aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/wakeup_64.S10
-rw-r--r--arch/x86/kernel/alternative.c6
-rw-r--r--arch/x86/kernel/amd_nb.c3
-rw-r--r--arch/x86/kernel/apic/apic.c92
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c24
-rw-r--r--arch/x86/kernel/apic/io_apic.c8
-rw-r--r--arch/x86/kernel/apic/probe_32.c3
-rw-r--r--arch/x86/kernel/asm-offsets_64.c20
-rw-r--r--arch/x86/kernel/cpu/amd.c92
-rw-r--r--arch/x86/kernel/cpu/bugs.c125
-rw-r--r--arch/x86/kernel/cpu/common.c45
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c97
-rw-r--r--arch/x86/kernel/cpu/hygon.c21
-rw-r--r--arch/x86/kernel/cpu/intel.c31
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c2
-rw-r--r--arch/x86/kernel/cpu/mce/severity.c4
-rw-r--r--arch/x86/kernel/cpu/mtrr/cyrix.c1
-rw-r--r--arch/x86/kernel/cpu/umwait.c39
-rw-r--r--arch/x86/kernel/cpu/vmware.c94
-rw-r--r--arch/x86/kernel/crash.c2
-rw-r--r--arch/x86/kernel/dumpstack.c7
-rw-r--r--arch/x86/kernel/head_64.S8
-rw-r--r--arch/x86/kernel/hpet.c12
-rw-r--r--arch/x86/kernel/irq.c10
-rw-r--r--arch/x86/kernel/irq_32.c7
-rw-r--r--arch/x86/kernel/irq_64.c9
-rw-r--r--arch/x86/kernel/kprobes/core.c2
-rw-r--r--arch/x86/kernel/kprobes/opt.c2
-rw-r--r--arch/x86/kernel/kvm.c10
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kernel/pci-dma.c20
-rw-r--r--arch/x86/kernel/ptrace.c1
-rw-r--r--arch/x86/kernel/quirks.c4
-rw-r--r--arch/x86/kernel/smpboot.c5
-rw-r--r--arch/x86/kernel/stacktrace.c2
-rw-r--r--arch/x86/kernel/sysfb_efi.c46
-rw-r--r--arch/x86/kernel/tsc.c2
-rw-r--r--arch/x86/kernel/tsc_msr.c5
-rw-r--r--arch/x86/kernel/umip.c65
-rw-r--r--arch/x86/kernel/uprobes.c17
40 files changed, 641 insertions, 316 deletions
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index b0715c3ac18d..7f9ade13bbcf 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -18,8 +18,13 @@ ENTRY(wakeup_long64)
movq saved_magic, %rax
movq $0x123456789abcdef0, %rdx
cmpq %rdx, %rax
- jne bogus_64_magic
+ je 2f
+ /* stop here on a saved_magic mismatch */
+ movq $0xbad6d61676963, %rcx
+1:
+ jmp 1b
+2:
movw $__KERNEL_DS, %ax
movw %ax, %ss
movw %ax, %ds
@@ -37,9 +42,6 @@ ENTRY(wakeup_long64)
jmp *%rax
ENDPROC(wakeup_long64)
-bogus_64_magic:
- jmp bogus_64_magic
-
ENTRY(do_suspend_lowlevel)
FRAME_BEGIN
subq $8, %rsp
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ccd32013c47a..9d3a971ea364 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -713,7 +713,7 @@ void __init alternative_instructions(void)
* Don't stop machine check exceptions while patching.
* MCEs only happen when something got corrupted and in this
* case we must do something about the corruption.
- * Ignoring it is worse than a unlikely patching race.
+ * Ignoring it is worse than an unlikely patching race.
* Also machine checks tend to be broadcast and if one CPU
* goes into machine check the others follow quickly, so we don't
* expect a machine check to cause undue problems during to code
@@ -753,8 +753,8 @@ void __init alternative_instructions(void)
* When you use this code to patch more than one byte of an instruction
* you need to make sure that other CPUs cannot execute this code in parallel.
* Also no thread must be currently preempted in the middle of these
- * instructions. And on the local CPU you need to be protected again NMI or MCE
- * handlers seeing an inconsistent instruction while you patch.
+ * instructions. And on the local CPU you need to be protected against NMI or
+ * MCE handlers seeing an inconsistent instruction while you patch.
*/
void __init_or_module text_poke_early(void *addr, const void *opcode,
size_t len)
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index d63e63b7d1d9..251c795b4eb3 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -21,6 +21,7 @@
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
+#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
/* Protect the PCI config register pairs used for SMN and DF indirect access. */
static DEFINE_MUTEX(smn_mutex);
@@ -50,6 +51,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
{}
};
EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -63,6 +65,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{}
};
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3a31875bd0a3..9e2dd2b296cd 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -590,21 +590,21 @@ static u32 skx_deadline_rev(void)
static const struct x86_cpu_id deadline_match[] = {
DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev),
DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020),
- DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev),
+ DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_D, bdx_deadline_rev),
DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_GT3E, 0x17),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL, 0x22),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_L, 0x20),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_G, 0x17),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_CORE, 0x25),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_GT3E, 0x17),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL, 0x25),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_G, 0x17),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_MOBILE, 0xb2),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_DESKTOP, 0xb2),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_L, 0xb2),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE, 0xb2),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_MOBILE, 0x52),
- DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_DESKTOP, 0x52),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_L, 0x52),
+ DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE, 0x52),
{},
};
@@ -722,7 +722,7 @@ static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2;
static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;
/*
- * Temporary interrupt handler.
+ * Temporary interrupt handler and polled calibration function.
*/
static void __init lapic_cal_handler(struct clock_event_device *dev)
{
@@ -834,6 +834,10 @@ bool __init apic_needs_pit(void)
if (!boot_cpu_has(X86_FEATURE_APIC))
return true;
+ /* Virt guests may lack ARAT, but still have DEADLINE */
+ if (!boot_cpu_has(X86_FEATURE_ARAT))
+ return true;
+
/* Deadline timer is based on TSC so no further PIT action required */
if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
return false;
@@ -851,7 +855,8 @@ bool __init apic_needs_pit(void)
static int __init calibrate_APIC_clock(void)
{
struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
- void (*real_handler)(struct clock_event_device *dev);
+ u64 tsc_perj = 0, tsc_start = 0;
+ unsigned long jif_start;
unsigned long deltaj;
long delta, deltatsc;
int pm_referenced = 0;
@@ -878,28 +883,64 @@ static int __init calibrate_APIC_clock(void)
apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
"calibrating APIC timer ...\n");
+ /*
+ * There are platforms w/o global clockevent devices. Instead of
+ * making the calibration conditional on that, use a polling based
+ * approach everywhere.
