x86/mm: Provide general kernel support for memory encryption

Changes to the existing page table macros will allow the SME support to
be enabled in a simple fashion with minimal changes to files that use these
macros.  Since the memory encryption mask will now be part of the regular
pagetable macros, we introduce two new macros (_PAGE_TABLE_NOENC and
_KERNPG_TABLE_NOENC) to allow for early pagetable creation/initialization
without the encryption mask before SME becomes active.  Two new pgprot()
macros are defined to allow setting or clearing the page encryption mask.

The FIXMAP_PAGE_NOCACHE define is introduced for use with MMIO.  SME does
not support encryption for MMIO areas so this define removes the encryption
mask from the page attribute.

Two new macros are introduced (__sme_pa() / __sme_pa_nodebug()) to allow
creating a physical address with the encryption mask.  These are used when
working with the cr3 register so that the PGD can be encrypted. The current
__va() macro is updated so that the virtual address is generated based off
of the physical address without the encryption mask thus allowing the same
virtual address to be generated regardless of whether encryption is enabled
for that physical location or not.

Also, an early initialization function is added for SME.  If SME is active,
this function:

 - Updates the early_pmd_flags so that early page faults create mappings
   with the encryption mask.

 - Updates the __supported_pte_mask to include the encryption mask.

 - Updates the protection_map entries to include the encryption mask so
   that user-space allocations will automatically have the encryption mask
   applied.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NBorislav Petkov <bp@suse.de>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Toshimitsu Kani <toshi.kani@hpe.com>
Cc: kasan-dev@googlegroups.com
Cc: kvm@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-efi@vger.kernel.org
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/b36e952c4c39767ae7f0a41cf5345adf27438480.1500319216.git.thomas.lendacky@amd.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

arch/x86/boot/compressed/pagetable.c

@@ -15,6 +15,13 @@
 #define __pa(x)  ((unsigned long)(x))
 #define __va(x)  ((void *)((unsigned long)(x)))
 
+/*
+ * The pgtable.h and mm/ident_map.c includes make use of the SME related
+ * information which is not used in the compressed image support. Un-define
+ * the SME support to avoid any compile and link errors.
+ */
+#undef CONFIG_AMD_MEM_ENCRYPT
+
 #include "misc.h"
 
 /* These actually do the work of building the kernel identity maps. */

arch/x86/include/asm/fixmap.h

@@ -157,6 +157,13 @@ static inline void __set_fixmap(enum fixed_addresses idx,
 }
 #endif
 
+/*
+ * FIXMAP_PAGE_NOCACHE is used for MMIO. Memory encryption is not
+ * supported for MMIO addresses, so make sure that the memory encryption
+ * mask is not part of the page attributes.
+ */
+#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_IO_NOCACHE
+
 #include <asm-generic/fixmap.h>
 
 #define __late_set_fixmap(idx, phys, flags) __set_fixmap(idx, phys, flags)

arch/x86/include/asm/mem_encrypt.h

@@ -21,6 +21,8 @@
 
 extern unsigned long sme_me_mask;
 
+void __init sme_early_init(void);
+
 void __init sme_encrypt_kernel(void);
 void __init sme_enable(void);
 
@@ -28,11 +30,22 @@ void __init sme_enable(void);
 
 #define sme_me_mask	0UL
 
+static inline void __init sme_early_init(void) { }
+
 static inline void __init sme_encrypt_kernel(void) { }
 static inline void __init sme_enable(void) { }
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
+/*
+ * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when
+ * writing to or comparing values from the cr3 register.  Having the
+ * encryption mask set in cr3 enables the PGD entry to be encrypted and
+ * avoid special case handling of PGD allocations.
+ */
+#define __sme_pa(x)		(__pa(x) | sme_me_mask)
+#define __sme_pa_nodebug(x)	(__pa_nodebug(x) | sme_me_mask)
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __X86_MEM_ENCRYPT_H__ */

arch/x86/include/asm/page_types.h

@@ -3,6 +3,7 @@
 
 #include <linux/const.h>
 #include <linux/types.h>
+#include <linux/mem_encrypt.h>
 
 /* PAGE_SHIFT determines the page size */
 #define PAGE_SHIFT		12
@@ -15,7 +16,7 @@
 #define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
 
-#define __PHYSICAL_MASK		((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
+#define __PHYSICAL_MASK		((phys_addr_t)(__sme_clr((1ULL << __PHYSICAL_MASK_SHIFT) - 1)))
 #define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
 
 /* Cast *PAGE_MASK to a signed type so that it is sign-extended if

arch/x86/include/asm/pgtable.h

 #ifndef _ASM_X86_PGTABLE_H
 #define _ASM_X86_PGTABLE_H
 
+#include <linux/mem_encrypt.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 
@@ -13,6 +14,12 @@
 		     cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)))	\
 	 : (prot))
 
