Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Ingo Molnar:
 "PCID support, 5-level paging support, Secure Memory Encryption support

  The main changes in this cycle are support for three new, complex
  hardware features of x86 CPUs:

   - Add 5-level paging support, which is a new hardware feature on
     upcoming Intel CPUs allowing up to 128 PB of virtual address space
     and 4 PB of physical RAM space - a 512-fold increase over the old
     limits. (Supercomputers of the future forecasting hurricanes on an
     ever warming planet can certainly make good use of more RAM.)

     Many of the necessary changes went upstream in previous cycles,
     v4.14 is the first kernel that can enable 5-level paging.

     This feature is activated via CONFIG_X86_5LEVEL=y - disabled by
     default.

     (By Kirill A. Shutemov)

   - Add 'encrypted memory' support, which is a new hardware feature on
     upcoming AMD CPUs ('Secure Memory Encryption', SME) allowing system
     RAM to be encrypted and decrypted (mostly) transparently by the
     CPU, with a little help from the kernel to transition to/from
     encrypted RAM. Such RAM should be more secure against various
     attacks like RAM access via the memory bus and should make the
     radio signature of memory bus traffic harder to intercept (and
     decrypt) as well.

     This feature is activated via CONFIG_AMD_MEM_ENCRYPT=y - disabled
     by default.

     (By Tom Lendacky)

   - Enable PCID optimized TLB flushing on newer Intel CPUs: PCID is a
     hardware feature that attaches an address space tag to TLB entries
     and thus allows to skip TLB flushing in many cases, even if we
     switch mm's.

     (By Andy Lutomirski)

  All three of these features were in the works for a long time, and
  it's coincidence of the three independent development paths that they
  are all enabled in v4.14 at once"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (65 commits)
  x86/mm: Enable RCU based page table freeing (CONFIG_HAVE_RCU_TABLE_FREE=y)
  x86/mm: Use pr_cont() in dump_pagetable()
  x86/mm: Fix SME encryption stack ptr handling
  kvm/x86: Avoid clearing the C-bit in rsvd_bits()
  x86/CPU: Align CR3 defines
  x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages
  acpi, x86/mm: Remove encryption mask from ACPI page protection type
  x86/mm, kexec: Fix memory corruption with SME on successive kexecs
  x86/mm/pkeys: Fix typo in Documentation/x86/protection-keys.txt
  x86/mm/dump_pagetables: Speed up page tables dump for CONFIG_KASAN=y
  x86/mm: Implement PCID based optimization: try to preserve old TLB entries using PCID
  x86: Enable 5-level paging support via CONFIG_X86_5LEVEL=y
  x86/mm: Allow userspace have mappings above 47-bit
  x86/mm: Prepare to expose larger address space to userspace
  x86/mpx: Do not allow MPX if we have mappings above 47-bit
  x86/mm: Rename tasksize_32bit/64bit to task_size_32bit/64bit()
  x86/xen: Redefine XEN_ELFNOTE_INIT_P2M using PUD_SIZE * PTRS_PER_PUD
  x86/mm/dump_pagetables: Fix printout of p4d level
  x86/mm/dump_pagetables: Generalize address normalization
  x86/boot: Fix memremap() related build failure
  ...

1 files changed, 79 insertions, 16 deletions

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 9ba79543d9ee..6a193b93fd95 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -14,6 +14,7 @@
 #include <linux/start_kernel.h>
 #include <linux/io.h>
 #include <linux/memblock.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -33,7 +34,6 @@
 /*
  * Manage page tables very early on.
  */
-extern pgd_t early_top_pgt[PTRS_PER_PGD];
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
 static unsigned int __initdata next_early_pgt;
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
@@ -45,9 +45,11 @@ static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
 	return ptr - (void *)_text + (void *)physaddr;
 }
 
-void __head __startup_64(unsigned long physaddr)
+unsigned long __head __startup_64(unsigned long physaddr,
+				  struct boot_params *bp)
 {
 	unsigned long load_delta, *p;
+	unsigned long pgtable_flags;
 	pgdval_t *pgd;
 	p4dval_t *p4d;
 	pudval_t *pud;
@@ -69,6 +71,12 @@ void __head __startup_64(unsigned long physaddr)
 	if (load_delta & ~PMD_PAGE_MASK)
 		for (;;);
 