+ */
local_irq_disable();
- /* Replace the global interrupt handler */
- real_handler = global_clock_event->event_handler;
- global_clock_event->event_handler = lapic_cal_handler;
-
/*
* Setup the APIC counter to maximum. There is no way the lapic
* can underflow in the 100ms detection time frame
*/
__setup_APIC_LVTT(0xffffffff, 0, 0);
- /* Let the interrupts run */
+ /*
+ * Methods to terminate the calibration loop:
+ * 1) Global clockevent if available (jiffies)
+ * 2) TSC if available and frequency is known
+ */
+ jif_start = READ_ONCE(jiffies);
+
+ if (tsc_khz) {
+ tsc_start = rdtsc();
+ tsc_perj = div_u64((u64)tsc_khz * 1000, HZ);
+ }
+
+ /*
+ * Enable interrupts so the tick can fire, if a global
+ * clockevent device is available
+ */
local_irq_enable();
- while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
- cpu_relax();
+ while (lapic_cal_loops <= LAPIC_CAL_LOOPS) {
+ /* Wait for a tick to elapse */
+ while (1) {
+ if (tsc_khz) {
+ u64 tsc_now = rdtsc();
+ if ((tsc_now - tsc_start) >= tsc_perj) {
+ tsc_start += tsc_perj;
+ break;
+ }
+ } else {
+ unsigned long jif_now = READ_ONCE(jiffies);
+
+ if (time_after(jif_now, jif_start)) {
+ jif_start = jif_now;
+ break;
+ }
+ }
+ cpu_relax();
+ }
- local_irq_disable();
+ /* Invoke the calibration routine */
+ local_irq_disable();
+ lapic_cal_handler(NULL);
+ local_irq_enable();
+ }
- /* Restore the real event handler */
- global_clock_event->event_handler = real_handler;
+ local_irq_disable();
/* Build delta t1-t2 as apic timer counts down */
delta = lapic_cal_t1 - lapic_cal_t2;
@@ -943,10 +984,11 @@ static int __init calibrate_APIC_clock(void)
levt->features &= ~CLOCK_EVT_FEAT_DUMMY;
/*
- * PM timer calibration failed or not turned on
- * so lets try APIC timer based calibration
+ * PM timer calibration failed or not turned on so lets try APIC
+ * timer based calibration, if a global clockevent device is
+ * available.
*/
- if (!pm_referenced) {
+ if (!pm_referenced && global_clock_event) {
apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
/*
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 9703b552f25a..38b5b51d42f6 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -33,32 +33,12 @@ static int bigsmp_early_logical_apicid(int cpu)
return early_per_cpu(x86_cpu_to_apicid, cpu);
}
-static inline unsigned long calculate_ldr(int cpu)
-{
- unsigned long val, id;
-
- val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
- id = per_cpu(x86_bios_cpu_apicid, cpu);
- val |= SET_APIC_LOGICAL_ID(id);
-
- return val;
-}
-
/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116). So here it goes...
+ * bigsmp enables physical destination mode
+ * and doesn't use LDR and DFR
*/
static void bigsmp_init_apic_ldr(void)
{
- unsigned long val;
- int cpu = smp_processor_id();
-
- apic_write(APIC_DFR, APIC_DFR_FLAT);
- val = calculate_ldr(cpu);
- apic_write(APIC_LDR, val);
}
static void bigsmp_setup_apic_routing(void)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c7bb6c69f21c..d6af97fd170a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2438,7 +2438,13 @@ unsigned int arch_dynirq_lower_bound(unsigned int from)
* dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use
* gsi_top if ioapic_dynirq_base hasn't been initialized yet.
*/
- return ioapic_initialized ? ioapic_dynirq_base : gsi_top;
+ if (!ioapic_initialized)
+ return gsi_top;
+ /*
+ * For DT enabled machines ioapic_dynirq_base is irrelevant and not
+ * updated. So simply return @from if ioapic_dynirq_base == 0.
+ */
+ return ioapic_dynirq_base ? : from;
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 0ac9fd667c99..67b33d67002f 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -147,7 +147,8 @@ void __init default_setup_apic_routing(void)
def_to_bigsmp = 0;
break;
}
- /* If P4 and above fall through */
+ /* P4 and above */
+ /* fall through */
case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
def_to_bigsmp = 1;
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 8b54d8e3a561..24d2fde30d00 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -6,13 +6,28 @@
#include <asm/ia32.h>
#define __SYSCALL_64(nr, sym, qual) [nr] = 1,
+#define __SYSCALL_X32(nr, sym, qual)
static char syscalls_64[] = {
#include <asm/syscalls_64.h>
};
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+
+#ifdef CONFIG_X86_X32_ABI
+#define __SYSCALL_64(nr, sym, qual)
+#define __SYSCALL_X32(nr, sym, qual) [nr] = 1,
+static char syscalls_x32[] = {
+#include <asm/syscalls_64.h>
+};
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+#endif
+
#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
static char syscalls_ia32[] = {
#include <asm/syscalls_32.h>
};
+#undef __SYSCALL_I386
#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
#include <asm/kvm_para.h>
@@ -79,6 +94,11 @@ int main(void)
DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
DEFINE(NR_syscalls, sizeof(syscalls_64));
+#ifdef CONFIG_X86_X32_ABI
+ DEFINE(__NR_syscall_x32_max, sizeof(syscalls_x32) - 1);
+ DEFINE(X32_NR_syscalls, sizeof(syscalls_x32));
+#endif
+
DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8d4e50428b68..90f75e515876 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -8,6 +8,7 @@
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/random.h>
+#include <linux/topology.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cacheinfo.h>
@@ -804,6 +805,64 @@ static void init_amd_ln(struct cpuinfo_x86 *c)
msr_set_bit(MSR_AMD64_DE_CFG, 31);
}
+static bool rdrand_force;
+
+static int __init rdrand_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "force"))
+ rdrand_force = true;
+ else
+ return -EINVAL;
+
+ return 0;
+}
+early_param("rdrand", rdrand_cmdline);
+
+static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c)
+{
+ /*
+ * Saving of the MSR used to hide the RDRAND support during
+ * suspend/resume is done by arch/x86/power/cpu.c, which is
+ * dependent on CONFIG_PM_SLEEP.
+ */
+ if (!IS_ENABLED(CONFIG_PM_SLEEP))
+ return;
+
+ /*
+ * The nordrand option can clear X86_FEATURE_RDRAND, so check for
+ * RDRAND support using the CPUID function directly.
+ */
+ if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force)
+ return;
+
+ msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62);
+
+ /*
+ * Verify that the CPUID change has occurred in case the kernel is
+ * running virtualized and the hypervisor doesn't support the MSR.
+ */
+ if (cpuid_ecx(1) & BIT(30)) {
+ pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n");
+ return;
+ }
+
+ clear_cpu_cap(c, X86_FEATURE_RDRAND);
+ pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n");
+}
+
+static void init_amd_jg(struct cpuinfo_x86 *c)
+{
+ /*
+ * Some BIOS implementations do not restore proper RDRAND support
+ * across suspend and resume. Check on whether to hide the RDRAND
+ * instruction support via CPUID.
+ */
+ clear_rdrand_cpuid_bit(c);
+}
+
static void init_amd_bd(struct cpuinfo_x86 *c)
{
u64 value;
@@ -818,12 +877,23 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
wrmsrl_safe(MSR_F15H_IC_CFG, value);
}
}
+
+ /*
+ * Some BIOS implementations do not restore proper RDRAND support
+ * across suspend and resume. Check on whether to hide the RDRAND
+ * instruction support via CPUID.
