 0x0F + +#define LP87565_RESET_SW_RESET BIT(0) + +#define LP87565_CONFIG_DOUBLE_DELAY BIT(7) +#define LP87565_CONFIG_CLKIN_PD BIT(6) +#define LP87565_CONFIG_EN4_PD BIT(5) +#define LP87565_CONFIG_EN3_PD BIT(4) +#define LP87565_CONFIG_TDIE_WARN_LEVEL BIT(3) +#define LP87565_CONFIG_EN2_PD BIT(2) +#define LP87565_CONFIG_EN1_PD BIT(1) + +#define LP87565_INT_GPIO BIT(7) +#define LP87565_INT_BUCK23 BIT(6) +#define LP87565_INT_BUCK01 BIT(5) +#define LP87565_NO_SYNC_CLK BIT(4) +#define LP87565_TDIE_SD BIT(3) +#define LP87565_TDIE_WARN BIT(2) +#define LP87565_INT_OVP BIT(1) +#define LP87565_I_LOAD_READY BIT(0) + +#define LP87565_INT_TOP2_RESET_REG BIT(0) + +#define LP87565_BUCK1_PG_INT BIT(6) +#define LP87565_BUCK1_SC_INT BIT(5) +#define LP87565_BUCK1_ILIM_INT BIT(4) +#define LP87565_BUCK0_PG_INT BIT(2) +#define LP87565_BUCK0_SC_INT BIT(1) +#define LP87565_BUCK0_ILIM_INT BIT(0) + +#define LP87565_BUCK3_PG_INT BIT(6) +#define LP87565_BUCK3_SC_INT BIT(5) +#define LP87565_BUCK3_ILIM_INT BIT(4) +#define LP87565_BUCK2_PG_INT BIT(2) +#define LP87565_BUCK2_SC_INT BIT(1) +#define LP87565_BUCK2_ILIM_INT BIT(0) + +#define LP87565_SYNC_CLK_STAT BIT(4) +#define LP87565_TDIE_SD_STAT BIT(3) +#define LP87565_TDIE_WARN_STAT BIT(2) +#define LP87565_OVP_STAT BIT(1) + +#define LP87565_BUCK1_STAT BIT(7) +#define LP87565_BUCK1_PG_STAT BIT(6) +#define LP87565_BUCK1_ILIM_STAT BIT(4) +#define LP87565_BUCK0_STAT BIT(3) +#define LP87565_BUCK0_PG_STAT BIT(2) +#define LP87565_BUCK0_ILIM_STAT BIT(0) + +#define LP87565_BUCK3_STAT BIT(7) +#define LP87565_BUCK3_PG_STAT BIT(6) +#define LP87565_BUCK3_ILIM_STAT BIT(4) +#define LP87565_BUCK2_STAT BIT(3) +#define LP87565_BUCK2_PG_STAT BIT(2) +#define LP87565_BUCK2_ILIM_STAT BIT(0) + +#define LPL87565_GPIO_MASK BIT(7) +#define LPL87565_SYNC_CLK_MASK BIT(4) +#define LPL87565_TDIE_WARN_MASK BIT(2) +#define LPL87565_I_LOAD_READY_MASK BIT(0) + +#define LPL87565_RESET_REG_MASK BIT(0) + +#define LPL87565_BUCK1_PG_MASK BIT(6) +#define LPL87565_BUCK1_ILIM_MASK BIT(4) +#define LPL87565_BUCK0_PG_MASK BIT(2) +#define LPL87565_BUCK0_ILIM_MASK BIT(0) + +#define LPL87565_BUCK3_PG_MASK BIT(6) +#define LPL87565_BUCK3_ILIM_MASK BIT(4) +#define LPL87565_BUCK2_PG_MASK BIT(2) +#define LPL87565_BUCK2_ILIM_MASK BIT(0) + +#define LP87565_LOAD_CURRENT_BUCK_SELECT 0x3 + +#define LP87565_I_LOAD2_BUCK_LOAD_CURRENT 0x3 +#define LP87565_I_LOAD1_BUCK_LOAD_CURRENT 0xFF + +#define LP87565_PG3_SEL 0xC0 +#define LP87565_PG2_SEL 0x30 +#define LP87565_PG1_SEL 0x0C +#define LP87565_PG0_SEL 0x03 + +#define LP87565_HALF_DAY BIT(7) +#define LP87565_EN_PG0_NINT BIT(6) +#define LP87565_PGOOD_SET_DELAY BIT(5) +#define LP87565_EN_PGFLT_STAT BIT(4) +#define LP87565_PGOOD_WINDOW BIT(2) +#define LP87565_PGOOD_OD BIT(1) +#define LP87565_PGOOD_POL BIT(0) + +#define LP87565_PG3_FLT BIT(3) +#define LP87565_PG2_FLT BIT(2) +#define LP87565_PG1_FLT BIT(1) +#define LP87565_PG0_FLT BIT(0) + +#define LP87565_PLL_MODE 0xC0 +#define LP87565_EXT_CLK_FREQ 0x1F + +#define LP87565_EN_SPREAD_SPEC BIT(7) +#define LP87565_EN_PIN_CTRL_GPIO3 BIT(6) +#define LP87565_EN_PIN_SELECT_GPIO3 BIT(5) +#define LP87565_EN_PIN_CTRL_GPIO2 BIT(4) +#define LP87565_EN_PIN_SELECT_GPIO2 BIT(3) +#define LP87565_GPIO3_SEL BIT(2) +#define LP87565_GPIO2_SEL BIT(1) +#define LP87565_GPIO1_SEL BIT(0) + +#define LP87565_GOIO3_OD BIT(6) +#define LP87565_GOIO2_OD BIT(5) +#define LP87565_GOIO1_OD BIT(4) +#define LP87565_GOIO3_DIR BIT(2) +#define LP87565_GOIO2_DIR BIT(1) +#define LP87565_GOIO1_DIR BIT(0) + +#define LP87565_GOIO3_IN BIT(2) +#define LP87565_GOIO2_IN BIT(1) +#define LP87565_GOIO1_IN BIT(0) + +#define LP87565_GOIO3_OUT BIT(2) +#define LP87565_GOIO2_OUT BIT(1) +#define LP87565_GOIO1_OUT BIT(0) + +/* Number of step-down converters available */ +#define LP87565_NUM_BUCK 6 + +enum LP87565_regulator_id { + /* BUCK's */ + LP87565_BUCK_0, + LP87565_BUCK_1, + LP87565_BUCK_2, + LP87565_BUCK_3, + LP87565_BUCK_10, + LP87565_BUCK_23, +}; + +/** + * struct LP87565 - state holder for the LP87565 driver + * @dev: struct device pointer for MFD device + * @rev: revision of the LP87565 + * @dev_type: The device type for example lp87565-q1 + * @lock: lock guarding the data structure + * @regmap: register map of the LP87565 PMIC + * + * Device data may be used to access the LP87565 chip + */ +struct lp87565 { + struct device *dev; + u8 rev; + u8 dev_type; + struct regmap *regmap; +}; +#endif /* __LINUX_MFD_LP87565_H */ diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 5c9a1d44c125..6dec43826303 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -250,6 +250,7 @@ enum tps65917_regulators { TPS65917_REG_SMPS3, TPS65917_REG_SMPS4, TPS65917_REG_SMPS5, + TPS65917_REG_SMPS12, /* LDO regulators */ TPS65917_REG_LDO1, TPS65917_REG_LDO2, @@ -317,6 +318,7 @@ enum tps65917_external_requestor_id { TPS65917_EXTERNAL_REQSTR_ID_SMPS3, TPS65917_EXTERNAL_REQSTR_ID_SMPS4, TPS65917_EXTERNAL_REQSTR_ID_SMPS5, + TPS65917_EXTERNAL_REQSTR_ID_SMPS12, TPS65917_EXTERNAL_REQSTR_ID_LDO1, TPS65917_EXTERNAL_REQSTR_ID_LDO2, TPS65917_EXTERNAL_REQSTR_ID_LDO3, diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 83701ef7d3c7..d3156594674c 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -206,6 +206,97 @@ enum rk818_reg { #define RK818_USB_ILMIN_2000MA 0x7 #define RK818_USB_CHG_SD_VSEL_MASK 0x70 +/* RK805 */ +enum rk805_reg { + RK805_ID_DCDC1, + RK805_ID_DCDC2, + RK805_ID_DCDC3, + RK805_ID_DCDC4, + RK805_ID_LDO1, + RK805_ID_LDO2, + RK805_ID_LDO3, +}; + +/* CONFIG REGISTER */ +#define RK805_VB_MON_REG 0x21 +#define RK805_THERMAL_REG 0x22 + +/* POWER CHANNELS ENABLE REGISTER */ +#define RK805_DCDC_EN_REG 0x23 +#define RK805_SLP_DCDC_EN_REG 0x25 +#define RK805_SLP_LDO_EN_REG 0x26 +#define RK805_LDO_EN_REG 0x27 + +/* BUCK AND LDO CONFIG REGISTER */ +#define RK805_BUCK_LDO_SLP_LP_EN_REG 0x2A +#define RK805_BUCK1_CONFIG_REG 0x2E +#define RK805_BUCK1_ON_VSEL_REG 0x2F +#define RK805_BUCK1_SLP_VSEL_REG 0x30 +#define RK805_BUCK2_CONFIG_REG 0x32 +#define RK805_BUCK2_ON_VSEL_REG 0x33 +#define RK805_BUCK2_SLP_VSEL_REG 0x34 +#define RK805_BUCK3_CONFIG_REG 0x36 +#define RK805_BUCK4_CONFIG_REG 0x37 +#define RK805_BUCK4_ON_VSEL_REG 0x38 +#define RK805_BUCK4_SLP_VSEL_REG 0x39 +#define RK805_LDO1_ON_VSEL_REG 0x3B +#define RK805_LDO1_SLP_VSEL_REG 0x3C +#define RK805_LDO2_ON_VSEL_REG 0x3D +#define RK805_LDO2_SLP_VSEL_REG 0x3E +#define RK805_LDO3_ON_VSEL_REG 0x3F +#define RK805_LDO3_SLP_VSEL_REG 0x40 + +/* INTERRUPT REGISTER */ +#define RK805_PWRON_LP_INT_TIME_REG 0x47 +#define RK805_PWRON_DB_REG 0x48 +#define RK805_DEV_CTRL_REG 0x4B +#define RK805_INT_STS_REG 0x4C +#define RK805_INT_STS_MSK_REG 0x4D +#define RK805_GPIO_IO_POL_REG 0x50 +#define RK805_OUT_REG 0x52 +#define RK805_ON_SOURCE_REG 0xAE +#define RK805_OFF_SOURCE_REG 0xAF + +#define RK805_NUM_REGULATORS 7 + +#define RK805_PWRON_FALL_RISE_INT_EN 0x0 +#define RK805_PWRON_FALL_RISE_INT_MSK 0x81 + +/* RK805 IRQ Definitions */ +#define RK805_IRQ_PWRON_RISE 0 +#define RK805_IRQ_VB_LOW 1 +#define RK805_IRQ_PWRON 2 +#define RK805_IRQ_PWRON_LP 3 +#define RK805_IRQ_HOTDIE 4 +#define RK805_IRQ_RTC_ALARM 5 +#define RK805_IRQ_RTC_PERIOD 6 +#define RK805_IRQ_PWRON_FALL 7 + +#define RK805_IRQ_PWRON_RISE_MSK BIT(0) +#define RK805_IRQ_VB_LOW_MSK BIT(1) +#define RK805_IRQ_PWRON_MSK BIT(2) +#define RK805_IRQ_PWRON_LP_MSK BIT(3) +#define RK805_IRQ_HOTDIE_MSK BIT(4) +#define RK805_IRQ_RTC_ALARM_MSK BIT(5) +#define RK805_IRQ_RTC_PERIOD_MSK BIT(6) +#define RK805_IRQ_PWRON_FALL_MSK BIT(7) + +#define RK805_PWR_RISE_INT_STATUS BIT(0) +#define RK805_VB_LOW_INT_STATUS BIT(1) +#define RK805_PWRON_INT_STATUS BIT(2) +#define RK805_PWRON_LP_INT_STATUS BIT(3) +#define RK805_HOTDIE_INT_STATUS BIT(4) +#define RK805_ALARM_INT_STATUS BIT(5) +#define RK805_PERIOD_INT_STATUS BIT(6) +#define RK805_PWR_FALL_INT_STATUS BIT(7) + +#define RK805_BUCK1_2_ILMAX_MASK (3 << 6) +#define RK805_BUCK3_4_ILMAX_MASK (3 << 3) +#define RK805_RTC_PERIOD_INT_MASK (1 << 6) +#define RK805_RTC_ALARM_INT_MASK (1 << 5) +#define RK805_INT_ALARM_EN (1 << 3) +#define RK805_INT_TIMER_EN (1 << 2) + /* RK808 IRQ Definitions */ #define RK808_IRQ_VOUT_LO 0 #define RK808_IRQ_VB_LO 1 @@ -298,6 +389,14 @@ enum rk818_reg { #define VOUT_LO_INT BIT(0) #define CLK32KOUT2_EN BIT(0) +#define TEMP115C 0x0c +#define TEMP_HOTDIE_MSK 0x0c +#define SLP_SD_MSK (0x3 << 2) +#define SHUTDOWN_FUN (0x2 << 2) +#define SLEEP_FUN (0x1 << 2) +#define RK8XX_ID_MSK 0xfff0 +#define FPWM_MODE BIT(7) + enum { BUCK_ILMIN_50MA, BUCK_ILMIN_100MA, @@ -321,6 +420,28 @@ enum { }; enum { + RK805_BUCK1_2_ILMAX_2500MA, + RK805_BUCK1_2_ILMAX_3000MA, + RK805_BUCK1_2_ILMAX_3500MA, + RK805_BUCK1_2_ILMAX_4000MA, +}; + +enum { + RK805_BUCK3_ILMAX_1500MA, + RK805_BUCK3_ILMAX_2000MA, + RK805_BUCK3_ILMAX_2500MA, + RK805_BUCK3_ILMAX_3000MA, +}; + +enum { + RK805_BUCK4_ILMAX_2000MA, + RK805_BUCK4_ILMAX_2500MA, + RK805_BUCK4_ILMAX_3000MA, + RK805_BUCK4_ILMAX_3500MA, +}; + +enum { + RK805_ID = 0x8050, RK808_ID = 0x0000, RK818_ID = 0x8181, }; diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h index e5a6cdeb77db..d61bc58aba8a 100644 --- a/include/linux/mfd/rn5t618.h +++ b/include/linux/mfd/rn5t618.h @@ -226,11 +226,17 @@ enum { RN5T618_DCDC2, RN5T618_DCDC3, RN5T618_DCDC4, + RN5T618_DCDC5, RN5T618_LDO1, RN5T618_LDO2, RN5T618_LDO3, RN5T618_LDO4, RN5T618_LDO5, + RN5T618_LDO6, + RN5T618_LDO7, + RN5T618_LDO8, + RN5T618_LDO9, + RN5T618_LDO10, RN5T618_LDORTC1, RN5T618_LDORTC2, RN5T618_REG_NUM, diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 7eb7cbac0a9a..116816fb9110 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -850,6 +850,9 @@ #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) +#define RTS5227_DEVICE_ID 0x5227 +#define RTS_MAX_TIMES_FREQ_REDUCTION 8 + struct rtsx_pcr; struct pcr_handle { @@ -957,6 +960,8 @@ struct rtsx_pcr { int num_slots; struct rtsx_slot *slots; + + u8 dma_error_count; }; #define CHK_PCI_PID(pcr, pid) ((pcr)->pci->device == (pid)) diff --git a/include/linux/mfd/stm32-lptimer.h b/include/linux/mfd/stm32-lptimer.h new file mode 100644 index 000000000000..77c7cf40d9b4 --- /dev/null +++ b/include/linux/mfd/stm32-lptimer.h @@ -0,0 +1,62 @@ +/* + * STM32 Low-Power Timer parent driver. + * + * Copyright (C) STMicroelectronics 2017 + * + * Author: Fabrice Gasnier <fabrice.gasnier@st.com> + * + * Inspired by Benjamin Gaignard's stm32-timers driver + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#ifndef _LINUX_STM32_LPTIMER_H_ +#define _LINUX_STM32_LPTIMER_H_ + +#include <linux/clk.h> +#include <linux/regmap.h> + +#define STM32_LPTIM_ISR 0x00 /* Interrupt and Status Reg */ +#define STM32_LPTIM_ICR 0x04 /* Interrupt Clear Reg */ +#define STM32_LPTIM_IER 0x08 /* Interrupt Enable Reg */ +#define STM32_LPTIM_CFGR 0x0C /* Configuration Reg */ +#define STM32_LPTIM_CR 0x10 /* Control Reg */ +#define STM32_LPTIM_CMP 0x14 /* Compare Reg */ +#define STM32_LPTIM_ARR 0x18 /* Autoreload Reg */ +#define STM32_LPTIM_CNT 0x1C /* Counter Reg */ + +/* STM32_LPTIM_ISR - bit fields */ +#define STM32_LPTIM_CMPOK_ARROK GENMASK(4, 3) +#define STM32_LPTIM_ARROK BIT(4) +#define STM32_LPTIM_CMPOK BIT(3) + +/* STM32_LPTIM_ICR - bit fields */ +#define STM32_LPTIM_CMPOKCF_ARROKCF GENMASK(4, 3) + +/* STM32_LPTIM_CR - bit fields */ +#define STM32_LPTIM_CNTSTRT BIT(2) +#define STM32_LPTIM_ENABLE BIT(0) + +/* STM32_LPTIM_CFGR - bit fields */ +#define STM32_LPTIM_ENC BIT(24) +#define STM32_LPTIM_COUNTMODE BIT(23) +#define STM32_LPTIM_WAVPOL BIT(21) +#define STM32_LPTIM_PRESC GENMASK(11, 9) +#define STM32_LPTIM_CKPOL GENMASK(2, 1) + +/* STM32_LPTIM_ARR */ +#define STM32_LPTIM_MAX_ARR 0xFFFF + +/** + * struct stm32_lptimer - STM32 Low-Power Timer data assigned by parent device + * @clk: clock reference for this instance + * @regmap: register map reference for this instance + * @has_encoder: indicates this Low-Power Timer supports encoder mode + */ +struct stm32_lptimer { + struct clk *clk; + struct regmap *regmap; + bool has_encoder; +}; + +#endif diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 4a0abbc10ef6..ce7346e7f77a 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -34,6 +34,7 @@ #define TIM_CR1_DIR BIT(4) /* Counter Direction */ #define TIM_CR1_ARPE BIT(7) /* Auto-reload Preload Ena */ #define TIM_CR2_MMS (BIT(4) | BIT(5) | BIT(6)) /* Master mode selection */ +#define TIM_CR2_MMS2 GENMASK(23, 20) /* Master mode selection 2 */ #define TIM_SMCR_SMS (BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */ #define TIM_SMCR_TS (BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */ #define TIM_DIER_UIE BIT(0) /* Update interrupt */ @@ -60,6 +61,7 @@ #define MAX_TIM_PSC 0xFFFF #define TIM_CR2_MMS_SHIFT 4 +#define TIM_CR2_MMS2_SHIFT 20 #define TIM_SMCR_TS_SHIFT 4 #define TIM_BDTR_BKF_MASK 0xF #define TIM_BDTR_BKF_SHIFT 16 diff --git a/include/linux/mfd/syscon/atmel-smc.h b/include/linux/mfd/syscon/atmel-smc.h index afa266169800..7a367f34b66a 100644 --- a/include/linux/mfd/syscon/atmel-smc.h +++ b/include/linux/mfd/syscon/atmel-smc.h @@ -15,21 +15,26 @@ #define _LINUX_MFD_SYSCON_ATMEL_SMC_H_ #include <linux/kernel.h> +#include <linux/of.h> #include <linux/regmap.h> #define ATMEL_SMC_SETUP(cs) (((cs) * 0x10)) -#define ATMEL_HSMC_SETUP(cs) (0x600 + ((cs) * 0x14)) +#define ATMEL_HSMC_SETUP(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14)) #define ATMEL_SMC_PULSE(cs) (((cs) * 0x10) + 0x4) -#define ATMEL_HSMC_PULSE(cs) (0x600 + ((cs) * 0x14) + 0x4) +#define ATMEL_HSMC_PULSE(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0x4) #define ATMEL_SMC_CYCLE(cs) (((cs) * 0x10) + 0x8) -#define ATMEL_HSMC_CYCLE(cs) (0x600 + ((cs) * 0x14) + 0x8) +#define ATMEL_HSMC_CYCLE(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0x8) #define ATMEL_SMC_NWE_SHIFT 0 #define ATMEL_SMC_NCS_WR_SHIFT 8 #define ATMEL_SMC_NRD_SHIFT 16 #define ATMEL_SMC_NCS_RD_SHIFT 24 #define ATMEL_SMC_MODE(cs) (((cs) * 0x10) + 0xc) -#define ATMEL_HSMC_MODE(cs) (0x600 + ((cs) * 0x14) + 0x10) +#define ATMEL_HSMC_MODE(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0x10) #define ATMEL_SMC_MODE_READMODE_MASK BIT(0) #define ATMEL_SMC_MODE_READMODE_NCS (0 << 0) #define ATMEL_SMC_MODE_READMODE_NRD (1 << 0) @@ -59,7 +64,8 @@ #define ATMEL_SMC_MODE_PS_16 (2 << 28) #define ATMEL_SMC_MODE_PS_32 (3 << 28) -#define ATMEL_HSMC_TIMINGS(cs) (0x600 + ((cs) * 0x14) + 0xc) +#define ATMEL_HSMC_TIMINGS(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0xc) #define ATMEL_HSMC_TIMINGS_OCMS BIT(12) #define ATMEL_HSMC_TIMINGS_RBNSEL(x) ((x) << 28) #define ATMEL_HSMC_TIMINGS_NFSEL BIT(31) @@ -69,6 +75,10 @@ #define ATMEL_HSMC_TIMINGS_TRR_SHIFT 16 #define ATMEL_HSMC_TIMINGS_TWB_SHIFT 24 +struct atmel_hsmc_reg_layout { + unsigned int timing_regs_offset; +}; + /** * struct atmel_smc_cs_conf - SMC CS config as described in the datasheet. * @setup: NCS/NWE/NRD setup timings (not applicable to at91rm9200) @@ -98,11 +108,15 @@ int atmel_smc_cs_conf_set_cycle(struct atmel_smc_cs_conf *conf, unsigned int shift, unsigned int ncycles); void atmel_smc_cs_conf_apply(struct regmap *regmap, int cs, const struct atmel_smc_cs_conf *conf); -void atmel_hsmc_cs_conf_apply(struct regmap *regmap, int cs, - const struct atmel_smc_cs_conf *conf); +void atmel_hsmc_cs_conf_apply(struct regmap *regmap, + const struct atmel_hsmc_reg_layout *reglayout, + int cs, const struct atmel_smc_cs_conf *conf); void atmel_smc_cs_conf_get(struct regmap *regmap, int cs, struct atmel_smc_cs_conf *conf); -void atmel_hsmc_cs_conf_get(struct regmap *regmap, int cs, - struct atmel_smc_cs_conf *conf); +void atmel_hsmc_cs_conf_get(struct regmap *regmap, + const struct atmel_hsmc_reg_layout *reglayout, + int cs, struct atmel_smc_cs_conf *conf); +const struct atmel_hsmc_reg_layout * +atmel_hsmc_get_reg_layout(struct device_node *np); #endif /* _LINUX_MFD_SYSCON_ATMEL_SMC_H_ */ diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index a1520d88ebf3..15646740e2a8 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -13,15 +13,15 @@ #define tmio_ioread16(addr) readw(addr) #define tmio_ioread16_rep(r, b, l) readsw(r, b, l) #define tmio_ioread32(addr) \ - (((u32) readw((addr))) | (((u32) readw((addr) + 2)) << 16)) + (((u32)readw((addr))) | (((u32)readw((addr) + 2)) << 16)) #define tmio_iowrite8(val, addr) writeb((val), (addr)) #define tmio_iowrite16(val, addr) writew((val), (addr)) #define tmio_iowrite16_rep(r, b, l) writesw(r, b, l) #define tmio_iowrite32(val, addr) \ do { \ - writew((val), (addr)); \ - writew((val) >> 16, (addr) + 2); \ + writew((val), (addr)); \ + writew((val) >> 16, (addr) + 2); \ } while (0) #define CNF_CMD 0x04 @@ -55,57 +55,60 @@ } while (0) /* tmio MMC platform flags */ -#define TMIO_MMC_WRPROTECT_DISABLE (1 << 0) +#define TMIO_MMC_WRPROTECT_DISABLE BIT(0) /* * Some controllers can support a 2-byte block size when the bus width * is configured in 4-bit mode. */ -#define TMIO_MMC_BLKSZ_2BYTES (1 << 1) +#define TMIO_MMC_BLKSZ_2BYTES BIT(1) /* * Some controllers can support SDIO IRQ signalling. */ -#define TMIO_MMC_SDIO_IRQ (1 << 2) +#define TMIO_MMC_SDIO_IRQ BIT(2) -/* Some features are only available or tested on RCar Gen2 or later */ -#define TMIO_MMC_MIN_RCAR2 (1 << 3) +/* Some features are only available or tested on R-Car Gen2 or later */ +#define TMIO_MMC_MIN_RCAR2 BIT(3) /* * Some controllers require waiting for the SD bus to become * idle before writing to some registers. */ -#define TMIO_MMC_HAS_IDLE_WAIT (1 << 4) +#define TMIO_MMC_HAS_IDLE_WAIT BIT(4) /* * A GPIO is used for card hotplug detection. We need an extra flag for this, * because 0 is a valid GPIO number too, and requiring users to specify * cd_gpio < 0 to disable GPIO hotplug would break backwards compatibility. */ -#define TMIO_MMC_USE_GPIO_CD (1 << 5) +#define TMIO_MMC_USE_GPIO_CD BIT(5) /* * Some controllers doesn't have over 0x100 register. * it is used to checking accessibility of * CTL_SD_CARD_CLK_CTL / CTL_CLK_AND_WAIT_CTL */ -#define TMIO_MMC_HAVE_HIGH_REG (1 << 6) +#define TMIO_MMC_HAVE_HIGH_REG BIT(6) /* * Some controllers have CMD12 automatically * issue/non-issue register */ -#define TMIO_MMC_HAVE_CMD12_CTRL (1 << 7) +#define TMIO_MMC_HAVE_CMD12_CTRL BIT(7) /* Controller has some SDIO status bits which must be 1 */ -#define TMIO_MMC_SDIO_STATUS_SETBITS (1 << 8) +#define TMIO_MMC_SDIO_STATUS_SETBITS BIT(8) /* * Some controllers have a 32-bit wide data port register */ -#define TMIO_MMC_32BIT_DATA_PORT (1 << 9) +#define TMIO_MMC_32BIT_DATA_PORT BIT(9) /* * Some controllers allows to set SDx actual clock */ -#define TMIO_MMC_CLK_ACTUAL (1 << 10) +#define TMIO_MMC_CLK_ACTUAL BIT(10) + +/* Some controllers have a CBSY bit */ +#define TMIO_MMC_HAVE_CBSY BIT(11) int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); @@ -128,6 +131,8 @@ struct tmio_mmc_data { unsigned int cd_gpio; int alignment_shift; dma_addr_t dma_rx_offset; + unsigned int max_blk_count; + unsigned short max_segs; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); }; @@ -139,6 +144,7 @@ struct tmio_nand_data { struct nand_bbt_descr *badblock_pattern; struct mtd_partition *partition; unsigned int num_partitions; + const char *const *part_parsers; }; #define FBIO_TMIO_ACC_WRITE 0x7C639300 @@ -146,9 +152,9 @@ struct tmio_nand_data { struct tmio_fb_data { int (*lcd_set_power)(struct platform_device *fb_dev, - bool on); + bool on); int (*lcd_mode)(struct platform_device *fb_dev, - const struct fb_videomode *mode); + const struct fb_videomode *mode); int num_modes; struct fb_videomode *modes; @@ -157,5 +163,4 @@ struct tmio_fb_data { int width; }; - #endif diff --git a/include/linux/i2c/tps65010.h b/include/linux/mfd/tps65010.h index 08aa92278d71..a1fb9bc5311d 100644 --- a/include/linux/i2c/tps65010.h +++ b/include/linux/mfd/tps65010.h @@ -1,4 +1,4 @@ -/* linux/i2c/tps65010.h +/* linux/mfd/tps65010.h * * Functions to access TPS65010 power management device. * diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index ffb21e79204d..deffdcd0236f 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -879,7 +879,7 @@ struct tps65910_board { bool en_ck32k_xtal; bool en_dev_slp; bool pm_off; - struct tps65910_sleep_keepon_data *slp_keepon; + struct tps65910_sleep_keepon_data slp_keepon; bool en_gpio_sleep[TPS6591X_MAX_NUM_GPIO]; unsigned long regulator_ext_sleep_control[TPS65910_NUM_REGS]; struct regulator_init_data *tps65910_pmic_init_data[TPS65910_NUM_REGS]; diff --git a/include/linux/mfd/tps68470.h b/include/linux/mfd/tps68470.h new file mode 100644 index 000000000000..44f9d9f647ed --- /dev/null +++ b/include/linux/mfd/tps68470.h @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2017 Intel Corporation + * + * Functions to access TPS68470 power management chip. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_TPS68470_H +#define __LINUX_MFD_TPS68470_H + +/* Register addresses */ +#define TPS68470_REG_POSTDIV2 0x06 +#define TPS68470_REG_BOOSTDIV 0x07 +#define TPS68470_REG_BUCKDIV 0x08 +#define TPS68470_REG_PLLSWR 0x09 +#define TPS68470_REG_XTALDIV 0x0A +#define TPS68470_REG_PLLDIV 0x0B +#define TPS68470_REG_POSTDIV 0x0C +#define TPS68470_REG_PLLCTL 0x0D +#define TPS68470_REG_PLLCTL2 0x0E +#define TPS68470_REG_CLKCFG1 0x0F +#define TPS68470_REG_CLKCFG2 0x10 +#define TPS68470_REG_GPCTL0A 0x14 +#define TPS68470_REG_GPCTL0B 0x15 +#define TPS68470_REG_GPCTL1A 0x16 +#define TPS68470_REG_GPCTL1B 0x17 +#define TPS68470_REG_GPCTL2A 0x18 +#define TPS68470_REG_GPCTL2B 0x19 +#define TPS68470_REG_GPCTL3A 0x1A +#define TPS68470_REG_GPCTL3B 0x1B +#define TPS68470_REG_GPCTL4A 0x1C +#define TPS68470_REG_GPCTL4B 0x1D +#define TPS68470_REG_GPCTL5A 0x1E +#define TPS68470_REG_GPCTL5B 0x1F +#define TPS68470_REG_GPCTL6A 0x20 +#define TPS68470_REG_GPCTL6B 0x21 +#define TPS68470_REG_SGPO 0x22 +#define TPS68470_REG_GPDI 0x26 +#define TPS68470_REG_GPDO 0x27 +#define TPS68470_REG_VCMVAL 0x3C +#define TPS68470_REG_VAUX1VAL 0x3D +#define TPS68470_REG_VAUX2VAL 0x3E +#define TPS68470_REG_VIOVAL 0x3F +#define TPS68470_REG_VSIOVAL 0x40 +#define TPS68470_REG_VAVAL 0x41 +#define TPS68470_REG_VDVAL 0x42 +#define TPS68470_REG_S_I2C_CTL 0x43 +#define TPS68470_REG_VCMCTL 0x44 +#define TPS68470_REG_VAUX1CTL 0x45 +#define TPS68470_REG_VAUX2CTL 0x46 +#define TPS68470_REG_VACTL 0x47 +#define TPS68470_REG_VDCTL 0x48 +#define TPS68470_REG_RESET 0x50 +#define TPS68470_REG_REVID 0xFF + +#define TPS68470_REG_MAX TPS68470_REG_REVID + +/* Register field definitions */ + +#define TPS68470_REG_RESET_MASK GENMASK(7, 0) +#define TPS68470_VAVAL_AVOLT_MASK GENMASK(6, 0) + +#define TPS68470_VDVAL_DVOLT_MASK GENMASK(5, 0) +#define TPS68470_VCMVAL_VCVOLT_MASK GENMASK(6, 0) +#define TPS68470_VIOVAL_IOVOLT_MASK GENMASK(6, 0) +#define TPS68470_VSIOVAL_IOVOLT_MASK GENMASK(6, 0) +#define TPS68470_VAUX1VAL_AUX1VOLT_MASK GENMASK(6, 0) +#define TPS68470_VAUX2VAL_AUX2VOLT_MASK GENMASK(6, 0) + +#define TPS68470_VACTL_EN_MASK GENMASK(0, 0) +#define TPS68470_VDCTL_EN_MASK GENMASK(0, 0) +#define TPS68470_VCMCTL_EN_MASK GENMASK(0, 0) +#define TPS68470_S_I2C_CTL_EN_MASK GENMASK(1, 0) +#define TPS68470_VAUX1CTL_EN_MASK GENMASK(0, 0) +#define TPS68470_VAUX2CTL_EN_MASK GENMASK(0, 0) +#define TPS68470_PLL_EN_MASK GENMASK(0, 0) + +#define TPS68470_CLKCFG1_MODE_A_MASK GENMASK(1, 0) +#define TPS68470_CLKCFG1_MODE_B_MASK GENMASK(3, 2) + +#define TPS68470_GPIO_CTL_REG_A(x) (TPS68470_REG_GPCTL0A + (x) * 2) +#define TPS68470_GPIO_CTL_REG_B(x) (TPS68470_REG_GPCTL0B + (x) * 2) +#define TPS68470_GPIO_MODE_MASK GENMASK(1, 0) +#define TPS68470_GPIO_MODE_IN 0 +#define TPS68470_GPIO_MODE_IN_PULLUP 1 +#define TPS68470_GPIO_MODE_OUT_CMOS 2 +#define TPS68470_GPIO_MODE_OUT_ODRAIN 3 + +#endif /* __LINUX_MFD_TPS68470_H */ diff --git a/include/linux/i2c/twl.h b/include/linux/mfd/twl.h index 9ad7828d9d34..9ad7828d9d34 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/mfd/twl.h diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index f541da68d1e7..472fa4d4ea62 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -37,6 +37,8 @@ #define PHY_ID_KSZ8795 0x00221550 +#define PHY_ID_KSZ9477 0x00221631 + /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 48e24844b3c5..643c7ae7d7b4 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -4,6 +4,7 @@ #include <linux/mm.h> #include <linux/mempolicy.h> #include <linux/migrate_mode.h> +#include <linux/hugetlb.h> typedef struct page *new_page_t(struct page *page, unsigned long private, int **reason); @@ -30,6 +31,34 @@ enum migrate_reason { /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern char *migrate_reason_names[MR_TYPES]; +static inline struct page *new_page_nodemask(struct page *page, + int preferred_nid, nodemask_t *nodemask) +{ + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; + unsigned int order = 0; + struct page *new_page = NULL; + + if (PageHuge(page)) + return alloc_huge_page_nodemask(page_hstate(compound_head(page)), + preferred_nid, nodemask); + + if (thp_migration_supported() && PageTransHuge(page)) { + order = HPAGE_PMD_ORDER; + gfp_mask |= GFP_TRANSHUGE; + } + + if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) + gfp_mask |= __GFP_HIGHMEM; + + new_page = __alloc_pages_nodemask(gfp_mask, order, + preferred_nid, nodemask); + + if (new_page && PageTransHuge(page)) + prep_transhuge_page(new_page); + + return new_page; +} + #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); @@ -43,6 +72,7 @@ extern void putback_movable_page(struct page *page); extern int migrate_prep(void); extern int migrate_prep_local(void); +extern void migrate_page_states(struct page *newpage, struct page *page); extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); @@ -63,6 +93,10 @@ static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } +static inline void migrate_page_states(struct page *newpage, struct page *page) +{ +} + static inline void migrate_page_copy(struct page *newpage, struct page *page) {} @@ -122,4 +156,136 @@ static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm, } #endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/ + +#ifdef CONFIG_MIGRATION + +/* + * Watch out for PAE architecture, which has an unsigned long, and might not + * have enough bits to store all physical address and flags. So far we have + * enough room for all our flags. + */ +#define MIGRATE_PFN_VALID (1UL << 0) +#define MIGRATE_PFN_MIGRATE (1UL << 1) +#define MIGRATE_PFN_LOCKED (1UL << 2) +#define MIGRATE_PFN_WRITE (1UL << 3) +#define MIGRATE_PFN_DEVICE (1UL << 4) +#define MIGRATE_PFN_ERROR (1UL << 5) +#define MIGRATE_PFN_SHIFT 6 + +static inline struct page *migrate_pfn_to_page(unsigned long mpfn) +{ + if (!(mpfn & MIGRATE_PFN_VALID)) + return NULL; + return pfn_to_page(mpfn >> MIGRATE_PFN_SHIFT); +} + +static inline unsigned long migrate_pfn(unsigned long pfn) +{ + return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID; +} + +/* + * struct migrate_vma_ops - migrate operation callback + * + * @alloc_and_copy: alloc destination memory and copy source memory to it + * @finalize_and_map: allow caller to map the successfully migrated pages + * + * + * The alloc_and_copy() callback happens once all source pages have been locked, + * unmapped and checked (checked whether pinned or not). All pages that can be + * migrated will have an entry in the src array set with the pfn value of the + * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set (other + * flags might be set but should be ignored by the callback). + * + * The alloc_and_copy() callback can then allocate destination memory and copy + * source memory to it for all those entries (ie with MIGRATE_PFN_VALID and + * MIGRATE_PFN_MIGRATE flag set). Once these are allocated and copied, the + * callback must update each corresponding entry in the dst array with the pfn + * value of the destination page and with the MIGRATE_PFN_VALID and + * MIGRATE_PFN_LOCKED flags set (destination pages must have their struct pages + * locked, via lock_page()). + * + * At this point the alloc_and_copy() callback is done and returns. + * + * Note that the callback does not have to migrate all the pages that are + * marked with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration + * from device memory to system memory (ie the MIGRATE_PFN_DEVICE flag is also + * set in the src array entry). If the device driver cannot migrate a device + * page back to system memory, then it must set the corresponding dst array + * entry to MIGRATE_PFN_ERROR. This will trigger a SIGBUS if CPU tries to + * access any of the virtual addresses originally backed by this page. Because + * a SIGBUS is such a severe result for the userspace process, the device + * driver should avoid setting MIGRATE_PFN_ERROR unless it is really in an + * unrecoverable state. + * + * For empty entry inside CPU page table (pte_none() or pmd_none() is true) we + * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus + * allowing device driver to allocate device memory for those unback virtual + * address. For this the device driver simply have to allocate device memory + * and properly set the destination entry like for regular migration. Note that + * this can still fails and thus inside the device driver must check if the + * migration was successful for those entry inside the finalize_and_map() + * callback just like for regular migration. + * + * THE alloc_and_copy() CALLBACK MUST NOT CHANGE ANY OF THE SRC ARRAY ENTRIES + * OR BAD THINGS WILL HAPPEN ! + * + * + * The finalize_and_map() callback happens after struct page migration from + * source to destination (destination struct pages are the struct pages for the + * memory allocated by the alloc_and_copy() callback). Migration can fail, and + * thus the finalize_and_map() allows the driver to inspect which pages were + * successfully migrated, and which were not. Successfully migrated pages will + * have the MIGRATE_PFN_MIGRATE flag set for their src array entry. + * + * It is safe to update device page table from within the finalize_and_map() + * callback because both destination and source page are still locked, and the + * mmap_sem is held in read mode (hence no one can unmap the range being + * migrated). + * + * Once callback is done cleaning up things and updating its page table (if it + * chose to do so, this is not an obligation) then it returns. At this point, + * the HMM core will finish up the final steps, and the migration is complete. + * + * THE finalize_and_map() CALLBACK MUST NOT CHANGE ANY OF THE SRC OR DST ARRAY + * ENTRIES OR BAD THINGS WILL HAPPEN ! + */ +struct migrate_vma_ops { + void (*alloc_and_copy)(struct vm_area_struct *vma, + const unsigned long *src, + unsigned long *dst, + unsigned long start, + unsigned long end, + void *private); + void (*finalize_and_map)(struct vm_area_struct *vma, + const unsigned long *src, + const unsigned long *dst, + unsigned long start, + unsigned long end, + void *private); +}; + +#if defined(CONFIG_MIGRATE_VMA_HELPER) +int migrate_vma(const struct migrate_vma_ops *ops, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long *src, + unsigned long *dst, + void *private); +#else +static inline int migrate_vma(const struct migrate_vma_ops *ops, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long *src, + unsigned long *dst, + void *private) +{ + return -EINVAL; +} +#endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */ + +#endif /* CONFIG_MIGRATION */ + #endif /* _LINUX_MIGRATE_H */ diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index ebf3d89a3919..bdf66af9b937 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -6,11 +6,16 @@ * on most operations but not ->writepage as the potential stall time * is too significant * MIGRATE_SYNC will block when migrating pages + * MIGRATE_SYNC_NO_COPY will block when migrating pages but will not copy pages + * with the CPU. Instead, page copy happens outside the migratepage() + * callback and is likely using a DMA engine. See migrate_vma() and HMM + * (mm/hmm.c) for users of this mode. */ enum migrate_mode { MIGRATE_ASYNC, MIGRATE_SYNC_LIGHT, MIGRATE_SYNC, + MIGRATE_SYNC_NO_COPY, }; #endif /* MIGRATE_MODE_H_INCLUDED */ diff --git a/include/linux/mii.h b/include/linux/mii.h index 1629a0c32679..e870bfa6abfe 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -31,7 +31,7 @@ struct mii_if_info { extern int mii_link_ok (struct mii_if_info *mii); extern int mii_nway_restart (struct mii_if_info *mii); extern int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); -extern int mii_ethtool_get_link_ksettings( +extern void mii_ethtool_get_link_ksettings( struct mii_if_info *mii, struct ethtool_link_ksettings *cmd); extern int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); extern int mii_ethtool_set_link_ksettings( diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 762b5fec3383..58751eae5f77 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -54,6 +54,7 @@ #define VHOST_NET_MINOR 238 #define UHID_MINOR 239 #define USERIO_MINOR 240 +#define VHOST_VSOCK_MINOR 241 #define MISC_DYNAMIC_MINOR 255 struct device; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index d5bed0875d30..b0a57e043fa3 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -224,6 +224,7 @@ enum { MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT = 1ULL << 35, MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36, MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37, + MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38, }; enum { @@ -428,6 +429,12 @@ enum mlx4_steer_type { MLX4_NUM_STEERS }; +enum mlx4_resource_usage { + MLX4_RES_USAGE_NONE, + MLX4_RES_USAGE_DRIVER, + MLX4_RES_USAGE_USER_VERBS, +}; + enum { MLX4_NUM_FEXCH = 64 * 1024, }; @@ -518,6 +525,14 @@ struct mlx4_phys_caps { u32 base_tunnel_sqpn; }; +struct mlx4_spec_qps { + u32 qp0_qkey; + u32 qp0_proxy; + u32 qp0_tunnel; + u32 qp1_proxy; + u32 qp1_tunnel; +}; + struct mlx4_caps { u64 fw_ver; u32 function; @@ -547,11 +562,7 @@ struct mlx4_caps { int max_qp_init_rdma; int max_qp_dest_rdma; int max_tc_eth; - u32 *qp0_qkey; - u32 *qp0_proxy; - u32 *qp1_proxy; - u32 *qp0_tunnel; - u32 *qp1_tunnel; + struct mlx4_spec_qps *spec_qps; int num_srqs; int max_srq_wqes; int max_srq_sge; @@ -620,6 +631,7 @@ struct mlx4_caps { u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; u32 vf_caps; + bool wol_port[MLX4_MAX_PORTS + 1]; struct mlx4_rate_limit_caps rl_caps; }; @@ -748,6 +760,7 @@ struct mlx4_cq { } tasklet_ctx; int reset_notify_added; struct list_head reset_notify; + u8 usage; }; struct mlx4_qp { @@ -757,6 +770,7 @@ struct mlx4_qp { atomic_t refcount; struct completion free; + u8 usage; }; struct mlx4_srq { @@ -1068,7 +1082,7 @@ static inline int mlx4_is_eth(struct mlx4_dev *dev, int port) } int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, - struct mlx4_buf *buf, gfp_t gfp); + struct mlx4_buf *buf); void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf); static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset) { @@ -1105,10 +1119,9 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw); int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int start_index, int npages, u64 *page_list); int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, - struct mlx4_buf *buf, gfp_t gfp); + struct mlx4_buf *buf); -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, - gfp_t gfp); +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order); void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db); int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, @@ -1121,11 +1134,10 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, unsigned vector, int collapsed, int timestamp_en); void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq); int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, - int *base, u8 flags); + int *base, u8 flags, u8 usage); void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt); -int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, - gfp_t gfp); +int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp); void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp); int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcdn, @@ -1374,6 +1386,7 @@ int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port); int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac); int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx); +int mlx4_SET_PORT_user_mac(struct mlx4_dev *dev, u8 port, u8 *user_mac); int mlx4_SET_PORT_user_mtu(struct mlx4_dev *dev, u8 port, u16 user_mtu); int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u8 promisc); @@ -1419,7 +1432,7 @@ int mlx4_get_phys_port_id(struct mlx4_dev *dev); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); -int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); +int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage); void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index a940ec6a046c..eaf4ad209c8f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -48,7 +48,7 @@ /* helper macros */ #define __mlx5_nullp(typ) ((struct mlx5_ifc_##typ##_bits *)0) #define __mlx5_bit_sz(typ, fld) sizeof(__mlx5_nullp(typ)->fld) -#define __mlx5_bit_off(typ, fld) ((unsigned)(unsigned long)(&(__mlx5_nullp(typ)->fld))) +#define __mlx5_bit_off(typ, fld) (offsetof(struct mlx5_ifc_##typ##_bits, fld)) #define __mlx5_dw_off(typ, fld) (__mlx5_bit_off(typ, fld) / 32) #define __mlx5_64_off(typ, fld) (__mlx5_bit_off(typ, fld) / 64) #define __mlx5_dw_bit_off(typ, fld) (32 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0x1f)) @@ -290,6 +290,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_GPIO_EVENT = 0x15, MLX5_EVENT_TYPE_PORT_MODULE_EVENT = 0x16, MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19, + MLX5_EVENT_TYPE_GENERAL_EVENT = 0x22, MLX5_EVENT_TYPE_PPS_EVENT = 0x25, MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a, @@ -300,6 +301,12 @@ enum mlx5_event { MLX5_EVENT_TYPE_PAGE_FAULT = 0xc, MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd, + + MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, +}; + +enum { + MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, }; enum { @@ -707,7 +714,7 @@ static inline int mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) return (cqe->op_own >> 2) & 0x3; } -static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) +static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro_tcppsh_abort_dupack >> 6) & 1; } @@ -966,13 +973,14 @@ enum mlx5_cap_type { MLX5_CAP_ATOMIC, MLX5_CAP_ROCE, MLX5_CAP_IPOIB_OFFLOADS, - MLX5_CAP_EOIB_OFFLOADS, + MLX5_CAP_IPOIB_ENHANCED_OFFLOADS, MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, MLX5_CAP_RESERVED, MLX5_CAP_VECTOR_CALC, MLX5_CAP_QOS, + MLX5_CAP_FPGA, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1008,6 +1016,10 @@ enum mlx5_mcam_feature_groups { MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) +#define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->caps.hca_cur[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS], cap) + #define MLX5_CAP_ROCE(mdev, cap) \ MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap) @@ -1091,9 +1103,18 @@ enum mlx5_mcam_feature_groups { #define MLX5_CAP_PCAM_FEATURE(mdev, fld) \ MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld) +#define MLX5_CAP_MCAM_REG(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_access_reg_cap_mask.access_regs.reg) + #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) +#define MLX5_CAP_FPGA(mdev, cap) \ + MLX5_GET(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + +#define MLX5_CAP64_FPGA(mdev, cap) \ + MLX5_GET64(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 93273d9ea4d1..02ff700e4f30 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -44,6 +44,7 @@ #include <linux/workqueue.h> #include <linux/mempool.h> #include <linux/interrupt.h> +#include <linux/idr.h> #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> @@ -108,6 +109,9 @@ enum { MLX5_REG_QTCT = 0x400a, MLX5_REG_DCBX_PARAM = 0x4020, MLX5_REG_DCBX_APP = 0x4021, + MLX5_REG_FPGA_CAP = 0x4022, + MLX5_REG_FPGA_CTRL = 0x4023, + MLX5_REG_FPGA_ACCESS_REG = 0x4024, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, @@ -129,6 +133,9 @@ enum { MLX5_REG_MPCNT = 0x9051, MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, + MLX5_REG_MCQI = 0x9061, + MLX5_REG_MCC = 0x9062, + MLX5_REG_MCDA = 0x9063, MLX5_REG_MCAM = 0x907f, }; @@ -155,6 +162,13 @@ enum dbg_rsc_type { MLX5_DBG_RSC_CQ, }; +enum port_state_policy { + MLX5_POLICY_DOWN = 0, + MLX5_POLICY_UP = 1, + MLX5_POLICY_FOLLOW = 2, + MLX5_POLICY_INVALID = 0xffffffff +}; + struct mlx5_field_desc { struct dentry *dent; int i; @@ -178,6 +192,7 @@ enum mlx5_dev_event { MLX5_DEV_EVENT_GUID_CHANGE, MLX5_DEV_EVENT_CLIENT_REREG, MLX5_DEV_EVENT_PPS, + MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, }; enum mlx5_port_status { @@ -284,7 +299,7 @@ struct mlx5_cmd { struct semaphore pages_sem; int mode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; - struct pci_pool *pool; + struct dma_pool *pool; struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; @@ -403,6 +418,7 @@ enum mlx5_res_type { MLX5_RES_SQ = MLX5_EVENT_QUEUE_TYPE_SQ, MLX5_RES_SRQ = 3, MLX5_RES_XSRQ = 4, + MLX5_RES_XRQ = 5, }; struct mlx5_core_rsc_common { @@ -518,6 +534,9 @@ struct mlx5_mkey_table { struct mlx5_vf_context { int enabled; + u64 port_guid; + u64 node_guid; + enum port_state_policy policy; }; struct mlx5_core_sriov { @@ -527,7 +546,6 @@ struct mlx5_core_sriov { }; struct mlx5_irq_info { - cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; }; @@ -543,6 +561,7 @@ struct mlx5_fc_stats { unsigned long sampling_interval; /* jiffies */ }; +struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; struct mlx5_pagefault; @@ -590,7 +609,6 @@ struct mlx5_port_module_event_stats { struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; - struct msix_entry *msix_arr; struct mlx5_irq_info *irq_info; /* pages stuff */ @@ -639,7 +657,11 @@ struct mlx5_priv { struct list_head ctx_list; spinlock_t ctx_lock; + struct list_head waiting_events_list; + bool is_accum_events; + struct mlx5_flow_steering *steering; + struct mlx5_mpfs *mpfs; struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; struct mlx5_lag *lag; @@ -666,9 +688,7 @@ enum mlx5_device_state { }; enum mlx5_interface_state { - MLX5_INTERFACE_STATE_DOWN = BIT(0), - MLX5_INTERFACE_STATE_UP = BIT(1), - MLX5_INTERFACE_STATE_SHUTDOWN = BIT(2), + MLX5_INTERFACE_STATE_UP = BIT(0), }; enum mlx5_pci_status { @@ -732,6 +752,14 @@ struct mlx5e_resources { struct mlx5_sq_bfreg bfreg; }; +#define MLX5_MAX_RESERVED_GIDS 8 + +struct mlx5_rsvd_gids { + unsigned int start; + unsigned int count; + struct ida ida; +}; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -761,6 +789,13 @@ struct mlx5_core_dev { atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; + struct { + struct mlx5_rsvd_gids reserved_gids; + atomic_t roce_en; + } roce; +#ifdef CONFIG_MLX5_FPGA + struct mlx5_fpga_device *fpga; +#endif #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif @@ -812,6 +847,7 @@ struct mlx5_cmd_work_ent { u64 ts1; u64 ts2; u16 op; + bool polling; }; struct mlx5_pas { @@ -819,13 +855,6 @@ struct mlx5_pas { u8 log_sz; }; -enum port_state_policy { - MLX5_POLICY_DOWN = 0, - MLX5_POLICY_UP = 1, - MLX5_POLICY_FOLLOW = 2, - MLX5_POLICY_INVALID = 0xffffffff -}; - enum phy_port_state { MLX5_AAA_111 }; @@ -862,8 +891,6 @@ static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset) return buf->direct.buf + offset; } -extern struct workqueue_struct *mlx5_core_wq; - #define STRUCT_FIELD(header, field) \ .struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \ .struct_size_bytes = sizeof((struct ib_unpacked_ ## header *)0)->field @@ -895,11 +922,6 @@ static inline u16 cmdif_rev(struct mlx5_core_dev *dev) return ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; } -static inline void *mlx5_vzalloc(unsigned long size) -{ - return kvzalloc(size, GFP_KERNEL); -} - static inline u32 mlx5_base_mkey(const u32 key) { return key & 0xffffff00u; @@ -915,6 +937,8 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size, mlx5_cmd_cbk_t callback, void *context); +int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, + void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); @@ -925,6 +949,8 @@ int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); +void mlx5_trigger_health_work(struct mlx5_core_dev *dev); +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); @@ -1038,6 +1064,11 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg, bool map_wc, bool fast_path); void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg); +unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev); +int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, + u8 roce_version, u8 roce_l3_type, const u8 *gid, + const u8 *mac, bool vlan, u16 vlan_id); + static inline int fw_initializing(struct mlx5_core_dev *dev) { return ioread32be(&dev->iseg->initializing) >> 31; @@ -1064,7 +1095,7 @@ enum { }; enum { - MAX_UMR_CACHE_ENTRY = 20, + MR_CACHE_LAST_STD_ENTRY = 20, MLX5_IMR_MTT_CACHE_ENTRY, MLX5_IMR_KSM_CACHE_ENTRY, MAX_MR_CACHE_ENTRIES @@ -1158,4 +1189,10 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; +static inline const struct cpumask * +mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector) +{ + return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector); +} + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index edafedb7b509..a528b35a022e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -32,6 +32,8 @@ #ifndef MLX5_IFC_H #define MLX5_IFC_H +#include "mlx5_ifc_fpga.h" + enum { MLX5_EVENT_TYPE_CODING_COMPLETION_EVENTS = 0x0, MLX5_EVENT_TYPE_CODING_PATH_MIGRATED_SUCCEEDED = 0x1, @@ -56,7 +58,8 @@ enum { MLX5_EVENT_TYPE_CODING_STALL_VL_EVENT = 0x1b, MLX5_EVENT_TYPE_CODING_DROPPED_PACKET_LOGGED_EVENT = 0x1f, MLX5_EVENT_TYPE_CODING_COMMAND_INTERFACE_COMPLETION = 0xa, - MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb + MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb, + MLX5_EVENT_TYPE_CODING_FPGA_ERROR = 0x20, }; enum { @@ -197,6 +200,7 @@ enum { MLX5_CMD_OP_QUERY_SQ = 0x907, MLX5_CMD_OP_CREATE_RQ = 0x908, MLX5_CMD_OP_MODIFY_RQ = 0x909, + MLX5_CMD_OP_SET_DELAY_DROP_PARAMS = 0x910, MLX5_CMD_OP_DESTROY_RQ = 0x90a, MLX5_CMD_OP_QUERY_RQ = 0x90b, MLX5_CMD_OP_CREATE_RMP = 0x90c, @@ -229,6 +233,11 @@ enum { MLX5_CMD_OP_DEALLOC_ENCAP_HEADER = 0x93e, MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, + MLX5_CMD_OP_FPGA_CREATE_QP = 0x960, + MLX5_CMD_OP_FPGA_MODIFY_QP = 0x961, + MLX5_CMD_OP_FPGA_QUERY_QP = 0x962, + MLX5_CMD_OP_FPGA_DESTROY_QP = 0x963, + MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS = 0x964, MLX5_CMD_OP_MAX }; @@ -240,7 +249,7 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_first_prio[0x1]; u8 outer_first_cfi[0x1]; u8 outer_first_vid[0x1]; - u8 reserved_at_7[0x1]; + u8 outer_ipv4_ttl[0x1]; u8 outer_second_prio[0x1]; u8 outer_second_cfi[0x1]; u8 outer_second_vid[0x1]; @@ -286,8 +295,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_tcp_dport[0x1]; u8 inner_tcp_flags[0x1]; u8 reserved_at_37[0x9]; + u8 reserved_at_40[0x1a]; + u8 bth_dst_qp[0x1]; - u8 reserved_at_40[0x40]; + u8 reserved_at_5b[0x25]; }; struct mlx5_ifc_flow_table_prop_layout_bits { @@ -377,7 +388,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x20]; + u8 reserved_at_c0[0x18]; + u8 ttl_hoplimit[0x8]; u8 udp_sport[0x10]; u8 udp_dport[0x10]; @@ -422,7 +434,9 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_100[0xc]; u8 inner_ipv6_flow_label[0x14]; - u8 reserved_at_120[0xe0]; + u8 reserved_at_120[0x28]; + u8 bth_dst_qp[0x18]; + u8 reserved_at_160[0xa0]; }; struct mlx5_ifc_cmd_pas_bits { @@ -590,13 +604,16 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 rss_ind_tbl_cap[0x4]; u8 reg_umr_sq[0x1]; u8 scatter_fcs[0x1]; - u8 reserved_at_1a[0x1]; + u8 enhanced_multi_pkt_send_wqe[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; u8 reserved_at_1c[0x2]; - u8 tunnel_statless_gre[0x1]; + u8 tunnel_stateless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; - u8 reserved_at_20[0x20]; + u8 swp[0x1]; + u8 swp_csum[0x1]; + u8 swp_lso[0x1]; + u8 reserved_at_23[0x1d]; u8 reserved_at_40[0x10]; u8 lro_min_mss_size[0x10]; @@ -658,9 +675,9 @@ enum { struct mlx5_ifc_atomic_caps_bits { u8 reserved_at_0[0x40]; - u8 atomic_req_8B_endianess_mode[0x2]; + u8 atomic_req_8B_endianness_mode[0x2]; u8 reserved_at_42[0x4]; - u8 supported_atomic_req_8B_endianess_mode_1[0x1]; + u8 supported_atomic_req_8B_endianness_mode_1[0x1]; u8 reserved_at_47[0x19]; @@ -798,7 +815,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_indirection[0x8]; u8 fixed_buffer_size[0x1]; u8 log_max_mrw_sz[0x7]; - u8 reserved_at_110[0x2]; + u8 force_teardown[0x1]; + u8 reserved_at_111[0x1]; u8 log_max_bsf_list_size[0x6]; u8 umr_extended_translation_offset[0x1]; u8 null_mkey[0x1]; @@ -819,7 +837,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cc_modify_allowed[0x1]; u8 start_pad[0x1]; u8 cache_line_128byte[0x1]; - u8 reserved_at_163[0xb]; + u8 reserved_at_165[0xb]; u8 gid_table_size[0x10]; u8 out_of_seq_cnt[0x1]; @@ -827,7 +845,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 retransmission_q_counters[0x1]; u8 reserved_at_183[0x1]; u8 modify_rq_counter_set_id[0x1]; - u8 reserved_at_185[0x1]; + u8 rq_delay_drop[0x1]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; @@ -844,7 +862,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pcam_reg[0x1]; u8 local_ca_ack_delay[0x5]; u8 port_module_event[0x1]; - u8 reserved_at_1b1[0x1]; + u8 enhanced_error_q_counters[0x1]; u8 ports_check[0x1]; u8 reserved_at_1b3[0x1]; u8 disable_link_up[0x1]; @@ -860,7 +878,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_tc[0x4]; u8 reserved_at_1d0[0x1]; u8 dcbx[0x1]; - u8 reserved_at_1d2[0x4]; + u8 general_notification_event[0x1]; + u8 reserved_at_1d3[0x2]; + u8 fpga[0x1]; u8 rol_s[0x1]; u8 rol_g[0x1]; u8 reserved_at_1d8[0x1]; @@ -949,7 +969,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2a0[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_at_2c0[0x10]; + u8 max_flow_counter_31_16[0x10]; u8 max_wqe_sz_sq_dc[0x10]; u8 reserved_at_2e0[0x7]; @@ -967,7 +987,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_340[0x8]; u8 log_max_flow_counter_bulk[0x8]; - u8 max_flow_counter[0x10]; + u8 max_flow_counter_15_0[0x10]; u8 reserved_at_360[0x3]; @@ -1002,7 +1022,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 reserved_at_3e1[0xa]; + u8 disable_local_lb[0x1]; + u8 reserved_at_3e2[0x9]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; u8 log_max_current_mc_list[0x5]; @@ -1057,9 +1078,7 @@ struct mlx5_ifc_dest_format_struct_bits { }; struct mlx5_ifc_flow_counter_list_bits { - u8 clear[0x1]; - u8 num_of_counters[0xf]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_20[0x20]; }; @@ -1173,7 +1192,8 @@ struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { u8 reserved_at_c0[0x12]; u8 cnp_dscp[0x6]; - u8 reserved_at_d8[0x5]; + u8 reserved_at_d8[0x4]; + u8 cnp_prio_mode[0x1]; u8 cnp_802p_prio[0x3]; u8 reserved_at_e0[0x720]; @@ -1526,7 +1546,17 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { u8 port_transmit_wait_low[0x20]; - u8 reserved_at_40[0x780]; + u8 reserved_at_40[0x100]; + + u8 rx_buffer_almost_full_high[0x20]; + + u8 rx_buffer_almost_full_low[0x20]; + + u8 rx_buffer_full_high[0x20]; + + u8 rx_buffer_full_low[0x20]; + + u8 reserved_at_1c0[0x600]; }; struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { @@ -1842,7 +1872,19 @@ struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits { u8 crc_error_tlp[0x20]; - u8 reserved_at_140[0x680]; + u8 tx_overflow_buffer_pkt_high[0x20]; + + u8 tx_overflow_buffer_pkt_low[0x20]; + + u8 outbound_stalled_reads[0x20]; + + u8 outbound_stalled_writes[0x20]; + + u8 outbound_stalled_reads_events[0x20]; + + u8 outbound_stalled_writes_events[0x20]; + + u8 reserved_at_200[0x5c0]; }; struct mlx5_ifc_cmd_inter_comp_event_bits { @@ -2001,6 +2043,10 @@ enum { }; enum { + MLX5_QPC_OFFLOAD_TYPE_RNDV = 0x1, +}; + +enum { MLX5_QPC_END_PADDING_MODE_SCATTER_AS_IS = 0x0, MLX5_QPC_END_PADDING_MODE_PAD_TO_CACHE_LINE_ALIGNMENT = 0x1, }; @@ -2043,7 +2089,8 @@ struct mlx5_ifc_qpc_bits { u8 st[0x8]; u8 reserved_at_10[0x3]; u8 pm_state[0x2]; - u8 reserved_at_15[0x7]; + u8 reserved_at_15[0x3]; + u8 offload_type[0x4]; u8 end_padding_mode[0x2]; u8 reserved_at_1e[0x2]; @@ -2194,6 +2241,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; + struct mlx5_ifc_fpga_cap_bits fpga_cap; u8 reserved_at_0[0x8000]; }; @@ -2422,11 +2470,12 @@ struct mlx5_ifc_sqc_bits { u8 cd_master[0x1]; u8 fre[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_at_4[0x1]; + u8 allow_multi_pkt_send_wqe[0x1]; u8 min_wqe_inline_mode[0x3]; u8 state[0x4]; u8 reg_umr[0x1]; - u8 reserved_at_d[0x13]; + u8 allow_swp[0x1]; + u8 reserved_at_e[0x12]; u8 reserved_at_20[0x8]; u8 user_index[0x18]; @@ -2499,7 +2548,7 @@ enum { struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; - u8 reserved_at_1[0x1]; + u8 delay_drop_en[0x1]; u8 scatter_fcs[0x1]; u8 vsd[0x1]; u8 mem_rq_type[0x4]; @@ -2546,7 +2595,9 @@ struct mlx5_ifc_rmpc_bits { struct mlx5_ifc_nic_vport_context_bits { u8 reserved_at_0[0x5]; u8 min_wqe_inline_mode[0x3]; - u8 reserved_at_8[0x17]; + u8 reserved_at_8[0x15]; + u8 disable_mc_local_lb[0x1]; + u8 disable_uc_local_lb[0x1]; u8 roce_en[0x1]; u8 arm_change_event[0x1]; @@ -2984,7 +3035,7 @@ struct mlx5_ifc_xrqc_bits { struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context; - u8 reserved_at_180[0x880]; + u8 reserved_at_180[0x280]; struct mlx5_ifc_wq_bits wq; }; @@ -3089,18 +3140,25 @@ struct mlx5_ifc_tsar_element_bits { u8 reserved_at_10[0x10]; }; +enum { + MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_SUCCESS = 0x0, + MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL = 0x1, +}; + struct mlx5_ifc_teardown_hca_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x3f]; + + u8 force_state[0x1]; }; enum { MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, - MLX5_TEARDOWN_HCA_IN_PROFILE_PANIC_CLOSE = 0x1, + MLX5_TEARDOWN_HCA_IN_PROFILE_FORCE_CLOSE = 0x1, }; struct mlx5_ifc_teardown_hca_in_bits { @@ -3924,7 +3982,47 @@ struct mlx5_ifc_query_q_counter_out_bits { u8 local_ack_timeout_err[0x20]; - u8 reserved_at_320[0x4e0]; + u8 reserved_at_320[0xa0]; + + u8 resp_local_length_error[0x20]; + + u8 req_local_length_error[0x20]; + + u8 resp_local_qp_error[0x20]; + + u8 local_operation_error[0x20]; + + u8 resp_local_protection[0x20]; + + u8 req_local_protection[0x20]; + + u8 resp_cqe_error[0x20]; + + u8 req_cqe_error[0x20]; + + u8 req_mw_binding[0x20]; + + u8 req_bad_response[0x20]; + + u8 req_remote_invalid_request[0x20]; + + u8 resp_remote_invalid_request[0x20]; + + u8 req_remote_access_errors[0x20]; + + u8 resp_remote_access_errors[0x20]; + + u8 req_remote_operation_errors[0x20]; + + u8 req_transport_retries_exceeded[0x20]; + + u8 cq_overflow[0x20]; + + u8 resp_cqe_flush_error[0x20]; + + u8 req_cqe_flush_error[0x20]; + + u8 reserved_at_620[0x1e0]; }; struct mlx5_ifc_query_q_counter_in_bits { @@ -4380,8 +4478,7 @@ struct mlx5_ifc_query_flow_counter_in_bits { u8 reserved_at_c1[0xf]; u8 num_of_counters[0x10]; - u8 reserved_at_e0[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; }; struct mlx5_ifc_query_esw_vport_context_out_bits { @@ -4606,6 +4703,7 @@ enum { MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0 = 0x14, MLX5_ACTION_IN_FIELD_OUT_SIPV4 = 0x15, MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16, + MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { @@ -5205,7 +5303,9 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits { }; struct mlx5_ifc_modify_nic_vport_field_select_bits { - u8 reserved_at_0[0x16]; + u8 reserved_at_0[0x14]; + u8 disable_uc_local_lb[0x1]; + u8 disable_mc_local_lb[0x1]; u8 node_guid[0x1]; u8 port_guid[0x1]; u8 min_inline[0x1]; @@ -5823,6 +5923,28 @@ struct mlx5_ifc_destroy_rq_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_set_delay_drop_params_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x10]; + u8 delay_drop_timeout[0x10]; +}; + +struct mlx5_ifc_set_delay_drop_params_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_destroy_rmp_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -6248,8 +6370,7 @@ struct mlx5_ifc_dealloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; @@ -6622,6 +6743,24 @@ struct mlx5_ifc_create_flow_table_out_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_flow_table_context_bits { + u8 encap_en[0x1]; + u8 decap_en[0x1]; + u8 reserved_at_2[0x2]; + u8 table_miss_action[0x4]; + u8 level[0x8]; + u8 reserved_at_10[0x8]; + u8 log_size[0x8]; + + u8 reserved_at_20[0x8]; + u8 table_miss_id[0x18]; + + u8 reserved_at_40[0x8]; + u8 lag_master_next_table_id[0x18]; + + u8 reserved_at_60[0xe0]; +}; + struct mlx5_ifc_create_flow_table_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -6640,21 +6779,7 @@ struct mlx5_ifc_create_flow_table_in_bits { u8 reserved_at_a0[0x20]; - u8 encap_en[0x1]; - u8 decap_en[0x1]; - u8 reserved_at_c2[0x2]; - u8 table_miss_mode[0x4]; - u8 level[0x8]; - u8 reserved_at_d0[0x8]; - u8 log_size[0x8]; - - u8 reserved_at_e0[0x8]; - u8 table_miss_id[0x18]; - - u8 reserved_at_100[0x8]; - u8 lag_master_next_table_id[0x18]; - - u8 reserved_at_120[0x80]; + struct mlx5_ifc_flow_table_context_bits flow_table_context; }; struct mlx5_ifc_create_flow_group_out_bits { @@ -7070,8 +7195,7 @@ struct mlx5_ifc_alloc_flow_counter_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; @@ -7286,7 +7410,8 @@ struct mlx5_ifc_ptys_reg_bits { u8 ib_link_width_oper[0x10]; u8 ib_proto_oper[0x10]; - u8 reserved_at_160[0x20]; + u8 reserved_at_160[0x1c]; + u8 connector_type[0x4]; u8 eth_proto_lp_advertise[0x20]; @@ -7689,8 +7814,11 @@ struct mlx5_ifc_peir_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x7e]; + u8 reserved_at_0[0x7b]; + u8 rx_buffer_fullness_counters[0x1]; + u8 ptys_connector_type[0x1]; + u8 reserved_at_7d[0x1]; u8 ppcnt_discard_group[0x1]; u8 ppcnt_statistical_group[0x1]; }; @@ -7718,11 +7846,26 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x7f]; - + u8 reserved_at_0[0x7b]; + u8 pcie_outbound_stalled[0x1]; + u8 tx_overflow_buffer_pkt[0x1]; + u8 mtpps_enh_out_per_adj[0x1]; + u8 mtpps_fs[0x1]; u8 pcie_performance_group[0x1]; }; +struct mlx5_ifc_mcam_access_reg_bits { + u8 reserved_at_0[0x1c]; + u8 mcda[0x1]; + u8 mcc[0x1]; + u8 mcqi[0x1]; + u8 reserved_at_1f[0x1]; + + u8 regs_95_to_64[0x20]; + u8 regs_63_to_32[0x20]; + u8 regs_31_to_0[0x20]; +}; + struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_0[0x8]; u8 feature_group[0x8]; @@ -7732,6 +7875,7 @@ struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_20[0x20]; union { + struct mlx5_ifc_mcam_access_reg_bits access_regs; u8 reserved_at_0[0x80]; } mng_access_reg_cap_mask; @@ -8115,7 +8259,8 @@ struct mlx5_ifc_mtpps_reg_bits { u8 reserved_at_78[0x4]; u8 cap_pin_4_mode[0x4]; - u8 reserved_at_80[0x80]; + u8 field_select[0x20]; + u8 reserved_at_a0[0x60]; u8 enable[0x1]; u8 reserved_at_101[0xb]; @@ -8130,8 +8275,9 @@ struct mlx5_ifc_mtpps_reg_bits { u8 out_pulse_duration[0x10]; u8 out_periodic_adjustment[0x10]; + u8 enhanced_out_periodic_adjustment[0x20]; - u8 reserved_at_1a0[0x60]; + u8 reserved_at_1c0[0x20]; }; struct mlx5_ifc_mtppse_reg_bits { @@ -8143,6 +8289,85 @@ struct mlx5_ifc_mtppse_reg_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_mcqi_cap_bits { + u8 supported_info_bitmask[0x20]; + + u8 component_size[0x20]; + + u8 max_component_size[0x20]; + + u8 log_mcda_word_size[0x4]; + u8 reserved_at_64[0xc]; + u8 mcda_max_write_size[0x10]; + + u8 rd_en[0x1]; + u8 reserved_at_81[0x1]; + u8 match_chip_id[0x1]; + u8 match_psid[0x1]; + u8 check_user_timestamp[0x1]; + u8 match_base_guid_mac[0x1]; + u8 reserved_at_86[0x1a]; +}; + +struct mlx5_ifc_mcqi_reg_bits { + u8 read_pending_component[0x1]; + u8 reserved_at_1[0xf]; + u8 component_index[0x10]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x1b]; + u8 info_type[0x5]; + + u8 info_size[0x20]; + + u8 offset[0x20]; + + u8 reserved_at_a0[0x10]; + u8 data_size[0x10]; + + u8 data[0][0x20]; +}; + +struct mlx5_ifc_mcc_reg_bits { + u8 reserved_at_0[0x4]; + u8 time_elapsed_since_last_cmd[0xc]; + u8 reserved_at_10[0x8]; + u8 instruction[0x8]; + + u8 reserved_at_20[0x10]; + u8 component_index[0x10]; + + u8 reserved_at_40[0x8]; + u8 update_handle[0x18]; + + u8 handle_owner_type[0x4]; + u8 handle_owner_host_id[0x4]; + u8 reserved_at_68[0x1]; + u8 control_progress[0x7]; + u8 error_code[0x8]; + u8 reserved_at_78[0x4]; + u8 control_state[0x4]; + + u8 component_size[0x20]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_mcda_reg_bits { + u8 reserved_at_0[0x8]; + u8 update_handle[0x18]; + + u8 offset[0x20]; + + u8 reserved_at_40[0x10]; + u8 size[0x10]; + + u8 reserved_at_60[0x20]; + + u8 data[0][0x20]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -8190,6 +8415,12 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_sltp_reg_bits sltp_reg; struct mlx5_ifc_mtpps_reg_bits mtpps_reg; struct mlx5_ifc_mtppse_reg_bits mtppse_reg; + struct mlx5_ifc_fpga_access_reg_bits fpga_access_reg; + struct mlx5_ifc_fpga_ctrl_bits fpga_ctrl_bits; + struct mlx5_ifc_fpga_cap_bits fpga_cap_bits; + struct mlx5_ifc_mcqi_reg_bits mcqi_reg; + struct mlx5_ifc_mcc_reg_bits mcc_reg; + struct mlx5_ifc_mcda_reg_bits mcda_reg; u8 reserved_at_0[0x60e0]; }; @@ -8270,17 +8501,7 @@ struct mlx5_ifc_modify_flow_table_in_bits { u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_at_c0[0x4]; - u8 table_miss_mode[0x4]; - u8 reserved_at_c8[0x18]; - - u8 reserved_at_e0[0x8]; - u8 table_miss_id[0x18]; - - u8 reserved_at_100[0x8]; - u8 lag_master_next_table_id[0x18]; - - u8 reserved_at_120[0x80]; + struct mlx5_ifc_flow_table_context_bits flow_table_context; }; struct mlx5_ifc_ets_tcn_config_reg_bits { diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h new file mode 100644 index 000000000000..255a88d08078 --- /dev/null +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -0,0 +1,432 @@ +/* + * Copyright (c) 2017, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef MLX5_IFC_FPGA_H +#define MLX5_IFC_FPGA_H + +enum { + MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX = 0x2c9, +}; + +enum { + MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, +}; + +struct mlx5_ifc_fpga_shell_caps_bits { + u8 max_num_qps[0x10]; + u8 reserved_at_10[0x8]; + u8 total_rcv_credits[0x8]; + + u8 reserved_at_20[0xe]; + u8 qp_type[0x2]; + u8 reserved_at_30[0x5]; + u8 rae[0x1]; + u8 rwe[0x1]; + u8 rre[0x1]; + u8 reserved_at_38[0x4]; + u8 dc[0x1]; + u8 ud[0x1]; + u8 uc[0x1]; + u8 rc[0x1]; + + u8 reserved_at_40[0x1a]; + u8 log_ddr_size[0x6]; + + u8 max_fpga_qp_msg_size[0x20]; + + u8 reserved_at_80[0x180]; +}; + +struct mlx5_ifc_fpga_cap_bits { + u8 fpga_id[0x8]; + u8 fpga_device[0x18]; + + u8 register_file_ver[0x20]; + + u8 fpga_ctrl_modify[0x1]; + u8 reserved_at_41[0x5]; + u8 access_reg_query_mode[0x2]; + u8 reserved_at_48[0x6]; + u8 access_reg_modify_mode[0x2]; + u8 reserved_at_50[0x10]; + + u8 reserved_at_60[0x20]; + + u8 image_version[0x20]; + + u8 image_date[0x20]; + + u8 image_time[0x20]; + + u8 shell_version[0x20]; + + u8 reserved_at_100[0x80]; + + struct mlx5_ifc_fpga_shell_caps_bits shell_caps; + + u8 reserved_at_380[0x8]; + u8 ieee_vendor_id[0x18]; + + u8 sandbox_product_version[0x10]; + u8 sandbox_product_id[0x10]; + + u8 sandbox_basic_caps[0x20]; + + u8 reserved_at_3e0[0x10]; + u8 sandbox_extended_caps_len[0x10]; + + u8 sandbox_extended_caps_addr[0x40]; + + u8 fpga_ddr_start_addr[0x40]; + + u8 fpga_cr_space_start_addr[0x40]; + + u8 fpga_ddr_size[0x20]; + + u8 fpga_cr_space_size[0x20]; + + u8 reserved_at_500[0x300]; +}; + +enum { + MLX5_FPGA_CTRL_OPERATION_LOAD = 0x1, + MLX5_FPGA_CTRL_OPERATION_RESET = 0x2, + MLX5_FPGA_CTRL_OPERATION_FLASH_SELECT = 0x3, + MLX5_FPGA_CTRL_OPERATION_SANDBOX_BYPASS_ON = 0x4, + MLX5_FPGA_CTRL_OPERATION_SANDBOX_BYPASS_OFF = 0x5, + MLX5_FPGA_CTRL_OPERATION_RESET_SANDBOX = 0x6, +}; + +struct mlx5_ifc_fpga_ctrl_bits { + u8 reserved_at_0[0x8]; + u8 operation[0x8]; + u8 reserved_at_10[0x8]; + u8 status[0x8]; + + u8 reserved_at_20[0x8]; + u8 flash_select_admin[0x8]; + u8 reserved_at_30[0x8]; + u8 flash_select_oper[0x8]; + + u8 reserved_at_40[0x40]; +}; + +enum { + MLX5_FPGA_ERROR_EVENT_SYNDROME_CORRUPTED_DDR = 0x1, + MLX5_FPGA_ERROR_EVENT_SYNDROME_FLASH_TIMEOUT = 0x2, + MLX5_FPGA_ERROR_EVENT_SYNDROME_INTERNAL_LINK_ERROR = 0x3, + MLX5_FPGA_ERROR_EVENT_SYNDROME_WATCHDOG_FAILURE = 0x4, + MLX5_FPGA_ERROR_EVENT_SYNDROME_I2C_FAILURE = 0x5, + MLX5_FPGA_ERROR_EVENT_SYNDROME_IMAGE_CHANGED = 0x6, + MLX5_FPGA_ERROR_EVENT_SYNDROME_TEMPERATURE_CRITICAL = 0x7, +}; + +struct mlx5_ifc_fpga_error_event_bits { + u8 reserved_at_0[0x40]; + + u8 reserved_at_40[0x18]; + u8 syndrome[0x8]; + + u8 reserved_at_60[0x80]; +}; + +#define MLX5_FPGA_ACCESS_REG_SIZE_MAX 64 + +struct mlx5_ifc_fpga_access_reg_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x10]; + u8 size[0x10]; + + u8 address[0x40]; + + u8 data[0][0x8]; +}; + +enum mlx5_ifc_fpga_qp_state { + MLX5_FPGA_QPC_STATE_INIT = 0x0, + MLX5_FPGA_QPC_STATE_ACTIVE = 0x1, + MLX5_FPGA_QPC_STATE_ERROR = 0x2, +}; + +enum mlx5_ifc_fpga_qp_type { + MLX5_FPGA_QPC_QP_TYPE_SHELL_QP = 0x0, + MLX5_FPGA_QPC_QP_TYPE_SANDBOX_QP = 0x1, +}; + +enum mlx5_ifc_fpga_qp_service_type { + MLX5_FPGA_QPC_ST_RC = 0x0, +}; + +struct mlx5_ifc_fpga_qpc_bits { + u8 state[0x4]; + u8 reserved_at_4[0x1b]; + u8 qp_type[0x1]; + + u8 reserved_at_20[0x4]; + u8 st[0x4]; + u8 reserved_at_28[0x10]; + u8 traffic_class[0x8]; + + u8 ether_type[0x10]; + u8 prio[0x3]; + u8 dei[0x1]; + u8 vid[0xc]; + + u8 reserved_at_60[0x20]; + + u8 reserved_at_80[0x8]; + u8 next_rcv_psn[0x18]; + + u8 reserved_at_a0[0x8]; + u8 next_send_psn[0x18]; + + u8 reserved_at_c0[0x10]; + u8 pkey[0x10]; + + u8 reserved_at_e0[0x8]; + u8 remote_qpn[0x18]; + + u8 reserved_at_100[0x15]; + u8 rnr_retry[0x3]; + u8 reserved_at_118[0x5]; + u8 retry_count[0x3]; + + u8 reserved_at_120[0x20]; + + u8 reserved_at_140[0x10]; + u8 remote_mac_47_32[0x10]; + + u8 remote_mac_31_0[0x20]; + + u8 remote_ip[16][0x8]; + + u8 reserved_at_200[0x40]; + + u8 reserved_at_240[0x10]; + u8 fpga_mac_47_32[0x10]; + + u8 fpga_mac_31_0[0x20]; + + u8 fpga_ip[16][0x8]; +}; + +struct mlx5_ifc_fpga_create_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_create_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_modify_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 field_select[0x20]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_modify_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_fpga_query_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_fpga_query_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_query_qp_counters_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 clear[0x1]; + u8 reserved_at_41[0x7]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_fpga_query_qp_counters_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 rx_ack_packets[0x40]; + + u8 rx_send_packets[0x40]; + + u8 tx_ack_packets[0x40]; + + u8 tx_send_packets[0x40]; + + u8 rx_total_drop[0x40]; + + u8 reserved_at_1c0[0x1c0]; +}; + +struct mlx5_ifc_fpga_destroy_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_fpga_destroy_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_ipsec_extended_cap_bits { + u8 encapsulation[0x20]; + + u8 reserved_0[0x15]; + u8 ipv4_fragment[0x1]; + u8 ipv6[0x1]; + u8 esn[0x1]; + u8 lso[0x1]; + u8 transport_and_tunnel_mode[0x1]; + u8 tunnel_mode[0x1]; + u8 transport_mode[0x1]; + u8 ah_esp[0x1]; + u8 esp[0x1]; + u8 ah[0x1]; + u8 ipv4_options[0x1]; + + u8 auth_alg[0x20]; + + u8 enc_alg[0x20]; + + u8 sa_cap[0x20]; + + u8 reserved_1[0x10]; + u8 number_of_ipsec_counters[0x10]; + + u8 ipsec_counters_addr_low[0x20]; + u8 ipsec_counters_addr_high[0x20]; +}; + +struct mlx5_ifc_ipsec_counters_bits { + u8 dec_in_packets[0x40]; + + u8 dec_out_packets[0x40]; + + u8 dec_bypass_packets[0x40]; + + u8 enc_in_packets[0x40]; + + u8 enc_out_packets[0x40]; + + u8 enc_bypass_packets[0x40]; + + u8 drop_dec_packets[0x40]; + + u8 failed_auth_dec_packets[0x40]; + + u8 drop_enc_packets[0x40]; + + u8 success_add_sa[0x40]; + + u8 fail_add_sa[0x40]; + + u8 success_delete_sa[0x40]; + + u8 fail_delete_sa[0x40]; + + u8 dropped_cmd[0x40]; +}; + +#endif /* MLX5_IFC_FPGA_H */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index e527732fb31b..c57d4b7de3a8 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -92,6 +92,19 @@ enum mlx5e_link_mode { MLX5E_LINK_MODES_NUMBER, }; +enum mlx5e_connector_type { + MLX5E_PORT_UNKNOWN = 0, + MLX5E_PORT_NONE = 1, + MLX5E_PORT_TP = 2, + MLX5E_PORT_AUI = 3, + MLX5E_PORT_BNC = 4, + MLX5E_PORT_MII = 5, + MLX5E_PORT_FIBRE = 6, + MLX5E_PORT_DA = 7, + MLX5E_PORT_OTHER = 8, + MLX5E_CONNECTOR_TYPE_NUMBER, +}; + #define MLX5E_PROT_MASK(link_mode) (1 << link_mode) #define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index bef80d0a0e30..66d19b611fe4 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_OPCODE_MASK 0xff #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 -#define MLX5_WQE_AV_EXT 0x80000000 enum { MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, @@ -225,10 +224,20 @@ enum { MLX5_ETH_WQE_INSERT_VLAN = 1 << 15, }; +enum { + MLX5_ETH_WQE_SWP_INNER_L3_IPV6 = 1 << 0, + MLX5_ETH_WQE_SWP_INNER_L4_UDP = 1 << 1, + MLX5_ETH_WQE_SWP_OUTER_L3_IPV6 = 1 << 4, + MLX5_ETH_WQE_SWP_OUTER_L4_UDP = 1 << 5, +}; + struct mlx5_wqe_eth_seg { - u8 rsvd0[4]; + u8 swp_outer_l4_offset; + u8 swp_outer_l3_offset; + u8 swp_inner_l4_offset; + u8 swp_inner_l3_offset; u8 cs_flags; - u8 rsvd1; + u8 swp_flags; __be16 mss; __be32 rsvd2; union { @@ -551,6 +560,9 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev, int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, u32 *out, int outlen); +int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev, + u32 timeout_usec); + int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn); int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn); void mlx5_init_qp_table(struct mlx5_core_dev *dev); @@ -569,8 +581,6 @@ int mlx5_core_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id); int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id); int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id, int reset, void *out, int out_size); -int mlx5_core_query_out_of_buffer(struct mlx5_core_dev *dev, u16 counter_id, - u32 *out_of_buffer); static inline const char *mlx5_qp_type_str(int type) { diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 1cde0fd53f90..24ff23e27c8a 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -38,6 +38,7 @@ enum { MLX5_SRQ_FLAG_ERR = (1 << 0), MLX5_SRQ_FLAG_WQ_SIG = (1 << 1), + MLX5_SRQ_FLAG_RNDV = (1 << 2), }; struct mlx5_srq_attr { @@ -56,6 +57,10 @@ struct mlx5_srq_attr { u32 user_index; u64 db_record; __be64 *pas; + u32 tm_log_list_size; + u32 tm_next_tag; + u32 tm_hw_phase_cnt; + u32 tm_sw_phase_cnt; }; struct mlx5_core_dev; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 656c70b65dd2..aaa0bb9e7655 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -114,5 +114,6 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev, u8 other_vport, u8 port_num, int vf, struct mlx5_hca_vport_context *req); - +int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable); +int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status); #endif /* __MLX5_VPORT_H__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 6f543a47fc92..f8c10d336e42 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -23,6 +23,7 @@ #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page_ref.h> +#include <linux/memremap.h> struct mempolicy; struct anon_vma; @@ -189,7 +190,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ -#define VM_ARCH_2 0x02000000 +#define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY @@ -208,10 +209,12 @@ extern unsigned int kobjsize(const void *objp); #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) +#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #if defined(CONFIG_X86) @@ -235,9 +238,11 @@ extern unsigned int kobjsize(const void *objp); # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -#if defined(CONFIG_X86) +#if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_ARCH_2 +# define VM_MPX VM_HIGH_ARCH_BIT_4 +#else +# define VM_MPX VM_NONE #endif #ifndef VM_GROWSUP @@ -795,6 +800,28 @@ static inline bool is_zone_device_page(const struct page *page) } #endif +#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) +void put_zone_device_private_or_public_page(struct page *page); +DECLARE_STATIC_KEY_FALSE(device_private_key); +#define IS_HMM_ENABLED static_branch_unlikely(&device_private_key) +static inline bool is_device_private_page(const struct page *page); +static inline bool is_device_public_page(const struct page *page); +#else /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ +static inline void put_zone_device_private_or_public_page(struct page *page) +{ +} +#define IS_HMM_ENABLED 0 +static inline bool is_device_private_page(const struct page *page) +{ + return false; +} +static inline bool is_device_public_page(const struct page *page) +{ + return false; +} +#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ + + static inline void get_page(struct page *page) { page = compound_head(page); @@ -810,6 +837,18 @@ static inline void put_page(struct page *page) { page = compound_head(page); + /* + * For private device pages we need to catch refcount transition from + * 2 to 1, when refcount reach one it means the private device page is + * free and we need to inform the device driver through callback. See + * include/linux/memremap.h and HMM for details. + */ + if (IS_HMM_ENABLED && unlikely(is_device_private_page(page) || + unlikely(is_device_public_page(page)))) { + put_zone_device_private_or_public_page(page); + return; + } + if (put_page_testzero(page)) __put_page(page); } @@ -1195,8 +1234,10 @@ struct zap_details { pgoff_t last_index; /* Highest page->index to unmap */ }; -struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte); +struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte, bool with_public_device); +#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false) + struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); @@ -1260,6 +1301,7 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + unsigned long *start, unsigned long *end, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); @@ -1992,13 +2034,13 @@ extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, - struct rb_root *root); + struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, - struct rb_root *root); + struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, - struct rb_root *root); -struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root *root, + struct rb_root_cached *root); +struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); @@ -2008,11 +2050,12 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, - struct rb_root *root); + struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, - struct rb_root *root); -struct anon_vma_chain *anon_vma_interval_tree_iter_first( - struct rb_root *root, unsigned long start, unsigned long last); + struct rb_root_cached *root); +struct anon_vma_chain * +anon_vma_interval_tree_iter_first(struct rb_root_cached *root, + unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB @@ -2171,7 +2214,7 @@ extern void filemap_map_pages(struct vm_fault *vmf, extern int filemap_page_mkwrite(struct vm_fault *vmf); /* mm/page-writeback.c */ -int write_one_page(struct page *page, int wait); +int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); /* readahead.c */ @@ -2293,6 +2336,8 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); +int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); @@ -2505,7 +2550,7 @@ enum mf_action_page_type { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, - unsigned long addr, + unsigned long addr_hint, unsigned int pages_per_huge_page); extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e030a68ead7e..25438b2b6f22 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -126,4 +126,10 @@ static __always_inline enum lru_list page_lru(struct page *page) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) +#ifdef arch_unmap_kpfn +extern void arch_unmap_kpfn(unsigned long pfn); +#else +static __always_inline void arch_unmap_kpfn(unsigned long pfn) { } +#endif + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 45cdb27791a3..46f4ecf5479a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -23,6 +23,7 @@ struct address_space; struct mem_cgroup; +struct hmm; /* * Each physical page in the system has a struct page associated with @@ -335,6 +336,7 @@ struct vm_area_struct { struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ + atomic_long_t swap_readahead_info; #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif @@ -342,7 +344,7 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; -}; +} __randomize_layout; struct core_thread { struct task_struct *task; @@ -487,20 +489,27 @@ struct mm_struct { /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; #endif -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) /* * An operation with batched TLB flushing is going on. Anything that * can move process memory needs to flush the TLB when moving a * PROT_NONE or PROT_NUMA mapped page. */ - bool tlb_flush_pending; + atomic_t tlb_flush_pending; +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH + /* See flush_tlb_batched_pending() */ + bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; -}; + +#if IS_ENABLED(CONFIG_HMM) + /* HMM needs to track a few things per mm */ + struct hmm *hmm; +#endif +} __randomize_layout; extern struct mm_struct init_mm; @@ -518,46 +527,95 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return mm->cpu_vm_mask_var; } -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) -/* - * Memory barriers to keep this state in sync are graciously provided by - * the page table locks, outside of which no page table modifications happen. - * The barriers below prevent the compiler from re-ordering the instructions - * around the memory barriers that are already present in the code. - */ -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +struct mmu_gather; +extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end); +extern void tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end); + +static inline void init_tlb_flush_pending(struct mm_struct *mm) { - barrier(); - return mm->tlb_flush_pending; + atomic_set(&mm->tlb_flush_pending, 0); } -static inline void set_tlb_flush_pending(struct mm_struct *mm) -{ - mm->tlb_flush_pending = true; +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); /* - * Guarantee that the tlb_flush_pending store does not leak into the - * critical section updating the page tables + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * atomic_inc(&mm->tlb_flush_pending); + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * atomic_dec(&mm->tlb_flush_pending); + * + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. */ - smp_mb__before_spinlock(); } -/* Clearing is done after a TLB flush, which also provides a barrier. */ -static inline void clear_tlb_flush_pending(struct mm_struct *mm) + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) { - barrier(); - mm->tlb_flush_pending = false; + /* + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. + */ + atomic_dec(&mm->tlb_flush_pending); } -#else + static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { - return false; -} -static inline void set_tlb_flush_pending(struct mm_struct *mm) -{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); } -static inline void clear_tlb_flush_pending(struct mm_struct *mm) + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; } -#endif struct vm_fault; diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 136dfdf63ba1..fc412fbd80bd 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -14,6 +14,10 @@ #include <asm/page.h> +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +#include <asm/tlbbatch.h> +#endif + #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) @@ -67,12 +71,15 @@ struct page_frag { struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* - * Each bit set is a CPU that potentially has a TLB entry for one of - * the PFNs being flushed. See set_tlb_ubc_flush_pending(). + * The arch code makes the following promise: generic code can modify a + * PTE, then call arch_tlbbatch_add_mm() (which internally provides all + * needed barriers), then call arch_tlbbatch_flush(), and the entries + * will be flushed on all CPUs by the time that arch_tlbbatch_flush() + * returns. */ - struct cpumask cpumask; + struct arch_tlbflush_unmap_batch arch; - /* True if any bit in cpumask is set */ + /* True if a flush is needed. */ bool flush_required; /* diff --git a/include/linux/mman.h b/include/linux/mman.h index 634c4c51fe3a..c8367041fafd 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -22,7 +22,7 @@ unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { - __percpu_counter_add(&vm_committed_as, pages, vm_committed_as_batch); + percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index aad015e0152b..279b39008a33 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -29,8 +29,8 @@ struct mmc_csd { unsigned char structure; unsigned char mmca_vsn; unsigned short cmdclass; - unsigned short tacc_clks; - unsigned int tacc_ns; + unsigned short taac_clks; + unsigned int taac_ns; unsigned int c_size; unsigned int r2w_factor; unsigned int max_dtr; @@ -305,9 +305,7 @@ struct mmc_card { struct mmc_part part[MMC_NUM_PHY_PARTITION]; /* physical partitions */ unsigned int nr_parts; - struct mmc_queue_req *mqrq; /* Shared queue structure */ unsigned int bouncesz; /* Bounce buffer size */ - int qdepth; /* Shared queue depth */ }; static inline bool mmc_large_sector(struct mmc_card *card) diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index a0c63ea28796..927519385482 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -122,11 +122,18 @@ struct mmc_data { unsigned int timeout_clks; /* data timeout (in clocks) */ unsigned int blksz; /* data block size */ unsigned int blocks; /* number of blocks */ + unsigned int blk_addr; /* block address */ int error; /* data error */ unsigned int flags; -#define MMC_DATA_WRITE (1 << 8) -#define MMC_DATA_READ (1 << 9) +#define MMC_DATA_WRITE BIT(8) +#define MMC_DATA_READ BIT(9) +/* Extra flags used by CQE */ +#define MMC_DATA_QBR BIT(10) /* CQE queue barrier*/ +#define MMC_DATA_PRIO BIT(11) /* CQE high priority */ +#define MMC_DATA_REL_WR BIT(12) /* Reliable write */ +#define MMC_DATA_DAT_TAG BIT(13) /* Tag request */ +#define MMC_DATA_FORCED_PRG BIT(14) /* Forced programming */ unsigned int bytes_xfered; @@ -149,18 +156,22 @@ struct mmc_request { struct completion completion; struct completion cmd_completion; void (*done)(struct mmc_request *);/* completion function */ + /* + * Notify uppers layers (e.g. mmc block driver) that recovery is needed + * due to an error associated with the mmc_request. Currently used only + * by CQE. + */ + void (*recovery_notifier)(struct mmc_request *); struct mmc_host *host; /* Allow other commands during this ongoing data transfer or busy wait */ bool cap_cmd_during_tfr; + + int tag; }; struct mmc_card; -struct mmc_async_req; -struct mmc_async_req *mmc_start_areq(struct mmc_host *host, - struct mmc_async_req *areq, - enum mmc_blk_status *ret_stat); void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 21385ac0c9b1..f3f2d07feb2a 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -130,6 +130,7 @@ struct mmc_host_ops { int (*get_cd)(struct mmc_host *host); void (*enable_sdio_irq)(struct mmc_host *host, int enable); + void (*ack_sdio_irq)(struct mmc_host *host); /* optional callback for HC quirks */ void (*init_card)(struct mmc_host *host, struct mmc_card *card); @@ -161,6 +162,50 @@ struct mmc_host_ops { unsigned int direction, int blk_size); }; +struct mmc_cqe_ops { + /* Allocate resources, and make the CQE operational */ + int (*cqe_enable)(struct mmc_host *host, struct mmc_card *card); + /* Free resources, and make the CQE non-operational */ + void (*cqe_disable)(struct mmc_host *host); + /* + * Issue a read, write or DCMD request to the CQE. Also deal with the + * effect of ->cqe_off(). + */ + int (*cqe_request)(struct mmc_host *host, struct mmc_request *mrq); + /* Free resources (e.g. DMA mapping) associated with the request */ + void (*cqe_post_req)(struct mmc_host *host, struct mmc_request *mrq); + /* + * Prepare the CQE and host controller to accept non-CQ commands. There + * is no corresponding ->cqe_on(), instead ->cqe_request() is required + * to deal with that. + */ + void (*cqe_off)(struct mmc_host *host); + /* + * Wait for all CQE tasks to complete. Return an error if recovery + * becomes necessary. + */ + int (*cqe_wait_for_idle)(struct mmc_host *host); + /* + * Notify CQE that a request has timed out. Return false if the request + * completed or true if a timeout happened in which case indicate if + * recovery is needed. + */ + bool (*cqe_timeout)(struct mmc_host *host, struct mmc_request *mrq, + bool *recovery_needed); + /* + * Stop all CQE activity and prepare the CQE and host controller to + * accept recovery commands. + */ + void (*cqe_recovery_start)(struct mmc_host *host); + /* + * Clear the queue and call mmc_cqe_request_done() on all requests. + * Requests that errored will have the error set on the mmc_request + * (data->error or cmd->error for DCMD). Requests that did not error + * will have zero data bytes transferred. + */ + void (*cqe_recovery_finish)(struct mmc_host *host); +}; + struct mmc_async_req { /* active mmc request */ struct mmc_request *mrq; @@ -184,6 +229,7 @@ struct mmc_async_req { */ struct mmc_slot { int cd_irq; + bool cd_wake_enabled; void *handler_priv; }; @@ -270,9 +316,11 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ +#define MMC_CAP_NO_BOUNCE_BUFF (1 << 21) /* Disable bounce buffers on host */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ +#define MMC_CAP_CD_WAKE (1 << 28) /* Enable card detect wake */ #define MMC_CAP_CMD_DURING_TFR (1 << 29) /* Commands during data transfer */ #define MMC_CAP_CMD23 (1 << 30) /* CMD23 supported. */ #define MMC_CAP_HW_RESET (1 << 31) /* Hardware reset */ @@ -285,13 +333,8 @@ struct mmc_host { #define MMC_CAP2_HS200_1_2V_SDR (1 << 6) /* can support */ #define MMC_CAP2_HS200 (MMC_CAP2_HS200_1_8V_SDR | \ MMC_CAP2_HS200_1_2V_SDR) -#define MMC_CAP2_HC_ERASE_SZ (1 << 9) /* High-capacity erase size */ #define MMC_CAP2_CD_ACTIVE_HIGH (1 << 10) /* Card-detect signal active high */ #define MMC_CAP2_RO_ACTIVE_HIGH (1 << 11) /* Write-protect signal active high */ -#define MMC_CAP2_PACKED_RD (1 << 12) /* Allow packed read */ -#define MMC_CAP2_PACKED_WR (1 << 13) /* Allow packed write */ -#define MMC_CAP2_PACKED_CMD (MMC_CAP2_PACKED_RD | \ - MMC_CAP2_PACKED_WR) #define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14) /* Don't power up before scan */ #define MMC_CAP2_HS400_1_8V (1 << 15) /* Can support HS400 1.8V */ #define MMC_CAP2_HS400_1_2V (1 << 16) /* Can support HS400 1.2V */ @@ -304,6 +347,8 @@ struct mmc_host { #define MMC_CAP2_HS400_ES (1 << 20) /* Host supports enhanced strobe */ #define MMC_CAP2_NO_SD (1 << 21) /* Do not send SD commands during initialization */ #define MMC_CAP2_NO_MMC (1 << 22) /* Do not send (e)MMC commands during initialization */ +#define MMC_CAP2_CQE (1 << 23) /* Has eMMC command queue engine */ +#define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ mmc_pm_flag_t pm_caps; /* supported pm features */ @@ -325,9 +370,6 @@ struct mmc_host { unsigned int use_spi_crc:1; unsigned int claimed:1; /* host exclusively claimed */ unsigned int bus_dead:1; /* bus has been released */ -#ifdef CONFIG_MMC_DEBUG - unsigned int removed:1; /* host is being removed */ -#endif unsigned int can_retune:1; /* re-tuning can be used */ unsigned int doing_retune:1; /* re-tuning in progress */ unsigned int retune_now:1; /* do re-tuning at next req */ @@ -358,6 +400,7 @@ struct mmc_host { unsigned int sdio_irqs; struct task_struct *sdio_irq_thread; + struct delayed_work sdio_irq_work; bool sdio_irq_pending; atomic_t sdio_irq_thread_abort; @@ -389,6 +432,13 @@ struct mmc_host { int dsr_req; /* DSR value is valid */ u32 dsr; /* optional driver stage (DSR) value */ + /* Command Queue Engine (CQE) support */ + const struct mmc_cqe_ops *cqe_ops; + void *cqe_private; + int cqe_qdepth; + bool cqe_enabled; + bool cqe_on; + unsigned long private[0] ____cacheline_aligned; }; @@ -428,6 +478,7 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host) } void sdio_run_irqs(struct mmc_host *host); +void sdio_signal_irq(struct mmc_host *host); #ifdef CONFIG_REGULATOR int mmc_regulator_get_ocrmask(struct regulator *supply); diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index b733eb404ffc..abacd5484bc0 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -39,6 +39,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 +#define SDIO_DEVICE_ID_CYPRESS_4373 0x4373 #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index c91b3bcd158f..7b2e31b1745a 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -95,17 +95,6 @@ struct mmu_notifier_ops { pte_t pte); /* - * Before this is invoked any secondary MMU is still ok to - * read/write to the page previously pointed to by the Linux - * pte because the page hasn't been freed yet and it won't be - * freed until this returns. If required set_page_dirty has to - * be called internally to this method. - */ - void (*invalidate_page)(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address); - - /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_sem and/or the * locks protecting the reverse maps are held. If the subsystem @@ -220,8 +209,6 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); -extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address); extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end); extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, @@ -268,13 +255,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm, __mmu_notifier_change_pte(mm, address, pte); } -static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address) -{ - if (mm_has_notifiers(mm)) - __mmu_notifier_invalidate_page(mm, address); -} - static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { @@ -442,11 +422,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm, { } -static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address) -{ -} - static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ef6a13b7bd3e..356a814e7c8e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -114,6 +114,20 @@ struct zone_padding { #define ZONE_PADDING(name) #endif +#ifdef CONFIG_NUMA +enum numa_stat_item { + NUMA_HIT, /* allocated in intended node */ + NUMA_MISS, /* allocated in non intended node */ + NUMA_FOREIGN, /* was intended here, hit elsewhere */ + NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ + NUMA_LOCAL, /* allocation from local node */ + NUMA_OTHER, /* allocation from other node */ + NR_VM_NUMA_STAT_ITEMS +}; +#else +#define NR_VM_NUMA_STAT_ITEMS 0 +#endif + enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, @@ -125,8 +139,6 @@ enum zone_stat_item { NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_SLAB_RECLAIMABLE, - NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ NR_KERNEL_STACK_KB, /* measured in KiB */ /* Second 128 byte cacheline */ @@ -134,14 +146,6 @@ enum zone_stat_item { #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif -#ifdef CONFIG_NUMA - NUMA_HIT, /* allocated in intended node */ - NUMA_MISS, /* allocated in non intended node */ - NUMA_FOREIGN, /* was intended here, hit elsewhere */ - NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ - NUMA_LOCAL, /* allocation from local node */ - NUMA_OTHER, /* allocation from other node */ -#endif NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; @@ -152,6 +156,8 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, @@ -276,6 +282,7 @@ struct per_cpu_pageset { struct per_cpu_pages pcp; #ifdef CONFIG_NUMA s8 expire; + u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; #endif #ifdef CONFIG_SMP s8 stat_threshold; @@ -496,6 +503,7 @@ struct zone { ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; + atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { @@ -533,6 +541,22 @@ static inline bool zone_is_empty(struct zone *zone) } /* + * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty + * intersection with the given zone + */ +static inline bool zone_intersects(struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + if (zone_is_empty(zone)) + return false; + if (start_pfn >= zone_end_pfn(zone) || + start_pfn + nr_pages <= zone->zone_start_pfn) + return false; + + return true; +} + +/* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. @@ -587,12 +611,9 @@ extern struct page *mem_map; #endif /* - * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM - * (mostly NUMA machines?) to denote a higher-level memory zone than the - * zone denotes. - * * On NUMA machines, each NUMA node would have a pg_data_t to describe - * it's memory layout. + * it's memory layout. On UMA machines there is a single pglist_data which + * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. @@ -757,8 +778,7 @@ static inline bool is_dev_zone(const struct zone *zone) #include <linux/memory_hotplug.h> -extern struct mutex zonelists_mutex; -void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); +void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, unsigned int alloc_flags, @@ -772,7 +792,7 @@ enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, }; -extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, +extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); @@ -883,7 +903,7 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, extern int numa_zonelist_order_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern char numa_zonelist_order[]; -#define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ +#define NUMA_ZONELIST_ORDER_LEN 16 #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -1042,6 +1062,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) static inline unsigned long early_pfn_to_nid(unsigned long pfn) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #endif @@ -1144,9 +1165,10 @@ extern unsigned long usemap_size(void); */ #define SECTION_MARKED_PRESENT (1UL<<0) #define SECTION_HAS_MEM_MAP (1UL<<1) -#define SECTION_MAP_LAST_BIT (1UL<<2) +#define SECTION_IS_ONLINE (1UL<<2) +#define SECTION_MAP_LAST_BIT (1UL<<3) #define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 2 +#define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1175,11 +1197,30 @@ static inline int valid_section_nr(unsigned long nr) return valid_section(__nr_to_section(nr)); } +static inline int online_section(struct mem_section *section) +{ + return (section && (section->section_mem_map & SECTION_IS_ONLINE)); +} + +static inline int online_section_nr(unsigned long nr) +{ + return online_section(__nr_to_section(nr)); +} + +#ifdef CONFIG_MEMORY_HOTPLUG +void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); +#ifdef CONFIG_MEMORY_HOTREMOVE +void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); +#endif +#endif + static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } +extern int __highest_present_section_nr; + #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) { @@ -1251,10 +1292,15 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); #ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL /* * pfn_valid() is meant to be able to tell if a given PFN has valid memmap - * associated with it or not. In FLATMEM, it is expected that holes always - * have valid memmap as long as there is valid PFNs either side of the hole. - * In SPARSEMEM, it is assumed that a valid section has a memmap for the - * entire section. + * associated with it or not. This means that a struct page exists for this + * pfn. The caller cannot assume the page is fully initialized in general. + * Hotplugable pages might not have been onlined yet. pfn_to_online_page() + * will ensure the struct page is fully online and initialized. Special pages + * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly. + * + * In FLATMEM, it is expected that holes always have valid memmap as long as + * there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed + * that a valid section has a memmap for the entire section. * * However, an ARM, and maybe other embedded architectures in the future * free memmap backing holes to save memory on the assumption the memmap is diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 3f74ef2281e8..694cebb50f72 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -674,8 +674,6 @@ struct ulpi_device_id { * struct fsl_mc_device_id - MC object device identifier * @vendor: vendor ID * @obj_type: MC object type - * @ver_major: MC object version major number - * @ver_minor: MC object version minor number * * Type of entries in the "device Id" table for MC object devices supported by * a MC object device driver. The last entry of the table has vendor set to 0x0 diff --git a/include/linux/module.h b/include/linux/module.h index 21f56393602f..fe5aa3736707 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -45,7 +45,7 @@ struct module_kobject { struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; -}; +} __randomize_layout; struct module_attribute { struct attribute attr; @@ -209,7 +209,7 @@ extern void cleanup_module(void); #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ -extern const typeof(name) __mod_##type##__##name##_device_table \ +extern typeof(name) __mod_##type##__##name##_device_table \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) @@ -442,8 +442,8 @@ struct module { #ifdef CONFIG_EVENT_TRACING struct trace_event_call **trace_events; unsigned int num_trace_events; - struct trace_enum_map **trace_enums; - unsigned int num_trace_enums; + struct trace_eval_map **trace_evals; + unsigned int num_trace_evals; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD unsigned int num_ftrace_callsites; @@ -475,7 +475,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -} ____cacheline_aligned; +} ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif diff --git a/include/linux/mount.h b/include/linux/mount.h index 8e0352af06b7..1ce85e6fd95f 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,7 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; -}; +} __randomize_layout; struct file; /* forward dec */ struct path; diff --git a/include/linux/msg.h b/include/linux/msg.h index f3f302f9c197..81263fe3f9dc 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -2,6 +2,7 @@ #define _LINUX_MSG_H #include <linux/list.h> +#include <linux/time64.h> #include <uapi/linux/msg.h> /* one msg_msg structure for each message */ @@ -17,9 +18,9 @@ struct msg_msg { /* one msq_queue structure for each present queue on the system */ struct msg_queue { struct kern_ipc_perm q_perm; - time_t q_stime; /* last msgsnd time */ - time_t q_rtime; /* last msgrcv time */ - time_t q_ctime; /* last change time */ + time64_t q_stime; /* last msgsnd time */ + time64_t q_rtime; /* last msgrcv time */ + time64_t q_ctime; /* last change time */ unsigned long q_cbytes; /* current number of bytes on queue */ unsigned long q_qnum; /* number of messages in queue */ unsigned long q_qbytes; /* max number of bytes on queue */ @@ -29,14 +30,6 @@ struct msg_queue { struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; -}; - -/* Helper routines for sys_msgsnd and sys_msgrcv */ -extern long do_msgsnd(int msqid, long mtype, void __user *mtext, - size_t msgsz, int msgflg); -extern long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, - int msgflg, - long (*msg_fill)(void __user *, struct msg_msg *, - size_t)); +} __randomize_layout; #endif /* _LINUX_MSG_H */ diff --git a/include/linux/msi.h b/include/linux/msi.h index df6d59201d31..80e3b562bef6 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -66,6 +66,7 @@ struct fsl_mc_msi_desc { * @mask_pos: [PCI MSI] Mask register position * @mask_base: [PCI MSI-X] Mask register base address * @platform: [platform] Platform device specific msi descriptor data + * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data */ struct msi_desc { /* Shared device/bus type independent data */ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f8a2ef239c60..6cd0f6b7658b 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -206,6 +206,15 @@ struct mtd_pairing_scheme { struct module; /* only needed for owner field in mtd_info */ +/** + * struct mtd_debug_info - debugging information for an MTD device. + * + * @dfs_dir: direntry object of the MTD device debugfs directory + */ +struct mtd_debug_info { + struct dentry *dfs_dir; +}; + struct mtd_info { u_char type; uint32_t flags; @@ -346,6 +355,7 @@ struct mtd_info { struct module *owner; struct device dev; int usecount; + struct mtd_debug_info dbg; }; int mtd_ooblayout_ecc(struct mtd_info *mtd, int section, diff --git a/include/linux/mtd/nand-gpio.h b/include/linux/mtd/nand-gpio.h index 51534e50f7fc..be4f45d89be2 100644 --- a/include/linux/mtd/nand-gpio.h +++ b/include/linux/mtd/nand-gpio.h @@ -1,7 +1,7 @@ #ifndef __LINUX_MTD_NAND_GPIO_H #define __LINUX_MTD_NAND_GPIO_H -#include <linux/mtd/nand.h> +#include <linux/mtd/rawnand.h> struct gpio_nand_platdata { int gpio_nce; diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 06df1e06b6e0..c4beb70dacbd 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -20,6 +20,12 @@ * * For each partition, these fields are available: * name: string that will be used to label the partition's MTD device. + * types: some partitions can be containers using specific format to describe + * embedded subpartitions / volumes. E.g. many home routers use "firmware" + * partition that contains at least kernel and rootfs. In such case an + * extra parser is needed that will detect these dynamic partitions and + * report them to the MTD subsystem. If set this property stores an array + * of parser names to use when looking for subpartitions. * size: the partition size; if defined as MTDPART_SIZ_FULL, the partition * will extend to the end of the master MTD device. * offset: absolute starting position within the master MTD device; if @@ -38,6 +44,7 @@ struct mtd_partition { const char *name; /* identifier string */ + const char *const *types; /* names of parsers to use if any */ uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/rawnand.h index 8f67b1581683..2b05f4273bab 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/rawnand.h @@ -1,6 +1,4 @@ /* - * linux/include/linux/mtd/nand.h - * * Copyright © 2000-2010 David Woodhouse <dwmw2@infradead.org> * Steven J. Hill <sjhill@realitydiluted.com> * Thomas Gleixner <tglx@linutronix.de> @@ -15,8 +13,8 @@ * Changelog: * See git changelog. */ -#ifndef __LINUX_MTD_NAND_H -#define __LINUX_MTD_NAND_H +#ifndef __LINUX_MTD_RAWNAND_H +#define __LINUX_MTD_RAWNAND_H #include <linux/wait.h> #include <linux/spinlock.h> @@ -44,12 +42,6 @@ void nand_release(struct mtd_info *mtd); /* Internal helper for board drivers which need to override command function */ void nand_wait_ready(struct mtd_info *mtd); -/* locks all blocks present in the device */ -int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len); - -/* unlocks specified locked blocks */ -int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); - /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 @@ -89,10 +81,6 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_SET_FEATURES 0xef #define NAND_CMD_RESET 0xff -#define NAND_CMD_LOCK 0x2a -#define NAND_CMD_UNLOCK1 0x23 -#define NAND_CMD_UNLOCK2 0x24 - /* Extended commands for large page devices */ #define NAND_CMD_READSTART 0x30 #define NAND_CMD_RNDOUTSTART 0xE0 @@ -107,6 +95,8 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_STATUS_READY 0x40 #define NAND_STATUS_WP 0x80 +#define NAND_DATA_IFACE_CHECK_ONLY -1 + /* * Constants for ECC_MODES */ @@ -116,6 +106,7 @@ typedef enum { NAND_ECC_HW, NAND_ECC_HW_SYNDROME, NAND_ECC_HW_OOB_FIRST, + NAND_ECC_ON_DIE, } nand_ecc_modes_t; enum nand_ecc_algo { @@ -257,6 +248,8 @@ struct nand_chip; /* Vendor-specific feature address (Micron) */ #define ONFI_FEATURE_ADDR_READ_RETRY 0x89 +#define ONFI_FEATURE_ON_DIE_ECC 0x90 +#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) /* ONFI subfeature parameters length */ #define ONFI_SUBFEATURE_PARAM_LEN 4 @@ -444,14 +437,16 @@ struct nand_jedec_params { __le16 crc; } __packed; +/* The maximum expected count of bytes in the NAND ID sequence */ +#define NAND_MAX_ID_LEN 8 + /** * struct nand_id - NAND id structure - * @data: buffer containing the id bytes. Currently 8 bytes large, but can - * be extended if required. + * @data: buffer containing the id bytes. * @len: ID length. */ struct nand_id { - u8 data[8]; + u8 data[NAND_MAX_ID_LEN]; int len; }; @@ -477,6 +472,44 @@ static inline void nand_hw_control_init(struct nand_hw_control *nfc) } /** + * struct nand_ecc_step_info - ECC step information of ECC engine + * @stepsize: data bytes per ECC step + * @strengths: array of supported strengths + * @nstrengths: number of supported strengths + */ +struct nand_ecc_step_info { + int stepsize; + const int *strengths; + int nstrengths; +}; + +/** + * struct nand_ecc_caps - capability of ECC engine + * @stepinfos: array of ECC step information + * @nstepinfos: number of ECC step information + * @calc_ecc_bytes: driver's hook to calculate ECC bytes per step + */ +struct nand_ecc_caps { + const struct nand_ecc_step_info *stepinfos; + int nstepinfos; + int (*calc_ecc_bytes)(int step_size, int strength); +}; + +/* a shorthand to generate struct nand_ecc_caps with only one ECC stepsize */ +#define NAND_ECC_CAPS_SINGLE(__name, __calc, __step, ...) \ +static const int __name##_strengths[] = { __VA_ARGS__ }; \ +static const struct nand_ecc_step_info __name##_stepinfo = { \ + .stepsize = __step, \ + .strengths = __name##_strengths, \ + .nstrengths = ARRAY_SIZE(__name##_strengths), \ +}; \ +static const struct nand_ecc_caps __name = { \ + .stepinfos = &__name##_stepinfo, \ + .nstepinfos = 1, \ + .calc_ecc_bytes = __calc, \ +} + +/** * struct nand_ecc_ctrl - Control structure for ECC * @mode: ECC mode * @algo: ECC algorithm @@ -638,10 +671,10 @@ struct nand_buffers { * @tWW_min: WP# transition to WE# low */ struct nand_sdr_timings { - u32 tBERS_max; + u64 tBERS_max; u32 tCCS_min; - u32 tPROG_max; - u32 tR_max; + u64 tPROG_max; + u64 tR_max; u32 tALH_min; u32 tADL_min; u32 tALS_min; @@ -785,7 +818,7 @@ struct nand_manufacturer_ops { * Minimum amount of bit errors per @ecc_step_ds guaranteed * to be correctable. If unknown, set to zero. * @ecc_step_ds: [INTERN] ECC step required by the @ecc_strength_ds, - * also from the datasheet. It is the recommended ECC step + * also from the datasheet. It is the recommended ECC step * size, if known; if unknown, set to zero. * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is * set to the actually used ONFI mode if the chip is @@ -815,7 +848,10 @@ struct nand_manufacturer_ops { * @read_retries: [INTERN] the number of read retry modes supported * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand - * @setup_data_interface: [OPTIONAL] setup the data interface and timing + * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If + * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this + * means the configuration should not be applied but + * only checked. * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -826,9 +862,6 @@ struct nand_manufacturer_ops { * structure which is shared among multiple independent * devices. * @priv: [OPTIONAL] pointer to private chip data - * @errstat: [OPTIONAL] hardware specific function to perform - * additional error status checks (determine if errors are - * correctable). * @manufacturer: [INTERN] Contains manufacturer information */ @@ -852,16 +885,13 @@ struct nand_chip { int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); int (*erase)(struct mtd_info *mtd, int page); int (*scan_bbt)(struct mtd_info *mtd); - int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, - int status, int page); int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); - int (*setup_data_interface)(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only); + int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, + const struct nand_data_interface *conf); int chip_delay; @@ -988,8 +1018,6 @@ static inline void *nand_get_manufacturer_data(struct nand_chip *chip) #define NAND_MFR_ATO 0x9b #define NAND_MFR_WINBOND 0xef -/* The maximum expected count of bytes in the NAND ID sequence */ -#define NAND_MAX_ID_LEN 8 /* * A helper for defining older NAND chips where the second ID byte fully @@ -1206,6 +1234,8 @@ int onfi_init_data_interface(struct nand_chip *chip, */ static inline bool nand_is_slc(struct nand_chip *chip) { + WARN(chip->bits_per_cell == 0, + "chip->bits_per_cell is used uninitialized\n"); return chip->bits_per_cell == 1; } @@ -1244,6 +1274,15 @@ int nand_check_erased_ecc_chunk(void *data, int datalen, void *extraoob, int extraooblen, int threshold); +int nand_check_ecc_caps(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_match_ecc_req(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_maximize_ecc(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + /* Default write_oob implementation */ int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); @@ -1258,6 +1297,19 @@ int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int page); +/* Stub used by drivers that do not support GET/SET FEATURES operations */ +int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd, + struct nand_chip *chip, int addr, + u8 *subfeature_param); + +/* Default read_page_raw implementation */ +int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page); + +/* Default write_page_raw implementation */ +int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page); + /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); @@ -1266,4 +1318,4 @@ void nand_cleanup(struct nand_chip *chip); /* Default extended ID decoding function */ void nand_decode_ext_id(struct nand_chip *chip); -#endif /* __LINUX_MTD_NAND_H */ +#endif /* __LINUX_MTD_RAWNAND_H */ diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index 2251add65fa7..c759d403cbc0 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -22,7 +22,7 @@ #include <linux/completion.h> #include <linux/mtd/mtd.h> -#include <linux/mtd/nand.h> +#include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/pm_qos.h> diff --git a/include/linux/mtd/sharpsl.h b/include/linux/mtd/sharpsl.h index 65e91d0fa981..e1845fc4afbd 100644 --- a/include/linux/mtd/sharpsl.h +++ b/include/linux/mtd/sharpsl.h @@ -8,7 +8,7 @@ * published by the Free Software Foundation. */ -#include <linux/mtd/nand.h> +#include <linux/mtd/rawnand.h> #include <linux/mtd/nand_ecc.h> #include <linux/mtd/partitions.h> @@ -17,4 +17,5 @@ struct sharpsl_nand_platform_data { const struct mtd_ooblayout_ops *ecc_layout; struct mtd_partition *partitions; unsigned int nr_partitions; + const char *const *part_parsers; }; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index f2a718030476..1f0a7fc7772f 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -41,6 +41,8 @@ #define SPINOR_OP_WREN 0x06 /* Write enable */ #define SPINOR_OP_RDSR 0x05 /* Read status register */ #define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */ +#define SPINOR_OP_RDSR2 0x3f /* Read status register 2 */ +#define SPINOR_OP_WRSR2 0x3e /* Write status register 2 */ #define SPINOR_OP_READ 0x03 /* Read data bytes (low frequency) */ #define SPINOR_OP_READ_FAST 0x0b /* Read data bytes (high frequency) */ #define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual Output SPI) */ @@ -56,6 +58,7 @@ #define SPINOR_OP_CHIP_ERASE 0xc7 /* Erase whole flash chip */ #define SPINOR_OP_SE 0xd8 /* Sector erase (usually 64KiB) */ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ +#define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ #define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ @@ -73,6 +76,15 @@ #define SPINOR_OP_BE_32K_4B 0x5c /* Erase 32KiB block */ #define SPINOR_OP_SE_4B 0xdc /* Sector erase (usually 64KiB) */ +/* Double Transfer Rate opcodes - defined in JEDEC JESD216B. */ +#define SPINOR_OP_READ_1_1_1_DTR 0x0d +#define SPINOR_OP_READ_1_2_2_DTR 0xbd +#define SPINOR_OP_READ_1_4_4_DTR 0xed + +#define SPINOR_OP_READ_1_1_1_DTR_4B 0x0e +#define SPINOR_OP_READ_1_2_2_DTR_4B 0xbe +#define SPINOR_OP_READ_1_4_4_DTR_4B 0xee + /* Used for SST flashes only. */ #define SPINOR_OP_BP 0x02 /* Byte program */ #define SPINOR_OP_WRDI 0x04 /* Write disable */ @@ -93,6 +105,7 @@ /* Used for Spansion flashes only. */ #define SPINOR_OP_BRWR 0x17 /* Bank register write */ +#define SPINOR_OP_CLSR 0x30 /* Clear status register 1 */ /* Used for Micron flashes only. */ #define SPINOR_OP_RD_EVCR 0x65 /* Read EVCR register */ @@ -107,6 +120,9 @@ #define SR_BP2 BIT(4) /* Block protect 2 */ #define SR_TB BIT(5) /* Top/Bottom protect */ #define SR_SRWD BIT(7) /* SR write protect */ +/* Spansion/Cypress specific status bits */ +#define SR_E_ERR BIT(5) +#define SR_P_ERR BIT(6) #define SR_QUAD_EN_MX BIT(6) /* Macronix Quad I/O */ @@ -119,13 +135,84 @@ /* Configuration Register bits. */ #define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ -enum read_mode { - SPI_NOR_NORMAL = 0, - SPI_NOR_FAST, - SPI_NOR_DUAL, - SPI_NOR_QUAD, +/* Status Register 2 bits. */ +#define SR2_QUAD_EN_BIT7 BIT(7) + +/* Supported SPI protocols */ +#define SNOR_PROTO_INST_MASK GENMASK(23, 16) +#define SNOR_PROTO_INST_SHIFT 16 +#define SNOR_PROTO_INST(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_INST_SHIFT) & \ + SNOR_PROTO_INST_MASK) + +#define SNOR_PROTO_ADDR_MASK GENMASK(15, 8) +#define SNOR_PROTO_ADDR_SHIFT 8 +#define SNOR_PROTO_ADDR(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_ADDR_SHIFT) & \ + SNOR_PROTO_ADDR_MASK) + +#define SNOR_PROTO_DATA_MASK GENMASK(7, 0) +#define SNOR_PROTO_DATA_SHIFT 0 +#define SNOR_PROTO_DATA(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_DATA_SHIFT) & \ + SNOR_PROTO_DATA_MASK) + +#define SNOR_PROTO_IS_DTR BIT(24) /* Double Transfer Rate */ + +#define SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_INST(_inst_nbits) | \ + SNOR_PROTO_ADDR(_addr_nbits) | \ + SNOR_PROTO_DATA(_data_nbits)) +#define SNOR_PROTO_DTR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_IS_DTR | \ + SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits)) + +enum spi_nor_protocol { + SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1), + SNOR_PROTO_1_1_2 = SNOR_PROTO_STR(1, 1, 2), + SNOR_PROTO_1_1_4 = SNOR_PROTO_STR(1, 1, 4), + SNOR_PROTO_1_1_8 = SNOR_PROTO_STR(1, 1, 8), + SNOR_PROTO_1_2_2 = SNOR_PROTO_STR(1, 2, 2), + SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4), + SNOR_PROTO_1_8_8 = SNOR_PROTO_STR(1, 8, 8), + SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2), + SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4), + SNOR_PROTO_8_8_8 = SNOR_PROTO_STR(8, 8, 8), + + SNOR_PROTO_1_1_1_DTR = SNOR_PROTO_DTR(1, 1, 1), + SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2), + SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4), + SNOR_PROTO_1_8_8_DTR = SNOR_PROTO_DTR(1, 8, 8), }; +static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto) +{ + return !!(proto & SNOR_PROTO_IS_DTR); +} + +static inline u8 spi_nor_get_protocol_inst_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_INST_MASK)) >> + SNOR_PROTO_INST_SHIFT; +} + +static inline u8 spi_nor_get_protocol_addr_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_ADDR_MASK)) >> + SNOR_PROTO_ADDR_SHIFT; +} + +static inline u8 spi_nor_get_protocol_data_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_DATA_MASK)) >> + SNOR_PROTO_DATA_SHIFT; +} + +static inline u8 spi_nor_get_protocol_width(enum spi_nor_protocol proto) +{ + return spi_nor_get_protocol_data_nbits(proto); +} + #define SPI_NOR_MAX_CMD_SIZE 8 enum spi_nor_ops { SPI_NOR_OPS_READ = 0, @@ -141,6 +228,7 @@ enum spi_nor_option_flags { SNOR_F_NO_OP_CHIP_ERASE = BIT(2), SNOR_F_S3AN_ADDR_DEFAULT = BIT(3), SNOR_F_READY_XSR_RDY = BIT(4), + SNOR_F_USE_CLSR = BIT(5), }; /** @@ -154,9 +242,11 @@ enum spi_nor_option_flags { * @read_opcode: the read opcode * @read_dummy: the dummy needed by the read operation * @program_opcode: the program opcode - * @flash_read: the mode of the read * @sst_write_second: used by the SST write operation * @flags: flag options for the current SPI-NOR (SNOR_F_*) + * @read_proto: the SPI protocol for read operations + * @write_proto: the SPI protocol for write operations + * @reg_proto the SPI protocol for read_reg/write_reg/erase operations * @cmd_buf: used by the write_reg * @prepare: [OPTIONAL] do some preparations for the * read/write/erase/lock/unlock operations @@ -185,7 +275,9 @@ struct spi_nor { u8 read_opcode; u8 read_dummy; u8 program_opcode; - enum read_mode flash_read; + enum spi_nor_protocol read_proto; + enum spi_nor_protocol write_proto; + enum spi_nor_protocol reg_proto; bool sst_write_second; u32 flags; u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE]; @@ -220,10 +312,71 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) } /** + * struct spi_nor_hwcaps - Structure for describing the hardware capabilies + * supported by the SPI controller (bus master). + * @mask: the bitmask listing all the supported hw capabilies + */ +struct spi_nor_hwcaps { + u32 mask; +}; + +/* + *(Fast) Read capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * As a matter of performances, it is relevant to use Octo SPI protocols first, + * then Quad SPI protocols before Dual SPI protocols, Fast Read and lastly + * (Slow) Read. + */ +#define SNOR_HWCAPS_READ_MASK GENMASK(14, 0) +#define SNOR_HWCAPS_READ BIT(0) +#define SNOR_HWCAPS_READ_FAST BIT(1) +#define SNOR_HWCAPS_READ_1_1_1_DTR BIT(2) + +#define SNOR_HWCAPS_READ_DUAL GENMASK(6, 3) +#define SNOR_HWCAPS_READ_1_1_2 BIT(3) +#define SNOR_HWCAPS_READ_1_2_2 BIT(4) +#define SNOR_HWCAPS_READ_2_2_2 BIT(5) +#define SNOR_HWCAPS_READ_1_2_2_DTR BIT(6) + +#define SNOR_HWCAPS_READ_QUAD GENMASK(10, 7) +#define SNOR_HWCAPS_READ_1_1_4 BIT(7) +#define SNOR_HWCAPS_READ_1_4_4 BIT(8) +#define SNOR_HWCAPS_READ_4_4_4 BIT(9) +#define SNOR_HWCAPS_READ_1_4_4_DTR BIT(10) + +#define SNOR_HWCPAS_READ_OCTO GENMASK(14, 11) +#define SNOR_HWCAPS_READ_1_1_8 BIT(11) +#define SNOR_HWCAPS_READ_1_8_8 BIT(12) +#define SNOR_HWCAPS_READ_8_8_8 BIT(13) +#define SNOR_HWCAPS_READ_1_8_8_DTR BIT(14) + +/* + * Page Program capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * Like (Fast) Read capabilities, Octo/Quad SPI protocols are preferred to the + * legacy SPI 1-1-1 protocol. + * Note that Dual Page Programs are not supported because there is no existing + * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory + * implements such commands. + */ +#define SNOR_HWCAPS_PP_MASK GENMASK(22, 16) +#define SNOR_HWCAPS_PP BIT(16) + +#define SNOR_HWCAPS_PP_QUAD GENMASK(19, 17) +#define SNOR_HWCAPS_PP_1_1_4 BIT(17) +#define SNOR_HWCAPS_PP_1_4_4 BIT(18) +#define SNOR_HWCAPS_PP_4_4_4 BIT(19) + +#define SNOR_HWCAPS_PP_OCTO GENMASK(22, 20) +#define SNOR_HWCAPS_PP_1_1_8 BIT(20) +#define SNOR_HWCAPS_PP_1_8_8 BIT(21) +#define SNOR_HWCAPS_PP_8_8_8 BIT(22) + +/** * spi_nor_scan() - scan the SPI NOR * @nor: the spi_nor structure * @name: the chip type name - * @mode: the read mode supported by the driver + * @hwcaps: the hardware capabilities supported by the controller driver * * The drivers can use this fuction to scan the SPI NOR. * In the scanning, it will try to get all the necessary information to @@ -233,6 +386,7 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) * * Return: 0 for success, others for failure. */ -int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode); +int spi_nor_scan(struct spi_nor *nor, const char *name, + const struct spi_nor_hwcaps *hwcaps); #endif diff --git a/include/linux/mtd/xip.h b/include/linux/mtd/xip.h index abed4dec5c2f..e373690cce0a 100644 --- a/include/linux/mtd/xip.h +++ b/include/linux/mtd/xip.h @@ -30,7 +30,9 @@ * obviously not be running from flash. The __xipram is therefore marking * those functions so they get relocated to ram. */ -#define __xipram noinline __attribute__ ((__section__ (".data"))) +#ifdef CONFIG_XIP_KERNEL +#define __xipram noinline __attribute__ ((__section__ (".xiptext"))) +#endif /* * Each architecture has to provide the following macros. They must access @@ -90,10 +92,10 @@ #define xip_cpu_idle() do { } while (0) #endif -#else +#endif /* CONFIG_MTD_XIP */ +#ifndef __xipram #define __xipram - -#endif /* CONFIG_MTD_XIP */ +#endif #endif /* __LINUX_MTD_XIP_H__ */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 1127fe31645d..ffcba1f337da 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -214,9 +214,9 @@ enum mutex_trylock_recursive_enum { * raisins, and once those are gone this will be removed. * * Returns: - * MUTEX_TRYLOCK_FAILED - trylock failed, - * MUTEX_TRYLOCK_SUCCESS - lock acquired, - * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. + * - MUTEX_TRYLOCK_FAILED - trylock failed, + * - MUTEX_TRYLOCK_SUCCESS - lock acquired, + * - MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. */ static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum mutex_trylock_recursive(struct mutex *lock) diff --git a/include/linux/mux/consumer.h b/include/linux/mux/consumer.h new file mode 100644 index 000000000000..ea96d4c82be7 --- /dev/null +++ b/include/linux/mux/consumer.h @@ -0,0 +1,34 @@ +/* + * mux/consumer.h - definitions for the multiplexer consumer interface + * + * Copyright (C) 2017 Axentia Technologies AB + * + * Author: Peter Rosin <peda@axentia.se> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_MUX_CONSUMER_H +#define _LINUX_MUX_CONSUMER_H + +#include <linux/compiler.h> + +struct device; +struct mux_control; + +unsigned int mux_control_states(struct mux_control *mux); +int __must_check mux_control_select(struct mux_control *mux, + unsigned int state); +int __must_check mux_control_try_select(struct mux_control *mux, + unsigned int state); +int mux_control_deselect(struct mux_control *mux); + +struct mux_control *mux_control_get(struct device *dev, const char *mux_name); +void mux_control_put(struct mux_control *mux); + +struct mux_control *devm_mux_control_get(struct device *dev, + const char *mux_name); + +#endif /* _LINUX_MUX_CONSUMER_H */ diff --git a/include/linux/mux/driver.h b/include/linux/mux/driver.h new file mode 100644 index 000000000000..35c3579c3304 --- /dev/null +++ b/include/linux/mux/driver.h @@ -0,0 +1,108 @@ +/* + * mux/driver.h - definitions for the multiplexer driver interface + * + * Copyright (C) 2017 Axentia Technologies AB + * + * Author: Peter Rosin <peda@axentia.se> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_MUX_DRIVER_H +#define _LINUX_MUX_DRIVER_H + +#include <dt-bindings/mux/mux.h> +#include <linux/device.h> +#include <linux/semaphore.h> + +struct mux_chip; +struct mux_control; + +/** + * struct mux_control_ops - Mux controller operations for a mux chip. + * @set: Set the state of the given mux controller. + */ +struct mux_control_ops { + int (*set)(struct mux_control *mux, int state); +}; + +/** + * struct mux_control - Represents a mux controller. + * @lock: Protects the mux controller state. + * @chip: The mux chip that is handling this mux controller. + * @cached_state: The current mux controller state, or -1 if none. + * @states: The number of mux controller states. + * @idle_state: The mux controller state to use when inactive, or one + * of MUX_IDLE_AS_IS and MUX_IDLE_DISCONNECT. + * + * Mux drivers may only change @states and @idle_state, and may only do so + * between allocation and registration of the mux controller. Specifically, + * @cached_state is internal to the mux core and should never be written by + * mux drivers. + */ +struct mux_control { + struct semaphore lock; /* protects the state of the mux */ + + struct mux_chip *chip; + int cached_state; + + unsigned int states; + int idle_state; +}; + +/** + * struct mux_chip - Represents a chip holding mux controllers. + * @controllers: Number of mux controllers handled by the chip. + * @mux: Array of mux controllers that are handled. + * @dev: Device structure. + * @id: Used to identify the device internally. + * @ops: Mux controller operations. + */ +struct mux_chip { + unsigned int controllers; + struct mux_control *mux; + struct device dev; + int id; + + const struct mux_control_ops *ops; +}; + +#define to_mux_chip(x) container_of((x), struct mux_chip, dev) + +/** + * mux_chip_priv() - Get the extra memory reserved by mux_chip_alloc(). + * @mux_chip: The mux-chip to get the private memory from. + * + * Return: Pointer to the private memory reserved by the allocator. + */ +static inline void *mux_chip_priv(struct mux_chip *mux_chip) +{ + return &mux_chip->mux[mux_chip->controllers]; +} + +struct mux_chip *mux_chip_alloc(struct device *dev, + unsigned int controllers, size_t sizeof_priv); +int mux_chip_register(struct mux_chip *mux_chip); +void mux_chip_unregister(struct mux_chip *mux_chip); +void mux_chip_free(struct mux_chip *mux_chip); + +struct mux_chip *devm_mux_chip_alloc(struct device *dev, + unsigned int controllers, + size_t sizeof_priv); +int devm_mux_chip_register(struct device *dev, struct mux_chip *mux_chip); + +/** + * mux_control_get_index() - Get the index of the given mux controller + * @mux: The mux-control to get the index for. + * + * Return: The index of the mux controller within the mux chip the mux + * controller is a part of. + */ +static inline unsigned int mux_control_get_index(struct mux_control *mux) +{ + return mux - mux->chip->mux; +} + +#endif /* _LINUX_MUX_DRIVER_H */ diff --git a/include/linux/nd.h b/include/linux/nd.h index 194b8e002ea7..5dc6b695437d 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -21,6 +21,15 @@ enum nvdimm_event { NVDIMM_REVALIDATE_POISON, }; +enum nvdimm_claim_class { + NVDIMM_CCLASS_NONE, + NVDIMM_CCLASS_BTT, + NVDIMM_CCLASS_BTT2, + NVDIMM_CCLASS_PFN, + NVDIMM_CCLASS_DAX, + NVDIMM_CCLASS_UNKNOWN, +}; + struct nd_device_driver { struct device_driver drv; unsigned long type; @@ -41,12 +50,14 @@ static inline struct nd_device_driver *to_nd_device_driver( * @force_raw: ignore other personalities for the namespace (e.g. btt) * @dev: device model node * @claim: when set a another personality has taken ownership of the namespace + * @claim_class: restrict claim type to a given class * @rw_bytes: access the raw namespace capacity with byte-aligned transfers */ struct nd_namespace_common { int force_raw; struct device dev; struct device *claim; + enum nvdimm_claim_class claim_class; int (*rw_bytes)(struct nd_namespace_common *, resource_size_t offset, void *buf, size_t size, int rw, unsigned long flags); }; @@ -75,12 +86,14 @@ struct nd_namespace_io { /** * struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory * @nsio: device and system physical address range to drive + * @lbasize: logical sector size for the namespace in block-device-mode * @alt_name: namespace name supplied in the dimm label * @uuid: namespace name supplied in the dimm label * @id: ida allocated id */ struct nd_namespace_pmem { struct nd_namespace_io nsio; + unsigned long lbasize; char *alt_name; u8 *uuid; int id; diff --git a/include/linux/net.h b/include/linux/net.h index abcfa46a2bd9..d97d80d7fdf8 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -37,7 +37,7 @@ struct net; /* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. - * Eventually all flags will be in sk->sk_wq_flags. + * Eventually all flags will be in sk->sk_wq->flags. */ #define SOCKWQ_ASYNC_NOSPACE 0 #define SOCKWQ_ASYNC_WAITDATA 1 @@ -190,8 +190,16 @@ struct proto_ops { struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); + + /* The following functions are called internally by kernel with + * sock lock already held. + */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); + int (*sendpage_locked)(struct sock *sk, struct page *page, + int offset, size_t size, int flags); + int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, + size_t size); }; #define DECLARE_SOCKADDR(type, dst, src) \ @@ -274,9 +282,13 @@ do { \ #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) +#define net_get_random_once_wait(buf, nbytes) \ + get_random_once_wait((buf), (nbytes)) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); +int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, + struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); @@ -295,6 +307,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); +int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, + size_t size, int flags); int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 1d4737cffc71..dc8b4896b77b 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -36,7 +36,6 @@ enum { /**/NETIF_F_GSO_SHIFT, /* keep the order of SKB_GSO_* bits */ NETIF_F_TSO_BIT /* ... TCPv4 segmentation */ = NETIF_F_GSO_SHIFT, - NETIF_F_UFO_BIT, /* ... UDPv4 fragmentation */ NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */ NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ NETIF_F_TSO_MANGLEID_BIT, /* ... IPV4 ID mangling allowed */ @@ -76,6 +75,7 @@ enum { NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ + NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ /* * Add your fresh new feature above and remember to update @@ -118,7 +118,6 @@ enum { #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) #define NETIF_F_TSO __NETIF_F(TSO) -#define NETIF_F_UFO __NETIF_F(UFO) #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) @@ -140,6 +139,7 @@ enum { #define NETIF_F_HW_TC __NETIF_F(HW_TC) #define NETIF_F_HW_ESP __NETIF_F(HW_ESP) #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) +#define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) @@ -172,7 +172,7 @@ enum { NETIF_F_FSO) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_UFO | \ +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ NETIF_F_GSO_SCTP) /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4ed952c17fc7..f535779d9dc1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -35,7 +35,6 @@ #include <linux/percpu.h> #include <linux/rculist.h> -#include <linux/dmaengine.h> #include <linux/workqueue.h> #include <linux/dynamic_queue_limits.h> @@ -66,6 +65,7 @@ struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; struct bpf_prog; +struct xdp_buff; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -693,10 +693,9 @@ struct netdev_rx_queue { */ struct rx_queue_attribute { struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, char *buf); + ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); ssize_t (*store)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, const char *buf, size_t len); + const char *buf, size_t len); }; #ifdef CONFIG_XPS @@ -770,31 +769,14 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -/* These structures hold the attributes of qdisc and classifiers - * that are being passed to the netdevice through the setup_tc op. - */ -enum { +enum tc_setup_type { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, - TC_SETUP_MATCHALL, + TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, }; -struct tc_cls_u32_offload; - -struct tc_to_netdev { - unsigned int type; - union { - struct tc_cls_u32_offload *cls_u32; - struct tc_cls_flower_offload *cls_flower; - struct tc_cls_matchall_offload *cls_mall; - struct tc_cls_bpf_offload *cls_bpf; - struct tc_mqprio_qopt *mqprio; - }; - bool egress_dev; -}; - /* These structures hold the attributes of xdp state that are being passed * to the netdevice through the xdp op. */ @@ -807,8 +789,10 @@ enum xdp_netdev_command { * when it is no longer used. */ XDP_SETUP_PROG, + XDP_SETUP_PROG_HW, /* Check if a bpf program is set on the device. The callee should - * return true if a program is currently attached and running. + * set @prog_attached to one of XDP_ATTACHED_* values, note that "true" + * is equivalent to XDP_ATTACHED_DRV. */ XDP_QUERY_PROG, }; @@ -820,11 +804,15 @@ struct netdev_xdp { union { /* XDP_SETUP_PROG */ struct { + u32 flags; struct bpf_prog *prog; struct netlink_ext_ack *extack; }; /* XDP_QUERY_PROG */ - bool prog_attached; + struct { + u8 prog_attached; + u32 prog_id; + }; }; }; @@ -971,8 +959,8 @@ struct xfrmdev_ops { * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); - * int (*ndo_setup_tc)(struct net_device *dev, u32 handle, - * __be16 protocol, struct tc_to_netdev *tc); + * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, + * void *type_data); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif * tx queues stopped. This allows the netdevice to perform queue @@ -1108,12 +1096,6 @@ struct xfrmdev_ops { * by 'ndo_dfwd_add_station'. 'pdev' is the net device backing * the station and priv is the structure returned by the add * operation. - * netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb, - * struct net_device *dev, - * void *priv); - * Callback to use for xmit over the accelerated station. This - * is used in place of ndo_start_xmit on accelerated net - * devices. * int (*ndo_set_tx_maxrate)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific @@ -1138,7 +1120,12 @@ struct xfrmdev_ops { * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); * This function is used to set or query state related to XDP on the * netdevice. See definition of enum xdp_netdev_command for details. - * + * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); + * This function is used to submit a XDP packet for transmit on a + * netdevice. + * void (*ndo_xdp_flush)(struct net_device *dev); + * This function is used to inform the driver to flush a particular + * xdp tx queue. Must be called on same CPU as xdp_xmit. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1221,9 +1208,8 @@ struct net_device_ops { struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, - u32 handle, - __be16 protocol, - struct tc_to_netdev *tc); + enum tc_setup_type type, + void *type_data); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); @@ -1310,9 +1296,6 @@ struct net_device_ops { void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - netdev_tx_t (*ndo_dfwd_start_xmit) (struct sk_buff *skb, - struct net_device *dev, - void *priv); int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, @@ -1326,6 +1309,9 @@ struct net_device_ops { int needed_headroom); int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + int (*ndo_xdp_xmit)(struct net_device *dev, + struct xdp_buff *xdp); + void (*ndo_xdp_flush)(struct net_device *dev); }; /** @@ -1432,13 +1418,14 @@ enum netdev_priv_flags { /** * struct net_device - The DEVICE structure. - * Actually, this whole structure is a big mistake. It mixes I/O - * data with strictly "high-level" data, and it has to know about - * almost every data structure used in the INET module. + * + * Actually, this whole structure is a big mistake. It mixes I/O + * data with strictly "high-level" data, and it has to know about + * almost every data structure used in the INET module. * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name - * of the interface. + * of the interface. * * @name_hlist: Device name hash chain, please keep it close to name[] * @ifalias: SNMP alias @@ -1804,7 +1791,7 @@ struct net_device { #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS - struct nf_hook_entry __rcu *nf_hooks_ingress; + struct nf_hook_entries __rcu *nf_hooks_ingress; #endif unsigned char broadcast[MAX_ADDR_LEN]; @@ -1823,7 +1810,7 @@ struct net_device { #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif - unsigned long tx_queue_len; + unsigned int tx_queue_len; spinlock_t tx_global_lock; int watchdog_timeo; @@ -2310,6 +2297,7 @@ struct netdev_lag_lower_state_info { #define NETDEV_PRECHANGEUPPER 0x001A #define NETDEV_CHANGELOWERSTATE 0x001B #define NETDEV_UDP_TUNNEL_PUSH_INFO 0x001C +#define NETDEV_UDP_TUNNEL_DROP_INFO 0x001D #define NETDEV_CHANGE_TX_QUEUE_LEN 0x001E int register_netdevice_notifier(struct notifier_block *nb); @@ -2425,8 +2413,8 @@ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev); -int dev_close(struct net_device *dev); -int dev_close_many(struct list_head *head, bool unlink); +void dev_close(struct net_device *dev); +void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); @@ -2456,6 +2444,7 @@ static inline int dev_recursion_level(void) struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); +struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); @@ -2573,9 +2562,7 @@ static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_gro_checksum_validate_complete(skb, \ compute_pseudo(skb, proto)); \ - if (__ret) \ - __skb_mark_checksum_bad(skb); \ - else \ + if (!__ret) \ skb_gro_incr_csum_unnecessary(skb); \ __ret; \ }) @@ -2777,7 +2764,7 @@ struct softnet_data { unsigned int input_queue_head ____cacheline_aligned_in_smp; /* Elements below can be accessed between CPUs for RPS/RFS */ - struct call_single_data csd ____cacheline_aligned_in_smp; + call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; unsigned int input_queue_tail; @@ -3254,6 +3241,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } +void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); @@ -3287,6 +3276,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags, int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); +int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); void dev_set_group(struct net_device *, int); int dev_set_mac_address(struct net_device *, struct sockaddr *); @@ -3303,7 +3293,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); -bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op); +u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); @@ -3868,6 +3858,8 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev, bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); +bool netdev_has_any_upper_dev(struct net_device *dev); + void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, @@ -3931,6 +3923,10 @@ void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); +int skb_crc32c_csum_help(struct sk_buff *skb); +int skb_csum_hwoffload_help(struct sk_buff *skb, + const netdev_features_t features); + struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, @@ -4017,22 +4013,22 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi return rc; } -int netdev_class_create_file_ns(struct class_attribute *class_attr, +int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns); -void netdev_class_remove_file_ns(struct class_attribute *class_attr, +void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns); -static inline int netdev_class_create_file(struct class_attribute *class_attr) +static inline int netdev_class_create_file(const struct class_attribute *class_attr) { return netdev_class_create_file_ns(class_attr, NULL); } -static inline void netdev_class_remove_file(struct class_attribute *class_attr) +static inline void netdev_class_remove_file(const struct class_attribute *class_attr) { netdev_class_remove_file_ns(class_attr, NULL); } -extern struct kobj_ns_type_operations net_ns_type_operations; +extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); @@ -4087,7 +4083,6 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index a4b97be30b28..f84bca1703cd 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -61,8 +61,6 @@ typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); struct nf_hook_ops { - struct list_head list; - /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; @@ -74,25 +72,32 @@ struct nf_hook_ops { }; struct nf_hook_entry { - struct nf_hook_entry __rcu *next; nf_hookfn *hook; void *priv; - const struct nf_hook_ops *orig_ops; }; -static inline void -nf_hook_entry_init(struct nf_hook_entry *entry, const struct nf_hook_ops *ops) -{ - entry->next = NULL; - entry->hook = ops->hook; - entry->priv = ops->priv; - entry->orig_ops = ops; -} +struct nf_hook_entries { + u16 num_hook_entries; + /* padding */ + struct nf_hook_entry hooks[]; + + /* trailer: pointers to original orig_ops of each hook. + * + * This is not part of struct nf_hook_entry since its only + * needed in slow path (hook register/unregister). + * + * const struct nf_hook_ops *orig_ops[] + */ +}; -static inline int -nf_hook_entry_priority(const struct nf_hook_entry *entry) +static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e) { - return entry->orig_ops->priority; + unsigned int n = e->num_hook_entries; + const void *hook_end; + + hook_end = &e->hooks[n]; /* this is *past* ->hooks[]! */ + + return (struct nf_hook_ops **)hook_end; } static inline int @@ -102,12 +107,6 @@ nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, return entry->hook(entry->priv, skb, state); } -static inline const struct nf_hook_ops * -nf_hook_entry_ops(const struct nf_hook_entry *entry) -{ - return entry->orig_ops; -} - static inline void nf_hook_state_init(struct nf_hook_state *p, unsigned int hook, u_int8_t pf, @@ -160,13 +159,6 @@ int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); -int nf_register_hook(struct nf_hook_ops *reg); -void nf_unregister_hook(struct nf_hook_ops *reg); -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); -int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); - /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); @@ -177,7 +169,7 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, - struct nf_hook_entry *entry); + const struct nf_hook_entries *e, unsigned int i); /** * nf_hook - call a netfilter hook @@ -191,7 +183,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - struct nf_hook_entry *hook_head; + struct nf_hook_entries *hook_head; int ret = 1; #ifdef HAVE_JUMP_LABEL @@ -209,7 +201,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, nf_hook_state_init(&state, hook, pf, indev, outdev, sk, net, okfn); - ret = nf_hook_slow(skb, &state, hook_head); + ret = nf_hook_slow(skb, &state, hook_head, 0); } rcu_read_unlock(); diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 996711d8a7b4..41d04e9d088a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -1,7 +1,6 @@ #ifndef _NFNETLINK_H #define _NFNETLINK_H - #include <linux/netlink.h> #include <linux/capability.h> #include <net/netlink.h> @@ -10,13 +9,16 @@ struct nfnl_callback { int (*call)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); int (*call_rcu)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); const struct nla_policy *policy; /* netlink attribute policy */ const u_int16_t attr_count; /* number of nlattr's */ }; diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h index 074790c0cf74..0fc458bde80b 100644 --- a/include/linux/netfilter/xt_hashlimit.h +++ b/include/linux/netfilter/xt_hashlimit.h @@ -5,5 +5,6 @@ #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ - XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES) + XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ + XT_HASHLIMIT_RATE_MATCH) #endif /*_XT_HASHLIMIT_H*/ diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index e0cbf17af780..2c2a5514b0df 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -122,8 +122,6 @@ extern unsigned int ebt_do_table(struct sk_buff *skb, #define BASE_CHAIN (par->hook_mask & (1 << NF_BR_NUMHOOKS)) /* Clear the bit in the hook mask that tells if the rule is on a base chain */ #define CLEAR_BASE_CHAIN_BIT (par->hook_mask &= ~(1 << NF_BR_NUMHOOKS)) -/* True if the target is not a standard target */ -#define INVALID_TARGET (info->target < -NUM_STANDARD_TARGETS || info->target >= 0) static inline bool ebt_invalid_target(int target) { diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index 59476061de86..8d5dae1e2ff8 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -17,7 +17,7 @@ static inline bool nf_hook_ingress_active(const struct sk_buff *skb) /* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { - struct nf_hook_entry *e = rcu_dereference(skb->dev->nf_hooks_ingress); + struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; int ret; @@ -30,7 +30,7 @@ static inline int nf_hook_ingress(struct sk_buff *skb) nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); - ret = nf_hook_slow(skb, &state, e); + ret = nf_hook_slow(skb, &state, e, 0); if (ret == 0) return -1; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 5fff5ba5964e..8664fd26eb5d 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -97,6 +97,21 @@ struct netlink_ext_ack { #define NL_SET_ERR_MSG_MOD(extack, msg) \ NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg) +#define NL_SET_BAD_ATTR(extack, attr) do { \ + if ((extack)) \ + (extack)->bad_attr = (attr); \ +} while (0) + +#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ + static const char __msg[] = (msg); \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) { \ + __extack->_msg = __msg; \ + __extack->bad_attr = (attr); \ + } \ +} while (0) + extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 1828900c9411..27c0aaa22cb0 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -11,6 +11,7 @@ #include <linux/interrupt.h> #include <linux/rcupdate.h> #include <linux/list.h> +#include <linux/refcount.h> union inet_addr { __u32 all[4]; @@ -34,7 +35,7 @@ struct netpoll { }; struct netpoll_info { - atomic_t refcnt; + refcount_t refcnt; struct semaphore dev_lock; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 1b1ca04820a3..47239c336688 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -479,6 +479,7 @@ enum { NFSPROC4_CLNT_ACCESS, NFSPROC4_CLNT_GETATTR, NFSPROC4_CLNT_LOOKUP, + NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LOOKUP_ROOT, NFSPROC4_CLNT_REMOVE, NFSPROC4_CLNT_RENAME, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bb0eb2c9acca..a0282ceaa48b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -49,9 +49,8 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - unsigned long jiffies; struct rpc_cred * cred; - int mask; + __u32 mask; struct rcu_head rcu_head; }; @@ -154,7 +153,7 @@ struct nfs_inode { */ __be32 cookieverf[2]; - unsigned long nrequests; + atomic_long_t nrequests; struct nfs_mds_commit_info commit_info; /* Open contexts for shared mmap writes */ @@ -163,6 +162,7 @@ struct nfs_inode { /* Readers: in-flight sillydelete RPC calls */ /* Writers: rmdir */ struct rw_semaphore rmdir_sem; + struct mutex commit_mutex; #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; @@ -332,6 +332,7 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); +struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); @@ -509,7 +510,7 @@ extern void nfs_commit_free(struct nfs_commit_data *data); static inline int nfs_have_writebacks(struct inode *inode) { - return NFS_I(inode)->nrequests != 0; + return atomic_long_read(&NFS_I(inode)->nrequests) != 0; } /* diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index e418a1096662..74c44665e6d3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -42,6 +42,7 @@ struct nfs_client { #define NFS_CS_MIGRATION 2 /* - transparent state migr */ #define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ +#define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -210,6 +211,7 @@ struct nfs_server { unsigned long mig_status; #define NFS_MIG_IN_TRANSITION (1) #define NFS_MIG_FAILED (2) +#define NFS_MIG_TSM_POSSIBLE (3) void (*destroy)(struct nfs_server *); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 247cc3d3498f..d117120c9b6e 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -33,6 +33,8 @@ enum { PG_UPTODATE, /* page group sync bit in read path */ PG_WB_END, /* page group sync bit in write path */ PG_REMOVE, /* page group sync bit in write path */ + PG_CONTENDED1, /* Is someone waiting for a lock? */ + PG_CONTENDED2, /* Is someone waiting for a lock? */ }; struct nfs_inode; @@ -93,8 +95,8 @@ struct nfs_pageio_descriptor { const struct rpc_call_ops *pg_rpc_callops; const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; + struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; - void *pg_layout_private; unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; @@ -123,8 +125,7 @@ extern void nfs_pageio_init(struct nfs_pageio_descriptor *desc, const struct nfs_pgio_completion_ops *compl_ops, const struct nfs_rw_ops *rw_ops, size_t bsize, - int how, - gfp_t gfp_flags); + int how); extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, struct nfs_page *); extern int nfs_pageio_resend(struct nfs_pageio_descriptor *, @@ -137,8 +138,7 @@ extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); -extern int nfs_page_group_lock(struct nfs_page *, bool); -extern void nfs_page_group_lock_wait(struct nfs_page *); +extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b28c83475ee8..164d5359d4ab 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -878,7 +878,7 @@ struct nfs3_readdirargs { struct nfs_fh * fh; __u64 cookie; __be32 verf[2]; - int plus; + bool plus; unsigned int count; struct page ** pages; }; @@ -909,7 +909,7 @@ struct nfs3_linkres { struct nfs3_readdirres { struct nfs_fattr * dir_attr; __be32 * verf; - int plus; + bool plus; }; struct nfs3_getaclres { @@ -1012,7 +1012,6 @@ struct nfs4_link_res { struct nfs_fattr * dir_attr; }; - struct nfs4_lookup_arg { struct nfs4_sequence_args seq_args; const struct nfs_fh * dir_fh; @@ -1028,6 +1027,20 @@ struct nfs4_lookup_res { struct nfs4_label *label; }; +struct nfs4_lookupp_arg { + struct nfs4_sequence_args seq_args; + const struct nfs_fh *fh; + const u32 *bitmask; +}; + +struct nfs4_lookupp_res { + struct nfs4_sequence_res seq_res; + const struct nfs_server *server; + struct nfs_fattr *fattr; + struct nfs_fh *fh; + struct nfs4_label *label; +}; + struct nfs4_lookup_root_arg { struct nfs4_sequence_args seq_args; const u32 * bitmask; @@ -1053,7 +1066,7 @@ struct nfs4_readdir_arg { struct page ** pages; /* zero-copy data */ unsigned int pgbase; /* zero-copy data */ const u32 * bitmask; - int plus; + bool plus; }; struct nfs4_readdir_res { @@ -1222,7 +1235,7 @@ struct nfs41_state_protection { struct nfs41_exchange_id_args { struct nfs_client *client; - nfs4_verifier *verifier; + nfs4_verifier verifier; u32 flags; struct nfs41_state_protection state_protect; }; @@ -1422,6 +1435,7 @@ enum { NFS_IOHDR_STAT, }; +struct nfs_io_completion; struct nfs_pgio_header { struct inode *inode; struct rpc_cred *cred; @@ -1435,8 +1449,8 @@ struct nfs_pgio_header { void (*release) (struct nfs_pgio_header *hdr); const struct nfs_pgio_completion_ops *completion_ops; const struct nfs_rw_ops *rw_ops; + struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; - void *layout_private; spinlock_t lock; /* fields protected by lock */ int pnfs_error; @@ -1462,7 +1476,7 @@ struct nfs_pgio_header { struct nfs_mds_commit_info { atomic_t rpcs_out; - unsigned long ncommit; + atomic_long_t ncommit; struct list_head list; }; @@ -1533,6 +1547,7 @@ struct nfs_renamedata { struct nfs_fattr new_fattr; void (*complete)(struct rpc_task *, struct nfs_renamedata *); long timeout; + bool cancelled; }; struct nfs_access_entry; @@ -1567,6 +1582,8 @@ struct nfs_rpc_ops { int (*lookup) (struct inode *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); + int (*lookupp) (struct inode *, struct nfs_fh *, + struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); @@ -1585,7 +1602,7 @@ struct nfs_rpc_ops { int (*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct dentry *, struct rpc_cred *, - u64, struct page **, unsigned int, int); + u64, struct page **, unsigned int, bool); int (*mknod) (struct inode *, struct dentry *, struct iattr *, dev_t); int (*statfs) (struct nfs_server *, struct nfs_fh *, @@ -1595,7 +1612,7 @@ struct nfs_rpc_ops { int (*pathconf) (struct nfs_server *, struct nfs_fh *, struct nfs_pathconf *); int (*set_capabilities)(struct nfs_server *, struct nfs_fh *); - int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int); + int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, bool); int (*pgio_rpc_prepare)(struct rpc_task *, struct nfs_pgio_header *); void (*read_setup)(struct nfs_pgio_header *, struct rpc_message *); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aa3cd0878270..a36abe2da13e 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -6,18 +6,26 @@ #include <linux/sched.h> #include <asm/irq.h> +#if defined(CONFIG_HAVE_NMI_WATCHDOG) +#include <asm/nmi.h> +#endif #ifdef CONFIG_LOCKUP_DETECTOR +void lockup_detector_init(void); +#else +static inline void lockup_detector_init(void) +{ +} +#endif + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; -extern unsigned int hardlockup_panic; -void lockup_detector_init(void); +extern int soft_watchdog_enabled; +extern atomic_t watchdog_park_in_progress; #else static inline void touch_softlockup_watchdog_sched(void) { @@ -31,9 +39,6 @@ static inline void touch_softlockup_watchdog_sync(void) static inline void touch_all_softlockup_watchdogs(void) { } -static inline void lockup_detector_init(void) -{ -} #endif #ifdef CONFIG_DETECT_HUNG_TASK @@ -61,6 +66,21 @@ static inline void reset_hung_task_detector(void) #define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) #define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) +#if defined(CONFIG_HARDLOCKUP_DETECTOR) +extern void hardlockup_detector_disable(void); +extern unsigned int hardlockup_panic; +#else +static inline void hardlockup_detector_disable(void) {} +#endif + +#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) +extern void arch_touch_nmi_watchdog(void); +#else +#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline void arch_touch_nmi_watchdog(void) {} +#endif +#endif + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * @@ -68,21 +88,11 @@ static inline void reset_hung_task_detector(void) * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) -#include <asm/nmi.h> -extern void touch_nmi_watchdog(void); -#else static inline void touch_nmi_watchdog(void) { + arch_touch_nmi_watchdog(); touch_softlockup_watchdog(); } -#endif - -#if defined(CONFIG_HARDLOCKUP_DETECTOR) -extern void hardlockup_detector_disable(void); -#else -static inline void hardlockup_detector_disable(void) {} -#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided @@ -139,15 +149,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu) } #endif -#ifdef CONFIG_LOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh); +#endif + +#ifdef CONFIG_LOCKUP_DETECTOR extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; +extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; -extern atomic_t watchdog_park_in_progress; +extern int __read_mostly watchdog_suspended; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; @@ -155,6 +168,14 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_softlockup_all_cpu_backtrace 0 #define sysctl_hardlockup_all_cpu_backtrace 0 #endif + +#if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ + defined(CONFIG_HARDLOCKUP_DETECTOR) +void watchdog_update_hrtimer_threshold(u64 period); +#else +static inline void watchdog_update_hrtimer_threshold(u64 period) { } +#endif + extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , diff --git a/include/linux/node.h b/include/linux/node.h index 2115ad5d6f19..d1751beb462c 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -30,9 +30,38 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); +#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages); +#else +static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) +{ + return 0; +} +#endif + extern void unregister_node(struct node *node); #ifdef CONFIG_NUMA -extern int register_one_node(int nid); +/* Core of the node registration - only memory hotplug should use this */ +extern int __register_one_node(int nid); + +/* Registers an online node */ +static inline int register_one_node(int nid) +{ + int error = 0; + + if (node_online(nid)) { + struct pglist_data *pgdat = NODE_DATA(nid); + + error = __register_one_node(nid); + if (error) + return error; + /* link memory sections under this node */ + error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages); + } + + return error; +} + extern void unregister_one_node(int nid); extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); @@ -46,6 +75,10 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister, node_registration_func_t unregister); #endif #else +static inline int __register_one_node(int nid) +{ + return 0; +} static inline int register_one_node(int nid) { return 0; diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index f746e44d4046..cf0b91c3ec12 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -387,11 +387,7 @@ enum node_states { #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif -#ifdef CONFIG_MOVABLE_NODE N_MEMORY, /* The node has memory(regular, high, movable) */ -#else - N_MEMORY = N_HIGH_MEMORY, -#endif N_CPU, /* The node has one or more cpus */ NR_NODE_STATES }; diff --git a/include/linux/ntb.h b/include/linux/ntb.h index de87ceac110e..609e232c00da 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -18,6 +19,7 @@ * BSD LICENSE * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -106,6 +108,7 @@ static inline char *ntb_topo_string(enum ntb_topo topo) * @NTB_SPEED_GEN1: Link is trained to gen1 speed. * @NTB_SPEED_GEN2: Link is trained to gen2 speed. * @NTB_SPEED_GEN3: Link is trained to gen3 speed. + * @NTB_SPEED_GEN4: Link is trained to gen4 speed. */ enum ntb_speed { NTB_SPEED_AUTO = -1, @@ -113,6 +116,7 @@ enum ntb_speed { NTB_SPEED_GEN1 = 1, NTB_SPEED_GEN2 = 2, NTB_SPEED_GEN3 = 3, + NTB_SPEED_GEN4 = 4 }; /** @@ -140,6 +144,20 @@ enum ntb_width { }; /** + * enum ntb_default_port - NTB default port number + * @NTB_PORT_PRI_USD: Default port of the NTB_TOPO_PRI/NTB_TOPO_B2B_USD + * topologies + * @NTB_PORT_SEC_DSD: Default port of the NTB_TOPO_SEC/NTB_TOPO_B2B_DSD + * topologies + */ +enum ntb_default_port { + NTB_PORT_PRI_USD, + NTB_PORT_SEC_DSD +}; +#define NTB_DEF_PEER_CNT (1) +#define NTB_DEF_PEER_IDX (0) + +/** * struct ntb_client_ops - ntb client operations * @probe: Notify client of a new device. * @remove: Notify client to remove a device. @@ -162,10 +180,12 @@ static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops) * struct ntb_ctx_ops - ntb driver context operations * @link_event: See ntb_link_event(). * @db_event: See ntb_db_event(). + * @msg_event: See ntb_msg_event(). */ struct ntb_ctx_ops { void (*link_event)(void *ctx); void (*db_event)(void *ctx, int db_vector); + void (*msg_event)(void *ctx); }; static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) @@ -174,18 +194,27 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) return /* ops->link_event && */ /* ops->db_event && */ + /* ops->msg_event && */ 1; } /** * struct ntb_ctx_ops - ntb device operations - * @mw_count: See ntb_mw_count(). - * @mw_get_range: See ntb_mw_get_range(). - * @mw_set_trans: See ntb_mw_set_trans(). - * @mw_clear_trans: See ntb_mw_clear_trans(). + * @port_number: See ntb_port_number(). + * @peer_port_count: See ntb_peer_port_count(). + * @peer_port_number: See ntb_peer_port_number(). + * @peer_port_idx: See ntb_peer_port_idx(). * @link_is_up: See ntb_link_is_up(). * @link_enable: See ntb_link_enable(). * @link_disable: See ntb_link_disable(). + * @mw_count: See ntb_mw_count(). + * @mw_get_align: See ntb_mw_get_align(). + * @mw_set_trans: See ntb_mw_set_trans(). + * @mw_clear_trans: See ntb_mw_clear_trans(). + * @peer_mw_count: See ntb_peer_mw_count(). + * @peer_mw_get_addr: See ntb_peer_mw_get_addr(). + * @peer_mw_set_trans: See ntb_peer_mw_set_trans(). + * @peer_mw_clear_trans:See ntb_peer_mw_clear_trans(). * @db_is_unsafe: See ntb_db_is_unsafe(). * @db_valid_mask: See ntb_db_valid_mask(). * @db_vector_count: See ntb_db_vector_count(). @@ -210,22 +239,43 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @peer_spad_addr: See ntb_peer_spad_addr(). * @peer_spad_read: See ntb_peer_spad_read(). * @peer_spad_write: See ntb_peer_spad_write(). + * @msg_count: See ntb_msg_count(). + * @msg_inbits: See ntb_msg_inbits(). + * @msg_outbits: See ntb_msg_outbits(). + * @msg_read_sts: See ntb_msg_read_sts(). + * @msg_clear_sts: See ntb_msg_clear_sts(). + * @msg_set_mask: See ntb_msg_set_mask(). + * @msg_clear_mask: See ntb_msg_clear_mask(). + * @msg_read: See ntb_msg_read(). + * @msg_write: See ntb_msg_write(). */ struct ntb_dev_ops { - int (*mw_count)(struct ntb_dev *ntb); - int (*mw_get_range)(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size); - int (*mw_set_trans)(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size); - int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); + int (*port_number)(struct ntb_dev *ntb); + int (*peer_port_count)(struct ntb_dev *ntb); + int (*peer_port_number)(struct ntb_dev *ntb, int pidx); + int (*peer_port_idx)(struct ntb_dev *ntb, int port); - int (*link_is_up)(struct ntb_dev *ntb, + u64 (*link_is_up)(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width); int (*link_enable)(struct ntb_dev *ntb, enum ntb_speed max_speed, enum ntb_width max_width); int (*link_disable)(struct ntb_dev *ntb); + int (*mw_count)(struct ntb_dev *ntb, int pidx); + int (*mw_get_align)(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max); + int (*mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size); + int (*mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*peer_mw_count)(struct ntb_dev *ntb); + int (*peer_mw_get_addr)(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size); + int (*peer_mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size); + int (*peer_mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*db_is_unsafe)(struct ntb_dev *ntb); u64 (*db_valid_mask)(struct ntb_dev *ntb); int (*db_vector_count)(struct ntb_dev *ntb); @@ -252,32 +302,55 @@ struct ntb_dev_ops { int (*spad_is_unsafe)(struct ntb_dev *ntb); int (*spad_count)(struct ntb_dev *ntb); - u32 (*spad_read)(struct ntb_dev *ntb, int idx); - int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*spad_read)(struct ntb_dev *ntb, int sidx); + int (*spad_write)(struct ntb_dev *ntb, int sidx, u32 val); - int (*peer_spad_addr)(struct ntb_dev *ntb, int idx, + int (*peer_spad_addr)(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr); - u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx); - int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx); + int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx, + u32 val); + + int (*msg_count)(struct ntb_dev *ntb); + u64 (*msg_inbits)(struct ntb_dev *ntb); + u64 (*msg_outbits)(struct ntb_dev *ntb); + u64 (*msg_read_sts)(struct ntb_dev *ntb); + int (*msg_clear_sts)(struct ntb_dev *ntb, u64 sts_bits); + int (*msg_set_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_clear_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_read)(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg); + int (*msg_write)(struct ntb_dev *ntb, int midx, int pidx, u32 msg); }; static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) { /* commented callbacks are not required: */ return - ops->mw_count && - ops->mw_get_range && - ops->mw_set_trans && - /* ops->mw_clear_trans && */ + /* Port operations are required for multiport devices */ + !ops->peer_port_count == !ops->port_number && + !ops->peer_port_number == !ops->port_number && + !ops->peer_port_idx == !ops->port_number && + + /* Link operations are required */ ops->link_is_up && ops->link_enable && ops->link_disable && + + /* One or both MW interfaces should be developed */ + ops->mw_count && + ops->mw_get_align && + (ops->mw_set_trans || + ops->peer_mw_set_trans) && + /* ops->mw_clear_trans && */ + ops->peer_mw_count && + ops->peer_mw_get_addr && + /* ops->peer_mw_clear_trans && */ + + /* Doorbell operations are mostly required */ /* ops->db_is_unsafe && */ ops->db_valid_mask && - /* both set, or both unset */ - (!ops->db_vector_count == !ops->db_vector_mask) && - + (!ops->db_vector_count == !ops->db_vector_mask) && ops->db_read && /* ops->db_set && */ ops->db_clear && @@ -291,13 +364,24 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* ops->peer_db_read_mask && */ /* ops->peer_db_set_mask && */ /* ops->peer_db_clear_mask && */ - /* ops->spad_is_unsafe && */ - ops->spad_count && - ops->spad_read && - ops->spad_write && - /* ops->peer_spad_addr && */ - /* ops->peer_spad_read && */ - ops->peer_spad_write && + + /* Scrachpads interface is optional */ + /* !ops->spad_is_unsafe == !ops->spad_count && */ + !ops->spad_read == !ops->spad_count && + !ops->spad_write == !ops->spad_count && + /* !ops->peer_spad_addr == !ops->spad_count && */ + /* !ops->peer_spad_read == !ops->spad_count && */ + !ops->peer_spad_write == !ops->spad_count && + + /* Messaging interface is optional */ + !ops->msg_inbits == !ops->msg_count && + !ops->msg_outbits == !ops->msg_count && + !ops->msg_read_sts == !ops->msg_count && + !ops->msg_clear_sts == !ops->msg_count && + /* !ops->msg_set_mask == !ops->msg_count && */ + /* !ops->msg_clear_mask == !ops->msg_count && */ + !ops->msg_read == !ops->msg_count && + !ops->msg_write == !ops->msg_count && 1; } @@ -310,13 +394,12 @@ struct ntb_client { struct device_driver drv; const struct ntb_client_ops ops; }; - #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) /** * struct ntb_device - ntb device * @dev: Linux device object. - * @pdev: Pci device entry of the ntb. + * @pdev: PCI device entry of the ntb. * @topo: Detected topology of the ntb. * @ops: See &ntb_dev_ops. * @ctx: See &ntb_ctx_ops. @@ -337,7 +420,6 @@ struct ntb_dev { /* block unregister until device is fully released */ struct completion released; }; - #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) /** @@ -434,86 +516,152 @@ void ntb_link_event(struct ntb_dev *ntb); * multiple interrupt vectors for doorbells, the vector number indicates which * vector received the interrupt. The vector number is relative to the first * vector used for doorbells, starting at zero, and must be less than - ** ntb_db_vector_count(). The driver may call ntb_db_read() to check which + * ntb_db_vector_count(). The driver may call ntb_db_read() to check which * doorbell bits need service, and ntb_db_vector_mask() to determine which of * those bits are associated with the vector number. */ void ntb_db_event(struct ntb_dev *ntb, int vector); /** - * ntb_mw_count() - get the number of memory windows + * ntb_msg_event() - notify driver context of a message event * @ntb: NTB device context. * - * Hardware and topology may support a different number of memory windows. + * Notify the driver context of a message event. If hardware supports + * message registers, this event indicates, that a new message arrived in + * some incoming message register or last sent message couldn't be delivered. + * The events can be masked/unmasked by the methods ntb_msg_set_mask() and + * ntb_msg_clear_mask(). + */ +void ntb_msg_event(struct ntb_dev *ntb); + +/** + * ntb_default_port_number() - get the default local port number + * @ntb: NTB device context. * - * Return: the number of memory windows. + * If hardware driver doesn't specify port_number() callback method, the NTB + * is considered with just two ports. So this method returns default local + * port number in compliance with topology. + * + * NOTE Don't call this method directly. The ntb_port_number() function should + * be used instead. + * + * Return: the default local port number + */ +int ntb_default_port_number(struct ntb_dev *ntb); + +/** + * ntb_default_port_count() - get the default number of peer device ports + * @ntb: NTB device context. + * + * By default hardware driver supports just one peer device. + * + * NOTE Don't call this method directly. The ntb_peer_port_count() function + * should be used instead. + * + * Return: the default number of peer ports + */ +int ntb_default_peer_port_count(struct ntb_dev *ntb); + +/** + * ntb_default_peer_port_number() - get the default peer port by given index + * @ntb: NTB device context. + * @idx: Peer port index (should not differ from zero). + * + * By default hardware driver supports just one peer device, so this method + * shall return the corresponding value from enum ntb_default_port. + * + * NOTE Don't call this method directly. The ntb_peer_port_number() function + * should be used instead. + * + * Return: the peer device port or negative value indicating an error + */ +int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx); + +/** + * ntb_default_peer_port_idx() - get the default peer device port index by + * given port number + * @ntb: NTB device context. + * @port: Peer port number (should be one of enum ntb_default_port). + * + * By default hardware driver supports just one peer device, so while + * specified port-argument indicates peer port from enum ntb_default_port, + * the return value shall be zero. + * + * NOTE Don't call this method directly. The ntb_peer_port_idx() function + * should be used instead. + * + * Return: the peer port index or negative value indicating an error + */ +int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port); + +/** + * ntb_port_number() - get the local port number + * @ntb: NTB device context. + * + * Hardware must support at least simple two-ports ntb connection + * + * Return: the local port number */ -static inline int ntb_mw_count(struct ntb_dev *ntb) +static inline int ntb_port_number(struct ntb_dev *ntb) { - return ntb->ops->mw_count(ntb); + if (!ntb->ops->port_number) + return ntb_default_port_number(ntb); + + return ntb->ops->port_number(ntb); } /** - * ntb_mw_get_range() - get the range of a memory window + * ntb_peer_port_count() - get the number of peer device ports * @ntb: NTB device context. - * @idx: Memory window number. - * @base: OUT - the base address for mapping the memory window - * @size: OUT - the size for mapping the memory window - * @align: OUT - the base alignment for translating the memory window - * @align_size: OUT - the size alignment for translating the memory window * - * Get the range of a memory window. NULL may be given for any output - * parameter if the value is not needed. The base and size may be used for - * mapping the memory window, to access the peer memory. The alignment and - * size may be used for translating the memory window, for the peer to access - * memory on the local system. + * Hardware may support an access to memory of several remote domains + * over multi-port NTB devices. This method returns the number of peers, + * local device can have shared memory with. * - * Return: Zero on success, otherwise an error number. + * Return: the number of peer ports */ -static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size) +static inline int ntb_peer_port_count(struct ntb_dev *ntb) { - return ntb->ops->mw_get_range(ntb, idx, base, size, - align, align_size); + if (!ntb->ops->peer_port_count) + return ntb_default_peer_port_count(ntb); + + return ntb->ops->peer_port_count(ntb); } /** - * ntb_mw_set_trans() - set the translation of a memory window + * ntb_peer_port_number() - get the peer port by given index * @ntb: NTB device context. - * @idx: Memory window number. - * @addr: The dma address local memory to expose to the peer. - * @size: The size of the local memory to expose to the peer. + * @pidx: Peer port index. * - * Set the translation of a memory window. The peer may access local memory - * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * Peer ports are continuously enumerated by NTB API logic, so this method + * lets to retrieve port real number by its index. * - * Return: Zero on success, otherwise an error number. + * Return: the peer device port or negative value indicating an error */ -static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size) +static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx) { - return ntb->ops->mw_set_trans(ntb, idx, addr, size); + if (!ntb->ops->peer_port_number) + return ntb_default_peer_port_number(ntb, pidx); + + return ntb->ops->peer_port_number(ntb, pidx); } /** - * ntb_mw_clear_trans() - clear the translation of a memory window + * ntb_peer_port_idx() - get the peer device port index by given port number * @ntb: NTB device context. - * @idx: Memory window number. + * @port: Peer port number. * - * Clear the translation of a memory window. The peer may no longer access - * local memory through the window. + * Inverse operation of ntb_peer_port_number(), so one can get port index + * by specified port number. * - * Return: Zero on success, otherwise an error number. + * Return: the peer port index or negative value indicating an error */ -static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) +static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port) { - if (!ntb->ops->mw_clear_trans) - return ntb->ops->mw_set_trans(ntb, idx, 0, 0); + if (!ntb->ops->peer_port_idx) + return ntb_default_peer_port_idx(ntb, port); - return ntb->ops->mw_clear_trans(ntb, idx); + return ntb->ops->peer_port_idx(ntb, port); } /** @@ -526,25 +674,26 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) * state once after every link event. It is safe to query the link state in * the context of the link event callback. * - * Return: One if the link is up, zero if the link is down, otherwise a - * negative value indicating the error number. + * Return: bitfield of indexed ports link state: bit is set/cleared if the + * link is up/down respectively. */ -static inline int ntb_link_is_up(struct ntb_dev *ntb, +static inline u64 ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { return ntb->ops->link_is_up(ntb, speed, width); } /** - * ntb_link_enable() - enable the link on the secondary side of the ntb + * ntb_link_enable() - enable the local port ntb connection * @ntb: NTB device context. * @max_speed: The maximum link speed expressed as PCIe generation number. * @max_width: The maximum link width expressed as the number of PCIe lanes. * - * Enable the link on the secondary side of the ntb. This can only be done - * from the primary side of the ntb in primary or b2b topology. The ntb device - * should train the link to its maximum speed and width, or the requested speed - * and width, whichever is smaller, if supported. + * Enable the NTB/PCIe link on the local or remote (for bridge-to-bridge + * topology) side of the bridge. If it's supported the ntb device should train + * the link to its maximum speed and width, or the requested speed and width, + * whichever is smaller. Some hardware doesn't support PCIe link training, so + * the last two arguments will be ignored then. * * Return: Zero on success, otherwise an error number. */ @@ -556,14 +705,14 @@ static inline int ntb_link_enable(struct ntb_dev *ntb, } /** - * ntb_link_disable() - disable the link on the secondary side of the ntb + * ntb_link_disable() - disable the local port ntb connection * @ntb: NTB device context. * - * Disable the link on the secondary side of the ntb. This can only be - * done from the primary side of the ntb in primary or b2b topology. The ntb - * device should disable the link. Returning from this call must indicate that - * a barrier has passed, though with no more writes may pass in either - * direction across the link, except if this call returns an error number. + * Disable the link on the local or remote (for b2b topology) of the ntb. + * The ntb device should disable the link. Returning from this call must + * indicate that a barrier has passed, though with no more writes may pass in + * either direction across the link, except if this call returns an error + * number. * * Return: Zero on success, otherwise an error number. */ @@ -573,6 +722,183 @@ static inline int ntb_link_disable(struct ntb_dev *ntb) } /** + * ntb_mw_count() - get the number of inbound memory windows, which could + * be created for a specified peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * + * Hardware and topology may support a different number of memory windows. + * Moreover different peer devices can support different number of memory + * windows. Simply speaking this method returns the number of possible inbound + * memory windows to share with specified peer device. + * + * Return: the number of memory windows. + */ +static inline int ntb_mw_count(struct ntb_dev *ntb, int pidx) +{ + return ntb->ops->mw_count(ntb, pidx); +} + +/** + * ntb_mw_get_align() - get the restriction parameters of inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr_align: OUT - the base alignment for translating the memory window + * @size_align: OUT - the size alignment for translating the memory window + * @size_max: OUT - the maximum size of the memory window + * + * Get the alignments of an inbound memory window with specified index. + * NULL may be given for any output parameter if the value is not needed. + * The alignment and size parameters may be used for allocation of proper + * shared memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) +{ + return ntb->ops->mw_get_align(ntb, pidx, widx, addr_align, size_align, + size_max); +} + +/** + * ntb_mw_set_trans() - set the translation of an inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr: The dma address of local memory to expose to the peer. + * @size: The size of the local memory to expose to the peer. + * + * Set the translation of a memory window. The peer may access local memory + * through the window starting at the address, up to the size. The address + * and size must be aligned in compliance with restrictions of + * ntb_mw_get_align(). The region size should not exceed the size_max parameter + * of that method. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size) +{ + if (!ntb->ops->mw_set_trans) + return 0; + + return ntb->ops->mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_mw_clear_trans() - clear the translation address of an inbound memory + * window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of an inbound memory window. The peer may no longer + * access local memory through the window. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int pidx, int widx) +{ + if (!ntb->ops->mw_clear_trans) + return ntb_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->mw_clear_trans(ntb, pidx, widx); +} + +/** + * ntb_peer_mw_count() - get the number of outbound memory windows, which could + * be mapped to access a shared memory + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of memory windows. + * This method returns the number of outbound memory windows supported by + * local device. + * + * Return: the number of memory windows. + */ +static inline int ntb_peer_mw_count(struct ntb_dev *ntb) +{ + return ntb->ops->peer_mw_count(ntb); +} + +/** + * ntb_peer_mw_get_addr() - get map address of an outbound memory window + * @ntb: NTB device context. + * @widx: Memory window index (within ntb_peer_mw_count() return value). + * @base: OUT - the base address of mapping region. + * @size: OUT - the size of mapping region. + * + * Get base and size of memory region to map. NULL may be given for any output + * parameter if the value is not needed. The base and size may be used for + * mapping the memory window, to access the peer memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size) +{ + return ntb->ops->peer_mw_get_addr(ntb, widx, base, size); +} + +/** + * ntb_peer_mw_set_trans() - set a translation address of a memory window + * retrieved from a peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device the translation address received from. + * @widx: Memory window index. + * @addr: The dma address of the shared memory to access. + * @size: The size of the shared memory to access. + * + * Set the translation of an outbound memory window. The local device may + * access shared memory allocated by a peer device sent the address. + * + * This method may not be implemented due to the hardware specific memory + * windows interface, so a translation address can be only set on the side, + * where shared memory (inbound memory windows) is allocated. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size) +{ + if (!ntb->ops->peer_mw_set_trans) + return 0; + + return ntb->ops->peer_mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_peer_mw_clear_trans() - clear the translation address of an outbound + * memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of a outbound memory window. The local device may no + * longer access a shared memory through the window. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, + int widx) +{ + if (!ntb->ops->peer_mw_clear_trans) + return ntb_peer_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->peer_mw_clear_trans(ntb, pidx, widx); +} + +/** * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell * @ntb: NTB device context. * @@ -900,47 +1226,58 @@ static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) * @ntb: NTB device context. * * Hardware and topology may support a different number of scratchpads. + * Although it must be the same for all ports per NTB device. * * Return: the number of scratchpads. */ static inline int ntb_spad_count(struct ntb_dev *ntb) { + if (!ntb->ops->spad_count) + return 0; + return ntb->ops->spad_count(ntb); } /** * ntb_spad_read() - read the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * * Read the local scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_spad_read(struct ntb_dev *ntb, int sidx) { - return ntb->ops->spad_read(ntb, idx); + if (!ntb->ops->spad_read) + return ~(u32)0; + + return ntb->ops->spad_read(ntb, sidx); } /** * ntb_spad_write() - write the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the local scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val) { - return ntb->ops->spad_write(ntb, idx, val); + if (!ntb->ops->spad_write) + return -EINVAL; + + return ntb->ops->spad_write(ntb, sidx, val); } /** * ntb_peer_spad_addr() - address of the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @spad_addr: OUT - The address of the peer scratchpad register. * * Return the address of the peer doorbell register. This may be used, for @@ -948,45 +1285,213 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, +static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr) { if (!ntb->ops->peer_spad_addr) return -EINVAL; - return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); + return ntb->ops->peer_spad_addr(ntb, pidx, sidx, spad_addr); } /** * ntb_peer_spad_read() - read the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * * Read the peer scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { if (!ntb->ops->peer_spad_read) - return 0; + return ~(u32)0; - return ntb->ops->peer_spad_read(ntb, idx); + return ntb->ops->peer_spad_read(ntb, pidx, sidx); } /** * ntb_peer_spad_write() - write the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the peer scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx, + u32 val) +{ + if (!ntb->ops->peer_spad_write) + return -EINVAL; + + return ntb->ops->peer_spad_write(ntb, pidx, sidx, val); +} + +/** + * ntb_msg_count() - get the number of message registers + * @ntb: NTB device context. + * + * Hardware may support a different number of message registers. + * + * Return: the number of message registers. + */ +static inline int ntb_msg_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_count) + return 0; + + return ntb->ops->msg_count(ntb); +} + +/** + * ntb_msg_inbits() - get a bitfield of inbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to inbound message registers. + * + * Return: bitfield of inbound message registers. + */ +static inline u64 ntb_msg_inbits(struct ntb_dev *ntb) { - return ntb->ops->peer_spad_write(ntb, idx, val); + if (!ntb->ops->msg_inbits) + return 0; + + return ntb->ops->msg_inbits(ntb); +} + +/** + * ntb_msg_outbits() - get a bitfield of outbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to outbound message registers. + * + * Return: bitfield of outbound message registers. + */ +static inline u64 ntb_msg_outbits(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_outbits) + return 0; + + return ntb->ops->msg_outbits(ntb); +} + +/** + * ntb_msg_read_sts() - read the message registers status + * @ntb: NTB device context. + * + * Read the status of message register. Inbound and outbound message registers + * related bits can be filtered by masks retrieved from ntb_msg_inbits() and + * ntb_msg_outbits(). + * + * Return: status bits of message registers + */ +static inline u64 ntb_msg_read_sts(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_read_sts) + return 0; + + return ntb->ops->msg_read_sts(ntb); +} + +/** + * ntb_msg_clear_sts() - clear status bits of message registers + * @ntb: NTB device context. + * @sts_bits: Status bits to clear. + * + * Clear bits in the status register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits) +{ + if (!ntb->ops->msg_clear_sts) + return -EINVAL; + + return ntb->ops->msg_clear_sts(ntb, sts_bits); +} + +/** + * ntb_msg_set_mask() - set mask of message register status bits + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Mask the message registers status bits from raising the message event. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_set_mask) + return -EINVAL; + + return ntb->ops->msg_set_mask(ntb, mask_bits); +} + +/** + * ntb_msg_clear_mask() - clear message registers mask + * @ntb: NTB device context. + * @mask_bits: Mask bits to clear. + * + * Clear bits in the message events mask register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_clear_mask) + return -EINVAL; + + return ntb->ops->msg_clear_mask(ntb, mask_bits); +} + +/** + * ntb_msg_read() - read message register with specified index + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: OUT - Port index of peer device a message retrieved from + * @msg: OUT - Data + * + * Read data from the specified message register. Source port index of a + * message is retrieved as well. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx, + u32 *msg) +{ + if (!ntb->ops->msg_read) + return -EINVAL; + + return ntb->ops->msg_read(ntb, midx, pidx, msg); +} + +/** + * ntb_msg_write() - write data to the specified message register + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: Port index of peer device a message being sent to + * @msg: Data to send + * + * Send data to a specified peer device using the defined message register. + * Message event can be raised if the midx registers isn't empty while + * calling this method and the corresponding interrupt isn't masked. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx, + u32 msg) +{ + if (!ntb->ops->msg_write) + return -EINVAL; + + return ntb->ops->msg_write(ntb, midx, pidx, msg); } #endif diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 6c8c5d8041b7..9c5cb4480806 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,6 +346,11 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -619,7 +624,7 @@ struct nvmefc_tgt_fcp_req { u32 timeout; u32 transfer_length; struct fc_ba_rjt ba_rjt; - struct scatterlist sg[NVME_FC_MAX_SEGMENTS]; + struct scatterlist *sg; int sg_cnt; void *rspaddr; dma_addr_t rspdma; @@ -846,6 +851,8 @@ struct nvmet_fc_target_template { struct nvmefc_tgt_fcp_req *fcpreq); void (*fcp_req_release)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); + void (*defer_rcv)(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *fcpreq); u32 max_hw_queues; u16 max_sgl_segments; diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index e997c4a49a88..36cca93a5ff2 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -17,6 +17,7 @@ /* * This file contains definitions relative to FC-NVME r1.14 (16-020vB). + * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. */ #ifndef _NVME_FC_H @@ -177,7 +178,6 @@ struct fcnvme_lsdesc_rjt { }; -#define FCNVME_ASSOC_HOSTID_LEN 16 #define FCNVME_ASSOC_HOSTNQN_LEN 256 #define FCNVME_ASSOC_SUBNQN_LEN 256 @@ -191,12 +191,24 @@ struct fcnvme_lsdesc_cr_assoc_cmd { __be16 cntlid; __be16 sqsize; __be32 rsvd52; - u8 hostid[FCNVME_ASSOC_HOSTID_LEN]; + uuid_t hostid; u8 hostnqn[FCNVME_ASSOC_HOSTNQN_LEN]; u8 subnqn[FCNVME_ASSOC_SUBNQN_LEN]; - u8 rsvd632[384]; + __be32 rsvd584[108]; /* pad to 1016 bytes, + * which makes overall LS rqst + * payload 1024 bytes + */ }; +#define FCNVME_LSDESC_CRA_CMD_DESC_MINLEN \ + offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, rsvd584) + +#define FCNVME_LSDESC_CRA_CMD_DESC_MIN_DESCLEN \ + (FCNVME_LSDESC_CRA_CMD_DESC_MINLEN - \ + offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, ersp_ratio)) + + + /* FCNVME_LSDESC_CREATE_CONN_CMD */ struct fcnvme_lsdesc_cr_conn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ @@ -274,6 +286,14 @@ struct fcnvme_ls_cr_assoc_rqst { struct fcnvme_lsdesc_cr_assoc_cmd assoc_cmd; }; +#define FCNVME_LSDESC_CRA_RQST_MINLEN \ + (offsetof(struct fcnvme_ls_cr_assoc_rqst, assoc_cmd) + \ + FCNVME_LSDESC_CRA_CMD_DESC_MINLEN) + +#define FCNVME_LSDESC_CRA_RQST_MIN_LISTLEN \ + FCNVME_LSDESC_CRA_CMD_DESC_MINLEN + + struct fcnvme_ls_cr_assoc_acc { struct fcnvme_ls_acc_hdr hdr; struct fcnvme_lsdesc_assoc_id associd; @@ -314,5 +334,24 @@ struct fcnvme_ls_disconnect_acc { #define NVME_FC_LS_TIMEOUT_SEC 2 /* 2 seconds */ #define NVME_FC_TGTOP_TIMEOUT_SEC 2 /* 2 seconds */ +/* + * TRADDR string must be of form "nn-<16hexdigits>:pn-<16hexdigits>" + * the string is allowed to be specified with or without a "0x" prefix + * infront of the <16hexdigits>. Without is considered the "min" string + * and with is considered the "max" string. The hexdigits may be upper + * or lower case. + */ +#define NVME_FC_TRADDR_NNLEN 3 /* "?n-" */ +#define NVME_FC_TRADDR_OXNNLEN 5 /* "?n-0x" */ +#define NVME_FC_TRADDR_HEXNAMELEN 16 +#define NVME_FC_TRADDR_MINLENGTH \ + (2 * (NVME_FC_TRADDR_NNLEN + NVME_FC_TRADDR_HEXNAMELEN) + 1) +#define NVME_FC_TRADDR_MAXLENGTH \ + (2 * (NVME_FC_TRADDR_OXNNLEN + NVME_FC_TRADDR_HEXNAMELEN) + 1) +#define NVME_FC_TRADDR_MIN_PN_OFFSET \ + (NVME_FC_TRADDR_NNLEN + NVME_FC_TRADDR_HEXNAMELEN + 1) +#define NVME_FC_TRADDR_MAX_PN_OFFSET \ + (NVME_FC_TRADDR_OXNNLEN + NVME_FC_TRADDR_HEXNAMELEN + 1) + #endif /* _NVME_FC_H */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b625bacf37ef..87723c86f136 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -16,6 +16,7 @@ #define _LINUX_NVME_H #include <linux/types.h> +#include <linux/uuid.h> /* NQN names in commands fields specified one size */ #define NVMF_NQN_FIELD_LEN 256 @@ -31,6 +32,8 @@ #define NVME_RDMA_IP_PORT 4420 +#define NVME_NSID_ALL 0xffffffff + enum nvme_subsys_type { NVME_NQN_DISC = 1, /* Discovery type target subsystem */ NVME_NQN_NVME = 2, /* NVME type target subsystem */ @@ -86,7 +89,7 @@ enum { NVMF_RDMA_CMS_RDMA_CM = 1, /* Sockets based endpoint addressing */ }; -#define NVMF_AQ_DEPTH 32 +#define NVME_AQ_DEPTH 32 enum { NVME_REG_CAP = 0x0000, /* Controller Capabilities */ @@ -101,6 +104,7 @@ enum { NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; #define NVME_CAP_MQES(cap) ((cap) & 0xffff) @@ -131,19 +135,26 @@ enum { enum { NVME_CC_ENABLE = 1 << 0, NVME_CC_CSS_NVM = 0 << 4, + NVME_CC_EN_SHIFT = 0, + NVME_CC_CSS_SHIFT = 4, NVME_CC_MPS_SHIFT = 7, - NVME_CC_ARB_RR = 0 << 11, - NVME_CC_ARB_WRRU = 1 << 11, - NVME_CC_ARB_VS = 7 << 11, - NVME_CC_SHN_NONE = 0 << 14, - NVME_CC_SHN_NORMAL = 1 << 14, - NVME_CC_SHN_ABRUPT = 2 << 14, - NVME_CC_SHN_MASK = 3 << 14, - NVME_CC_IOSQES = NVME_NVM_IOSQES << 16, - NVME_CC_IOCQES = NVME_NVM_IOCQES << 20, + NVME_CC_AMS_SHIFT = 11, + NVME_CC_SHN_SHIFT = 14, + NVME_CC_IOSQES_SHIFT = 16, + NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_AMS_RR = 0 << NVME_CC_AMS_SHIFT, + NVME_CC_AMS_WRRU = 1 << NVME_CC_AMS_SHIFT, + NVME_CC_AMS_VS = 7 << NVME_CC_AMS_SHIFT, + NVME_CC_SHN_NONE = 0 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_NORMAL = 1 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_ABRUPT = 2 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, + NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, + NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, + NVME_CSTS_PP = 1 << 5, NVME_CSTS_SHST_NORMAL = 0 << 2, NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, @@ -207,9 +218,17 @@ struct nvme_id_ctrl { __u8 tnvmcap[16]; __u8 unvmcap[16]; __le32 rpmbs; - __u8 rsvd316[4]; + __le16 edstt; + __u8 dsto; + __u8 fwug; __le16 kas; - __u8 rsvd322[190]; + __le16 hctma; + __le16 mntmt; + __le16 mxtmt; + __le32 sanicap; + __le32 hmminds; + __le16 hmmaxd; + __u8 rsvd338[174]; __u8 sqes; __u8 cqes; __le16 maxcmd; @@ -243,9 +262,11 @@ enum { NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, NVME_CTRL_ONCS_DSM = 1 << 2, NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3, + NVME_CTRL_ONCS_TIMESTAMP = 1 << 6, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, - NVME_CTRL_OACS_DBBUF_SUPP = 1 << 7, + NVME_CTRL_OACS_DIRECTIVES = 1 << 5, + NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, }; struct nvme_lbaf { @@ -274,7 +295,7 @@ struct nvme_id_ns { __le16 nabsn; __le16 nabo; __le16 nabspf; - __u16 rsvd46; + __le16 noiob; __u8 nvmcap[16]; __u8 rsvd64[40]; __u8 nguid[16]; @@ -288,6 +309,7 @@ enum { NVME_ID_CNS_NS = 0x00, NVME_ID_CNS_CTRL = 0x01, NVME_ID_CNS_NS_ACTIVE_LIST = 0x02, + NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -295,6 +317,19 @@ enum { }; enum { + NVME_DIR_IDENTIFY = 0x00, + NVME_DIR_STREAMS = 0x01, + NVME_DIR_SND_ID_OP_ENABLE = 0x01, + NVME_DIR_SND_ST_OP_REL_ID = 0x01, + NVME_DIR_SND_ST_OP_REL_RSC = 0x02, + NVME_DIR_RCV_ID_OP_PARAM = 0x01, + NVME_DIR_RCV_ST_OP_PARAM = 0x01, + NVME_DIR_RCV_ST_OP_STATUS = 0x02, + NVME_DIR_RCV_ST_OP_RESOURCE = 0x03, + NVME_DIR_ENDIR = 0x01, +}; + +enum { NVME_NS_FEAT_THIN = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, NVME_NS_FLBAS_META_EXT = 0x10, @@ -314,6 +349,22 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +struct nvme_ns_id_desc { + __u8 nidt; + __u8 nidl; + __le16 reserved; +}; + +#define NVME_NIDT_EUI64_LEN 8 +#define NVME_NIDT_NGUID_LEN 16 +#define NVME_NIDT_UUID_LEN 16 + +enum { + NVME_NIDT_EUI64 = 0x01, + NVME_NIDT_NGUID = 0x02, + NVME_NIDT_UUID = 0x03, +}; + struct nvme_smart_log { __u8 critical_warning; __u8 temperature[2]; @@ -337,6 +388,13 @@ struct nvme_smart_log { __u8 rsvd216[296]; }; +struct nvme_fw_slot_info_log { + __u8 afi; + __u8 rsvd1[7]; + __le64 frs[7]; + __u8 rsvd64[448]; +}; + enum { NVME_SMART_CRIT_SPARE = 1 << 0, NVME_SMART_CRIT_TEMPERATURE = 1 << 1, @@ -347,6 +405,7 @@ enum { enum { NVME_AER_NOTICE_NS_CHANGED = 0x0002, + NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102, }; struct nvme_lba_range_type { @@ -535,6 +594,7 @@ enum { NVME_RW_PRINFO_PRCHK_APP = 1 << 11, NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12, NVME_RW_PRINFO_PRACT = 1 << 13, + NVME_RW_DTYPE_STREAMS = 1 << 4, }; struct nvme_dsm_cmd { @@ -586,6 +646,11 @@ struct nvme_feat_auto_pst { __le64 entries[32]; }; +enum { + NVME_HOST_MEM_ENABLE = (1 << 0), + NVME_HOST_MEM_RETURN = (1 << 1), +}; + /* Admin commands */ enum nvme_admin_opcode { @@ -604,6 +669,8 @@ enum nvme_admin_opcode { nvme_admin_download_fw = 0x11, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, + nvme_admin_directive_send = 0x19, + nvme_admin_directive_recv = 0x1a, nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, @@ -630,6 +697,7 @@ enum { NVME_FEAT_ASYNC_EVENT = 0x0b, NVME_FEAT_AUTO_PST = 0x0c, NVME_FEAT_HOST_MEM_BUF = 0x0d, + NVME_FEAT_TIMESTAMP = 0x0e, NVME_FEAT_KATO = 0x0f, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, @@ -658,6 +726,8 @@ struct nvme_identify { __u32 rsvd11[5]; }; +#define NVME_IDENTIFY_DATA_SIZE 4096 + struct nvme_features { __u8 opcode; __u8 flags; @@ -667,7 +737,16 @@ struct nvme_features { union nvme_data_ptr dptr; __le32 fid; __le32 dword11; - __u32 rsvd12[4]; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct nvme_host_mem_buf_desc { + __le64 addr; + __le32 size; + __u32 rsvd; }; struct nvme_create_cq { @@ -756,6 +835,24 @@ struct nvme_get_log_page_command { __u32 rsvd14[2]; }; +struct nvme_directive_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + union nvme_data_ptr dptr; + __le32 numd; + __u8 doper; + __u8 dtype; + __le16 dspec; + __u8 endir; + __u8 tdtype; + __u16 rsvd15; + + __u32 rsvd16[3]; +}; + /* * Fabrics subcommands. */ @@ -843,7 +940,7 @@ struct nvmf_connect_command { }; struct nvmf_connect_data { - __u8 hostid[16]; + uuid_t hostid; __le16 cntlid; char resv4[238]; char subsysnqn[NVMF_NQN_FIELD_LEN]; @@ -886,6 +983,18 @@ struct nvme_dbbuf { __u32 rsvd12[6]; }; +struct streams_directive_params { + __le16 msl; + __le16 nssa; + __le16 nsso; + __u8 rsvd[10]; + __le32 sws; + __le16 sgs; + __le16 nsa; + __le16 nso; + __u8 rsvd2[6]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -906,6 +1015,7 @@ struct nvme_command { struct nvmf_property_set_command prop_set; struct nvmf_property_get_command prop_get; struct nvme_dbbuf dbbuf; + struct nvme_directive_cmd directive; }; }; @@ -917,7 +1027,7 @@ static inline bool nvme_is_write(struct nvme_command *cmd) * Why can't we simply have a Fabrics In and Fabrics out command? */ if (unlikely(cmd->common.opcode == nvme_fabrics_command)) - return cmd->fabrics.opcode & 1; + return cmd->fabrics.fctype & 1; return cmd->common.opcode & 1; } @@ -1050,4 +1160,8 @@ struct nvme_completion { #define NVME_VS(major, minor, tertiary) \ (((major) << 16) | ((minor) << 8) | (tertiary)) +#define NVME_MAJOR(ver) ((ver) >> 16) +#define NVME_MINOR(ver) (((ver) >> 8) & 0xff) +#define NVME_TERTIARY(ver) ((ver) & 0xff) + #endif /* _LINUX_NVME_H */ diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index c2256d746543..4e85447f7860 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -12,6 +12,9 @@ #ifndef _LINUX_NVMEM_CONSUMER_H #define _LINUX_NVMEM_CONSUMER_H +#include <linux/err.h> +#include <linux/errno.h> + struct device; struct device_node; /* consumer cookie */ @@ -35,6 +38,7 @@ void nvmem_cell_put(struct nvmem_cell *cell); void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell); void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len); int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len); +int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val); /* direct nvmem device read/write interface */ struct nvmem_device *nvmem_device_get(struct device *dev, const char *name); @@ -85,6 +89,12 @@ static inline int nvmem_cell_write(struct nvmem_cell *cell, return -ENOSYS; } +static inline int nvmem_cell_read_u32(struct device *dev, + const char *cell_id, u32 *val) +{ + return -ENOSYS; +} + static inline struct nvmem_device *nvmem_device_get(struct device *dev, const char *name) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index cd93416d762e..497706f5adca 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -12,6 +12,9 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include <linux/err.h> +#include <linux/errno.h> + struct nvmem_device; struct nvmem_cell_info; typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, diff --git a/include/linux/of.h b/include/linux/of.h index 50fcdb54087f..cfc34117fc92 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -100,10 +100,11 @@ struct of_reconfig_data { /* initialize a node */ extern struct kobj_type of_node_ktype; +extern const struct fwnode_operations of_fwnode_ops; static inline void of_node_init(struct device_node *node) { kobject_init(&node->kobj, &of_node_ktype); - node->fwnode.type = FWNODE_OF; + node->fwnode.ops = &of_fwnode_ops; } /* true when node is initialized */ @@ -148,18 +149,28 @@ extern raw_spinlock_t devtree_lock; #ifdef CONFIG_OF void of_core_init(void); -static inline bool is_of_node(struct fwnode_handle *fwnode) +static inline bool is_of_node(const struct fwnode_handle *fwnode) { - return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_OF; + return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &of_fwnode_ops; } -static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) -{ - return is_of_node(fwnode) ? - container_of(fwnode, struct device_node, fwnode) : NULL; -} +#define to_of_node(__fwnode) \ + ({ \ + typeof(__fwnode) __to_of_node_fwnode = (__fwnode); \ + \ + is_of_node(__to_of_node_fwnode) ? \ + container_of(__to_of_node_fwnode, \ + struct device_node, fwnode) : \ + NULL; \ + }) -#define of_fwnode_handle(node) (&(node)->fwnode) +#define of_fwnode_handle(node) \ + ({ \ + typeof(node) __of_fwnode_handle_node = (node); \ + \ + __of_fwnode_handle_node ? \ + &__of_fwnode_handle_node->fwnode : NULL; \ + }) static inline bool of_have_populated_dt(void) { @@ -533,12 +544,12 @@ static inline void of_core_init(void) { } -static inline bool is_of_node(struct fwnode_handle *fwnode) +static inline bool is_of_node(const struct fwnode_handle *fwnode) { return false; } -static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) +static inline struct device_node *to_of_node(const struct fwnode_handle *fwnode) { return NULL; } @@ -627,6 +638,12 @@ static inline int of_device_is_compatible(const struct device_node *device, return 0; } +static inline int of_device_compatible_match(struct device_node *device, + const char *const *compat) +{ + return 0; +} + static inline bool of_device_is_available(const struct device_node *device) { return false; diff --git a/include/linux/of_device.h b/include/linux/of_device.h index b4ad8b4f8506..611502524425 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -50,7 +50,7 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) struct device *cpu_dev; cpu_dev = get_cpu_device(cpu); if (!cpu_dev) - return NULL; + return of_get_cpu_node(cpu, NULL); return of_node_get(cpu_dev->of_node); } diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 1dfbfd0d8040..013c5418aeec 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -31,9 +31,6 @@ extern void *of_fdt_get_property(const void *blob, unsigned long node, const char *name, int *size); -extern int of_fdt_is_compatible(const void *blob, - unsigned long node, - const char *compat); extern bool of_fdt_is_big_endian(const void *blob, unsigned long node); extern int of_fdt_match(const void *blob, unsigned long node, diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 1e089d5a182b..ca10f43564de 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -31,6 +31,7 @@ enum of_gpio_flags { OF_GPIO_ACTIVE_LOW = 0x1, OF_GPIO_SINGLE_ENDED = 0x2, OF_GPIO_OPEN_DRAIN = 0x4, + OF_GPIO_SLEEP_MAY_LOOSE_VALUE = 0x8, }; #ifdef CONFIG_OF_GPIO diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h index abdb02eaef06..3e058f05ab04 100644 --- a/include/linux/of_graph.h +++ b/include/linux/of_graph.h @@ -43,11 +43,15 @@ struct of_endpoint { #ifdef CONFIG_OF int of_graph_parse_endpoint(const struct device_node *node, struct of_endpoint *endpoint); +int of_graph_get_endpoint_count(const struct device_node *np); struct device_node *of_graph_get_port_by_id(struct device_node *node, u32 id); struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, struct device_node *previous); struct device_node *of_graph_get_endpoint_by_regs( const struct device_node *parent, int port_reg, int reg); +struct device_node *of_graph_get_remote_endpoint( + const struct device_node *node); +struct device_node *of_graph_get_port_parent(struct device_node *node); struct device_node *of_graph_get_remote_port_parent( const struct device_node *node); struct device_node *of_graph_get_remote_port(const struct device_node *node); @@ -61,6 +65,11 @@ static inline int of_graph_parse_endpoint(const struct device_node *node, return -ENOSYS; } +static inline int of_graph_get_endpoint_count(const struct device_node *np) +{ + return 0; +} + static inline struct device_node *of_graph_get_port_by_id( struct device_node *node, u32 id) { @@ -80,6 +89,18 @@ static inline struct device_node *of_graph_get_endpoint_by_regs( return NULL; } +static inline struct device_node *of_graph_get_remote_endpoint( + const struct device_node *node) +{ + return NULL; +} + +static inline struct device_node *of_graph_get_port_parent( + struct device_node *node) +{ + return NULL; +} + static inline struct device_node *of_graph_get_remote_port_parent( const struct device_node *node) { diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index ba35ba520487..f5db93bcd069 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -27,11 +27,33 @@ struct phy_device *of_phy_attach(struct net_device *dev, phy_interface_t iface); extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); -extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np); extern int of_phy_register_fixed_link(struct device_node *np); extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); + +static inline int of_mdio_parse_addr(struct device *dev, + const struct device_node *np) +{ + u32 addr; + int ret; + + ret = of_property_read_u32(np, "reg", &addr); + if (ret < 0) { + dev_err(dev, "%s has invalid PHY address\n", np->full_name); + return ret; + } + + /* A PHY must have a reg property in the range [0-31] */ + if (addr >= PHY_MAX_ADDR) { + dev_err(dev, "%s PHY address %i is too large\n", + np->full_name, addr); + return -EINVAL; + } + + return addr; +} + #else /* CONFIG_OF_MDIO */ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { diff --git a/include/linux/once.h b/include/linux/once.h index 285f12cb40e6..9c98aaa87cbc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -53,5 +53,7 @@ void __do_once_done(bool *done, struct static_key *once_key, #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) +#define get_random_once_wait(buf, nbytes) \ + DO_ONCE(get_random_bytes_wait, (buf), (nbytes)) \ #endif /* _LINUX_ONCE_H */ diff --git a/include/linux/oom.h b/include/linux/oom.h index 8a266e2be5a6..76aac4ce39bc 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -6,6 +6,8 @@ #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> +#include <linux/sched/coredump.h> /* MMF_* */ +#include <linux/mm.h> /* VM_FAULT* */ struct zonelist; struct notifier_block; @@ -63,6 +65,26 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) return tsk->signal->oom_mm; } +/* + * Checks whether a page fault on the given mm is still reliable. + * This is no longer true if the oom reaper started to reap the + * address space which is reflected by MMF_UNSTABLE flag set in + * the mm. At that moment any !shared mapping would lose the content + * and could cause a memory corruption (zero pages instead of the + * original content). + * + * User should call this before establishing a page table entry for + * a !shared mapping and under the proper page table lock. + * + * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. + */ +static inline int check_stable_address_space(struct mm_struct *mm) +{ + if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) + return VM_FAULT_SIGBUS; + return 0; +} + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); diff --git a/include/linux/padata.h b/include/linux/padata.h index 0f9e567d5e15..2f9c1f93b1ce 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -166,9 +166,6 @@ struct padata_instance { extern struct padata_instance *padata_alloc_possible( struct workqueue_struct *wq); -extern struct padata_instance *padata_alloc(struct workqueue_struct *wq, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask); extern void padata_free(struct padata_instance *pinst); extern int padata_do_parallel(struct padata_instance *pinst, struct padata_priv *padata, int cb_cpu); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6b5818d6de32..ba2d470d2d0a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,8 +303,8 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ -TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND) - TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND) +TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) + TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ @@ -326,11 +326,14 @@ PAGEFLAG_FALSE(HighMem) #ifdef CONFIG_SWAP static __always_inline int PageSwapCache(struct page *page) { +#ifdef CONFIG_THP_SWAP + page = compound_head(page); +#endif return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); } -SETPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) -CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) +SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) +CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) #else PAGEFLAG_FALSE(SwapCache) #endif diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 610e13271918..1fd71733aa68 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -174,6 +174,7 @@ static inline void page_ref_unfreeze(struct page *page, int count) VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); + smp_mb(); atomic_set(&page->_refcount, count); if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) __page_ref_unfreeze(page, count); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 316a19f6b635..5bbd6780f205 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -28,14 +28,33 @@ enum mapping_flags { AS_NO_WRITEBACK_TAGS = 5, }; +/** + * mapping_set_error - record a writeback error in the address_space + * @mapping - the mapping in which an error should be set + * @error - the error to set in the mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * mapping_set_error to record the error in the mapping so that it can be + * reported when the application calls fsync(2). + */ static inline void mapping_set_error(struct address_space *mapping, int error) { - if (unlikely(error)) { - if (error == -ENOSPC) - set_bit(AS_ENOSPC, &mapping->flags); - else - set_bit(AS_EIO, &mapping->flags); - } + if (likely(!error)) + return; + + /* Record in wb_err for checkers using errseq_t based tracking */ + filemap_set_wb_err(mapping, error); + + /* Record it in flags for now, for legacy callers */ + if (error == -ENOSPC) + set_bit(AS_ENOSPC, &mapping->flags); + else + set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) @@ -144,8 +163,6 @@ void release_pages(struct page **pages, int nr, bool cold); */ static inline int page_cache_get_speculative(struct page *page) { - VM_BUG_ON(in_interrupt()); - #ifdef CONFIG_TINY_RCU # ifdef CONFIG_PREEMPT_COUNT VM_BUG_ON(!in_atomic() && !irqs_disabled()); @@ -336,8 +353,16 @@ struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); -unsigned find_get_pages(struct address_space *mapping, pgoff_t start, - unsigned int nr_pages, struct page **pages); +unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, + pgoff_t end, unsigned int nr_pages, + struct page **pages); +static inline unsigned find_get_pages(struct address_space *mapping, + pgoff_t *start, unsigned int nr_pages, + struct page **pages) +{ + return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, + pages); +} unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, @@ -524,7 +549,7 @@ void page_endio(struct page *page, bool is_write, int err); /* * Add an arbitrary waiter to a page's wait queue */ -extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter); +extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index b45d391b4540..4dcd5506f1ed 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -27,8 +27,16 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec, pgoff_t start, unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); -unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, - pgoff_t start, unsigned nr_pages); +unsigned pagevec_lookup_range(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t *start, pgoff_t end); +static inline unsigned pagevec_lookup(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t *start) +{ + return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); +} + unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, int tag, unsigned nr_pages); diff --git a/include/linux/path.h b/include/linux/path.h index d1372186f431..cde895cc4af4 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -7,7 +7,7 @@ struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; -}; +} __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 7a4e83a8c89c..dd86c97f2454 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -105,7 +105,7 @@ static inline void acpiphp_remove_slots(struct pci_bus *bus) { } static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { } #endif -extern const u8 pci_acpi_dsm_uuid[]; +extern const guid_t pci_acpi_dsm_guid; #define DEVICE_LABEL_DSM 0x07 #define RESET_DELAY_DSM 0x08 #define FUNCTION_DELAY_DSM 0x09 diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 57e0b8250947..782fb8e0755f 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -7,6 +7,7 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); +void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); #else /* CONFIG_PCI_PRI */ @@ -20,6 +21,10 @@ static inline void pci_disable_pri(struct pci_dev *pdev) { } +static inline void pci_restore_pri_state(struct pci_dev *pdev) +{ +} + static inline int pci_reset_pri(struct pci_dev *pdev) { return -ENODEV; @@ -31,6 +36,7 @@ static inline int pci_reset_pri(struct pci_dev *pdev) int pci_enable_pasid(struct pci_dev *pdev, int features); void pci_disable_pasid(struct pci_dev *pdev); +void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); @@ -45,6 +51,10 @@ static inline void pci_disable_pasid(struct pci_dev *pdev) { } +static inline void pci_restore_pasid_state(struct pci_dev *pdev) +{ +} + static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index af5edbf3eea3..f7a04e1af112 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -62,11 +62,13 @@ struct pci_epc_ops { * @size: the size of the PCI address space * @bitmap: bitmap to manage the PCI address space * @pages: number of bits representing the address region + * @page_size: size of each page */ struct pci_epc_mem { phys_addr_t phys_base; size_t size; unsigned long *bitmap; + size_t page_size; int pages; }; @@ -98,6 +100,9 @@ struct pci_epc { #define devm_pci_epc_create(dev, ops) \ __devm_pci_epc_create((dev), (ops), THIS_MODULE) +#define pci_epc_mem_init(epc, phys_addr, size) \ + __pci_epc_mem_init((epc), (phys_addr), (size), PAGE_SIZE) + static inline void epc_set_drvdata(struct pci_epc *epc, void *data) { dev_set_drvdata(&epc->dev, data); @@ -135,7 +140,8 @@ void pci_epc_stop(struct pci_epc *epc); struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); -int pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size); +int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size, + size_t page_size); void pci_epc_mem_exit(struct pci_epc *epc); void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, phys_addr_t *phys_addr, size_t size); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 0d529cb90143..60d551a9a1ba 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -14,17 +14,10 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> +#include <linux/pci.h> struct pci_epf; -enum pci_interrupt_pin { - PCI_INTERRUPT_UNKNOWN, - PCI_INTERRUPT_INTA, - PCI_INTERRUPT_INTB, - PCI_INTERRUPT_INTC, - PCI_INTERRUPT_INTD, -}; - enum pci_barno { BAR_0, BAR_1, @@ -149,6 +142,8 @@ static inline void *epf_get_drvdata(struct pci_epf *epf) return dev_get_drvdata(&epf->dev); } +const struct pci_epf_device_id * +pci_epf_match_device(const struct pci_epf_device_id *id, struct pci_epf *epf); struct pci_epf *pci_epf_create(const char *name); void pci_epf_destroy(struct pci_epf *epf); int __pci_epf_register_driver(struct pci_epf_driver *driver, diff --git a/include/linux/pci.h b/include/linux/pci.h index 8039f9f0ca05..f68c58a93dd0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -102,6 +102,28 @@ enum { DEVICE_COUNT_RESOURCE = PCI_NUM_RESOURCES, }; +/** + * enum pci_interrupt_pin - PCI INTx interrupt values + * @PCI_INTERRUPT_UNKNOWN: Unknown or unassigned interrupt + * @PCI_INTERRUPT_INTA: PCI INTA pin + * @PCI_INTERRUPT_INTB: PCI INTB pin + * @PCI_INTERRUPT_INTC: PCI INTC pin + * @PCI_INTERRUPT_INTD: PCI INTD pin + * + * Corresponds to values for legacy PCI INTx interrupts, as can be found in the + * PCI_INTERRUPT_PIN register. + */ +enum pci_interrupt_pin { + PCI_INTERRUPT_UNKNOWN, + PCI_INTERRUPT_INTA, + PCI_INTERRUPT_INTB, + PCI_INTERRUPT_INTC, + PCI_INTERRUPT_INTD, +}; + +/* The number of legacy PCI INTx interrupts */ +#define PCI_NUM_INTX 4 + /* * pci_power_t values must match the bits in the Capabilities PME_Support * and Control/Status PowerState fields in the Power Management capability. @@ -188,6 +210,8 @@ enum pci_dev_flags { * the direct_complete optimization. */ PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11), + /* Don't use Relaxed Ordering for TLPs directed at this device */ + PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 12), }; enum pci_irq_reroute_variant { @@ -307,7 +331,6 @@ struct pci_dev { u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ - unsigned int pme_interrupt:1; unsigned int pme_poll:1; /* Poll device's PME status bit */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ @@ -361,6 +384,8 @@ struct pci_dev { unsigned int msix_enabled:1; unsigned int ari_enabled:1; /* ARI forwarding */ unsigned int ats_enabled:1; /* Address Translation Service */ + unsigned int pasid_enabled:1; /* Process Address Space ID */ + unsigned int pri_enabled:1; /* Page Request Interface */ unsigned int is_managed:1; unsigned int needs_freset:1; /* Dev requires fundamental reset */ unsigned int state_saved:1; @@ -371,11 +396,12 @@ struct pci_dev { unsigned int is_thunderbolt:1; /* Thunderbolt controller */ unsigned int __aer_firmware_first_valid:1; unsigned int __aer_firmware_first:1; - unsigned int broken_intx_masking:1; + unsigned int broken_intx_masking:1; /* INTx masking can't be used */ unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */ unsigned int irq_managed:1; unsigned int has_secondary_link:1; unsigned int non_compliant_bars:1; /* broken BARs; ignore them */ + unsigned int is_probed:1; /* device probing in progress */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -404,6 +430,12 @@ struct pci_dev { u8 ats_stu; /* ATS Smallest Translation Unit */ atomic_t ats_ref_cnt; /* number of VFs with ATS enabled */ #endif +#ifdef CONFIG_PCI_PRI + u32 pri_reqs_alloc; /* Number of PRI requests allocated */ +#endif +#ifdef CONFIG_PCI_PASID + u16 pasid_features; +#endif phys_addr_t rom; /* Physical address of ROM if it's not from the BAR */ size_t romlen; /* Length of ROM if it's not from the BAR */ char *driver_override; /* Driver name to force a match */ @@ -437,10 +469,13 @@ struct pci_host_bridge { void *sysdata; int busnr; struct list_head windows; /* resource_entry */ + u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* platform IRQ swizzler */ + int (*map_irq)(const struct pci_dev *, u8, u8); void (*release_fn)(struct pci_host_bridge *); void *release_data; struct msi_controller *msi; unsigned int ignore_reset_delay:1; /* for entire hierarchy */ + unsigned int no_ext_tags:1; /* no Extended Tags */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, const struct resource *res, @@ -463,7 +498,9 @@ static inline struct pci_host_bridge *pci_host_bridge_from_priv(void *priv) } struct pci_host_bridge *pci_alloc_host_bridge(size_t priv); -int pci_register_host_bridge(struct pci_host_bridge *bridge); +struct pci_host_bridge *devm_pci_alloc_host_bridge(struct device *dev, + size_t priv); +void pci_free_host_bridge(struct pci_host_bridge *bridge); struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus); void pci_set_host_bridge_release(struct pci_host_bridge *bridge, @@ -695,7 +732,8 @@ struct pci_error_handlers { pci_ers_result_t (*slot_reset)(struct pci_dev *dev); /* PCI function reset prepare or completed */ - void (*reset_notify)(struct pci_dev *dev, bool prepare); + void (*reset_prepare)(struct pci_dev *dev); + void (*reset_done)(struct pci_dev *dev); /* Device driver may resume normal operations */ void (*resume)(struct pci_dev *dev); @@ -716,6 +754,7 @@ struct pci_driver { void (*shutdown) (struct pci_dev *dev); int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* PF pdev */ const struct pci_error_handlers *err_handler; + const struct attribute_group **groups; struct device_driver driver; struct pci_dynids dynids; }; @@ -831,7 +870,6 @@ char *pcibios_setup(char *str); resource_size_t pcibios_align_resource(void *, const struct resource *, resource_size_t, resource_size_t); -void pcibios_update_irq(struct pci_dev *, int irq); /* Weak but can be overriden by arch */ void pci_fixup_cardbus(struct pci_bus *); @@ -852,13 +890,10 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int busmax); int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax); void pci_bus_release_busn_res(struct pci_bus *b); -struct pci_bus *pci_scan_root_bus_msi(struct device *parent, int bus, - struct pci_ops *ops, void *sysdata, - struct list_head *resources, - struct msi_controller *msi); struct pci_bus *pci_scan_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, struct list_head *resources); +int pci_scan_root_bus_bridge(struct pci_host_bridge *bridge); struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr); void pcie_update_link_speed(struct pci_bus *bus, u16 link_status); @@ -1008,6 +1043,15 @@ int __must_check pci_reenable_device(struct pci_dev *); int __must_check pcim_enable_device(struct pci_dev *pdev); void pcim_pin_device(struct pci_dev *pdev); +static inline bool pci_intx_mask_supported(struct pci_dev *pdev) +{ + /* + * INTx masking is supported if PCI_COMMAND_INTX_DISABLE is + * writable and no quirk has marked the feature broken. + */ + return !pdev->broken_intx_masking; +} + static inline int pci_is_enabled(struct pci_dev *pdev) { return (atomic_read(&pdev->enable_cnt) > 0); @@ -1031,7 +1075,6 @@ int __must_check pci_set_mwi(struct pci_dev *dev); int pci_try_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); void pci_intx(struct pci_dev *dev, int enable); -bool pci_intx_mask_supported(struct pci_dev *dev); bool pci_check_and_mask_intx(struct pci_dev *dev); bool pci_check_and_unmask_intx(struct pci_dev *dev); int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask); @@ -1049,6 +1092,7 @@ void pcie_flr(struct pci_dev *dev); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); @@ -1098,8 +1142,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); void pci_pme_active(struct pci_dev *dev, bool enable); -int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, - bool runtime, bool enable); +int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable); int pci_wake_from_d3(struct pci_dev *dev, bool enable); int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); @@ -1108,12 +1151,7 @@ bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); - -static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, - bool enable) -{ - return __pci_enable_wake(dev, state, false, enable); -} +bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev); @@ -1149,8 +1187,7 @@ void pci_assign_unassigned_bus_resources(struct pci_bus *bus); void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus); void pdev_enable_device(struct pci_dev *); int pci_enable_resources(struct pci_dev *, int mask); -void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), - int (*)(const struct pci_dev *, u8, u8)); +void pci_assign_irq(struct pci_dev *dev); struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res); #define HAVE_PCI_REQ_REGIONS 2 int __must_check pci_request_regions(struct pci_dev *, const char *); @@ -1382,6 +1419,38 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, NULL); } +/** + * pci_irqd_intx_xlate() - Translate PCI INTx value to an IRQ domain hwirq + * @d: the INTx IRQ domain + * @node: the DT node for the device whose interrupt we're translating + * @intspec: the interrupt specifier data from the DT + * @intsize: the number of entries in @intspec + * @out_hwirq: pointer at which to write the hwirq number + * @out_type: pointer at which to write the interrupt type + * + * Translate a PCI INTx interrupt number from device tree in the range 1-4, as + * stored in the standard PCI_INTERRUPT_PIN register, to a value in the range + * 0-3 suitable for use in a 4 entry IRQ domain. That is, subtract one from the + * INTx value to obtain the hwirq number. + * + * Returns 0 on success, or -EINVAL if the interrupt specifier is out of range. + */ +static inline int pci_irqd_intx_xlate(struct irq_domain *d, + struct device_node *node, + const u32 *intspec, + unsigned int intsize, + unsigned long *out_hwirq, + unsigned int *out_type) +{ + const u32 intx = intspec[0]; + + if (intx < PCI_INTERRUPT_INTA || intx > PCI_INTERRUPT_INTD) + return -EINVAL; + + *out_hwirq = intx - PCI_INTERRUPT_INTA; + return 0; +} + #ifdef CONFIG_PCIEPORTBUS extern bool pcie_ports_disabled; extern bool pcie_ports_auto; @@ -2047,7 +2116,7 @@ static inline u16 pci_vpd_lrdt_tag(const u8 *lrdt) /** * pci_vpd_srdt_size - Extracts the Small Resource Data Type length - * @lrdt: Pointer to the beginning of the Small Resource Data Type tag + * @srdt: Pointer to the beginning of the Small Resource Data Type tag * * Returns the extracted Small Resource Data Type length. */ @@ -2058,7 +2127,7 @@ static inline u8 pci_vpd_srdt_size(const u8 *srdt) /** * pci_vpd_srdt_tag - Extracts the Small Resource Data Type Tag Item - * @lrdt: Pointer to the beginning of the Small Resource Data Type tag + * @srdt: Pointer to the beginning of the Small Resource Data Type tag * * Returns the extracted Small Resource Data Type Tag Item. */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 5f6b71d15393..4adf6161ec77 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -576,6 +576,7 @@ #define PCI_DEVICE_ID_AMD_CS5536_EHC 0x2095 #define PCI_DEVICE_ID_AMD_CS5536_UDC 0x2096 #define PCI_DEVICE_ID_AMD_CS5536_UOC 0x2097 +#define PCI_DEVICE_ID_AMD_CS5536_DEV_IDE 0x2092 #define PCI_DEVICE_ID_AMD_CS5536_IDE 0x209A #define PCI_DEVICE_ID_AMD_LX_VIDEO 0x2081 #define PCI_DEVICE_ID_AMD_LX_AES 0x2082 @@ -1373,6 +1374,8 @@ #define PCI_DEVICE_ID_TTI_HPT374 0x0008 #define PCI_DEVICE_ID_TTI_HPT372N 0x0009 /* apparently a 372N variant? */ +#define PCI_VENDOR_ID_SIGMA 0x1105 + #define PCI_VENDOR_ID_VIA 0x1106 #define PCI_DEVICE_ID_VIA_8763_0 0x0198 #define PCI_DEVICE_ID_VIA_8380_0 0x0204 diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index afcd130ab3a9..e8f3f7479224 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -38,7 +38,7 @@ static inline void set_service_data(struct pcie_device *dev, void *data) dev->priv_data = data; } -static inline void* get_service_data(struct pcie_device *dev) +static inline void *get_service_data(struct pcie_device *dev) { return dev->priv_data; } @@ -50,8 +50,8 @@ struct pcie_port_service_driver { int (*suspend) (struct pcie_device *dev); int (*resume) (struct pcie_device *dev); - /* Service Error Recovery Handler */ - const struct pci_error_handlers *err_handler; + /* Device driver may resume normal operations */ + void (*error_resume)(struct pci_dev *dev); /* Link Reset Capability - AER service driver specific */ pci_ers_result_t (*reset_link) (struct pci_dev *dev); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 491b3f5a5f8a..6a5fb939d3e5 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -21,6 +21,25 @@ /* minimum unit size, also is the maximum supported allocation size */ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) +/* minimum allocation size and shift in bytes */ +#define PCPU_MIN_ALLOC_SHIFT 2 +#define PCPU_MIN_ALLOC_SIZE (1 << PCPU_MIN_ALLOC_SHIFT) + +/* number of bits per page, used to trigger a scan if blocks are > PAGE_SIZE */ +#define PCPU_BITS_PER_PAGE (PAGE_SIZE >> PCPU_MIN_ALLOC_SHIFT) + +/* + * This determines the size of each metadata block. There are several subtle + * constraints around this constant. The reserved region must be a multiple of + * PCPU_BITMAP_BLOCK_SIZE. Additionally, PCPU_BITMAP_BLOCK_SIZE must be a + * multiple of PAGE_SIZE or PAGE_SIZE must be a multiple of + * PCPU_BITMAP_BLOCK_SIZE to align with the populated page map. The unit_size + * also has to be a multiple of PCPU_BITMAP_BLOCK_SIZE to ensure full blocks. + */ +#define PCPU_BITMAP_BLOCK_SIZE PAGE_SIZE +#define PCPU_BITMAP_BLOCK_BITS (PCPU_BITMAP_BLOCK_SIZE >> \ + PCPU_MIN_ALLOC_SHIFT) + /* * Percpu allocator can serve percpu allocations before slab is * initialized which allows slab to depend on the percpu allocator. @@ -116,7 +135,6 @@ extern bool is_kernel_percpu_address(unsigned long addr); #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) extern void __init setup_per_cpu_areas(void); #endif -extern void __init percpu_init_late(void); extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp); extern void __percpu *__alloc_percpu(size_t size, size_t align); diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 84a109449610..ec065387f443 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -39,7 +39,8 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); -void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, + s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); @@ -50,7 +51,7 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { - __percpu_counter_add(fbc, amount, percpu_counter_batch); + percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) @@ -136,7 +137,7 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) } static inline void -__percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) +percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 1360dd6d5e61..af0f44effd44 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -24,10 +24,14 @@ * interrupt and passed the address of the low level handler, * and can be used to implement any platform specific handling * before or after calling it. + * + * @irq_flags: if non-zero, these flags will be passed to request_irq + * when requesting interrupts for this PMU device. */ struct arm_pmu_platdata { irqreturn_t (*handle_irq)(int irq, void *dev, irq_handler_t pmu_handler); + unsigned long irq_flags; }; #ifdef CONFIG_ARM_PMU diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 24a635887f28..8e22f24ded6a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -139,17 +139,6 @@ struct hw_perf_event { /* for tp_event->class */ struct list_head tp_list; }; - struct { /* intel_cqm */ - int cqm_state; - u32 cqm_rmid; - int is_group_event; - struct list_head cqm_events_entry; - struct list_head cqm_groups_entry; - struct list_head cqm_group_entry; - }; - struct { /* itrace */ - int itrace_started; - }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; @@ -310,8 +299,8 @@ struct pmu { * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ - void (*event_mapped) (struct perf_event *event); /*optional*/ - void (*event_unmapped) (struct perf_event *event); /*optional*/ + void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ + void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are @@ -417,11 +406,6 @@ struct pmu { /* - * Return the count value for a counter. - */ - u64 (*count) (struct perf_event *event); /*optional*/ - - /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (int cpu, void **pages, @@ -541,6 +525,7 @@ struct swevent_hlist { #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 +#define PERF_ATTACH_ITRACE 0x10 struct perf_cgroup; struct ring_buffer; @@ -801,6 +786,8 @@ struct perf_cpu_context { struct list_head sched_cb_entry; int sched_cb_usage; + + int online; }; struct perf_output_handle { @@ -862,6 +849,7 @@ extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); +extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); @@ -896,7 +884,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -extern u64 perf_event_read_local(struct perf_event *event); +int perf_event_read_local(struct perf_event *event, u64 *value); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -942,6 +930,8 @@ struct perf_sample_data { struct perf_regs regs_intr; u64 stack_user_size; + + u64 phys_addr; } ____cacheline_aligned; /* default value for data source */ @@ -1109,11 +1099,6 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, __perf_event_task_sched_out(prev, next); } -static inline u64 __perf_event_count(struct perf_event *event) -{ - return local64_read(&event->count) + atomic64_read(&event->child_count); -} - extern void perf_event_mmap(struct vm_area_struct *vma); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); @@ -1199,7 +1184,7 @@ extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, - struct task_struct *task); + struct task_struct *task, struct perf_event *event); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags @@ -1301,7 +1286,10 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event * { return ERR_PTR(-EINVAL); } -static inline u64 perf_event_read_local(struct perf_event *event) { return -EINVAL; } +static inline int perf_event_read_local(struct perf_event *event, u64 *value) +{ + return -EINVAL; +} static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } diff --git a/include/linux/phy.h b/include/linux/phy.h index e76e4adbc7c7..d78cd01ea513 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -58,13 +58,13 @@ #define PHY_IGNORE_INTERRUPT -2 #define PHY_HAS_INTERRUPT 0x00000001 -#define PHY_HAS_MAGICANEG 0x00000002 -#define PHY_IS_INTERNAL 0x00000004 +#define PHY_IS_INTERNAL 0x00000002 #define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ typedef enum { PHY_INTERFACE_MODE_NA, + PHY_INTERFACE_MODE_INTERNAL, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, @@ -84,6 +84,9 @@ typedef enum { PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_RXAUI, + PHY_INTERFACE_MODE_XAUI, + /* 10GBASE-KR, XFI, SFI - single lane 10G Serdes */ + PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -112,6 +115,8 @@ static inline const char *phy_modes(phy_interface_t interface) switch (interface) { case PHY_INTERFACE_MODE_NA: return ""; + case PHY_INTERFACE_MODE_INTERNAL: + return "internal"; case PHY_INTERFACE_MODE_MII: return "mii"; case PHY_INTERFACE_MODE_GMII: @@ -150,6 +155,10 @@ static inline const char *phy_modes(phy_interface_t interface) return "2500base-x"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; + case PHY_INTERFACE_MODE_XAUI: + return "xaui"; + case PHY_INTERFACE_MODE_10GKR: + return "10gbase-kr"; default: return "unknown"; } @@ -173,6 +182,7 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_ADDR_C45 (1<<30) struct device; +struct phylink; struct sk_buff; /* @@ -220,10 +230,8 @@ struct mii_bus { /* GPIO reset pulse width in microseconds */ int reset_delay_us; - /* Number of reset GPIOs */ - int num_reset_gpios; - /* Array of RESET GPIO descriptors */ - struct gpio_desc **reset_gpiod; + /* RESET GPIO descriptor pointer */ + struct gpio_desc *reset_gpiod; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) @@ -364,6 +372,8 @@ struct phy_c45_device_ids { * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. + * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. + * loopback_enabled: Set true if this phy has been loopbacked successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. * link_timeout: The number of timer firings to wait before the @@ -400,6 +410,8 @@ struct phy_device { bool is_pseudo_fixed_link; bool has_fixups; bool suspended; + bool sysfs_links; + bool loopback_enabled; enum phy_state state; @@ -458,11 +470,13 @@ struct phy_device { struct mutex lock; + struct phylink *phylink; struct net_device *attached_dev; u8 mdix; u8 mdix_ctrl; + void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); void (*adjust_link)(struct net_device *dev); }; #define to_phy_device(d) container_of(to_mdio_device(d), \ @@ -639,6 +653,7 @@ struct phy_driver { int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); + int (*set_loopback)(struct phy_device *dev, bool enable); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) @@ -655,6 +670,24 @@ struct phy_fixup { int (*run)(struct phy_device *phydev); }; +const char *phy_speed_to_str(int speed); +const char *phy_duplex_to_str(unsigned int duplex); + +/* A structure for mapping a particular speed and duplex + * combination to a particular SUPPORTED and ADVERTISED value + */ +struct phy_setting { + u32 speed; + u8 duplex; + u8 bit; +}; + +const struct phy_setting * +phy_lookup_setting(int speed, int duplex, const unsigned long *mask, + size_t maxbit, bool exact); +size_t phy_speeds(unsigned int *speeds, size_t size, + unsigned long *mask, size_t maxbit); + /** * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. @@ -717,14 +750,24 @@ static inline bool phy_is_internal(struct phy_device *phydev) } /** + * phy_interface_mode_is_rgmii - Convenience function for testing if a + * PHY interface mode is RGMII (all variants) + * @mode: the phy_interface_t enum + */ +static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) +{ + return mode >= PHY_INTERFACE_MODE_RGMII && + mode <= PHY_INTERFACE_MODE_RGMII_TXID; +}; + +/** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) * @phydev: the phy_device struct */ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { - return phydev->interface >= PHY_INTERFACE_MODE_RGMII && - phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID; + return phy_interface_mode_is_rgmii(phydev->interface); }; /* @@ -774,6 +817,7 @@ void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); +int phy_loopback(struct phy_device *phydev, bool enable); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); @@ -793,6 +837,7 @@ int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); int phy_stop_interrupts(struct phy_device *phydev); +int phy_restart_aneg(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { @@ -806,7 +851,7 @@ static inline int phy_read_status(struct phy_device *phydev) dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ - dev_dbg(&_phydev->mdio.dev, format, ##args); + dev_dbg(&_phydev->mdio.dev, format, ##args) static inline const char *phydev_name(const struct phy_device *phydev) { @@ -816,6 +861,8 @@ static inline const char *phydev_name(const struct phy_device *phydev) void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); void phy_attached_info(struct phy_device *phydev); + +/* Clause 22 PHY */ int genphy_config_init(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); @@ -825,11 +872,22 @@ int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); +int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; } + +/* Clause 45 PHY */ +int genphy_c45_restart_aneg(struct phy_device *phydev); +int genphy_c45_aneg_done(struct phy_device *phydev); +int genphy_c45_read_link(struct phy_device *phydev, u32 mmd_mask); +int genphy_c45_read_lpa(struct phy_device *phydev); +int genphy_c45_read_pma(struct phy_device *phydev); +int genphy_c45_pma_setup_forced(struct phy_device *phydev); +int genphy_c45_an_disable_aneg(struct phy_device *phydev); + void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); @@ -843,9 +901,8 @@ void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); void phy_trigger_machine(struct phy_device *phydev, bool sync); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); -int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); -int phy_ethtool_ksettings_get(struct phy_device *phydev, - struct ethtool_link_ksettings *cmd); +void phy_ethtool_ksettings_get(struct phy_device *phydev, + struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 78bb0d7f6b11..e694d4008c4a 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -27,6 +27,8 @@ enum phy_mode { PHY_MODE_USB_HOST, PHY_MODE_USB_DEVICE, PHY_MODE_USB_OTG, + PHY_MODE_SGMII, + PHY_MODE_10GKR, }; /** diff --git a/include/linux/phy/ulpi_phy.h b/include/linux/phy/ulpi_phy.h new file mode 100644 index 000000000000..f2ebe490a4bc --- /dev/null +++ b/include/linux/phy/ulpi_phy.h @@ -0,0 +1,31 @@ +#include <linux/phy/phy.h> + +/** + * Helper that registers PHY for a ULPI device and adds a lookup for binding it + * and it's controller, which is always the parent. + */ +static inline struct phy +*ulpi_phy_create(struct ulpi *ulpi, const struct phy_ops *ops) +{ + struct phy *phy; + int ret; + + phy = phy_create(&ulpi->dev, NULL, ops); + if (IS_ERR(phy)) + return phy; + + ret = phy_create_lookup(phy, "usb2-phy", dev_name(ulpi->dev.parent)); + if (ret) { + phy_destroy(phy); + return ERR_PTR(ret); + } + + return phy; +} + +/* Remove a PHY that was created with ulpi_phy_create() and it's lookup. */ +static inline void ulpi_phy_destroy(struct ulpi *ulpi, struct phy *phy) +{ + phy_remove_lookup(phy, "usb2-phy", dev_name(ulpi->dev.parent)); + phy_destroy(phy); +} diff --git a/include/linux/phylink.h b/include/linux/phylink.h new file mode 100644 index 000000000000..af67edd4ae38 --- /dev/null +++ b/include/linux/phylink.h @@ -0,0 +1,148 @@ +#ifndef NETDEV_PCS_H +#define NETDEV_PCS_H + +#include <linux/phy.h> +#include <linux/spinlock.h> +#include <linux/workqueue.h> + +struct device_node; +struct ethtool_cmd; +struct net_device; + +enum { + MLO_PAUSE_NONE, + MLO_PAUSE_ASYM = BIT(0), + MLO_PAUSE_SYM = BIT(1), + MLO_PAUSE_RX = BIT(2), + MLO_PAUSE_TX = BIT(3), + MLO_PAUSE_TXRX_MASK = MLO_PAUSE_TX | MLO_PAUSE_RX, + MLO_PAUSE_AN = BIT(4), + + MLO_AN_PHY = 0, /* Conventional PHY */ + MLO_AN_FIXED, /* Fixed-link mode */ + MLO_AN_SGMII, /* Cisco SGMII protocol */ + MLO_AN_8023Z, /* 1000base-X protocol */ +}; + +static inline bool phylink_autoneg_inband(unsigned int mode) +{ + return mode == MLO_AN_SGMII || mode == MLO_AN_8023Z; +} + +struct phylink_link_state { + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + phy_interface_t interface; /* PHY_INTERFACE_xxx */ + int speed; + int duplex; + int pause; + unsigned int link:1; + unsigned int an_enabled:1; + unsigned int an_complete:1; +}; + +struct phylink_mac_ops { + /** + * validate: validate and update the link configuration + * @ndev: net_device structure associated with MAC + * @config: configuration to validate + * + * Update the %config->supported and %config->advertised masks + * clearing bits that can not be supported. + * + * Note: the PHY may be able to transform from one connection + * technology to another, so, eg, don't clear 1000BaseX just + * because the MAC is unable to support it. This is more about + * clearing unsupported speeds and duplex settings. + * + * If the %config->interface mode is %PHY_INTERFACE_MODE_1000BASEX + * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode + * based on %config->advertised and/or %config->speed. + */ + void (*validate)(struct net_device *ndev, unsigned long *supported, + struct phylink_link_state *state); + + /* Read the current link state from the hardware */ + int (*mac_link_state)(struct net_device *, struct phylink_link_state *); + + /* Configure the MAC */ + /** + * mac_config: configure the MAC for the selected mode and state + * @ndev: net_device structure for the MAC + * @mode: one of MLO_AN_FIXED, MLO_AN_PHY, MLO_AN_8023Z, MLO_AN_SGMII + * @state: state structure + * + * The action performed depends on the currently selected mode: + * + * %MLO_AN_FIXED, %MLO_AN_PHY: + * set the specified speed, duplex, pause mode, and phy interface + * mode in the provided @state. + * %MLO_AN_8023Z: + * place the link in 1000base-X mode, advertising the parameters + * given in advertising in @state. + * %MLO_AN_SGMII: + * place the link in Cisco SGMII mode - there is no advertisment + * to make as the PHY communicates the speed and duplex to the + * MAC over the in-band control word. Configuration of the pause + * mode is as per MLO_AN_PHY since this is not included. + */ + void (*mac_config)(struct net_device *ndev, unsigned int mode, + const struct phylink_link_state *state); + + /** + * mac_an_restart: restart 802.3z BaseX autonegotiation + * @ndev: net_device structure for the MAC + */ + void (*mac_an_restart)(struct net_device *ndev); + + void (*mac_link_down)(struct net_device *, unsigned int mode); + void (*mac_link_up)(struct net_device *, unsigned int mode, + struct phy_device *); +}; + +struct phylink *phylink_create(struct net_device *, struct device_node *, + phy_interface_t iface, const struct phylink_mac_ops *ops); +void phylink_destroy(struct phylink *); + +int phylink_connect_phy(struct phylink *, struct phy_device *); +int phylink_of_phy_connect(struct phylink *, struct device_node *); +void phylink_disconnect_phy(struct phylink *); + +void phylink_mac_change(struct phylink *, bool up); + +void phylink_start(struct phylink *); +void phylink_stop(struct phylink *); + +void phylink_ethtool_get_wol(struct phylink *, struct ethtool_wolinfo *); +int phylink_ethtool_set_wol(struct phylink *, struct ethtool_wolinfo *); + +int phylink_ethtool_ksettings_get(struct phylink *, + struct ethtool_link_ksettings *); +int phylink_ethtool_ksettings_set(struct phylink *, + const struct ethtool_link_ksettings *); +int phylink_ethtool_nway_reset(struct phylink *); +void phylink_ethtool_get_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_ethtool_set_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_ethtool_get_module_info(struct phylink *, struct ethtool_modinfo *); +int phylink_ethtool_get_module_eeprom(struct phylink *, + struct ethtool_eeprom *, u8 *); +int phylink_init_eee(struct phylink *, bool); +int phylink_get_eee_err(struct phylink *); +int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); +int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); +int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); + +#define phylink_zero(bm) \ + bitmap_zero(bm, __ETHTOOL_LINK_MODE_MASK_NBITS) +#define __phylink_do_bit(op, bm, mode) \ + op(ETHTOOL_LINK_MODE_ ## mode ## _BIT, bm) + +#define phylink_set(bm, mode) __phylink_do_bit(__set_bit, bm, mode) +#define phylink_clear(bm, mode) __phylink_do_bit(__clear_bit, bm, mode) +#define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) + +void phylink_set_port_modes(unsigned long *bits); + +#endif diff --git a/include/linux/pid.h b/include/linux/pid.h index 4d179316e431..719582744a2e 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -8,7 +8,9 @@ enum pid_type PIDTYPE_PID, PIDTYPE_PGID, PIDTYPE_SID, - PIDTYPE_MAX + PIDTYPE_MAX, + /* only valid to __task_pid_nr_ns() */ + __PIDTYPE_TGID }; /* diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index c2a989dee876..b09136f88cf4 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -52,7 +52,7 @@ struct pid_namespace { int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -}; +} __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/linux/pinctrl/machine.h b/include/linux/pinctrl/machine.h index e5b1716f98cc..7fa5d87190c2 100644 --- a/include/linux/pinctrl/machine.h +++ b/include/linux/pinctrl/machine.h @@ -152,12 +152,12 @@ struct pinctrl_map { #ifdef CONFIG_PINCTRL -extern int pinctrl_register_mappings(struct pinctrl_map const *map, +extern int pinctrl_register_mappings(const struct pinctrl_map *map, unsigned num_maps); extern void pinctrl_provide_dummies(void); #else -static inline int pinctrl_register_mappings(struct pinctrl_map const *map, +static inline int pinctrl_register_mappings(const struct pinctrl_map *map, unsigned num_maps) { return 0; diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 7620eb127cff..5d8bc7f21c2a 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -73,13 +73,20 @@ * operation, if several modes of operation are supported these can be * passed in the argument on a custom form, else just use argument 1 * to indicate low power mode, argument 0 turns low power mode off. - * @PIN_CONFIG_OUTPUT: this will configure the pin as an output. Use argument - * 1 to indicate high level, argument 0 to indicate low level. (Please - * see Documentation/pinctrl.txt, section "GPIO mode pitfalls" for a - * discussion around this parameter.) + * @PIN_CONFIG_OUTPUT_ENABLE: this will enable the pin's output mode + * without driving a value there. For most platforms this reduces to + * enable the output buffers and then let the pin controller current + * configuration (eg. the currently selected mux function) drive values on + * the line. Use argument 1 to enable output mode, argument 0 to disable + * it. + * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a + * value on the line. Use argument 1 to indicate high level, argument 0 to + * indicate low level. (Please see Documentation/driver-api/pinctl.rst, + * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. + * @PIN_CONFIG_SLEEP_HARDWARE_STATE: indicate this is sleep related state. * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to * this parameter (on a custom format) tells the driver which alternative * slew rate to use. @@ -105,8 +112,10 @@ enum pin_config_param { PIN_CONFIG_INPUT_SCHMITT, PIN_CONFIG_INPUT_SCHMITT_ENABLE, PIN_CONFIG_LOW_POWER_MODE, + PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_OUTPUT, PIN_CONFIG_POWER_SOURCE, + PIN_CONFIG_SLEEP_HARDWARE_STATE, PIN_CONFIG_SLEW_RATE, PIN_CONFIG_END = 0x7F, PIN_CONFIG_MAX = 0xFF, diff --git a/include/linux/i2c/adp5588.h b/include/linux/platform_data/adp5588.h index c2153049cfbd..c2153049cfbd 100644 --- a/include/linux/i2c/adp5588.h +++ b/include/linux/platform_data/adp5588.h diff --git a/include/linux/i2c/adp8860.h b/include/linux/platform_data/adp8860.h index 0b4d39855c91..0b4d39855c91 100644 --- a/include/linux/i2c/adp8860.h +++ b/include/linux/platform_data/adp8860.h diff --git a/include/linux/i2c/adp8870.h b/include/linux/platform_data/adp8870.h index 624dceccbd5b..624dceccbd5b 100644 --- a/include/linux/i2c/adp8870.h +++ b/include/linux/platform_data/adp8870.h diff --git a/include/linux/i2c/ads1015.h b/include/linux/platform_data/ads1015.h index d5aa2a045669..d5aa2a045669 100644 --- a/include/linux/i2c/ads1015.h +++ b/include/linux/platform_data/ads1015.h diff --git a/include/linux/i2c/apds990x.h b/include/linux/platform_data/apds990x.h index d186fcc5d257..d186fcc5d257 100644 --- a/include/linux/i2c/apds990x.h +++ b/include/linux/platform_data/apds990x.h diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h index 3c8825b67298..cdceb4d4ef9d 100644 --- a/include/linux/platform_data/atmel.h +++ b/include/linux/platform_data/atmel.h @@ -7,10 +7,6 @@ #ifndef __ATMEL_H__ #define __ATMEL_H__ -#include <linux/mtd/nand.h> -#include <linux/mtd/partitions.h> -#include <linux/serial.h> - /* Compact Flash */ struct at91_cf_data { int irq_pin; /* I/O IRQ */ @@ -23,35 +19,14 @@ struct at91_cf_data { #define AT91_IDE_SWAP_A0_A2 0x02 }; - /* NAND / SmartMedia */ -struct atmel_nand_data { - int enable_pin; /* chip enable */ - int det_pin; /* card detect */ - int rdy_pin; /* ready/busy */ - u8 rdy_pin_active_low; /* rdy_pin value is inverted */ - u8 ale; /* address line number connected to ALE */ - u8 cle; /* address line number connected to CLE */ - u8 bus_width_16; /* buswidth is 16 bit */ - u8 ecc_mode; /* ecc mode */ - u8 on_flash_bbt; /* bbt on flash */ - struct mtd_partition *parts; - unsigned int num_parts; - bool has_dma; /* support dma transfer */ - - /* default is false, only for at32ap7000 chip is true */ - bool need_reset_workaround; -}; - - /* Serial */ -struct atmel_uart_data { - int num; /* port num */ - short use_dma_tx; /* use transmit DMA? */ - short use_dma_rx; /* use receive DMA? */ - void __iomem *regs; /* virt. base address, if any */ - struct serial_rs485 rs485; /* rs485 settings */ -}; - /* FIXME: this needs a better location, but gets stuff building again */ +#ifdef CONFIG_ATMEL_PM extern int at91_suspend_entering_slow_clock(void); +#else +static inline int at91_suspend_entering_slow_clock(void) +{ + return 0; +} +#endif #endif /* __ATMEL_H__ */ diff --git a/include/linux/i2c/bh1770glc.h b/include/linux/platform_data/bh1770glc.h index 8b5e2df36c72..8b5e2df36c72 100644 --- a/include/linux/i2c/bh1770glc.h +++ b/include/linux/platform_data/bh1770glc.h diff --git a/include/linux/platform_data/clk-realview.h b/include/linux/platform_data/clk-realview.h deleted file mode 100644 index 2e426a7dbc51..000000000000 --- a/include/linux/platform_data/clk-realview.h +++ /dev/null @@ -1 +0,0 @@ -void realview_clk_init(void __iomem *sysbase, bool is_pb1176); diff --git a/include/linux/i2c/ds620.h b/include/linux/platform_data/ds620.h index 736bb87ac0fc..736bb87ac0fc 100644 --- a/include/linux/i2c/ds620.h +++ b/include/linux/platform_data/ds620.h diff --git a/include/linux/platform_data/gpio_backlight.h b/include/linux/platform_data/gpio_backlight.h index 5ae0d9c80d4d..683d90453c41 100644 --- a/include/linux/platform_data/gpio_backlight.h +++ b/include/linux/platform_data/gpio_backlight.h @@ -14,7 +14,6 @@ struct gpio_backlight_platform_data { struct device *fbdev; int gpio; int def_value; - bool active_low; const char *name; }; diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h index 8e981be2e2c2..73d9098ada2d 100644 --- a/include/linux/platform_data/hsmmc-omap.h +++ b/include/linux/platform_data/hsmmc-omap.h @@ -55,9 +55,6 @@ struct omap_hsmmc_platform_data { u32 caps; /* Used for the MMC driver on 2430 and later */ u32 pm_caps; /* PM capabilities of the mmc */ - /* use the internal clock */ - unsigned internal_clock:1; - /* nonremovable e.g. eMMC */ unsigned nonremovable:1; @@ -70,16 +67,12 @@ struct omap_hsmmc_platform_data { #define HSMMC_HAS_HSPE_SUPPORT (1 << 2) unsigned features; + /* string specifying a particular variant of hardware */ + char *version; + int gpio_cd; /* gpio (card detect) */ int gpio_cod; /* gpio (cover detect) */ int gpio_wp; /* gpio (write protect) */ - - int (*set_power)(struct device *dev, int power_on, int vdd); - void (*remux)(struct device *dev, int power_on); - /* Call back before enabling / disabling regulators */ - void (*before_set_reg)(struct device *dev, int power_on, int vdd); - /* Call back after enabling / disabling regulators */ - void (*after_set_reg)(struct device *dev, int power_on, int vdd); /* if we have special card, init it using this callback */ void (*init_card)(struct mmc_card *card); diff --git a/include/linux/i2c/i2c-hid.h b/include/linux/platform_data/i2c-hid.h index 1fb088239d12..1fb088239d12 100644 --- a/include/linux/i2c/i2c-hid.h +++ b/include/linux/platform_data/i2c-hid.h diff --git a/include/linux/platform_data/leds-pca963x.h b/include/linux/platform_data/leds-pca963x.h index e731f0036329..54e845ffb5ed 100644 --- a/include/linux/platform_data/leds-pca963x.h +++ b/include/linux/platform_data/leds-pca963x.h @@ -33,10 +33,16 @@ enum pca963x_blink_type { PCA963X_HW_BLINK, }; +enum pca963x_direction { + PCA963X_NORMAL, + PCA963X_INVERTED, +}; + struct pca963x_platform_data { struct led_platform_data leds; enum pca963x_outdrv outdrv; enum pca963x_blink_type blink_type; + enum pca963x_direction dir; }; #endif /* __LINUX_PCA963X_H*/ diff --git a/include/linux/i2c/lm8323.h b/include/linux/platform_data/lm8323.h index 478d668bc590..478d668bc590 100644 --- a/include/linux/i2c/lm8323.h +++ b/include/linux/platform_data/lm8323.h diff --git a/include/linux/i2c/ltc4245.h b/include/linux/platform_data/ltc4245.h index 56bda4be0016..56bda4be0016 100644 --- a/include/linux/i2c/ltc4245.h +++ b/include/linux/platform_data/ltc4245.h diff --git a/include/linux/i2c/max6639.h b/include/linux/platform_data/max6639.h index 6011c42034da..6011c42034da 100644 --- a/include/linux/i2c/max6639.h +++ b/include/linux/platform_data/max6639.h diff --git a/include/linux/i2c/max732x.h b/include/linux/platform_data/max732x.h index c04bac8bf2fe..c04bac8bf2fe 100644 --- a/include/linux/i2c/max732x.h +++ b/include/linux/platform_data/max732x.h diff --git a/include/linux/i2c/mcs.h b/include/linux/platform_data/mcs.h index 61bb18a4fd3c..61bb18a4fd3c 100644 --- a/include/linux/i2c/mcs.h +++ b/include/linux/platform_data/mcs.h diff --git a/include/linux/platform_data/mdio-bcm-unimac.h b/include/linux/platform_data/mdio-bcm-unimac.h new file mode 100644 index 000000000000..8a5f9f0b2c52 --- /dev/null +++ b/include/linux/platform_data/mdio-bcm-unimac.h @@ -0,0 +1,13 @@ +#ifndef __MDIO_BCM_UNIMAC_PDATA_H +#define __MDIO_BCM_UNIMAC_PDATA_H + +struct unimac_mdio_pdata { + u32 phy_mask; + int (*wait_func)(void *data); + void *wait_func_data; + const char *bus_name; +}; + +#define UNIMAC_MDIO_DRV_NAME "unimac-mdio" + +#endif /* __MDIO_BCM_UNIMAC_PDATA_H */ diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h new file mode 100644 index 000000000000..84789ca634aa --- /dev/null +++ b/include/linux/platform_data/microchip-ksz.h @@ -0,0 +1,29 @@ +/* + * Microchip KSZ series switch platform data + * + * Copyright (C) 2017 + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef __MICROCHIP_KSZ_H +#define __MICROCHIP_KSZ_H + +#include <linux/kernel.h> + +struct ksz_platform_data { + u32 chip_id; + u16 enabled_ports; +}; + +#endif diff --git a/include/linux/i2c/mms114.h b/include/linux/platform_data/mms114.h index 5722ebfb2738..5722ebfb2738 100644 --- a/include/linux/i2c/mms114.h +++ b/include/linux/platform_data/mms114.h diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index 1cf555aef896..f1a2cf655bdb 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -28,7 +28,7 @@ #ifndef __ARCH_ARM_DAVINCI_NAND_H #define __ARCH_ARM_DAVINCI_NAND_H -#include <linux/mtd/nand.h> +#include <linux/mtd/rawnand.h> #define NANDFCR_OFFSET 0x60 #define NANDFSR_OFFSET 0x64 diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index f01659026b26..f8c553f92655 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -12,7 +12,7 @@ #ifndef __MTD_NAND_S3C2410_H #define __MTD_NAND_S3C2410_H -#include <linux/mtd/nand.h> +#include <linux/mtd/rawnand.h> /** * struct s3c2410_nand_set - define a set of one or more nand chips diff --git a/include/linux/platform_data/nfcmrvl.h b/include/linux/platform_data/nfcmrvl.h index a6f9d633f5be..9e75ac8d19be 100644 --- a/include/linux/platform_data/nfcmrvl.h +++ b/include/linux/platform_data/nfcmrvl.h @@ -23,7 +23,7 @@ struct nfcmrvl_platform_data { */ /* GPIO that is wired to RESET_N signal */ - unsigned int reset_n_io; + int reset_n_io; /* Tell if transport is muxed in HCI one */ unsigned int hci_muxed; diff --git a/include/linux/platform_data/omap_drm.h b/include/linux/platform_data/omap_drm.h deleted file mode 100644 index f4e4a237ebd2..000000000000 --- a/include/linux/platform_data/omap_drm.h +++ /dev/null @@ -1,53 +0,0 @@ -/* - * DRM/KMS platform data for TI OMAP platforms - * - * Copyright (C) 2012 Texas Instruments - * Author: Rob Clark <rob.clark@linaro.