+	/* Activate Secure Memory Encryption (SME) if supported and enabled */
+	sme_enable(bp);
+
+	/* Include the SME encryption mask in the fixup value */
+	load_delta += sme_get_me_mask();
+
 	/* Fixup the physical addresses in the page table */
 
 	pgd = fixup_pointer(&early_top_pgt, physaddr);
@@ -92,31 +100,35 @@ void __head __startup_64(unsigned long physaddr)
 	 * creates a bunch of nonsense entries but that is fine --
 	 * it avoids problems around wraparound.
 	 */
+
 	next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr);
 	pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
 	pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
 
+	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
+
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
 		p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
 
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE;
-		pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE;
+		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
 
 		i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D;
-		p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE;
-		p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE;
+		p4d[i + 0] = (pgdval_t)pud + pgtable_flags;
+		p4d[i + 1] = (pgdval_t)pud + pgtable_flags;
 	} else {
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE;
-		pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE;
+		pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
 	}
 
 	i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD;
-	pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE;
-	pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE;
+	pud[i + 0] = (pudval_t)pmd + pgtable_flags;
+	pud[i + 1] = (pudval_t)pmd + pgtable_flags;
 
 	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+	pmd_entry += sme_get_me_mask();
 	pmd_entry +=  physaddr;
 
 	for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) {
@@ -137,9 +149,30 @@ void __head __startup_64(unsigned long physaddr)
 			pmd[i] += load_delta;
 	}
 
-	/* Fixup phys_base */
+	/*
+	 * Fixup phys_base - remove the memory encryption mask to obtain
+	 * the true physical address.
+	 */
 	p = fixup_pointer(&phys_base, physaddr);
-	*p += load_delta;
+	*p += load_delta - sme_get_me_mask();
+
+	/* Encrypt the kernel (if SME is active) */
+	sme_encrypt_kernel();
+
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
+}
+
+unsigned long __startup_secondary_64(void)
+{
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
 }
 
 /* Wipe all early page tables except for the kernel symbol map */
@@ -147,17 +180,17 @@ static void __init reset_early_page_tables(void)
 {
 	memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1));
 	next_early_pgt = 0;
-	write_cr3(__pa_nodebug(early_top_pgt));
+	write_cr3(__sme_pa_nodebug(early_top_pgt));
 }
 
 /* Create a new PMD entry */
-int __init early_make_pgtable(unsigned long address)
+int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
 {
 	unsigned long physaddr = address - __PAGE_OFFSET;
 	pgdval_t pgd, *pgd_p;
 	p4dval_t p4d, *p4d_p;
 	pudval_t pud, *pud_p;
-	pmdval_t pmd, *pmd_p;
+	pmdval_t *pmd_p;
 
 	/* Invalid address or early pgt is done ?  */
 	if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt))
@@ -216,12 +249,21 @@ again:
 		memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
 		*pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
 	}
-	pmd = (physaddr & PMD_MASK) + early_pmd_flags;
 	pmd_p[pmd_index(address)] = pmd;
 
 	return 0;
 }
 
+int __init early_make_pgtable(unsigned long address)
+{
+	unsigned long physaddr = address - __PAGE_OFFSET;
+	pmdval_t pmd;
+
+	pmd = (physaddr & PMD_MASK) + early_pmd_flags;
+
+	return __early_make_pgtable(address, pmd);
+}
+
 /* Don't add a printk in there. printk relies on the PDA which is not initialized 
    yet. */
 static void __init clear_bss(void)
@@ -244,6 +286,12 @@ static void __init copy_bootdata(char *real_mode_data)
 	char * command_line;
 	unsigned long cmd_line_ptr;
 
+	/*
+	 * If SME is active, this will create decrypted mappings of the
+	 * boot data in advance of the copy operations.
+	 */
+	sme_map_bootdata(real_mode_data);
+
 	memcpy(&boot_params, real_mode_data, sizeof boot_params);
 	sanitize_boot_params(&boot_params);
 	cmd_line_ptr = get_cmd_line_ptr();
@@ -251,6 +299,14 @@ static void __init copy_bootdata(char *real_mode_data)
 		command_line = __va(cmd_line_ptr);
 		memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
 	}
+
+	/*
+	 * The old boot data is no longer needed and won't be reserved,
+	 * freeing up that memory for use by the system. If SME is active,
+	 * we need to remove the mappings that were created so that the
+	 * memory doesn't remain mapped as decrypted.
+	 */
+	sme_unmap_bootdata(real_mode_data);
 }
 
 asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
@@ -280,6 +336,13 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 
 	clear_page(init_top_pgt);
 
+	/*
+	 * SME support may update early_pmd_flags to include the memory
+	 * encryption mask, so it needs to be called before anything
+	 * that may generate a page fault.
+	 */
+	sme_early_init();
+
 	kasan_early_init();
 
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)