+ */
+ clear_rdrand_cpuid_bit(c);
}
static void init_amd_zn(struct cpuinfo_x86 *c)
{
set_cpu_cap(c, X86_FEATURE_ZEN);
+#ifdef CONFIG_NUMA
+ node_reclaim_distance = 32;
+#endif
+
/*
* Fix erratum 1076: CPB feature bit not being set in CPUID.
* Always set it, except when running under a hypervisor.
@@ -860,6 +930,7 @@ static void init_amd(struct cpuinfo_x86 *c)
case 0x10: init_amd_gh(c); break;
case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
+ case 0x16: init_amd_jg(c); break;
case 0x17: init_amd_zn(c); break;
}
@@ -879,12 +950,8 @@ static void init_amd(struct cpuinfo_x86 *c)
init_amd_cacheinfo(c);
if (cpu_has(c, X86_FEATURE_XMM2)) {
- unsigned long long val;
- int ret;
-
/*
- * A serializing LFENCE has less overhead than MFENCE, so
- * use it for execution serialization. On families which
+ * Use LFENCE for execution serialization. On families which
* don't have that MSR, LFENCE is already serializing.
* msr_set_bit() uses the safe accessors, too, even if the MSR
* is not present.
@@ -892,19 +959,8 @@ static void init_amd(struct cpuinfo_x86 *c)
msr_set_bit(MSR_F10H_DECFG,
MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
- /*
- * Verify that the MSR write was successful (could be running
- * under a hypervisor) and only then assume that LFENCE is
- * serializing.
- */
- ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
- if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
- /* A serializing LFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
- } else {
- /* MFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
- }
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
}
/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 6d9636c2ca51..91c2561b905f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -34,6 +34,7 @@
#include "cpu.h"
+static void __init spectre_v1_select_mitigation(void);
static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
static void __init l1tf_select_mitigation(void);
@@ -98,17 +99,11 @@ void __init check_bugs(void)
if (boot_cpu_has(X86_FEATURE_STIBP))
x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
- /* Select the proper spectre mitigation before patching alternatives */
+ /* Select the proper CPU mitigations before patching alternatives: */
+ spectre_v1_select_mitigation();
spectre_v2_select_mitigation();
-
- /*
- * Select proper mitigation for any exposure to the Speculative Store
- * Bypass vulnerability.
- */
ssb_select_mitigation();
-
l1tf_select_mitigation();
-
mds_select_mitigation();
arch_smt_update();
@@ -274,6 +269,98 @@ static int __init mds_cmdline(char *str)
early_param("mds", mds_cmdline);
#undef pr_fmt
+#define pr_fmt(fmt) "Spectre V1 : " fmt
+
+enum spectre_v1_mitigation {
+ SPECTRE_V1_MITIGATION_NONE,
+ SPECTRE_V1_MITIGATION_AUTO,
+};
+
+static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init =
+ SPECTRE_V1_MITIGATION_AUTO;
+
+static const char * const spectre_v1_strings[] = {
+ [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers",
+ [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization",
+};
+
+/*
+ * Does SMAP provide full mitigation against speculative kernel access to
+ * userspace?
+ */
+static bool smap_works_speculatively(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_SMAP))
+ return false;
+
+ /*
+ * On CPUs which are vulnerable to Meltdown, SMAP does not
+ * prevent speculative access to user data in the L1 cache.
+ * Consider SMAP to be non-functional as a mitigation on these
+ * CPUs.
+ */
+ if (boot_cpu_has(X86_BUG_CPU_MELTDOWN))
+ return false;
+
+ return true;
+}
+
+static void __init spectre_v1_select_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) {
+ spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+ return;
+ }
+
+ if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) {
+ /*
+ * With Spectre v1, a user can speculatively control either
+ * path of a conditional swapgs with a user-controlled GS
+ * value. The mitigation is to add lfences to both code paths.
+ *
+ * If FSGSBASE is enabled, the user can put a kernel address in
+ * GS, in which case SMAP provides no protection.
+ *
+ * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the
+ * FSGSBASE enablement patches have been merged. ]
+ *
+ * If FSGSBASE is disabled, the user can only put a user space
+ * address in GS. That makes an attack harder, but still
+ * possible if there's no SMAP protection.
+ */
+ if (!smap_works_speculatively()) {
+ /*
+ * Mitigation can be provided from SWAPGS itself or
+ * PTI as the CR3 write in the Meltdown mitigation
+ * is serializing.
+ *
+ * If neither is there, mitigate with an LFENCE to
+ * stop speculation through swapgs.
+ */
+ if (boot_cpu_has_bug(X86_BUG_SWAPGS) &&
+ !boot_cpu_has(X86_FEATURE_PTI))
+ setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER);
+
+ /*
+ * Enable lfences in the kernel entry (non-swapgs)
+ * paths, to prevent user entry from speculatively
+ * skipping swapgs.
+ */
+ setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL);
+ }
+ }
+
+ pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]);
+}
+
+static int __init nospectre_v1_cmdline(char *str)
+{
+ spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+ return 0;
+}
+early_param("nospectre_v1", nospectre_v1_cmdline);
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
@@ -1097,15 +1184,15 @@ static void override_cache_bits(struct cpuinfo_x86 *c)
case INTEL_FAM6_WESTMERE:
case INTEL_FAM6_SANDYBRIDGE:
case INTEL_FAM6_IVYBRIDGE:
- case INTEL_FAM6_HASWELL_CORE:
- case INTEL_FAM6_HASWELL_ULT:
- case INTEL_FAM6_HASWELL_GT3E:
- case INTEL_FAM6_BROADWELL_CORE:
- case INTEL_FAM6_BROADWELL_GT3E:
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
+ case INTEL_FAM6_HASWELL:
+ case INTEL_FAM6_HASWELL_L:
+ case INTEL_FAM6_HASWELL_G:
+ case INTEL_FAM6_BROADWELL:
+ case INTEL_FAM6_BROADWELL_G:
+ case INTEL_FAM6_SKYLAKE_L:
+ case INTEL_FAM6_SKYLAKE:
+ case INTEL_FAM6_KABYLAKE_L:
+ case INTEL_FAM6_KABYLAKE:
if (c->x86_cache_bits < 44)
c->x86_cache_bits = 44;
break;
@@ -1226,7 +1313,7 @@ static ssize_t l1tf_show_state(char *buf)
static ssize_t mds_show_state(char *buf)
{
- if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
return sprintf(buf, "%s; SMT Host state unknown\n",
mds_strings[mds_mitigation]);
}
@@ -1290,7 +1377,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
break;
case X86_BUG_SPECTRE_V1:
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+ return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]);
case X86_BUG_SPECTRE_V2:
return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e0489d2860d3..9ae7d1bcd4f4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1022,6 +1022,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#define NO_L1TF BIT(3)
#define NO_MDS BIT(4)
#define MSBDS_ONLY BIT(5)
+#define NO_SWAPGS BIT(6)
#define VULNWL(_vendor, _family, _model, _whitelist) \
{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -1048,30 +1049,39 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION),
VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION),
- VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(CORE_YONAH, NO_SSB),
- VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS),
- VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF),
- VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF),
- VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF),
+ VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS),
+
+ /*
+ * Technically, swapgs isn't serializing on AMD (despite it previously
+ * being documented as such in the APM). But according to AMD, %gs is
+ * updated non-speculatively, and the issuing of %gs-relative memory
+ * operands will be blocked until the %gs update completes, which is
+ * good enough for our purposes.