+/*
+ * Macros to add or remove encryption attribute
+ */
+#define pgprot_encrypted(prot)	__pgprot(__sme_set(pgprot_val(prot)))
+#define pgprot_decrypted(prot)	__pgprot(__sme_clr(pgprot_val(prot)))
+
 #ifndef __ASSEMBLY__
 #include <asm/x86_init.h>
 
@@ -38,6 +45,8 @@ extern struct list_head pgd_list;
 
 extern struct mm_struct *pgd_page_get_mm(struct page *page);
 
+extern pmdval_t early_pmd_flags;
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */

arch/x86/include/asm/pgtable_types.h

@@ -2,6 +2,8 @@
 #define _ASM_X86_PGTABLE_DEFS_H
 
 #include <linux/const.h>
+#include <linux/mem_encrypt.h>
+
 #include <asm/page_types.h>
 
 #define FIRST_USER_ADDRESS	0UL
@@ -121,10 +123,10 @@
 
 #define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
-#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
-			 _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
-			 _PAGE_DIRTY)
+#define _PAGE_TABLE_NOENC	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\
+				 _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE_NOENC	(_PAGE_PRESENT | _PAGE_RW |		\
+				 _PAGE_ACCESSED | _PAGE_DIRTY)
 
 /*
  * Set of bits not changed in pte_modify.  The pte's
@@ -191,18 +193,29 @@ enum page_cache_mode {
 #define __PAGE_KERNEL_IO		(__PAGE_KERNEL)
 #define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE)
 
-#define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
-#define PAGE_KERNEL_EXEC		__pgprot(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RX			__pgprot(__PAGE_KERNEL_RX)
-#define PAGE_KERNEL_NOCACHE		__pgprot(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_LARGE		__pgprot(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_LARGE_EXEC		__pgprot(__PAGE_KERNEL_LARGE_EXEC)
-#define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VVAR		__pgprot(__PAGE_KERNEL_VVAR)
-
-#define PAGE_KERNEL_IO			__pgprot(__PAGE_KERNEL_IO)
-#define PAGE_KERNEL_IO_NOCACHE		__pgprot(__PAGE_KERNEL_IO_NOCACHE)
+#ifndef __ASSEMBLY__
+
+#define _PAGE_ENC	(_AT(pteval_t, sme_me_mask))
+
+#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
+			 _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_ENC)
+#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
+			 _PAGE_DIRTY | _PAGE_ENC)
+
+#define PAGE_KERNEL		__pgprot(__PAGE_KERNEL | _PAGE_ENC)
+#define PAGE_KERNEL_RO		__pgprot(__PAGE_KERNEL_RO | _PAGE_ENC)
+#define PAGE_KERNEL_EXEC	__pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC)
+#define PAGE_KERNEL_RX		__pgprot(__PAGE_KERNEL_RX | _PAGE_ENC)
+#define PAGE_KERNEL_NOCACHE	__pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
+#define PAGE_KERNEL_LARGE	__pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
+#define PAGE_KERNEL_LARGE_EXEC	__pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC)
+#define PAGE_KERNEL_VSYSCALL	__pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC)
+#define PAGE_KERNEL_VVAR	__pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC)
+
+#define PAGE_KERNEL_IO		__pgprot(__PAGE_KERNEL_IO)
+#define PAGE_KERNEL_IO_NOCACHE	__pgprot(__PAGE_KERNEL_IO_NOCACHE)
+
+#endif	/* __ASSEMBLY__ */
 
 /*         xwr */
 #define __P000	PAGE_NONE

arch/x86/include/asm/processor.h

@@ -29,6 +29,7 @@ struct vm86;
 #include <linux/math64.h>
 #include <linux/err.h>
 #include <linux/irqflags.h>
+#include <linux/mem_encrypt.h>
 
 /*
  * We handle most unaligned accesses in hardware.  On the other hand
@@ -241,7 +242,7 @@ static inline unsigned long read_cr3_pa(void)
 
 static inline void load_cr3(pgd_t *pgdir)
 {
-	write_cr3(__pa(pgdir));
+	write_cr3(__sme_pa(pgdir));
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/espfix_64.c

@@ -195,7 +195,7 @@ void init_espfix_ap(int cpu)
 
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
-	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+	pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask));
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
 

arch/x86/kernel/head64.c

@@ -102,7 +102,7 @@ unsigned long __head __startup_64(unsigned long physaddr)
 
 	pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
 	pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
-	pgtable_flags = _KERNPG_TABLE + sme_get_me_mask();
+	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);
@@ -177,7 +177,7 @@ 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 */
@@ -310,6 +310,13 @@ 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++)

arch/x86/kernel/head_64.S

@@ -351,9 +351,9 @@ GLOBAL(name)
 NEXT_PAGE(early_top_pgt)
 	.fill	511,8,0
 #ifdef CONFIG_X86_5LEVEL
-	.quad	level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #else
-	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #endif
 