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef __PLATFORM_DATA_OMAP_DRM_H__ -#define __PLATFORM_DATA_OMAP_DRM_H__ - -/* - * Optional platform data to configure the default configuration of which - * pipes/overlays/CRTCs are used.. if this is not provided, then instead the - * first CONFIG_DRM_OMAP_NUM_CRTCS are used, and they are each connected to - * one manager, with priority given to managers that are connected to - * detected devices. Remaining overlays are used as video planes. This - * should be a good default behavior for most cases, but yet there still - * might be times when you wish to do something different. - */ -struct omap_kms_platform_data { - /* overlays to use as CRTCs: */ - int ovl_cnt; - const int *ovl_ids; - - /* overlays to use as video planes: */ - int pln_cnt; - const int *pln_ids; - - int mgr_cnt; - const int *mgr_ids; - - int dev_cnt; - const char **dev_names; -}; - -struct omap_drm_platform_data { - uint32_t omaprev; - struct omap_kms_platform_data *kms_pdata; -}; - -#endif /* __PLATFORM_DATA_OMAP_DRM_H__ */ diff --git a/include/linux/platform_data/omapdss.h b/include/linux/platform_data/omapdss.h index 679177929045..7feb011ed500 100644 --- a/include/linux/platform_data/omapdss.h +++ b/include/linux/platform_data/omapdss.h @@ -27,7 +27,6 @@ enum omapdss_version { /* Board specific data */ struct omap_dss_board_info { - const char *default_display_name; int (*dsi_enable_pads)(int dsi_id, unsigned int lane_mask); void (*dsi_disable_pads)(int dsi_id, unsigned int lane_mask); int (*set_min_bus_tput)(struct device *dev, unsigned long r); diff --git a/include/linux/i2c/pca954x.h b/include/linux/platform_data/pca954x.h index 1712677d5904..1712677d5904 100644 --- a/include/linux/i2c/pca954x.h +++ b/include/linux/platform_data/pca954x.h diff --git a/include/linux/i2c/pcf857x.h b/include/linux/platform_data/pcf857x.h index 0767a2a6b2f1..0767a2a6b2f1 100644 --- a/include/linux/i2c/pcf857x.h +++ b/include/linux/platform_data/pcf857x.h diff --git a/include/linux/platform_data/spi-mt65xx.h b/include/linux/platform_data/spi-mt65xx.h index 54b04483976c..ba4e4bb70262 100644 --- a/include/linux/platform_data/spi-mt65xx.h +++ b/include/linux/platform_data/spi-mt65xx.h @@ -16,5 +16,7 @@ struct mtk_chip_config { u32 tx_mlsb; u32 rx_mlsb; + u32 cs_pol; + u32 sample_sel; }; #endif diff --git a/include/linux/platform_data/st-nci.h b/include/linux/platform_data/st-nci.h deleted file mode 100644 index f6494b347c06..000000000000 --- a/include/linux/platform_data/st-nci.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * Driver include for ST NCI NFC chip family. - * - * Copyright (C) 2014-2015 STMicroelectronics SAS. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef _ST_NCI_H_ -#define _ST_NCI_H_ - -#define ST_NCI_DRIVER_NAME "st_nci" - -struct st_nci_nfc_platform_data { - unsigned int gpio_reset; - unsigned int irq_polarity; - bool is_ese_present; - bool is_uicc_present; -}; - -#endif /* _ST_NCI_H_ */ diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h index 79b0e4cdb814..f8274b0c6888 100644 --- a/include/linux/platform_data/st_sensors_pdata.h +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -17,10 +17,12 @@ * Available only for accelerometer and pressure sensors. * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). * @open_drain: set the interrupt line to be open drain if possible. + * @spi_3wire: enable spi-3wire mode. */ struct st_sensors_platform_data { u8 drdy_int_pin; bool open_drain; + bool spi_3wire; }; #endif /* ST_SENSORS_PDATA_H */ diff --git a/include/linux/i2c/tc35876x.h b/include/linux/platform_data/tc35876x.h index cd6a51c71e7e..cd6a51c71e7e 100644 --- a/include/linux/i2c/tc35876x.h +++ b/include/linux/platform_data/tc35876x.h diff --git a/include/linux/i2c/tsc2007.h b/include/linux/platform_data/tsc2007.h index 4f35b6ad3889..c2d3aa1dadd4 100644 --- a/include/linux/i2c/tsc2007.h +++ b/include/linux/platform_data/tsc2007.h @@ -1,7 +1,7 @@ #ifndef __LINUX_I2C_TSC2007_H #define __LINUX_I2C_TSC2007_H -/* linux/i2c/tsc2007.h */ +/* linux/platform_data/tsc2007.h */ struct tsc2007_platform_data { u16 model; /* 2007. */ diff --git a/include/linux/platform_data/usb-ohci-s3c2410.h b/include/linux/platform_data/usb-ohci-s3c2410.h index 7fa1fbefc3f2..cc7554ae6e8b 100644 --- a/include/linux/platform_data/usb-ohci-s3c2410.h +++ b/include/linux/platform_data/usb-ohci-s3c2410.h @@ -31,7 +31,7 @@ struct s3c2410_hcd_info { void (*report_oc)(struct s3c2410_hcd_info *, int ports); }; -static void inline s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) +static inline void s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) { if (info->report_oc != NULL) { (info->report_oc)(info, ports); diff --git a/include/linux/platform_data/x86/apple.h b/include/linux/platform_data/x86/apple.h new file mode 100644 index 000000000000..079e816c3c21 --- /dev/null +++ b/include/linux/platform_data/x86/apple.h @@ -0,0 +1,13 @@ +#ifndef PLATFORM_DATA_X86_APPLE_H +#define PLATFORM_DATA_X86_APPLE_H + +#ifdef CONFIG_X86 +/** + * x86_apple_machine - whether the machine is an x86 Apple Macintosh + */ +extern bool x86_apple_machine; +#else +#define x86_apple_machine false +#endif + +#endif diff --git a/include/linux/i2c/mlxcpld.h b/include/linux/platform_data/x86/mlxcpld.h index b08dcb183fca..b08dcb183fca 100644 --- a/include/linux/i2c/mlxcpld.h +++ b/include/linux/platform_data/x86/mlxcpld.h diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 98c2a7c7108e..49f634d96118 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -172,7 +172,7 @@ extern int platform_device_add_resources(struct platform_device *pdev, extern int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size); extern int platform_device_add_properties(struct platform_device *pdev, - struct property_entry *properties); + const struct property_entry *properties); extern int platform_device_add(struct platform_device *pdev); extern void platform_device_del(struct platform_device *pdev); extern void platform_device_put(struct platform_device *pdev); diff --git a/include/linux/pm.h b/include/linux/pm.h index a0894bc52bb4..47ded8aa8a5d 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -584,7 +584,6 @@ struct dev_pm_info { unsigned int idle_notification:1; unsigned int request_pending:1; unsigned int deferred_resume:1; - unsigned int run_wake:1; unsigned int runtime_auto:1; bool ignore_children:1; unsigned int no_callbacks:1; @@ -690,6 +689,8 @@ struct dev_pm_domain { extern void device_pm_lock(void); extern void dpm_resume_start(pm_message_t state); extern void dpm_resume_end(pm_message_t state); +extern void dpm_noirq_resume_devices(pm_message_t state); +extern void dpm_noirq_end(void); extern void dpm_resume_noirq(pm_message_t state); extern void dpm_resume_early(pm_message_t state); extern void dpm_resume(pm_message_t state); @@ -698,6 +699,8 @@ extern void dpm_complete(pm_message_t state); extern void device_pm_unlock(void); extern int dpm_suspend_end(pm_message_t state); extern int dpm_suspend_start(pm_message_t state); +extern void dpm_noirq_begin(void); +extern int dpm_noirq_suspend_devices(pm_message_t state); extern int dpm_suspend_noirq(pm_message_t state); extern int dpm_suspend_late(pm_message_t state); extern int dpm_suspend(pm_message_t state); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b7803a251044..84f423d5633e 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -43,6 +43,7 @@ struct genpd_power_state { s64 power_on_latency_ns; s64 residency_ns; struct fwnode_handle *fwnode; + ktime_t idle_time; }; struct genpd_lock_ops; @@ -78,6 +79,8 @@ struct generic_pm_domain { unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ void *free; /* Free the state that was allocated for default */ + ktime_t on_time; + ktime_t accounting_time; const struct genpd_lock_ops *lock_ops; union { struct mutex mlock; @@ -206,9 +209,13 @@ static inline void pm_genpd_syscore_poweron(struct device *dev) {} /* OF PM domain providers */ struct of_device_id; +typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args, + void *data); + struct genpd_onecell_data { struct generic_pm_domain **domains; unsigned int num_domains; + genpd_xlate_t xlate; }; #ifdef CONFIG_PM_GENERIC_DOMAINS_OF diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index a6685b3dde26..51ec727b4824 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -121,6 +121,8 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) void dev_pm_opp_put_prop_name(struct opp_table *opp_table); struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); void dev_pm_opp_put_regulators(struct opp_table *opp_table); +struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); +void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); @@ -257,6 +259,13 @@ static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, co static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} +static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name) +{ + return ERR_PTR(-ENOTSUPP); +} + +static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} + static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { return -ENOTSUPP; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index ca4823e675e2..2efb08a60e63 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -76,16 +76,6 @@ static inline void pm_runtime_put_noidle(struct device *dev) atomic_add_unless(&dev->power.usage_count, -1, 0); } -static inline bool device_run_wake(struct device *dev) -{ - return dev->power.run_wake; -} - -static inline void device_set_run_wake(struct device *dev, bool enable) -{ - dev->power.run_wake = enable; -} - static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED @@ -163,8 +153,6 @@ static inline void pm_runtime_forbid(struct device *dev) {} static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} -static inline bool device_run_wake(struct device *dev) { return false; } -static inline void device_set_run_wake(struct device *dev, bool enable) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } diff --git a/include/linux/i2c/pmbus.h b/include/linux/pmbus.h index ee3c2aba2a8e..ee3c2aba2a8e 100644 --- a/include/linux/i2c/pmbus.h +++ b/include/linux/pmbus.h diff --git a/include/linux/pmem.h b/include/linux/pmem.h deleted file mode 100644 index 71ecf3d46aac..000000000000 --- a/include/linux/pmem.h +++ /dev/null @@ -1,142 +0,0 @@ -/* - * Copyright(c) 2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ -#ifndef __PMEM_H__ -#define __PMEM_H__ - -#include <linux/io.h> -#include <linux/uio.h> - -#ifdef CONFIG_ARCH_HAS_PMEM_API -#define ARCH_MEMREMAP_PMEM MEMREMAP_WB -#include <asm/pmem.h> -#else -#define ARCH_MEMREMAP_PMEM MEMREMAP_WT -/* - * These are simply here to enable compilation, all call sites gate - * calling these symbols with arch_has_pmem_api() and redirect to the - * implementation in asm/pmem.h. - */ -static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n) -{ - BUG(); -} - -static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes, - struct iov_iter *i) -{ - BUG(); - return 0; -} - -static inline void arch_clear_pmem(void *addr, size_t size) -{ - BUG(); -} - -static inline void arch_wb_cache_pmem(void *addr, size_t size) -{ - BUG(); -} - -static inline void arch_invalidate_pmem(void *addr, size_t size) -{ - BUG(); -} -#endif - -static inline bool arch_has_pmem_api(void) -{ - return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API); -} - -/** - * memcpy_to_pmem - copy data to persistent memory - * @dst: destination buffer for the copy - * @src: source buffer for the copy - * @n: length of the copy in bytes - * - * Perform a memory copy that results in the destination of the copy - * being effectively evicted from, or never written to, the processor - * cache hierarchy after the copy completes. After memcpy_to_pmem() - * data may still reside in cpu or platform buffers, so this operation - * must be followed by a blkdev_issue_flush() on the pmem block device. - */ -static inline void memcpy_to_pmem(void *dst, const void *src, size_t n) -{ - if (arch_has_pmem_api()) - arch_memcpy_to_pmem(dst, src, n); - else - memcpy(dst, src, n); -} - -/** - * copy_from_iter_pmem - copy data from an iterator to PMEM - * @addr: PMEM destination address - * @bytes: number of bytes to copy - * @i: iterator with source data - * - * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. - * See blkdev_issue_flush() note for memcpy_to_pmem(). - */ -static inline size_t copy_from_iter_pmem(void *addr, size_t bytes, - struct iov_iter *i) -{ - if (arch_has_pmem_api()) - return arch_copy_from_iter_pmem(addr, bytes, i); - return copy_from_iter_nocache(addr, bytes, i); -} - -/** - * clear_pmem - zero a PMEM memory range - * @addr: virtual start address - * @size: number of bytes to zero - * - * Write zeros into the memory range starting at 'addr' for 'size' bytes. - * See blkdev_issue_flush() note for memcpy_to_pmem(). - */ -static inline void clear_pmem(void *addr, size_t size) -{ - if (arch_has_pmem_api()) - arch_clear_pmem(addr, size); - else - memset(addr, 0, size); -} - -/** - * invalidate_pmem - flush a pmem range from the cache hierarchy - * @addr: virtual start address - * @size: bytes to invalidate (internally aligned to cache line size) - * - * For platforms that support clearing poison this flushes any poisoned - * ranges out of the cache - */ -static inline void invalidate_pmem(void *addr, size_t size) -{ - if (arch_has_pmem_api()) - arch_invalidate_pmem(addr, size); -} - -/** - * wb_cache_pmem - write back processor cache for PMEM memory range - * @addr: virtual start address - * @size: number of bytes to write back - * - * Write back the processor cache range starting at 'addr' for 'size' bytes. - * See blkdev_issue_flush() note for memcpy_to_pmem(). - */ -static inline void wb_cache_pmem(void *addr, size_t size) -{ - if (arch_has_pmem_api()) - arch_wb_cache_pmem(addr, size); -} -#endif /* __PMEM_H__ */ diff --git a/include/linux/poll.h b/include/linux/poll.h index 75ffc5729e4c..2889f09a1c60 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -75,7 +75,7 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) struct poll_table_entry { struct file *filp; unsigned long key; - wait_queue_t wait; + wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index 83b22ae9ae12..38d8225510f1 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -42,12 +42,6 @@ struct posix_clock; * @clock_gettime: Read the current time * @clock_getres: Get the clock resolution * @clock_settime: Set the current time value - * @timer_create: Create a new timer - * @timer_delete: Remove a previously created timer - * @timer_gettime: Get remaining time and interval of a timer - * @timer_settime: Set a timer's initial expiration and interval - * @fasync: Optional character device fasync method - * @mmap: Optional character device mmap method * @open: Optional character device open method * @release: Optional character device release method * @ioctl: Optional character device ioctl method @@ -66,28 +60,12 @@ struct posix_clock_operations { int (*clock_settime)(struct posix_clock *pc, const struct timespec64 *ts); - int (*timer_create) (struct posix_clock *pc, struct k_itimer *kit); - - int (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit); - - void (*timer_gettime)(struct posix_clock *pc, - struct k_itimer *kit, struct itimerspec64 *tsp); - - int (*timer_settime)(struct posix_clock *pc, - struct k_itimer *kit, int flags, - struct itimerspec64 *tsp, struct itimerspec64 *old); /* * Optional character device methods: */ - int (*fasync) (struct posix_clock *pc, - int fd, struct file *file, int on); - long (*ioctl) (struct posix_clock *pc, unsigned int cmd, unsigned long arg); - int (*mmap) (struct posix_clock *pc, - struct vm_area_struct *vma); - int (*open) (struct posix_clock *pc, fmode_t f_mode); uint (*poll) (struct posix_clock *pc, diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 8c1e43ab14a9..62839fd04dce 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -7,6 +7,7 @@ #include <linux/timex.h> #include <linux/alarmtimer.h> +struct siginfo; struct cpu_timer_list { struct list_head entry; @@ -48,81 +49,68 @@ struct cpu_timer_list { #define FD_TO_CLOCKID(fd) ((~(clockid_t) (fd) << 3) | CLOCKFD) #define CLOCKID_TO_FD(clk) ((unsigned int) ~((clk) >> 3)) -/* POSIX.1b interval timer structure. */ -struct k_itimer { - struct list_head list; /* free/ allocate list */ - struct hlist_node t_hash; - spinlock_t it_lock; - clockid_t it_clock; /* which timer type */ - timer_t it_id; /* timer id */ - int it_overrun; /* overrun on pending signal */ - int it_overrun_last; /* overrun on last delivered signal */ - int it_requeue_pending; /* waiting to requeue this timer */ #define REQUEUE_PENDING 1 - int it_sigev_notify; /* notify word of sigevent struct */ - struct signal_struct *it_signal; + +/** + * struct k_itimer - POSIX.1b interval timer structure. + * @list: List head for binding the timer to signals->posix_timers + * @t_hash: Entry in the posix timer hash table + * @it_lock: Lock protecting the timer + * @kclock: Pointer to the k_clock struct handling this timer + * @it_clock: The posix timer clock id + * @it_id: The posix timer id for identifying the timer + * @it_active: Marker that timer is active + * @it_overrun: The overrun counter for pending signals + * @it_overrun_last: The overrun at the time of the last delivered signal + * @it_requeue_pending: Indicator that timer waits for being requeued on + * signal delivery + * @it_sigev_notify: The notify word of sigevent struct for signal delivery + * @it_interval: The interval for periodic timers + * @it_signal: Pointer to the creators signal struct + * @it_pid: The pid of the process/task targeted by the signal + * @it_process: The task to wakeup on clock_nanosleep (CPU timers) + * @sigq: Pointer to preallocated sigqueue + * @it: Union representing the various posix timer type + * internals. Also used for rcu freeing the timer. + */ +struct k_itimer { + struct list_head list; + struct hlist_node t_hash; + spinlock_t it_lock; + const struct k_clock *kclock; + clockid_t it_clock; + timer_t it_id; + int it_active; + int it_overrun; + int it_overrun_last; + int it_requeue_pending; + int it_sigev_notify; + ktime_t it_interval; + struct signal_struct *it_signal; union { - struct pid *it_pid; /* pid of process to send signal to */ - struct task_struct *it_process; /* for clock_nanosleep */ + struct pid *it_pid; + struct task_struct *it_process; }; - struct sigqueue *sigq; /* signal queue entry. */ + struct sigqueue *sigq; union { struct { - struct hrtimer timer; - ktime_t interval; + struct hrtimer timer; } real; - struct cpu_timer_list cpu; - struct { - unsigned int clock; - unsigned int node; - unsigned long incr; - unsigned long expires; - } mmtimer; + struct cpu_timer_list cpu; struct { - struct alarm alarmtimer; - ktime_t interval; + struct alarm alarmtimer; } alarm; - struct rcu_head rcu; + struct rcu_head rcu; } it; }; -struct k_clock { - int (*clock_getres) (const clockid_t which_clock, struct timespec64 *tp); - int (*clock_set) (const clockid_t which_clock, - const struct timespec64 *tp); - int (*clock_get) (const clockid_t which_clock, struct timespec64 *tp); - int (*clock_adj) (const clockid_t which_clock, struct timex *tx); - int (*timer_create) (struct k_itimer *timer); - int (*nsleep) (const clockid_t which_clock, int flags, - struct timespec64 *, struct timespec __user *); - long (*nsleep_restart) (struct restart_block *restart_block); - int (*timer_set) (struct k_itimer *timr, int flags, - struct itimerspec64 *new_setting, - struct itimerspec64 *old_setting); - int (*timer_del) (struct k_itimer *timr); -#define TIMER_RETRY 1 - void (*timer_get) (struct k_itimer *timr, - struct itimerspec64 *cur_setting); -}; - -extern struct k_clock clock_posix_cpu; -extern struct k_clock clock_posix_dynamic; - -void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock); - -/* function to call to trigger timer event */ -int posix_timer_event(struct k_itimer *timr, int si_private); - -void posix_cpu_timer_schedule(struct k_itimer *timer); - void run_posix_cpu_timers(struct task_struct *task); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); -long clock_nanosleep_restart(struct restart_block *restart_block); - void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); +void posixtimer_rearm(struct siginfo *info); #endif diff --git a/include/linux/power/bq24190_charger.h b/include/linux/power/bq24190_charger.h new file mode 100644 index 000000000000..45ce7f116a91 --- /dev/null +++ b/include/linux/power/bq24190_charger.h @@ -0,0 +1,18 @@ +/* + * Platform data for the TI bq24190 battery charger driver. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _BQ24190_CHARGER_H_ +#define _BQ24190_CHARGER_H_ + +#include <linux/regulator/machine.h> + +struct bq24190_platform_data { + const struct regulator_init_data *regulator_init_data; +}; + +#endif diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index b312bcef53da..43194e02c1ee 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -6,6 +6,7 @@ enum bq27xxx_chip { BQ27010, /* bq27010, bq27210 */ BQ2750X, /* bq27500 deprecated alias */ BQ2751X, /* bq27510, bq27520 deprecated alias */ + BQ2752X, BQ27500, /* bq27500/1 */ BQ27510G1, /* bq27510G1 */ BQ27510G2, /* bq27510G2 */ @@ -15,31 +16,24 @@ enum bq27xxx_chip { BQ27520G3, /* bq27520G3 */ BQ27520G4, /* bq27520G4 */ BQ27530, /* bq27530, bq27531 */ + BQ27531, BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ + BQ27542, + BQ27546, + BQ27742, BQ27545, /* bq27545 */ BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ -}; - -/** - * struct bq27xxx_plaform_data - Platform data for bq27xxx devices - * @name: Name of the battery. - * @chip: Chip class number of this device. - * @read: HDQ read callback. - * This function should provide access to the HDQ bus the battery is - * connected to. - * The first parameter is a pointer to the battery device, the second the - * register to be read. The return value should either be the content of - * the passed register or an error value. - */ -struct bq27xxx_platform_data { - const char *name; - enum bq27xxx_chip chip; - int (*read)(struct device *dev, unsigned int); + BQ27425, + BQ27441, + BQ27621, }; struct bq27xxx_device_info; struct bq27xxx_access_methods { int (*read)(struct bq27xxx_device_info *di, u8 reg, bool single); + int (*write)(struct bq27xxx_device_info *di, u8 reg, int value, bool single); + int (*read_bulk)(struct bq27xxx_device_info *di, u8 reg, u8 *data, int len); + int (*write_bulk)(struct bq27xxx_device_info *di, u8 reg, u8 *data, int len); }; struct bq27xxx_reg_cache { @@ -60,7 +54,10 @@ struct bq27xxx_device_info { struct device *dev; int id; enum bq27xxx_chip chip; + u32 opts; const char *name; + struct bq27xxx_dm_reg *dm_regs; + u32 unseal_key; struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 3965503315ef..79e90b3d3288 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -146,6 +146,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_TIME_TO_FULL_AVG, POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */ POWER_SUPPLY_PROP_SCOPE, + POWER_SUPPLY_PROP_PRECHARGE_CURRENT, POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, POWER_SUPPLY_PROP_CALIBRATE, /* Properties of type `const char *' */ @@ -159,13 +160,14 @@ enum power_supply_type { POWER_SUPPLY_TYPE_BATTERY, POWER_SUPPLY_TYPE_UPS, POWER_SUPPLY_TYPE_MAINS, - POWER_SUPPLY_TYPE_USB, /* Standard Downstream Port */ - POWER_SUPPLY_TYPE_USB_DCP, /* Dedicated Charging Port */ - POWER_SUPPLY_TYPE_USB_CDP, /* Charging Downstream Port */ - POWER_SUPPLY_TYPE_USB_ACA, /* Accessory Charger Adapters */ - POWER_SUPPLY_TYPE_USB_TYPE_C, /* Type C Port */ - POWER_SUPPLY_TYPE_USB_PD, /* Power Delivery Port */ - POWER_SUPPLY_TYPE_USB_PD_DRP, /* PD Dual Role Port */ + POWER_SUPPLY_TYPE_USB, /* Standard Downstream Port */ + POWER_SUPPLY_TYPE_USB_DCP, /* Dedicated Charging Port */ + POWER_SUPPLY_TYPE_USB_CDP, /* Charging Downstream Port */ + POWER_SUPPLY_TYPE_USB_ACA, /* Accessory Charger Adapters */ + POWER_SUPPLY_TYPE_USB_TYPE_C, /* Type C Port */ + POWER_SUPPLY_TYPE_USB_PD, /* Power Delivery Port */ + POWER_SUPPLY_TYPE_USB_PD_DRP, /* PD Dual Role Port */ + POWER_SUPPLY_TYPE_APPLE_BRICK_ID, /* Apple Charging Method */ }; enum power_supply_notifier_events { @@ -288,6 +290,25 @@ struct power_supply_info { int use_for_apm; }; +/* + * This is the recommended struct to manage static battery parameters, + * populated by power_supply_get_battery_info(). Most platform drivers should + * use these for consistency. + * Its field names must correspond to elements in enum power_supply_property. + * The default field value is -EINVAL. + * Power supply class itself doesn't use this. + */ + +struct power_supply_battery_info { + int energy_full_design_uwh; /* microWatt-hours */ + int charge_full_design_uah; /* microAmp-hours */ + int voltage_min_design_uv; /* microVolts */ + int precharge_current_ua; /* microAmps */ + int charge_term_current_ua; /* microAmps */ + int constant_charge_current_max_ua; /* microAmps */ + int constant_charge_voltage_max_uv; /* microVolts */ +}; + extern struct atomic_notifier_head power_supply_notifier; extern int power_supply_reg_notifier(struct notifier_block *nb); extern void power_supply_unreg_notifier(struct notifier_block *nb); @@ -306,8 +327,13 @@ static inline struct power_supply * devm_power_supply_get_by_phandle(struct device *dev, const char *property) { return NULL; } #endif /* CONFIG_OF */ + +extern int power_supply_get_battery_info(struct power_supply *psy, + struct power_supply_battery_info *info); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); +extern int power_supply_set_input_current_limit_from_supplier( + struct power_supply *psy); extern int power_supply_set_battery_charged(struct power_supply *psy); #ifdef CONFIG_POWER_SUPPLY @@ -359,6 +385,8 @@ static inline bool power_supply_is_amp_property(enum power_supply_property psp) case POWER_SUPPLY_PROP_CHARGE_NOW: case POWER_SUPPLY_PROP_CHARGE_AVG: case POWER_SUPPLY_PROP_CHARGE_COUNTER: + case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: + case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: case POWER_SUPPLY_PROP_CURRENT_MAX: diff --git a/include/linux/pps-gpio.h b/include/linux/pps-gpio.h index 0035abe41b9a..56f35dd3d01d 100644 --- a/include/linux/pps-gpio.h +++ b/include/linux/pps-gpio.h @@ -29,4 +29,4 @@ struct pps_gpio_platform_data { const char *gpio_label; }; -#endif +#endif /* _PPS_GPIO_H */ diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 35ac903956c7..80a980cc8d95 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -22,7 +22,6 @@ #define LINUX_PPS_KERNEL_H #include <linux/pps.h> - #include <linux/cdev.h> #include <linux/device.h> #include <linux/time.h> @@ -35,9 +34,9 @@ struct pps_device; /* The specific PPS source info */ struct pps_source_info { - char name[PPS_MAX_NAME_LEN]; /* simbolic name */ + char name[PPS_MAX_NAME_LEN]; /* symbolic name */ char path[PPS_MAX_NAME_LEN]; /* path of connected device */ - int mode; /* PPS's allowed mode */ + int mode; /* PPS allowed mode */ void (*echo)(struct pps_device *pps, int event, void *data); /* PPS echo function */ @@ -57,10 +56,10 @@ struct pps_event_time { struct pps_device { struct pps_source_info info; /* PSS source info */ - struct pps_kparams params; /* PPS's current params */ + struct pps_kparams params; /* PPS current params */ - __u32 assert_sequence; /* PPS' assert event seq # */ - __u32 clear_sequence; /* PPS' clear event seq # */ + __u32 assert_sequence; /* PPS assert event seq # */ + __u32 clear_sequence; /* PPS clear event seq # */ struct pps_ktime assert_tu; struct pps_ktime clear_tu; int current_mode; /* PPS mode at event time */ @@ -69,7 +68,7 @@ struct pps_device { wait_queue_head_t queue; /* PPS event queue */ unsigned int id; /* PPS source unique ID */ - void const *lookup_cookie; /* pps_lookup_dev only */ + void const *lookup_cookie; /* For pps_lookup_dev() only */ struct cdev cdev; struct device *dev; struct fasync_struct *async_queue; /* fasync method */ @@ -101,7 +100,7 @@ extern struct pps_device *pps_register_source( extern void pps_unregister_source(struct pps_device *pps); extern void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, void *data); -/* Look up a pps device by magic cookie */ +/* Look up a pps_device by magic cookie */ struct pps_device *pps_lookup_dev(void const *cookie); static inline void timespec_to_pps_ktime(struct pps_ktime *kt, @@ -132,4 +131,3 @@ static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec64 delta } #endif /* LINUX_PPS_KERNEL_H */ - diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2d2bf592d9db..76124dd4e36d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -28,13 +28,7 @@ extern struct proc_dir_entry *proc_create_data(const char *, umode_t, const struct file_operations *, void *); -static inline struct proc_dir_entry *proc_create( - const char *name, umode_t mode, struct proc_dir_entry *parent, - const struct file_operations *proc_fops) -{ - return proc_create_data(name, mode, parent, proc_fops, NULL); -} - +struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); extern void *PDE_DATA(const struct inode *); diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 58ab28d81fc2..06844b54dfc1 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -21,7 +21,7 @@ struct proc_ns_operations { int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); -}; +} __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; diff --git a/include/linux/processor.h b/include/linux/processor.h new file mode 100644 index 000000000000..da0c5e56ca02 --- /dev/null +++ b/include/linux/processor.h @@ -0,0 +1,70 @@ +/* Misc low level processor primitives */ +#ifndef _LINUX_PROCESSOR_H +#define _LINUX_PROCESSOR_H + +#include <asm/processor.h> + +/* + * spin_begin is used before beginning a busy-wait loop, and must be paired + * with spin_end when the loop is exited. spin_cpu_relax must be called + * within the loop. + * + * The loop body should be as small and fast as possible, on the order of + * tens of instructions/cycles as a guide. It should and avoid calling + * cpu_relax, or any "spin" or sleep type of primitive including nested uses + * of these primitives. It should not lock or take any other resource. + * Violations of these guidelies will not cause a bug, but may cause sub + * optimal performance. + * + * These loops are optimized to be used where wait times are expected to be + * less than the cost of a context switch (and associated overhead). + * + * Detection of resource owner and decision to spin or sleep or guest-yield + * (e.g., spin lock holder vcpu preempted, or mutex owner not on CPU) can be + * tested within the loop body. + */ +#ifndef spin_begin +#define spin_begin() +#endif + +#ifndef spin_cpu_relax +#define spin_cpu_relax() cpu_relax() +#endif + +/* + * spin_cpu_yield may be called to yield (undirected) to the hypervisor if + * necessary. This should be used if the wait is expected to take longer + * than context switch overhead, but we can't sleep or do a directed yield. + */ +#ifndef spin_cpu_yield +#define spin_cpu_yield() cpu_relax_yield() +#endif + +#ifndef spin_end +#define spin_end() +#endif + +/* + * spin_until_cond can be used to wait for a condition to become true. It + * may be expected that the first iteration will true in the common case + * (no spinning), so that callers should not require a first "likely" test + * for the uncontended case before using this primitive. + * + * Usage and implementation guidelines are the same as for the spin_begin + * primitives, above. + */ +#ifndef spin_until_cond +#define spin_until_cond(cond) \ +do { \ + if (unlikely(!(cond))) { \ + spin_begin(); \ + do { \ + spin_cpu_relax(); \ + } while (!(cond)); \ + spin_end(); \ + } \ +} while (0) + +#endif + +#endif /* _LINUX_PROCESSOR_H */ diff --git a/include/linux/property.h b/include/linux/property.h index 2f482616a2f2..6bebee13c5e0 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -51,45 +51,52 @@ int device_property_read_string(struct device *dev, const char *propname, int device_property_match_string(struct device *dev, const char *propname, const char *string); -bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname); -int fwnode_property_read_u8_array(struct fwnode_handle *fwnode, +bool fwnode_device_is_available(const struct fwnode_handle *fwnode); +bool fwnode_property_present(const struct fwnode_handle *fwnode, + const char *propname); +int fwnode_property_read_u8_array(const struct fwnode_handle *fwnode, const char *propname, u8 *val, size_t nval); -int fwnode_property_read_u16_array(struct fwnode_handle *fwnode, +int fwnode_property_read_u16_array(const struct fwnode_handle *fwnode, const char *propname, u16 *val, size_t nval); -int fwnode_property_read_u32_array(struct fwnode_handle *fwnode, +int fwnode_property_read_u32_array(const struct fwnode_handle *fwnode, const char *propname, u32 *val, size_t nval); -int fwnode_property_read_u64_array(struct fwnode_handle *fwnode, +int fwnode_property_read_u64_array(const struct fwnode_handle *fwnode, const char *propname, u64 *val, size_t nval); -int fwnode_property_read_string_array(struct fwnode_handle *fwnode, +int fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval); -int fwnode_property_read_string(struct fwnode_handle *fwnode, +int fwnode_property_read_string(const struct fwnode_handle *fwnode, const char *propname, const char **val); -int fwnode_property_match_string(struct fwnode_handle *fwnode, +int fwnode_property_match_string(const struct fwnode_handle *fwnode, const char *propname, const char *string); +int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode, + const char *prop, const char *nargs_prop, + unsigned int nargs, unsigned int index, + struct fwnode_reference_args *args); -struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode, - struct fwnode_handle *child); +struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_parent( + struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_child_node( + const struct fwnode_handle *fwnode, struct fwnode_handle *child); #define fwnode_for_each_child_node(fwnode, child) \ for (child = fwnode_get_next_child_node(fwnode, NULL); child; \ child = fwnode_get_next_child_node(fwnode, child)) -struct fwnode_handle *device_get_next_child_node(struct device *dev, - struct fwnode_handle *child); +struct fwnode_handle *device_get_next_child_node( + struct device *dev, struct fwnode_handle *child); #define device_for_each_child_node(dev, child) \ for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) -struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode, - const char *childname); +struct fwnode_handle *fwnode_get_named_child_node( + const struct fwnode_handle *fwnode, const char *childname); struct fwnode_handle *device_get_named_child_node(struct device *dev, const char *childname); @@ -128,31 +135,31 @@ static inline int device_property_read_u64(struct device *dev, return device_property_read_u64_array(dev, propname, val, 1); } -static inline bool fwnode_property_read_bool(struct fwnode_handle *fwnode, +static inline bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, const char *propname) { return fwnode_property_present(fwnode, propname); } -static inline int fwnode_property_read_u8(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u8(const struct fwnode_handle *fwnode, const char *propname, u8 *val) { return fwnode_property_read_u8_array(fwnode, propname, val, 1); } -static inline int fwnode_property_read_u16(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u16(const struct fwnode_handle *fwnode, const char *propname, u16 *val) { return fwnode_property_read_u16_array(fwnode, propname, val, 1); } -static inline int fwnode_property_read_u32(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u32(const struct fwnode_handle *fwnode, const char *propname, u32 *val) { return fwnode_property_read_u32_array(fwnode, propname, val, 1); } -static inline int fwnode_property_read_u64(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u64(const struct fwnode_handle *fwnode, const char *propname, u64 *val) { return fwnode_property_read_u64_array(fwnode, propname, val, 1); @@ -273,15 +280,20 @@ int device_get_phy_mode(struct device *dev); void *device_get_mac_address(struct device *dev, char *addr, int alen); struct fwnode_handle *fwnode_graph_get_next_endpoint( - struct fwnode_handle *fwnode, struct fwnode_handle *prev); + const struct fwnode_handle *fwnode, struct fwnode_handle *prev); +struct fwnode_handle * +fwnode_graph_get_port_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port_parent( - struct fwnode_handle *fwnode); + const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port( - struct fwnode_handle *fwnode); + const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_endpoint( - struct fwnode_handle *fwnode); + const struct fwnode_handle *fwnode); +struct fwnode_handle * +fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port, + u32 endpoint); -int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode, +int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); #endif /* _LINUX_PROPERTY_H_ */ diff --git a/include/linux/pstore.h b/include/linux/pstore.h index e2233f50f428..61f806a7fe29 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -138,7 +138,10 @@ struct pstore_record { * memory allocation may be broken during an Oops. Regardless, * @buf must be proccesed or copied before returning. The * backend is also expected to write @id with something that - 8 can help identify this record to a future @erase callback. + * can help identify this record to a future @erase callback. + * The @time field will be prepopulated with the current time, + * when available. The @size field will have the size of data + * in @buf. * * Returns 0 on success, and non-zero on error. * diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index a026bfd089db..51349d124ee5 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -99,6 +99,11 @@ struct system_device_crosststamp; * parameter func: the desired function to use. * parameter chan: the function channel index to use. * + * @do_work: Request driver to perform auxiliary (periodic) operations + * Driver should return delay of the next auxiliary work scheduling + * time (>=0) or negative value in case further scheduling + * is not required. + * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). * @@ -126,6 +131,7 @@ struct ptp_clock_info { struct ptp_clock_request *request, int on); int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan); + long (*do_aux_work)(struct ptp_clock_info *ptp); }; struct ptp_clock; @@ -211,6 +217,16 @@ extern int ptp_clock_index(struct ptp_clock *ptp); int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan); +/** + * ptp_schedule_worker() - schedule ptp auxiliary work + * + * @ptp: The clock obtained from ptp_clock_register(). + * @delay: number of jiffies to wait before queuing + * See kthread_queue_delayed_work() for more info. + */ + +int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -225,6 +241,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp) static inline int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan) { return -1; } +static inline int ptp_schedule_worker(struct ptp_clock *ptp, + unsigned long delay) +{ return -EOPNOTSUPP; } + #endif #endif diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 6b2e0dd88569..37b4bb2545b3 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -278,6 +278,22 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r) return ptr; } +static inline int __ptr_ring_consume_batched(struct ptr_ring *r, + void **array, int n) +{ + void *ptr; + int i; + + for (i = 0; i < n; i++) { + ptr = __ptr_ring_consume(r); + if (!ptr) + break; + array[i] = ptr; + } + + return i; +} + /* * Note: resize (below) nests producer lock within consumer lock, so if you * call this in interrupt or BH context, you must disable interrupts/BH when @@ -328,6 +344,55 @@ static inline void *ptr_ring_consume_bh(struct ptr_ring *r) return ptr; } +static inline int ptr_ring_consume_batched(struct ptr_ring *r, + void **array, int n) +{ + int ret; + + spin_lock(&r->consumer_lock); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock(&r->consumer_lock); + + return ret; +} + +static inline int ptr_ring_consume_batched_irq(struct ptr_ring *r, + void **array, int n) +{ + int ret; + + spin_lock_irq(&r->consumer_lock); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock_irq(&r->consumer_lock); + + return ret; +} + +static inline int ptr_ring_consume_batched_any(struct ptr_ring *r, + void **array, int n) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&r->consumer_lock, flags); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock_irqrestore(&r->consumer_lock, flags); + + return ret; +} + +static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, + void **array, int n) +{ + int ret; + + spin_lock_bh(&r->consumer_lock); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock_bh(&r->consumer_lock); + + return ret; +} + /* Cast to structure type and call a function without discarding from FIFO. * Function must return a value. * Callers must take consumer_lock. @@ -371,9 +436,9 @@ static inline void *ptr_ring_consume_bh(struct ptr_ring *r) __PTR_RING_PEEK_CALL_v; \ }) -static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp) +static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) { - return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp); + return kcalloc(size, sizeof(void *), gfp); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) @@ -403,6 +468,61 @@ static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) return 0; } +/* + * Return entries into ring. Destroy entries that don't fit. + * + * Note: this is expected to be a rare slow path operation. + * + * Note: producer lock is nested within consumer lock, so if you + * resize you must make sure all uses nest correctly. + * In particular if you consume ring in interrupt or BH context, you must + * disable interrupts/BH when doing so. + */ +static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n, + void (*destroy)(void *)) +{ + unsigned long flags; + int head; + + spin_lock_irqsave(&r->consumer_lock, flags); + spin_lock(&r->producer_lock); + + if (!r->size) + goto done; + + /* + * Clean out buffered entries (for simplicity). This way following code + * can test entries for NULL and if not assume they are valid. + */ + head = r->consumer_head - 1; + while (likely(head >= r->consumer_tail)) + r->queue[head--] = NULL; + r->consumer_tail = r->consumer_head; + + /* + * Go over entries in batch, start moving head back and copy entries. + * Stop when we run into previously unconsumed entries. + */ + while (n) { + head = r->consumer_head - 1; + if (head < 0) + head = r->size - 1; + if (r->queue[head]) { + /* This batch entry will have to be destroyed. */ + goto done; + } + r->queue[head] = batch[--n]; + r->consumer_tail = r->consumer_head = head; + } + +done: + /* Destroy all entries left in the batch. */ + while (n) + destroy(batch[--n]); + spin_unlock(&r->producer_lock); + spin_unlock_irqrestore(&r->consumer_lock, flags); +} + static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, int size, gfp_t gfp, void (*destroy)(void *)) @@ -462,7 +582,8 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, +static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, + unsigned int nrings, int size, gfp_t gfp, void (*destroy)(void *)) { @@ -470,7 +591,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, void ***queues; int i; - queues = kmalloc(nrings * sizeof *queues, gfp); + queues = kmalloc_array(nrings, sizeof(*queues), gfp); if (!queues) goto noqueues; diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index ef3eb8bbfee4..0e5fcc11b1b8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -391,10 +391,6 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, #define current_pt_regs() task_pt_regs(current) #endif -#ifndef ptrace_signal_deliver -#define ptrace_signal_deliver() ((void)0) -#endif - /* * unlike current_pt_regs(), this one is equal to task_pt_regs(current) * on *all* architectures; the only reason to have a per-arch definition diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index a0522328d7aa..8461b18e4608 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -196,6 +196,7 @@ enum pxa_ssp_type { LPSS_BSW_SSP, LPSS_SPT_SSP, LPSS_BXT_SSP, + LPSS_CNL_SSP, }; struct ssp_device { diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index fbab6e0514f0..39e2a2ac2471 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -38,6 +38,8 @@ #include <linux/slab.h> /* dma_addr_t manip */ +#define PTR_LO(x) ((u32)(((uintptr_t)(x)) & 0xffffffff)) +#define PTR_HI(x) ((u32)((((uintptr_t)(x)) >> 16) >> 16)) #define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x)) #define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x)) #define DMA_REGPAIR_LE(x, val) do { \ @@ -96,12 +98,12 @@ #define CORE_SPQE_PAGE_SIZE_BYTES 4096 -#define MAX_NUM_LL2_RX_QUEUES 32 -#define MAX_NUM_LL2_TX_STATS_COUNTERS 32 +#define MAX_NUM_LL2_RX_QUEUES 48 +#define MAX_NUM_LL2_TX_STATS_COUNTERS 48 #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 15 -#define FW_REVISION_VERSION 3 +#define FW_MINOR_VERSION 20 +#define FW_REVISION_VERSION 0 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -181,6 +183,14 @@ #define CDU_VF_FL_SEG_TYPE_OFFSET_REG_TYPE_SHIFT (12) #define CDU_VF_FL_SEG_TYPE_OFFSET_REG_OFFSET_MASK (0xfff) + +#define CDU_CONTEXT_VALIDATION_CFG_ENABLE_SHIFT (0) +#define CDU_CONTEXT_VALIDATION_CFG_VALIDATION_TYPE_SHIFT (1) +#define CDU_CONTEXT_VALIDATION_CFG_USE_TYPE (2) +#define CDU_CONTEXT_VALIDATION_CFG_USE_REGION (3) +#define CDU_CONTEXT_VALIDATION_CFG_USE_CID (4) +#define CDU_CONTEXT_VALIDATION_CFG_USE_ACTIVE (5) + /*****************/ /* DQ CONSTANTS */ /*****************/ @@ -457,7 +467,6 @@ #define PXP_BAR_DQ 1 /* PTT and GTT */ -#define PXP_NUM_PF_WINDOWS 12 #define PXP_PER_PF_ENTRY_SIZE 8 #define PXP_NUM_GLOBAL_WINDOWS 243 #define PXP_GLOBAL_ENTRY_SIZE 4 @@ -482,6 +491,7 @@ #define PXP_PF_ME_OPAQUE_ADDR 0x1f8 #define PXP_PF_ME_CONCRETE_ADDR 0x1fc +#define PXP_NUM_PF_WINDOWS 12 #define PXP_EXTERNAL_BAR_PF_WINDOW_START 0x1000 #define PXP_EXTERNAL_BAR_PF_WINDOW_NUM PXP_NUM_PF_WINDOWS #define PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE 0x1000 @@ -618,16 +628,21 @@ /*****************/ /* PRM CONSTANTS */ /*****************/ -#define PRM_DMA_PAD_BYTES_NUM 2 -/******************/ -/* SDMs CONSTANTS */ -/******************/ -#define SDM_OP_GEN_TRIG_NONE 0 -#define SDM_OP_GEN_TRIG_WAKE_THREAD 1 -#define SDM_OP_GEN_TRIG_AGG_INT 2 -#define SDM_OP_GEN_TRIG_LOADER 4 -#define SDM_OP_GEN_TRIG_INDICATE_ERROR 6 -#define SDM_OP_GEN_TRIG_RELEASE_THREAD 7 +#define PRM_DMA_PAD_BYTES_NUM 2 +/*****************/ +/* SDMs CONSTANTS */ +/*****************/ + +#define SDM_OP_GEN_TRIG_NONE 0 +#define SDM_OP_GEN_TRIG_WAKE_THREAD 1 +#define SDM_OP_GEN_TRIG_AGG_INT 2 +#define SDM_OP_GEN_TRIG_LOADER 4 +#define SDM_OP_GEN_TRIG_INDICATE_ERROR 6 +#define SDM_OP_GEN_TRIG_INC_ORDER_CNT 9 + +/********************/ +/* Completion types */ +/********************/ #define SDM_COMP_TYPE_NONE 0 #define SDM_COMP_TYPE_WAKE_THREAD 1 @@ -638,10 +653,11 @@ #define SDM_COMP_TYPE_INDICATE_ERROR 6 #define SDM_COMP_TYPE_RELEASE_THREAD 7 #define SDM_COMP_TYPE_RAM 8 +#define SDM_COMP_TYPE_INC_ORDER_CNT 9 -/******************/ -/* PBF CONSTANTS */ -/******************/ +/*****************/ +/* PBF Constants */ +/*****************/ /* Number of PBF command queue lines. Each line is 32B. */ #define PBF_MAX_CMD_LINES 3328 @@ -764,7 +780,7 @@ enum protocol_type { PROTOCOLID_ROCE, PROTOCOLID_CORE, PROTOCOLID_ETH, - PROTOCOLID_RESERVED4, + PROTOCOLID_IWARP, PROTOCOLID_RESERVED5, PROTOCOLID_PREROCE, PROTOCOLID_COMMON, @@ -861,7 +877,7 @@ enum db_dest { /* Enum of doorbell DPM types */ enum db_dpm_type { DPM_LEGACY, - DPM_ROCE, + DPM_RDMA, DPM_L2_INLINE, DPM_L2_BD, MAX_DB_DPM_TYPE @@ -884,8 +900,8 @@ struct db_l2_dpm_data { #define DB_L2_DPM_DATA_RESERVED0_SHIFT 27 #define DB_L2_DPM_DATA_SGE_NUM_MASK 0x7 #define DB_L2_DPM_DATA_SGE_NUM_SHIFT 28 -#define DB_L2_DPM_DATA_RESERVED1_MASK 0x1 -#define DB_L2_DPM_DATA_RESERVED1_SHIFT 31 +#define DB_L2_DPM_DATA_GFS_SRC_EN_MASK 0x1 +#define DB_L2_DPM_DATA_GFS_SRC_EN_SHIFT 31 }; /* Structure for SGE in a DPM doorbell of type DPM_L2_BD */ @@ -931,31 +947,33 @@ struct db_pwm_addr { }; /* Parameters to RoCE firmware, passed in EDPM doorbell */ -struct db_roce_dpm_params { +struct db_rdma_dpm_params { __le32 params; -#define DB_ROCE_DPM_PARAMS_SIZE_MASK 0x3F -#define DB_ROCE_DPM_PARAMS_SIZE_SHIFT 0 -#define DB_ROCE_DPM_PARAMS_DPM_TYPE_MASK 0x3 -#define DB_ROCE_DPM_PARAMS_DPM_TYPE_SHIFT 6 -#define DB_ROCE_DPM_PARAMS_OPCODE_MASK 0xFF -#define DB_ROCE_DPM_PARAMS_OPCODE_SHIFT 8 -#define DB_ROCE_DPM_PARAMS_WQE_SIZE_MASK 0x7FF -#define DB_ROCE_DPM_PARAMS_WQE_SIZE_SHIFT 16 -#define DB_ROCE_DPM_PARAMS_RESERVED0_MASK 0x1 -#define DB_ROCE_DPM_PARAMS_RESERVED0_SHIFT 27 -#define DB_ROCE_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 -#define DB_ROCE_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 -#define DB_ROCE_DPM_PARAMS_S_FLG_MASK 0x1 -#define DB_ROCE_DPM_PARAMS_S_FLG_SHIFT 29 -#define DB_ROCE_DPM_PARAMS_RESERVED1_MASK 0x3 -#define DB_ROCE_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_SIZE_MASK 0x3F +#define DB_RDMA_DPM_PARAMS_SIZE_SHIFT 0 +#define DB_RDMA_DPM_PARAMS_DPM_TYPE_MASK 0x3 +#define DB_RDMA_DPM_PARAMS_DPM_TYPE_SHIFT 6 +#define DB_RDMA_DPM_PARAMS_OPCODE_MASK 0xFF +#define DB_RDMA_DPM_PARAMS_OPCODE_SHIFT 8 +#define DB_RDMA_DPM_PARAMS_WQE_SIZE_MASK 0x7FF +#define DB_RDMA_DPM_PARAMS_WQE_SIZE_SHIFT 16 +#define DB_RDMA_DPM_PARAMS_RESERVED0_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_RESERVED0_SHIFT 27 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_DPM_PARAMS_S_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_S_FLG_SHIFT 29 +#define DB_RDMA_DPM_PARAMS_RESERVED1_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 }; /* Structure for doorbell data, in ROCE DPM mode, for 1st db in a DPM burst */ -struct db_roce_dpm_data { +struct db_rdma_dpm_data { __le16 icid; __le16 prod_val; - struct db_roce_dpm_params params; + struct db_rdma_dpm_params params; }; /* Igu interrupt command */ @@ -1026,6 +1044,42 @@ struct parsing_and_err_flags { #define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMERROR_SHIFT 15 }; +struct parsing_err_flags { + __le16 flags; +#define PARSING_ERR_FLAGS_MAC_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_MAC_ERROR_SHIFT 0 +#define PARSING_ERR_FLAGS_TRUNC_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_TRUNC_ERROR_SHIFT 1 +#define PARSING_ERR_FLAGS_PKT_TOO_SMALL_MASK 0x1 +#define PARSING_ERR_FLAGS_PKT_TOO_SMALL_SHIFT 2 +#define PARSING_ERR_FLAGS_ANY_HDR_MISSING_TAG_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_MISSING_TAG_SHIFT 3 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_VER_MISMTCH_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_VER_MISMTCH_SHIFT 4 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_V4_HDR_LEN_TOO_SMALL_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_V4_HDR_LEN_TOO_SMALL_SHIFT 5 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_BAD_TOTAL_LEN_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_BAD_TOTAL_LEN_SHIFT 6 +#define PARSING_ERR_FLAGS_IP_V4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_IP_V4_CHKSM_ERROR_SHIFT 7 +#define PARSING_ERR_FLAGS_ANY_HDR_L4_IP_LEN_MISMTCH_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_L4_IP_LEN_MISMTCH_SHIFT 8 +#define PARSING_ERR_FLAGS_ZERO_UDP_IP_V6_CHKSM_MASK 0x1 +#define PARSING_ERR_FLAGS_ZERO_UDP_IP_V6_CHKSM_SHIFT 9 +#define PARSING_ERR_FLAGS_INNER_L4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_INNER_L4_CHKSM_ERROR_SHIFT 10 +#define PARSING_ERR_FLAGS_ANY_HDR_ZERO_TTL_OR_HOP_LIM_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_ZERO_TTL_OR_HOP_LIM_SHIFT 11 +#define PARSING_ERR_FLAGS_NON_8021Q_TAG_EXISTS_IN_BOTH_HDRS_MASK 0x1 +#define PARSING_ERR_FLAGS_NON_8021Q_TAG_EXISTS_IN_BOTH_HDRS_SHIFT 12 +#define PARSING_ERR_FLAGS_GENEVE_OPTION_OVERSIZED_MASK 0x1 +#define PARSING_ERR_FLAGS_GENEVE_OPTION_OVERSIZED_SHIFT 13 +#define PARSING_ERR_FLAGS_TUNNEL_IP_V4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_TUNNEL_IP_V4_CHKSM_ERROR_SHIFT 14 +#define PARSING_ERR_FLAGS_TUNNEL_L4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_TUNNEL_L4_CHKSM_ERROR_SHIFT 15 +}; + struct pb_context { __le32 crc[4]; }; @@ -1288,39 +1342,56 @@ struct tdif_task_context { struct timers_context { __le32 logical_client_0; -#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_SHIFT 0 -#define TIMERS_CONTEXT_VALIDLC0_MASK 0x1 -#define TIMERS_CONTEXT_VALIDLC0_SHIFT 28 -#define TIMERS_CONTEXT_ACTIVELC0_MASK 0x1 -#define TIMERS_CONTEXT_ACTIVELC0_SHIFT 29 -#define TIMERS_CONTEXT_RESERVED0_MASK 0x3 -#define TIMERS_CONTEXT_RESERVED0_SHIFT 30 +#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED0_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED0_SHIFT 27 +#define TIMERS_CONTEXT_VALIDLC0_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC0_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC0_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC0_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED1_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED1_SHIFT 30 __le32 logical_client_1; -#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_SHIFT 0 -#define TIMERS_CONTEXT_VALIDLC1_MASK 0x1 -#define TIMERS_CONTEXT_VALIDLC1_SHIFT 28 -#define TIMERS_CONTEXT_ACTIVELC1_MASK 0x1 -#define TIMERS_CONTEXT_ACTIVELC1_SHIFT 29 -#define TIMERS_CONTEXT_RESERVED1_MASK 0x3 -#define TIMERS_CONTEXT_RESERVED1_SHIFT 30 +#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED2_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED2_SHIFT 27 +#define TIMERS_CONTEXT_VALIDLC1_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC1_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC1_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC1_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED3_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED3_SHIFT 30 __le32 logical_client_2; -#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_SHIFT 0 -#define TIMERS_CONTEXT_VALIDLC2_MASK 0x1 -#define TIMERS_CONTEXT_VALIDLC2_SHIFT 28 -#define TIMERS_CONTEXT_ACTIVELC2_MASK 0x1 -#define TIMERS_CONTEXT_ACTIVELC2_SHIFT 29 -#define TIMERS_CONTEXT_RESERVED2_MASK 0x3 -#define TIMERS_CONTEXT_RESERVED2_SHIFT 30 +#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED4_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED4_SHIFT 27 +#define TIMERS_CONTEXT_VALIDLC2_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC2_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC2_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC2_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED5_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED5_SHIFT 30 __le32 host_expiration_fields; -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_SHIFT 0 -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_MASK 0x1 -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_SHIFT 28 -#define TIMERS_CONTEXT_RESERVED3_MASK 0x7 -#define TIMERS_CONTEXT_RESERVED3_SHIFT 29 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED6_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED6_SHIFT 27 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_MASK 0x1 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_SHIFT 28 +#define TIMERS_CONTEXT_RESERVED7_MASK 0x7 +#define TIMERS_CONTEXT_RESERVED7_SHIFT 29 }; + +enum tunnel_next_protocol { + e_unknown = 0, + e_l2 = 1, + e_ipv4 = 2, + e_ipv6 = 3, + MAX_TUNNEL_NEXT_PROTOCOL +}; + #endif /* __COMMON_HSI__ */ #endif diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 34d93eb5bfba..cb06e6e368e1 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -75,7 +75,8 @@ (ETH_NUM_STATISTIC_COUNTERS - 3 * MAX_NUM_VFS / 4) /* Maximum number of buffers, used for RX packet placement */ -#define ETH_RX_MAX_BUFF_PER_PKT 5 +#define ETH_RX_MAX_BUFF_PER_PKT 5 +#define ETH_RX_BD_THRESHOLD 12 /* num of MAC/VLAN filters */ #define ETH_NUM_MAC_FILTERS 512 diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index 947a635d04bb..12fc9e788eea 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -13,7 +13,6 @@ /*********************/ #define FC_ABTS_REPLY_MAX_PAYLOAD_LEN 12 -#define FCOE_MAX_SIZE_FCP_DATA_SUPER (8600) struct fcoe_abts_pkt { __le32 abts_rsp_fc_payload_lo; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 69949f8e354b..85e086cba639 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -75,25 +75,13 @@ #define ISCSI_TARGET_MODE 1 /* iSCSI request op codes */ -#define ISCSI_OPCODE_NOP_OUT_NO_IMM (0) -#define ISCSI_OPCODE_NOP_OUT ( \ - ISCSI_OPCODE_NOP_OUT_NO_IMM | 0x40) -#define ISCSI_OPCODE_SCSI_CMD_NO_IMM (1) -#define ISCSI_OPCODE_SCSI_CMD ( \ - ISCSI_OPCODE_SCSI_CMD_NO_IMM | 0x40) -#define ISCSI_OPCODE_TMF_REQUEST_NO_IMM (2) -#define ISCSI_OPCODE_TMF_REQUEST ( \ - ISCSI_OPCODE_TMF_REQUEST_NO_IMM | 0x40) -#define ISCSI_OPCODE_LOGIN_REQUEST_NO_IMM (3) -#define ISCSI_OPCODE_LOGIN_REQUEST ( \ - ISCSI_OPCODE_LOGIN_REQUEST_NO_IMM | 0x40) -#define ISCSI_OPCODE_TEXT_REQUEST_NO_IMM (4) -#define ISCSI_OPCODE_TEXT_REQUEST ( \ - ISCSI_OPCODE_TEXT_REQUEST_NO_IMM | 0x40) -#define ISCSI_OPCODE_DATA_OUT (5) -#define ISCSI_OPCODE_LOGOUT_REQUEST_NO_IMM (6) -#define ISCSI_OPCODE_LOGOUT_REQUEST ( \ - ISCSI_OPCODE_LOGOUT_REQUEST_NO_IMM | 0x40) +#define ISCSI_OPCODE_NOP_OUT (0) +#define ISCSI_OPCODE_SCSI_CMD (1) +#define ISCSI_OPCODE_TMF_REQUEST (2) +#define ISCSI_OPCODE_LOGIN_REQUEST (3) +#define ISCSI_OPCODE_TEXT_REQUEST (4) +#define ISCSI_OPCODE_DATA_OUT (5) +#define ISCSI_OPCODE_LOGOUT_REQUEST (6) /* iSCSI response/messages op codes */ #define ISCSI_OPCODE_NOP_IN (0x20) @@ -172,17 +160,23 @@ struct iscsi_async_msg_hdr { struct iscsi_cmd_hdr { __le16 reserved1; u8 flags_attr; -#define ISCSI_CMD_HDR_ATTR_MASK 0x7 -#define ISCSI_CMD_HDR_ATTR_SHIFT 0 -#define ISCSI_CMD_HDR_RSRV_MASK 0x3 -#define ISCSI_CMD_HDR_RSRV_SHIFT 3 -#define ISCSI_CMD_HDR_WRITE_MASK 0x1 -#define ISCSI_CMD_HDR_WRITE_SHIFT 5 -#define ISCSI_CMD_HDR_READ_MASK 0x1 -#define ISCSI_CMD_HDR_READ_SHIFT 6 -#define ISCSI_CMD_HDR_FINAL_MASK 0x1 -#define ISCSI_CMD_HDR_FINAL_SHIFT 7 - u8 opcode; +#define ISCSI_CMD_HDR_ATTR_MASK 0x7 +#define ISCSI_CMD_HDR_ATTR_SHIFT 0 +#define ISCSI_CMD_HDR_RSRV_MASK 0x3 +#define ISCSI_CMD_HDR_RSRV_SHIFT 3 +#define ISCSI_CMD_HDR_WRITE_MASK 0x1 +#define ISCSI_CMD_HDR_WRITE_SHIFT 5 +#define ISCSI_CMD_HDR_READ_MASK 0x1 +#define ISCSI_CMD_HDR_READ_SHIFT 6 +#define ISCSI_CMD_HDR_FINAL_MASK 0x1 +#define ISCSI_CMD_HDR_FINAL_SHIFT 7 + u8 hdr_first_byte; +#define ISCSI_CMD_HDR_OPCODE_MASK 0x3F +#define ISCSI_CMD_HDR_OPCODE_SHIFT 0 +#define ISCSI_CMD_HDR_IMM_MASK 0x1 +#define ISCSI_CMD_HDR_IMM_SHIFT 6 +#define ISCSI_CMD_HDR_RSRV1_MASK 0x1 +#define ISCSI_CMD_HDR_RSRV1_SHIFT 7 __le32 hdr_second_dword; #define ISCSI_CMD_HDR_DATA_SEG_LEN_MASK 0xFFFFFF #define ISCSI_CMD_HDR_DATA_SEG_LEN_SHIFT 0 @@ -790,9 +784,9 @@ enum iscsi_error_types { ISCSI_CONN_ERROR_LOCAL_COMPLETION_ERROR, ISCSI_CONN_ERROR_DATA_OVERRUN, ISCSI_CONN_ERROR_OUT_OF_SGES_ERROR, - ISCSI_CONN_ERROR_TCP_SEG_PROC_URG_ERROR, - ISCSI_CONN_ERROR_TCP_SEG_PROC_IP_OPTIONS_ERROR, - ISCSI_CONN_ERROR_TCP_SEG_PROC_CONNECT_INVALID_WS_OPTION, + ISCSI_CONN_ERROR_IP_OPTIONS_ERROR, + ISCSI_CONN_ERROR_PRS_ERRORS, + ISCSI_CONN_ERROR_CONNECT_INVALID_TCP_OPTION, ISCSI_CONN_ERROR_TCP_IP_FRAGMENT_ERROR, ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_LEN, ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_TYPE, @@ -1304,22 +1298,6 @@ struct ystorm_iscsi_stats_drv { struct regpair iscsi_tx_total_pdu_cnt; }; -struct iscsi_db_data { - u8 params; -#define ISCSI_DB_DATA_DEST_MASK 0x3 -#define ISCSI_DB_DATA_DEST_SHIFT 0 -#define ISCSI_DB_DATA_AGG_CMD_MASK 0x3 -#define ISCSI_DB_DATA_AGG_CMD_SHIFT 2 -#define ISCSI_DB_DATA_BYPASS_EN_MASK 0x1 -#define ISCSI_DB_DATA_BYPASS_EN_SHIFT 4 -#define ISCSI_DB_DATA_RESERVED_MASK 0x1 -#define ISCSI_DB_DATA_RESERVED_SHIFT 5 -#define ISCSI_DB_DATA_AGG_VAL_SEL_MASK 0x3 -#define ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT 6 - u8 agg_flags; - __le16 sq_prod; -}; - struct tstorm_iscsi_task_ag_ctx { u8 byte0; u8 byte1; @@ -1398,5 +1376,20 @@ struct tstorm_iscsi_task_ag_ctx { __le32 reg1; __le32 reg2; }; +struct iscsi_db_data { + u8 params; +#define ISCSI_DB_DATA_DEST_MASK 0x3 +#define ISCSI_DB_DATA_DEST_SHIFT 0 +#define ISCSI_DB_DATA_AGG_CMD_MASK 0x3 +#define ISCSI_DB_DATA_AGG_CMD_SHIFT 2 +#define ISCSI_DB_DATA_BYPASS_EN_MASK 0x1 +#define ISCSI_DB_DATA_BYPASS_EN_SHIFT 4 +#define ISCSI_DB_DATA_RESERVED_MASK 0x1 +#define ISCSI_DB_DATA_RESERVED_SHIFT 5 +#define ISCSI_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 sq_prod; +}; #endif /* __ISCSI_COMMON__ */ diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h new file mode 100644 index 000000000000..b8b3e1cfae90 --- /dev/null +++ b/include/linux/qed/iwarp_common.h @@ -0,0 +1,53 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015-2017 QLogic Corporation + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __IWARP_COMMON__ +#define __IWARP_COMMON__ +#include <linux/qed/rdma_common.h> +/************************/ +/* IWARP FW CONSTANTS */ +/************************/ + +#define IWARP_ACTIVE_MODE 0 +#define IWARP_PASSIVE_MODE 1 + +#define IWARP_SHARED_QUEUE_PAGE_SIZE (0x8000) +#define IWARP_SHARED_QUEUE_PAGE_RQ_PBL_OFFSET (0x4000) +#define IWARP_SHARED_QUEUE_PAGE_RQ_PBL_MAX_SIZE (0x1000) +#define IWARP_SHARED_QUEUE_PAGE_SQ_PBL_OFFSET (0x5000) +#define IWARP_SHARED_QUEUE_PAGE_SQ_PBL_MAX_SIZE (0x3000) + +#define IWARP_REQ_MAX_INLINE_DATA_SIZE (128) +#define IWARP_REQ_MAX_SINGLE_SQ_WQE_SIZE (176) + +#define IWARP_MAX_QPS (64 * 1024) + +#endif /* __IWARP_COMMON__ */ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 5cd7a4608c9b..59ddf9af909e 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -80,6 +80,11 @@ struct qed_chain_pbl_u32 { u32 cons_page_idx; }; +struct qed_chain_ext_pbl { + dma_addr_t p_pbl_phys; + void *p_pbl_virt; +}; + struct qed_chain_u16 { /* Cyclic index of next element to produce/consme */ u16 prod_idx; @@ -155,6 +160,8 @@ struct qed_chain { u32 size; u8 intended_use; + + bool b_external_pbl; }; #define QED_CHAIN_PBL_ENTRY_SIZE (8) diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index d66d16a559e1..d60de4a39810 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -47,8 +47,7 @@ struct qed_queue_start_common_params { /* Relative, but relevant only for PFs */ u8 stats_id; - /* These are always absolute */ - u16 sb; + struct qed_sb_info *p_sb; u8 sb_idx; }; @@ -74,6 +73,9 @@ struct qed_dev_eth_info { /* Legacy VF - this affects the datapath, so qede has to know */ bool is_legacy; + + /* Might depend on available resources [in case of VF] */ + bool xdp_supported; }; struct qed_update_vport_rss_params { @@ -321,6 +323,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, bool en_searcher); + int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index bd6bcb809415..1e015c50e6b8 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -24,6 +24,11 @@ struct qed_dev_fcoe_info { void __iomem *primary_dbq_rq_addr; void __iomem *secondary_bdq_rq_addr; + + u64 wwpn; + u64 wwnn; + + u8 num_cqs; }; struct qed_fcoe_params_offload { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index c70ac13a97e6..cc646ca97974 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -156,6 +156,23 @@ struct qed_dcbx_get { struct qed_dcbx_admin_params local; }; +enum qed_nvm_images { + QED_NVM_IMAGE_ISCSI_CFG, + QED_NVM_IMAGE_FCOE_CFG, +}; + +struct qed_link_eee_params { + u32 tx_lpi_timer; +#define QED_EEE_1G_ADV BIT(0) +#define QED_EEE_10G_ADV BIT(1) + + /* Capabilities are represented using QED_EEE_*_ADV values */ + u8 adv_caps; + u8 lp_adv_caps; + bool enable; + bool tx_lpi_enable; +}; + enum qed_led_mode { QED_LED_MODE_OFF, QED_LED_MODE_ON, @@ -167,8 +184,9 @@ enum qed_led_mode { #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) -#define QED_COALESCE_MAX 0xFF +#define QED_COALESCE_MAX 0x1FF #define QED_DEFAULT_RX_USECS 12 +#define QED_DEFAULT_TX_USECS 48 /* forward */ struct qed_dev; @@ -180,6 +198,10 @@ struct qed_eth_pf_params { */ u16 num_cons; + /* per-VF number of CIDs */ + u8 num_vf_cons; +#define ETH_PF_PARAMS_VF_CONS_DEFAULT (32) + /* To enable arfs, previous to HW-init a positive number needs to be * set [as filters require allocated searcher ILT memory]. * This will set the maximal number of configured steering-filters. @@ -328,6 +350,14 @@ struct qed_dev_info { /* MFW version */ u32 mfw_rev; +#define QED_MFW_VERSION_0_MASK 0x000000FF +#define QED_MFW_VERSION_0_OFFSET 0 +#define QED_MFW_VERSION_1_MASK 0x0000FF00 +#define QED_MFW_VERSION_1_OFFSET 8 +#define QED_MFW_VERSION_2_MASK 0x00FF0000 +#define QED_MFW_VERSION_2_OFFSET 16 +#define QED_MFW_VERSION_3_MASK 0xFF000000 +#define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; u8 mf_mode; @@ -337,12 +367,23 @@ struct qed_dev_info { bool wol_support; + /* MBI version */ + u32 mbi_version; +#define QED_MBI_VERSION_0_MASK 0x000000FF +#define QED_MBI_VERSION_0_OFFSET 0 +#define QED_MBI_VERSION_1_MASK 0x0000FF00 +#define QED_MBI_VERSION_1_OFFSET 8 +#define QED_MBI_VERSION_2_MASK 0x00FF0000 +#define QED_MBI_VERSION_2_OFFSET 16 + enum qed_dev_type dev_type; /* Output parameters for qede */ bool vxlan_enable; bool gre_enable; bool geneve_enable; + + u8 abs_pf_id; }; enum qed_sb_type { @@ -380,6 +421,7 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) #define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) #define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) +#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) u32 override_flags; bool autoneg; u32 adv_speeds; @@ -394,6 +436,7 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_EXT BIT(3) #define QED_LINK_LOOPBACK_MAC BIT(4) u32 loopback_mode; + struct qed_link_eee_params eee; }; struct qed_link_output { @@ -409,6 +452,12 @@ struct qed_link_output { u8 port; /* In PORT defs */ bool autoneg; u32 pause_config; + + /* EEE - capability & param */ + bool eee_supported; + bool eee_active; + u8 sup_caps; + struct qed_link_eee_params eee; }; struct qed_probe_params { @@ -503,9 +552,7 @@ struct qed_common_ops { int (*set_power_state)(struct qed_dev *cdev, pci_power_t state); - void (*set_id)(struct qed_dev *cdev, - char name[], - char ver_str[]); + void (*set_name) (struct qed_dev *cdev, char name[]); /* Client drivers need to make this call before slowpath_start. * PF params required for the call before slowpath_start is @@ -608,20 +655,24 @@ struct qed_common_ops { enum qed_chain_cnt_type cnt_type, u32 num_elems, size_t elem_size, - struct qed_chain *p_chain); + struct qed_chain *p_chain, + struct qed_chain_ext_pbl *ext_pbl); void (*chain_free)(struct qed_dev *cdev, struct qed_chain *p_chain); /** - * @brief get_coalesce - Get coalesce parameters in usec + * @brief nvm_get_image - reads an entire image from nvram * * @param cdev - * @param rx_coal - Rx coalesce value in usec - * @param tx_coal - Tx coalesce value in usec + * @param type - type of the request nvram image + * @param buf - preallocated buffer to fill with the image + * @param len - length of the allocated buffer * + * @return 0 on success, error otherwise */ - void (*get_coalesce)(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal); + int (*nvm_get_image)(struct qed_dev *cdev, + enum qed_nvm_images type, u8 *buf, u16 len); /** * @brief set_coalesce - Configure Rx coalesce value in usec @@ -634,8 +685,8 @@ struct qed_common_ops { * * @return 0 on success, error otherwise. */ - int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, - u16 qid, u16 sb_id); + int (*set_coalesce)(struct qed_dev *cdev, + u16 rx_coal, u16 tx_coal, void *handle); /** * @brief set_led - Configure LED mode @@ -700,11 +751,13 @@ struct qed_common_ops { (((value) >> (name ## _SHIFT)) & name ## _MASK) /* Debug print definitions */ -#define DP_ERR(cdev, fmt, ...) \ - pr_err("[%s:%d(%s)]" fmt, \ - __func__, __LINE__, \ - DP_NAME(cdev) ? DP_NAME(cdev) : "", \ - ## __VA_ARGS__) \ +#define DP_ERR(cdev, fmt, ...) \ + do { \ + pr_err("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + } while (0) #define DP_NOTICE(cdev, fmt, ...) \ do { \ @@ -869,9 +922,15 @@ struct qed_eth_stats { #define TX_PI(tc) (RX_PI + 1 + tc) struct qed_sb_cnt_info { - int sb_cnt; - int sb_iov_cnt; - int sb_free_blk; + /* Original, current, and free SBs for PF */ + int orig; + int cnt; + int free_cnt; + + /* Original, current and free SBS for child VFs */ + int iov_orig; + int iov_cnt; + int free_cnt_iov; }; static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index 3414649133d2..111e606a74c8 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -210,6 +210,11 @@ struct qed_iscsi_cb_ops { * @param stats - pointer to struck that would be filled * we stats * @return 0 on success, error otherwise. + * @change_mac Change MAC of interface + * @param cdev + * @param handle - the connection handle. + * @param mac - new MAC to configure. + * @return 0 on success, otherwise error value. */ struct qed_iscsi_ops { const struct qed_common_ops *common; @@ -248,6 +253,8 @@ struct qed_iscsi_ops { int (*get_stats)(struct qed_dev *cdev, struct qed_iscsi_stats *stats); + + int (*change_mac)(struct qed_dev *cdev, u32 handle, const u8 *mac); }; const struct qed_iscsi_ops *qed_get_iscsi_ops(void); diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 4fb4666ea879..dd7a3b86bb9e 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -43,6 +43,36 @@ #include <linux/slab.h> #include <linux/qed/qed_if.h> +enum qed_ll2_conn_type { + QED_LL2_TYPE_FCOE, + QED_LL2_TYPE_ISCSI, + QED_LL2_TYPE_TEST, + QED_LL2_TYPE_OOO, + QED_LL2_TYPE_RESERVED2, + QED_LL2_TYPE_ROCE, + QED_LL2_TYPE_IWARP, + QED_LL2_TYPE_RESERVED3, + MAX_QED_LL2_RX_CONN_TYPE +}; + +enum qed_ll2_roce_flavor_type { + QED_LL2_ROCE, + QED_LL2_RROCE, + MAX_QED_LL2_ROCE_FLAVOR_TYPE +}; + +enum qed_ll2_tx_dest { + QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */ + QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */ + QED_LL2_TX_DEST_MAX +}; + +enum qed_ll2_error_handle { + QED_LL2_DROP_PACKET, + QED_LL2_DO_NOTHING, + QED_LL2_ASSERT, +}; + struct qed_ll2_stats { u64 gsi_invalid_hdr; u64 gsi_invalid_pkt_length; @@ -67,6 +97,105 @@ struct qed_ll2_stats { u64 sent_bcast_pkts; }; +struct qed_ll2_comp_rx_data { + void *cookie; + dma_addr_t rx_buf_addr; + u16 parse_flags; + u16 vlan; + bool b_last_packet; + u8 connection_handle; + + union { + u16 packet_length; + u16 data_length; + } length; + + u32 opaque_data_0; + u32 opaque_data_1; + + /* GSI only */ + u32 gid_dst[4]; + u16 qp_id; + + union { + u8 placement_offset; + u8 data_length_error; + } u; +}; + +typedef +void (*qed_ll2_complete_rx_packet_cb)(void *cxt, + struct qed_ll2_comp_rx_data *data); + +typedef +void (*qed_ll2_release_rx_packet_cb)(void *cxt, + u8 connection_handle, + void *cookie, + dma_addr_t rx_buf_addr, + bool b_last_packet); + +typedef +void (*qed_ll2_complete_tx_packet_cb)(void *cxt, + u8 connection_handle, + void *cookie, + dma_addr_t first_frag_addr, + bool b_last_fragment, + bool b_last_packet); + +typedef +void (*qed_ll2_release_tx_packet_cb)(void *cxt, + u8 connection_handle, + void *cookie, + dma_addr_t first_frag_addr, + bool b_last_fragment, bool b_last_packet); + +struct qed_ll2_cbs { + qed_ll2_complete_rx_packet_cb rx_comp_cb; + qed_ll2_release_rx_packet_cb rx_release_cb; + qed_ll2_complete_tx_packet_cb tx_comp_cb; + qed_ll2_release_tx_packet_cb tx_release_cb; + void *cookie; +}; + +struct qed_ll2_acquire_data_inputs { + enum qed_ll2_conn_type conn_type; + u16 mtu; + u16 rx_num_desc; + u16 rx_num_ooo_buffers; + u8 rx_drop_ttl0_flg; + u8 rx_vlan_removal_en; + u16 tx_num_desc; + u8 tx_max_bds_per_packet; + u8 tx_tc; + enum qed_ll2_tx_dest tx_dest; + enum qed_ll2_error_handle ai_err_packet_too_big; + enum qed_ll2_error_handle ai_err_no_buf; + u8 gsi_enable; +}; + +struct qed_ll2_acquire_data { + struct qed_ll2_acquire_data_inputs input; + const struct qed_ll2_cbs *cbs; + + /* Output container for LL2 connection's handle */ + u8 *p_connection_handle; +}; + +struct qed_ll2_tx_pkt_info { + void *cookie; + dma_addr_t first_frag; + enum qed_ll2_tx_dest tx_dest; + enum qed_ll2_roce_flavor_type qed_roce_flavor; + u16 vlan; + u16 l4_hdr_offset_w; /* from start of packet */ + u16 first_frag_len; + u8 num_of_bds; + u8 bd_flags; + bool enable_ip_cksum; + bool enable_l4_cksum; + bool calc_ip_len; +}; + #define QED_LL2_UNUSED_HANDLE (0xff) struct qed_ll2_cb_ops { diff --git a/include/linux/qed/qed_roce_if.h b/include/linux/qed/qed_rdma_if.h index cbb2ff0ce4bc..4dd72ba210f5 100644 --- a/include/linux/qed/qed_roce_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -29,13 +29,11 @@ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ -#ifndef _QED_ROCE_IF_H -#define _QED_ROCE_IF_H +#ifndef _QED_RDMA_IF_H +#define _QED_RDMA_IF_H #include <linux/types.h> #include <linux/delay.h> #include <linux/list.h> -#include <linux/mutex.h> -#include <linux/pci.h> #include <linux/slab.h> #include <linux/qed/qed_if.h> #include <linux/qed/qed_ll2_if.h> @@ -472,6 +470,101 @@ struct qed_rdma_counters_out_params { #define QED_ROCE_TX_HEAD_FAILURE (1) #define QED_ROCE_TX_FRAG_FAILURE (2) +enum qed_iwarp_event_type { + QED_IWARP_EVENT_MPA_REQUEST, /* Passive side request received */ + QED_IWARP_EVENT_PASSIVE_COMPLETE, /* ack on mpa response */ + QED_IWARP_EVENT_ACTIVE_COMPLETE, /* Active side reply received */ + QED_IWARP_EVENT_DISCONNECT, + QED_IWARP_EVENT_CLOSE, + QED_IWARP_EVENT_IRQ_FULL, + QED_IWARP_EVENT_RQ_EMPTY, + QED_IWARP_EVENT_LLP_TIMEOUT, + QED_IWARP_EVENT_REMOTE_PROTECTION_ERROR, + QED_IWARP_EVENT_CQ_OVERFLOW, + QED_IWARP_EVENT_QP_CATASTROPHIC, + QED_IWARP_EVENT_ACTIVE_MPA_REPLY, + QED_IWARP_EVENT_LOCAL_ACCESS_ERROR, + QED_IWARP_EVENT_REMOTE_OPERATION_ERROR, + QED_IWARP_EVENT_TERMINATE_RECEIVED +}; + +enum qed_tcp_ip_version { + QED_TCP_IPV4, + QED_TCP_IPV6, +}; + +struct qed_iwarp_cm_info { + enum qed_tcp_ip_version ip_version; + u32 remote_ip[4]; + u32 local_ip[4]; + u16 remote_port; + u16 local_port; + u16 vlan; + u8 ord; + u8 ird; + u16 private_data_len; + const void *private_data; +}; + +struct qed_iwarp_cm_event_params { + enum qed_iwarp_event_type event; + const struct qed_iwarp_cm_info *cm_info; + void *ep_context; /* To be passed to accept call */ + int status; +}; + +typedef int (*iwarp_event_handler) (void *context, + struct qed_iwarp_cm_event_params *event); + +struct qed_iwarp_connect_in { + iwarp_event_handler event_cb; + void *cb_context; + struct qed_rdma_qp *qp; + struct qed_iwarp_cm_info cm_info; + u16 mss; + u8 remote_mac_addr[ETH_ALEN]; + u8 local_mac_addr[ETH_ALEN]; +}; + +struct qed_iwarp_connect_out { + void *ep_context; +}; + +struct qed_iwarp_listen_in { + iwarp_event_handler event_cb; + void *cb_context; /* passed to event_cb */ + u32 max_backlog; + enum qed_tcp_ip_version ip_version; + u32 ip_addr[4]; + u16 port; + u16 vlan; +}; + +struct qed_iwarp_listen_out { + void *handle; +}; + +struct qed_iwarp_accept_in { + void *ep_context; + void *cb_context; + struct qed_rdma_qp *qp; + const void *private_data; + u16 private_data_len; + u8 ord; + u8 ird; +}; + +struct qed_iwarp_reject_in { + void *ep_context; + void *cb_context; + const void *private_data; + u16 private_data_len; +}; + +struct qed_iwarp_send_rtr_in { + void *ep_context; +}; + struct qed_roce_ll2_header { void *vaddr; dma_addr_t baddr; @@ -491,44 +584,9 @@ struct qed_roce_ll2_packet { enum qed_roce_ll2_tx_dest tx_dest; }; -struct qed_roce_ll2_tx_params { - int reserved; -}; - -struct qed_roce_ll2_rx_params { - u16 vlan_id; - u8 smac[ETH_ALEN]; - int rc; -}; - -struct qed_roce_ll2_cbs { - void (*tx_cb)(void *pdev, struct qed_roce_ll2_packet *pkt); - - void (*rx_cb)(void *pdev, struct qed_roce_ll2_packet *pkt, - struct qed_roce_ll2_rx_params *params); -}; - -struct qed_roce_ll2_params { - u16 max_rx_buffers; - u16 max_tx_buffers; - u16 mtu; - u8 mac_address[ETH_ALEN]; - struct qed_roce_ll2_cbs cbs; - void *cb_cookie; -}; - -struct qed_roce_ll2_info { - u8 handle; - struct qed_roce_ll2_cbs cbs; - u8 mac_address[ETH_ALEN]; - void *cb_cookie; - - /* Lock to protect ll2 */ - struct mutex lock; -}; - enum qed_rdma_type { QED_RDMA_TYPE_ROCE, + QED_RDMA_TYPE_IWARP }; struct qed_dev_rdma_info { @@ -579,26 +637,58 @@ struct qed_rdma_ops { int (*rdma_query_qp)(void *rdma_cxt, struct qed_rdma_qp *qp, struct qed_rdma_query_qp_out_params *oparams); int (*rdma_destroy_qp)(void *rdma_cxt, struct qed_rdma_qp *qp); + int (*rdma_register_tid)(void *rdma_cxt, struct qed_rdma_register_tid_in_params *iparams); + int (*rdma_deregister_tid)(void *rdma_cxt, u32 itid); int (*rdma_alloc_tid)(void *rdma_cxt, u32 *itid); void (*rdma_free_tid)(void *rdma_cxt, u32 itid); - int (*roce_ll2_start)(struct qed_dev *cdev, - struct qed_roce_ll2_params *params); - int (*roce_ll2_stop)(struct qed_dev *cdev); - int (*roce_ll2_tx)(struct qed_dev *cdev, - struct qed_roce_ll2_packet *packet, - struct qed_roce_ll2_tx_params *params); - int (*roce_ll2_post_rx_buffer)(struct qed_dev *cdev, - struct qed_roce_ll2_buffer *buf, - u64 cookie, u8 notify_fw); - int (*roce_ll2_set_mac_filter)(struct qed_dev *cdev, - u8 *old_mac_address, - u8 *new_mac_address); - int (*roce_ll2_stats)(struct qed_dev *cdev, - struct qed_ll2_stats *stats); + + int (*ll2_acquire_connection)(void *rdma_cxt, + struct qed_ll2_acquire_data *data); + + int (*ll2_establish_connection)(void *rdma_cxt, u8 connection_handle); + int (*ll2_terminate_connection)(void *rdma_cxt, u8 connection_handle); + void (*ll2_release_connection)(void *rdma_cxt, u8 connection_handle); + + int (*ll2_prepare_tx_packet)(void *rdma_cxt, + u8 connection_handle, + struct qed_ll2_tx_pkt_info *pkt, + bool notify_fw); + + int (*ll2_set_fragment_of_tx_packet)(void *rdma_cxt, + u8 connection_handle, + dma_addr_t addr, + u16 nbytes); + int (*ll2_post_rx_buffer)(void *rdma_cxt, u8 connection_handle, + dma_addr_t addr, u16 buf_len, void *cookie, + u8 notify_fw); + int (*ll2_get_stats)(void *rdma_cxt, + u8 connection_handle, + struct qed_ll2_stats *p_stats); + int (*ll2_set_mac_filter)(struct qed_dev *cdev, + u8 *old_mac_address, u8 *new_mac_address); + + int (*iwarp_connect)(void *rdma_cxt, + struct qed_iwarp_connect_in *iparams, + struct qed_iwarp_connect_out *oparams); + + int (*iwarp_create_listen)(void *rdma_cxt, + struct qed_iwarp_listen_in *iparams, + struct qed_iwarp_listen_out *oparams); + + int (*iwarp_accept)(void *rdma_cxt, + struct qed_iwarp_accept_in *iparams); + + int (*iwarp_reject)(void *rdma_cxt, + struct qed_iwarp_reject_in *iparams); + + int (*iwarp_destroy_listen)(void *rdma_cxt, void *handle); + + int (*iwarp_send_rtr)(void *rdma_cxt, + struct qed_iwarp_send_rtr_in *iparams); }; const struct qed_rdma_ops *qed_get_rdma_ops(void); diff --git a/include/linux/qed/qede_roce.h b/include/linux/qed/qede_rdma.h index 3b8dd551a98c..9904617a9730 100644 --- a/include/linux/qed/qede_roce.h +++ b/include/linux/qed/qede_rdma.h @@ -32,22 +32,27 @@ #ifndef QEDE_ROCE_H #define QEDE_ROCE_H +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/types.h> +#include <linux/workqueue.h> + struct qedr_dev; struct qed_dev; struct qede_dev; -enum qede_roce_event { +enum qede_rdma_event { QEDE_UP, QEDE_DOWN, QEDE_CHANGE_ADDR, QEDE_CLOSE }; -struct qede_roce_event_work { +struct qede_rdma_event_work { struct list_head list; struct work_struct work; void *ptr; - enum qede_roce_event event; + enum qede_rdma_event event; }; struct qedr_driver { @@ -57,32 +62,33 @@ struct qedr_driver { struct net_device *); void (*remove)(struct qedr_dev *); - void (*notify)(struct qedr_dev *, enum qede_roce_event); + void (*notify)(struct qedr_dev *, enum qede_rdma_event); }; -/* APIs for RoCE driver to register callback handlers, +/* APIs for RDMA driver to register callback handlers, * which will be invoked when device is added, removed, ifup, ifdown */ -int qede_roce_register_driver(struct qedr_driver *drv); -void qede_roce_unregister_driver(struct qedr_driver *drv); +int qede_rdma_register_driver(struct qedr_driver *drv); +void qede_rdma_unregister_driver(struct qedr_driver *drv); -bool qede_roce_supported(struct qede_dev *dev); +bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_roce_dev_add(struct qede_dev *dev); -void qede_roce_dev_event_open(struct qede_dev *dev); -void qede_roce_dev_event_close(struct qede_dev *dev); -void qede_roce_dev_remove(struct qede_dev *dev); -void qede_roce_event_changeaddr(struct qede_dev *qedr); +int qede_rdma_dev_add(struct qede_dev *dev); +void qede_rdma_dev_event_open(struct qede_dev *dev); +void qede_rdma_dev_event_close(struct qede_dev *dev); +void qede_rdma_dev_remove(struct qede_dev *dev); +void qede_rdma_event_changeaddr(struct qede_dev *edr); + #else -static inline int qede_roce_dev_add(struct qede_dev *dev) +static inline int qede_rdma_dev_add(struct qede_dev *dev) { return 0; } -static inline void qede_roce_dev_event_open(struct qede_dev *dev) {} -static inline void qede_roce_dev_event_close(struct qede_dev *dev) {} -static inline void qede_roce_dev_remove(struct qede_dev *dev) {} -static inline void qede_roce_event_changeaddr(struct qede_dev *qedr) {} +static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} +static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} +static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index 72c770f9f666..a9b3050f469c 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -42,7 +42,7 @@ #define RDMA_MAX_SGE_PER_SQ_WQE (4) #define RDMA_MAX_SGE_PER_RQ_WQE (4) -#define RDMA_MAX_DATA_SIZE_IN_WQE (0x7FFFFFFF) +#define RDMA_MAX_DATA_SIZE_IN_WQE (0x80000000) #define RDMA_REQ_RD_ATOMIC_ELM_SIZE (0x50) #define RDMA_RESP_RD_ATOMIC_ELM_SIZE (0x20) diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index 866f063026de..fe6a33e45977 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -37,6 +37,8 @@ #define ROCE_REQ_MAX_SINGLE_SQ_WQE_SIZE (288) #define ROCE_MAX_QPS (32 * 1024) +#define ROCE_DCQCN_NP_MAX_QPS (64) +#define ROCE_DCQCN_RP_MAX_QPS (64) enum roce_async_events_type { ROCE_ASYNC_EVENT_NONE = 0, diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index a5e843268f0e..dbf7a43c3e1f 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -111,7 +111,6 @@ struct tcp_offload_params { __le32 snd_wnd; __le32 rcv_wnd; __le32 snd_wl1; - __le32 ts_time; __le32 ts_recent; __le32 ts_recent_age; __le32 total_rt; @@ -122,7 +121,7 @@ struct tcp_offload_params { u8 ka_probe_cnt; u8 rt_cnt; __le16 rtt_var; - __le16 reserved2; + __le16 fw_internal; __le32 ka_timeout; __le32 ka_interval; __le32 max_rt_time; @@ -130,7 +129,7 @@ struct tcp_offload_params { u8 snd_wnd_scale; u8 ack_frequency; __le16 da_timeout_value; - __le32 ts_ticks_per_second; + __le32 reserved3[2]; }; struct tcp_offload_params_opt2 { diff --git a/include/linux/quota.h b/include/linux/quota.h index 3434eef2a5aa..5ac9de4fcd6f 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -223,12 +223,12 @@ struct mem_dqinfo { struct quota_format_type *dqi_format; int dqi_fmt_id; /* Id of the dqi_format - used when turning * quotas on after remount RW */ - struct list_head dqi_dirty_list; /* List of dirty dquots */ - unsigned long dqi_flags; - unsigned int dqi_bgrace; - unsigned int dqi_igrace; - qsize_t dqi_max_spc_limit; - qsize_t dqi_max_ino_limit; + struct list_head dqi_dirty_list; /* List of dirty dquots [dq_list_lock] */ + unsigned long dqi_flags; /* DFQ_ flags [dq_data_lock] */ + unsigned int dqi_bgrace; /* Space grace time [dq_data_lock] */ + unsigned int dqi_igrace; /* Inode grace time [dq_data_lock] */ + qsize_t dqi_max_spc_limit; /* Maximum space limit [static] */ + qsize_t dqi_max_ino_limit; /* Maximum inode limit [static] */ void *dqi_priv; }; @@ -293,18 +293,18 @@ static inline void dqstats_dec(unsigned int type) * clear them when it sees fit. */ struct dquot { - struct hlist_node dq_hash; /* Hash list in memory */ - struct list_head dq_inuse; /* List of all quotas */ - struct list_head dq_free; /* Free list element */ - struct list_head dq_dirty; /* List of dirty dquots */ + struct hlist_node dq_hash; /* Hash list in memory [dq_list_lock] */ + struct list_head dq_inuse; /* List of all quotas [dq_list_lock] */ + struct list_head dq_free; /* Free list element [dq_list_lock] */ + struct list_head dq_dirty; /* List of dirty dquots [dq_list_lock] */ struct mutex dq_lock; /* dquot IO lock */ + spinlock_t dq_dqb_lock; /* Lock protecting dq_dqb changes */ atomic_t dq_count; /* Use count */ - wait_queue_head_t dq_wait_unused; /* Wait queue for dquot to become unused */ struct super_block *dq_sb; /* superblock this applies to */ struct kqid dq_id; /* ID this applies to (uid, gid, projid) */ - loff_t dq_off; /* Offset of dquot on disk */ + loff_t dq_off; /* Offset of dquot on disk [dq_lock, stable once set] */ unsigned long dq_flags; /* See DQ_* */ - struct mem_dqblk dq_dqb; /* Diskquota usage */ + struct mem_dqblk dq_dqb; /* Diskquota usage [dq_dqb_lock] */ }; /* Operations which must be implemented by each quota format */ @@ -332,6 +332,8 @@ struct dquot_operations { * quota code only */ qsize_t *(*get_reserved_space) (struct inode *); int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */ + /* Get number of inodes that were charged for a given inode */ + int (*get_inode_usage) (struct inode *, qsize_t *); /* Get next ID with active quota structure */ int (*get_next_id) (struct super_block *sb, struct kqid *qid); }; @@ -489,6 +491,9 @@ enum { */ #define DQUOT_NEGATIVE_USAGE (1 << (DQUOT_STATE_LAST + 1)) /* Allow negative quota usage */ +/* Do not track dirty dquots in a list */ +#define DQUOT_NOLIST_DIRTY (1 << (DQUOT_STATE_LAST + 2)) + static inline unsigned int dquot_state_flag(unsigned int flags, int type) { return flags << type; @@ -519,7 +524,7 @@ static inline void quota_send_warning(struct kqid qid, dev_t dev, struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ - struct mutex dqio_mutex; /* lock device while I/O in progress */ + struct rw_semaphore dqio_sem; /* Lock quota file while I/O in progress */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index dda22f45fc1b..0ce6fc49962e 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -38,11 +38,6 @@ void __quota_error(struct super_block *sb, const char *func, /* * declaration of quota_function calls in kernel. */ -void inode_add_rsv_space(struct inode *inode, qsize_t number); -void inode_claim_rsv_space(struct inode *inode, qsize_t number); -void inode_sub_rsv_space(struct inode *inode, qsize_t number); -void inode_reclaim_rsv_space(struct inode *inode, qsize_t number); - int dquot_initialize(struct inode *inode); bool dquot_initialize_needed(struct inode *inode); void dquot_drop(struct inode *inode); diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 3e5735064b71..567ebb5eaab0 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -357,8 +357,25 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); -void __rcu **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *, - gfp_t, int end); + +void __rcu **idr_get_free_cmn(struct radix_tree_root *root, + struct radix_tree_iter *iter, gfp_t gfp, + unsigned long max); +static inline void __rcu **idr_get_free(struct radix_tree_root *root, + struct radix_tree_iter *iter, + gfp_t gfp, + int end) +{ + return idr_get_free_cmn(root, iter, gfp, end > 0 ? end - 1 : INT_MAX); +} + +static inline void __rcu **idr_get_free_ext(struct radix_tree_root *root, + struct radix_tree_iter *iter, + gfp_t gfp, + unsigned long end) +{ + return idr_get_free_cmn(root, iter, gfp, end - 1); +} enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 4d57bbaaa1bf..583cdd3d49ca 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -121,6 +121,7 @@ extern const struct raid6_recov_calls raid6_recov_ssse3; extern const struct raid6_recov_calls raid6_recov_avx2; extern const struct raid6_recov_calls raid6_recov_avx512; extern const struct raid6_recov_calls raid6_recov_s390xc; +extern const struct raid6_recov_calls raid6_recov_neon; extern const struct raid6_calls raid6_neonx1; extern const struct raid6_calls raid6_neonx2; @@ -142,6 +143,7 @@ int raid6_select_algo(void); extern const u8 raid6_gfmul[256][256] __attribute__((aligned(256))); extern const u8 raid6_vgfmul[256][32] __attribute__((aligned(256))); extern const u8 raid6_gfexp[256] __attribute__((aligned(256))); +extern const u8 raid6_gflog[256] __attribute__((aligned(256))); extern const u8 raid6_gfinv[256] __attribute__((aligned(256))); extern const u8 raid6_gfexi[256] __attribute__((aligned(256))); diff --git a/include/linux/random.h b/include/linux/random.h index ed5c3838780d..eafea6a09361 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern void add_input_randomness(unsigned int type, unsigned int code, extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); +extern int wait_for_random_bytes(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); @@ -57,6 +58,52 @@ static inline unsigned long get_random_long(void) #endif } +/* + * On 64-bit architectures, protect against non-terminated C string overflows + * by zeroing out the first byte of the canary; this leaves 56 bits of entropy. + */ +#ifdef CONFIG_64BIT +# ifdef __LITTLE_ENDIAN +# define CANARY_MASK 0xffffffffffffff00UL +# else /* big endian, 64 bits: */ +# define CANARY_MASK 0x00ffffffffffffffUL +# endif +#else /* 32 bits: */ +# define CANARY_MASK 0xffffffffUL +#endif + +static inline unsigned long get_random_canary(void) +{ + unsigned long val = get_random_long(); + + return val & CANARY_MASK; +} + +/* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). + * Returns the result of the call to wait_for_random_bytes. */ +static inline int get_random_bytes_wait(void *buf, int nbytes) +{ + int ret = wait_for_random_bytes(); + if (unlikely(ret)) + return ret; + get_random_bytes(buf, nbytes); + return 0; +} + +#define declare_get_random_var_wait(var) \ + static inline int get_random_ ## var ## _wait(var *out) { \ + int ret = wait_for_random_bytes(); \ + if (unlikely(ret)) \ + return ret; \ + *out = get_random_ ## var(); \ + return 0; \ + } +declare_get_random_var_wait(u32) +declare_get_random_var_wait(u64) +declare_get_random_var_wait(int) +declare_get_random_var_wait(long) +#undef declare_get_random_var + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); diff --git a/include/linux/ras.h b/include/linux/ras.h index ffb147185e8d..be5338a35d57 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -2,6 +2,8 @@ #define __RAS_H__ #include <asm/errno.h> +#include <linux/uuid.h> +#include <linux/cper.h> #ifdef CONFIG_DEBUG_FS int ras_userspace_consumers(void); @@ -22,4 +24,19 @@ static inline void __init cec_init(void) { } static inline int cec_add_elem(u64 pfn) { return -ENODEV; } #endif +#ifdef CONFIG_RAS +void log_non_standard_event(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, + const u8 sev, const u8 *err, const u32 len); +void log_arm_hw_error(struct cper_sec_proc_arm *err); +#else +static inline void +log_non_standard_event(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, + const u8 sev, const u8 *err, const u32 len) +{ return; } +static inline void +log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } +#endif + #endif /* __RAS_H__ */ diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index e585018498d5..d574361943ea 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -44,10 +44,25 @@ struct rb_root { struct rb_node *rb_node; }; +/* + * Leftmost-cached rbtrees. + * + * We do not cache the rightmost node based on footprint + * size vs number of potential users that could benefit + * from O(1) rb_last(). Just not worth it, users that want + * this feature can always implement the logic explicitly. + * Furthermore, users that want to cache both pointers may + * find it a bit asymmetric, but that's ok. + */ +struct rb_root_cached { + struct rb_root rb_root; + struct rb_node *rb_leftmost; +}; #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define RB_ROOT (struct rb_root) { NULL, } +#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) @@ -69,6 +84,12 @@ extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); +extern void rb_insert_color_cached(struct rb_node *, + struct rb_root_cached *, bool); +extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *); +/* Same as rb_first(), but O(1) */ +#define rb_first_cached(root) (root)->rb_leftmost + /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 9702b6e183bc..6bfd2b581f75 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -41,7 +41,9 @@ struct rb_augment_callbacks { void (*rotate)(struct rb_node *old, struct rb_node *new); }; -extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, +extern void __rb_insert_augmented(struct rb_node *node, + struct rb_root *root, + bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. @@ -57,7 +59,16 @@ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - __rb_insert_augmented(node, root, augment->rotate); + __rb_insert_augmented(node, root, false, NULL, augment->rotate); +} + +static inline void +rb_insert_augmented_cached(struct rb_node *node, + struct rb_root_cached *root, bool newleft, + const struct rb_augment_callbacks *augment) +{ + __rb_insert_augmented(node, &root->rb_root, + newleft, &root->rb_leftmost, augment->rotate); } #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \ @@ -150,6 +161,7 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, + struct rb_node **leftmost, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; @@ -157,6 +169,9 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, struct rb_node *parent, *rebalance; unsigned long pc; + if (leftmost && node == *leftmost) + *leftmost = rb_next(node); + if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) @@ -256,9 +271,21 @@ static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); + struct rb_node *rebalance = __rb_erase_augmented(node, root, + NULL, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } +static __always_inline void +rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, + const struct rb_augment_callbacks *augment) +{ + struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root, + &root->rb_leftmost, + augment); + if (rebalance) + __rb_erase_color(rebalance, &root->rb_root, augment->rotate); +} + #endif /* _LINUX_RBTREE_AUGMENTED_H */ diff --git a/include/linux/rcu_node_tree.h b/include/linux/rcu_node_tree.h index 4b766b61e1a0..426cee67f0e2 100644 --- a/include/linux/rcu_node_tree.h +++ b/include/linux/rcu_node_tree.h @@ -7,6 +7,10 @@ * unlimited scalability while maintaining a constant level of contention * on the root node. * + * This seemingly RCU-private file must be available to SRCU users + * because the size of the TREE SRCU srcu_struct structure depends + * on these definitions. + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index ba4d2621d9ca..c3ad00e63556 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -1,6 +1,10 @@ /* * RCU segmented callback lists * + * This seemingly RCU-private file must be available to SRCU users + * because the size of the TREE SRCU srcu_struct structure depends + * on these definitions. + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e1e5d002fdb9..de50d8a4cf41 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -34,104 +34,15 @@ #define __LINUX_RCUPDATE_H #include <linux/types.h> -#include <linux/cache.h> -#include <linux/spinlock.