+ */
/* AMD Family 0xf - 0x12 */
- VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
- VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
- VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
- VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
- VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
- VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
{}
};
@@ -1108,6 +1118,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
}
+ if (!cpu_matches(NO_SWAPGS))
+ setup_force_cpu_bug(X86_BUG_SWAPGS);
+
if (cpu_matches(NO_MELTDOWN))
return;
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index b5353244749b..3cbe24ca80ab 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -20,54 +20,55 @@ struct cpuid_dep {
* but it's difficult to tell that to the init reference checker.
*/
static const struct cpuid_dep cpuid_deps[] = {
- { X86_FEATURE_FXSR, X86_FEATURE_FPU },
- { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE },
- { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE },
- { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE },
- { X86_FEATURE_AVX, X86_FEATURE_XSAVE },
- { X86_FEATURE_PKU, X86_FEATURE_XSAVE },
- { X86_FEATURE_MPX, X86_FEATURE_XSAVE },
- { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE },
- { X86_FEATURE_CMOV, X86_FEATURE_FXSR },
- { X86_FEATURE_MMX, X86_FEATURE_FXSR },
- { X86_FEATURE_MMXEXT, X86_FEATURE_MMX },
- { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR },
- { X86_FEATURE_XSAVE, X86_FEATURE_FXSR },
- { X86_FEATURE_XMM, X86_FEATURE_FXSR },
- { X86_FEATURE_XMM2, X86_FEATURE_XMM },
- { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
- { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 },
- { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 },
- { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
- { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 },
- { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, },
- { X86_FEATURE_F16C, X86_FEATURE_XMM2, },
- { X86_FEATURE_AES, X86_FEATURE_XMM2 },
- { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 },
- { X86_FEATURE_FMA, X86_FEATURE_AVX },
- { X86_FEATURE_AVX2, X86_FEATURE_AVX, },
- { X86_FEATURE_AVX512F, X86_FEATURE_AVX, },
- { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL },
- { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VAES, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL },
- { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL },
- { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL },
- { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
- { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
- { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC },
- { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
- { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
- { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_FXSR, X86_FEATURE_FPU },
+ { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE },
+ { X86_FEATURE_AVX, X86_FEATURE_XSAVE },
+ { X86_FEATURE_PKU, X86_FEATURE_XSAVE },
+ { X86_FEATURE_MPX, X86_FEATURE_XSAVE },
+ { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE },
+ { X86_FEATURE_CMOV, X86_FEATURE_FXSR },
+ { X86_FEATURE_MMX, X86_FEATURE_FXSR },
+ { X86_FEATURE_MMXEXT, X86_FEATURE_MMX },
+ { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR },
+ { X86_FEATURE_XSAVE, X86_FEATURE_FXSR },
+ { X86_FEATURE_XMM, X86_FEATURE_FXSR },
+ { X86_FEATURE_XMM2, X86_FEATURE_XMM },
+ { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 },
+ { X86_FEATURE_XMM3, X86_FEATURE_XMM2 },
+ { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 },
+ { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, },
+ { X86_FEATURE_F16C, X86_FEATURE_XMM2, },
+ { X86_FEATURE_AES, X86_FEATURE_XMM2 },
+ { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 },
+ { X86_FEATURE_FMA, X86_FEATURE_AVX },
+ { X86_FEATURE_AVX2, X86_FEATURE_AVX, },
+ { X86_FEATURE_AVX512F, X86_FEATURE_AVX, },
+ { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_VAES, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F },
+ { X86_FEATURE_AVX512_VP2INTERSECT, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
+ { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
{}
};
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 415621ddb8a2..4e28c1fc8749 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -330,12 +330,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
init_hygon_cacheinfo(c);
if (cpu_has(c, X86_FEATURE_XMM2)) {
- unsigned long long val;
- int ret;
-
/*
- * A serializing LFENCE has less overhead than MFENCE, so
- * use it for execution serialization. On families which
+ * Use LFENCE for execution serialization. On families which
* don't have that MSR, LFENCE is already serializing.
* msr_set_bit() uses the safe accessors, too, even if the MSR
* is not present.
@@ -343,19 +339,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
msr_set_bit(MSR_F10H_DECFG,
MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
- /*
- * Verify that the MSR write was successful (could be running
- * under a hypervisor) and only then assume that LFENCE is
- * serializing.
- */
- ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
- if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
- /* A serializing LFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
- } else {
- /* MFENCE stops RDTSC speculation */
- set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
- }
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
}
/*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8d6d92ebeb54..c2fdc00df163 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -142,21 +142,21 @@ struct sku_microcode {
u32 microcode;
};
static const struct sku_microcode spectre_bad_microcodes[] = {
- { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 },
- { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 },
- { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 },
- { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 },
- { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 },
+ { INTEL_FAM6_KABYLAKE, 0x0B, 0x80 },
+ { INTEL_FAM6_KABYLAKE, 0x0A, 0x80 },
+ { INTEL_FAM6_KABYLAKE, 0x09, 0x80 },
+ { INTEL_FAM6_KABYLAKE_L, 0x0A, 0x80 },
+ { INTEL_FAM6_KABYLAKE_L, 0x09, 0x80 },
{ INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e },
{ INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c },
- { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 },
- { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b },
- { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 },
- { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 },
+ { INTEL_FAM6_BROADWELL, 0x04, 0x28 },
+ { INTEL_FAM6_BROADWELL_G, 0x01, 0x1b },
+ { INTEL_FAM6_BROADWELL_D, 0x02, 0x14 },
+ { INTEL_FAM6_BROADWELL_D, 0x03, 0x07000011 },
{ INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 },
- { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 },
- { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 },
- { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 },
+ { INTEL_FAM6_HASWELL_L, 0x01, 0x21 },
+ { INTEL_FAM6_HASWELL_G, 0x01, 0x18 },
+ { INTEL_FAM6_HASWELL, 0x03, 0x23 },
{ INTEL_FAM6_HASWELL_X, 0x02, 0x3b },
{ INTEL_FAM6_HASWELL_X, 0x04, 0x10 },
{ INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a },
@@ -265,9 +265,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
if (c->x86 == 6) {
switch (c->x86_model) {
- case 0x27: /* Penwell */
- case 0x35: /* Cloverview */
- case 0x4a: /* Merrifield */
+ case INTEL_FAM6_ATOM_SALTWELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
+ case INTEL_FAM6_ATOM_AIRMONT_NP:
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
break;
default:
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index e43eb6732630..88cd9598fa57 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -479,7 +479,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
switch (c->x86_model) {
case INTEL_FAM6_IVYBRIDGE_X:
case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_BROADWELL_XEON_D:
+ case INTEL_FAM6_BROADWELL_D:
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_XEON_PHI_KNL:
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 210f1f5db5f7..87bcdc6dc2f0 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -107,11 +107,11 @@ static struct severity {
*/
MCESEV(
AO, "Action optional: memory scrubbing error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
+ SER, MASK(MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
),
MCESEV(
AO, "Action optional: last level cache writeback error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
+ SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
),
/* ignore OVER for UCNA */
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 4296c702a3f7..72182809b333 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -98,6 +98,7 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg)
case 7:
if (size < 0x40)
break;
+ /* Else, fall through */
case 6:
case 5:
case 4:
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 6a204e7336c1..32b4dc9030aa 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -18,6 +18,12 @@
static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
/*
+ * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by
+ * hardware or BIOS before kernel boot.