 NEXT_PAGE(early_dynamic_pgts)
@@ -366,15 +366,15 @@ NEXT_PAGE(init_top_pgt)
 	.fill	512,8,0
 #else
 NEXT_PAGE(init_top_pgt)
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_PAGE_OFFSET*8, 0
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
-	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 
 NEXT_PAGE(level3_ident_pgt)
-	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.fill	511, 8, 0
 NEXT_PAGE(level2_ident_pgt)
 	/* Since I easily can, map the first 1G.
@@ -386,14 +386,14 @@ NEXT_PAGE(level2_ident_pgt)
 #ifdef CONFIG_X86_5LEVEL
 NEXT_PAGE(level4_kernel_pgt)
 	.fill	511,8,0
-	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #endif
 
 NEXT_PAGE(level3_kernel_pgt)
 	.fill	L3_START_KERNEL,8,0
 	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
-	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
-	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 
 NEXT_PAGE(level2_kernel_pgt)
 	/*
@@ -411,7 +411,7 @@ NEXT_PAGE(level2_kernel_pgt)
 
 NEXT_PAGE(level2_fixmap_pgt)
 	.fill	506,8,0
-	.quad	level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 	/* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
 	.fill	5,8,0
 

arch/x86/mm/kasan_init_64.c

@@ -87,7 +87,7 @@ static struct notifier_block kasan_die_notifier = {
 void __init kasan_early_init(void)
 {
 	int i;
-	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
+	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL | _PAGE_ENC;
 	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
 	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
 	p4dval_t p4d_val = __pa_nodebug(kasan_zero_pud) | _KERNPG_TABLE;
@@ -153,7 +153,7 @@ void __init kasan_init(void)
 	 */
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 	for (i = 0; i < PTRS_PER_PTE; i++) {
-		pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO);
+		pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO | _PAGE_ENC);
 		set_pte(&kasan_zero_pte[i], pte);
 	}
 	/* Flush TLBs again to be sure that write protection applied. */

arch/x86/mm/mem_encrypt.c

@@ -12,6 +12,7 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 
 /*
  * Since SME related variables are set early in the boot process they must
@@ -21,6 +22,22 @@
 unsigned long sme_me_mask __section(.data) = 0;
 EXPORT_SYMBOL_GPL(sme_me_mask);
 
+void __init sme_early_init(void)
+{
+	unsigned int i;
+
+	if (!sme_me_mask)
+		return;
+
+	early_pmd_flags = __sme_set(early_pmd_flags);
+
+	__supported_pte_mask = __sme_set(__supported_pte_mask);
+
+	/* Update the protection map with memory encryption mask */
+	for (i = 0; i < ARRAY_SIZE(protection_map); i++)
+		protection_map[i] = pgprot_encrypted(protection_map[i]);
+}
+
 void __init sme_encrypt_kernel(void)
 {
 }

arch/x86/mm/pageattr.c

@@ -2020,6 +2020,9 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 	if (!(page_flags & _PAGE_RW))
 		cpa.mask_clr = __pgprot(_PAGE_RW);
 
+	if (!(page_flags & _PAGE_ENC))
+		cpa.mask_clr = pgprot_encrypted(cpa.mask_clr);
+
 	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);
 
 	retval = __change_page_attr_set_clr(&cpa, 0);

arch/x86/mm/tlb.c

@@ -115,7 +115,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			 */
 			this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen,
 				       next_tlb_gen);
-			write_cr3(__pa(next->pgd));
+			write_cr3(__sme_pa(next->pgd));
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
 					TLB_FLUSH_ALL);
 		}
@@ -157,7 +157,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, next->context.ctx_id);
 		this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, next_tlb_gen);
 		this_cpu_write(cpu_tlbstate.loaded_mm, next);
-		write_cr3(__pa(next->pgd));
+		write_cr3(__sme_pa(next->pgd));
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	}

include/asm-generic/pgtable.h

@@ -582,6 +582,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
 #endif /* CONFIG_MMU */
 
+/*
+ * No-op macros that just return the current protection value. Defined here
+ * because these macros can be used used even if CONFIG_MMU is not defined.
+ */
+#ifndef pgprot_encrypted
+#define pgprot_encrypted(prot)	(prot)
+#endif
+
+#ifndef pgprot_decrypted
+#define pgprot_decrypted(prot)	(prot)
+#endif
+
 /*
  * A facility to provide lazy MMU batching.  This allows PTE updates and
  * page invalidations to be delayed until a call to leave lazy MMU mode

include/linux/mem_encrypt.h

@@ -35,6 +35,14 @@ static inline unsigned long sme_get_me_mask(void)
 	return sme_me_mask;
 }
 
+/*
+ * 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)		((unsigned long)(x) | sme_me_mask)
+#define __sme_clr(x)		((unsigned long)(x) & ~sme_me_mask)
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __MEM_ENCRYPT_H__ */