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/seqlock.h> -#include <linux/lockdep.h> -#include <linux/debugobjects.h> -#include <linux/bug.h> #include <linux/compiler.h> -#include <linux/ktime.h> +#include <linux/atomic.h> #include <linux/irqflags.h> +#include <linux/preempt.h> +#include <linux/bottom_half.h> +#include <linux/lockdep.h> +#include <asm/processor.h> +#include <linux/cpumask.h> -#include <asm/barrier.h> - -#ifndef CONFIG_TINY_RCU -extern int rcu_expedited; /* for sysctl */ -extern int rcu_normal; /* also for sysctl */ -#endif /* #ifndef CONFIG_TINY_RCU */ - -#ifdef CONFIG_TINY_RCU -/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ -static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ -{ - return true; -} -static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ -{ - return false; -} - -static inline void rcu_expedite_gp(void) -{ -} - -static inline void rcu_unexpedite_gp(void) -{ -} -#else /* #ifdef CONFIG_TINY_RCU */ -bool rcu_gp_is_normal(void); /* Internal RCU use. */ -bool rcu_gp_is_expedited(void); /* Internal RCU use. */ -void rcu_expedite_gp(void); -void rcu_unexpedite_gp(void); -#endif /* #else #ifdef CONFIG_TINY_RCU */ - -enum rcutorture_type { - RCU_FLAVOR, - RCU_BH_FLAVOR, - RCU_SCHED_FLAVOR, - RCU_TASKS_FLAVOR, - SRCU_FLAVOR, - INVALID_RCU_FLAVOR -}; - -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) -void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed); -void rcutorture_record_test_transition(void); -void rcutorture_record_progress(unsigned long vernum); -void do_trace_rcu_torture_read(const char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -bool rcu_irq_enter_disabled(void); -#else -static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, - int *flags, - unsigned long *gpnum, - unsigned long *completed) -{ - *flags = 0; - *gpnum = 0; - *completed = 0; -} -static inline void rcutorture_record_test_transition(void) -{ -} -static inline void rcutorture_record_progress(unsigned long vernum) -{ -} -static inline bool rcu_irq_enter_disabled(void) -{ - return false; -} -#ifdef CONFIG_RCU_TRACE -void do_trace_rcu_torture_read(const char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -#else -#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ - do { } while (0) -#endif -#endif - -#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) -#define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) @@ -139,117 +50,14 @@ void do_trace_rcu_torture_read(const char *rcutorturename, /* Exported common interfaces */ #ifdef CONFIG_PREEMPT_RCU - -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing RCU read-side critical section. On systems with more - * than one CPU, this means that when "func()" is invoked, each CPU is - * guaranteed to have executed a full memory barrier since the end of its - * last RCU read-side critical section whose beginning preceded the call - * to call_rcu(). It also means that each CPU executing an RCU read-side - * critical section that continues beyond the start of "func()" must have - * executed a memory barrier after the call_rcu() but before the beginning - * of that RCU read-side critical section. Note that these guarantees - * include CPUs that are offline, idle, or executing in user mode, as - * well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting RCU callback function "func()", then both CPU A and CPU B are - * guaranteed to execute a full memory barrier during the time interval - * between the call to call_rcu() and the invocation of "func()" -- even - * if CPU A and CPU B are the same CPU (but again only if the system has - * more than one CPU). - */ -void call_rcu(struct rcu_head *head, - rcu_callback_t func); - +void call_rcu(struct rcu_head *head, rcu_callback_t func); #else /* #ifdef CONFIG_PREEMPT_RCU */ - -/* In classic RCU, call_rcu() is just call_rcu_sched(). */ #define call_rcu call_rcu_sched - #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ -/** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_bh(struct rcu_head *head, - rcu_callback_t func); - -/** - * call_rcu_sched() - Queue an RCU for invocation after sched grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_sched() assumes - * that the read-side critical sections end on enabling of preemption - * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), - * OR - * anything that disables preemption. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_sched(struct rcu_head *head, - rcu_callback_t func); - +void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); +void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); - -/** - * call_rcu_tasks() - Queue an RCU for invocation task-based grace period - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_tasks() assumes - * that the read-side critical sections end at a voluntary context - * switch (not a preemption!), entry into idle, or transition to usermode - * execution. As such, there are no read-side primitives analogous to - * rcu_read_lock() and rcu_read_unlock() because this primitive is intended - * to determine that all tasks have passed through a safe state, not so - * much for data-strcuture synchronization. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); -void synchronize_rcu_tasks(void); void rcu_barrier_tasks(void); #ifdef CONFIG_PREEMPT_RCU @@ -295,28 +103,20 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); +extern int rcu_scheduler_active __read_mostly; void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcu_cpu_starting(unsigned int cpu); - -#ifndef CONFIG_TINY_RCU -void rcu_end_inkernel_boot(void); -#else /* #ifndef CONFIG_TINY_RCU */ -static inline void rcu_end_inkernel_boot(void) { } -#endif /* #ifndef CONFIG_TINY_RCU */ +void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ -static inline void rcu_sysrq_start(void) -{ -} -static inline void rcu_sysrq_end(void) -{ -} +static inline void rcu_sysrq_start(void) { } +static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL @@ -330,9 +130,7 @@ static inline void rcu_user_exit(void) { } #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static inline void rcu_init_nohz(void) -{ -} +static inline void rcu_init_nohz(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** @@ -366,8 +164,6 @@ static inline void rcu_init_nohz(void) * macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU -#define TASKS_RCU(x) x -extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch_lite(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ @@ -378,10 +174,17 @@ extern struct srcu_struct tasks_rcu_exit_srcu; rcu_all_qs(); \ rcu_note_voluntary_context_switch_lite(t); \ } while (0) +void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); +void synchronize_rcu_tasks(void); +void exit_tasks_rcu_start(void); +void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ -#define TASKS_RCU(x) do { } while (0) #define rcu_note_voluntary_context_switch_lite(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() +#define call_rcu_tasks call_rcu_sched +#define synchronize_rcu_tasks synchronize_sched +static inline void exit_tasks_rcu_start(void) { } +static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** @@ -397,10 +200,6 @@ do { \ rcu_note_voluntary_context_switch(current); \ } while (0) -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) -bool __rcu_is_watching(void); -#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */ - /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -414,10 +213,6 @@ bool __rcu_is_watching(void); #error "Unknown RCU implementation specified to kernel configuration" #endif -#define RCU_SCHEDULER_INACTIVE 0 -#define RCU_SCHEDULER_INIT 1 -#define RCU_SCHEDULER_RUNNING 2 - /* * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic * initialization and destruction of rcu_head on the stack. rcu_head structures @@ -430,30 +225,16 @@ void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -static inline void init_rcu_head(struct rcu_head *head) -{ -} - -static inline void destroy_rcu_head(struct rcu_head *head) -{ -} - -static inline void init_rcu_head_on_stack(struct rcu_head *head) -{ -} - -static inline void destroy_rcu_head_on_stack(struct rcu_head *head) -{ -} +static inline void init_rcu_head(struct rcu_head *head) { } +static inline void destroy_rcu_head(struct rcu_head *head) { } +static inline void init_rcu_head_on_stack(struct rcu_head *head) { } +static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ -static inline bool rcu_lockdep_current_cpu_online(void) -{ - return true; -} +static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -473,18 +254,8 @@ extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); - int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); - -/** - * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? - * - * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an - * RCU-sched read-side critical section. In absence of - * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side - * critical section unless it can prove otherwise. - */ int rcu_read_lock_sched_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -531,9 +302,7 @@ static inline void rcu_preempt_sleep_check(void) "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ -static inline void rcu_preempt_sleep_check(void) -{ -} +static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ @@ -644,6 +413,22 @@ static inline void rcu_preempt_sleep_check(void) }) /** + * rcu_swap_protected() - swap an RCU and a regular pointer + * @rcu_ptr: RCU pointer + * @ptr: regular pointer + * @c: the conditions under which the dereference will take place + * + * Perform swap(@rcu_ptr, @ptr) where @rcu_ptr is an RCU-annotated pointer and + * @c is the argument that is passed to the rcu_dereference_protected() call + * used to read that pointer. + */ +#define rcu_swap_protected(rcu_ptr, ptr, c) do { \ + typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ + rcu_assign_pointer((rcu_ptr), (ptr)); \ + (ptr) = __tmp; \ +} while (0) + +/** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * @@ -1084,52 +869,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) -#ifdef CONFIG_TINY_RCU -static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) -{ - *nextevt = KTIME_MAX; - return 0; -} -#endif /* #ifdef CONFIG_TINY_RCU */ - -#if defined(CONFIG_RCU_NOCB_CPU_ALL) -static inline bool rcu_is_nocb_cpu(int cpu) { return true; } -#elif defined(CONFIG_RCU_NOCB_CPU) -bool rcu_is_nocb_cpu(int cpu); -#else -static inline bool rcu_is_nocb_cpu(int cpu) { return false; } -#endif - - -/* Only for use by adaptive-ticks code. */ -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE -bool rcu_sys_is_idle(void); -void rcu_sysidle_force_exit(void); -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - -static inline bool rcu_sys_is_idle(void) -{ - return false; -} - -static inline void rcu_sysidle_force_exit(void) -{ -} - -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - - -/* - * Dump the ftrace buffer, but only one time per callsite per boot. - */ -#define rcu_ftrace_dump(oops_dump_mode) \ -do { \ - static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \ - \ - if (!atomic_read(&___rfd_beenhere) && \ - !atomic_xchg(&___rfd_beenhere, 1)) \ - ftrace_dump(oops_dump_mode); \ -} while (0) /* * Place this after a lock-acquisition primitive to guarantee that diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 74d9c3a1feee..b3dbf9502fd0 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -25,7 +25,7 @@ #ifndef __LINUX_TINY_H #define __LINUX_TINY_H -#include <linux/cache.h> +#include <linux/ktime.h> struct rcu_dynticks; static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) @@ -33,10 +33,8 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) return 0; } -static inline bool rcu_eqs_special_set(int cpu) -{ - return false; /* Never flag non-existent other CPUs! */ -} +/* Never flag non-existent other CPUs! */ +static inline bool rcu_eqs_special_set(int cpu) { return false; } static inline unsigned long get_state_synchronize_rcu(void) { @@ -98,159 +96,36 @@ static inline void kfree_call_rcu(struct rcu_head *head, rcu_note_voluntary_context_switch_lite(current); \ } while (0) -/* - * Take advantage of the fact that there is only one CPU, which - * allows us to ignore virtualization-based context switches. - */ -static inline void rcu_virt_note_context_switch(int cpu) -{ -} - -/* - * Return the number of grace periods started. - */ -static inline unsigned long rcu_batches_started(void) +static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) { + *nextevt = KTIME_MAX; return 0; } /* - * Return the number of bottom-half grace periods started. - */ -static inline unsigned long rcu_batches_started_bh(void) -{ - return 0; -} - -/* - * Return the number of sched grace periods started. - */ -static inline unsigned long rcu_batches_started_sched(void) -{ - return 0; -} - -/* - * Return the number of grace periods completed. - */ -static inline unsigned long rcu_batches_completed(void) -{ - return 0; -} - -/* - * Return the number of bottom-half grace periods completed. - */ -static inline unsigned long rcu_batches_completed_bh(void) -{ - return 0; -} - -/* - * Return the number of sched grace periods completed. - */ -static inline unsigned long rcu_batches_completed_sched(void) -{ - return 0; -} - -/* - * Return the number of expedited grace periods completed. - */ -static inline unsigned long rcu_exp_batches_completed(void) -{ - return 0; -} - -/* - * Return the number of expedited sched grace periods completed. + * Take advantage of the fact that there is only one CPU, which + * allows us to ignore virtualization-based context switches. */ -static inline unsigned long rcu_exp_batches_completed_sched(void) -{ - return 0; -} - -static inline void rcu_force_quiescent_state(void) -{ -} - -static inline void rcu_bh_force_quiescent_state(void) -{ -} - -static inline void rcu_sched_force_quiescent_state(void) -{ -} - -static inline void show_rcu_gp_kthreads(void) -{ -} - -static inline void rcu_cpu_stall_reset(void) -{ -} - -static inline void rcu_idle_enter(void) -{ -} - -static inline void rcu_idle_exit(void) -{ -} - -static inline void rcu_irq_enter(void) -{ -} - -static inline void rcu_irq_exit_irqson(void) -{ -} - -static inline void rcu_irq_enter_irqson(void) -{ -} - -static inline void rcu_irq_exit(void) -{ -} - -static inline void exit_rcu(void) -{ -} - -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) -extern int rcu_scheduler_active __read_mostly; +static inline void rcu_virt_note_context_switch(int cpu) { } +static inline void rcu_cpu_stall_reset(void) { } +static inline void rcu_idle_enter(void) { } +static inline void rcu_idle_exit(void) { } +static inline void rcu_irq_enter(void) { } +static inline bool rcu_irq_enter_disabled(void) { return false; } +static inline void rcu_irq_exit_irqson(void) { } +static inline void rcu_irq_enter_irqson(void) { } +static inline void rcu_irq_exit(void) { } +static inline void exit_rcu(void) { } +#ifdef CONFIG_SRCU void rcu_scheduler_starting(void); -#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ -static inline void rcu_scheduler_starting(void) -{ -} -#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ - -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) - -static inline bool rcu_is_watching(void) -{ - return __rcu_is_watching(); -} - -#else /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - -static inline bool rcu_is_watching(void) -{ - return true; -} - -#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - -static inline void rcu_request_urgent_qs_task(struct task_struct *t) -{ -} - -static inline void rcu_all_qs(void) -{ - barrier(); /* Avoid RCU read-side critical sections leaking across. */ -} +#else /* #ifndef CONFIG_SRCU */ +static inline void rcu_scheduler_starting(void) { } +#endif /* #else #ifndef CONFIG_SRCU */ +static inline void rcu_end_inkernel_boot(void) { } +static inline bool rcu_is_watching(void) { return true; } + +/* Avoid RCU read-side critical sections leaking across. */ +static inline void rcu_all_qs(void) { barrier(); } /* RCUtree hotplug events */ #define rcutree_prepare_cpu NULL diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 0bacb6b2af69..37d6fd3b7ff8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -79,37 +79,20 @@ void cond_synchronize_rcu(unsigned long oldstate); unsigned long get_state_synchronize_sched(void); void cond_synchronize_sched(unsigned long oldstate); -extern unsigned long rcutorture_testseq; -extern unsigned long rcutorture_vernum; -unsigned long rcu_batches_started(void); -unsigned long rcu_batches_started_bh(void); -unsigned long rcu_batches_started_sched(void); -unsigned long rcu_batches_completed(void); -unsigned long rcu_batches_completed_bh(void); -unsigned long rcu_batches_completed_sched(void); -unsigned long rcu_exp_batches_completed(void); -unsigned long rcu_exp_batches_completed_sched(void); -void show_rcu_gp_kthreads(void); - -void rcu_force_quiescent_state(void); -void rcu_bh_force_quiescent_state(void); -void rcu_sched_force_quiescent_state(void); - void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); +bool rcu_irq_enter_disabled(void); void exit_rcu(void); void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; - +void rcu_end_inkernel_boot(void); bool rcu_is_watching(void); -void rcu_request_urgent_qs_task(struct task_struct *t); - void rcu_all_qs(void); /* RCUtree hotplug events */ diff --git a/include/linux/reboot-mode.h b/include/linux/reboot-mode.h new file mode 100644 index 000000000000..75f7fe5c881f --- /dev/null +++ b/include/linux/reboot-mode.h @@ -0,0 +1,18 @@ +#ifndef __REBOOT_MODE_H__ +#define __REBOOT_MODE_H__ + +struct reboot_mode_driver { + struct device *dev; + struct list_head head; + int (*write)(struct reboot_mode_driver *reboot, unsigned int magic); + struct notifier_block reboot_notifier; +}; + +int reboot_mode_register(struct reboot_mode_driver *reboot); +int reboot_mode_unregister(struct reboot_mode_driver *reboot); +int devm_reboot_mode_register(struct device *dev, + struct reboot_mode_driver *reboot); +void devm_reboot_mode_unregister(struct device *dev, + struct reboot_mode_driver *reboot); + +#endif diff --git a/include/linux/refcount.h b/include/linux/refcount.h index b34aa649d204..48b7c9c68c4d 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -41,6 +41,7 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } +#ifdef CONFIG_REFCOUNT_FULL extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); extern void refcount_add(unsigned int i, refcount_t *r); @@ -48,10 +49,49 @@ extern __must_check bool refcount_inc_not_zero(refcount_t *r); extern void refcount_inc(refcount_t *r); extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); -extern void refcount_sub(unsigned int i, refcount_t *r); extern __must_check bool refcount_dec_and_test(refcount_t *r); extern void refcount_dec(refcount_t *r); +#else +# ifdef CONFIG_ARCH_HAS_REFCOUNT +# include <asm/refcount.h> +# else +static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r) +{ + return atomic_add_unless(&r->refs, i, 0); +} + +static inline void refcount_add(unsigned int i, refcount_t *r) +{ + atomic_add(i, &r->refs); +} + +static inline __must_check bool refcount_inc_not_zero(refcount_t *r) +{ + return atomic_add_unless(&r->refs, 1, 0); +} + +static inline void refcount_inc(refcount_t *r) +{ + atomic_inc(&r->refs); +} + +static inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) +{ + return atomic_sub_and_test(i, &r->refs); +} + +static inline __must_check bool refcount_dec_and_test(refcount_t *r) +{ + return atomic_dec_and_test(&r->refs); +} + +static inline void refcount_dec(refcount_t *r) +{ + atomic_dec(&r->refs); +} +# endif /* !CONFIG_ARCH_HAS_REFCOUNT */ +#endif /* CONFIG_REFCOUNT_FULL */ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 6e1df5e721a9..1474ab0a3922 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -462,6 +462,10 @@ struct regmap *__regmap_init_spmi_ext(struct spmi_device *dev, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__regmap_init_w1(struct device *w1_dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__regmap_init_mmio_clk(struct device *dev, const char *clk_id, void __iomem *regs, const struct regmap_config *config, @@ -494,6 +498,10 @@ struct regmap *__devm_regmap_init_spmi_ext(struct spmi_device *dev, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__devm_regmap_init_w1(struct device *w1_dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id, void __iomem *regs, @@ -598,6 +606,19 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, dev, config) /** + * regmap_init_w1() - Initialise register map + * + * @w1_dev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_w1(w1_dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_w1, #config, \ + w1_dev, config) + +/** * regmap_init_mmio_clk() - Initialise register map with register clock * * @dev: Device that will be interacted with @@ -713,6 +734,19 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); dev, config) /** + * devm_regmap_init_w1() - Initialise managed register map + * + * @w1_dev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_w1(w1_dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_w1, #config, \ + w1_dev, config) +/** * devm_regmap_init_mmio_clk() - Initialise managed register map with clock * * @dev: Device that will be interacted with @@ -885,6 +919,7 @@ struct regmap_irq { * * @status_base: Base status register address. * @mask_base: Base mask register address. + * @mask_writeonly: Base mask register is write only. * @unmask_base: Base unmask register address. for chips who have * separate mask and unmask registers * @ack_base: Base ack address. If zero then the chip is clear on read. @@ -928,6 +963,7 @@ struct regmap_irq_chip { unsigned int wake_base; unsigned int type_base; unsigned int irq_reg_stride; + bool mask_writeonly:1; bool init_ack_masked:1; bool mask_invert:1; bool use_ack:1; diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 117699d1f7df..9cd4fef37203 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -110,6 +110,10 @@ struct regulator_state { * @ramp_delay: Time to settle down after voltage change (unit: uV/us) * @settling_time: Time to settle down after voltage change when voltage * change is non-linear (unit: microseconds). + * @settling_time_up: Time to settle down after voltage increase when voltage + * change is non-linear (unit: microseconds). + * @settling_time_down : Time to settle down after voltage decrease when + * voltage change is non-linear (unit: microseconds). * @active_discharge: Enable/disable active discharge. The enum * regulator_active_discharge values are used for * initialisation. @@ -152,6 +156,8 @@ struct regulation_constraints { unsigned int ramp_delay; unsigned int settling_time; + unsigned int settling_time_up; + unsigned int settling_time_down; unsigned int enable_time; unsigned int active_discharge; diff --git a/include/linux/regulator/mt6380-regulator.h b/include/linux/regulator/mt6380-regulator.h new file mode 100644 index 000000000000..465182da6315 --- /dev/null +++ b/include/linux/regulator/mt6380-regulator.h @@ -0,0 +1,32 @@ +/* + * Copyright (c) 2017 MediaTek Inc. + * Author: Chenglin Xu <chenglin.xu@mediatek.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_REGULATOR_mt6380_H +#define __LINUX_REGULATOR_mt6380_H + +enum { + MT6380_ID_VCPU = 0, + MT6380_ID_VCORE, + MT6380_ID_VRF, + MT6380_ID_VMLDO, + MT6380_ID_VALDO, + MT6380_ID_VPHYLDO, + MT6380_ID_VDDRLDO, + MT6380_ID_VTLDO, + MT6380_ID_RG_MAX, +}; + +#define MT6380_MAX_REGULATOR MT6380_ID_RG_MAX + +#endif /* __LINUX_REGULATOR_mt6380_H */ diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 81da49564ff4..44e630eb3d94 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -510,6 +510,8 @@ struct rproc_vdev { }; struct rproc *rproc_get_by_phandle(phandle phandle); +struct rproc *rproc_get_by_child(struct device *dev); + struct rproc *rproc_alloc(struct device *dev, const char *name, const struct rproc_ops *ops, const char *firmware, int len); diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h new file mode 100644 index 000000000000..fa8e38681b4b --- /dev/null +++ b/include/linux/remoteproc/qcom_rproc.h @@ -0,0 +1,22 @@ +#ifndef __QCOM_RPROC_H__ +#define __QCOM_RPROC_H__ + +struct notifier_block; + +#if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) + +int qcom_register_ssr_notifier(struct notifier_block *nb); +void qcom_unregister_ssr_notifier(struct notifier_block *nb); + +#else + +static inline int qcom_register_ssr_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline void qcom_unregister_ssr_notifier(struct notifier_block *nb) {} + +#endif + +#endif diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 156cfd330b66..21fc84d82d41 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -254,6 +254,9 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, unsigned *pshared_count, struct dma_fence ***pshared); +int reservation_object_copy_fences(struct reservation_object *dst, + struct reservation_object *src); + long reservation_object_wait_timeout_rcu(struct reservation_object *obj, bool wait_all, bool intr, unsigned long timeout); diff --git a/include/linux/reset.h b/include/linux/reset.h index 13d8681210d5..56463f37f3e6 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -25,6 +25,11 @@ struct reset_control *__devm_reset_control_get(struct device *dev, int __must_check device_reset(struct device *dev); +struct reset_control *devm_reset_control_array_get(struct device *dev, + bool shared, bool optional); +struct reset_control *of_reset_control_array_get(struct device_node *np, + bool shared, bool optional); + static inline int device_reset_optional(struct device *dev) { return device_reset(dev); @@ -89,6 +94,18 @@ static inline struct reset_control *__devm_reset_control_get( return optional ? NULL : ERR_PTR(-ENOTSUPP); } +static inline struct reset_control * +devm_reset_control_array_get(struct device *dev, bool shared, bool optional) +{ + return optional ? NULL : ERR_PTR(-ENOTSUPP); +} + +static inline struct reset_control * +of_reset_control_array_get(struct device_node *np, bool shared, bool optional) +{ + return optional ? NULL : ERR_PTR(-ENOTSUPP); +} + #endif /* CONFIG_RESET_CONTROLLER */ /** @@ -374,4 +391,55 @@ static inline struct reset_control *devm_reset_control_get_by_index( { return devm_reset_control_get_exclusive_by_index(dev, index); } + +/* + * APIs to manage a list of reset controllers + */ +static inline struct reset_control * +devm_reset_control_array_get_exclusive(struct device *dev) +{ + return devm_reset_control_array_get(dev, false, false); +} + +static inline struct reset_control * +devm_reset_control_array_get_shared(struct device *dev) +{ + return devm_reset_control_array_get(dev, true, false); +} + +static inline struct reset_control * +devm_reset_control_array_get_optional_exclusive(struct device *dev) +{ + return devm_reset_control_array_get(dev, false, true); +} + +static inline struct reset_control * +devm_reset_control_array_get_optional_shared(struct device *dev) +{ + return devm_reset_control_array_get(dev, true, true); +} + +static inline struct reset_control * +of_reset_control_array_get_exclusive(struct device_node *node) +{ + return of_reset_control_array_get(node, false, false); +} + +static inline struct reset_control * +of_reset_control_array_get_shared(struct device_node *node) +{ + return of_reset_control_array_get(node, true, false); +} + +static inline struct reset_control * +of_reset_control_array_get_optional_exclusive(struct device_node *node) +{ + return of_reset_control_array_get(node, false, true); +} + +static inline struct reset_control * +of_reset_control_array_get_optional_shared(struct device_node *node) +{ + return of_reset_control_array_get(node, true, true); +} #endif diff --git a/include/linux/resource.h b/include/linux/resource.h index 5bc3116e649c..277afdad6589 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -6,7 +6,7 @@ struct task_struct; -int getrusage(struct task_struct *p, int who, struct rusage __user *ru); +void getrusage(struct task_struct *p, int who, struct rusage *ru); int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim); diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 0d905d8ec553..19df8422606c 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -11,6 +11,14 @@ struct timespec; struct compat_timespec; struct pollfd; +enum timespec_type { + TT_NONE = 0, + TT_NATIVE = 1, +#ifdef CONFIG_COMPAT + TT_COMPAT = 2, +#endif +}; + /* * System call restart block. */ @@ -29,10 +37,13 @@ struct restart_block { /* For nanosleep */ struct { clockid_t clockid; - struct timespec __user *rmtp; + enum timespec_type type; + union { + struct timespec __user *rmtp; #ifdef CONFIG_COMPAT - struct compat_timespec __user *compat_rmtp; + struct compat_timespec __user *compat_rmtp; #endif + }; u64 expires; } nanosleep; /* For poll */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 7d56a7ea2b2e..361c08e35dbc 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -127,7 +127,7 @@ struct rhashtable; * @head_offset: Offset of rhash_head in struct to be hashed * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking - * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) + * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) * @automatic_shrinking: Enable automatic shrinking of tables * @nulls_base: Base value to generate nulls marker * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 43ef2c30cb0f..733d3d8181e2 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -55,7 +55,9 @@ struct anon_vma { * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ - struct rb_root rb_root; /* Interval tree of private "related" vmas */ + + /* Interval tree of private "related" vmas */ + struct rb_root_cached rb_root; }; /* @@ -93,8 +95,9 @@ enum ttu_flags { TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ - TTU_RMAP_LOCKED = 0x80 /* do not grab rmap lock: + TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ + TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ }; #ifdef CONFIG_MMU diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h new file mode 100644 index 000000000000..a622f029836e --- /dev/null +++ b/include/linux/rpmsg/qcom_glink.h @@ -0,0 +1,27 @@ +#ifndef _LINUX_RPMSG_QCOM_GLINK_H +#define _LINUX_RPMSG_QCOM_GLINK_H + +#include <linux/device.h> + +struct qcom_glink; + +#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SMEM) + +struct qcom_glink *qcom_glink_smem_register(struct device *parent, + struct device_node *node); +void qcom_glink_smem_unregister(struct qcom_glink *glink); + +#else + +static inline struct qcom_glink * +qcom_glink_smem_register(struct device *parent, + struct device_node *node) +{ + return NULL; +} + +static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} + +#endif + +#endif diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b693adac853b..e6d0f9c1cafd 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/interrupt.h> +#include <linux/nvmem-provider.h> #include <uapi/linux/rtc.h> extern int rtc_month_days(unsigned int month, unsigned int year); @@ -32,17 +33,11 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs); } -/** - * Deprecated. Use rtc_time64_to_tm(). - */ static inline void rtc_time_to_tm(unsigned long time, struct rtc_time *tm) { rtc_time64_to_tm(time, tm); } -/** - * Deprecated. Use rtc_tm_to_time64(). - */ static inline int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time) { *time = rtc_tm_to_time64(tm); @@ -77,8 +72,6 @@ extern struct class *rtc_class; * issued through ioctl() ... */ struct rtc_class_ops { - int (*open)(struct device *); - void (*release)(struct device *); int (*ioctl)(struct device *, unsigned int, unsigned long); int (*read_time)(struct device *, struct rtc_time *); int (*set_time)(struct device *, struct rtc_time *); @@ -116,7 +109,6 @@ struct rtc_device { struct module *owner; int id; - char name[RTC_DEVICE_NAME_SIZE]; const struct rtc_class_ops *ops; struct mutex ops_lock; @@ -143,6 +135,14 @@ struct rtc_device { /* Some hardware can't support UIE mode */ int uie_unsupported; + bool registered; + + struct nvmem_config *nvmem_config; + struct nvmem_device *nvmem; + /* Old ABI support */ + bool nvram_old_abi; + struct bin_attribute *nvram; + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; @@ -164,6 +164,8 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); +struct rtc_device *devm_rtc_allocate_device(struct device *dev); +int __rtc_register_device(struct module *owner, struct rtc_device *rtc); extern void rtc_device_unregister(struct rtc_device *rtc); extern void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc); @@ -219,6 +221,9 @@ static inline bool is_leap_year(unsigned int year) return (!(year % 4) && (year % 100)) || !(year % 400); } +#define rtc_register_device(device) \ + __rtc_register_device(THIS_MODULE, device) + #ifdef CONFIG_RTC_HCTOSYS_DEVICE extern int rtc_hctosys_ret; #else diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1abba5ce2a2f..53fcbe9de7fd 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -22,21 +22,23 @@ extern int max_lock_depth; /* for sysctl */ * The rt_mutex structure * * @wait_lock: spinlock to protect the structure - * @waiters: rbtree root to enqueue waiters in priority order - * @waiters_leftmost: top waiter + * @waiters: rbtree root to enqueue waiters in priority order; + * caches top-waiter (leftmost node). * @owner: the mutex owner */ struct rt_mutex { raw_spinlock_t wait_lock; - struct rb_root waiters; - struct rb_node *waiters_leftmost; + struct rb_root_cached waiters; struct task_struct *owner; #ifdef CONFIG_DEBUG_RT_MUTEXES int save_state; - const char *name, *file; + const char *name, *file; int line; void *magic; #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif }; struct rt_mutex_waiter; @@ -58,19 +60,33 @@ struct hrtimer_sleeper; #ifdef CONFIG_DEBUG_RT_MUTEXES # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ , .name = #mutexname, .file = __FILE__, .line = __LINE__ -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) + +# define rt_mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + __rt_mutex_init(mutex, __func__, &__key); \ +} while (0) + extern void rt_mutex_debug_task_free(struct task_struct *tsk); #else # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) +# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL, NULL) # define rt_mutex_debug_task_free(t) do { } while (0) #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ + , .dep_map = { .name = #mutexname } +#else +#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) +#endif + #define __RT_MUTEX_INITIALIZER(mutexname) \ { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ - , .waiters = RB_ROOT \ + , .waiters = RB_ROOT_CACHED \ , .owner = NULL \ - __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} + __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ + __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) @@ -86,7 +102,7 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) return lock->owner != NULL; } -extern void __rt_mutex_init(struct rt_mutex *lock, const char *name); +extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); extern void rt_mutex_lock(struct rt_mutex *lock); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 57e54847b0b9..dea59c8eec54 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -18,7 +18,8 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, - unsigned change, gfp_t flags); + unsigned change, u32 event, + gfp_t flags); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index ae0528b834cd..e784761a4443 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -32,6 +32,7 @@ struct rw_semaphore { #define RWSEM_UNLOCKED_VALUE 0x00000000 extern void __down_read(struct rw_semaphore *sem); +extern int __must_check __down_read_killable(struct rw_semaphore *sem); extern int __down_read_trylock(struct rw_semaphore *sem); extern void __down_write(struct rw_semaphore *sem); extern int __must_check __down_write_killable(struct rw_semaphore *sem); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index dd1d14250340..0ad7318ff299 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -44,6 +44,7 @@ struct rw_semaphore { }; extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h deleted file mode 100644 index c68307bc306f..000000000000 --- a/include/linux/rxrpc.h +++ /dev/null @@ -1,72 +0,0 @@ -/* AF_RXRPC parameters - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _LINUX_RXRPC_H -#define _LINUX_RXRPC_H - -#include <linux/in.h> -#include <linux/in6.h> - -/* - * RxRPC socket address - */ -struct sockaddr_rxrpc { - sa_family_t srx_family; /* address family */ - u16 srx_service; /* service desired */ - u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ - u16 transport_len; /* length of transport address */ - union { - sa_family_t family; /* transport address family */ - struct sockaddr_in sin; /* IPv4 transport address */ - struct sockaddr_in6 sin6; /* IPv6 transport address */ - } transport; -}; - -/* - * RxRPC socket options - */ -#define RXRPC_SECURITY_KEY 1 /* [clnt] set client security key */ -#define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ -#define RXRPC_EXCLUSIVE_CONNECTION 3 /* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */ -#define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ - -/* - * RxRPC control messages - * - If neither abort or accept are specified, the message is a data message. - * - terminal messages mean that a user call ID tag can be recycled - * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() - */ -#define RXRPC_USER_CALL_ID 1 /* sr: user call ID specifier */ -#define RXRPC_ABORT 2 /* sr: abort request / notification [terminal] */ -#define RXRPC_ACK 3 /* -r: [Service] RPC op final ACK received [terminal] */ -#define RXRPC_NET_ERROR 5 /* -r: network error received [terminal] */ -#define RXRPC_BUSY 6 /* -r: server busy received [terminal] */ -#define RXRPC_LOCAL_ERROR 7 /* -r: local error generated [terminal] */ -#define RXRPC_NEW_CALL 8 /* -r: [Service] new incoming call notification */ -#define RXRPC_ACCEPT 9 /* s-: [Service] accept request */ -#define RXRPC_EXCLUSIVE_CALL 10 /* s-: Call should be on exclusive connection */ - -/* - * RxRPC security levels - */ -#define RXRPC_SECURITY_PLAIN 0 /* plain secure-checksummed packets only */ -#define RXRPC_SECURITY_AUTH 1 /* authenticated packets */ -#define RXRPC_SECURITY_ENCRYPT 2 /* encrypted packets */ - -/* - * RxRPC security indices - */ -#define RXRPC_SECURITY_NONE 0 /* no security protocol */ -#define RXRPC_SECURITY_RXKAD 2 /* kaserver or kerberos 4 */ -#define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ -#define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ - -#endif /* _LINUX_RXRPC_H */ diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index cb3c8fe6acd7..4b3286ac60c8 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -278,6 +278,8 @@ size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen, off_t skip); size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip); +size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, + size_t buflen, off_t skip); /* * Maximum number of entries that will be allocated in one piece, if diff --git a/include/linux/sched.h b/include/linux/sched.h index 2b69fc650201..92fb8dd5a9e4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -223,6 +223,24 @@ struct task_cputime { #define prof_exp stime #define sched_exp sum_exec_runtime +enum vtime_state { + /* Task is sleeping or running in a CPU with VTIME inactive: */ + VTIME_INACTIVE = 0, + /* Task runs in userspace in a CPU with VTIME active: */ + VTIME_USER, + /* Task runs in kernelspace in a CPU with VTIME active: */ + VTIME_SYS, +}; + +struct vtime { + seqcount_t seqcount; + unsigned long long starttime; + enum vtime_state state; + u64 utime; + u64 stime; + u64 gtime; +}; + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ @@ -408,7 +426,7 @@ struct sched_rt_entity { /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif -}; +} __randomize_layout; struct sched_dl_entity { struct rb_node rb_node; @@ -421,7 +439,8 @@ struct sched_dl_entity { u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ - u64 dl_bw; /* dl_runtime / dl_deadline */ + u64 dl_bw; /* dl_runtime / dl_period */ + u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, @@ -445,16 +464,33 @@ struct sched_dl_entity { * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. + * + * @dl_non_contending tells if the task is inactive while still + * contributing to the active utilization. In other words, it + * indicates if the inactive timer has been armed and its handler + * has not been executed yet. This flag is useful to avoid race + * conditions between the inactive timer handler and the wakeup + * code. */ int dl_throttled; int dl_boosted; int dl_yielded; + int dl_non_contending; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; + + /* + * Inactive timer, responsible for decreasing the active utilization + * at the "0-lag time". When a -deadline task blocks, it contributes + * to GRUB's active utilization until the "0-lag time", hence a + * timer is needed to decrease the active utilization at the correct + * time. + */ + struct hrtimer inactive_timer; }; union rcu_special { @@ -490,6 +526,13 @@ struct task_struct { #endif /* -1 unrunnable, 0 runnable, >0 stopped: */ volatile long state; + + /* + * This begins the randomizable portion of task_struct. Only + * scheduling-critical items should be added above here. + */ + randomized_struct_fields_start + void *stack; atomic_t usage; /* Per task flags (PF_*), defined further below: */ @@ -546,9 +589,10 @@ struct task_struct { #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; - bool rcu_tasks_holdout; - struct list_head rcu_tasks_holdout_list; + u8 rcu_tasks_holdout; + u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; + struct list_head rcu_tasks_holdout_list; #endif /* #ifdef CONFIG_TASKS_RCU */ struct sched_info sched_info; @@ -670,16 +714,7 @@ struct task_struct { u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqcount_t vtime_seqcount; - unsigned long long vtime_snap; - enum { - /* Task is sleeping or running in a CPU with VTIME inactive: */ - VTIME_INACTIVE = 0, - /* Task runs in userspace in a CPU with VTIME active: */ - VTIME_USER, - /* Task runs in kernelspace in a CPU with VTIME active: */ - VTIME_SYS, - } vtime_snap_whence; + struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL @@ -777,8 +812,7 @@ struct task_struct { #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ - struct rb_root pi_waiters; - struct rb_node *pi_waiters_leftmost; + struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ @@ -812,7 +846,17 @@ struct task_struct { int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; - gfp_t lockdep_reclaim_gfp; +#endif + +#ifdef CONFIG_LOCKDEP_CROSSRELEASE +#define MAX_XHLOCKS_NR 64UL + struct hist_lock *xhlocks; /* Crossrelease history locks */ + unsigned int xhlock_idx; + /* For restoring at history boundaries */ + unsigned int xhlock_idx_hist[XHLOCK_CTX_NR]; + unsigned int hist_id; + /* For overwrite check at each context exit */ + unsigned int hist_id_save[XHLOCK_CTX_NR]; #endif #ifdef CONFIG_UBSAN @@ -864,8 +908,9 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_INTEL_RDT_A - int closid; +#ifdef CONFIG_INTEL_RDT + u32 closid; + u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; @@ -886,7 +931,7 @@ struct task_struct { #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; - short il_next; + short il_prev; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING @@ -947,6 +992,7 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; + unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call @@ -1051,6 +1097,13 @@ struct task_struct { /* Used by LSM modules for access restriction: */ void *security; #endif + + /* + * New fields for task_struct should be added above here, so that + * they are included in the randomized portion of task_struct. + */ + randomized_struct_fields_end + /* CPU-specific state of this task: */ struct thread_struct thread; @@ -1096,8 +1149,6 @@ static inline struct pid *task_session(struct task_struct *task) * current. * task_xid_nr_ns() : id seen from the ns specified; * - * set_task_vxid() : assigns a virtual id to a task; - * * see also pid_nr() etc in include/linux/pid.h */ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); @@ -1123,13 +1174,6 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) return tsk->tgid; } -extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); - -static inline pid_t task_tgid_vnr(struct task_struct *tsk) -{ - return pid_vnr(task_tgid(tsk)); -} - /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. @@ -1145,23 +1189,6 @@ static inline int pid_alive(const struct task_struct *p) return p->pids[PIDTYPE_PID].pid != NULL; } -static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) -{ - pid_t pid = 0; - - rcu_read_lock(); - if (pid_alive(tsk)) - pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); - rcu_read_unlock(); - - return pid; -} - -static inline pid_t task_ppid_nr(const struct task_struct *tsk) -{ - return task_ppid_nr_ns(tsk, &init_pid_ns); -} - static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); @@ -1183,12 +1210,52 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } +static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns); +} + +static inline pid_t task_tgid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL); +} + +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { return task_pgrp_nr_ns(tsk, &init_pid_ns); } +static inline char task_state_to_char(struct task_struct *task) +{ + const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + unsigned long state = task->state; + + state = state ? __ffs(state) + 1 : 0; + + /* Make sure the string lines up properly with the number of task states: */ + BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + + return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'; +} + /** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. @@ -1265,6 +1332,16 @@ extern struct pid *cad_pid; #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) +static inline bool is_percpu_thread(void) +{ +#ifdef CONFIG_SMP + return (current->flags & PF_NO_SETAFFINITY) && + (current->nr_cpus_allowed == 1); +#else + return true; +#endif +} + /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h index 34fe92ce1ebd..a55600ffdf4b 100644 --- a/include/linux/sched/clock.h +++ b/include/linux/sched/clock.h @@ -23,10 +23,6 @@ extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static inline void sched_clock_init_late(void) -{ -} - static inline void sched_clock_tick(void) { } @@ -39,7 +35,7 @@ static inline void sched_clock_idle_sleep_event(void) { } -static inline void sched_clock_idle_wakeup_event(u64 delta_ns) +static inline void sched_clock_idle_wakeup_event(void) { } @@ -53,7 +49,6 @@ static inline u64 local_clock(void) return sched_clock(); } #else -extern void sched_clock_init_late(void); extern int sched_clock_stable(void); extern void clear_sched_clock_stable(void); @@ -63,10 +58,10 @@ extern void clear_sched_clock_stable(void); */ extern u64 __sched_clock_offset; - extern void sched_clock_tick(void); +extern void sched_clock_tick_stable(void); extern void sched_clock_idle_sleep_event(void); -extern void sched_clock_idle_wakeup_event(u64 delta_ns); +extern void sched_clock_idle_wakeup_event(void); /* * As outlined in clock.c, provides a fast, high resolution, nanosecond diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 69eedcef8f03..98ae0d05aa32 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -68,7 +68,10 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ + MMF_DISABLE_THP_MASK) #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index e0eaee54c5a4..5d58d49e9f87 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -6,6 +6,7 @@ */ struct task_struct; +struct pid_namespace; extern void dump_cpu_task(int cpu); @@ -34,7 +35,8 @@ extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_SCHED_DEBUG struct seq_file; -extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); +extern void proc_sched_show_task(struct task_struct *p, + struct pid_namespace *ns, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); #endif diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2b24a6974847..3a19c253bdb1 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,12 +84,6 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); -#ifdef CONFIG_MMU -/* same as above but performs the slow path from the async context. Can - * be called from the atomic context as well - */ -extern void mmput_async(struct mm_struct *); -#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); @@ -167,6 +161,14 @@ static inline gfp_t current_gfp_context(gfp_t flags) return flags; } +#ifdef CONFIG_LOCKDEP +extern void fs_reclaim_acquire(gfp_t gfp_mask); +extern void fs_reclaim_release(gfp_t gfp_mask); +#else +static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } +static inline void fs_reclaim_release(gfp_t gfp_mask) { } +#endif + static inline unsigned int memalloc_noio_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOIO; diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 4995b717500b..028d17b918a7 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -2,7 +2,7 @@ #define _LINUX_SCHED_NOHZ_H /* - * This is the interface between the scheduler and nohz/dyntics: + * This is the interface between the scheduler and nohz/dynticks: */ #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) @@ -23,11 +23,11 @@ static inline void set_cpu_sd_state_idle(void) { } #endif #ifdef CONFIG_NO_HZ_COMMON -void calc_load_enter_idle(void); -void calc_load_exit_idle(void); +void calc_load_nohz_start(void); +void calc_load_nohz_stop(void); #else -static inline void calc_load_enter_idle(void) { } -static inline void calc_load_exit_idle(void) { } +static inline void calc_load_nohz_start(void) { } +static inline void calc_load_nohz_stop(void) { } #endif /* CONFIG_NO_HZ_COMMON */ #if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index c06d63b3a583..2a0dd40b15db 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -222,7 +222,7 @@ struct signal_struct { struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) */ -}; +} __randomize_layout; /* * Bits in flags field of signal_struct. diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index a978d7189cfd..79a2a744648d 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -9,6 +9,7 @@ #include <linux/sched.h> struct task_struct; +struct rusage; union thread_union; /* @@ -29,7 +30,6 @@ extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); -extern void init_idle_bootup_task(struct task_struct *idle); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_dead(struct task_struct *p); @@ -74,6 +74,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern long kernel_wait4(pid_t, int *, int, struct rusage *); extern void free_task(struct task_struct *tsk); @@ -95,8 +96,6 @@ static inline void put_task_struct(struct task_struct *t) } struct task_struct *task_rcu_dereference(struct task_struct **ptask); -struct task_struct *try_get_task_struct(struct task_struct **ptask); - #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7d065abc7a47..d7b6dab956ec 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -71,6 +71,14 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; + + /* + * Some variables from the most recent sd_lb_stats for this domain, + * used by wake_affine(). + */ + unsigned long nr_running; + unsigned long load; + unsigned long capacity; }; struct sched_domain { diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 5d5415e129d4..3c07e4135127 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,7 +36,8 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ + defined(CONFIG_NET) atomic_long_t locked_vm; #endif }; diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index dc5f989be226..327d65663dbf 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -67,6 +67,9 @@ struct scpi_ops { int (*dvfs_get_idx)(u8); int (*dvfs_set_idx)(u8, u8); struct scpi_dvfs_info *(*dvfs_get_info)(u8); + int (*device_domain_id)(struct device *); + int (*get_transition_latency)(struct device *); + int (*add_opps_to_device)(struct device *); int (*sensor_get_capability)(u16 *sensors); int (*sensor_get_info)(u16 sensor_id, struct scpi_sensor_info *); int (*sensor_get_value)(u16, u64 *); diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 7a4804c4a593..82b171e1aa0b 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -57,12 +57,12 @@ #include <uapi/linux/sctp.h> /* Section 3.1. SCTP Common Header Format */ -typedef struct sctphdr { +struct sctphdr { __be16 source; __be16 dest; __be32 vtag; __le32 checksum; -} sctp_sctphdr_t; +}; static inline struct sctphdr *sctp_hdr(const struct sk_buff *skb) { @@ -70,11 +70,11 @@ static inline struct sctphdr *sctp_hdr(const struct sk_buff *skb) } /* Section 3.2. Chunk Field Descriptions. */ -typedef struct sctp_chunkhdr { +struct sctp_chunkhdr { __u8 type; __u8 flags; __be16 length; -} sctp_chunkhdr_t; +}; /* Section 3.2. Chunk Type Values. @@ -82,7 +82,7 @@ typedef struct sctp_chunkhdr { * Value field. It takes a value from 0 to 254. The value of 255 is * reserved for future use as an extension field. */ -typedef enum { +enum sctp_cid { SCTP_CID_DATA = 0, SCTP_CID_INIT = 1, SCTP_CID_INIT_ACK = 2, @@ -109,7 +109,7 @@ typedef enum { SCTP_CID_ASCONF = 0xC1, SCTP_CID_ASCONF_ACK = 0x80, SCTP_CID_RECONF = 0x82, -} sctp_cid_t; /* enum */ +}; /* enum */ /* Section 3.2 @@ -117,12 +117,12 @@ typedef enum { * the action that must be taken if the processing endpoint does not * recognize the Chunk Type. */ -typedef enum { +enum { SCTP_CID_ACTION_DISCARD = 0x00, SCTP_CID_ACTION_DISCARD_ERR = 0x40, SCTP_CID_ACTION_SKIP = 0x80, SCTP_CID_ACTION_SKIP_ERR = 0xc0, -} sctp_cid_action_t; +}; enum { SCTP_CID_ACTION_MASK = 0xc0, }; @@ -162,12 +162,12 @@ enum { SCTP_CHUNK_FLAG_T = 0x01 }; * Section 3.2.1 Optional/Variable-length Parmaeter Format. */ -typedef struct sctp_paramhdr { +struct sctp_paramhdr { __be16 type; __be16 length; -} sctp_paramhdr_t; +}; -typedef enum { +enum sctp_param { /* RFC 2960 Section 3.3.5 */ SCTP_PARAM_HEARTBEAT_INFO = cpu_to_be16(1), @@ -207,7 +207,7 @@ typedef enum { SCTP_PARAM_RESET_RESPONSE = cpu_to_be16(0x0010), SCTP_PARAM_RESET_ADD_OUT_STREAMS = cpu_to_be16(0x0011), SCTP_PARAM_RESET_ADD_IN_STREAMS = cpu_to_be16(0x0012), -} sctp_param_t; /* enum */ +}; /* enum */ /* RFC 2960 Section 3.2.1 @@ -216,29 +216,29 @@ typedef enum { * not recognize the Parameter Type. * */ -typedef enum { +enum { SCTP_PARAM_ACTION_DISCARD = cpu_to_be16(0x0000), SCTP_PARAM_ACTION_DISCARD_ERR = cpu_to_be16(0x4000), SCTP_PARAM_ACTION_SKIP = cpu_to_be16(0x8000), SCTP_PARAM_ACTION_SKIP_ERR = cpu_to_be16(0xc000), -} sctp_param_action_t; +}; enum { SCTP_PARAM_ACTION_MASK = cpu_to_be16(0xc000), }; /* RFC 2960 Section 3.3.1 Payload Data (DATA) (0) */ -typedef struct sctp_datahdr { +struct sctp_datahdr { __be32 tsn; __be16 stream; __be16 ssn; __be32 ppid; __u8 payload[0]; -} sctp_datahdr_t; +}; -typedef struct sctp_data_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_datahdr_t data_hdr; -} sctp_data_chunk_t; +struct sctp_data_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_datahdr data_hdr; +}; /* DATA Chuck Specific Flags */ enum { @@ -257,103 +257,101 @@ enum { SCTP_DATA_FRAG_MASK = 0x03, }; * This chunk is used to initiate a SCTP association between two * endpoints. */ -typedef struct sctp_inithdr { +struct sctp_inithdr { __be32 init_tag; __be32 a_rwnd; __be16 num_outbound_streams; __be16 num_inbound_streams; __be32 initial_tsn; __u8 params[0]; -} sctp_inithdr_t; +}; -typedef struct sctp_init_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_inithdr_t init_hdr; -} sctp_init_chunk_t; +struct sctp_init_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_inithdr init_hdr; +}; /* Section 3.3.2.1. IPv4 Address Parameter (5) */ -typedef struct sctp_ipv4addr_param { - sctp_paramhdr_t param_hdr; - struct in_addr addr; -} sctp_ipv4addr_param_t; +struct sctp_ipv4addr_param { + struct sctp_paramhdr param_hdr; + struct in_addr addr; +}; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ -typedef struct sctp_ipv6addr_param { - sctp_paramhdr_t param_hdr; +struct sctp_ipv6addr_param { + struct sctp_paramhdr param_hdr; struct in6_addr addr; -} sctp_ipv6addr_param_t; +}; /* Section 3.3.2.1 Cookie Preservative (9) */ -typedef struct sctp_cookie_preserve_param { - sctp_paramhdr_t param_hdr; - __be32 lifespan_increment; -} sctp_cookie_preserve_param_t; +struct sctp_cookie_preserve_param { + struct sctp_paramhdr param_hdr; + __be32 lifespan_increment; +}; /* Section 3.3.2.1 Host Name Address (11) */ -typedef struct sctp_hostname_param { - sctp_paramhdr_t param_hdr; +struct sctp_hostname_param { + struct sctp_paramhdr param_hdr; uint8_t hostname[0]; -} sctp_hostname_param_t; +}; /* Section 3.3.2.1 Supported Address Types (12) */ -typedef struct sctp_supported_addrs_param { - sctp_paramhdr_t param_hdr; +struct sctp_supported_addrs_param { + struct sctp_paramhdr param_hdr; __be16 types[0]; -} sctp_supported_addrs_param_t; - -/* Appendix A. ECN Capable (32768) */ -typedef struct sctp_ecn_capable_param { - sctp_paramhdr_t param_hdr; -} sctp_ecn_capable_param_t; +}; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ -typedef struct sctp_adaptation_ind_param { +struct sctp_adaptation_ind_param { struct sctp_paramhdr param_hdr; __be32 adaptation_ind; -} sctp_adaptation_ind_param_t; +}; /* ADDIP Section 4.2.7 Supported Extensions Parameter */ -typedef struct sctp_supported_ext_param { +struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_supported_ext_param_t; +}; /* AUTH Section 3.1 Random */ -typedef struct sctp_random_param { - sctp_paramhdr_t param_hdr; +struct sctp_random_param { + struct sctp_paramhdr param_hdr; __u8 random_val[0]; -} sctp_random_param_t; +}; /* AUTH Section 3.2 Chunk List */ -typedef struct sctp_chunks_param { - sctp_paramhdr_t param_hdr; +struct sctp_chunks_param { + struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_chunks_param_t; +}; /* AUTH Section 3.3 HMAC Algorithm */ -typedef struct sctp_hmac_algo_param { - sctp_paramhdr_t param_hdr; +struct sctp_hmac_algo_param { + struct sctp_paramhdr param_hdr; __be16 hmac_ids[0]; -} sctp_hmac_algo_param_t; +}; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): * The INIT ACK chunk is used to acknowledge the initiation of an SCTP * association. */ -typedef sctp_init_chunk_t sctp_initack_chunk_t; +struct sctp_initack_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_inithdr init_hdr; +}; /* Section 3.3.3.1 State Cookie (7) */ -typedef struct sctp_cookie_param { - sctp_paramhdr_t p; +struct sctp_cookie_param { + struct sctp_paramhdr p; __u8 body[0]; -} sctp_cookie_param_t; +}; /* Section 3.3.3.1 Unrecognized Parameters (8) */ -typedef struct sctp_unrecognized_param { - sctp_paramhdr_t param_hdr; - sctp_paramhdr_t unrecognized; -} sctp_unrecognized_param_t; +struct sctp_unrecognized_param { + struct sctp_paramhdr param_hdr; + struct sctp_paramhdr unrecognized; +}; @@ -365,30 +363,28 @@ typedef struct sctp_unrecognized_param { * subsequences of DATA chunks as represented by their TSNs. */ -typedef struct sctp_gap_ack_block { +struct sctp_gap_ack_block { __be16 start; __be16 end; -} sctp_gap_ack_block_t; - -typedef __be32 sctp_dup_tsn_t; +}; -typedef union { - sctp_gap_ack_block_t gab; - sctp_dup_tsn_t dup; -} sctp_sack_variable_t; +union sctp_sack_variable { + struct sctp_gap_ack_block gab; + __be32 dup; +}; -typedef struct sctp_sackhdr { +struct sctp_sackhdr { __be32 cum_tsn_ack; __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - sctp_sack_variable_t variable[0]; -} sctp_sackhdr_t; + union sctp_sack_variable variable[0]; +}; -typedef struct sctp_sack_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_sackhdr_t sack_hdr; -} sctp_sack_chunk_t; +struct sctp_sack_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_sackhdr sack_hdr; +}; /* RFC 2960. Section 3.3.5 Heartbeat Request (HEARTBEAT) (4): @@ -398,49 +394,49 @@ typedef struct sctp_sack_chunk { * the present association. */ -typedef struct sctp_heartbeathdr { - sctp_paramhdr_t info; -} sctp_heartbeathdr_t; +struct sctp_heartbeathdr { + struct sctp_paramhdr info; +}; -typedef struct sctp_heartbeat_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_heartbeathdr_t hb_hdr; -} sctp_heartbeat_chunk_t; +struct sctp_heartbeat_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_heartbeathdr hb_hdr; +}; /* For the abort and shutdown ACK we must carry the init tag in the * common header. Just the common header is all that is needed with a * chunk descriptor. */ -typedef struct sctp_abort_chunk { - sctp_chunkhdr_t uh; -} sctp_abort_chunk_t; +struct sctp_abort_chunk { + struct sctp_chunkhdr uh; +}; /* For the graceful shutdown we must carry the tag (in common header) * and the highest consecutive acking value. */ -typedef struct sctp_shutdownhdr { +struct sctp_shutdownhdr { __be32 cum_tsn_ack; -} sctp_shutdownhdr_t; +}; -struct sctp_shutdown_chunk_t { - sctp_chunkhdr_t chunk_hdr; - sctp_shutdownhdr_t shutdown_hdr; +struct sctp_shutdown_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_shutdownhdr shutdown_hdr; }; /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ -typedef struct sctp_errhdr { +struct sctp_errhdr { __be16 cause; __be16 length; __u8 variable[0]; -} sctp_errhdr_t; +}; -typedef struct sctp_operr_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_errhdr_t err_hdr; -} sctp_operr_chunk_t; +struct sctp_operr_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_errhdr err_hdr; +}; /* RFC 2960 3.3.10 - Operation Error * @@ -461,7 +457,7 @@ typedef struct sctp_operr_chunk { * 9 No User Data * 10 Cookie Received While Shutting Down */ -typedef enum { +enum sctp_error { SCTP_ERROR_NO_ERROR = cpu_to_be16(0x00), SCTP_ERROR_INV_STRM = cpu_to_be16(0x01), @@ -516,33 +512,28 @@ typedef enum { * 0x0105 Unsupported HMAC Identifier */ SCTP_ERROR_UNSUP_HMAC = cpu_to_be16(0x0105) -} sctp_error_t; +}; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Explicit Congestion Notification Echo (ECNE) (12) */ -typedef struct sctp_ecnehdr { +struct sctp_ecnehdr { __be32 lowest_tsn; -} sctp_ecnehdr_t; +}; -typedef struct sctp_ecne_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_ecnehdr_t ence_hdr; -} sctp_ecne_chunk_t; +struct sctp_ecne_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_ecnehdr ence_hdr; +}; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Congestion Window Reduced (CWR) (13) */ -typedef struct sctp_cwrhdr { +struct sctp_cwrhdr { __be32 lowest_tsn; -} sctp_cwrhdr_t; - -typedef struct sctp_cwr_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_cwrhdr_t cwr_hdr; -} sctp_cwr_chunk_t; +}; /* PR-SCTP * 3.2 Forward Cumulative TSN Chunk Definition (FORWARD TSN) @@ -638,20 +629,20 @@ struct sctp_fwdtsn_chunk { * The ASCONF Parameter Response is used in the ASCONF-ACK to * report status of ASCONF processing. */ -typedef struct sctp_addip_param { - sctp_paramhdr_t param_hdr; - __be32 crr_id; -} sctp_addip_param_t; +struct sctp_addip_param { + struct sctp_paramhdr param_hdr; + __be32 crr_id; +}; -typedef struct sctp_addiphdr { +struct sctp_addiphdr { __be32 serial; __u8 params[0]; -} sctp_addiphdr_t; +}; -typedef struct sctp_addip_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_addiphdr_t addip_hdr; -} sctp_addip_chunk_t; +struct sctp_addip_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_addiphdr addip_hdr; +}; /* AUTH * Section 4.1 Authentication Chunk (AUTH) @@ -702,16 +693,16 @@ typedef struct sctp_addip_chunk { * HMAC: n bytes (unsigned integer) This hold the result of the HMAC * calculation. */ -typedef struct sctp_authhdr { +struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; __u8 hmac[0]; -} sctp_authhdr_t; +}; -typedef struct sctp_auth_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_authhdr_t auth_hdr; -} sctp_auth_chunk_t; +struct sctp_auth_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_authhdr auth_hdr; +}; struct sctp_infox { struct sctp_info *sctpinfo; @@ -719,12 +710,12 @@ struct sctp_infox { }; struct sctp_reconf_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; __u8 params[0]; }; struct sctp_strreset_outreq { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; __u32 response_seq; __u32 send_reset_at_tsn; @@ -732,18 +723,18 @@ struct sctp_strreset_outreq { }; struct sctp_strreset_inreq { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; __u16 list_of_streams[0]; }; struct sctp_strreset_tsnreq { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; }; struct sctp_strreset_addstrm { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; __u16 number_of_streams; __u16 reserved; @@ -760,13 +751,13 @@ enum { }; struct sctp_strreset_resp { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 response_seq; __u32 result; }; struct sctp_strreset_resptsn { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 response_seq; __u32 result; __u32 senders_next_tsn; diff --git a/include/linux/security.h b/include/linux/security.h index af675b576645..ce6265960d6c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -6,6 +6,7 @@ * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) + * Copyright (C) 2016 Mellanox Techonologies * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -68,6 +69,10 @@ struct audit_krule; struct user_namespace; struct timezone; +enum lsm_event { + LSM_POLICY_CHANGE, +}; + /* These functions are in security/commoncap.c */ extern int cap_capable(const struct cred *cred, struct user_namespace *ns, int cap, int audit); @@ -80,12 +85,13 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); extern int cap_bprm_set_creds(struct linux_binprm *bprm); -extern int cap_bprm_secureexec(struct linux_binprm *bprm); extern int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_inode_getsecurity(struct inode *inode, const char *name, + void **buffer, bool alloc); extern int cap_mmap_addr(unsigned long addr); extern int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags); @@ -163,6 +169,10 @@ struct security_mnt_opts { int num_mnt_opts; }; +int call_lsm_notifier(enum lsm_event event, void *data); +int register_lsm_notifier(struct notifier_block *nb); +int unregister_lsm_notifier(struct notifier_block *nb); + static inline void security_init_mnt_opts(struct security_mnt_opts *opts) { opts->mnt_opts = NULL; @@ -223,7 +233,6 @@ int security_bprm_set_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); -int security_bprm_secureexec(struct linux_binprm *bprm); int security_sb_alloc(struct super_block *sb); void security_sb_free(struct super_block *sb); int security_sb_copy_data(char *orig, char *copy); @@ -240,7 +249,9 @@ int security_sb_set_mnt_opts(struct super_block *sb, unsigned long kern_flags, unsigned long *set_kern_flags); int security_sb_clone_mnt_opts(const struct super_block *oldsb, - struct super_block *newsb); + struct super_block *newsb, + unsigned long kern_flags, + unsigned long *set_kern_flags); int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts); int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, @@ -307,7 +318,6 @@ int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig); int security_file_receive(struct file *file); int security_file_open(struct file *file, const struct cred *cred); -int security_task_create(unsigned long clone_flags); int security_task_alloc(struct task_struct *task, unsigned long clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); @@ -381,6 +391,21 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); struct security_mnt_opts { }; +static inline int call_lsm_notifier(enum lsm_event event, void *data) +{ + return 0; +} + +static inline int register_lsm_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int unregister_lsm_notifier(struct notifier_block *nb) +{ + return 0; +} + static inline void security_init_mnt_opts(struct security_mnt_opts *opts) { } @@ -515,11 +540,6 @@ static inline void security_bprm_committed_creds(struct linux_binprm *bprm) { } -static inline int security_bprm_secureexec(struct linux_binprm *bprm) -{ - return cap_bprm_secureexec(bprm); -} - static inline int security_sb_alloc(struct super_block *sb) { return 0; @@ -581,7 +601,9 @@ static inline int security_sb_set_mnt_opts(struct super_block *sb, } static inline int security_sb_clone_mnt_opts(const struct super_block *oldsb, - struct super_block *newsb) + struct super_block *newsb, + unsigned long kern_flags, + unsigned long *set_kern_flags) { return 0; } @@ -857,11 +879,6 @@ static inline int security_file_open(struct file *file, return 0; } -static inline int security_task_create(unsigned long clone_flags) -{ - return 0; -} - static inline int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { @@ -1406,6 +1423,32 @@ static inline int security_tun_dev_open(void *security) } #endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_INFINIBAND +int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey); +int security_ib_endport_manage_subnet(void *sec, const char *name, u8 port_num); +int security_ib_alloc_security(void **sec); +void security_ib_free_security(void *sec); +#else /* CONFIG_SECURITY_INFINIBAND */ +static inline int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) +{ + return 0; +} + +static inline int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) +{ + return 0; +} + +static inline int security_ib_alloc_security(void **sec) +{ + return 0; +} + +static inline void security_ib_free_security(void *sec) +{ +} +#endif /* CONFIG_SECURITY_INFINIBAND */ + #ifdef CONFIG_SECURITY_NETWORK_XFRM int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, @@ -1651,6 +1694,10 @@ extern struct dentry *securityfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); extern struct dentry *securityfs_create_dir(const char *name, struct dentry *parent); +struct dentry *securityfs_create_symlink(const char *name, + struct dentry *parent, + const char *target, + const struct inode_operations *iops); extern void securityfs_remove(struct dentry *dentry); #else /* CONFIG_SECURITYFS */ @@ -1670,6 +1717,14 @@ static inline struct dentry *securityfs_create_file(const char *name, return ERR_PTR(-ENODEV); } +static inline struct dentry *securityfs_create_symlink(const char *name, + struct dentry *parent, + const char *target, + const struct inode_operations *iops) +{ + return ERR_PTR(-ENODEV); +} + static inline void securityfs_remove(struct dentry *dentry) {} diff --git a/include/linux/seg6_local.h b/include/linux/seg6_local.h new file mode 100644 index 000000000000..ee63e76fe0c7 --- /dev/null +++ b/include/linux/seg6_local.