+ */
+static u32 orig_umwait_control_cached __ro_after_init;
+
+/*
* Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
* the sysfs write functions.
*/
@@ -53,6 +59,23 @@ static int umwait_cpu_online(unsigned int cpu)
}
/*
+ * The CPU hotplug callback sets the control MSR to the original control
+ * value.
+ */
+static int umwait_cpu_offline(unsigned int cpu)
+{
+ /*
+ * This code is protected by the CPU hotplug already and
+ * orig_umwait_control_cached is never changed after it caches
+ * the original control MSR value in umwait_init(). So there
+ * is no race condition here.
+ */
+ wrmsr(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached, 0);
+
+ return 0;
+}
+
+/*
* On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
* is the only active CPU at this time. The MSR is set up on the APs via the
* CPU hotplug callback.
@@ -185,8 +208,22 @@ static int __init umwait_init(void)
if (!boot_cpu_has(X86_FEATURE_WAITPKG))
return -ENODEV;
+ /*
+ * Cache the original control MSR value before the control MSR is
+ * changed. This is the only place where orig_umwait_control_cached
+ * is modified.
+ */
+ rdmsrl(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
+
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
- umwait_cpu_online, NULL);
+ umwait_cpu_online, umwait_cpu_offline);
+ if (ret < 0) {
+ /*
+ * On failure, the control MSR on all CPUs has the
+ * original control value.
+ */
+ return ret;
+ }
register_syscore_ops(&umwait_syscore_ops);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 3c648476d4fb..9735139cfdf8 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -30,34 +30,69 @@
#include <asm/hypervisor.h>
#include <asm/timer.h>
#include <asm/apic.h>
+#include <asm/vmware.h>
#undef pr_fmt
#define pr_fmt(fmt) "vmware: " fmt
-#define CPUID_VMWARE_INFO_LEAF 0x40000000
+#define CPUID_VMWARE_INFO_LEAF 0x40000000
+#define CPUID_VMWARE_FEATURES_LEAF 0x40000010
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
+
#define VMWARE_HYPERVISOR_MAGIC 0x564D5868
-#define VMWARE_HYPERVISOR_PORT 0x5658
-#define VMWARE_PORT_CMD_GETVERSION 10
-#define VMWARE_PORT_CMD_GETHZ 45
-#define VMWARE_PORT_CMD_GETVCPU_INFO 68
-#define VMWARE_PORT_CMD_LEGACY_X2APIC 3
-#define VMWARE_PORT_CMD_VCPU_RESERVED 31
+#define VMWARE_CMD_GETVERSION 10
+#define VMWARE_CMD_GETHZ 45
+#define VMWARE_CMD_GETVCPU_INFO 68
+#define VMWARE_CMD_LEGACY_X2APIC 3
+#define VMWARE_CMD_VCPU_RESERVED 31
#define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \
__asm__("inl (%%dx)" : \
- "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
- "0"(VMWARE_HYPERVISOR_MAGIC), \
- "1"(VMWARE_PORT_CMD_##cmd), \
- "2"(VMWARE_HYPERVISOR_PORT), "3"(UINT_MAX) : \
- "memory");
+ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
+ "a"(VMWARE_HYPERVISOR_MAGIC), \
+ "c"(VMWARE_CMD_##cmd), \
+ "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) : \
+ "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+ __asm__("vmcall" : \
+ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
+ "a"(VMWARE_HYPERVISOR_MAGIC), \
+ "c"(VMWARE_CMD_##cmd), \
+ "d"(0), "b"(UINT_MAX) : \
+ "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx) \
+ __asm__("vmmcall" : \
+ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
+ "a"(VMWARE_HYPERVISOR_MAGIC), \
+ "c"(VMWARE_CMD_##cmd), \
+ "d"(0), "b"(UINT_MAX) : \
+ "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do { \
+ switch (vmware_hypercall_mode) { \
+ case CPUID_VMWARE_FEATURES_ECX_VMCALL: \
+ VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+ break; \
+ case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+ VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx); \
+ break; \
+ default: \
+ VMWARE_PORT(cmd, eax, ebx, ecx, edx); \
+ break; \
+ } \
+ } while (0)
static unsigned long vmware_tsc_khz __ro_after_init;
+static u8 vmware_hypercall_mode __ro_after_init;
static inline int __vmware_platform(void)
{
uint32_t eax, ebx, ecx, edx;
- VMWARE_PORT(GETVERSION, eax, ebx, ecx, edx);
+ VMWARE_CMD(GETVERSION, eax, ebx, ecx, edx);
return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
}
@@ -129,6 +164,10 @@ static void __init vmware_set_capabilities(void)
{
setup_force_cpu_cap(X86_FEATURE_CONSTANT_TSC);
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+ if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMCALL)
+ setup_force_cpu_cap(X86_FEATURE_VMCALL);
+ else if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMMCALL)
+ setup_force_cpu_cap(X86_FEATURE_VMW_VMMCALL);
}
static void __init vmware_platform_setup(void)
@@ -136,7 +175,7 @@ static void __init vmware_platform_setup(void)
uint32_t eax, ebx, ecx, edx;
uint64_t lpj, tsc_khz;
- VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
+ VMWARE_CMD(GETHZ, eax, ebx, ecx, edx);
if (ebx != UINT_MAX) {
lpj = tsc_khz = eax | (((uint64_t)ebx) << 32);
@@ -174,10 +213,21 @@ static void __init vmware_platform_setup(void)
vmware_set_capabilities();
}
+static u8 vmware_select_hypercall(void)
+{
+ int eax, ebx, ecx, edx;
+
+ cpuid(CPUID_VMWARE_FEATURES_LEAF, &eax, &ebx, &ecx, &edx);
+ return (ecx & (CPUID_VMWARE_FEATURES_ECX_VMMCALL |
+ CPUID_VMWARE_FEATURES_ECX_VMCALL));
+}
+
/*
* While checking the dmi string information, just checking the product
* serial key should be enough, as this will always have a VMware
* specific string when running under VMware hypervisor.
+ * If !boot_cpu_has(X86_FEATURE_HYPERVISOR), vmware_hypercall_mode
+ * intentionally defaults to 0.
*/
static uint32_t __init vmware_platform(void)
{
@@ -187,8 +237,16 @@ static uint32_t __init vmware_platform(void)
cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0],
&hyper_vendor_id[1], &hyper_vendor_id[2]);
- if (!memcmp(hyper_vendor_id, "VMwareVMware", 12))
+ if (!memcmp(hyper_vendor_id, "VMwareVMware", 12)) {
+ if (eax >= CPUID_VMWARE_FEATURES_LEAF)
+ vmware_hypercall_mode =
+ vmware_select_hypercall();
+
+ pr_info("hypercall mode: 0x%02x\n",
+ (unsigned int) vmware_hypercall_mode);
+
return CPUID_VMWARE_INFO_LEAF;
+ }
} else if (dmi_available && dmi_name_in_serial("VMware") &&
__vmware_platform())
return 1;
@@ -200,9 +258,9 @@ static uint32_t __init vmware_platform(void)
static bool __init vmware_legacy_x2apic_available(void)
{
uint32_t eax, ebx, ecx, edx;
- VMWARE_PORT(GETVCPU_INFO, eax, ebx, ecx, edx);
- return (eax & (1 << VMWARE_PORT_CMD_VCPU_RESERVED)) == 0 &&
- (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0;
+ VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx);
+ return (eax & (1 << VMWARE_CMD_VCPU_RESERVED)) == 0 &&
+ (eax & (1 << VMWARE_CMD_LEGACY_X2APIC)) != 0;
}
const __initconst struct hypervisor_x86 x86_hyper_vmware = {
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2bf70a2fed90..eb651fbde92a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -225,8 +225,6 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
if (crashk_low_res.end) {
ret = crash_exclude_mem_range(cmem, crashk_low_res.start,
crashk_low_res.end);
- if (ret)
- return ret;
}
return ret;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2b5886401e5f..e07424e19274 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -367,13 +367,18 @@ NOKPROBE_SYMBOL(oops_end);
int __die(const char *str, struct pt_regs *regs, long err)
{
+ const char *pr = "";
+
/* Save the regs of the first oops for the executive summary later. */
if (!die_counter)
exec_summary_regs = *regs;
+ if (IS_ENABLED(CONFIG_PREEMPTION))
+ pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
+
printk(KERN_DEFAULT
"%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
- IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
+ pr,
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a6342c899be5..f3d3e9646a99 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -193,10 +193,10 @@ ENTRY(secondary_startup_64)
/* Set up %gs.
*
- * The base of %gs always points to the bottom of the irqstack
- * union. If the stack protector canary is enabled, it is
- * located at %gs:40. Note that, on SMP, the boot cpu uses
- * init data section till per cpu areas are set up.
+ * The base of %gs always points to fixed_percpu_data. If the
+ * stack protector canary is enabled, it is located at %gs:40.
+ * Note that, on SMP, the boot cpu uses init data section until
+ * the per cpu areas are set up.
*/
movl $MSR_GS_BASE,%ecx
movl initial_gs(%rip),%eax
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index c43e96a938d0..c6f791bc481e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -827,10 +827,6 @@ int __init hpet_enable(void)
if (!hpet_cfg_working())
goto out_nohpet;
- /* Validate that the counter is counting */
- if (!hpet_counting())
- goto out_nohpet;
-
/*
* Read the period and check for a sane value:
*/
@@ -896,6 +892,14 @@ int __init hpet_enable(void)
}
hpet_print_config();
+ /*
+ * Validate that the counter is counting. This needs to be done
+ * after sanitizing the config registers to properly deal with
+ * force enabled HPETs.
+ */
+ if (!hpet_counting())
+ goto out_nohpet;
+
clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
if (id & HPET_ID_LEGSUP) {
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 4215653f8a8e..21efee32e2b1 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -243,11 +243,15 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
desc = __this_cpu_read(vector_irq[vector]);
-
- if (!handle_irq(desc, regs)) {
+ if (likely(!IS_ERR_OR_NULL(desc))) {
+ if (IS_ENABLED(CONFIG_X86_32))
+ handle_irq(desc, regs);
+ else
+ generic_handle_irq_desc(desc);
+ } else {
ack_APIC_irq();
- if (desc != VECTOR_RETRIGGERED && desc != VECTOR_SHUTDOWN) {
+ if (desc == VECTOR_UNUSED) {
pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
__func__, smp_processor_id(),
vector);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index fc34816c6f04..a759ca97cd01 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -148,18 +148,13 @@ void do_softirq_own_stack(void)
call_on_stack(__do_softirq, isp);
}
-bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
+void handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
int overflow = check_stack_overflow();
- if (IS_ERR_OR_NULL(desc))
- return false;
-
if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
if (unlikely(overflow))
print_stack_overflow();
generic_handle_irq_desc(desc);
}
-
- return true;
}
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 6bf6517a05bb..12df3a4abfdd 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,15 +26,6 @@
DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
DECLARE_INIT_PER_CPU(irq_stack_backing_store);
-bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
-{
- if (IS_ERR_OR_NULL(desc))
- return false;
-
- generic_handle_irq_desc(desc);
- return true;
-}
-
#ifdef CONFIG_VMAP_STACK
/*
* VMAP the backing store with guard pages
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0e0b08008b5a..43fc13c831af 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -580,7 +580,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
if (setup_detour_execution(p, regs, reenter))
return;
-#if !defined(CONFIG_PREEMPT)
+#if !defined(CONFIG_PREEMPTION)
if (p->ainsn.boostable && !p->post_handler) {
/* Boost up -- we can execute copied instructions directly */
if (!reenter)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 9d4aedece363..b348dd506d58 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -403,7 +403,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
(u8 *)op->kp.addr + op->optinsn.size);
len += RELATIVEJUMP_SIZE;
- /* We have to use text_poke for instuction buffer because it is RO */
+ /* We have to use text_poke() for instruction buffer because it is RO */
text_poke(slot, buf, len);
ret = 0;
out:
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b7f34fe2171e..4cc967178bf9 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -308,13 +308,10 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val)
static void kvm_guest_cpu_init(void)
{
- if (!kvm_para_available())
- return;
-
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
pa |= KVM_ASYNC_PF_SEND_ALWAYS;
#endif
pa |= KVM_ASYNC_PF_ENABLED;
@@ -625,9 +622,6 @@ static void __init kvm_guest_init(void)
{
int i;
- if (!kvm_para_available())
- return;
-
paravirt_ops_setup();
register_reboot_notifier(&kvm_pv_reboot_nb);
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
@@ -848,8 +842,6 @@ asm(
*/
void __init kvm_spinlock_init(void)
{
- if (!kvm_para_available())
- return;
/* Does host kernel support KVM_FEATURE_PV_UNHALT? */
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 77854b192fef..7b45e8daad22 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -148,7 +148,7 @@ int machine_kexec_prepare(struct kimage *image)
{
int error;
- set_pages_x(image->control_code_page, 1);
+ set_memory_x((unsigned long)page_address(image->control_code_page), 1);
error = machine_kexec_alloc_page_tables(image);
if (error)
return error;
@@ -162,7 +162,7 @@ int machine_kexec_prepare(struct kimage *image)
*/
void machine_kexec_cleanup(struct kimage *image)
{
- set_pages_nx(image->control_code_page, 1);
+ set_memory_nx((unsigned long)page_address(image->control_code_page), 1);
machine_kexec_free_page_tables(image);
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f62b498b18fb..fa4352dce491 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/dma-direct.h>
#include <linux/dma-debug.h>
+#include <linux/iommu.h>
#include <linux/dmar.h>
#include <linux/export.h>
#include <linux/memblock.h>
@@ -34,21 +35,6 @@ int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
-/*
- * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA translation for
- * devices and allow every device to access to whole physical memory. This is
- * useful if a user wants to use an IOMMU only for KVM device assignment to
- * guests and not for driver dma translation.