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_LOCAL_H +#define _LINUX_SEG6_LOCAL_H + +#include <uapi/linux/seg6_local.h> + +#endif diff --git a/include/linux/sem.h b/include/linux/sem.h index 9edec926e9d9..0083128318f6 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -4,15 +4,34 @@ #include <linux/atomic.h> #include <linux/rcupdate.h> #include <linux/cache.h> +#include <linux/time64.h> #include <uapi/linux/sem.h> struct task_struct; +/* One semaphore structure for each semaphore in the system. */ +struct sem { + int semval; /* current value */ + /* + * PID of the process that last modified the semaphore. For + * Linux, specifically these are: + * - semop + * - semctl, via SETVAL and SETALL. + * - at task exit when performing undo adjustments (see exit_sem). + */ + int sempid; + spinlock_t lock; /* spinlock for fine-grained semtimedop */ + struct list_head pending_alter; /* pending single-sop operations */ + /* that alter the semaphore */ + struct list_head pending_const; /* pending single-sop operations */ + /* that do not alter the semaphore*/ + time_t sem_otime; /* candidate for sem_otime */ +} ____cacheline_aligned_in_smp; + /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ - time_t sem_ctime; /* last change time */ - struct sem *sem_base; /* ptr to first semaphore in array */ + time64_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ @@ -21,7 +40,9 @@ struct sem_array { int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ -}; + + struct sem sems[]; +} __randomize_layout; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 61fbb440449c..a27ef5f56431 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -80,9 +80,10 @@ struct uart_8250_ops { }; struct uart_8250_em485 { - struct timer_list start_tx_timer; /* "rs485 start tx" timer */ - struct timer_list stop_tx_timer; /* "rs485 stop tx" timer */ - struct timer_list *active_timer; /* pointer to active timer */ + struct hrtimer start_tx_timer; /* "rs485 start tx" timer */ + struct hrtimer stop_tx_timer; /* "rs485 stop tx" timer */ + struct hrtimer *active_timer; /* pointer to active timer */ + struct uart_8250_port *port; /* for hrtimer callbacks */ }; /* diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 64d892f1e5cd..5553e04e59c9 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -20,7 +20,7 @@ #ifndef LINUX_SERIAL_CORE_H #define LINUX_SERIAL_CORE_H - +#include <linux/bitops.h> #include <linux/compiler.h> #include <linux/interrupt.h> #include <linux/circ_buf.h> @@ -144,7 +144,7 @@ struct uart_port { unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ unsigned char iotype; /* io access style */ - unsigned char unused1; + unsigned char quirks; /* internal quirks */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ @@ -155,6 +155,9 @@ struct uart_port { #define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ #define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ + /* quirks must be updated while holding port mutex */ +#define UPQ_NO_TXEN_TEST BIT(0) + unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ struct uart_state *state; /* pointer to parent state */ @@ -175,7 +178,6 @@ struct uart_port { * [for bit definitions in the UPF_CHANGE_MASK] * * Bits [0..UPF_LAST_USER] are userspace defined/visible/changeable - * except bit 15 (UPF_NO_TXEN_TEST) which is masked off. * The remaining bits are serial-core specific and not modifiable by * userspace. */ @@ -192,9 +194,9 @@ struct uart_port { #define UPF_SPD_SHI ((__force upf_t) ASYNC_SPD_SHI /* 12 */ ) #define UPF_LOW_LATENCY ((__force upf_t) ASYNC_LOW_LATENCY /* 13 */ ) #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) -#define UPF_NO_TXEN_TEST ((__force upf_t) (1 << 15)) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) +#define UPF_NO_THRE_TEST ((__force upf_t) (1 << 19)) /* Port has hardware-assisted h/w flow control */ #define UPF_AUTO_CTS ((__force upf_t) (1 << 20)) #define UPF_AUTO_RTS ((__force upf_t) (1 << 21)) @@ -245,7 +247,6 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char irq_wake; unsigned char unused[2]; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h new file mode 100644 index 000000000000..e5140648f638 --- /dev/null +++ b/include/linux/set_memory.h @@ -0,0 +1,20 @@ +/* + * Copyright 2017, Michael Ellerman, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation; + */ +#ifndef _LINUX_SET_MEMORY_H_ +#define _LINUX_SET_MEMORY_H_ + +#ifdef CONFIG_ARCH_HAS_SET_MEMORY +#include <asm/set_memory.h> +#else +static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } +#endif + +#endif /* _LINUX_SET_MEMORY_H_ */ diff --git a/include/linux/sfp.h b/include/linux/sfp.h new file mode 100644 index 000000000000..4a906f560817 --- /dev/null +++ b/include/linux/sfp.h @@ -0,0 +1,434 @@ +#ifndef LINUX_SFP_H +#define LINUX_SFP_H + +#include <linux/phy.h> + +struct __packed sfp_eeprom_base { + u8 phys_id; + u8 phys_ext_id; + u8 connector; +#if defined __BIG_ENDIAN_BITFIELD + u8 e10g_base_er:1; + u8 e10g_base_lrm:1; + u8 e10g_base_lr:1; + u8 e10g_base_sr:1; + u8 if_1x_sx:1; + u8 if_1x_lx:1; + u8 if_1x_copper_active:1; + u8 if_1x_copper_passive:1; + + u8 escon_mmf_1310_led:1; + u8 escon_smf_1310_laser:1; + u8 sonet_oc192_short_reach:1; + u8 sonet_reach_bit1:1; + u8 sonet_reach_bit2:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_short_reach:1; + + u8 unallocated_5_7:1; + u8 sonet_oc12_smf_long_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_short_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc3_smf_long_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_short_reach:1; + + u8 e_base_px:1; + u8 e_base_bx10:1; + u8 e100_base_fx:1; + u8 e100_base_lx:1; + u8 e1000_base_t:1; + u8 e1000_base_cx:1; + u8 e1000_base_lx:1; + u8 e1000_base_sx:1; + + u8 fc_ll_v:1; + u8 fc_ll_s:1; + u8 fc_ll_i:1; + u8 fc_ll_l:1; + u8 fc_ll_m:1; + u8 fc_tech_sa:1; + u8 fc_tech_lc:1; + u8 fc_tech_electrical_inter_enclosure:1; + + u8 fc_tech_electrical_intra_enclosure:1; + u8 fc_tech_sn:1; + u8 fc_tech_sl:1; + u8 fc_tech_ll:1; + u8 sfp_ct_active:1; + u8 sfp_ct_passive:1; + u8 unallocated_8_1:1; + u8 unallocated_8_0:1; + + u8 fc_media_tw:1; + u8 fc_media_tp:1; + u8 fc_media_mi:1; + u8 fc_media_tv:1; + u8 fc_media_m6:1; + u8 fc_media_m5:1; + u8 unallocated_9_1:1; + u8 fc_media_sm:1; + + u8 fc_speed_1200:1; + u8 fc_speed_800:1; + u8 fc_speed_1600:1; + u8 fc_speed_400:1; + u8 fc_speed_3200:1; + u8 fc_speed_200:1; + u8 unallocated_10_1:1; + u8 fc_speed_100:1; +#elif defined __LITTLE_ENDIAN_BITFIELD + u8 if_1x_copper_passive:1; + u8 if_1x_copper_active:1; + u8 if_1x_lx:1; + u8 if_1x_sx:1; + u8 e10g_base_sr:1; + u8 e10g_base_lr:1; + u8 e10g_base_lrm:1; + u8 e10g_base_er:1; + + u8 sonet_oc3_short_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_smf_long_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc12_short_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_smf_long_reach:1; + u8 unallocated_5_7:1; + + u8 sonet_oc48_short_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_reach_bit2:1; + u8 sonet_reach_bit1:1; + u8 sonet_oc192_short_reach:1; + u8 escon_smf_1310_laser:1; + u8 escon_mmf_1310_led:1; + + u8 e1000_base_sx:1; + u8 e1000_base_lx:1; + u8 e1000_base_cx:1; + u8 e1000_base_t:1; + u8 e100_base_lx:1; + u8 e100_base_fx:1; + u8 e_base_bx10:1; + u8 e_base_px:1; + + u8 fc_tech_electrical_inter_enclosure:1; + u8 fc_tech_lc:1; + u8 fc_tech_sa:1; + u8 fc_ll_m:1; + u8 fc_ll_l:1; + u8 fc_ll_i:1; + u8 fc_ll_s:1; + u8 fc_ll_v:1; + + u8 unallocated_8_0:1; + u8 unallocated_8_1:1; + u8 sfp_ct_passive:1; + u8 sfp_ct_active:1; + u8 fc_tech_ll:1; + u8 fc_tech_sl:1; + u8 fc_tech_sn:1; + u8 fc_tech_electrical_intra_enclosure:1; + + u8 fc_media_sm:1; + u8 unallocated_9_1:1; + u8 fc_media_m5:1; + u8 fc_media_m6:1; + u8 fc_media_tv:1; + u8 fc_media_mi:1; + u8 fc_media_tp:1; + u8 fc_media_tw:1; + + u8 fc_speed_100:1; + u8 unallocated_10_1:1; + u8 fc_speed_200:1; + u8 fc_speed_3200:1; + u8 fc_speed_400:1; + u8 fc_speed_1600:1; + u8 fc_speed_800:1; + u8 fc_speed_1200:1; +#else +#error Unknown Endian +#endif + u8 encoding; + u8 br_nominal; + u8 rate_id; + u8 link_len[6]; + char vendor_name[16]; + u8 extended_cc; + char vendor_oui[3]; + char vendor_pn[16]; + char vendor_rev[4]; + union { + __be16 optical_wavelength; + u8 cable_spec; + }; + u8 reserved62; + u8 cc_base; +}; + +struct __packed sfp_eeprom_ext { + __be16 options; + u8 br_max; + u8 br_min; + char vendor_sn[16]; + char datecode[8]; + u8 diagmon; + u8 enhopts; + u8 sff8472_compliance; + u8 cc_ext; +}; + +struct __packed sfp_eeprom_id { + struct sfp_eeprom_base base; + struct sfp_eeprom_ext ext; +}; + +/* SFP EEPROM registers */ +enum { + SFP_PHYS_ID = 0x00, + SFP_PHYS_EXT_ID = 0x01, + SFP_CONNECTOR = 0x02, + SFP_COMPLIANCE = 0x03, + SFP_ENCODING = 0x0b, + SFP_BR_NOMINAL = 0x0c, + SFP_RATE_ID = 0x0d, + SFP_LINK_LEN_SM_KM = 0x0e, + SFP_LINK_LEN_SM_100M = 0x0f, + SFP_LINK_LEN_50UM_OM2_10M = 0x10, + SFP_LINK_LEN_62_5UM_OM1_10M = 0x11, + SFP_LINK_LEN_COPPER_1M = 0x12, + SFP_LINK_LEN_50UM_OM4_10M = 0x12, + SFP_LINK_LEN_50UM_OM3_10M = 0x13, + SFP_VENDOR_NAME = 0x14, + SFP_VENDOR_OUI = 0x25, + SFP_VENDOR_PN = 0x28, + SFP_VENDOR_REV = 0x38, + SFP_OPTICAL_WAVELENGTH_MSB = 0x3c, + SFP_OPTICAL_WAVELENGTH_LSB = 0x3d, + SFP_CABLE_SPEC = 0x3c, + SFP_CC_BASE = 0x3f, + SFP_OPTIONS = 0x40, /* 2 bytes, MSB, LSB */ + SFP_BR_MAX = 0x42, + SFP_BR_MIN = 0x43, + SFP_VENDOR_SN = 0x44, + SFP_DATECODE = 0x54, + SFP_DIAGMON = 0x5c, + SFP_ENHOPTS = 0x5d, + SFP_SFF8472_COMPLIANCE = 0x5e, + SFP_CC_EXT = 0x5f, + + SFP_PHYS_ID_SFP = 0x03, + SFP_PHYS_EXT_ID_SFP = 0x04, + SFP_CONNECTOR_UNSPEC = 0x00, + /* codes 01-05 not supportable on SFP, but some modules have single SC */ + SFP_CONNECTOR_SC = 0x01, + SFP_CONNECTOR_FIBERJACK = 0x06, + SFP_CONNECTOR_LC = 0x07, + SFP_CONNECTOR_MT_RJ = 0x08, + SFP_CONNECTOR_MU = 0x09, + SFP_CONNECTOR_SG = 0x0a, + SFP_CONNECTOR_OPTICAL_PIGTAIL = 0x0b, + SFP_CONNECTOR_MPO_1X12 = 0x0c, + SFP_CONNECTOR_MPO_2X16 = 0x0d, + SFP_CONNECTOR_HSSDC_II = 0x20, + SFP_CONNECTOR_COPPER_PIGTAIL = 0x21, + SFP_CONNECTOR_RJ45 = 0x22, + SFP_CONNECTOR_NOSEPARATE = 0x23, + SFP_CONNECTOR_MXC_2X16 = 0x24, + SFP_ENCODING_UNSPEC = 0x00, + SFP_ENCODING_8B10B = 0x01, + SFP_ENCODING_4B5B = 0x02, + SFP_ENCODING_NRZ = 0x03, + SFP_ENCODING_8472_MANCHESTER = 0x04, + SFP_ENCODING_8472_SONET = 0x05, + SFP_ENCODING_8472_64B66B = 0x06, + SFP_ENCODING_256B257B = 0x07, + SFP_ENCODING_PAM4 = 0x08, + SFP_OPTIONS_HIGH_POWER_LEVEL = BIT(13), + SFP_OPTIONS_PAGING_A2 = BIT(12), + SFP_OPTIONS_RETIMER = BIT(11), + SFP_OPTIONS_COOLED_XCVR = BIT(10), + SFP_OPTIONS_POWER_DECL = BIT(9), + SFP_OPTIONS_RX_LINEAR_OUT = BIT(8), + SFP_OPTIONS_RX_DECISION_THRESH = BIT(7), + SFP_OPTIONS_TUNABLE_TX = BIT(6), + SFP_OPTIONS_RATE_SELECT = BIT(5), + SFP_OPTIONS_TX_DISABLE = BIT(4), + SFP_OPTIONS_TX_FAULT = BIT(3), + SFP_OPTIONS_LOS_INVERTED = BIT(2), + SFP_OPTIONS_LOS_NORMAL = BIT(1), + SFP_DIAGMON_DDM = BIT(6), + SFP_DIAGMON_INT_CAL = BIT(5), + SFP_DIAGMON_EXT_CAL = BIT(4), + SFP_DIAGMON_RXPWR_AVG = BIT(3), + SFP_DIAGMON_ADDRMODE = BIT(2), + SFP_ENHOPTS_ALARMWARN = BIT(7), + SFP_ENHOPTS_SOFT_TX_DISABLE = BIT(6), + SFP_ENHOPTS_SOFT_TX_FAULT = BIT(5), + SFP_ENHOPTS_SOFT_RX_LOS = BIT(4), + SFP_ENHOPTS_SOFT_RATE_SELECT = BIT(3), + SFP_ENHOPTS_APP_SELECT_SFF8079 = BIT(2), + SFP_ENHOPTS_SOFT_RATE_SFF8431 = BIT(1), + SFP_SFF8472_COMPLIANCE_NONE = 0x00, + SFP_SFF8472_COMPLIANCE_REV9_3 = 0x01, + SFP_SFF8472_COMPLIANCE_REV9_5 = 0x02, + SFP_SFF8472_COMPLIANCE_REV10_2 = 0x03, + SFP_SFF8472_COMPLIANCE_REV10_4 = 0x04, + SFP_SFF8472_COMPLIANCE_REV11_0 = 0x05, + SFP_SFF8472_COMPLIANCE_REV11_3 = 0x06, + SFP_SFF8472_COMPLIANCE_REV11_4 = 0x07, + SFP_SFF8472_COMPLIANCE_REV12_0 = 0x08, +}; + +/* SFP Diagnostics */ +enum { + /* Alarm and warnings stored MSB at lower address then LSB */ + SFP_TEMP_HIGH_ALARM = 0x00, + SFP_TEMP_LOW_ALARM = 0x02, + SFP_TEMP_HIGH_WARN = 0x04, + SFP_TEMP_LOW_WARN = 0x06, + SFP_VOLT_HIGH_ALARM = 0x08, + SFP_VOLT_LOW_ALARM = 0x0a, + SFP_VOLT_HIGH_WARN = 0x0c, + SFP_VOLT_LOW_WARN = 0x0e, + SFP_BIAS_HIGH_ALARM = 0x10, + SFP_BIAS_LOW_ALARM = 0x12, + SFP_BIAS_HIGH_WARN = 0x14, + SFP_BIAS_LOW_WARN = 0x16, + SFP_TXPWR_HIGH_ALARM = 0x18, + SFP_TXPWR_LOW_ALARM = 0x1a, + SFP_TXPWR_HIGH_WARN = 0x1c, + SFP_TXPWR_LOW_WARN = 0x1e, + SFP_RXPWR_HIGH_ALARM = 0x20, + SFP_RXPWR_LOW_ALARM = 0x22, + SFP_RXPWR_HIGH_WARN = 0x24, + SFP_RXPWR_LOW_WARN = 0x26, + SFP_LASER_TEMP_HIGH_ALARM = 0x28, + SFP_LASER_TEMP_LOW_ALARM = 0x2a, + SFP_LASER_TEMP_HIGH_WARN = 0x2c, + SFP_LASER_TEMP_LOW_WARN = 0x2e, + SFP_TEC_CUR_HIGH_ALARM = 0x30, + SFP_TEC_CUR_LOW_ALARM = 0x32, + SFP_TEC_CUR_HIGH_WARN = 0x34, + SFP_TEC_CUR_LOW_WARN = 0x36, + SFP_CAL_RXPWR4 = 0x38, + SFP_CAL_RXPWR3 = 0x3c, + SFP_CAL_RXPWR2 = 0x40, + SFP_CAL_RXPWR1 = 0x44, + SFP_CAL_RXPWR0 = 0x48, + SFP_CAL_TXI_SLOPE = 0x4c, + SFP_CAL_TXI_OFFSET = 0x4e, + SFP_CAL_TXPWR_SLOPE = 0x50, + SFP_CAL_TXPWR_OFFSET = 0x52, + SFP_CAL_T_SLOPE = 0x54, + SFP_CAL_T_OFFSET = 0x56, + SFP_CAL_V_SLOPE = 0x58, + SFP_CAL_V_OFFSET = 0x5a, + SFP_CHKSUM = 0x5f, + + SFP_TEMP = 0x60, + SFP_VCC = 0x62, + SFP_TX_BIAS = 0x64, + SFP_TX_POWER = 0x66, + SFP_RX_POWER = 0x68, + SFP_LASER_TEMP = 0x6a, + SFP_TEC_CUR = 0x6c, + + SFP_STATUS = 0x6e, + SFP_ALARM = 0x70, + + SFP_EXT_STATUS = 0x76, + SFP_VSL = 0x78, + SFP_PAGE = 0x7f, +}; + +struct device_node; +struct ethtool_eeprom; +struct ethtool_modinfo; +struct net_device; +struct sfp_bus; + +struct sfp_upstream_ops { + int (*module_insert)(void *, const struct sfp_eeprom_id *id); + void (*module_remove)(void *); + void (*link_down)(void *); + void (*link_up)(void *); + int (*connect_phy)(void *, struct phy_device *); + void (*disconnect_phy)(void *); +}; + +#if IS_ENABLED(CONFIG_SFP) +int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); +phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id); +void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); + +int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); +int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, + u8 *data); +void sfp_upstream_start(struct sfp_bus *bus); +void sfp_upstream_stop(struct sfp_bus *bus); +struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops); +void sfp_unregister_upstream(struct sfp_bus *bus); +#else +static inline int sfp_parse_port(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ + return PORT_OTHER; +} + +static inline phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id) +{ + return PHY_INTERFACE_MODE_NA; +} + +static inline void sfp_parse_support(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ +} + +static inline int sfp_get_module_info(struct sfp_bus *bus, + struct ethtool_modinfo *modinfo) +{ + return -EOPNOTSUPP; +} + +static inline int sfp_get_module_eeprom(struct sfp_bus *bus, + struct ethtool_eeprom *ee, u8 *data) +{ + return -EOPNOTSUPP; +} + +static inline void sfp_upstream_start(struct sfp_bus *bus) +{ +} + +static inline void sfp_upstream_stop(struct sfp_bus *bus) +{ +} + +static inline struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops) +{ + return (struct sfp_bus *)-1; +} + +static inline void sfp_unregister_upstream(struct sfp_bus *bus) +{ +} +#endif + +#endif diff --git a/include/linux/shm.h b/include/linux/shm.h index 04e881829625..74a4b3b64352 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -12,9 +12,9 @@ struct shmid_kernel /* private to the kernel */ struct file *shm_file; unsigned long shm_nattch; unsigned long shm_segsz; - time_t shm_atim; - time_t shm_dtim; - time_t shm_ctim; + time64_t shm_atim; + time64_t shm_dtim; + time64_t shm_ctim; pid_t shm_cprid; pid_t shm_lprid; struct user_struct *mlock_user; @@ -22,28 +22,11 @@ struct shmid_kernel /* private to the kernel */ /* The task created the shm object. NULL if the task is dead. */ struct task_struct *shm_creator; struct list_head shm_clist; /* list by creator */ -}; +} __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ -#define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ -#define SHM_NORESERVE 010000 /* don't check for reservations */ - -/* Bits [26:31] are reserved */ - -/* - * When SHM_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define SHM_HUGE_SHIFT 26 -#define SHM_HUGE_MASK 0x3f -#define SHM_HUGE_2MB (21 << SHM_HUGE_SHIFT) -#define SHM_HUGE_1GB (30 << SHM_HUGE_SHIFT) #ifdef CONFIG_SYSVIPC struct sysv_shm { diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a7d6bd2a918f..b6c3540e07bc 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -137,9 +137,15 @@ extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); +extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr); #else #define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) +#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ + dst_addr) ({ BUG(); 0; }) #endif #endif diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 4fcacd915d45..51d189615bda 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -18,6 +18,13 @@ struct shrink_control { */ unsigned long nr_to_scan; + /* + * How many objects did scan_objects process? + * This defaults to nr_to_scan before every call, but the callee + * should track its actual progress. + */ + unsigned long nr_scanned; + /* current node being shrunk (for NUMA aware shrinkers) */ int nid; diff --git a/include/linux/signal.h b/include/linux/signal.h index 1f5a16620693..38564e3e54c7 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -3,16 +3,13 @@ #include <linux/bug.h> #include <linux/signal_types.h> +#include <linux/string.h> struct task_struct; /* for sysctl */ extern int print_fatal_signals; -#ifndef HAVE_ARCH_COPY_SIGINFO - -#include <linux/string.h> - static inline void copy_siginfo(struct siginfo *to, struct siginfo *from) { if (from->si_code < 0) @@ -22,7 +19,21 @@ static inline void copy_siginfo(struct siginfo *to, struct siginfo *from) memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld)); } +int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); + +enum siginfo_layout { + SIL_KILL, + SIL_TIMER, + SIL_POLL, + SIL_FAULT, + SIL_CHLD, + SIL_RT, +#ifdef __ARCH_SIGSYS + SIL_SYS, #endif +}; + +enum siginfo_layout siginfo_layout(int sig, int si_code); /* * Define some primitives to manipulate sigset_t. @@ -246,8 +257,6 @@ extern int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, bool group); extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p); extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); -extern int do_sigtimedwait(const sigset_t *, siginfo_t *, - const struct timespec *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); @@ -385,10 +394,18 @@ int unhandled_signal(struct task_struct *tsk, int sig); rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) ) +#define SIG_SPECIFIC_SICODES_MASK (\ + rt_sigmask(SIGILL) | rt_sigmask(SIGFPE) | \ + rt_sigmask(SIGSEGV) | rt_sigmask(SIGBUS) | \ + rt_sigmask(SIGTRAP) | rt_sigmask(SIGCHLD) | \ + rt_sigmask(SIGPOLL) | rt_sigmask(SIGSYS) | \ + SIGEMT_MASK ) + #define sig_kernel_only(sig) siginmask(sig, SIG_KERNEL_ONLY_MASK) #define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK) #define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) #define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) +#define sig_specific_sicodes(sig) siginmask(sig, SIG_SPECIFIC_SICODES_MASK) #define sig_fatal(t, signr) \ (!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index f4dfade428f0..8621ffdeecbf 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -97,21 +97,46 @@ static inline struct sk_buff *skb_array_consume(struct skb_array *a) return ptr_ring_consume(&a->ring); } +static inline int skb_array_consume_batched(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched(&a->ring, (void **)array, n); +} + static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a) { return ptr_ring_consume_irq(&a->ring); } +static inline int skb_array_consume_batched_irq(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched_irq(&a->ring, (void **)array, n); +} + static inline struct sk_buff *skb_array_consume_any(struct skb_array *a) { return ptr_ring_consume_any(&a->ring); } +static inline int skb_array_consume_batched_any(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched_any(&a->ring, (void **)array, n); +} + + static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a) { return ptr_ring_consume_bh(&a->ring); } +static inline int skb_array_consume_batched_bh(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched_bh(&a->ring, (void **)array, n); +} + static inline int __skb_array_len_with_tag(struct sk_buff *skb) { if (likely(skb)) { @@ -156,13 +181,20 @@ static void __skb_array_destroy_skb(void *ptr) kfree_skb(ptr); } +static inline void skb_array_unconsume(struct skb_array *a, + struct sk_buff **skbs, int n) +{ + ptr_ring_unconsume(&a->ring, (void **)skbs, n, __skb_array_destroy_skb); +} + static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } static inline int skb_array_resize_multiple(struct skb_array **rings, - int nrings, int size, gfp_t gfp) + int nrings, unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); return ptr_ring_resize_multiple((struct ptr_ring **)rings, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a098d95b3d84..72299ef00061 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -22,6 +22,7 @@ #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> +#include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> @@ -109,6 +110,7 @@ * may perform further validation in this case. * GRE: only if the checksum is present in the header. * SCTP: indicates the CRC in SCTP header has been validated. + * FCOE: indicates the CRC in FC frame has been validated. * * skb->csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. @@ -126,8 +128,10 @@ * packet as seen by netif_rx() and fills out in skb->csum. Meaning, the * hardware doesn't need to parse L3/L4 headers to implement this. * - * Note: Even if device supports only some protocols, but is able to produce - * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * Notes: + * - Even if device supports only some protocols, but is able to produce + * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * CHECKSUM_PARTIAL: * @@ -162,14 +166,11 @@ * * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate - * checksum offload capability. If a device has limited checksum capabilities - * (for instance can only perform NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM as - * described above) a helper function can be called to resolve - * CHECKSUM_PARTIAL. The helper functions are skb_csum_off_chk*. The helper - * function takes a spec argument that describes the protocol layer that is - * supported for checksum offload and can be called for each packet. If a - * packet does not match the specification for offload, skb_checksum_help - * is called to resolve the checksum. + * checksum offload capability. + * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based + * on network device checksumming capabilities: if a packet does not match + * them, skb_checksum_help or skb_crc32c_help (depending on the value of + * csum_not_inet, see item D.) is called to resolve the checksum. * * CHECKSUM_NONE: * @@ -189,11 +190,13 @@ * * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack - * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset - * accordingly. Note the there is no indication in the skbuff that the - * CHECKSUM_PARTIAL refers to an SCTP checksum, a driver that supports - * both IP checksum offload and SCTP CRC offload must verify which offload - * is configured for a packet presumably by inspecting packet headers. + * will set set csum_start and csum_offset accordingly, set ip_summed to + * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in + * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. + * A driver that supports both IP checksum offload and SCTP CRC32c offload + * must verify which offload is configured for a packet by testing the + * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve + * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of * offloading the FCOE CRC in a packet. To perform this offload the stack @@ -250,7 +253,7 @@ struct nf_conntrack { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { - atomic_t use; + refcount_t use; enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, @@ -343,6 +346,42 @@ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) frag->size -= delta; } +static inline bool skb_frag_must_loop(struct page *p) +{ +#if defined(CONFIG_HIGHMEM) + if (PageHighMem(p)) + return true; +#endif + return false; +} + +/** + * skb_frag_foreach_page - loop over pages in a fragment + * + * @f: skb frag to operate on + * @f_off: offset from start of f->page.p + * @f_len: length from f_off to loop over + * @p: (temp var) current page + * @p_off: (temp var) offset from start of current page, + * non-zero only on first page. + * @p_len: (temp var) length in current page, + * < PAGE_SIZE only on first and last page. + * @copied: (temp var) length so far, excluding current p_len. + * + * A fragment can hold a compound page, in which case per-page + * operations, notably kmap_atomic, must be called for each + * regular page. + */ +#define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ + for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ + p_off = (f_off) & (PAGE_SIZE - 1), \ + p_len = skb_frag_must_loop(p) ? \ + min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ + copied = 0; \ + copied < f_len; \ + copied += p_len, p++, p_off = 0, \ + p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ + #define HAVE_HW_TIME_STAMP /** @@ -391,6 +430,7 @@ enum { SKBTX_SCHED_TSTAMP = 1 << 6, }; +#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) @@ -405,10 +445,46 @@ enum { */ struct ubuf_info { void (*callback)(struct ubuf_info *, bool zerocopy_success); - void *ctx; - unsigned long desc; + union { + struct { + unsigned long desc; + void *ctx; + }; + struct { + u32 id; + u16 len; + u16 zerocopy:1; + u32 bytelen; + }; + }; + refcount_t refcnt; + + struct mmpin { + struct user_struct *user; + unsigned int num_pg; + } mmp; }; +#define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) + +struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); + +static inline void sock_zerocopy_get(struct ubuf_info *uarg) +{ + refcount_inc(&uarg->refcnt); +} + +void sock_zerocopy_put(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg); + +void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -461,39 +537,38 @@ enum { enum { SKB_GSO_TCPV4 = 1 << 0, - SKB_GSO_UDP = 1 << 1, /* This indicates the skb is from an untrusted source. */ - SKB_GSO_DODGY = 1 << 2, + SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ - SKB_GSO_TCP_ECN = 1 << 3, + SKB_GSO_TCP_ECN = 1 << 2, - SKB_GSO_TCP_FIXEDID = 1 << 4, + SKB_GSO_TCP_FIXEDID = 1 << 3, - SKB_GSO_TCPV6 = 1 << 5, + SKB_GSO_TCPV6 = 1 << 4, - SKB_GSO_FCOE = 1 << 6, + SKB_GSO_FCOE = 1 << 5, - SKB_GSO_GRE = 1 << 7, + SKB_GSO_GRE = 1 << 6, - SKB_GSO_GRE_CSUM = 1 << 8, + SKB_GSO_GRE_CSUM = 1 << 7, - SKB_GSO_IPXIP4 = 1 << 9, + SKB_GSO_IPXIP4 = 1 << 8, - SKB_GSO_IPXIP6 = 1 << 10, + SKB_GSO_IPXIP6 = 1 << 9, - SKB_GSO_UDP_TUNNEL = 1 << 11, + SKB_GSO_UDP_TUNNEL = 1 << 10, - SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12, + SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, - SKB_GSO_PARTIAL = 1 << 13, + SKB_GSO_PARTIAL = 1 << 12, - SKB_GSO_TUNNEL_REMCSUM = 1 << 14, + SKB_GSO_TUNNEL_REMCSUM = 1 << 13, - SKB_GSO_SCTP = 1 << 15, + SKB_GSO_SCTP = 1 << 14, - SKB_GSO_ESP = 1 << 16, + SKB_GSO_ESP = 1 << 15, }; #if BITS_PER_LONG > 32 @@ -506,66 +581,6 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif -/** - * struct skb_mstamp - multi resolution time stamps - * @stamp_us: timestamp in us resolution - * @stamp_jiffies: timestamp in jiffies - */ -struct skb_mstamp { - union { - u64 v64; - struct { - u32 stamp_us; - u32 stamp_jiffies; - }; - }; -}; - -/** - * skb_mstamp_get - get current timestamp - * @cl: place to store timestamps - */ -static inline void skb_mstamp_get(struct skb_mstamp *cl) -{ - u64 val = local_clock(); - - do_div(val, NSEC_PER_USEC); - cl->stamp_us = (u32)val; - cl->stamp_jiffies = (u32)jiffies; -} - -/** - * skb_mstamp_delta - compute the difference in usec between two skb_mstamp - * @t1: pointer to newest sample - * @t0: pointer to oldest sample - */ -static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 delta_us = t1->stamp_us - t0->stamp_us; - u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; - - /* If delta_us is negative, this might be because interval is too big, - * or local_clock() drift is too big : fallback using jiffies. - */ - if (delta_us <= 0 || - delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) - - delta_us = jiffies_to_usecs(delta_jiffies); - - return delta_us; -} - -static inline bool skb_mstamp_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 diff = t1->stamp_jiffies - t0->stamp_jiffies; - - if (!diff) - diff = t1->stamp_us - t0->stamp_us; - return diff > 0; -} - /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -616,6 +631,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS + * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @dst_pending_confirm: need to confirm neighbour * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking @@ -646,7 +662,7 @@ struct sk_buff { union { ktime_t tstamp; - struct skb_mstamp skb_mstamp; + u64 skb_mstamp; }; }; struct rb_node rbnode; /* used in netem & tcp stack */ @@ -744,7 +760,7 @@ struct sk_buff { __u8 csum_valid:1; __u8 csum_complete_sw:1; __u8 csum_level:2; - __u8 csum_bad:1; + __u8 csum_not_inet:1; __u8 dst_pending_confirm:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -818,7 +834,7 @@ struct sk_buff { unsigned char *head, *data; unsigned int truesize; - atomic_t users; + refcount_t users; }; #ifdef __KERNEL__ @@ -915,10 +931,34 @@ static inline bool skb_pkt_type_ok(u32 ptype) return ptype <= PACKET_OTHERHOST; } +static inline unsigned int skb_napi_id(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + return skb->napi_id; +#else + return 0; +#endif +} + +/* decrement the reference count and return true if we can free the skb */ +static inline bool skb_unref(struct sk_buff *skb) +{ + if (unlikely(!skb)) + return false; + if (likely(refcount_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!refcount_dec_and_test(&skb->users))) + return false; + + return true; +} + +void skb_release_head_state(struct sk_buff *skb); void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_tx_error(struct sk_buff *skb); void consume_skb(struct sk_buff *skb); +void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; @@ -948,7 +988,7 @@ struct sk_buff_fclones { struct sk_buff skb2; - atomic_t fclone_ref; + refcount_t fclone_ref; }; /** @@ -968,7 +1008,7 @@ static inline bool skb_fclone_busy(const struct sock *sk, fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && - atomic_read(&fclones->fclone_ref) > 1 && + refcount_read(&fclones->fclone_ref) > 1 && fclones->skb2.sk == sk; } @@ -978,12 +1018,6 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } -struct sk_buff *__alloc_skb_head(gfp_t priority, int node); -static inline struct sk_buff *alloc_skb_head(gfp_t priority) -{ - return __alloc_skb_head(priority, -1); -} - struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); @@ -1001,12 +1035,28 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); -int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, - int offset, int len); -int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, - int len); +int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); +int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); -int skb_pad(struct sk_buff *skb, int pad); +int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); + +/** + * skb_pad - zero pad the tail of an skb + * @skb: buffer to pad + * @pad: space to pad + * + * Ensure that a buffer is followed by a padding area that is zero + * filled. Used by network drivers which may DMA or transfer data + * beyond the buffer end onto the wire. + * + * May return error in out of memory cases. The skb is freed on error. + */ +static inline int skb_pad(struct sk_buff *skb, int pad) +{ + return __skb_pad(skb, pad, true); +} #define dev_kfree_skb(a) consume_skb(a) int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, @@ -1162,8 +1212,6 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } -__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6); - static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { @@ -1176,20 +1224,6 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 return skb->hash; } -__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl); - -static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) -{ - if (!skb->l4_hash && !skb->sw_hash) { - struct flow_keys keys; - __u32 hash = __get_hash_from_flowi4(fl4, &keys); - - __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); - } - - return skb->hash; -} - __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) @@ -1234,6 +1268,50 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) return &skb_shinfo(skb)->hwtstamps; } +static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) +{ + bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; + + return is_zcopy ? skb_uarg(skb) : NULL; +} + +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +{ + if (skb && uarg && !skb_zcopy(skb)) { + sock_zerocopy_get(uarg); + skb_shinfo(skb)->destructor_arg = uarg; + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + } +} + +/* Release a reference on a zerocopy structure */ +static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + if (uarg->callback == sock_zerocopy_callback) { + uarg->zerocopy = uarg->zerocopy && zerocopy; + sock_zerocopy_put(uarg); + } else { + uarg->callback(uarg, zerocopy); + } + + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + +/* Abort a zerocopy operation and revert zckey on error in send syscall */ +static inline void skb_zcopy_abort(struct sk_buff *skb) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + sock_zerocopy_put_abort(uarg); + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head @@ -1316,7 +1394,7 @@ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); return skb; } @@ -1417,7 +1495,7 @@ static inline void __skb_header_release(struct sk_buff *skb) */ static inline int skb_shared(const struct sk_buff *skb) { - return atomic_read(&skb->users) != 1; + return refcount_read(&skb->users) != 1; } /** @@ -1816,13 +1894,18 @@ static inline unsigned int skb_headlen(const struct sk_buff *skb) return skb->len - skb->data_len; } -static inline unsigned int skb_pagelen(const struct sk_buff *skb) +static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); - return len + skb_headlen(skb); + return len; +} + +static inline unsigned int skb_pagelen(const struct sk_buff *skb) +{ + return skb_headlen(skb) + __skb_pagelen(skb); } /** @@ -1926,41 +2009,87 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) /* * Add data to an sk_buff */ -unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); -unsigned char *skb_put(struct sk_buff *skb, unsigned int len); -static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len) +void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); +void *skb_put(struct sk_buff *skb, unsigned int len); +static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { - unsigned char *tmp = skb_tail_pointer(skb); + void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } -unsigned char *skb_push(struct sk_buff *skb, unsigned int len); -static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len) +static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) +{ + void *tmp = __skb_put(skb, len); + + memset(tmp, 0, len); + return tmp; +} + +static inline void *__skb_put_data(struct sk_buff *skb, const void *data, + unsigned int len) +{ + void *tmp = __skb_put(skb, len); + + memcpy(tmp, data, len); + return tmp; +} + +static inline void __skb_put_u8(struct sk_buff *skb, u8 val) +{ + *(u8 *)__skb_put(skb, 1) = val; +} + +static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) +{ + void *tmp = skb_put(skb, len); + + memset(tmp, 0, len); + + return tmp; +} + +static inline void *skb_put_data(struct sk_buff *skb, const void *data, + unsigned int len) +{ + void *tmp = skb_put(skb, len); + + memcpy(tmp, data, len); + + return tmp; +} + +static inline void skb_put_u8(struct sk_buff *skb, u8 val) +{ + *(u8 *)skb_put(skb, 1) = val; +} + +void *skb_push(struct sk_buff *skb, unsigned int len); +static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; return skb->data; } -unsigned char *skb_pull(struct sk_buff *skb, unsigned int len); -static inline unsigned char *__skb_pull(struct sk_buff *skb, unsigned int len) +void *skb_pull(struct sk_buff *skb, unsigned int len); +static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; BUG_ON(skb->len < skb->data_len); return skb->data += len; } -static inline unsigned char *skb_pull_inline(struct sk_buff *skb, unsigned int len) +static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } -unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta); +void *__pskb_pull_tail(struct sk_buff *skb, int delta); -static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len) +static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) { if (len > skb_headlen(skb) && !__pskb_pull_tail(skb, len - skb_headlen(skb))) @@ -1969,7 +2098,7 @@ static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len) return skb->data += len; } -static inline unsigned char *pskb_pull(struct sk_buff *skb, unsigned int len) +static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); } @@ -2193,6 +2322,11 @@ static inline int skb_mac_offset(const struct sk_buff *skb) return skb_mac_header(skb) - skb->data; } +static inline u32 skb_mac_header_len(const struct sk_buff *skb) +{ + return skb->network_header - skb->mac_header; +} + static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; @@ -2416,7 +2550,17 @@ static inline void skb_orphan(struct sk_buff *skb) */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { - if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY))) + if (likely(!skb_zcopy(skb))) + return 0; + if (skb_uarg(skb)->callback == sock_zerocopy_callback) + return 0; + return skb_copy_ubufs(skb, gfp_mask); +} + +/* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ +static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) +{ + if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } @@ -2691,7 +2835,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map - * @dir: the direction of the mapping (%PCI_DMA_*) + * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ @@ -2807,25 +2951,42 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length + * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on - * success. The skb is freed on error. + * success. The skb is freed on error if @free_on_error is true. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, + bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; - if (skb_pad(skb, len)) + if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } +/** + * skb_put_padto - increase size and pad an skbuff up to a minimal size + * @skb: buffer to pad + * @len: minimal length + * + * Pads up a buffer to ensure the trailing bytes exist and are + * blanked. If the buffer already contains sufficient data it + * is untouched. Otherwise it is extended. Returns zero on + * success. The skb is freed on error. + */ +static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +{ + return __skb_put_padto(skb, len, true); +} + static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { @@ -2848,6 +3009,8 @@ static inline int skb_add_data(struct sk_buff *skb, static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { + if (skb_zcopy(skb)) + return false; if (i) { const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; @@ -2952,7 +3115,7 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb, __skb_postpush_rcsum(skb, start, len, 0); } -unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum @@ -2965,8 +3128,7 @@ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ -static inline unsigned char *skb_push_rcsum(struct sk_buff *skb, - unsigned int len) +static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); @@ -3056,6 +3218,13 @@ static inline void skb_frag_list_init(struct sk_buff *skb) int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, const struct sk_buff *skb); +struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), + int *peeked, int *off, int *err, + struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), @@ -3096,6 +3265,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); +int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, + int len); +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, @@ -3129,6 +3301,8 @@ struct skb_checksum_ops { __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; +extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; + __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, @@ -3298,13 +3472,6 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); -static inline void sw_tx_timestamp(struct sk_buff *skb) -{ - if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP && - !(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) - skb_tstamp_tx(skb, NULL); -} - /** * skb_tx_timestamp() - Driver hook for transmit timestamping * @@ -3320,7 +3487,8 @@ static inline void sw_tx_timestamp(struct sk_buff *skb) static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); - sw_tx_timestamp(skb); + if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) + skb_tstamp_tx(skb, NULL); } /** @@ -3386,21 +3554,6 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) } } -static inline void __skb_mark_checksum_bad(struct sk_buff *skb) -{ - /* Mark current checksum as bad (typically called from GRO - * path). In the case that ip_summed is CHECKSUM_NONE - * this must be the first checksum encountered in the packet. - * When ip_summed is CHECKSUM_UNNECESSARY, this is the first - * checksum after the last one validated. For UDP, a zero - * checksum can not be marked as bad. - */ - - if (skb->ip_summed == CHECKSUM_NONE || - skb->ip_summed == CHECKSUM_UNNECESSARY) - skb->csum_bad = 1; -} - /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise @@ -3454,9 +3607,6 @@ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, skb->csum_valid = 1; return 0; } - } else if (skb->csum_bad) { - /* ip_summed == CHECKSUM_NONE in this case */ - return (__force __sum16)1; } skb->csum = psum; @@ -3516,8 +3666,7 @@ static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { - return (skb->ip_summed == CHECKSUM_NONE && - skb->csum_valid && !skb->csum_bad); + return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, @@ -3593,13 +3742,13 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct) #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) { - if (nf_bridge && atomic_dec_and_test(&nf_bridge->use)) + if (nf_bridge && refcount_dec_and_test(&nf_bridge->use)) kfree(nf_bridge); } static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) { if (nf_bridge) - atomic_inc(&nf_bridge->use); + refcount_inc(&nf_bridge->use); } #endif /* CONFIG_BRIDGE_NETFILTER */ static inline void nf_reset(struct sk_buff *skb) diff --git a/include/linux/slab.h b/include/linux/slab.h index 04a7f7993e67..41473df6dfb0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -471,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * * %__GFP_NOWARN - If allocation fails, don't issue any warnings. * - * %__GFP_REPEAT - If allocation fails initially, try once more before failing. + * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail + * eventually. * * There are other flags available as well, but these are not intended * for general use, and so are not documented here. For a full list of diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 93315d6b21a8..0783b622311e 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -41,12 +41,31 @@ struct kmem_cache_cpu { void **freelist; /* Pointer to next available object */ unsigned long tid; /* Globally unique transaction id */ struct page *page; /* The slab from which we are allocating */ +#ifdef CONFIG_SLUB_CPU_PARTIAL struct page *partial; /* Partially allocated frozen slabs */ +#endif #ifdef CONFIG_SLUB_STATS unsigned stat[NR_SLUB_STAT_ITEMS]; #endif }; +#ifdef CONFIG_SLUB_CPU_PARTIAL +#define slub_percpu_partial(c) ((c)->partial) + +#define slub_set_percpu_partial(c, p) \ +({ \ + slub_percpu_partial(c) = (p)->next; \ +}) + +#define slub_percpu_partial_read_once(c) READ_ONCE(slub_percpu_partial(c)) +#else +#define slub_percpu_partial(c) NULL + +#define slub_set_percpu_partial(c, p) + +#define slub_percpu_partial_read_once(c) NULL +#endif // CONFIG_SLUB_CPU_PARTIAL + /* * Word size structure that can be atomically updated or read and that * contains both the order and the number of objects that a slab of the @@ -67,7 +86,9 @@ struct kmem_cache { int size; /* The size of an object including meta data */ int object_size; /* The size of an object without meta data */ int offset; /* Free pointer offset. */ +#ifdef CONFIG_SLUB_CPU_PARTIAL int cpu_partial; /* Number of per cpu partial objects to keep around */ +#endif struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ @@ -79,9 +100,9 @@ struct kmem_cache { int inuse; /* Offset to metadata */ int align; /* Alignment */ int reserved; /* Reserved bytes at the end of slabs */ + int red_left_pad; /* Left redzone padding size */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ - int red_left_pad; /* Left redzone padding size */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ struct work_struct kobj_remove_work; @@ -94,6 +115,10 @@ struct kmem_cache { #endif #endif +#ifdef CONFIG_SLAB_FREELIST_HARDENED + unsigned long random; +#endif + #ifdef CONFIG_NUMA /* * Defragmentation by allocating from a remote node. @@ -112,6 +137,17 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; +#ifdef CONFIG_SLUB_CPU_PARTIAL +#define slub_cpu_partial(s) ((s)->cpu_partial) +#define slub_set_cpu_partial(s, n) \ +({ \ + slub_cpu_partial(s) = (n); \ +}) +#else +#define slub_cpu_partial(s) (0) +#define slub_set_cpu_partial(s, n) +#endif // CONFIG_SLUB_CPU_PARTIAL + #ifdef CONFIG_SYSFS #define SLAB_SUPPORTS_SYSFS void sysfs_slab_release(struct kmem_cache *); diff --git a/include/linux/smp.h b/include/linux/smp.h index 68123c1fe549..98b1fe027fc9 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -14,13 +14,17 @@ #include <linux/llist.h> typedef void (*smp_call_func_t)(void *info); -struct call_single_data { +struct __call_single_data { struct llist_node llist; smp_call_func_t func; void *info; unsigned int flags; }; +/* Use __aligned() to avoid to use 2 cache lines for 1 csd */ +typedef struct __call_single_data call_single_data_t + __aligned(sizeof(struct __call_single_data)); + /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; @@ -48,7 +52,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), smp_call_func_t func, void *info, bool wait, gfp_t gfp_flags); -int smp_call_function_single_async(int cpu, struct call_single_data *csd); +int smp_call_function_single_async(int cpu, call_single_data_t *csd); #ifdef CONFIG_SMP diff --git a/include/linux/soc/actions/owl-sps.h b/include/linux/soc/actions/owl-sps.h new file mode 100644 index 000000000000..33d0dbeceb55 --- /dev/null +++ b/include/linux/soc/actions/owl-sps.h @@ -0,0 +1,11 @@ +/* + * Copyright (c) 2017 Andreas Färber + * + * SPDX-License-Identifier: GPL-2.0+ + */ +#ifndef SOC_ACTIONS_OWL_SPS_H +#define SOC_ACTIONS_OWL_SPS_H + +int owl_sps_set_pg(void __iomem *base, u32 pwr_mask, u32 ack_mask, bool enable); + +#endif diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index a5714e93fb34..a0182ec2a621 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -20,6 +20,13 @@ #define MT8173_TOP_AXI_PROT_EN_MFG_M1 BIT(22) #define MT8173_TOP_AXI_PROT_EN_MFG_SNOOP_OUT BIT(23) +#define MT7622_TOP_AXI_PROT_EN_ETHSYS (BIT(3) | BIT(17)) +#define MT7622_TOP_AXI_PROT_EN_HIF0 (BIT(24) | BIT(25)) +#define MT7622_TOP_AXI_PROT_EN_HIF1 (BIT(26) | BIT(27) | \ + BIT(28)) +#define MT7622_TOP_AXI_PROT_EN_WB (BIT(2) | BIT(6) | \ + BIT(7) | BIT(8)) + int mtk_infracfg_set_bus_protection(struct regmap *infracfg, u32 mask); int mtk_infracfg_clear_bus_protection(struct regmap *infracfg, u32 mask); diff --git a/include/linux/soc/renesas/rcar-rst.h b/include/linux/soc/renesas/rcar-rst.h index 787e7ad53d45..2c231f2280a6 100644 --- a/include/linux/soc/renesas/rcar-rst.h +++ b/include/linux/soc/renesas/rcar-rst.h @@ -1,8 +1,7 @@ #ifndef __LINUX_SOC_RENESAS_RCAR_RST_H__ #define __LINUX_SOC_RENESAS_RCAR_RST_H__ -#if defined(CONFIG_ARCH_RCAR_GEN1) || defined(CONFIG_ARCH_RCAR_GEN2) || \ - defined(CONFIG_ARCH_R8A7795) || defined(CONFIG_ARCH_R8A7796) +#ifdef CONFIG_RST_RCAR int rcar_rst_read_mode_pins(u32 *mode); #else static inline int rcar_rst_read_mode_pins(u32 *mode) { return -ENODEV; } diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 2b7882666ef6..66693bc4c6ad 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -17,6 +17,8 @@ #ifndef __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ #define __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ +#include <linux/dmaengine.h> + /* * PKTDMA descriptor manipulation macros for host packet descriptor */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 082027457825..8ad963cdc88c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -287,6 +287,7 @@ struct ucred { #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN +#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through @@ -334,6 +335,7 @@ struct ucred { #define SOL_ALG 279 #define SOL_NFC 280 #define SOL_KCM 281 +#define SOL_TLS 282 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h index aa07d7b32568..82d96a346e6f 100644 --- a/include/linux/spi/mcp23s08.h +++ b/include/linux/spi/mcp23s08.h @@ -1,11 +1,3 @@ - -/* FIXME driver should be able to handle IRQs... */ - -struct mcp23s08_chip_info { - bool is_present; /* true if populated */ - unsigned pullups; /* BIT(x) means enable pullup x */ -}; - struct mcp23s08_platform_data { /* For mcp23s08, up to 4 slaves (numbered 0..3) can share one SPI * chipselect, each providing 1 gpio_chip instance with 8 gpios. @@ -13,31 +5,13 @@ struct mcp23s08_platform_data { * chipselect, each providing 1 gpio_chip (port A + port B) with * 16 gpios. */ - struct mcp23s08_chip_info chip[8]; + u32 spi_present_mask; - /* "base" is the number of the first GPIO. Dynamic assignment is - * not currently supported, and even if there are gaps in chip - * addressing the GPIO numbers are sequential .. so for example - * if only slaves 0 and 3 are present, their GPIOs range from - * base to base+15 (or base+31 for s17 variant). + /* "base" is the number of the first GPIO or -1 for dynamic + * assignment. If there are gaps in chip addressing the GPIO + * numbers are sequential .. so for example if only slaves 0 + * and 3 are present, their GPIOs range from base to base+15 + * (or base+31 for s17 variant). */ unsigned base; - /* Marks the device as a interrupt controller. - * NOTE: The interrupt functionality is only supported for i2c - * versions of the chips. The spi chips can also do the interrupts, - * but this is not supported by the linux driver yet. - */ - bool irq_controller; - - /* Sets the mirror flag in the IOCON register. Devices - * with two interrupt outputs (these are the devices ending with 17 and - * those that have 16 IOs) have two IO banks: IO 0-7 form bank 1 and - * IO 8-15 are bank 2. These chips have two different interrupt outputs: - * One for bank 1 and another for bank 2. If irq-mirror is set, both - * interrupts are generated regardless of the bank that an input change - * occurred on. If it is not set, the interrupt are only generated for - * the bank they belong to. - * On devices with only one interrupt output this property is useless. - */ - bool mirror; }; diff --git a/include/linux/spi/sh_msiof.h b/include/linux/spi/sh_msiof.h index b087a85f5f72..f74b581f242f 100644 --- a/include/linux/spi/sh_msiof.h +++ b/include/linux/spi/sh_msiof.h @@ -1,10 +1,16 @@ #ifndef __SPI_SH_MSIOF_H__ #define __SPI_SH_MSIOF_H__ +enum { + MSIOF_SPI_MASTER, + MSIOF_SPI_SLAVE, +}; + struct sh_msiof_spi_info { int tx_fifo_override; int rx_fifo_override; u16 num_chipselect; + int mode; unsigned int dma_tx_id; unsigned int dma_rx_id; u32 dtdl; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 935bd2854ff1..7b2170bfd6e7 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -24,13 +24,13 @@ struct dma_chan; struct property_entry; -struct spi_master; +struct spi_controller; struct spi_transfer; struct spi_flash_read_message; /* - * INTERFACES between SPI master-side drivers and SPI infrastructure. - * (There's no SPI slave support for Linux yet...) + * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, + * and SPI infrastructure. */ extern struct bus_type spi_bus_type; @@ -84,7 +84,7 @@ struct spi_statistics { void spi_statistics_add_transfer_stats(struct spi_statistics *stats, struct spi_transfer *xfer, - struct spi_master *master); + struct spi_controller *ctlr); #define SPI_STATISTICS_ADD_TO_FIELD(stats, field, count) \ do { \ @@ -98,13 +98,14 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, SPI_STATISTICS_ADD_TO_FIELD(stats, field, 1) /** - * struct spi_device - Master side proxy for an SPI slave device + * struct spi_device - Controller side proxy for an SPI slave device * @dev: Driver model representation of the device. - * @master: SPI controller used with the device. + * @controller: SPI controller used with the device. + * @master: Copy of controller, for backwards compatibility. * @max_speed_hz: Maximum clock rate to be used with this chip * (on this board); may be changed by the device's driver. * The spi_transfer.speed_hz can override this for each transfer. - * @chip_select: Chipselect, distinguishing chips handled by @master. + * @chip_select: Chipselect, distinguishing chips handled by @controller. * @mode: The spi mode defines how data is clocked out and in. * This may be changed by the device's driver. * The "active low" default for chipselect mode can be overridden @@ -140,7 +141,8 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, */ struct spi_device { struct device dev; - struct spi_master *master; + struct spi_controller *controller; + struct spi_controller *master; /* compatibility layer */ u32 max_speed_hz; u8 chip_select; u8 bits_per_word; @@ -198,7 +200,7 @@ static inline void spi_dev_put(struct spi_device *spi) put_device(&spi->dev); } -/* ctldata is for the bus_master driver's runtime state */ +/* ctldata is for the bus_controller driver's runtime state */ static inline void *spi_get_ctldata(struct spi_device *spi) { return spi->controller_state; @@ -292,9 +294,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) spi_unregister_driver) /** - * struct spi_master - interface to SPI master controller + * struct spi_controller - interface to SPI master or slave controller * @dev: device interface to this driver - * @list: link with the global spi_master list + * @list: link with the global spi_controller list * @bus_num: board-specific (and often SOC-specific) identifier for a * given SPI controller. * @num_chipselect: chipselects are used to distinguish individual @@ -311,6 +313,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @min_speed_hz: Lowest supported transfer speed * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver + * @slave: indicates that this is an SPI slave controller * @max_transfer_size: function that returns the max transfer size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @max_message_size: function that returns the max message size for @@ -326,8 +329,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * the device whose settings are being modified. * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state - * @can_dma: determine whether this master supports DMA - * @queued: whether this master is providing an internal message queue + * @can_dma: determine whether this controller supports DMA + * @queued: whether this controller is providing an internal message queue * @kworker: thread struct for message pump * @kworker_task: pointer to task for message pump kworker thread * @pump_messages: work struct for scheduling work to the message pump @@ -374,6 +377,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @handle_err: the subsystem calls the driver to handle an error that occurs * in the generic implementation of transfer_one_message(). * @unprepare_message: undo any work done by prepare_message(). + * @slave_abort: abort the ongoing transfer request on an SPI slave controller * @spi_flash_read: to support spi-controller hardwares that provide * accelerated interface to read from flash devices. * @spi_flash_can_dma: analogous to can_dma() interface, but for @@ -382,7 +386,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). - * @statistics: statistics for the spi_master + * @statistics: statistics for the spi_controller * @dma_tx: DMA transmit channel * @dma_rx: DMA receive channel * @dummy_rx: dummy receive buffer for full-duplex devices @@ -391,7 +395,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * what Linux expects, this optional hook can be used to translate * between the two. * - * Each SPI master controller can communicate with one or more @spi_device + * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals * but not chip select signals. Each device may be configured to use a * different clock rate, since those shared signals are ignored unless @@ -402,7 +406,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * an SPI slave device. For each such message it queues, it calls the * message's completion function when the transaction completes. */ -struct spi_master { +struct spi_controller { struct device dev; struct list_head list; @@ -440,12 +444,16 @@ struct spi_master { /* other constraints relevant to this driver */ u16 flags; -#define SPI_MASTER_HALF_DUPLEX BIT(0) /* can't do full duplex */ -#define SPI_MASTER_NO_RX BIT(1) /* can't do buffer read */ -#define SPI_MASTER_NO_TX BIT(2) /* can't do buffer write */ -#define SPI_MASTER_MUST_RX BIT(3) /* requires rx */ -#define SPI_MASTER_MUST_TX BIT(4) /* requires tx */ -#define SPI_MASTER_GPIO_SS BIT(5) /* GPIO CS must select slave */ +#define SPI_CONTROLLER_HALF_DUPLEX BIT(0) /* can't do full duplex */ +#define SPI_CONTROLLER_NO_RX BIT(1) /* can't do buffer read */ +#define SPI_CONTROLLER_NO_TX BIT(2) /* can't do buffer write */ +#define SPI_CONTROLLER_MUST_RX BIT(3) /* requires rx */ +#define SPI_CONTROLLER_MUST_TX BIT(4) /* requires tx */ + +#define SPI_MASTER_GPIO_SS BIT(5) /* GPIO CS must select slave */ + + /* flag indicating this is an SPI slave controller */ + bool slave; /* * on some hardware transfer / message size may be constrained @@ -480,8 +488,8 @@ struct spi_master { * any other request management * + To a given spi_device, message queueing is pure fifo * - * + The master's main job is to process its message queue, - * selecting a chip then transferring data + * + The controller's main job is to process its message queue, + * selecting a chip (for masters), then transferring data * + If there are multiple spi_device children, the i/o queue * arbitration algorithm is unspecified (round robin, fifo, * priority, reservations, preemption, etc) @@ -494,7 +502,7 @@ struct spi_master { int (*transfer)(struct spi_device *spi, struct spi_message *mesg); - /* called on release() to free memory provided by spi_master */ + /* called on release() to free memory provided by spi_controller */ void (*cleanup)(struct spi_device *spi); /* @@ -504,13 +512,13 @@ struct spi_master { * not modify or store xfer and dma_tx and dma_rx must be set * while the device is prepared. */ - bool (*can_dma)(struct spi_master *master, + bool (*can_dma)(struct spi_controller *ctlr, struct spi_device *spi, struct spi_transfer *xfer); /* * These hooks are for drivers that want to use the generic - * master transfer queueing mechanism. If these are used, the + * controller transfer queueing mechanism. If these are used, the * transfer() function above must NOT be specified by the driver. * Over time we expect SPI drivers to be phased over to this API. */ @@ -531,14 +539,15 @@ struct spi_master { struct completion xfer_completion; size_t max_dma_len; - int (*prepare_transfer_hardware)(struct spi_master *master); - int (*transfer_one_message)(struct spi_master *master, + int (*prepare_transfer_hardware)(struct spi_controller *ctlr); + int (*transfer_one_message)(struct spi_controller *ctlr, struct spi_message *mesg); - int (*unprepare_transfer_hardware)(struct spi_master *master); - int (*prepare_message)(struct spi_master *master, + int (*unprepare_transfer_hardware)(struct spi_controller *ctlr); + int (*prepare_message)(struct spi_controller *ctlr, struct spi_message *message); - int (*unprepare_message)(struct spi_master *master, + int (*unprepare_message)(struct spi_controller *ctlr, struct spi_message *message); + int (*slave_abort)(struct spi_controller *ctlr); int (*spi_flash_read)(struct spi_device *spi, struct spi_flash_read_message *msg); bool (*spi_flash_can_dma)(struct spi_device *spi, @@ -550,9 +559,9 @@ struct spi_master { * of transfer_one_message() provied by the core. */ void (*set_cs)(struct spi_device *spi, bool enable); - int (*transfer_one)(struct spi_master *master, struct spi_device *spi, + int (*transfer_one)(struct spi_controller *ctlr, struct spi_device *spi, struct spi_transfer *transfer); - void (*handle_err)(struct spi_master *master, + void (*handle_err)(struct spi_controller *ctlr, struct spi_message *message); /* gpio chip select */ @@ -569,57 +578,78 @@ struct spi_master { void *dummy_rx; void *dummy_tx; - int (*fw_translate_cs)(struct spi_master *master, unsigned cs); + int (*fw_translate_cs)(struct spi_controller *ctlr, unsigned cs); }; -static inline void *spi_master_get_devdata(struct spi_master *master) +static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) { - return dev_get_drvdata(&master->dev); + return dev_get_drvdata(&ctlr->dev); } -static inline void spi_master_set_devdata(struct spi_master *master, void *data) +static inline void spi_controller_set_devdata(struct spi_controller *ctlr, + void *data) { - dev_set_drvdata(&master->dev, data); + dev_set_drvdata(&ctlr->dev, data); } -static inline struct spi_master *spi_master_get(struct spi_master *master) +static inline struct spi_controller *spi_controller_get(struct spi_controller *ctlr) { - if (!master || !get_device(&master->dev)) + if (!ctlr || !get_device(&ctlr->dev)) return NULL; - return master; + return ctlr; +} + +static inline void spi_controller_put(struct spi_controller *ctlr) +{ + if (ctlr) + put_device(&ctlr->dev); } -static inline void spi_master_put(struct spi_master *master) +static inline bool spi_controller_is_slave(struct spi_controller *ctlr) { - if (master) - put_device(&master->dev); + return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->slave; } /* PM calls that need to be issued by the driver */ -extern int spi_master_suspend(struct spi_master *master); -extern int spi_master_resume(struct spi_master *master); +extern int spi_controller_suspend(struct spi_controller *ctlr); +extern int spi_controller_resume(struct spi_controller *ctlr); /* Calls the driver make to interact with the message queue */ -extern struct spi_message *spi_get_next_queued_message(struct spi_master *master); -extern void spi_finalize_current_message(struct spi_master *master); -extern void spi_finalize_current_transfer(struct spi_master *master); +extern struct spi_message *spi_get_next_queued_message(struct spi_controller *ctlr); +extern void spi_finalize_current_message(struct spi_controller *ctlr); +extern void spi_finalize_current_transfer(struct spi_controller *ctlr); -/* the spi driver core manages memory for the spi_master classdev */ -extern struct spi_master * -spi_alloc_master(struct device *host, unsigned size); +/* the spi driver core manages memory for the spi_controller classdev */ +extern struct spi_controller *__spi_alloc_controller(struct device *host, + unsigned int size, bool slave); -extern int spi_register_master(struct spi_master *master); -extern int devm_spi_register_master(struct device *dev, - struct spi_master *master); -extern void spi_unregister_master(struct spi_master *master); +static inline struct spi_controller *spi_alloc_master(struct device *host, + unsigned int size) +{ + return __spi_alloc_controller(host, size, false); +} -extern struct spi_master *spi_busnum_to_master(u16 busnum); +static inline struct spi_controller *spi_alloc_slave(struct device *host, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __spi_alloc_controller(host, size, true); +} + +extern int spi_register_controller(struct spi_controller *ctlr); +extern int devm_spi_register_controller(struct device *dev, + struct spi_controller *ctlr); +extern void spi_unregister_controller(struct spi_controller *ctlr); + +extern struct spi_controller *spi_busnum_to_master(u16 busnum); /* * SPI resource management while processing a SPI message */ -typedef void (*spi_res_release_t)(struct spi_master *master, +typedef void (*spi_res_release_t)(struct spi_controller *ctlr, struct spi_message *msg, void *res); @@ -644,7 +674,7 @@ extern void *spi_res_alloc(struct spi_device *spi, extern void spi_res_add(struct spi_message *message, void *res); extern void spi_res_free(void *res); -extern void spi_res_release(struct spi_master *master, +extern void spi_res_release(struct spi_controller *ctlr, struct spi_message *message); /*---------------------------------------------------------------------------*/ @@ -828,7 +858,7 @@ struct spi_message { /* for optional use by whatever driver currently owns the * spi_message ... between calls to spi_async and then later - * complete(), that's the spi_master controller driver. + * complete(), that's the spi_controller controller driver. */ struct list_head queue; void *state; @@ -912,25 +942,27 @@ extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); extern int spi_async_locked(struct spi_device *spi, struct spi_message *message); +extern int spi_slave_abort(struct spi_device *spi); static inline size_t spi_max_message_size(struct spi_device *spi) { - struct spi_master *master = spi->master; - if (!master->max_message_size) + struct spi_controller *ctlr = spi->controller; + + if (!ctlr->max_message_size) return SIZE_MAX; - return master->max_message_size(spi); + return ctlr->max_message_size(spi); } static inline size_t spi_max_transfer_size(struct spi_device *spi) { - struct spi_master *master = spi->master; + struct spi_controller *ctlr = spi->controller; size_t tr_max = SIZE_MAX; size_t msg_max = spi_max_message_size(spi); - if (master->max_transfer_size) - tr_max = master->max_transfer_size(spi); + if (ctlr->max_transfer_size) + tr_max = ctlr->max_transfer_size(spi); /* transfer size limit must not be greater than messsage size limit */ return min(tr_max, msg_max); @@ -941,7 +973,7 @@ spi_max_transfer_size(struct spi_device *spi) /* SPI transfer replacement methods which make use of spi_res */ struct spi_replaced_transfers; -typedef void (*spi_replaced_release_t)(struct spi_master *master, +typedef void (*spi_replaced_release_t)(struct spi_controller *ctlr, struct spi_message *msg, struct spi_replaced_transfers *res); /** @@ -985,7 +1017,7 @@ extern struct spi_replaced_transfers *spi_replace_transfers( /* SPI transfer transformation methods */ -extern int spi_split_transfers_maxsize(struct spi_master *master, +extern int spi_split_transfers_maxsize(struct spi_controller *ctlr, struct spi_message *msg, size_t maxsize, gfp_t gfp); @@ -999,8 +1031,8 @@ extern int spi_split_transfers_maxsize(struct spi_master *master, extern int spi_sync(struct spi_device *spi, struct spi_message *message); extern int spi_sync_locked(struct spi_device *spi, struct spi_message *message); -extern int spi_bus_lock(struct spi_master *master); -extern int spi_bus_unlock(struct spi_master *master); +extern int spi_bus_lock(struct spi_controller *ctlr); +extern int spi_bus_unlock(struct spi_controller *ctlr); /** * spi_sync_transfer - synchronous SPI data transfer @@ -1185,9 +1217,9 @@ struct spi_flash_read_message { /* SPI core interface for flash read support */ static inline bool spi_flash_read_supported(struct spi_device *spi) { - return spi->master->spi_flash_read && - (!spi->master->flash_read_supported || - spi->master->flash_read_supported(spi)); + return spi->controller->spi_flash_read && + (!spi->controller->flash_read_supported || + spi->controller->flash_read_supported(spi)); } int spi_flash_read(struct spi_device *spi, @@ -1220,7 +1252,7 @@ int spi_flash_read(struct spi_device *spi, * @irq: Initializes spi_device.irq; depends on how the board is wired. * @max_speed_hz: Initializes spi_device.max_speed_hz; based on limits * from the chip datasheet and board-specific signal quality issues. - * @bus_num: Identifies which spi_master parents the spi_device; unused + * @bus_num: Identifies which spi_controller parents the spi_device; unused * by spi_new_device(), and otherwise depends on board wiring. * @chip_select: Initializes spi_device.chip_select; depends on how * the board is wired. @@ -1261,7 +1293,7 @@ struct spi_board_info { /* bus_num is board specific and matches the bus_num of some - * spi_master that will probably be registered later. + * spi_controller that will probably be registered later. * * chip_select reflects how this chip is wired to that master; * it's less than num_chipselect. @@ -1295,7 +1327,7 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) /* If you're hotplugging an adapter with devices (parport, usb, etc) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but - * normally that would be handled by spi_unregister_master(). + * normally that would be handled by spi_unregister_controller(). * * You can also use spi_alloc_device() and spi_add_device() to use a two * stage registration sequence for each spi_device. This gives the caller @@ -1304,13 +1336,13 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) * be defined using the board info. */ extern struct spi_device * -spi_alloc_device(struct spi_master *master); +spi_alloc_device(struct spi_controller *ctlr); extern int spi_add_device(struct spi_device *spi); extern struct spi_device * -spi_new_device(struct spi_master *, struct spi_board_info *); +spi_new_device(struct spi_controller *, struct spi_board_info *); extern void spi_unregister_device(struct spi_device *spi); @@ -1318,9 +1350,32 @@ extern const struct spi_device_id * spi_get_device_id(const struct spi_device *sdev); static inline bool -spi_transfer_is_last(struct spi_master *master, struct spi_transfer *xfer) +spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer) { - return list_is_last(&xfer->transfer_list, &master->cur_msg->transfers); + return list_is_last(&xfer->transfer_list, &ctlr->cur_msg->transfers); } + +/* Compatibility layer */ +#define spi_master spi_controller + +#define SPI_MASTER_HALF_DUPLEX SPI_CONTROLLER_HALF_DUPLEX +#define SPI_MASTER_NO_RX SPI_CONTROLLER_NO_RX +#define SPI_MASTER_NO_TX SPI_CONTROLLER_NO_TX +#define SPI_MASTER_MUST_RX SPI_CONTROLLER_MUST_RX +#define SPI_MASTER_MUST_TX SPI_CONTROLLER_MUST_TX + +#define spi_master_get_devdata(_ctlr) spi_controller_get_devdata(_ctlr) +#define spi_master_set_devdata(_ctlr, _data) \ + spi_controller_set_devdata(_ctlr, _data) +#define spi_master_get(_ctlr) spi_controller_get(_ctlr) +#define spi_master_put(_ctlr) spi_controller_put(_ctlr) +#define spi_master_suspend(_ctlr) spi_controller_suspend(_ctlr) +#define spi_master_resume(_ctlr) spi_controller_resume(_ctlr) + +#define spi_register_master(_ctlr) spi_register_controller(_ctlr) +#define devm_spi_register_master(_dev, _ctlr) \ + devm_spi_register_controller(_dev, _ctlr) +#define spi_unregister_master(_ctlr) spi_unregister_controller(_ctlr) + #endif /* __LINUX_SPI_H */ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 59248dcc6ef3..69e079c5ff98 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -118,24 +118,41 @@ do { \ #endif /* - * Despite its name it doesn't necessarily has to be a full barrier. - * It should only guarantee that a STORE before the critical section - * can not be reordered with LOADs and STOREs inside this section. - * spin_lock() is the one-way barrier, this LOAD can not escape out - * of the region. So the default implementation simply ensures that - * a STORE can not move into the critical section, smp_wmb() should - * serialize it with another STORE done by spin_lock(). + * This barrier must provide two things: + * + * - it must guarantee a STORE before the spin_lock() is ordered against a + * LOAD after it, see the comments at its two usage sites. + * + * - it must ensure the critical section is RCsc. + * + * The latter is important for cases where we observe values written by other + * CPUs in spin-loops, without barriers, while being subject to scheduling. + * + * CPU0 CPU1 CPU2 + * + * for (;;) { + * if (READ_ONCE(X)) + * break; + * } + * X=1 + * <sched-out> + * <sched-in> + * r = X; + * + * without transitivity it could be that CPU1 observes X!=0 breaks the loop, + * we get migrated and CPU2 sees X==0. + * + * Since most load-store architectures implement ACQUIRE with an smp_mb() after + * the LL/SC loop, they need no further barriers. Similarly all our TSO + * architectures imply an smp_mb() for each atomic instruction and equally don't + * need more. + * + * Architectures that can implement ACQUIRE better need to take care. */ -#ifndef smp_mb__before_spinlock -#define smp_mb__before_spinlock() smp_wmb() +#ifndef smp_mb__after_spinlock +#define smp_mb__after_spinlock() do { } while (0) #endif -/** - * raw_spin_unlock_wait - wait until the spinlock gets unlocked - * @lock: the spinlock in question. - */ -#define raw_spin_unlock_wait(lock) arch_spin_unlock_wait(&(lock)->raw_lock) - #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock) @@ -369,11 +386,6 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock) raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) -static __always_inline void spin_unlock_wait(spinlock_t *lock) -{ - raw_spin_unlock_wait(&lock->rlock); -} - static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 0d9848de677d..612fb530af41 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -26,11 +26,6 @@ #ifdef CONFIG_DEBUG_SPINLOCK #define arch_spin_is_locked(x) ((x)->slock == 0) -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - smp_cond_load_acquire(&lock->slock, VAL); -} - static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; @@ -73,7 +68,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) -#define arch_spin_unlock_wait(lock) do { barrier(); (void)(lock); } while (0) /* for sched/core.c and kernel_lock.c: */ # define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) # define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) diff --git a/include/linux/sram.h b/include/linux/sram.h index c97dcbe8ce25..4fb405fb0480 100644 --- a/include/linux/sram.h +++ b/include/linux/sram.h @@ -16,12 +16,12 @@ struct gen_pool; #ifdef CONFIG_SRAM_EXEC -int sram_exec_copy(struct gen_pool *pool, void *dst, void *src, size_t size); +void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src, size_t size); #else -static inline int sram_exec_copy(struct gen_pool *pool, void *dst, void *src, - size_t size) +static inline void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src, + size_t size) { - return -ENODEV; + return NULL; } #endif /* CONFIG_SRAM_EXEC */ #endif /* __LINUX_SRAM_H__ */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 4c1d5f7e62c4..39af9bc0f653 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -60,32 +60,15 @@ int init_srcu_struct(struct srcu_struct *sp); #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> -#elif defined(CONFIG_CLASSIC_SRCU) -#include <linux/srcuclassic.h> -#else +#elif defined(CONFIG_SRCU) #error "Unknown SRCU implementation specified to kernel configuration" +#else +/* Dummy definition for things like notifiers. Actual use gets link error. */ +struct srcu_struct { }; #endif -/** - * call_srcu() - Queue a callback for invocation after an SRCU grace period - * @sp: srcu_struct in queue the callback - * @head: structure to be used for queueing the SRCU callback. - * @func: function to be invoked after the SRCU grace period - * - * The callback function will be invoked some time after a full SRCU - * grace period elapses, in other words after all pre-existing SRCU - * read-side critical sections have completed. However, the callback - * function might well execute concurrently with other SRCU read-side - * critical sections that started after call_srcu() was invoked. SRCU - * read-side critical sections are delimited by srcu_read_lock() and - * srcu_read_unlock(), and may be nested. - * - * The callback will be invoked from process context, but must nevertheless - * be fast and must not block. - */ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, void (*func)(struct rcu_head *head)); - void cleanup_srcu_struct(struct srcu_struct *sp); int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); diff --git a/include/linux/srcuclassic.h b/include/linux/srcuclassic.h deleted file mode 100644 index 5753f7322262..000000000000 --- a/include/linux/srcuclassic.h +++ /dev/null @@ -1,115 +0,0 @@ -/* - * Sleepable Read-Copy Update mechanism for mutual exclusion, - * classic v4.11 variant. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, you can access it online at - * http://www.gnu.org/licenses/gpl-2.0.html. - * - * Copyright (C) IBM Corporation, 2017 - * - * Author: Paul McKenney <paulmck@us.ibm.com> - */ - -#ifndef _LINUX_SRCU_CLASSIC_H -#define _LINUX_SRCU_CLASSIC_H - -struct srcu_array { - unsigned long lock_count[2]; - unsigned long unlock_count[2]; -}; - -struct rcu_batch { - struct rcu_head *head, **tail; -}; - -#define RCU_BATCH_INIT(name) { NULL, &(name.head) } - -struct srcu_struct { - unsigned long completed; - struct srcu_array __percpu *per_cpu_ref; - spinlock_t queue_lock; /* protect ->batch_queue, ->running */ - bool running; - /* callbacks just queued */ - struct rcu_batch batch_queue; - /* callbacks try to do the first check_zero */ - struct rcu_batch batch_check0; - /* callbacks done with the first check_zero and the flip */ - struct rcu_batch batch_check1; - struct rcu_batch batch_done; - struct delayed_work work; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -}; - -void process_srcu(struct work_struct *work); - -#define __SRCU_STRUCT_INIT(name) \ - { \ - .completed = -300, \ - .per_cpu_ref = &name##_srcu_array, \ - .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ - .running = false, \ - .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ - .batch_check0 = RCU_BATCH_INIT(name.batch_check0), \ - .batch_check1 = RCU_BATCH_INIT(name.batch_check1), \ - .batch_done = RCU_BATCH_INIT(name.batch_done), \ - .work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\ - __SRCU_DEP_MAP_INIT(name) \ - } - -/* - * Define and initialize a srcu struct at build time. - * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it. - * - * Note that although DEFINE_STATIC_SRCU() hides the name from other - * files, the per-CPU variable rules nevertheless require that the - * chosen name be globally unique. These rules also prohibit use of - * DEFINE_STATIC_SRCU() within a function. If these rules are too - * restrictive, declare the srcu_struct manually. For example, in - * each file: - * - * static struct srcu_struct my_srcu; - * - * Then, before the first use of each my_srcu, manually initialize it: - * - * init_srcu_struct(&my_srcu); - * - * See include/linux/percpu-defs.h for the rules on per-CPU variables. - */ -#define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\ - is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) -#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) -#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) - -void synchronize_srcu_expedited(struct srcu_struct *sp); -void srcu_barrier(struct srcu_struct *sp); -unsigned long srcu_batches_completed(struct srcu_struct *sp); - -static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, - unsigned long *gpnum, - unsigned long *completed) -{ - if (test_type != SRCU_FLAVOR) - return; - *flags = 0; - *completed = sp->completed; - *gpnum = *completed; - if (sp->batch_queue.head || sp->batch_check0.head || sp->batch_check0.head) - (*gpnum)++; -} - -#endif diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 42311ee0334f..261471f407a5 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -27,15 +27,14 @@ #include <linux/swait.h> struct srcu_struct { - int srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ + short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ + short srcu_idx; /* Current reader array element. */ + u8 srcu_gp_running; /* GP workqueue running? */ + u8 srcu_gp_waiting; /* GP waiting for readers? */ struct swait_queue_head srcu_wq; /* Last srcu_read_unlock() wakes GP. */ - unsigned long srcu_gp_seq; /* GP seq # for callback tagging. */ - struct rcu_segcblist srcu_cblist; - /* Pending SRCU callbacks. */ - int srcu_idx; /* Current reader array element. */ - bool srcu_gp_running; /* GP workqueue running? */ - bool srcu_gp_waiting; /* GP waiting for readers? */ + struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ + struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -47,7 +46,7 @@ void srcu_drive_gp(struct work_struct *wp); #define __SRCU_STRUCT_INIT(name) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ - .srcu_cblist = RCU_SEGCBLIST_INITIALIZER(name.srcu_cblist), \ + .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ __SRCU_DEP_MAP_INIT(name) \ } @@ -63,6 +62,21 @@ void srcu_drive_gp(struct work_struct *wp); void synchronize_srcu(struct srcu_struct *sp); +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Can be invoked from irq/bh handlers, but the matching + * __srcu_read_unlock() must be in the same handler instance. Returns an + * index that must be passed to the matching srcu_read_unlock(). + */ +static inline int __srcu_read_lock(struct srcu_struct *sp) +{ + int idx; + + idx = READ_ONCE(sp->srcu_idx); + WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1); + return idx; +} + static inline void synchronize_srcu_expedited(struct srcu_struct *sp) { synchronize_srcu(sp); @@ -73,21 +87,17 @@ static inline void srcu_barrier(struct srcu_struct *sp) synchronize_srcu(sp); } -static inline unsigned long srcu_batches_completed(struct srcu_struct *sp) +/* Defined here to avoid size increase for non-torture kernels. */ +static inline void srcu_torture_stats_print(struct srcu_struct *sp, + char *tt, char *tf) { - return 0; -} + int idx; -static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, - unsigned long *gpnum, - unsigned long *completed) -{ - if (test_type != SRCU_FLAVOR) - return; - *flags = 0; - *completed = sp->srcu_gp_seq; - *gpnum = *completed; + idx = READ_ONCE(sp->srcu_idx) & 0x1; + pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", + tt, tf, idx, + READ_ONCE(sp->srcu_lock_nesting[!idx]), + READ_ONCE(sp->srcu_lock_nesting[idx])); } #endif diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 32e86d85fd11..a949f4f9e4d7 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -40,7 +40,7 @@ struct srcu_data { unsigned long srcu_unlock_count[2]; /* Unlocks per CPU. */ /* Update-side state. */ - spinlock_t lock ____cacheline_internodealigned_in_smp; + raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp; struct rcu_segcblist srcu_cblist; /* List of callbacks.*/ unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ @@ -58,7 +58,7 @@ struct srcu_data { * Node in SRCU combining tree, similar in function to rcu_data. */ struct srcu_node { - spinlock_t lock; + raw_spinlock_t __private lock; unsigned long srcu_have_cbs[4]; /* GP seq for children */ /* having CBs, but only */ /* is > ->srcu_gq_seq. */ @@ -78,7 +78,7 @@ struct srcu_struct { struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t gp_lock; /* protect ->srcu_cblist */ + raw_spinlock_t __private lock; /* Protect counters */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ @@ -104,12 +104,10 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -void process_srcu(struct work_struct *work); - #define __SRCU_STRUCT_INIT(name) \ { \ .sda = &name##_srcu_data, \ - .gp_lock = __SPIN_LOCK_UNLOCKED(name.gp_lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = 0 - 1, \ __SRCU_DEP_MAP_INIT(name) \ } @@ -141,10 +139,6 @@ void process_srcu(struct work_struct *work); void synchronize_srcu_expedited(struct srcu_struct *sp); void srcu_barrier(struct srcu_struct *sp); -unsigned long srcu_batches_completed(struct srcu_struct *sp); - -void srcutorture_get_gp_data(enum rcutorture_type test_type, - struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed); +void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf); #endif diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 3921cb9dfadb..108739ff9223 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -177,6 +177,7 @@ struct plat_stmmacenet_data { void (*fix_mac_speed)(void *priv, unsigned int speed); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); + struct mac_device_info *(*setup)(void *priv); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; @@ -185,6 +186,7 @@ struct plat_stmmacenet_data { struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; + bool has_sun8i; bool tso_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 3cc9632dcc2a..3d60275e3ba9 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -116,15 +116,29 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * @fn() runs. * * This can be thought of as a very heavy write lock, equivalent to - * grabbing every spinlock in the kernel. */ + * grabbing every spinlock in the kernel. + * + * Protects against CPU hotplug. + */ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +/** + * stop_machine_cpuslocked: freeze the machine on all CPUs and run this function + * @fn: the function to run + * @data: the data ptr for the @fn() + * @cpus: the cpus to run the @fn() on (NULL = any online cpu) + * + * Same as above. Must be called from with in a cpus_read_lock() protected + * region. Avoids nested calls to cpus_read_lock(). + */ +int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); + int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -static inline int stop_machine(cpu_stop_fn_t fn, void *data, - const struct cpumask *cpus) +static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, + const struct cpumask *cpus) { unsigned long flags; int ret; @@ -134,6 +148,12 @@ static inline int stop_machine(cpu_stop_fn_t fn, void *data, return ret; } +static inline int stop_machine(cpu_stop_fn_t fn, void *data, + const struct cpumask *cpus) +{ + return stop_machine_cpuslocked(fn, data, cpus); +} + static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { diff --git a/include/linux/string.h b/include/linux/string.h index 537918f8a98e..54d21783e18d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -99,6 +99,36 @@ extern __kernel_size_t strcspn(const char *,const char *); #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif + +#ifndef __HAVE_ARCH_MEMSET16 +extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); +#endif + +static inline void *memset_l(unsigned long *p, unsigned long v, + __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, v, n); + else + return memset64((uint64_t *)p, v, n); +} + +static inline void *memset_p(void **p, void *v, __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, (uintptr_t)v, n); + else + return memset64((uint64_t *)p, (uintptr_t)v, n); +} + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif @@ -122,6 +152,12 @@ static inline __must_check int memcpy_mcsafe(void *dst, const void *src, return 0; } #endif +#ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE +static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) +{ + memcpy(dst, src, cnt); +} +#endif void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *s, char old, char new); @@ -131,6 +167,7 @@ extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); +extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); @@ -187,4 +224,224 @@ static inline const char *kbasename(const char *path) return tail ? tail + 1 : path; } +#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#define __RENAME(x) __asm__(#x) + +void fortify_panic(const char *name) __noreturn __cold; +void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); +void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); +void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); +void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); + +#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 0); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __builtin_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __builtin_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} + +/* defined after fortified strlen and memcpy to reuse them */ +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strcpy(p, q); + memcpy(p, q, strlen(q) + 1); + return p; +} + +#endif + +/** + * memcpy_and_pad - Copy one buffer to another with padding + * @dest: Where to copy to + * @dest_len: The destination buffer size + * @src: Where to copy from + * @count: The number of bytes to copy + * @pad: Character to use for padding if space is left in destination. + */ +static inline void memcpy_and_pad(void *dest, size_t dest_len, + const void *src, size_t count, int pad) +{ + if (dest_len > count) { + memcpy(dest, src, count); + memset(dest + count, pad, dest_len - count); + } else + memcpy(dest, src, dest_len); +} + #endif /* _LINUX_STRING_H_ */ diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 36eebc451b41..cebdf8745901 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -13,6 +13,7 @@ #define _LINUX_SUNRPC_AUTH_GSS_H #ifdef __KERNEL__ +#include <linux/refcount.h> #include <linux/sunrpc/auth.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/gss_api.h> @@ -65,7 +66,7 @@ struct rpc_gss_init_res { * the wire when communicating with a server. */ struct gss_cl_ctx { - atomic_t count; + refcount_t count; enum rpc_gss_proc gc_proc; u32 gc_seq; spinlock_t gc_seq_lock; diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 6095ecba0dde..55ef67bea06b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -39,7 +39,7 @@ struct rpc_clnt { struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ - struct rpc_procinfo * cl_procinfo; /* procedure info */ + const struct rpc_procinfo *cl_procinfo; /* procedure info */ u32 cl_prog, /* RPC program number */ cl_vers, /* RPC version number */ cl_maxproc; /* max procedure number */ @@ -87,7 +87,8 @@ struct rpc_program { struct rpc_version { u32 number; /* version number */ unsigned int nrprocs; /* number of procs */ - struct rpc_procinfo * procs; /* procedure array */ + const struct rpc_procinfo *procs; /* procedure array */ + unsigned int *counts; /* call counts */ }; /* @@ -99,7 +100,6 @@ struct rpc_procinfo { kxdrdproc_t p_decode; /* XDR decode function */ unsigned int p_arglen; /* argument hdr length (u32) */ unsigned int p_replen; /* reply hdr length (u32) */ - unsigned int p_count; /* call count */ unsigned int p_timer; /* Which RTT timer to use */ u32 p_statidx; /* Which procedure to account */ const char * p_name; /* name of procedure */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 7ba040c797ec..c1768f9d993b 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -13,7 +13,7 @@ #include <linux/ktime.h> #include <linux/sunrpc/types.h> #include <linux/spinlock.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/workqueue.h> #include <linux/sunrpc/xdr.h> @@ -22,7 +22,7 @@ */ struct rpc_procinfo; struct rpc_message { - struct rpc_procinfo * rpc_proc; /* Procedure information */ + const struct rpc_procinfo *rpc_proc; /* Procedure information */ void * rpc_argp; /* Arguments */ void * rpc_resp; /* Result */ struct rpc_cred * rpc_cred; /* Credentials */ @@ -139,6 +139,8 @@ struct rpc_task_setup { #define RPC_TASK_RUNNING 0 #define RPC_TASK_QUEUED 1 #define RPC_TASK_ACTIVE 2 +#define RPC_TASK_MSG_RECV 3 +#define RPC_TASK_MSG_RECV_WAIT 4 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 11cef5a7bc87..38f561b2dda3 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -99,7 +99,7 @@ struct svc_serv { unsigned int sv_nrpools; /* number of thread pools */ struct svc_pool * sv_pools; /* array of thread pools */ - struct svc_serv_ops *sv_ops; /* server operations */ + const struct svc_serv_ops *sv_ops; /* server operations */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same @@ -237,7 +237,7 @@ struct svc_rqst { struct svc_serv * rq_server; /* RPC service definition */ struct svc_pool * rq_pool; /* thread pool */ - struct svc_procedure * rq_procinfo; /* procedure info */ + const struct svc_procedure *rq_procinfo;/* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ @@ -246,7 +246,7 @@ struct svc_rqst { size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; struct xdr_buf rq_res; - struct page * rq_pages[RPCSVC_MAXPAGES]; + struct page *rq_pages[RPCSVC_MAXPAGES + 1]; struct page * *rq_respages; /* points into rq_pages */ struct page * *rq_next_page; /* next reply page to use */ struct page * *rq_page_end; /* one past the last page */ @@ -384,7 +384,7 @@ struct svc_program { unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ unsigned int pg_nvers; /* number of versions */ - struct svc_version ** pg_vers; /* version array */ + const struct svc_version **pg_vers; /* version array */ char * pg_name; /* service name */ char * pg_class; /* class name: services sharing authentication */ struct svc_stat * pg_stats; /* rpc statistics */ @@ -397,7 +397,8 @@ struct svc_program { struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ - struct svc_procedure * vs_proc; /* per-procedure info */ + const struct svc_procedure *vs_proc; /* per-procedure info */ + unsigned int *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ /* Don't register with rpcbind */ @@ -419,15 +420,17 @@ struct svc_version { /* * RPC procedure info */ -typedef __be32 (*svc_procfunc)(struct svc_rqst *, void *argp, void *resp); struct svc_procedure { - svc_procfunc pc_func; /* process the request */ - kxdrproc_t pc_decode; /* XDR decode args */ - kxdrproc_t pc_encode; /* XDR encode result */ - kxdrproc_t pc_release; /* XDR free result */ + /* process the request: */ + __be32 (*pc_func)(struct svc_rqst *); + /* XDR decode args: */ + int (*pc_decode)(struct svc_rqst *, __be32 *data); + /* XDR encode result: */ + int (*pc_encode)(struct svc_rqst *, __be32 *data); + /* XDR free result: */ + void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ unsigned int pc_ressize; /* result struct size */ - unsigned int pc_count; /* call count */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ }; @@ -462,7 +465,7 @@ int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, - struct svc_serv_ops *); + const struct svc_serv_ops *); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, @@ -472,7 +475,7 @@ void svc_exit_thread(struct svc_rqst *); unsigned int svc_pool_map_get(void); void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - struct svc_serv_ops *); + const struct svc_serv_ops *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index f3787d800ba4..995c6fe9ee90 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -77,46 +77,25 @@ extern atomic_t rdma_stat_sq_prod; */ struct svc_rdma_op_ctxt { struct list_head list; - struct svc_rdma_op_ctxt *read_hdr; - struct svc_rdma_fastreg_mr *frmr; - int hdr_count; struct xdr_buf arg; struct ib_cqe cqe; - struct ib_cqe reg_cqe; - struct ib_cqe inv_cqe; u32 byte_len; - u32 position; struct svcxprt_rdma *xprt; - unsigned long flags; enum dma_data_direction direction; int count; unsigned int mapped_sges; + int hdr_count; struct ib_send_wr send_wr; struct ib_sge sge[1 + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE]; struct page *pages[RPCSVC_MAXPAGES]; }; -struct svc_rdma_fastreg_mr { - struct ib_mr *mr; - struct scatterlist *sg; - int sg_nents; - unsigned long access_flags; - enum dma_data_direction direction; - struct list_head frmr_list; -}; - -#define RDMACTXT_F_LAST_CTXT 2 - -#define SVCRDMA_DEVCAP_FAST_REG 1 /* fast mr registration */ -#define SVCRDMA_DEVCAP_READ_W_INV 2 /* read w/ invalidate */ - struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ int sc_max_sge; - int sc_max_sge_rd; /* max sge for read target */ bool sc_snd_w_inv; /* OK to use Send With Invalidate */ atomic_t sc_sq_avail; /* SQEs ready to be consumed */ @@ -141,14 +120,6 @@ struct svcxprt_rdma { struct ib_qp *sc_qp; struct ib_cq *sc_rq_cq; struct ib_cq *sc_sq_cq; - int (*sc_reader)(struct svcxprt_rdma *, - struct svc_rqst *, - struct svc_rdma_op_ctxt *, - int *, u32 *, u32, u32, u64, bool); - u32 sc_dev_caps; /* distilled device caps */ - unsigned int sc_frmr_pg_list_len; - struct list_head sc_frmr_q; - spinlock_t sc_frmr_q_lock; spinlock_t sc_lock; /* transport lock */ @@ -185,20 +156,14 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, struct xdr_buf *rcvbuf); -/* svc_rdma_marshal.c */ -extern int svc_rdma_xdr_decode_req(struct xdr_buf *); - /* svc_rdma_recvfrom.c */ extern int svc_rdma_recvfrom(struct svc_rqst *); -extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); -extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); /* svc_rdma_rw.c */ extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma); +extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, + struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, __be32 *p); extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, struct xdr_buf *xdr); extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, @@ -226,9 +191,6 @@ extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt); -extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *); -extern void svc_rdma_put_frmr(struct svcxprt_rdma *, - struct svc_rdma_fastreg_mr *); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); extern void svc_rdma_prep_reply_hdr(struct svc_rqst *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index ddb7f94a9d06..6a2ad38f5458 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -31,7 +31,7 @@ struct svc_xprt_ops { struct svc_xprt_class { const char *xcl_name; struct module *xcl_owner; - struct svc_xprt_ops *xcl_ops; + const struct svc_xprt_ops *xcl_ops; struct list_head xcl_list; u32 xcl_max_payload; int xcl_ident; @@ -49,7 +49,7 @@ struct svc_xpt_user { struct svc_xprt { struct svc_xprt_class *xpt_class; - struct svc_xprt_ops *xpt_ops; + const struct svc_xprt_ops *xpt_ops; struct kref xpt_ref; struct list_head xpt_list; struct list_head xpt_ready; diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 054c8cde18f3..86b59e3525a5 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -17,6 +17,8 @@ #include <asm/unaligned.h> #include <linux/scatterlist.h> +struct rpc_rqst; + /* * Buffer adjustment */ @@ -33,13 +35,6 @@ struct xdr_netobj { }; /* - * This is the legacy generic XDR function. rqstp is either a rpc_rqst - * (client side) or svc_rqst pointer (server side). - * Encode functions always assume there's enough room in the buffer. - */ -typedef int (*kxdrproc_t)(void *rqstp, __be32 *data, void *obj); - -/* * Basic structure for transmission/reception of a client XDR message. * Features a header (for a linear buffer containing RPC headers * and the data payload for short messages), and then an array of @@ -222,8 +217,10 @@ struct xdr_stream { /* * These are the xdr_stream style generic XDR encode and decode functions. */ -typedef void (*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); -typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj); +typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); @@ -242,6 +239,19 @@ extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); +/** + * xdr_stream_remaining - Return the number of bytes remaining in the stream + * @xdr: pointer to struct xdr_stream + * + * Return value: + * Number of bytes remaining in @xdr before xdr->end + */ +static inline size_t +xdr_stream_remaining(const struct xdr_stream *xdr) +{ + return xdr->nwords << 2; +} + ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); /** diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index eab1c749e192..5a7bff41f6b7 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -174,7 +174,7 @@ enum xprt_transports { struct rpc_xprt { struct kref kref; /* Reference count */ - struct rpc_xprt_ops * ops; /* transport methods */ + const struct rpc_xprt_ops *ops; /* transport methods */ const struct rpc_timeout *timeout; /* timeout parms */ struct sockaddr_storage addr; /* server address */ @@ -232,6 +232,7 @@ struct rpc_xprt { */ spinlock_t transport_lock; /* lock transport info */ spinlock_t reserve_lock; /* lock slot table */ + spinlock_t recv_lock; /* lock receive list */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ @@ -372,6 +373,8 @@ void xprt_write_space(struct rpc_xprt *xprt); void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_rqst(struct rpc_task *task, int copied); +void xprt_pin_rqst(struct rpc_rqst *req); +void xprt_unpin_rqst(struct rpc_rqst *req); void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); diff --git a/include/linux/superhyway.h b/include/linux/superhyway.h index 17ea468fa362..8d3376775813 100644 --- a/include/linux/superhyway.h +++ b/include/linux/superhyway.h @@ -101,7 +101,7 @@ int superhyway_add_device(unsigned long base, struct superhyway_device *, struct int superhyway_add_devices(struct superhyway_bus *bus, struct superhyway_device **devices, int nr_devices); /* drivers/sh/superhyway/superhyway-sysfs.c */ -extern struct device_attribute superhyway_dev_attrs[]; +extern const struct attribute_group *superhyway_dev_groups[]; #endif /* __LINUX_SUPERHYWAY_H */ diff --git a/include/linux/suspend.h b/include/linux/suspend.h index d9718378a8be..d10b7980799d 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -33,10 +33,10 @@ static inline void pm_restore_console(void) typedef int __bitwise suspend_state_t; #define PM_SUSPEND_ON ((__force suspend_state_t) 0) -#define PM_SUSPEND_FREEZE ((__force suspend_state_t) 1) +#define PM_SUSPEND_TO_IDLE ((__force suspend_state_t) 1) #define PM_SUSPEND_STANDBY ((__force suspend_state_t) 2) #define PM_SUSPEND_MEM ((__force suspend_state_t) 3) -#define PM_SUSPEND_MIN PM_SUSPEND_FREEZE +#define PM_SUSPEND_MIN PM_SUSPEND_TO_IDLE #define PM_SUSPEND_MAX ((__force suspend_state_t) 4) enum suspend_stat_step { @@ -186,14 +186,19 @@ struct platform_suspend_ops { void (*recover)(void); }; -struct platform_freeze_ops { +struct platform_s2idle_ops { int (*begin)(void); int (*prepare)(void); + void (*wake)(void); + void (*sync)(void); void (*restore)(void); void (*end)(void); }; #ifdef CONFIG_SUSPEND +extern suspend_state_t mem_sleep_current; +extern suspend_state_t mem_sleep_default; + /** * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. @@ -232,22 +237,22 @@ static inline bool pm_resume_via_firmware(void) } /* Suspend-to-idle state machnine. */ -enum freeze_state { - FREEZE_STATE_NONE, /* Not suspended/suspending. */ - FREEZE_STATE_ENTER, /* Enter suspend-to-idle. */ - FREEZE_STATE_WAKE, /* Wake up from suspend-to-idle. */ +enum s2idle_states { + S2IDLE_STATE_NONE, /* Not suspended/suspending. */ + S2IDLE_STATE_ENTER, /* Enter suspend-to-idle. */ + S2IDLE_STATE_WAKE, /* Wake up from suspend-to-idle. */ }; -extern enum freeze_state __read_mostly suspend_freeze_state; +extern enum s2idle_states __read_mostly s2idle_state; -static inline bool idle_should_freeze(void) +static inline bool idle_should_enter_s2idle(void) { - return unlikely(suspend_freeze_state == FREEZE_STATE_ENTER); + return unlikely(s2idle_state == S2IDLE_STATE_ENTER); } extern void __init pm_states_init(void); -extern void freeze_set_ops(const struct platform_freeze_ops *ops); -extern void freeze_wake(void); +extern void s2idle_set_ops(const struct platform_s2idle_ops *ops); +extern void s2idle_wake(void); /** * arch_suspend_disable_irqs - disable IRQs for suspend @@ -279,10 +284,10 @@ static inline bool pm_resume_via_firmware(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } -static inline bool idle_should_freeze(void) { return false; } +static inline bool idle_should_enter_s2idle(void) { return false; } static inline void __init pm_states_init(void) {} -static inline void freeze_set_ops(const struct platform_freeze_ops *ops) {} -static inline void freeze_wake(void) {} +static inline void s2idle_set_ops(const struct platform_s2idle_ops *ops) {} +static inline void s2idle_wake(void) {} #endif /* !CONFIG_SUSPEND */ /* struct pbe is used for creating lists of pages that should be restored @@ -425,10 +430,12 @@ extern int unregister_pm_notifier(struct notifier_block *nb); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; extern unsigned int pm_wakeup_irq; +extern suspend_state_t pm_suspend_target_state; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); -extern void pm_wakeup_clear(void); +extern void pm_system_cancel_wakeup(void); +extern void pm_wakeup_clear(bool reset); extern void pm_system_irq_wakeup(unsigned int irq_number); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); @@ -478,7 +485,7 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) static inline bool pm_wakeup_pending(void) { return false; } static inline void pm_system_wakeup(void) {} -static inline void pm_wakeup_clear(void) {} +static inline void pm_wakeup_clear(bool reset) {} static inline void pm_system_irq_wakeup(unsigned int irq_number) {} static inline void lock_system_sleep(void) {} @@ -488,10 +495,24 @@ static inline void unlock_system_sleep(void) {} #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; +extern bool pm_debug_messages_on; +extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...); #else #define pm_print_times_enabled (false) +#define pm_debug_messages_on (false) + +#include <linux/printk.h> + +#define __pm_pr_dbg(defer, fmt, ...) \ + no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) #endif +#define pm_pr_dbg(fmt, ...) \ + __pm_pr_dbg(false, fmt, ##__VA_ARGS__) + +#define pm_deferred_pr_dbg(fmt, ...) \ + __pm_pr_dbg(true, fmt, ##__VA_ARGS__) + #ifdef CONFIG_PM_AUTOSLEEP /* kernel/power/autosleep.c */ diff --git a/include/linux/swait.h b/include/linux/swait.h index c1f9c62a8a50..73e97a08d3d0 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -79,9 +79,63 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name DECLARE_SWAIT_QUEUE_HEAD(name) #endif -static inline int swait_active(struct swait_queue_head *q) +/** + * swait_active -- locklessly test for waiters on the queue + * @wq: the waitqueue to test for waiters + * + * returns true if the wait list is not empty + * + * NOTE: this function is lockless and requires care, incorrect usage _will_ + * lead to sporadic and non-obvious failure. + * + * NOTE2: this function has the same above implications as regular waitqueues. + * + * Use either while holding swait_queue_head::lock or when used for wakeups + * with an extra smp_mb() like: + * + * CPU0 - waker CPU1 - waiter + * + * for (;;) { + * @cond = true; prepare_to_swait(&wq_head, &wait, state); + * smp_mb(); // smp_mb() from set_current_state() + * if (swait_active(wq_head)) if (@cond) + * wake_up(wq_head); break; + * schedule(); + * } + * finish_swait(&wq_head, &wait); + * + * Because without the explicit smp_mb() it's possible for the + * swait_active() load to get hoisted over the @cond store such that we'll + * observe an empty wait list while the waiter might not observe @cond. + * This, in turn, can trigger missing wakeups. + * + * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), + * which (when the lock is uncontended) are of roughly equal cost. + */ +static inline int swait_active(struct swait_queue_head *wq) { - return !list_empty(&q->task_list); + return !list_empty(&wq->task_list); +} + +/** + * swq_has_sleeper - check if there are any waiting processes + * @wq: the waitqueue to test for waiters + * + * Returns true if @wq has waiting processes + * + * Please refer to the comment for swait_active. + */ +static inline bool swq_has_sleeper(struct swait_queue_head *wq) +{ + /* + * We need to be sure we are in sync with the list_add() + * modifications to the wait queue (task_list). + * + * This memory barrier should be paired with one on the + * waiting side. + */ + smp_mb(); + return swait_active(wq); } extern void swake_up(struct swait_queue_head *q); @@ -169,4 +223,59 @@ do { \ __ret; \ }) +#define __swait_event_idle(wq, condition) \ + (void)___swait_event(wq, condition, TASK_IDLE, 0, schedule()) + +/** + * swait_event_idle - wait without system load contribution + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * + * The process is put to sleep (TASK_IDLE) until the @condition evaluates to + * true. The @condition is checked each time the waitqueue @wq is woken up. + * + * This function is mostly used when a kthread or workqueue waits for some + * condition and doesn't want to contribute to system load. Signals are + * ignored. + */ +#define swait_event_idle(wq, condition) \ +do { \ + if (condition) \ + break; \ + __swait_event_idle(wq, condition); \ +} while (0) + +#define __swait_event_idle_timeout(wq, condition, timeout) \ + ___swait_event(wq, ___wait_cond_timeout(condition), \ + TASK_IDLE, timeout, \ + __ret = schedule_timeout(__ret)) + +/** + * swait_event_idle_timeout - wait up to timeout without load contribution + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout at which we'll give up in jiffies + * + * The process is put to sleep (TASK_IDLE) until the @condition evaluates to + * true. The @condition is checked each time the waitqueue @wq is woken up. + * + * This function is mostly used when a kthread or workqueue waits for some + * condition and doesn't want to contribute to system load. Signals are + * ignored. + * + * Returns: + * 0 if the @condition evaluated to %false after the @timeout elapsed, + * 1 if the @condition evaluated to %true after the @timeout elapsed, + * or the remaining jiffies (at least 1) if the @condition evaluated + * to %true before the @timeout elapsed. + */ +#define swait_event_idle_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __swait_event_idle_timeout(wq, \ + condition, timeout); \ + __ret; \ +}) + #endif /* _LINUX_SWAIT_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index ba5882419a7d..8a807292037f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -51,6 +51,23 @@ static inline int current_is_kswapd(void) */ /* + * Unaddressable device memory support. See include/linux/hmm.h and + * Documentation/vm/hmm.txt. Short description is we need struct pages for + * device memory that is unaddressable (inaccessible) by CPU, so that we can + * migrate part of a process memory to device memory. + * + * When a page is migrated from CPU to device, we set the CPU page table entry + * to a special SWP_DEVICE_* entry. + */ +#ifdef CONFIG_DEVICE_PRIVATE +#define SWP_DEVICE_NUM 2 +#define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) +#define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) +#else +#define SWP_DEVICE_NUM 0 +#endif + +/* * NUMA node memory migration support */ #ifdef CONFIG_MIGRATION @@ -72,7 +89,8 @@ static inline int current_is_kswapd(void) #endif #define MAX_SWAPFILES \ - ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) /* * Magic header for a swap area. The first part of the union is @@ -188,6 +206,7 @@ struct swap_cluster_info { }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ +#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from @@ -211,7 +230,7 @@ struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ - struct plist_node avail_list; /* entry in swap_avail_head */ + struct plist_node avail_lists[MAX_NUMNODES];/* entry in swap_avail_heads */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ @@ -250,6 +269,25 @@ struct swap_info_struct { struct swap_cluster_list discard_clusters; /* discard clusters list */ }; +#ifdef CONFIG_64BIT +#define SWAP_RA_ORDER_CEILING 5 +#else +/* Avoid stack overflow, because we need to save part of page table */ +#define SWAP_RA_ORDER_CEILING 3 +#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) +#endif + +struct vma_swap_readahead { + unsigned short win; + unsigned short offset; + unsigned short nr_pte; +#ifdef CONFIG_64BIT + pte_t *ptes; +#else + pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; +#endif +}; + /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); @@ -262,8 +300,8 @@ extern unsigned long totalreserve_pages; extern unsigned long nr_free_buffer_pages(void); extern unsigned long nr_free_pagecache_pages(void); -/* Definition of global_page_state not available yet */ -#define nr_free_pages() global_page_state(NR_FREE_PAGES) +/* Definition of global_zone_page_state not available yet */ +#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ @@ -277,6 +315,7 @@ extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); +extern void lru_add_drain_all_cpuslocked(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); extern void mark_page_lazyfree(struct page *page); @@ -331,7 +370,7 @@ extern void kswapd_stop(int nid); #include <linux/blk_types.h> /* for bio_end_io_t */ /* linux/mm/page_io.c */ -extern int swap_readpage(struct page *); +extern int swap_readpage(struct page *page, bool do_poll); extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, @@ -348,32 +387,48 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, #define SWAP_ADDRESS_SPACE_SHIFT 14 #define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) extern struct address_space *swapper_spaces[]; +extern bool swap_vma_readahead; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *, struct list_head *list); +extern int add_to_swap(struct page *page); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); extern void __delete_from_swap_cache(struct page *); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t); +extern struct page *lookup_swap_cache(swp_entry_t entry, + struct vm_area_struct *vma, + unsigned long addr); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr); + struct vm_area_struct *vma, unsigned long addr, + bool do_poll); extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated); extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); +extern struct page *swap_readahead_detect(struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); +extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); + /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; +extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); +static inline bool swap_use_vma_readahead(void) +{ + return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap); +} + /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { @@ -386,15 +441,15 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(void); +extern swp_entry_t get_swap_page(struct page *page); +extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); -extern int get_swap_pages(int n, swp_entry_t swp_entries[]); +extern int get_swap_pages(int n, bool cluster, swp_entry_t swp_entries[]); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); -extern void swapcache_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern int free_swap_and_cache(swp_entry_t); extern int swap_type_of(dev_t, sector_t, struct block_device **); @@ -432,8 +487,8 @@ static inline void show_swap_cache_info(void) { } -#define free_swap_and_cache(swp) is_migration_entry(swp) -#define swapcache_prepare(swp) is_migration_entry(swp) +#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) +#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { @@ -453,7 +508,7 @@ static inline void swap_free(swp_entry_t swp) { } -static inline void swapcache_free(swp_entry_t swp) +static inline void put_swap_page(struct page *page, swp_entry_t swp) { } @@ -463,17 +518,37 @@ static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, return NULL; } +static inline bool swap_use_vma_readahead(void) +{ + return false; +} + +static inline struct page *swap_readahead_detect( + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + +static inline struct page *do_swap_page_readahead( + swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + static inline int swap_writepage(struct page *p, struct writeback_control *wbc) { return 0; } -static inline struct page *lookup_swap_cache(swp_entry_t swp) +static inline struct page *lookup_swap_cache(swp_entry_t swp, + struct vm_area_struct *vma, + unsigned long addr) { return NULL; } -static inline int add_to_swap(struct page *page, struct list_head *list) +static inline int add_to_swap(struct page *page) { return 0; } @@ -507,15 +582,15 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_mapcount) \ - (page_trans_huge_mapcount(page, total_mapcount) == 1) +#define reuse_swap_page(page, total_map_swapcount) \ + (page_trans_huge_mapcount(page, total_map_swapcount) == 1) static inline int try_to_free_swap(struct page *page) { return 0; } -static inline swp_entry_t get_swap_page(void) +static inline swp_entry_t get_swap_page(struct page *page) { swp_entry_t entry; entry.val = 0; @@ -524,6 +599,15 @@ static inline swp_entry_t get_swap_page(void) #endif /* CONFIG_SWAP */ +#ifdef CONFIG_THP_SWAP +extern int split_swap_cluster(swp_entry_t entry); +#else +static inline int split_swap_cluster(swp_entry_t entry) +{ + return 0; +} +#endif + #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { @@ -548,7 +632,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) #ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -extern void mem_cgroup_uncharge_swap(swp_entry_t entry); +extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct page *page); #else @@ -562,7 +646,8 @@ static inline int mem_cgroup_try_charge_swap(struct page *page, return 0; } -static inline void mem_cgroup_uncharge_swap(swp_entry_t entry) +static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, + unsigned int nr_pages) { } diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index 145306bdc92f..b2b8ec7bda3f 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -7,7 +7,8 @@ extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, unsigned short old, unsigned short new); -extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id); +extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, + unsigned int nr_ents); extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent); extern int swap_cgroup_swapon(int type, unsigned long max_pages); extern void swap_cgroup_swapoff(int type); @@ -15,7 +16,8 @@ extern void swap_cgroup_swapoff(int type); #else static inline -unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, + unsigned int nr_ents) { return 0; } diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5c3a5f3e7eec..291c4b534658 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -100,10 +100,79 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); } +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) +static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +{ + return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, + page_to_pfn(page)); +} + +static inline bool is_device_private_entry(swp_entry_t entry) +{ + int type = swp_type(entry); + return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; +} + +static inline void make_device_private_entry_read(swp_entry_t *entry) +{ + *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); +} + +static inline bool is_write_device_private_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); +} + +static inline struct page *device_private_entry_to_page(swp_entry_t entry) +{ + return pfn_to_page(swp_offset(entry)); +} + +int device_private_entry_fault(struct vm_area_struct *vma, + unsigned long addr, + swp_entry_t entry, + unsigned int flags, + pmd_t *pmdp); +#else /* CONFIG_DEVICE_PRIVATE */ +static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +{ + return swp_entry(0, 0); +} + +static inline void make_device_private_entry_read(swp_entry_t *entry) +{ +} + +static inline bool is_device_private_entry(swp_entry_t entry) +{ + return false; +} + +static inline bool is_write_device_private_entry(swp_entry_t entry) +{ + return false; +} + +static inline struct page *device_private_entry_to_page(swp_entry_t entry) +{ + return NULL; +} + +static inline int device_private_entry_fault(struct vm_area_struct *vma, + unsigned long addr, + swp_entry_t entry, + unsigned int flags, + pmd_t *pmdp) +{ + return VM_FAULT_SIGBUS; +} +#endif /* CONFIG_DEVICE_PRIVATE */ + #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { - BUG_ON(!PageLocked(page)); + BUG_ON(!PageLocked(compound_head(page))); + return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ, page_to_pfn(page)); } @@ -126,7 +195,7 @@ static inline struct page *migration_entry_to_page(swp_entry_t entry) * Any use of migration entries may only occur while the * corresponding page is locked */ - BUG_ON(!PageLocked(p)); + BUG_ON(!PageLocked(compound_head(p))); return p; } @@ -148,7 +217,11 @@ static inline int is_migration_entry(swp_entry_t swp) { return 0; } -#define migration_entry_to_page(swp) NULL +static inline struct page *migration_entry_to_page(swp_entry_t entry) +{ + return NULL; +} + static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } @@ -163,6 +236,70 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif +struct page_vma_mapped_walk; + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, + struct page *page); + +extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, + struct page *new); + +extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); + +static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) +{ + swp_entry_t arch_entry; + + if (pmd_swp_soft_dirty(pmd)) + pmd = pmd_swp_clear_soft_dirty(pmd); + arch_entry = __pmd_to_swp_entry(pmd); + return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); +} + +static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) +{ + swp_entry_t arch_entry; + + arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); + return __swp_entry_to_pmd(arch_entry); +} + +static inline int is_pmd_migration_entry(pmd_t pmd) +{ + return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); +} +#else +static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, + struct page *page) +{ + BUILD_BUG(); +} + +static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, + struct page *new) +{ + BUILD_BUG(); +} + +static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } + +static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) +{ + return swp_entry(0, 0); +} + +static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) +{ + return __pmd(0); +} + +static inline int is_pmd_migration_entry(pmd_t pmd) +{ + return 0; +} +#endif + #ifdef CONFIG_MEMORY_FAILURE extern atomic_long_t num_poisoned_pages __read_mostly; @@ -196,15 +333,6 @@ static inline void num_poisoned_pages_dec(void) atomic_long_dec(&num_poisoned_pages); } -static inline void num_poisoned_pages_add(long num) -{ - atomic_long_add(num, &num_poisoned_pages); -} - -static inline void num_poisoned_pages_sub(long num) -{ - atomic_long_sub(num, &num_poisoned_pages); -} #else static inline swp_entry_t make_hwpoison_entry(struct page *page) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 4ee479f2f355..15e7160751a8 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -35,6 +35,7 @@ int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); +extern void __init swiotlb_update_mem_attributes(void); /* * Enumeration for sync targets diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index 3e3ab84fc4cd..0ad87c434ae6 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -14,7 +14,6 @@ #define _LINUX_SYNC_FILE_H #include <linux/types.h> -#include <linux/kref.h> #include <linux/ktime.h> #include <linux/list.h> #include <linux/spinlock.h> @@ -24,8 +23,6 @@ /** * struct sync_file - sync file to export to the userspace * @file: file representing this fence - * @kref: reference count on fence. - * @name: name of sync_file. Useful for debugging * @sync_file_list: membership in global file list * @wq: wait queue for fence signaling * @fence: fence with the fences in the sync_file @@ -33,21 +30,29 @@ */ struct sync_file { struct file *file; - struct kref kref; - char name[32]; + /** + * @user_name: + * + * Name of the sync file provided by userspace, for merged fences. + * Otherwise generated through driver callbacks (in which case the + * entire array is 0). + */ + char user_name[32]; #ifdef CONFIG_DEBUG_FS struct list_head sync_file_list; #endif wait_queue_head_t wq; + unsigned long flags; struct dma_fence *fence; struct dma_fence_cb cb; }; -#define POLL_ENABLED DMA_FENCE_FLAG_USER_BITS +#define POLL_ENABLED 0 struct sync_file *sync_file_create(struct dma_fence *fence); struct dma_fence *sync_file_get_fence(int fd); +char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len); #endif /* _LINUX_SYNC_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 980c3c9b06f8..95606a2d556f 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -100,11 +100,12 @@ union bpf_attr; #define __MAP(n,...) __MAP##n(__VA_ARGS__) #define __SC_DECL(t, a) t a -#define __TYPE_IS_L(t) (__same_type((t)0, 0L)) -#define __TYPE_IS_UL(t) (__same_type((t)0, 0UL)) -#define __TYPE_IS_LL(t) (__same_type((t)0, 0LL) || __same_type((t)0, 0ULL)) +#define __TYPE_AS(t, v) __same_type((__force t)0, v) +#define __TYPE_IS_L(t) (__TYPE_AS(t, 0L)) +#define __TYPE_IS_UL(t) (__TYPE_AS(t, 0UL)) +#define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a -#define __SC_CAST(t, a) (t) a +#define __SC_CAST(t, a) (__force t) a #define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) @@ -172,8 +173,20 @@ extern struct trace_event_functions exit_syscall_print_funcs; static struct syscall_metadata __used \ __attribute__((section("__syscalls_metadata"))) \ *__p_syscall_meta_##sname = &__syscall_meta_##sname; + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return tp_event->class == &event_class_syscall_enter || + tp_event->class == &event_class_syscall_exit; +} + #else #define SYSCALL_METADATA(sname, nb, ...) + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return 0; +} #endif #define SYSCALL_DEFINE0(sname) \ @@ -187,6 +200,8 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) #define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) +#define SYSCALL_DEFINE_MAXARGS 6 + #define SYSCALL_DEFINEx(x, sname, ...) \ SYSCALL_METADATA(sname, x, __VA_ARGS__) \ __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) @@ -206,6 +221,22 @@ extern struct trace_event_functions exit_syscall_print_funcs; } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#ifdef TIF_FSCHECK +/* + * Called before coming back to user-mode. Returning to user-mode with an + * address limit different than USER_DS can allow to overwrite kernel memory. + */ +static inline void addr_limit_user_check(void) +{ + + if (!test_thread_flag(TIF_FSCHECK)) + return; + + BUG_ON(!segment_eq(get_fs(), USER_DS)); + clear_thread_flag(TIF_FSCHECK); +} +#endif + asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); asmlinkage long sys_time(time_t __user *tloc); @@ -578,12 +609,12 @@ asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); asmlinkage long sys_chdir(const char __user *filename); @@ -650,7 +681,7 @@ asmlinkage long sys_olduname(struct oldold_utsname __user *); asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim); -#if defined(COMPAT_RLIM_OLD_INFINITY) || !(defined(CONFIG_IA64)) +#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim); #endif asmlinkage long sys_setrlimit(unsigned int resource, diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..1d4dba490fb6 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -47,6 +47,9 @@ extern int proc_douintvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, @@ -117,7 +120,7 @@ struct ctl_table struct ctl_table_poll *poll; void *extra1; void *extra2; -}; +} __randomize_layout; struct ctl_node { struct rb_node node; @@ -143,7 +146,7 @@ struct ctl_table_header struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; - struct list_head inodes; /* head for proc_inode->sysctl_inodes */ + struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ }; struct ctl_dir { diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index c6f0f0d0e17e..aa02c328dff5 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -512,7 +512,7 @@ static inline void sysfs_notify_dirent(struct kernfs_node *kn) } static inline struct kernfs_node *sysfs_get_dirent(struct kernfs_node *parent, - const unsigned char *name) + const char *name) { return kernfs_find_and_get(parent, name); } diff --git a/include/linux/syslog.h b/include/linux/syslog.h index c3a7f0cc3a27..e1c3632f4e81 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -49,13 +49,4 @@ int do_syslog(int type, char __user *buf, int count, int source); -#ifdef CONFIG_PRINTK -int check_syslog_permissions(int type, int source); -#else -static inline int check_syslog_permissions(int type, int source) -{ - return 0; -} -#endif - #endif /* _LINUX_SYSLOG_H */ diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 9375d23a24e7..635a3c5706bd 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -33,6 +33,8 @@ struct t10_pi_tuple { __be32 ref_tag; /* Target LBA or indirect LBA */ }; +#define T10_PI_APP_ESCAPE cpu_to_be16(0xffff) +#define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff) extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b6d5adcee8fc..4aa40ef02d32 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -123,7 +123,7 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; - struct skb_mstamp snt_synack; /* first SYNACK sent time */ + u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; u32 txhash; u32 rcv_isn; @@ -192,15 +192,6 @@ struct tcp_sock { struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - /* Data for direct copy to user */ - struct { - struct sk_buff_head prequeue; - struct task_struct *task; - struct msghdr *msg; - int memory; - int len; - } ucopy; - u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ u32 max_window; /* Maximal window ever seen from peer */ @@ -211,7 +202,7 @@ struct tcp_sock { /* Information of the most recently (s)acked skb */ struct tcp_rack { - struct skb_mstamp mstamp; /* (Re)sent time of the skb */ + u64 mstamp; /* (Re)sent time of the skb */ u32 rtt_us; /* Associated RTT */ u32 end_seq; /* Ending TCP sequence of the skb */ u8 advanced; /* mstamp advanced since last lost marking */ @@ -240,7 +231,7 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ - struct skb_mstamp tcp_mstamp; /* most recent packet received/sent */ + u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ @@ -273,15 +264,15 @@ struct tcp_sock { u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; - u32 prior_cwnd; /* Congestion window at start of Recovery. */ + u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ u32 lost; /* Total data packets lost incl. rexmits */ u32 app_limited; /* limited until "delivered" reaches this val */ - struct skb_mstamp first_tx_mstamp; /* start of window send phase */ - struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u64 first_tx_mstamp; /* start of window send phase */ + u64 delivered_mstamp; /* time we reached "delivered" */ u32 rate_delivered; /* saved rate sample: packets delivered */ u32 rate_interval_us; /* saved rate sample: time elapsed */ @@ -293,6 +284,8 @@ struct tcp_sock { u32 sacked_out; /* SACK'd packets */ u32 fackets_out; /* FACK'd packets */ + struct hrtimer pacing_timer; + /* from STCP, retrans queue hinting */ struct sk_buff* lost_skb_hint; struct sk_buff *retransmit_skb_hint; @@ -333,16 +326,16 @@ struct tcp_sock { /* Receiver side RTT estimation */ struct { - u32 rtt_us; - u32 seq; - struct skb_mstamp time; + u32 rtt_us; + u32 seq; + u64 time; } rcv_rtt_est; /* Receiver queue space */ struct { - int space; - u32 seq; - struct skb_mstamp time; + int space; + u32 seq; + u64 time; } rcvq_space; /* TCP-specific MTU probe information. */ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 0f175b8f6456..cb889afe576b 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -28,6 +28,7 @@ #define TEE_SHM_MAPPED 0x1 /* Memory mapped by the kernel */ #define TEE_SHM_DMA_BUF 0x2 /* Memory with dma-buf handle */ +struct device; struct tee_device; struct tee_shm; struct tee_shm_pool; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index dab11f97e1c6..fd5b959c753c 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -102,6 +102,7 @@ enum thermal_notify_event { THERMAL_DEVICE_DOWN, /* Thermal device is down */ THERMAL_DEVICE_UP, /* Thermal device is up after a down event */ THERMAL_DEVICE_POWER_CAPABILITY_CHANGED, /* power capability changed */ + THERMAL_TABLE_CHANGED, /* Thermal table(s) changed */ }; struct thermal_zone_device_ops { diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index d7d3ea637dd0..905d769d8ddc 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -38,6 +38,10 @@ enum { #ifdef __KERNEL__ +#ifndef THREAD_ALIGN +#define THREAD_ALIGN THREAD_SIZE +#endif + #ifdef CONFIG_DEBUG_STACK_USAGE # define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ __GFP_ZERO) @@ -113,6 +117,33 @@ static inline void check_object_size(const void *ptr, unsigned long n, { } #endif /* CONFIG_HARDENED_USERCOPY */ +extern void __compiletime_error("copy source size is too small") +__bad_copy_from(void); +extern void __compiletime_error("copy destination size is too small") +__bad_copy_to(void); + +static inline void copy_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + +static __always_inline bool +check_copy_size(const void *addr, size_t bytes, bool is_source) +{ + int sz = __compiletime_object_size(addr); + if (unlikely(sz >= 0 && sz < bytes)) { + if (!__builtin_constant_p(bytes)) + copy_overflow(sz, bytes); + else if (is_source) + __bad_copy_from(); + else + __bad_copy_to(); + return false; + } + check_object_size(addr, bytes, is_source); + return true; +} + #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif diff --git a/include/linux/time.h b/include/linux/time.h index c0543f5f25de..9bc1f945777c 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -8,6 +8,15 @@ extern struct timezone sys_tz; +int get_timespec64(struct timespec64 *ts, + const struct timespec __user *uts); +int put_timespec64(const struct timespec64 *ts, + struct timespec __user *uts); +int get_itimerspec64(struct itimerspec64 *it, + const struct itimerspec __user *uit); +int put_itimerspec64(const struct itimerspec64 *it, + struct itimerspec __user *uit); + #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) static inline int timespec_equal(const struct timespec *a, @@ -169,10 +178,7 @@ extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); extern int do_getitimer(int which, struct itimerval *value); -extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); - -struct tms; -extern void do_sys_times(struct tms *); +extern long do_utimes(int dfd, const char __user *filename, struct timespec64 *times, int flags); /* * Similar to the struct tm in userspace <time.h>, but it needs to be here so @@ -270,4 +276,28 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } +static inline bool itimerspec64_valid(const struct itimerspec64 *its) +{ + if (!timespec64_valid(&(its->it_interval)) || + !timespec64_valid(&(its->it_value))) + return false; + + return true; +} + +/** + * time_after32 - compare two 32-bit relative times + * @a: the time which may be after @b + * @b: the time which may be before @a + * + * time_after32(a, b) returns true if the time @a is after time @b. + * time_before32(b, a) returns true if the time @b is before time @a. + * + * Similar to time_after(), compare two 32-bit timestamps for relative + * times. This is useful for comparing 32-bit seconds values that can't + * be converted to 64-bit values (e.g. due to disk format or wire protocol + * issues) when it is known that the times are less than 68 years apart. + */ +#define time_after32(a, b) ((s32)((u32)(b) - (u32)(a)) < 0) +#define time_before32(b, a) time_after32(a, b) #endif diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index f7043ccca81c..0a0a53daf2a2 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -51,7 +51,7 @@ struct tk_read_base { * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second - * @raw_time: Monotonic raw base time in timespec64 format + * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP * interval. @@ -93,7 +93,7 @@ struct timekeeper { unsigned int clock_was_set_seq; u8 cs_was_changed_seq; ktime_t next_leap_ktime; - struct timespec64 raw_time; + u64 raw_sec; /* The following members are for timekeeping internal use */ u64 cycle_interval; diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h index 46eb27ddbfab..3e00122bcf88 100644 --- a/include/linux/timeriomem-rng.h +++ b/include/linux/timeriomem-rng.h @@ -13,4 +13,7 @@ struct timeriomem_rng_data { /* measures in usecs */ unsigned int period; + + /* bits of entropy per 1024 bits read */ + unsigned int quality; }; diff --git a/include/linux/tnum.h b/include/linux/tnum.h new file mode 100644 index 000000000000..0d2d3da46139 --- /dev/null +++ b/include/linux/tnum.h @@ -0,0 +1,81 @@ +/* tnum: tracked (or tristate) numbers + * + * A tnum tracks knowledge about the bits of a value. Each bit can be either + * known (0 or 1), or unknown (x). Arithmetic operations on tnums will + * propagate the unknown bits such that the tnum result represents all the + * possible results for possible values of the operands. + */ +#include <linux/types.h> + +struct tnum { + u64 value; + u64 mask; +}; + +/* Constructors */ +/* Represent a known constant as a tnum. */ +struct tnum tnum_const(u64 value); +/* A completely unknown value */ +extern const struct tnum tnum_unknown; +/* A value that's unknown except that @min <= value <= @max */ +struct tnum tnum_range(u64 min, u64 max); + +/* Arithmetic and logical ops */ +/* Shift a tnum left (by a fixed shift) */ +struct tnum tnum_lshift(struct tnum a, u8 shift); +/* Shift a tnum right (by a fixed shift) */ +struct tnum tnum_rshift(struct tnum a, u8 shift); +/* Add two tnums, return @a + @b */ +struct tnum tnum_add(struct tnum a, struct tnum b); +/* Subtract two tnums, return @a - @b */ +struct tnum tnum_sub(struct tnum a, struct tnum b); +/* Bitwise-AND, return @a & @b */ +struct tnum tnum_and(struct tnum a, struct tnum b); +/* Bitwise-OR, return @a | @b */ +struct tnum tnum_or(struct tnum a, struct tnum b); +/* Bitwise-XOR, return @a ^ @b */ +struct tnum tnum_xor(struct tnum a, struct tnum b); +/* Multiply two tnums, return @a * @b */ +struct tnum tnum_mul(struct tnum a, struct tnum b); + +/* Return a tnum representing numbers satisfying both @a and @b */ +struct tnum tnum_intersect(struct tnum a, struct tnum b); + +/* Return @a with all but the lowest @size bytes cleared */ +struct tnum tnum_cast(struct tnum a, u8 size); + +/* Returns true if @a is a known constant */ +static inline bool tnum_is_const(struct tnum a) +{ + return !a.mask; +} + +/* Returns true if @a == tnum_const(@b) */ +static inline bool tnum_equals_const(struct tnum a, u64 b) +{ + return tnum_is_const(a) && a.value == b; +} + +/* Returns true if @a is completely unknown */ +static inline bool tnum_is_unknown(struct tnum a) +{ + return !~a.mask; +} + +/* Returns true if @a is known to be a multiple of @size. + * @size must be a power of two. + */ +bool tnum_is_aligned(struct tnum a, u64 size); + +/* Returns true if @b represents a subset of @a. */ +bool tnum_in(struct tnum a, struct tnum b); + +/* Formatting functions. These have snprintf-like semantics: they will write + * up to @size bytes (including the terminating NUL byte), and return the number + * of bytes (excluding the terminating NUL) which would have been written had + * sufficient space been available. (Thus tnum_sbin always returns 64.) + */ +/* Format a tnum as a pair of hex numbers (value; mask) */ +int tnum_strn(char *str, size_t size, struct tnum a); +/* Format a tnum as tristate binary expansion */ +int tnum_sbin(char *str, size_t size, struct tnum a); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index a556805eff8a..7f11050746ae 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -151,7 +151,15 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, int type, unsigned long len, unsigned long flags, int pc); -void tracing_record_cmdline(struct task_struct *tsk); +#define TRACE_RECORD_CMDLINE BIT(0) +#define TRACE_RECORD_TGID BIT(1) + +void tracing_record_taskinfo(struct task_struct *task, int flags); +void tracing_record_taskinfo_sched_switch(struct task_struct *prev, + struct task_struct *next, int flags); + +void tracing_record_cmdline(struct task_struct *task); +void tracing_record_tgid(struct task_struct *task); int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...); @@ -209,7 +217,6 @@ enum { TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, - TRACE_EVENT_FL_WAS_ENABLED_BIT, TRACE_EVENT_FL_TRACEPOINT_BIT, TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, @@ -221,9 +228,6 @@ enum { * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored * IGNORE_ENABLE - For trace internal events, do not enable with debugfs file - * WAS_ENABLED - Set and stays set when an event was ever enabled - * (used for module unloading, if a module event is enabled, - * it is best to clear the buffers that used it). * TRACEPOINT - Event is a tracepoint * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe @@ -233,7 +237,6 @@ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), - TRACE_EVENT_FL_WAS_ENABLED = (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT), TRACE_EVENT_FL_TRACEPOINT = (1 << TRACE_EVENT_FL_TRACEPOINT_BIT), TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), @@ -290,6 +293,7 @@ struct trace_subsystem_dir; enum { EVENT_FILE_FL_ENABLED_BIT, EVENT_FILE_FL_RECORDED_CMD_BIT, + EVENT_FILE_FL_RECORDED_TGID_BIT, EVENT_FILE_FL_FILTERED_BIT, EVENT_FILE_FL_NO_SET_FILTER_BIT, EVENT_FILE_FL_SOFT_MODE_BIT, @@ -297,12 +301,14 @@ enum { EVENT_FILE_FL_TRIGGER_MODE_BIT, EVENT_FILE_FL_TRIGGER_COND_BIT, EVENT_FILE_FL_PID_FILTER_BIT, + EVENT_FILE_FL_WAS_ENABLED_BIT, }; /* * Event file flags: * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch + * RECORDED_TGID - The tgids should be recorded at sched_switch * FILTERED - The event has a filter attached * NO_SET_FILTER - Set when filter has error and is to be ignored * SOFT_MODE - The event is enabled/disabled by SOFT_DISABLED @@ -311,10 +317,12 @@ enum { * TRIGGER_MODE - When set, invoke the triggers associated with the event * TRIGGER_COND - When set, one or more triggers has an associated filter * PID_FILTER - When set, the event is filtered based on pid + * WAS_ENABLED - Set when enabled to know to clear trace on module removal */ enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), EVENT_FILE_FL_RECORDED_CMD = (1 << EVENT_FILE_FL_RECORDED_CMD_BIT), + EVENT_FILE_FL_RECORDED_TGID = (1 << EVENT_FILE_FL_RECORDED_TGID_BIT), EVENT_FILE_FL_FILTERED = (1 << EVENT_FILE_FL_FILTERED_BIT), EVENT_FILE_FL_NO_SET_FILTER = (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT), EVENT_FILE_FL_SOFT_MODE = (1 << EVENT_FILE_FL_SOFT_MODE_BIT), @@ -322,12 +330,13 @@ enum { EVENT_FILE_FL_TRIGGER_MODE = (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT), EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), + EVENT_FILE_FL_WAS_ENABLED = (1 << EVENT_FILE_FL_WAS_ENABLED_BIT), }; struct trace_event_file { struct list_head list; struct trace_event_call *event_call; - struct event_filter *filter; + struct event_filter __rcu *filter; struct dentry *dir; struct trace_array *tr; struct trace_subsystem_dir *system; @@ -497,9 +506,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, u64 count, struct pt_regs *regs, void *head, - struct task_struct *task) + struct task_struct *task, struct perf_event *event) { - perf_tp_event(type, count, raw_data, size, regs, head, rctx, task); + perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event); } #endif diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index cc48cb2ce209..a26ffbe09e71 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -25,10 +25,10 @@ struct module; struct tracepoint; struct notifier_block; -struct trace_enum_map { +struct trace_eval_map { const char *system; - const char *enum_string; - unsigned long enum_value; + const char *eval_string; + unsigned long eval_value; }; #define TRACEPOINT_DEFAULT_PRIO 10 @@ -88,6 +88,7 @@ extern void syscall_unregfunc(void); #define PARAMS(args...) args #define TRACE_DEFINE_ENUM(x) +#define TRACE_DEFINE_SIZEOF(x) #endif /* _LINUX_TRACEPOINT_H */ diff --git a/include/linux/tty.h b/include/linux/tty.h index eccb4ec30a8a..cf53eb539f6e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -261,6 +261,8 @@ struct tty_port { */ #define TTY_PORT_CTS_FLOW 3 /* h/w flow control enabled */ #define TTY_PORT_CHECK_CD 4 /* carrier detect enabled */ +#define TTY_PORT_KOPENED 5 /* device exclusively opened by + kernel */ /* * Where all of the state associated with a tty is kept while the tty @@ -316,7 +318,6 @@ struct tty_struct { struct tty_struct *link; struct fasync_struct *fasync; - int alt_speed; /* For magic substitution of 38400 bps */ wait_queue_head_t write_wait; wait_queue_head_t read_wait; struct work_struct hangup_work; @@ -333,7 +334,7 @@ struct tty_struct { /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; -}; +} __randomize_layout; /* Each of a tty's open files has private_data pointing to tty_file_private */ struct tty_file_private { @@ -400,6 +401,9 @@ extern struct tty_struct *get_current_tty(void); /* tty_io.c */ extern int __init tty_init(void); extern const char *tty_name(const struct tty_struct *tty); +extern struct tty_struct *tty_kopen(dev_t device); +extern void tty_kclose(struct tty_struct *tty); +extern int tty_dev_name_to_number(const char *name, dev_t *number); #else static inline void tty_kref_put(struct tty_struct *tty) { } @@ -420,6 +424,12 @@ static inline int __init tty_init(void) { return 0; } static inline const char *tty_name(const struct tty_struct *tty) { return "(none)"; } +static inline struct tty_struct *tty_kopen(dev_t device) +{ return ERR_PTR(-ENODEV); } +static inline void tty_kclose(struct tty_struct *tty) +{ } +static inline int tty_dev_name_to_number(const char *name, dev_t *number) +{ return -ENOTSUPP; } #endif extern struct ktermios tty_std_termios; @@ -645,6 +655,19 @@ static inline void tty_port_set_initialized(struct tty_port *port, bool val) clear_bit(TTY_PORT_INITIALIZED, &port->iflags); } +static inline bool tty_port_kopened(struct tty_port *port) +{ + return test_bit(TTY_PORT_KOPENED, &port->iflags); +} + +static inline void tty_port_set_kopened(struct tty_port *port, bool val) +{ + if (val) + set_bit(TTY_PORT_KOPENED, &port->iflags); + else + clear_bit(TTY_PORT_KOPENED, &port->iflags); +} + extern struct tty_struct *tty_port_tty_get(struct tty_port *port); extern void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty); extern int tty_port_carrier_raised(struct tty_port *port); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index b742b5e47cc2..fcdc0f5d9098 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -243,6 +243,7 @@ #include <linux/list.h> #include <linux/cdev.h> #include <linux/termios.h> +#include <linux/seq_file.h> struct tty_struct; struct tty_driver; @@ -285,13 +286,14 @@ struct tty_operations { int (*set_termiox)(struct tty_struct *tty, struct termiox *tnew); int (*get_icount)(struct tty_struct *tty, struct serial_icounter_struct *icount); + void (*show_fdinfo)(struct tty_struct *tty, struct seq_file *m); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct tty_driver *driver, int line, char *options); int (*poll_get_char)(struct tty_driver *driver, int line); void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif const struct file_operations *proc_fops; -}; +} __randomize_layout; struct tty_driver { int magic; /* magic number for this structure */ @@ -325,7 +327,7 @@ struct tty_driver { const struct tty_operations *ops; struct list_head tty_drivers; -}; +} __randomize_layout; extern struct list_head tty_drivers; diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index c28dd523f96e..d43837f2ce3a 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -12,6 +12,7 @@ extern int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, size_t size); extern void tty_flip_buffer_push(struct tty_port *port); void tty_schedule_flip(struct tty_port *port); +int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); static inline int tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag) @@ -26,7 +27,7 @@ static inline int tty_insert_flip_char(struct tty_port *port, *char_buf_ptr(tb, tb->used++) = ch; return 1; } - return tty_insert_flip_string_flags(port, &ch, &flag, 1); + return __tty_insert_flip_char(port, ch, flag); } static inline int tty_insert_flip_string(struct tty_port *port, diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 201418d5e15c..20ef8e6ec2db 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -109,8 +109,11 @@ static inline unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; - if (likely(access_ok(VERIFY_READ, from, n))) + might_fault(); + if (likely(access_ok(VERIFY_READ, from, n))) { + kasan_check_write(to, n); res = raw_copy_from_user(to, from, n); + } if (unlikely(res)) memset(to + (n - res), 0, res); return res; @@ -124,8 +127,11 @@ _copy_from_user(void *, const void __user *, unsigned long); static inline unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { - if (access_ok(VERIFY_WRITE, to, n)) + might_fault(); + if (access_ok(VERIFY_WRITE, to, n)) { + kasan_check_read(from, n); n = raw_copy_to_user(to, from, n); + } return n; } #else @@ -133,60 +139,24 @@ extern unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif -extern void __compiletime_error("usercopy buffer size is too small") -__bad_copy_user(void); - -static inline void copy_user_overflow(int size, unsigned long count) -{ - WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); -} - static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - int sz = __compiletime_object_size(to); - - might_fault(); - kasan_check_write(to, n); - - if (likely(sz < 0 || sz >= n)) { - check_object_size(to, n, false); + if (likely(check_copy_size(to, n, false))) n = _copy_from_user(to, from, n); - } else if (!__builtin_constant_p(n)) - copy_user_overflow(sz, n); - else - __bad_copy_user(); - return n; } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { - int sz = __compiletime_object_size(from); - - kasan_check_read(from, n); - might_fault(); - - if (likely(sz < 0 || sz >= n)) { - check_object_size(from, n, true); + if (likely(check_copy_size(from, n, true))) n = _copy_to_user(to, from, n); - } else if (!__builtin_constant_p(n)) - copy_user_overflow(sz, n); - else - __bad_copy_user(); - return n; } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check -__copy_in_user(void __user *to, const void *from, unsigned long n) -{ - might_fault(); - return raw_copy_in_user(to, from, n); -} -static __always_inline unsigned long __must_check -copy_in_user(void __user *to, const void *from, unsigned long n) +copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n)) diff --git a/include/linux/udp.h b/include/linux/udp.h index 6cb4061a720d..eaea63bc79bb 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -80,6 +80,9 @@ struct udp_sock { struct sk_buff *skb, int nhoff); + /* udp_recvmsg try to use this before splicing sk_receive_queue */ + struct sk_buff_head reader_queue ____cacheline_aligned_in_smp; + /* This field is dirtied by udp_recvmsg() */ int forward_deficit; }; diff --git a/include/linux/uio.h b/include/linux/uio.h index f2d36a3d3005..8a642cda641c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -10,6 +10,7 @@ #define __LINUX_UIO_H #include <linux/kernel.h> +#include <linux/thread_info.h> #include <uapi/linux/uio.h> struct page; @@ -91,11 +92,79 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); -size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); -size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); -bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); -size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); -bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); + +size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); +size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); +bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); +size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); +bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); + +static __always_inline __must_check +size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, true))) + return 0; + else + return _copy_to_iter(addr, bytes, i); +} + +static __always_inline __must_check +size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return 0; + else + return _copy_from_iter(addr, bytes, i); +} + +static __always_inline __must_check +bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return false; + else + return _copy_from_iter_full(addr, bytes, i); +} + +static __always_inline __must_check +size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return 0; + else + return _copy_from_iter_nocache(addr, bytes, i); +} + +static __always_inline __must_check +bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return false; + else + return _copy_from_iter_full_nocache(addr, bytes, i); +} + +#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +/* + * Note, users like pmem that depend on the stricter semantics of + * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for + * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the + * destination is flushed from the cache on return. + */ +size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); +#else +#define _copy_from_iter_flushcache _copy_from_iter_nocache +#endif + +static __always_inline __must_check +size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return 0; + else + return _copy_from_iter_flushcache(addr, bytes, i); +} + size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); diff --git a/include/linux/umh.h b/include/linux/umh.h new file mode 100644 index 000000000000..244aff638220 --- /dev/null +++ b/include/linux/umh.h @@ -0,0 +1,69 @@ +#ifndef __LINUX_UMH_H__ +#define __LINUX_UMH_H__ + +#include <linux/gfp.h> +#include <linux/stddef.h> +#include <linux/errno.h> +#include <linux/compiler.h> +#include <linux/workqueue.h> +#include <linux/sysctl.h> + +struct cred; +struct file; + +#define UMH_NO_WAIT 0 /* don't wait at all */ +#define UMH_WAIT_EXEC 1 /* wait for the exec, but not the process */ +#define UMH_WAIT_PROC 2 /* wait for the process to complete */ +#define UMH_KILLABLE 4 /* wait for EXEC/PROC killable */ + +struct subprocess_info { + struct work_struct work; + struct completion *complete; + const char *path; + char **argv; + char **envp; + int wait; + int retval; + int (*init)(struct subprocess_info *info, struct cred *new); + void (*cleanup)(struct subprocess_info *info); + void *data; +} __randomize_layout; + +extern int +call_usermodehelper(const char *path, char **argv, char **envp, int wait); + +extern struct subprocess_info * +call_usermodehelper_setup(const char *path, char **argv, char **envp, + gfp_t gfp_mask, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *), void *data); + +extern int +call_usermodehelper_exec(struct subprocess_info *info, int wait); + +extern struct ctl_table usermodehelper_table[]; + +enum umh_disable_depth { + UMH_ENABLED = 0, + UMH_FREEZING, + UMH_DISABLED, +}; + +extern int __usermodehelper_disable(enum umh_disable_depth depth); +extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth); + +static inline int usermodehelper_disable(void) +{ + return __usermodehelper_disable(UMH_DISABLED); +} + +static inline void usermodehelper_enable(void) +{ + __usermodehelper_set_disable_depth(UMH_ENABLED); +} + +extern int usermodehelper_read_trylock(void); +extern long usermodehelper_read_lock_wait(long timeout); +extern void usermodehelper_read_unlock(void); + +#endif /* __LINUX_UMH_H__ */ diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index c5f2158ab00e..fd73bc0e9027 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -115,13 +115,13 @@ struct uac2_input_terminal_descriptor { __u8 bDescriptorType; __u8 bDescriptorSubtype; __u8 bTerminalID; - __u16 wTerminalType; + __le16 wTerminalType; __u8 bAssocTerminal; __u8 bCSourceID; __u8 bNrChannels; - __u32 bmChannelConfig; + __le32 bmChannelConfig; __u8 iChannelNames; - __u16 bmControls; + __le16 bmControls; __u8 iTerminal; } __attribute__((packed)); @@ -132,11 +132,11 @@ struct uac2_output_terminal_descriptor { __u8 bDescriptorType; __u8 bDescriptorSubtype; __u8 bTerminalID; - __u16 wTerminalType; + __le16 wTerminalType; __u8 bAssocTerminal; __u8 bSourceID; __u8 bCSourceID; - __u16 bmControls; + __le16 bmControls; __u8 iTerminal; } __attribute__((packed)); @@ -164,9 +164,9 @@ struct uac2_as_header_descriptor { __u8 bTerminalLink; __u8 bmControls; __u8 bFormatType; - __u32 bmFormats; + __le32 bmFormats; __u8 bNrChannels; - __u32 bmChannelConfig; + __le32 bmChannelConfig; __u8 iChannelNames; } __attribute__((packed)); diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 00d232406f18..1a59699cf82a 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -83,6 +83,7 @@ /* Driver flags */ #define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ #define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ +#define CDC_NCM_FLAG_RESET_NTB16 0x08 /* set NDP16 one more time after altsetting switch */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) @@ -117,6 +118,9 @@ struct cdc_ncm_ctx { u32 tx_curr_frame_num; u32 rx_max; u32 tx_max; + u32 tx_curr_size; + u32 tx_low_mem_max_cnt; + u32 tx_low_mem_val; u32 max_datagram_size; u16 tx_max_datagrams; u16 tx_remainder; diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index c5fdfcf99828..d725cff7268d 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -58,6 +58,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_OVERRIDE_TX_BURST BIT(10) #define CI_HDRC_OVERRIDE_RX_BURST BIT(11) #define CI_HDRC_OVERRIDE_PHY_CONTROL BIT(12) /* Glue layer manages phy */ +#define CI_HDRC_REQUIRES_ALIGNED_DMA BIT(13) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index fbc22a39e7bc..21468a722c4a 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -48,6 +48,7 @@ struct usb_ep; * by adding a zero length packet as needed; * @short_not_ok: When reading data, makes short packets be * treated as errors (queue stops advancing till cleanup). + * @dma_mapped: Indicates if request has been mapped to DMA (internal) * @complete: Function called when request completes, so this request and * its buffer may be re-used. The function will always be called with * interrupts disabled, and it must not sleep. @@ -103,6 +104,7 @@ struct usb_request { unsigned no_interrupt:1; unsigned zero:1; unsigned short_not_ok:1; + unsigned dma_mapped:1; void (*complete)(struct usb_ep *ep, struct usb_request *req); @@ -304,6 +306,7 @@ struct usb_gadget_ops { int (*udc_start)(struct usb_gadget *, struct usb_gadget_driver *); int (*udc_stop)(struct usb_gadget *); + void (*udc_set_speed)(struct usb_gadget *, enum usb_device_speed); struct usb_ep *(*match_ep)(struct usb_gadget *, struct usb_endpoint_descriptor *, struct usb_ss_ep_comp_descriptor *); @@ -352,6 +355,8 @@ struct usb_gadget_ops { * @deactivated: True if gadget is deactivated - in deactivated state it cannot * be connected. * @connected: True if gadget is connected. + * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag + * indicates that it supports LPM as per the LPM ECN & errata. * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -404,6 +409,7 @@ struct usb_gadget { unsigned is_selfpowered:1; unsigned deactivated:1; unsigned connected:1; + unsigned lpm_capable:1; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 50398b69ca44..a1f03ebfde47 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -565,9 +565,9 @@ extern void usb_ep0_reinit(struct usb_device *); ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) #define EndpointRequest \ - ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) + ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) #define EndpointOutRequest \ - ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) + ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) /* class requests from the USB 2.0 hub spec, table 11-15 */ #define HUB_CLASS_REQ(dir, type, request) ((((dir) | (type)) << 8) | (request)) diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index 31a8068c42a5..8c6914873a16 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -9,8 +9,10 @@ #ifndef __LINUX_USB_PHY_H #define __LINUX_USB_PHY_H +#include <linux/extcon.h> #include <linux/notifier.h> #include <linux/usb.h> +#include <uapi/linux/usb/charger.h> enum usb_phy_interface { USBPHY_INTERFACE_MODE_UNKNOWN, @@ -71,6 +73,17 @@ struct usb_phy_io_ops { int (*write)(struct usb_phy *x, u32 val, u32 reg); }; +struct usb_charger_current { + unsigned int sdp_min; + unsigned int sdp_max; + unsigned int dcp_min; + unsigned int dcp_max; + unsigned int cdp_min; + unsigned int cdp_max; + unsigned int aca_min; + unsigned int aca_max; +}; + struct usb_phy { struct device *dev; const char *label; @@ -85,6 +98,19 @@ struct usb_phy { struct usb_phy_io_ops *io_ops; void __iomem *io_priv; + /* to support extcon device */ + struct extcon_dev *edev; + struct extcon_dev *id_edev; + struct notifier_block vbus_nb; + struct notifier_block id_nb; + struct notifier_block type_nb; + + /* Support USB charger */ + enum usb_charger_type chg_type; + enum usb_charger_state chg_state; + struct usb_charger_current chg_cur; + struct work_struct chg_work; + /* for notification of usb_phy_events */ struct atomic_notifier_head notifier; @@ -122,6 +148,12 @@ struct usb_phy { enum usb_device_speed speed); int (*notify_disconnect)(struct usb_phy *x, enum usb_device_speed speed); + + /* + * Charger detection method can be implemented if you need to + * manually detect the charger type. + */ + enum usb_charger_type (*charger_detect)(struct usb_phy *x); }; /** @@ -212,6 +244,12 @@ extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x); extern int usb_bind_phy(const char *dev_name, u8 index, const char *phy_dev_name); extern void usb_phy_set_event(struct usb_phy *x, unsigned long event); +extern void usb_phy_set_charger_current(struct usb_phy *usb_phy, + unsigned int mA); +extern void usb_phy_get_charger_current(struct usb_phy *usb_phy, + unsigned int *min, unsigned int *max); +extern void usb_phy_set_charger_state(struct usb_phy *usb_phy, + enum usb_charger_state state); #else static inline struct usb_phy *usb_get_phy(enum usb_phy_type type) { @@ -263,12 +301,33 @@ static inline int usb_bind_phy(const char *dev_name, u8 index, static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event) { } + +static inline void usb_phy_set_charger_current(struct usb_phy *usb_phy, + unsigned int mA) +{ +} + +static inline void usb_phy_get_charger_current(struct usb_phy *usb_phy, + unsigned int *min, + unsigned int *max) +{ +} + +static inline void usb_phy_set_charger_state(struct usb_phy *usb_phy, + enum usb_charger_state state) +{ +} #endif static inline int usb_phy_set_power(struct usb_phy *x, unsigned mA) { - if (x && x->set_power) + if (!x) + return 0; + + usb_phy_set_charger_current(x, mA); + + if (x->set_power) return x->set_power(x, mA); return 0; } diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index ec78204964ab..ffe7487886ca 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -117,13 +117,13 @@ struct typec_altmode_desc { struct typec_altmode *typec_partner_register_altmode(struct typec_partner *partner, - struct typec_altmode_desc *desc); + const struct typec_altmode_desc *desc); struct typec_altmode *typec_plug_register_altmode(struct typec_plug *plug, - struct typec_altmode_desc *desc); + const struct typec_altmode_desc *desc); struct typec_altmode *typec_port_register_altmode(struct typec_port *port, - struct typec_altmode_desc *desc); + const struct typec_altmode_desc *desc); void typec_unregister_altmode(struct typec_altmode *altmode); struct typec_port *typec_altmode2port(struct typec_altmode *alt); @@ -190,6 +190,7 @@ struct typec_partner_desc { * @pr_set: Set Power Role * @vconn_set: Set VCONN Role * @activate_mode: Enter/exit given Alternate Mode + * @port_type_set: Set port type * * Static capabilities of a single USB Type-C port. */ @@ -214,6 +215,9 @@ struct typec_capability { int (*activate_mode)(const struct typec_capability *, int mode, int activate); + int (*port_type_set)(const struct typec_capability *, + enum typec_port_type); + }; /* Specific to try_role(). Indicates the user want's to clear the preference. */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 32354b4b4b2b..c18e01252346 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -66,7 +66,7 @@ struct user_namespace { #endif struct ucounts *ucounts; int ucount_max[UCOUNT_COUNTS]; -}; +} __randomize_layout; struct ucounts { struct hlist_node node; @@ -112,8 +112,9 @@ extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); +extern bool in_userns(const struct user_namespace *ancestor, + const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); - struct ns_common *ns_get_owner(struct ns_common *ns); #else @@ -144,6 +145,12 @@ static inline bool userns_may_setgroups(const struct user_namespace *ns) return true; } +static inline bool in_userns(const struct user_namespace *ancestor, + const struct user_namespace *child) +{ + return true; +} + static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 60f0bb83b313..da826ed059cf 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -26,7 +26,7 @@ struct uts_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 4dff73a89758..33b0bdbb613c 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -18,29 +18,18 @@ #include <uapi/linux/uuid.h> -/* - * V1 (time-based) UUID definition [RFC 4122]. - * - the timestamp is a 60-bit value, split 32/16/12, and goes in 100ns - * increments since midnight 15th October 1582 - * - add AFS_UUID_TO_UNIX_TIME to convert unix time in 100ns units to UUID - * time - * - the clock sequence is a 14-bit counter to avoid duplicate times - */ -struct uuid_v1 { - __be32 time_low; /* low part of timestamp */ - __be16 time_mid; /* mid part of timestamp */ - __be16 time_hi_and_version; /* high part of timestamp and version */ -#define UUID_TO_UNIX_TIME 0x01b21dd213814000ULL -#define UUID_TIMEHI_MASK 0x0fff -#define UUID_VERSION_TIME 0x1000 /* time-based UUID */ -#define UUID_VERSION_NAME 0x3000 /* name-based UUID */ -#define UUID_VERSION_RANDOM 0x4000 /* (pseudo-)random generated UUID */ - u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ -#define UUID_CLOCKHI_MASK 0x3f -#define UUID_VARIANT_STD 0x80 - u8 clock_seq_low; /* clock seq low */ - u8 node[6]; /* spatially unique node ID (MAC addr) */ -}; +#define UUID_SIZE 16 + +typedef struct { + __u8 b[UUID_SIZE]; +} uuid_t; + +#define UUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_t) \ +{{ ((a) >> 24) & 0xff, ((a) >> 16) & 0xff, ((a) >> 8) & 0xff, (a) & 0xff, \ + ((b) >> 8) & 0xff, (b) & 0xff, \ + ((c) >> 8) & 0xff, (c) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) /* * The length of a UUID string ("aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee") @@ -48,27 +37,59 @@ struct uuid_v1 { */ #define UUID_STRING_LEN 36 -static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) +extern const guid_t guid_null; +extern const uuid_t uuid_null; + +static inline bool guid_equal(const guid_t *u1, const guid_t *u2) +{ + return memcmp(u1, u2, sizeof(guid_t)) == 0; +} + +static inline void guid_copy(guid_t *dst, const guid_t *src) +{ + memcpy(dst, src, sizeof(guid_t)); +} + +static inline bool guid_is_null(const guid_t *guid) { - return memcmp(&u1, &u2, sizeof(uuid_le)); + return guid_equal(guid, &guid_null); } -static inline int uuid_be_cmp(const uuid_be u1, const uuid_be u2) +static inline bool uuid_equal(const uuid_t *u1, const uuid_t *u2) { - return memcmp(&u1, &u2, sizeof(uuid_be)); + return memcmp(u1, u2, sizeof(uuid_t)) == 0; +} + +static inline void uuid_copy(uuid_t *dst, const uuid_t *src) +{ + memcpy(dst, src, sizeof(uuid_t)); +} + +static inline bool uuid_is_null(const uuid_t *uuid) +{ + return uuid_equal(uuid, &uuid_null); } void generate_random_uuid(unsigned char uuid[16]); -extern void uuid_le_gen(uuid_le *u); -extern void uuid_be_gen(uuid_be *u); +extern void guid_gen(guid_t *u); +extern void uuid_gen(uuid_t *u); bool __must_check uuid_is_valid(const char *uuid); -extern const u8 uuid_le_index[16]; -extern const u8 uuid_be_index[16]; +extern const u8 guid_index[16]; +extern const u8 uuid_index[16]; + +int guid_parse(const char *uuid, guid_t *u); +int uuid_parse(const char *uuid, uuid_t *u); + +/* backwards compatibility, don't use in new code */ +#define uuid_le_gen(u) guid_gen(u) +#define uuid_le_to_bin(guid, u) guid_parse(guid, u) -int uuid_le_to_bin(const char *uuid, uuid_le *u); -int uuid_be_to_bin(const char *uuid, uuid_be *u); +static inline int uuid_le_cmp(const guid_t u1, const guid_t u2) +{ + return memcmp(&u1, &u2, sizeof(guid_t)); +} #endif diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 6f8fbcf10dfb..af6c03f7f986 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -24,10 +24,17 @@ #ifndef MODULE_ARCH_VERMAGIC #define MODULE_ARCH_VERMAGIC "" #endif +#ifdef RANDSTRUCT_PLUGIN +#include <generated/randomize_layout_hash.h> +#define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED +#else +#define MODULE_RANDSTRUCT_PLUGIN +#endif #define VERMAGIC_STRING \ UTS_RELEASE " " \ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ - MODULE_ARCH_VERMAGIC + MODULE_ARCH_VERMAGIC \ + MODULE_RANDSTRUCT_PLUGIN diff --git a/include/linux/vfio.h b/include/linux/vfio.h index edf9b2cad277..a47b985341d1 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -97,6 +97,8 @@ extern void vfio_unregister_iommu_driver( */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); +extern bool vfio_external_group_match_file(struct vfio_group *group, + struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); @@ -150,7 +152,7 @@ extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, size_t *data_size); struct pci_dev; -#ifdef CONFIG_EEH +#if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH) extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev); extern void vfio_spapr_pci_eeh_release(struct pci_dev *pdev); extern long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, @@ -171,7 +173,7 @@ static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, { return -ENOTTY; } -#endif /* CONFIG_EEH */ +#endif /* CONFIG_VFIO_SPAPR_EEH */ /* * IRQfd - generic @@ -183,7 +185,7 @@ struct virqfd { void (*thread)(void *, void *); void *data; struct work_struct inject; - wait_queue_t wait; + wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; struct virqfd **pvirqfd; diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 5209b5ed2a64..32fb046f2173 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -18,9 +18,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; break; - case VIRTIO_NET_HDR_GSO_UDP: - gso_type = SKB_GSO_UDP; - break; default: return -EINVAL; } @@ -73,8 +70,6 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index d84ae90ccd5c..d77bc35278b0 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -41,6 +41,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, PAGEOUTRUN, PGROTATED, DROP_PAGECACHE, DROP_SLAB, + OOM_KILL, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, NUMA_HUGE_PTE_UPDATES, @@ -84,6 +85,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, + THP_SWPOUT, + THP_SWPOUT_FALLBACK, #endif #ifdef CONFIG_MEMORY_BALLOON BALLOON_INFLATE, @@ -93,10 +96,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif #endif #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ @@ -105,6 +106,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, VMACACHE_FIND_HITS, VMACACHE_FULL_FLUSHES, #endif +#ifdef CONFIG_SWAP + SWAP_RA, + SWAP_RA_HIT, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 613771909b6e..ade7cb5f1359 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -3,7 +3,6 @@ #include <linux/types.h> #include <linux/percpu.h> -#include <linux/mm.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> @@ -108,8 +107,37 @@ static inline void vm_events_fold_cpu(int cpu) * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; +extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; +#ifdef CONFIG_NUMA +static inline void zone_numa_state_add(long x, struct zone *zone, + enum numa_stat_item item) +{ + atomic_long_add(x, &zone->vm_numa_stat[item]); + atomic_long_add(x, &vm_numa_stat[item]); +} + +static inline unsigned long global_numa_state(enum numa_stat_item item) +{ + long x = atomic_long_read(&vm_numa_stat[item]); + + return x; +} + +static inline unsigned long zone_numa_state_snapshot(struct zone *zone, + enum numa_stat_item item) +{ + long x = atomic_long_read(&zone->vm_numa_stat[item]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; + + return x; +} +#endif /* CONFIG_NUMA */ + static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { @@ -124,7 +152,7 @@ static inline void node_page_state_add(long x, struct pglist_data *pgdat, atomic_long_add(x, &vm_node_stat[item]); } -static inline unsigned long global_page_state(enum zone_stat_item item) +static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP @@ -195,12 +223,14 @@ static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat, #ifdef CONFIG_NUMA +extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); extern unsigned long sum_zone_node_page_state(int node, - enum zone_stat_item item); + enum zone_stat_item item); +extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); #else -#define sum_zone_node_page_state(node, item) global_page_state(item) +#define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #endif /* CONFIG_NUMA */ diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index f38c10ba3ff5..30b6e0d2a942 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -13,6 +13,7 @@ #ifndef _LINUX_VT_BUFFER_H_ #define _LINUX_VT_BUFFER_H_ +#include <linux/string.h> #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) #include <asm/vga.h> @@ -26,24 +27,33 @@ #ifndef VT_BUF_HAVE_MEMSETW static inline void scr_memsetw(u16 *s, u16 c, unsigned int count) { +#ifdef VT_BUF_HAVE_RW count /= 2; while (count--) scr_writew(c, s++); +#else + memset16(s, c, count / 2); +#endif } #endif #ifndef VT_BUF_HAVE_MEMCPYW static inline void scr_memcpyw(u16 *d, const u16 *s, unsigned int count) { +#ifdef VT_BUF_HAVE_RW count /= 2; while (count--) scr_writew(scr_readw(s++), d++); +#else + memcpy(d, s, count); +#endif } #endif #ifndef VT_BUF_HAVE_MEMMOVEW static inline void scr_memmovew(u16 *d, const u16 *s, unsigned int count) { +#ifdef VT_BUF_HAVE_RW if (d < s) scr_memcpyw(d, s, count); else { @@ -53,6 +63,9 @@ static inline void scr_memmovew(u16 *d, const u16 *s, unsigned int count) while (count--) scr_writew(scr_readw(--s), --d); } +#else + memmove(d, s, count); +#endif } #endif diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 0681fe25abeb..18b405e3cd93 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -67,19 +67,12 @@ static inline void vtime_account_system(struct task_struct *tsk) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); -extern void vtime_account_user(struct task_struct *tsk); extern void vtime_user_enter(struct task_struct *tsk); - -static inline void vtime_user_exit(struct task_struct *tsk) -{ - vtime_account_user(tsk); -} - +extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -static inline void vtime_account_user(struct task_struct *tsk) { } static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } diff --git a/include/linux/w1.h b/include/linux/w1.h new file mode 100644 index 000000000000..5b2972946dda --- /dev/null +++ b/include/linux/w1.h @@ -0,0 +1,324 @@ +/* + * Copyright (c) 2004 Evgeniy Polyakov <zbr@ioremap.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_W1_H +#define __LINUX_W1_H + +#include <linux/device.h> + +/** + * struct w1_reg_num - broken out slave device id + * + * @family: identifies the type of device + * @id: along with family is the unique device id + * @crc: checksum of the other bytes + */ +struct w1_reg_num { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u64 family:8, + id:48, + crc:8; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u64 crc:8, + id:48, + family:8; +#else +#error "Please fix <asm/byteorder.h>" +#endif +}; + +#ifdef __KERNEL__ + +#define W1_MAXNAMELEN 32 + +#define W1_SEARCH 0xF0 +#define W1_ALARM_SEARCH 0xEC +#define W1_CONVERT_TEMP 0x44 +#define W1_SKIP_ROM 0xCC +#define W1_COPY_SCRATCHPAD 0x48 +#define W1_WRITE_SCRATCHPAD 0x4E +#define W1_READ_SCRATCHPAD 0xBE +#define W1_READ_ROM 0x33 +#define W1_READ_PSUPPLY 0xB4 +#define W1_MATCH_ROM 0x55 +#define W1_RESUME_CMD 0xA5 + +/** + * struct w1_slave - holds a single slave device on the bus + * + * @owner: Points to the one wire "wire" kernel module. + * @name: Device id is ascii. + * @w1_slave_entry: data for the linked list + * @reg_num: the slave id in binary + * @refcnt: reference count, delete when 0 + * @flags: bit flags for W1_SLAVE_ACTIVE W1_SLAVE_DETACH + * @ttl: decrement per search this slave isn't found, deatch at 0 + * @master: bus which this slave is on + * @family: module for device family type + * @family_data: pointer for use by the family module + * @dev: kernel device identifier + * @hwmon: pointer to hwmon device + * + */ +struct w1_slave { + struct module *owner; + unsigned char name[W1_MAXNAMELEN]; + struct list_head w1_slave_entry; + struct w1_reg_num reg_num; + atomic_t refcnt; + int ttl; + unsigned long flags; + + struct w1_master *master; + struct w1_family *family; + void *family_data; + struct device dev; + struct device *hwmon; +}; + +typedef void (*w1_slave_found_callback)(struct w1_master *, u64); + +/** + * struct w1_bus_master - operations available on a bus master + * + * @data: the first parameter in all the functions below + * + * @read_bit: Sample the line level @return the level read (0 or 1) + * + * @write_bit: Sets the line level + * + * @touch_bit: the lowest-level function for devices that really support the + * 1-wire protocol. + * touch_bit(0) = write-0 cycle + * touch_bit(1) = write-1 / read cycle + * @return the bit read (0 or 1) + * + * @read_byte: Reads a bytes. Same as 8 touch_bit(1) calls. + * @return the byte read + * + * @write_byte: Writes a byte. Same as 8 touch_bit(x) calls. + * + * @read_block: Same as a series of read_byte() calls + * @return the number of bytes read + * + * @write_block: Same as a series of write_byte() calls + * + * @triplet: Combines two reads and a smart write for ROM searches + * @return bit0=Id bit1=comp_id bit2=dir_taken + * + * @reset_bus: long write-0 with a read for the presence pulse detection + * @return -1=Error, 0=Device present, 1=No device present + * + * @set_pullup: Put out a strong pull-up pulse of the specified duration. + * @return -1=Error, 0=completed + * + * @search: Really nice hardware can handles the different types of ROM search + * w1_master* is passed to the slave found callback. + * u8 is search_type, W1_SEARCH or W1_ALARM_SEARCH + * + * Note: read_bit and write_bit are very low level functions and should only + * be used with hardware that doesn't really support 1-wire operations, + * like a parallel/serial port. + * Either define read_bit and write_bit OR define, at minimum, touch_bit and + * reset_bus. + * + */ +struct w1_bus_master { + void *data; + + u8 (*read_bit)(void *); + + void (*write_bit)(void *, u8); + + u8 (*touch_bit)(void *, u8); + + u8 (*read_byte)(void *); + + void (*write_byte)(void *, u8); + + u8 (*read_block)(void *, u8 *, int); + + void (*write_block)(void *, const u8 *, int); + + u8 (*triplet)(void *, u8); + + u8 (*reset_bus)(void *); + + u8 (*set_pullup)(void *, int); + + void (*search)(void *, struct w1_master *, + u8, w1_slave_found_callback); +}; + +/** + * enum w1_master_flags - bitfields used in w1_master.flags + * @W1_ABORT_SEARCH: abort searching early on shutdown + * @W1_WARN_MAX_COUNT: limit warning when the maximum count is reached + */ +enum w1_master_flags { + W1_ABORT_SEARCH = 0, + W1_WARN_MAX_COUNT = 1, +}; + +/** + * struct w1_master - one per bus master + * @w1_master_entry: master linked list + * @owner: module owner + * @name: dynamically allocate bus name + * @list_mutex: protect slist and async_list + * @slist: linked list of slaves + * @async_list: linked list of netlink commands to execute + * @max_slave_count: maximum number of slaves to search for at a time + * @slave_count: current number of slaves known + * @attempts: number of searches ran + * @slave_ttl: number of searches before a slave is timed out + * @initialized: prevent init/removal race conditions + * @id: w1 bus number + * @search_count: number of automatic searches to run, -1 unlimited + * @search_id: allows continuing a search + * @refcnt: reference count + * @priv: private data storage + * @enable_pullup: allows a strong pullup + * @pullup_duration: time for the next strong pullup + * @flags: one of w1_master_flags + * @thread: thread for bus search and netlink commands + * @mutex: protect most of w1_master + * @bus_mutex: pretect concurrent bus access + * @driver: sysfs driver + * @dev: sysfs device + * @bus_master: io operations available + * @seq: sequence number used for netlink broadcasts + */ +struct w1_master { + struct list_head w1_master_entry; + struct module *owner; + unsigned char name[W1_MAXNAMELEN]; + /* list_mutex protects just slist and async_list so slaves can be + * searched for and async commands added while the master has + * w1_master.mutex locked and is operating on the bus. + * lock order w1_mlock, w1_master.mutex, w1_master.list_mutex + */ + struct mutex list_mutex; + struct list_head slist; + struct list_head async_list; + int max_slave_count, slave_count; + unsigned long attempts; + int slave_ttl; + int initialized; + u32 id; + int search_count; + /* id to start searching on, to continue a search or 0 to restart */ + u64 search_id; + + atomic_t refcnt; + + void *priv; + + /** 5V strong pullup enabled flag, 1 enabled, zero disabled. */ + int enable_pullup; + /** 5V strong pullup duration in milliseconds, zero disabled. */ + int pullup_duration; + + long flags; + + struct task_struct *thread; + struct mutex mutex; + struct mutex bus_mutex; + + struct device_driver *driver; + struct device dev; + + struct w1_bus_master *bus_master; + + u32 seq; +}; + +int w1_add_master_device(struct w1_bus_master *master); +void w1_remove_master_device(struct w1_bus_master *master); + +/** + * struct w1_family_ops - operations for a family type + * @add_slave: add_slave + * @remove_slave: remove_slave + * @groups: sysfs group + * @chip_info: pointer to struct hwmon_chip_info + */ +struct w1_family_ops { + int (*add_slave)(struct w1_slave *sl); + void (*remove_slave)(struct w1_slave *sl); + const struct attribute_group **groups; + const struct hwmon_chip_info *chip_info; +}; + +/** + * struct w1_family - reference counted family structure. + * @family_entry: family linked list + * @fid: 8 bit family identifier + * @fops: operations for this family + * @refcnt: reference counter + */ +struct w1_family { + struct list_head family_entry; + u8 fid; + + struct w1_family_ops *fops; + + atomic_t refcnt; +}; + +int w1_register_family(struct w1_family *family); +void w1_unregister_family(struct w1_family *family); + +/** + * module_w1_driver() - Helper macro for registering a 1-Wire families + * @__w1_family: w1_family struct + * + * Helper macro for 1-Wire families which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_w1_family(__w1_family) \ + module_driver(__w1_family, w1_register_family, \ + w1_unregister_family) + +u8 w1_triplet(struct w1_master *dev, int bdir); +void w1_write_8(struct w1_master *, u8); +u8 w1_read_8(struct w1_master *); +int w1_reset_bus(struct w1_master *); +u8 w1_calc_crc8(u8 *, int); +void w1_write_block(struct w1_master *, const u8 *, int); +void w1_touch_block(struct w1_master *, u8 *, int); +u8 w1_read_block(struct w1_master *, u8 *, int); +int w1_reset_select_slave(struct w1_slave *sl); +int w1_reset_resume_command(struct w1_master *); +void w1_next_pullup(struct w1_master *, int); + +static inline struct w1_slave* dev_to_w1_slave(struct device *dev) +{ + return container_of(dev, struct w1_slave, dev); +} + +static inline struct w1_slave* kobj_to_w1_slave(struct kobject *kobj) +{ + return dev_to_w1_slave(container_of(kobj, struct device, kobj)); +} + +static inline struct w1_master* dev_to_w1_master(struct device *dev) +{ + return container_of(dev, struct w1_master, dev); +} + +#endif /* __KERNEL__ */ + +#endif /* __LINUX_W1_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index db076ca7f11d..87c4641023fb 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -10,38 +10,31 @@ #include <asm/current.h> #include <uapi/linux/wait.h> -typedef struct __wait_queue wait_queue_t; -typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); -int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key); +typedef struct wait_queue_entry wait_queue_entry_t; -/* __wait_queue::flags */ +typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); +int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); + +/* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 +#define WQ_FLAG_BOOKMARK 0x04 -struct __wait_queue { +/* + * A single wait-queue entry structure: + */ +struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; - struct list_head task_list; -}; - -struct wait_bit_key { - void *flags; - int bit_nr; -#define WAIT_ATOMIC_T_BIT_NR -1 - unsigned long timeout; -}; - -struct wait_bit_queue { - struct wait_bit_key key; - wait_queue_t wait; + struct list_head entry; }; -struct __wait_queue_head { +struct wait_queue_head { spinlock_t lock; - struct list_head task_list; + struct list_head head; }; -typedef struct __wait_queue_head wait_queue_head_t; +typedef struct wait_queue_head wait_queue_head_t; struct task_struct; @@ -49,82 +42,76 @@ struct task_struct; * Macros for declaration and initialisaton of the datatypes */ -#define __WAITQUEUE_INITIALIZER(name, tsk) { \ - .private = tsk, \ - .func = default_wake_function, \ - .task_list = { NULL, NULL } } +#define __WAITQUEUE_INITIALIZER(name, tsk) { \ + .private = tsk, \ + .func = default_wake_function, \ + .entry = { NULL, NULL } } -#define DECLARE_WAITQUEUE(name, tsk) \ - wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk) +#define DECLARE_WAITQUEUE(name, tsk) \ + struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) -#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .task_list = { &(name).task_list, &(name).task_list } } +#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .head = { &(name).head, &(name).head } } #define DECLARE_WAIT_QUEUE_HEAD(name) \ - wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name) - -#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ - { .flags = word, .bit_nr = bit, } - -#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p) \ - { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, } + struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) -extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *); +extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); -#define init_waitqueue_head(q) \ - do { \ - static struct lock_class_key __key; \ - \ - __init_waitqueue_head((q), #q, &__key); \ +#define init_waitqueue_head(wq_head) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ - wait_queue_head_t name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) + struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif -static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p) +static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { - q->flags = 0; - q->private = p; - q->func = default_wake_function; + wq_entry->flags = 0; + wq_entry->private = p; + wq_entry->func = default_wake_function; } static inline void -init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) +init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { - q->flags = 0; - q->private = NULL; - q->func = func; + wq_entry->flags = 0; + wq_entry->private = NULL; + wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue - * @q: the waitqueue to test for waiters + * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * - * Use either while holding wait_queue_head_t::lock or when used for wakeups + * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like: * * CPU0 - waker CPU1 - waiter * * for (;;) { - * @cond = true; prepare_to_wait(&wq, &wait, state); + * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() - * if (waitqueue_active(wq)) if (@cond) - * wake_up(wq); break; + * if (waitqueue_active(wq_head)) if (@cond) + * wake_up(wq_head); break; * schedule(); * } - * finish_wait(&wq, &wait); + * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll @@ -133,20 +120,20 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ -static inline int waitqueue_active(wait_queue_head_t *q) +static inline int waitqueue_active(struct wait_queue_head *wq_head) { - return !list_empty(&q->task_list); + return !list_empty(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes - * @wq: wait queue head + * @wq_head: wait queue head * - * Returns true if wq has waiting processes + * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ -static inline bool wq_has_sleeper(wait_queue_head_t *wq) +static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the @@ -156,63 +143,53 @@ static inline bool wq_has_sleeper(wait_queue_head_t *wq) * waiting side. */ smp_mb(); - return waitqueue_active(wq); + return waitqueue_active(wq_head); } -extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); -extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait); -extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); +extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); -static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new) +static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_add(&new->task_list, &head->task_list); + list_add(&wq_entry->entry, &wq_head->head); } /* * Used for wake-one threads: */ static inline void -__add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +__add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - wait->flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue(wq_head, wq_entry); } -static inline void __add_wait_queue_tail(wait_queue_head_t *head, - wait_queue_t *new) +static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_add_tail(&new->task_list, &head->task_list); + list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void -__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +__add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - wait->flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void -__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) +__remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_del(&old->task_list); + list_del(&wq_entry->entry); } -typedef int wait_bit_action_f(struct wait_bit_key *, int mode); -void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); -void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); -void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); -void __wake_up_bit(wait_queue_head_t *, void *, int); -int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); -int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); -void wake_up_bit(void *, int); -void wake_up_atomic_t(atomic_t *); -int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned); -int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long); -int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned); -int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned); -wait_queue_head_t *bit_waitqueue(void *, int); +void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); +void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); +void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head, + unsigned int mode, void *key, wait_queue_entry_t *bookmark); +void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); +void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -228,28 +205,28 @@ wait_queue_head_t *bit_waitqueue(void *, int); /* * Wakeup macros to be used to report events to the targets. */ -#define wake_up_poll(x, m) \ +#define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, (void *) (m)) -#define wake_up_locked_poll(x, m) \ +#define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) -#define wake_up_interruptible_poll(x, m) \ +#define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) -#define wake_up_interruptible_sync_poll(x, m) \ +#define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m)) -#define ___wait_cond_timeout(condition) \ -({ \ - bool __cond = (condition); \ - if (__cond && !__ret) \ - __ret = 1; \ - __cond || !__ret; \ +#define ___wait_cond_timeout(condition) \ +({ \ + bool __cond = (condition); \ + if (__cond && !__ret) \ + __ret = 1; \ + __cond || !__ret; \ }) -#define ___wait_is_interruptible(state) \ - (!__builtin_constant_p(state) || \ - state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ +#define ___wait_is_interruptible(state) \ + (!__builtin_constant_p(state) || \ + state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ -extern void init_wait_entry(wait_queue_t *__wait, int flags); +extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret @@ -263,108 +240,108 @@ extern void init_wait_entry(wait_queue_t *__wait, int flags); * otherwise. */ -#define ___wait_event(wq, condition, state, exclusive, ret, cmd) \ -({ \ - __label__ __out; \ - wait_queue_t __wait; \ - long __ret = ret; /* explicit shadow */ \ - \ - init_wait_entry(&__wait, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ - for (;;) { \ - long __int = prepare_to_wait_event(&wq, &__wait, state);\ - \ - if (condition) \ - break; \ - \ - if (___wait_is_interruptible(state) && __int) { \ - __ret = __int; \ - goto __out; \ - } \ - \ - cmd; \ - } \ - finish_wait(&wq, &__wait); \ -__out: __ret; \ +#define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ +({ \ + __label__ __out; \ + struct wait_queue_entry __wq_entry; \ + long __ret = ret; /* explicit shadow */ \ + \ + init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ + for (;;) { \ + long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ + \ + if (condition) \ + break; \ + \ + if (___wait_is_interruptible(state) && __int) { \ + __ret = __int; \ + goto __out; \ + } \ + \ + cmd; \ + } \ + finish_wait(&wq_head, &__wq_entry); \ +__out: __ret; \ }) -#define __wait_event(wq, condition) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __wait_event(wq_head, condition) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event(wq, condition) \ -do { \ - might_sleep(); \ - if (condition) \ - break; \ - __wait_event(wq, condition); \ +#define wait_event(wq_head, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __wait_event(wq_head, condition); \ } while (0) -#define __io_wait_event(wq, condition) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __io_wait_event(wq_head, condition) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ -#define io_wait_event(wq, condition) \ -do { \ - might_sleep(); \ - if (condition) \ - break; \ - __io_wait_event(wq, condition); \ +#define io_wait_event(wq_head, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __io_wait_event(wq_head, condition); \ } while (0) -#define __wait_event_freezable(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ +#define __wait_event_freezable(wq_head, condition) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule(); try_to_freeze()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The - * @condition is checked each time the waitqueue @wq is woken up. + * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event_freezable(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_freezable(wq, condition); \ - __ret; \ +#define wait_event_freezable(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_freezable(wq_head, condition); \ + __ret; \ }) -#define __wait_event_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_UNINTERRUPTIBLE, 0, timeout, \ +#define __wait_event_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -375,83 +352,83 @@ do { \ * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ -#define wait_event_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_timeout(wq, condition, timeout); \ - __ret; \ +#define wait_event_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_timeout(wq_head, condition, timeout); \ + __ret; \ }) -#define __wait_event_freezable_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ +#define __wait_event_freezable_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret); try_to_freeze()) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ -#define wait_event_freezable_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_freezable_timeout(wq, condition, timeout); \ - __ret; \ +#define wait_event_freezable_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ + __ret; \ }) -#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ +#define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ -#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ -do { \ - if (condition) \ - break; \ - __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2); \ +#define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) -#define __wait_event_cmd(wq, condition, cmd1, cmd2) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event_cmd(wq, condition, cmd1, cmd2) \ -do { \ - if (condition) \ - break; \ - __wait_event_cmd(wq, condition, cmd1, cmd2); \ +#define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) -#define __wait_event_interruptible(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ +#define __wait_event_interruptible(wq_head, condition) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -459,29 +436,29 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_interruptible(wq, condition); \ - __ret; \ +#define wait_event_interruptible(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_interruptible(wq_head, condition); \ + __ret; \ }) -#define __wait_event_interruptible_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ +#define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -493,50 +470,49 @@ do { \ * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ -#define wait_event_interruptible_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_timeout(wq, \ - condition, timeout); \ - __ret; \ +#define wait_event_interruptible_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_interruptible_timeout(wq_head, \ + condition, timeout); \ + __ret; \ }) -#define __wait_event_hrtimeout(wq, condition, timeout, state) \ -({ \ - int __ret = 0; \ - struct hrtimer_sleeper __t; \ - \ - hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ - HRTIMER_MODE_REL); \ - hrtimer_init_sleeper(&__t, current); \ - if ((timeout) != KTIME_MAX) \ - hrtimer_start_range_ns(&__t.timer, timeout, \ - current->timer_slack_ns, \ - HRTIMER_MODE_REL); \ - \ - __ret = ___wait_event(wq, condition, state, 0, 0, \ - if (!__t.task) { \ - __ret = -ETIME; \ - break; \ - } \ - schedule()); \ - \ - hrtimer_cancel(&__t.timer); \ - destroy_hrtimer_on_stack(&__t.timer); \ - __ret; \ +#define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ +({ \ + int __ret = 0; \ + struct hrtimer_sleeper __t; \ + \ + hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \ + hrtimer_init_sleeper(&__t, current); \ + if ((timeout) != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ + HRTIMER_MODE_REL); \ + \ + __ret = ___wait_event(wq_head, condition, state, 0, 0, \ + if (!__t.task) { \ + __ret = -ETIME; \ + break; \ + } \ + schedule()); \ + \ + hrtimer_cancel(&__t.timer); \ + destroy_hrtimer_on_stack(&__t.timer); \ + __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -544,14 +520,14 @@ do { \ * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ -#define wait_event_hrtimeout(wq, condition, timeout) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_hrtimeout(wq, condition, timeout, \ - TASK_UNINTERRUPTIBLE); \ - __ret; \ +#define wait_event_hrtimeout(wq_head, condition, timeout) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ + TASK_UNINTERRUPTIBLE); \ + __ret; \ }) /** @@ -570,73 +546,73 @@ do { \ * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ -#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ -({ \ - long __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_hrtimeout(wq, condition, timeout, \ - TASK_INTERRUPTIBLE); \ - __ret; \ +#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ +({ \ + long __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ }) -#define __wait_event_interruptible_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ +#define __wait_event_interruptible_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) -#define wait_event_interruptible_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_interruptible_exclusive(wq, condition);\ - __ret; \ +#define wait_event_interruptible_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_interruptible_exclusive(wq, condition); \ + __ret; \ }) -#define __wait_event_killable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ +#define __wait_event_killable_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) -#define wait_event_killable_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_killable_exclusive(wq, condition); \ - __ret; \ +#define wait_event_killable_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_killable_exclusive(wq, condition); \ + __ret; \ }) -#define __wait_event_freezable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ +#define __wait_event_freezable_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule(); try_to_freeze()) -#define wait_event_freezable_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_freezable_exclusive(wq, condition);\ - __ret; \ +#define wait_event_freezable_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_freezable_exclusive(wq, condition); \ + __ret; \ }) -extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *); -extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); - -#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ -({ \ - int __ret; \ - DEFINE_WAIT(__wait); \ - if (exclusive) \ - __wait.flags |= WQ_FLAG_EXCLUSIVE; \ - do { \ - __ret = fn(&(wq), &__wait); \ - if (__ret) \ - break; \ - } while (!(condition)); \ - __remove_wait_queue(&(wq), &__wait); \ - __set_current_state(TASK_RUNNING); \ - __ret; \ +extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); +extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); + +#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ +({ \ + int __ret; \ + DEFINE_WAIT(__wait); \ + if (exclusive) \ + __wait.flags |= WQ_FLAG_EXCLUSIVE; \ + do { \ + __ret = fn(&(wq), &__wait); \ + if (__ret) \ + break; \ + } while (!(condition)); \ + __remove_wait_queue(&(wq), &__wait); \ + __set_current_state(TASK_RUNNING); \ + __ret; \ }) @@ -663,8 +639,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_locked(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_locked(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** @@ -690,8 +666,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_locked_irq(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_locked_irq(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** @@ -721,8 +697,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_exclusive_locked(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_exclusive_locked(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** @@ -752,22 +728,22 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ - ((condition) \ +#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ + ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) -#define __wait_event_killable(wq, condition) \ +#define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** * wait_event_killable - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -775,21 +751,58 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_killable(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_killable(wq, condition); \ - __ret; \ +#define wait_event_killable(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_killable(wq_head, condition); \ + __ret; \ +}) + +#define __wait_event_killable_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_KILLABLE, 0, timeout, \ + __ret = schedule_timeout(__ret)) + +/** + * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_KILLABLE) until the + * @condition evaluates to true or a kill signal is received. + * The @condition is checked each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * Returns: + * 0 if the @condition evaluated to %false after the @timeout elapsed, + * 1 if the @condition evaluated to %true after the @timeout elapsed, + * the remaining jiffies (at least 1) if the @condition evaluated + * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was + * interrupted by a kill signal. + * + * Only kill signals interrupt this process. + */ +#define wait_event_killable_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_killable_timeout(wq_head, \ + condition, timeout); \ + __ret; \ }) -#define __wait_event_lock_irq(wq, condition, lock, cmd) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ +#define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ spin_lock_irq(&lock)) /** @@ -797,7 +810,7 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * condition is checked under the lock. This * is expected to be called with the lock * taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. @@ -806,7 +819,7 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -815,11 +828,11 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ -#define wait_event_lock_irq_cmd(wq, condition, lock, cmd) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, cmd); \ +#define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** @@ -827,14 +840,14 @@ do { \ * condition is checked under the lock. This * is expected to be called with the lock * taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -842,26 +855,26 @@ do { \ * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ -#define wait_event_lock_irq(wq, condition, lock) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, ); \ +#define wait_event_lock_irq(wq_head, condition, lock) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) -#define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ +#define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. @@ -870,7 +883,7 @@ do { \ * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -882,27 +895,27 @@ do { \ * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __ret = __wait_event_interruptible_lock_irq(wq, \ - condition, lock, cmd); \ - __ret; \ +#define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_interruptible_lock_irq(wq_head, \ + condition, lock, cmd); \ + __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -913,28 +926,28 @@ do { \ * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_lock_irq(wq, condition, lock) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __ret = __wait_event_interruptible_lock_irq(wq, \ - condition, lock,); \ - __ret; \ +#define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_interruptible_lock_irq(wq_head, \ + condition, lock,); \ + __ret; \ }) -#define __wait_event_interruptible_lock_irq_timeout(wq, condition, \ - lock, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ - spin_unlock_irq(&lock); \ - __ret = schedule_timeout(__ret); \ +#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition, \ + lock, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ + spin_unlock_irq(&lock); \ + __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. @@ -942,7 +955,7 @@ do { \ * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -954,263 +967,42 @@ do { \ * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ -#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock, \ - timeout) \ -({ \ - long __ret = timeout; \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_lock_irq_timeout( \ - wq, condition, lock, timeout); \ - __ret; \ +#define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ + timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_interruptible_lock_irq_timeout( \ + wq_head, condition, lock, timeout); \ + __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ -void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state); -void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state); -long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state); -void finish_wait(wait_queue_head_t *q, wait_queue_t *wait); -long wait_woken(wait_queue_t *wait, unsigned mode, long timeout); -int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); - -#define DEFINE_WAIT_FUNC(name, function) \ - wait_queue_t name = { \ - .private = current, \ - .func = function, \ - .task_list = LIST_HEAD_INIT((name).task_list), \ +void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); +int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); +int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); + +#define DEFINE_WAIT_FUNC(name, function) \ + struct wait_queue_entry name = { \ + .private = current, \ + .func = function, \ + .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) -#define DEFINE_WAIT_BIT(name, word, bit) \ - struct wait_bit_queue name = { \ - .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ - .wait = { \ - .private = current, \ - .func = wake_bit_function, \ - .task_list = \ - LIST_HEAD_INIT((name).wait.task_list), \ - }, \ - } - -#define init_wait(wait) \ - do { \ - (wait)->private = current; \ - (wait)->func = autoremove_wake_function; \ - INIT_LIST_HEAD(&(wait)->task_list); \ - (wait)->flags = 0; \ +#define init_wait(wait) \ + do { \ + (wait)->private = current; \ + (wait)->func = autoremove_wake_function; \ + INIT_LIST_HEAD(&(wait)->entry); \ + (wait)->flags = 0; \ } while (0) - -extern int bit_wait(struct wait_bit_key *, int); -extern int bit_wait_io(struct wait_bit_key *, int); -extern int bit_wait_timeout(struct wait_bit_key *, int); -extern int bit_wait_io_timeout(struct wait_bit_key *, int); - -/** - * wait_on_bit - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit. - * For instance, if one were to have waiters on a bitflag, one would - * call wait_on_bit() in threads waiting for the bit to clear. - * One uses wait_on_bit() where one is waiting for the bit to clear, - * but has no intention of setting it. - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, - bit_wait, - mode); -} - -/** - * wait_on_bit_io - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), but calls - * io_schedule() instead of schedule() for the actual waiting. - * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit_io(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, - bit_wait_io, - mode); -} - -/** - * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * @timeout: timeout, in jiffies - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), except also takes a - * timeout parameter. - * - * Returned value will be zero if the bit was cleared before the - * @timeout elapsed, or non-zero if the @timeout elapsed or process - * received a signal and the mode permitted wakeup on that signal. - */ -static inline int -wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, - unsigned long timeout) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_timeout(word, bit, - bit_wait_timeout, - mode, timeout); -} - -/** - * wait_on_bit_action - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared, and allow the waiting action to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. - * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, - unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, action, mode); -} - -/** - * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit - * when one intends to set it, for instance, trying to lock bitflags. - * For instance, if one were to have waiters trying to set bitflag - * and waiting for it to clear before setting it, one would call - * wait_on_bit() in threads waiting to be able to set the bit. - * One uses wait_on_bit_lock() where one is waiting for the bit to - * clear with the intention of setting it, and when done, clearing it. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); -} - -/** - * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to atomically set it. This is similar - * to wait_on_bit(), but calls io_schedule() instead of schedule() - * for the actual waiting. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); -} - -/** - * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to set it, and allow the waiting action - * to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, - unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, action, mode); -} - -/** - * wait_on_atomic_t - Wait for an atomic_t to become 0 - * @val: The atomic value being waited on, a kernel virtual address - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Wait for an atomic_t to become 0. We abuse the bit-wait waitqueue table for - * the purpose of getting a waitqueue, but we set the key to a bit number - * outside of the target 'word'. - */ -static inline -int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode) -{ - might_sleep(); - if (atomic_read(val) == 0) - return 0; - return out_of_line_wait_on_atomic_t(val, action, mode); -} - #endif /* _LINUX_WAIT_H */ diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h new file mode 100644 index 000000000000..12b26660d7e9 --- /dev/null +++ b/include/linux/wait_bit.h @@ -0,0 +1,261 @@ +#ifndef _LINUX_WAIT_BIT_H +#define _LINUX_WAIT_BIT_H + +/* + * Linux wait-bit related types and methods: + */ +#include <linux/wait.h> + +struct wait_bit_key { + void *flags; + int bit_nr; +#define WAIT_ATOMIC_T_BIT_NR -1 + unsigned long timeout; +}; + +struct wait_bit_queue_entry { + struct wait_bit_key key; + struct wait_queue_entry wq_entry; +}; + +#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ + { .flags = word, .bit_nr = bit, } + +#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p) \ + { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, } + +typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); +void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); +int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); +int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); +void wake_up_bit(void *word, int bit); +void wake_up_atomic_t(atomic_t *p); +int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); +int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_atomic_t(atomic_t *p, int (*)(atomic_t *), unsigned int mode); +struct wait_queue_head *bit_waitqueue(void *word, int bit); +extern void __init wait_bit_init(void); + +int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); + +#define DEFINE_WAIT_BIT(name, word, bit) \ + struct wait_bit_queue_entry name = { \ + .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ + .wq_entry = { \ + .private = current, \ + .func = wake_bit_function, \ + .entry = \ + LIST_HEAD_INIT((name).wq_entry.entry), \ + }, \ + } + +extern int bit_wait(struct wait_bit_key *key, int bit); +extern int bit_wait_io(struct wait_bit_key *key, int bit); +extern int bit_wait_timeout(struct wait_bit_key *key, int bit); +extern int bit_wait_io_timeout(struct wait_bit_key *key, int bit); + +/** + * wait_on_bit - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit. + * For instance, if one were to have waiters on a bitflag, one would + * call wait_on_bit() in threads waiting for the bit to clear. + * One uses wait_on_bit() where one is waiting for the bit to clear, + * but has no intention of setting it. + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait, + mode); +} + +/** + * wait_on_bit_io - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), but calls + * io_schedule() instead of schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_io(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait_io, + mode); +} + +/** + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * @timeout: timeout, in jiffies + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), except also takes a + * timeout parameter. + * + * Returned value will be zero if the bit was cleared before the + * @timeout elapsed, or non-zero if the @timeout elapsed or process + * received a signal and the mode permitted wakeup on that signal. + */ +static inline int +wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, + unsigned long timeout) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_timeout(word, bit, + bit_wait_timeout, + mode, timeout); +} + +/** + * wait_on_bit_action - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared, and allow the waiting action to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, action, mode); +} + +/** + * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit + * when one intends to set it, for instance, trying to lock bitflags. + * For instance, if one were to have waiters trying to set bitflag + * and waiting for it to clear before setting it, one would call + * wait_on_bit() in threads waiting to be able to set the bit. + * One uses wait_on_bit_lock() where one is waiting for the bit to + * clear with the intention of setting it, and when done, clearing it. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); +} + +/** + * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to atomically set it. This is similar + * to wait_on_bit(), but calls io_schedule() instead of schedule() + * for the actual waiting. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); +} + +/** + * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to set it, and allow the waiting action + * to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, action, mode); +} + +/** + * wait_on_atomic_t - Wait for an atomic_t to become 0 + * @val: The atomic value being waited on, a kernel virtual address + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Wait for an atomic_t to become 0. We abuse the bit-wait waitqueue table for + * the purpose of getting a waitqueue, but we set the key to a bit number + * outside of the target 'word'. + */ +static inline +int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode) +{ + might_sleep(); + if (atomic_read(val) == 0) + return 0; + return out_of_line_wait_on_atomic_t(val, action, mode); +} + +#endif /* _LINUX_WAIT_BIT_H */ diff --git a/include/linux/wmi.h b/include/linux/wmi.h new file mode 100644 index 000000000000..cd0d7734dc49 --- /dev/null +++ b/include/linux/wmi.h @@ -0,0 +1,59 @@ +/* + * wmi.h - ACPI WMI interface + * + * Copyright (c) 2015 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _LINUX_WMI_H +#define _LINUX_WMI_H + +#include <linux/device.h> +#include <linux/acpi.h> + +struct wmi_device { + struct device dev; + + /* True for data blocks implementing the Set Control Method */ + bool setable; +}; + +/* Caller must kfree the result. */ +extern union acpi_object *wmidev_block_query(struct wmi_device *wdev, + u8 instance); + +/* Gets another device on the same bus. Caller must put_device the result. */ +extern struct wmi_device *wmidev_get_other_guid(struct wmi_device *wdev, + const char *guid_string); + +struct wmi_device_id { + const char *guid_string; +}; + +struct wmi_driver { + struct device_driver driver; + const struct wmi_device_id *id_table; + + int (*probe)(struct wmi_device *wdev); + int (*remove)(struct wmi_device *wdev); + void (*notify)(struct wmi_device *device, union acpi_object *data); +}; + +extern int __must_check __wmi_driver_register(struct wmi_driver *driver, + struct module *owner); +extern void wmi_driver_unregister(struct wmi_driver *driver); +#define wmi_driver_register(driver) __wmi_driver_register((driver), THIS_MODULE) + +#define module_wmi_driver(__wmi_driver) \ + module_driver(__wmi_driver, wmi_driver_register, \ + wmi_driver_unregister) + +#endif diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c102ef65cb64..1c49431f3121 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -324,6 +324,7 @@ enum { __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ + __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -422,7 +423,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ - alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) + alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \ + __WQ_ORDERED_EXPLICIT | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h new file mode 100644 index 000000000000..9e1f42cb57e9 --- /dev/null +++ b/include/linux/xxhash.h @@ -0,0 +1,236 @@ +/* + * xxHash - Extremely Fast Hash algorithm + * Copyright (C) 2012-2016, Yann Collet. + * + * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are + * met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following disclaimer + * in the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. This program is dual-licensed; you may select + * either version 2 of the GNU General Public License ("GPL") or BSD license + * ("BSD"). + * + * You can contact the author at: + * - xxHash homepage: http://cyan4973.github.io/xxHash/ + * - xxHash source repository: https://github.com/Cyan4973/xxHash + */ + +/* + * Notice extracted from xxHash homepage: + * + * xxHash is an extremely fast Hash algorithm, running at RAM speed limits. + * It also successfully passes all tests from the SMHasher suite. + * + * Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 + * Duo @3GHz) + * + * Name Speed Q.Score Author + * xxHash 5.4 GB/s 10 + * CrapWow 3.2 GB/s 2 Andrew + * MumurHash 3a 2.7 GB/s 10 Austin Appleby + * SpookyHash 2.0 GB/s 10 Bob Jenkins + * SBox 1.4 GB/s 9 Bret Mulvey + * Lookup3 1.2 GB/s 9 Bob Jenkins + * SuperFastHash 1.2 GB/s 1 Paul Hsieh + * CityHash64 1.05 GB/s 10 Pike & Alakuijala + * FNV 0.55 GB/s 5 Fowler, Noll, Vo + * CRC32 0.43 GB/s 9 + * MD5-32 0.33 GB/s 10 Ronald L. Rivest + * SHA1-32 0.28 GB/s 10 + * + * Q.Score is a measure of quality of the hash function. + * It depends on successfully passing SMHasher test set. + * 10 is a perfect score. + * + * A 64-bits version, named xxh64 offers much better speed, + * but for 64-bits applications only. + * Name Speed on 64 bits Speed on 32 bits + * xxh64 13.8 GB/s 1.9 GB/s + * xxh32 6.8 GB/s 6.0 GB/s + */ + +#ifndef XXHASH_H +#define XXHASH_H + +#include <linux/types.h> + +/*-**************************** + * Simple Hash Functions + *****************************/ + +/** + * xxh32() - calculate the 32-bit hash of the input with a given seed. + * + * @input: The data to hash. + * @length: The length of the data to hash. + * @seed: The seed can be used to alter the result predictably. + * + * Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s + * + * Return: The 32-bit hash of the data. + */ +uint32_t xxh32(const void *input, size_t length, uint32_t seed); + +/** + * xxh64() - calculate the 64-bit hash of the input with a given seed. + * + * @input: The data to hash. + * @length: The length of the data to hash. + * @seed: The seed can be used to alter the result predictably. + * + * This function runs 2x faster on 64-bit systems, but slower on 32-bit systems. + * + * Return: The 64-bit hash of the data. + */ +uint64_t xxh64(const void *input, size_t length, uint64_t seed); + +/*-**************************** + * Streaming Hash Functions + *****************************/ + +/* + * These definitions are only meant to allow allocation of XXH state + * statically, on stack, or in a struct for example. + * Do not use members directly. + */ + +/** + * struct xxh32_state - private xxh32 state, do not use members directly + */ +struct xxh32_state { + uint32_t total_len_32; + uint32_t large_len; + uint32_t v1; + uint32_t v2; + uint32_t v3; + uint32_t v4; + uint32_t mem32[4]; + uint32_t memsize; +}; + +/** + * struct xxh32_state - private xxh64 state, do not use members directly + */ +struct xxh64_state { + uint64_t total_len; + uint64_t v1; + uint64_t v2; + uint64_t v3; + uint64_t v4; + uint64_t mem64[4]; + uint32_t memsize; +}; + +/** + * xxh32_reset() - reset the xxh32 state to start a new hashing operation + * + * @state: The xxh32 state to reset. + * @seed: Initialize the hash state with this seed. + * + * Call this function on any xxh32_state to prepare for a new hashing operation. + */ +void xxh32_reset(struct xxh32_state *state, uint32_t seed); + +/** + * xxh32_update() - hash the data given and update the xxh32 state + * + * @state: The xxh32 state to update. + * @input: The data to hash. + * @length: The length of the data to hash. + * + * After calling xxh32_reset() call xxh32_update() as many times as necessary. + * + * Return: Zero on success, otherwise an error code. + */ +int xxh32_update(struct xxh32_state *state, const void *input, size_t length); + +/** + * xxh32_digest() - produce the current xxh32 hash + * + * @state: Produce the current xxh32 hash of this state. + * + * A hash value can be produced at any time. It is still possible to continue + * inserting input into the hash state after a call to xxh32_digest(), and + * generate new hashes later on, by calling xxh32_digest() again. + * + * Return: The xxh32 hash stored in the state. + */ +uint32_t xxh32_digest(const struct xxh32_state *state); + +/** + * xxh64_reset() - reset the xxh64 state to start a new hashing operation + * + * @state: The xxh64 state to reset. + * @seed: Initialize the hash state with this seed. + */ +void xxh64_reset(struct xxh64_state *state, uint64_t seed); + +/** + * xxh64_update() - hash the data given and update the xxh64 state + * @state: The xxh64 state to update. + * @input: The data to hash. + * @length: The length of the data to hash. + * + * After calling xxh64_reset() call xxh64_update() as many times as necessary. + * + * Return: Zero on success, otherwise an error code. + */ +int xxh64_update(struct xxh64_state *state, const void *input, size_t length); + +/** + * xxh64_digest() - produce the current xxh64 hash + * + * @state: Produce the current xxh64 hash of this state. + * + * A hash value can be produced at any time. It is still possible to continue + * inserting input into the hash state after a call to xxh64_digest(), and + * generate new hashes later on, by calling xxh64_digest() again. + * + * Return: The xxh64 hash stored in the state. + */ +uint64_t xxh64_digest(const struct xxh64_state *state); + +/*-************************** + * Utils + ***************************/ + +/** + * xxh32_copy_state() - copy the source state into the destination state + * + * @src: The source xxh32 state. + * @dst: The destination xxh32 state. + */ +void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src); + +/** + * xxh64_copy_state() - copy the source state into the destination state + * + * @src: The source xxh64 state. + * @dst: The destination xxh64 state. + */ +void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src); + +#endif /* XXHASH_H */ diff --git a/include/linux/zstd.h b/include/linux/zstd.h new file mode 100644 index 000000000000..249575e2485f --- /dev/null +++ b/include/linux/zstd.h @@ -0,0 +1,1157 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of https://github.com/facebook/zstd. + * An additional grant of patent rights can be found in the PATENTS file in the + * same directory. + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. This program is dual-licensed; you may select + * either version 2 of the GNU General Public License ("GPL") or BSD license + * ("BSD"). + */ + +#ifndef ZSTD_H +#define ZSTD_H + +/* ====== Dependency ======*/ +#include <linux/types.h> /* size_t */ + + +/*-***************************************************************************** + * Introduction + * + * zstd, short for Zstandard, is a fast lossless compression algorithm, + * targeting real-time compression scenarios at zlib-level and better + * compression ratios. The zstd compression library provides in-memory + * compression and decompression functions. The library supports compression + * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled + * ultra, should be used with caution, as they require more memory. + * Compression can be done in: + * - a single step, reusing a context (described as Explicit memory management) + * - unbounded multiple steps (described as Streaming compression) + * The compression ratio achievable on small data can be highly improved using + * compression with a dictionary in: + * - a single step (described as Simple dictionary API) + * - a single step, reusing a dictionary (described as Fast dictionary API) + ******************************************************************************/ + +/*====== Helper functions ======*/ + +/** + * enum ZSTD_ErrorCode - zstd error codes + * + * Functions that return size_t can be checked for errors using ZSTD_isError() + * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + */ +typedef enum { + ZSTD_error_no_error, + ZSTD_error_GENERIC, + ZSTD_error_prefix_unknown, + ZSTD_error_version_unsupported, + ZSTD_error_parameter_unknown, + ZSTD_error_frameParameter_unsupported, + ZSTD_error_frameParameter_unsupportedBy32bits, + ZSTD_error_frameParameter_windowTooLarge, + ZSTD_error_compressionParameter_unsupported, + ZSTD_error_init_missing, + ZSTD_error_memory_allocation, + ZSTD_error_stage_wrong, + ZSTD_error_dstSize_tooSmall, + ZSTD_error_srcSize_wrong, + ZSTD_error_corruption_detected, + ZSTD_error_checksum_wrong, + ZSTD_error_tableLog_tooLarge, + ZSTD_error_maxSymbolValue_tooLarge, + ZSTD_error_maxSymbolValue_tooSmall, + ZSTD_error_dictionary_corrupted, + ZSTD_error_dictionary_wrong, + ZSTD_error_dictionaryCreation_failed, + ZSTD_error_maxCode +} ZSTD_ErrorCode; + +/** + * ZSTD_maxCLevel() - maximum compression level available + * + * Return: Maximum compression level available. + */ +int ZSTD_maxCLevel(void); +/** + * ZSTD_compressBound() - maximum compressed size in worst case scenario + * @srcSize: The size of the data to compress. + * + * Return: The maximum compressed size in the worst case scenario. + */ +size_t ZSTD_compressBound(size_t srcSize); +/** + * ZSTD_isError() - tells if a size_t function result is an error code + * @code: The function result to check for error. + * + * Return: Non-zero iff the code is an error. + */ +static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) +{ + return code > (size_t)-ZSTD_error_maxCode; +} +/** + * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode + * @functionResult: The result of a function for which ZSTD_isError() is true. + * + * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 + * if the functionResult isn't an error. + */ +static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( + size_t functionResult) +{ + if (!ZSTD_isError(functionResult)) + return (ZSTD_ErrorCode)0; + return (ZSTD_ErrorCode)(0 - functionResult); +} + +/** + * enum ZSTD_strategy - zstd compression search strategy + * + * From faster to stronger. + */ +typedef enum { + ZSTD_fast, + ZSTD_dfast, + ZSTD_greedy, + ZSTD_lazy, + ZSTD_lazy2, + ZSTD_btlazy2, + ZSTD_btopt, + ZSTD_btopt2 +} ZSTD_strategy; + +/** + * struct ZSTD_compressionParameters - zstd compression parameters + * @windowLog: Log of the largest match distance. Larger means more + * compression, and more memory needed during decompression. + * @chainLog: Fully searched segment. Larger means more compression, slower, + * and more memory (useless for fast). + * @hashLog: Dispatch table. Larger means more compression, + * slower, and more memory. + * @searchLog: Number of searches. Larger means more compression and slower. + * @searchLength: Match length searched. Larger means faster decompression, + * sometimes less compression. + * @targetLength: Acceptable match size for optimal parser (only). Larger means + * more compression, and slower. + * @strategy: The zstd compression strategy. + */ +typedef struct { + unsigned int windowLog; + unsigned int chainLog; + unsigned int hashLog; + unsigned int searchLog; + unsigned int searchLength; + unsigned int targetLength; + ZSTD_strategy strategy; +} ZSTD_compressionParameters; + +/** + * struct ZSTD_frameParameters - zstd frame parameters + * @contentSizeFlag: Controls whether content size will be present in the frame + * header (when known). + * @checksumFlag: Controls whether a 32-bit checksum is generated at the end + * of the frame for error detection. + * @noDictIDFlag: Controls whether dictID will be saved into the frame header + * when using dictionary compression. + * + * The default value is all fields set to 0. + */ +typedef struct { + unsigned int contentSizeFlag; + unsigned int checksumFlag; + unsigned int noDictIDFlag; +} ZSTD_frameParameters; + +/** + * struct ZSTD_parameters - zstd parameters + * @cParams: The compression parameters. + * @fParams: The frame parameters. + */ +typedef struct { + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; +} ZSTD_parameters; + +/** + * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * Return: The selected ZSTD_compressionParameters. + */ +ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/** + * ZSTD_getParams() - returns ZSTD_parameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * The same as ZSTD_getCParams() except also selects the default frame + * parameters (all zero). + * + * Return: The selected ZSTD_parameters. + */ +ZSTD_parameters ZSTD_getParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/*-************************************* + * Explicit memory management + **************************************/ + +/** + * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx + * @cParams: The compression parameters to be used for compression. + * + * If multiple compression parameters might be used, the caller must call + * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum + * size. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCCtx(). + */ +size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CCtx - the zstd compression context + * + * When compressing many times it is recommended to allocate a context just once + * and reuse it for each successive compression operation. + */ +typedef struct ZSTD_CCtx_s ZSTD_CCtx; +/** + * ZSTD_initCCtx() - initialize a zstd compression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A compression context emplaced into workspace. + */ +ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_compressCCtx() - compress src into dst + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, ZSTD_parameters params); + +/** + * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDCtx(). + */ +size_t ZSTD_DCtxWorkspaceBound(void); + +/** + * struct ZSTD_DCtx - the zstd decompression context + * + * When decompressing many times it is recommended to allocate a context just + * once and reuse it for each successive decompression operation. + */ +typedef struct ZSTD_DCtx_s ZSTD_DCtx; +/** + * ZSTD_initDCtx() - initialize a zstd decompression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A decompression context emplaced into workspace. + */ +ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompressDCtx() - decompress zstd compressed src into dst + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + +/*-************************ + * Simple dictionary API + **************************/ + +/** + * ZSTD_compress_usingDict() - compress src into dst using a dictionary + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @dict: The dictionary to use for compression. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a predefined dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize, + ZSTD_parameters params); + +/** + * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @dict: The dictionary to use for decompression. The same dictionary + * must've been used to compress the data. + * @dictSize: The size of the dictionary. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize); + +/*-************************** + * Fast dictionary API + ***************************/ + +/** + * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCDict(). + */ +size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CDict - a digested dictionary to be used for compression + */ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/** + * ZSTD_initCDict() - initialize a digested dictionary for compression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_CDict so it must outlive the returned ZSTD_CDict. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * @workspace: The workspace. It must outlive the returned ZSTD_CDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_CDictWorkspaceBound(params.cParams). + * + * When compressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_CDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_CDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, + ZSTD_parameters params, void *workspace, size_t workspaceSize); + +/** + * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(cParams) where + * cParams are the compression parameters used to initialize the + * cdict. + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @cdict: The digested dictionary to use for compression. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a digested dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const ZSTD_CDict *cdict); + + +/** + * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDDict(). + */ +size_t ZSTD_DDictWorkspaceBound(void); + +/** + * struct ZSTD_DDict - a digested dictionary to be used for decompression + */ +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/** + * ZSTD_initDDict() - initialize a digested dictionary for decompression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_DDict so it must outlive the returned ZSTD_DDict. + * @dictSize: The size of the dictionary. + * @workspace: The workspace. It must outlive the returned ZSTD_DDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_DDictWorkspaceBound(). + * + * When decompressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_DDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_DDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, + void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @ddict: The digested dictionary to use for decompression. The same + * dictionary must've been used to compress the data. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, + size_t dstCapacity, const void *src, size_t srcSize, + const ZSTD_DDict *ddict); + + +/*-************************** + * Streaming + ***************************/ + +/** + * struct ZSTD_inBuffer - input buffer for streaming + * @src: Start of the input buffer. + * @size: Size of the input buffer. + * @pos: Position where reading stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_inBuffer_s { + const void *src; + size_t size; + size_t pos; +} ZSTD_inBuffer; + +/** + * struct ZSTD_outBuffer - output buffer for streaming + * @dst: Start of the output buffer. + * @size: Size of the output buffer. + * @pos: Position where writing stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_outBuffer_s { + void *dst; + size_t size; + size_t pos; +} ZSTD_outBuffer; + + + +/*-***************************************************************************** + * Streaming compression - HowTo + * + * A ZSTD_CStream object is required to track streaming operation. + * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. + * ZSTD_CStream objects can be reused multiple times on consecutive compression + * operations. It is recommended to re-use ZSTD_CStream in situations where many + * streaming operations will be achieved consecutively. Use one separate + * ZSTD_CStream per thread for parallel execution. + * + * Use ZSTD_compressStream() repetitively to consume input stream. + * The function will automatically update both `pos` fields. + * Note that it may not consume the entire input, in which case `pos < size`, + * and it's up to the caller to present again remaining data. + * It returns a hint for the preferred number of bytes to use as an input for + * the next function call. + * + * At any moment, it's possible to flush whatever data remains within internal + * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might + * still be some content left within the internal buffer if `output->size` is + * too small. It returns the number of bytes left in the internal buffer and + * must be called until it returns 0. + * + * ZSTD_endStream() instructs to finish a frame. It will perform a flush and + * write frame epilogue. The epilogue is required for decoders to consider a + * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush + * the full content if `output->size` is too small. In which case, call again + * ZSTD_endStream() to complete the flush. It returns the number of bytes left + * in the internal buffer and must be called until it returns 0. + ******************************************************************************/ + +/** + * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). + */ +size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CStream - the zstd streaming compression context + */ +typedef struct ZSTD_CStream_s ZSTD_CStream; + +/*===== ZSTD_CStream management functions =====*/ +/** + * ZSTD_initCStream() - initialize a zstd streaming compression context + * @params: The zstd compression parameters. + * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must + * pass the source size (zero means empty source). Otherwise, + * the caller may optionally pass the source size, or zero if + * unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/** + * ZSTD_initCStream_usingCDict() - initialize a streaming compression context + * @cdict: The digested dictionary to use for compression. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() + * with the cParams used to initialize the cdict to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/*===== Streaming compression functions =====*/ +/** + * ZSTD_resetCStream() - reset the context using parameters from creation + * @zcs: The zstd streaming compression context to reset. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame + * content size is always written into the frame header. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); +/** + * ZSTD_compressStream() - streaming compress some of input into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * @input: Source buffer. `input->pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input->pos < input->size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * + * Return: A hint for the number of bytes to use as the input for the next + * function call or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); +/** + * ZSTD_flushStream() - flush internal buffers into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_flushStream() must be called until it returns 0, meaning all the data + * has been flushed. Since ZSTD_flushStream() causes a block to be ended, + * calling it too often will degrade the compression ratio. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); +/** + * ZSTD_endStream() - flush internal buffers into output and end the frame + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_endStream() must be called until it returns 0, meaning all the data has + * been flushed and the frame epilogue has been written. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); + +/** + * ZSTD_CStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_CStreamInSize(void); +/** + * ZSTD_CStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete compressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_CStreamOutSize(void); + + + +/*-***************************************************************************** + * Streaming decompression - HowTo + * + * A ZSTD_DStream object is required to track streaming operations. + * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. + * ZSTD_DStream objects can be re-used multiple times. + * + * Use ZSTD_decompressStream() repetitively to consume your input. + * The function will update both `pos` fields. + * If `input->pos < input->size`, some input has not been consumed. + * It's up to the caller to present again remaining data. + * If `output->pos < output->size`, decoder has flushed everything it could. + * Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise it returns a suggested next input size that will never load more + * than the current frame. + ******************************************************************************/ + +/** + * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream + * @maxWindowSize: The maximum window size allowed for compressed frames. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). + */ +size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); + +/** + * struct ZSTD_DStream - the zstd streaming decompression context + */ +typedef struct ZSTD_DStream_s ZSTD_DStream; +/*===== ZSTD_DStream management functions =====*/ +/** + * ZSTD_initDStream() - initialize a zstd streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, + size_t workspaceSize); +/** + * ZSTD_initDStream_usingDDict() - initialize streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @ddict: The digested dictionary to use for decompression. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, + const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); + +/*===== Streaming decompression functions =====*/ +/** + * ZSTD_resetDStream() - reset the context using parameters from creation + * @zds: The zstd streaming decompression context to reset. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetDStream(ZSTD_DStream *zds); +/** + * ZSTD_decompressStream() - streaming decompress some of input into output + * @zds: The zstd streaming decompression context. + * @output: Destination buffer. `output.pos` is updated to indicate how much + * decompressed data was written. + * @input: Source buffer. `input.pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input.pos < input.size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * ZSTD_decompressStream() will not consume the last byte of the frame until + * the entire frame is flushed. + * + * Return: Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise returns a hint for the number of bytes to use as the input + * for the next function call or an error, which can be checked using + * ZSTD_isError(). The size hint will never load more than the frame. + */ +size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); + +/** + * ZSTD_DStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_DStreamInSize(void); +/** + * ZSTD_DStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete decompressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_DStreamOutSize(void); + + +/* --- Constants ---*/ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U + +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + +#define ZSTD_WINDOWLOG_MAX_32 27 +#define ZSTD_WINDOWLOG_MAX_64 27 +#define ZSTD_WINDOWLOG_MAX \ + ((unsigned int)(sizeof(size_t) == 4 \ + ? ZSTD_WINDOWLOG_MAX_32 \ + : ZSTD_WINDOWLOG_MAX_64)) +#define ZSTD_WINDOWLOG_MIN 10 +#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX +#define ZSTD_HASHLOG_MIN 6 +#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) +#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_HASHLOG3_MAX 17 +#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) +#define ZSTD_SEARCHLOG_MIN 1 +/* only for ZSTD_fast, other strategies are limited to 6 */ +#define ZSTD_SEARCHLENGTH_MAX 7 +/* only for ZSTD_btopt, other strategies are limited to 4 */ +#define ZSTD_SEARCHLENGTH_MIN 3 +#define ZSTD_TARGETLENGTH_MIN 4 +#define ZSTD_TARGETLENGTH_MAX 999 + +/* for static allocation */ +#define ZSTD_FRAMEHEADERSIZE_MAX 18 +#define ZSTD_FRAMEHEADERSIZE_MIN 6 +static const size_t ZSTD_frameHeaderSize_prefix = 5; +static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN; +static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; +/* magic number + skippable frame length */ +static const size_t ZSTD_skippableHeaderSize = 8; + + +/*-************************************* + * Compressed size functions + **************************************/ + +/** + * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame + * @src: Source buffer. It should point to the start of a zstd encoded frame + * or a skippable frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * size of the frame. + * + * Return: The compressed size of the frame pointed to by `src` or an error, + * which can be check with ZSTD_isError(). + * Suitable to pass to ZSTD_decompress() or similar functions. + */ +size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Decompressed size functions + **************************************/ +/** + * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header + * @src: It should point to the start of a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The frame content size stored in the frame header if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the + * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. + */ +unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + +/** + * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames + * @src: It should point to the start of a series of zstd encoded and/or + * skippable frames. + * @srcSize: The exact size of the series of frames. + * + * If any zstd encoded frame in the series doesn't have the frame content size + * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always + * set when using ZSTD_compress(). The decompressed size can be very large. + * If the source is untrusted, the decompressed size could be wrong or + * intentionally modified. Always ensure the result fits within the + * application's authorized limits. ZSTD_findDecompressedSize() handles multiple + * frames, and so it must traverse the input to read each frame header. This is + * efficient as most of the data is skipped, however it does mean that all frame + * data must be present and valid. + * + * Return: Decompressed size of all the data contained in the frames if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. + * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. + */ +unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Advanced compression functions + **************************************/ +/** + * ZSTD_checkCParams() - ensure parameter values remain within authorized range + * @cParams: The zstd compression parameters. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); + +/** + * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize + * @srcSize: Optionally the estimated source size, or zero if unknown. + * @dictSize: Optionally the estimated dictionary size, or zero if unknown. + * + * Return: The optimized parameters. + */ +ZSTD_compressionParameters ZSTD_adjustCParams( + ZSTD_compressionParameters cParams, unsigned long long srcSize, + size_t dictSize); + +/*--- Advanced decompression functions ---*/ + +/** + * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame + * @buffer: The source buffer to check. + * @size: The size of the source buffer, must be at least 4 bytes. + * + * Return: True iff the buffer starts with a zstd or skippable frame identifier. + */ +unsigned int ZSTD_isFrame(const void *buffer, size_t size); + +/** + * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary + * @dict: The dictionary buffer. + * @dictSize: The size of the dictionary buffer. + * + * Return: The dictionary id stored within the dictionary or 0 if the + * dictionary is not a zstd dictionary. If it returns 0 the + * dictionary can still be loaded as a content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); + +/** + * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict + * @ddict: The ddict to find the id of. + * + * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not + * a zstd dictionary. If it returns 0 `ddict` will be loaded as a + * content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); + +/** + * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame + * @src: Source buffer. It must be a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The dictionary id required to decompress the frame stored within + * `src` or 0 if the dictionary id could not be decoded. It can return + * 0 if the frame does not require a dictionary, the dictionary id + * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` + * is too small. + */ +unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); + +/** + * struct ZSTD_frameParams - zstd frame parameters stored in the frame header + * @frameContentSize: The frame content size, or 0 if not present. + * @windowSize: The window size, or 0 if the frame is a skippable frame. + * @dictID: The dictionary id, or 0 if not present. + * @checksumFlag: Whether a checksum was used. + */ +typedef struct { + unsigned long long frameContentSize; + unsigned int windowSize; + unsigned int dictID; + unsigned int checksumFlag; +} ZSTD_frameParams; + +/** + * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame + * @fparamsPtr: On success the frame parameters are written here. + * @src: The source buffer. It must point to a zstd or skippable frame. + * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is + * always large enough to succeed. + * + * Return: 0 on success. If more data is required it returns how many bytes + * must be provided to make forward progress. Otherwise it returns + * an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, + size_t srcSize); + +/*-***************************************************************************** + * Buffer-less and synchronous inner streaming functions + * + * This is an advanced API, giving full control over buffer management, for + * users which need direct control over memory. + * But it's also a complex one, with many restrictions (documented below). + * Prefer using normal streaming API for an easier experience + ******************************************************************************/ + +/*-***************************************************************************** + * Buffer-less streaming compression (synchronous mode) + * + * A ZSTD_CCtx object is required to track streaming operations. + * Use ZSTD_initCCtx() to initialize a context. + * ZSTD_CCtx object can be re-used multiple times within successive compression + * operations. + * + * Start by initializing a context. + * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary + * compression, + * or ZSTD_compressBegin_advanced(), for finer parameter control. + * It's also possible to duplicate a reference context which has already been + * initialized, using ZSTD_copyCCtx() + * + * Then, consume your input using ZSTD_compressContinue(). + * There are some important considerations to keep in mind when using this + * advanced function : + * - ZSTD_compressContinue() has no internal buffer. It uses externally provided + * buffer only. + * - Interface is synchronous : input is consumed entirely and produce 1+ + * (or more) compressed blocks. + * - Caller must ensure there is enough space in `dst` to store compressed data + * under worst case scenario. Worst case evaluation is provided by + * ZSTD_compressBound(). + * ZSTD_compressContinue() doesn't guarantee recover after a failed + * compression. + * - ZSTD_compressContinue() presumes prior input ***is still accessible and + * unmodified*** (up to maximum distance size, see WindowLog). + * It remembers all previous contiguous blocks, plus one separated memory + * segment (which can itself consists of multiple contiguous blocks) + * - ZSTD_compressContinue() detects that prior input has been overwritten when + * `src` buffer overlaps. In which case, it will "discard" the relevant memory + * section from its history. + * + * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) + * and optional checksum. It's possible to use srcSize==0, in which case, it + * will write a final empty block to end the frame. Without last block mark, + * frames will be considered unfinished (corrupted) by decoders. + * + * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new + * frame. + ******************************************************************************/ + +/*===== Buffer-less streaming compression functions =====*/ +size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); +size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, int compressionLevel); +size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, ZSTD_parameters params, + unsigned long long pledgedSrcSize); +size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + + + +/*-***************************************************************************** + * Buffer-less streaming decompression (synchronous mode) + * + * A ZSTD_DCtx object is required to track streaming operations. + * Use ZSTD_initDCtx() to initialize a context. + * A ZSTD_DCtx object can be re-used multiple times. + * + * First typical operation is to retrieve frame parameters, using + * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide + * important information to correctly decode the frame, such as the minimum + * rolling buffer size to allocate to decompress data (`windowSize`), and the + * dictionary ID used. + * Note: content size is optional, it may not be present. 0 means unknown. + * Note that these values could be wrong, either because of data malformation, + * or because an attacker is spoofing deliberate false information. As a + * consequence, check that values remain within valid application range, + * especially `windowSize`, before allocation. Each application can set its own + * limit, depending on local restrictions. For extended interoperability, it is + * recommended to support at least 8 MB. + * Frame parameters are extracted from the beginning of the compressed frame. + * Data fragment must be large enough to ensure successful decoding, typically + * `ZSTD_frameHeaderSize_max` bytes. + * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. + * >0: `srcSize` is too small, provide at least this many bytes. + * errorCode, which can be tested using ZSTD_isError(). + * + * Start decompression, with ZSTD_decompressBegin() or + * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared + * context, using ZSTD_copyDCtx(). + * + * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() + * alternatively. + * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' + * to ZSTD_decompressContinue(). + * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will + * fail. + * + * The result of ZSTD_decompressContinue() is the number of bytes regenerated + * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an + * error; it just means ZSTD_decompressContinue() has decoded some metadata + * item. It can also be an error code, which can be tested with ZSTD_isError(). + * + * ZSTD_decompressContinue() needs previous data blocks during decompression, up + * to `windowSize`. They should preferably be located contiguously, prior to + * current block. Alternatively, a round buffer of sufficient size is also + * possible. Sufficient size is determined by frame parameters. + * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't + * follow each other, make sure that either the compressor breaks contiguity at + * the same place, or that previous contiguous segment is large enough to + * properly handle maximum back-reference. + * + * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. + * Context can then be reset to start a new decompression. + * + * Note: it's possible to know if next input to present is a header or a block, + * using ZSTD_nextInputType(). This information is not required to properly + * decode a frame. + * + * == Special case: skippable frames == + * + * Skippable frames allow integration of user-defined data into a flow of + * concatenated frames. Skippable frames will be ignored (skipped) by a + * decompressor. The format of skippable frames is as follows: + * a) Skippable frame ID - 4 Bytes, Little endian format, any value from + * 0x184D2A50 to 0x184D2A5F + * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits + * c) Frame Content - any content (User Data) of length equal to Frame Size + * For skippable frames ZSTD_decompressContinue() always returns 0. + * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 + * what means that a frame is skippable. + * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might + * actually be a zstd encoded frame with no content. For purposes of + * decompression, it is valid in both cases to skip the frame using + * ZSTD_findFrameCompressedSize() to find its size in bytes. + * It also returns frame size as fparamsPtr->frameContentSize. + ******************************************************************************/ + +/*===== Buffer-less streaming decompression functions =====*/ +size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); +size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, + size_t dictSize); +void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); +size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); +size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +typedef enum { + ZSTDnit_frameHeader, + ZSTDnit_blockHeader, + ZSTDnit_block, + ZSTDnit_lastBlock, + ZSTDnit_checksum, + ZSTDnit_skippableFrame +} ZSTD_nextInputType_e; +ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); + +/*-***************************************************************************** + * Block functions + * + * Block functions produce and decode raw zstd blocks, without frame metadata. + * Frame metadata cost is typically ~18 bytes, which can be non-negligible for + * very small blocks (< 100 bytes). User will have to take in charge required + * information to regenerate data, such as compressed and content sizes. + * + * A few rules to respect: + * - Compressing and decompressing require a context structure + * + Use ZSTD_initCCtx() and ZSTD_initDCtx() + * - It is necessary to init context before starting + * + compression : ZSTD_compressBegin() + * + decompression : ZSTD_decompressBegin() + * + variants _usingDict() are also allowed + * + copyCCtx() and copyDCtx() work too + * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() + * + If you need to compress more, cut data into multiple blocks + * + Consider using the regular ZSTD_compress() instead, as frame metadata + * costs become negligible when source size is large. + * - When a block is considered not compressible enough, ZSTD_compressBlock() + * result will be zero. In which case, nothing is produced into `dst`. + * + User must test for such outcome and deal directly with uncompressed data + * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! + * + In case of multiple successive blocks, decoder must be informed of + * uncompressed block existence to follow proper history. Use + * ZSTD_insertBlock() in such a case. + ******************************************************************************/ + +/* Define for static allocation */ +#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) +/*===== Raw zstd block functions =====*/ +size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); +size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, + size_t blockSize); + +#endif /* ZSTD_H */ |