- * It is also possible to disable by default in kernel config, and enable with
- * iommu=nopt at boot time.
- */
-#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
-int iommu_pass_through __read_mostly = 1;
-#else
-int iommu_pass_through __read_mostly;
-#endif
-
extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
void __init pci_iommu_alloc(void)
@@ -120,9 +106,9 @@ static __init int iommu_setup(char *p)
swiotlb = 1;
#endif
if (!strncmp(p, "pt", 2))
- iommu_pass_through = 1;
+ iommu_set_default_passthrough(true);
if (!strncmp(p, "nopt", 4))
- iommu_pass_through = 0;
+ iommu_set_default_translated(true);
gart_parse_options(p);
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0fdbe89d0754..3c5bbe8e4120 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -201,6 +201,7 @@ static int set_segment_reg(struct task_struct *task,
case offsetof(struct user_regs_struct, ss):
if (unlikely(value == 0))
return -EIO;
+ /* Else, fall through */
default:
*pt_regs_access(task_pt_regs(task), offset) = value;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 8451f38ad399..1daf8f2aa21f 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -90,8 +90,6 @@ static void ich_force_hpet_resume(void)
BUG();
else
printk(KERN_DEBUG "Force enabled HPET at resume\n");
-
- return;
}
static void ich_force_enable_hpet(struct pci_dev *dev)
@@ -448,7 +446,6 @@ static void nvidia_force_enable_hpet(struct pci_dev *dev)
dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n",
force_hpet_address);
cached_dev = dev;
- return;
}
/* ISA Bridges */
@@ -513,7 +510,6 @@ static void e6xx_force_enable_hpet(struct pci_dev *dev)
force_hpet_resume_type = NONE_FORCE_HPET_RESUME;
dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at "
"0x%lx\n", force_hpet_address);
- return;
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU,
e6xx_force_enable_hpet);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c19f8e21b748..69881b2d446c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1023,8 +1023,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
int *cpu0_nmi_registered)
{
- volatile u32 *trampoline_status =
- (volatile u32 *) __va(real_mode_header->trampoline_status);
/* start_ip had better be page-aligned! */
unsigned long start_ip = real_mode_header->trampoline_start;
@@ -1116,9 +1114,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
}
}
- /* mark "stuck" area as not stuck */
- *trampoline_status = 0;
-
if (x86_platform.legacy.warm_reset) {
/*
* Cleanup possible dangling ends...
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 4f36d3241faf..2d6898c2cb64 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -100,7 +100,7 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
{
int ret;
- if (!access_ok(fp, sizeof(*frame)))
+ if (__range_not_ok(fp, sizeof(*frame), TASK_SIZE))
return 0;
ret = 1;
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
index 8eb67a670b10..653b7f617b61 100644
--- a/arch/x86/kernel/sysfb_efi.c
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -230,9 +230,55 @@ static const struct dmi_system_id efifb_dmi_system_table[] __initconst = {
{},
};
+/*
+ * Some devices have a portrait LCD but advertise a landscape resolution (and
+ * pitch). We simply swap width and height for these devices so that we can
+ * correctly deal with some of them coming with multiple resolutions.
+ */
+static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = {
+ {
+ /*
+ * Lenovo MIIX310-10ICR, only some batches have the troublesome
+ * 800x1280 portrait screen. Luckily the portrait version has
+ * its own BIOS version, so we match on that.
+ */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"),
+ DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"),
+ },
+ },
+ {
+ /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+ "Lenovo MIIX 320-10ICR"),
+ },
+ },
+ {
+ /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+ "Lenovo ideapad D330-10IGM"),
+ },
+ },
+ {},
+};
+
__init void sysfb_apply_efi_quirks(void)
{
if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI ||
!(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS))
dmi_check_system(efifb_dmi_system_table);
+
+ if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI &&
+ dmi_check_system(efifb_dmi_swap_width_height)) {
+ u16 temp = screen_info.lfb_width;
+
+ screen_info.lfb_width = screen_info.lfb_height;
+ screen_info.lfb_height = temp;
+ screen_info.lfb_linelength = 4 * screen_info.lfb_width;
+ }
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 57d87f79558f..c59454c382fd 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -638,7 +638,7 @@ unsigned long native_calibrate_tsc(void)
* clock.
*/
if (crystal_khz == 0 &&
- boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_X)
+ boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_D)
crystal_khz = 25000;
/*
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 067858fe4db8..e0cbe4f2af49 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -58,6 +58,10 @@ static const struct freq_desc freq_desc_ann = {
1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
};
+static const struct freq_desc freq_desc_lgm = {
+ 1, { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 }
+};
+
static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
INTEL_CPU_FAM6(ATOM_SALTWELL_MID, freq_desc_pnw),
INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET, freq_desc_clv),
@@ -65,6 +69,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, freq_desc_tng),
INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht),
INTEL_CPU_FAM6(ATOM_AIRMONT_MID, freq_desc_ann),
+ INTEL_CPU_FAM6(ATOM_AIRMONT_NP, freq_desc_lgm),
{}
};
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 5b345add550f..548fefed71ee 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -19,7 +19,7 @@
/** DOC: Emulation for User-Mode Instruction Prevention (UMIP)
*
* The feature User-Mode Instruction Prevention present in recent Intel
- * processor prevents a group of instructions (sgdt, sidt, sldt, smsw, and str)
+ * processor prevents a group of instructions (SGDT, SIDT, SLDT, SMSW and STR)
* from being executed with CPL > 0. Otherwise, a general protection fault is
* issued.
*
@@ -36,8 +36,8 @@
* DOSEMU2) rely on this subset of instructions to function.
*
* The instructions protected by UMIP can be split in two groups. Those which
- * return a kernel memory address (sgdt and sidt) and those which return a
- * value (sldt, str and smsw).
+ * return a kernel memory address (SGDT and SIDT) and those which return a
+ * value (SLDT, STR and SMSW).
*
* For the instructions that return a kernel memory address, applications
* such as WineHQ rely on the result being located in the kernel memory space,
@@ -45,15 +45,13 @@
* value that, lies close to the top of the kernel memory. The limit for the GDT
* and the IDT are set to zero.
*
- * Given that sldt and str are not commonly used in programs that run on WineHQ
+ * Given that SLDT and STR are not commonly used in programs that run on WineHQ
* or DOSEMU2, they are not emulated.
*
* The instruction smsw is emulated to return the value that the register CR0
* has at boot time as set in the head_32.
*
- * Also, emulation is provided only for 32-bit processes; 64-bit processes
- * that attempt to use the instructions that UMIP protects will receive the
- * SIGSEGV signal issued as a consequence of the general protection fault.
+ * Emulation is provided for both 32-bit and 64-bit processes.
*
* Care is taken to appropriately emulate the results when segmentation is
* used. That is, rather than relying on USER_DS and USER_CS, the function
@@ -63,17 +61,18 @@
* application uses a local descriptor table.
*/
-#define UMIP_DUMMY_GDT_BASE 0xfffe0000
-#define UMIP_DUMMY_IDT_BASE 0xffff0000
+#define UMIP_DUMMY_GDT_BASE 0xfffffffffffe0000ULL
+#define UMIP_DUMMY_IDT_BASE 0xffffffffffff0000ULL
/*
* The SGDT and SIDT instructions store the contents of the global descriptor
* table and interrupt table registers, respectively. The destination is a
* memory operand of X+2 bytes. X bytes are used to store the base address of
- * the table and 2 bytes are used to store the limit. In 32-bit processes, the
- * only processes for which emulation is provided, X has a value of 4.
+ * the table and 2 bytes are used to store the limit. In 32-bit processes X
+ * has a value of 4, in 64-bit processes X has a value of 8.
*/
-#define UMIP_GDT_IDT_BASE_SIZE 4
+#define UMIP_GDT_IDT_BASE_SIZE_64BIT 8
+#define UMIP_GDT_IDT_BASE_SIZE_32BIT 4
#define UMIP_GDT_IDT_LIMIT_SIZE 2
#define UMIP_INST_SGDT 0 /* 0F 01 /0 */
@@ -189,6 +188,7 @@ static int identify_insn(struct insn *insn)
* @umip_inst: A constant indicating the instruction to emulate
* @data: Buffer into which the dummy result is stored
* @data_size: Size of the emulated result
+ * @x86_64: true if process is 64-bit, false otherwise
*
* Emulate an instruction protected by UMIP and provide a dummy result. The
* result of the emulation is saved in @data. The size of the results depends
@@ -202,11 +202,8 @@ static int identify_insn(struct insn *insn)
* 0 on success, -EINVAL on error while emulating.
*/
static int emulate_umip_insn(struct insn *insn, int umip_inst,
- unsigned char *data, int *data_size)
+ unsigned char *data, int *data_size, bool x86_64)
{
- unsigned long dummy_base_addr, dummy_value;
- unsigned short dummy_limit = 0;
-
if (!data || !data_size || !insn)
return -EINVAL;
/*
@@ -219,6 +216,9 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
* is always returned irrespective of the operand size.
*/
if (umip_inst == UMIP_INST_SGDT || umip_inst == UMIP_INST_SIDT) {
+ u64 dummy_base_addr;
+ u16 dummy_limit = 0;
+
/* SGDT and SIDT do not use registers operands. */
if (X86_MODRM_MOD(insn->modrm.value) == 3)
return -EINVAL;
@@ -228,13 +228,24 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
else
dummy_base_addr = UMIP_DUMMY_IDT_BASE;
- *data_size = UMIP_GDT_IDT_LIMIT_SIZE + UMIP_GDT_IDT_BASE_SIZE;
+ /*
+ * 64-bit processes use the entire dummy base address.
+ * 32-bit processes use the lower 32 bits of the base address.
+ * dummy_base_addr is always 64 bits, but we memcpy the correct
+ * number of bytes from it to the destination.
+ */
+ if (x86_64)
+ *data_size = UMIP_GDT_IDT_BASE_SIZE_64BIT;
+ else
+ *data_size = UMIP_GDT_IDT_BASE_SIZE_32BIT;
+
+ memcpy(data + 2, &dummy_base_addr, *data_size);
- memcpy(data + 2, &dummy_base_addr, UMIP_GDT_IDT_BASE_SIZE);
+ *data_size += UMIP_GDT_IDT_LIMIT_SIZE;
memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE);
} else if (umip_inst == UMIP_INST_SMSW) {
- dummy_value = CR0_STATE;
+ unsigned long dummy_value = CR0_STATE;
/*
* Even though the CR0 register has 4 bytes, the number
@@ -290,11 +301,10 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
* fixup_umip_exception() - Fixup a general protection fault caused by UMIP
* @regs: Registers as saved when entering the #GP handler
*
- * The instructions sgdt, sidt, str, smsw, sldt cause a general protection
- * fault if executed with CPL > 0 (i.e., from user space). If the offending
- * user-space process is not in long mode, this function fixes the exception
- * up and provides dummy results for sgdt, sidt and smsw; str and sldt are not
- * fixed up. Also long mode user-space processes are not fixed up.
+ * The instructions SGDT, SIDT, STR, SMSW and SLDT cause a general protection
+ * fault if executed with CPL > 0 (i.e., from user space). This function fixes
+ * the exception up and provides dummy results for SGDT, SIDT and SMSW; STR
+ * and SLDT are not fixed up.
*
* If operands are memory addresses, results are copied to user-space memory as
* indicated by the instruction pointed by eIP using the registers indicated in
@@ -373,13 +383,14 @@ bool fixup_umip_exception(struct pt_regs *regs)
umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
umip_insns[umip_inst]);
- /* Do not emulate SLDT, STR or user long mode processes. */
- if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs))
+ /* Do not emulate (spoof) SLDT or STR. */
+ if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT)
return false;
umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
- if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size))
+ if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size,
+ user_64bit_mode(regs)))
return false;
/*
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index d8359ebeea70..8cd745ef8c7b 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -508,9 +508,12 @@ struct uprobe_xol_ops {
void (*abort)(struct arch_uprobe *, struct pt_regs *);
};
-static inline int sizeof_long(void)
+static inline int sizeof_long(struct pt_regs *regs)
{
- return in_ia32_syscall() ? 4 : 8;
+ /*
+ * Check registers for mode as in_xxx_syscall() does not apply here.
+ */
+ return user_64bit_mode(regs) ? 8 : 4;
}
static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
@@ -521,9 +524,9 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
static int emulate_push_stack(struct pt_regs *regs, unsigned long val)
{
- unsigned long new_sp = regs->sp - sizeof_long();
+ unsigned long new_sp = regs->sp - sizeof_long(regs);
- if (copy_to_user((void __user *)new_sp, &val, sizeof_long()))
+ if (copy_to_user((void __user *)new_sp, &val, sizeof_long(regs)))
return -EFAULT;
regs->sp = new_sp;
@@ -556,7 +559,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs
long correction = utask->vaddr - utask->xol_vaddr;
regs->ip += correction;
} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
- regs->sp += sizeof_long(); /* Pop incorrect return address */
+ regs->sp += sizeof_long(regs); /* Pop incorrect return address */
if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen))
return -ERESTART;
}
@@ -675,7 +678,7 @@ static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
* "call" insn was executed out-of-line. Just restore ->sp and restart.
* We could also restore ->ip and try to call branch_emulate_op() again.
*/
- regs->sp += sizeof_long();
+ regs->sp += sizeof_long(regs);
return -ERESTART;
}
@@ -1056,7 +1059,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
unsigned long
arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
{
- int rasize = sizeof_long(), nleft;
+ int rasize = sizeof_long(regs), nleft;
unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize))