x86/mm, kexec: Allow kexec to be used with SME

Provide support so that kexec can be used to boot a kernel when SME is
enabled.

Support is needed to allocate pages for kexec without encryption.  This
is needed in order to be able to reboot in the kernel in the same manner
as originally booted.

Additionally, when shutting down all of the CPUs we need to be sure to
flush the caches and then halt. This is needed when booting from a state
where SME was not active into a state where SME is active (or vice-versa).
Without these steps, it is possible for cache lines to exist for the same
physical location but tagged both with and without the encryption bit. This
can cause random memory corruption when caches are flushed depending on
which cacheline is written last.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: <kexec@lists.infradead.org>
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/b95ff075db3e7cd545313f2fb609a49619a09625.1500319216.git.thomas.lendacky@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 54 insertions, 7 deletions

diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 474eb8c66fee..05c4aa00cc86 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -7,6 +7,7 @@ struct x86_mapping_info {
 	unsigned long page_flag;	 /* page flag for PMD or PUD entry */
 	unsigned long offset;		 /* ident mapping offset */
 	bool direct_gbpages;		 /* PUD level 1GB page support */
+	unsigned long kernpg_flag;	 /* kernel pagetable flag override */
 };
 
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 70ef205489f0..e8183acf931f 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -207,6 +207,14 @@ struct kexec_entry64_regs {
 	uint64_t r15;
 	uint64_t rip;
 };
+
+extern int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages,
+				       gfp_t gfp);
+#define arch_kexec_post_alloc_pages arch_kexec_post_alloc_pages
+
+extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages);
+#define arch_kexec_pre_free_pages arch_kexec_pre_free_pages
+
 #endif
 
 typedef void crash_vmclear_fn(void);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 32095af0fefb..830992fc5a06 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -213,6 +213,7 @@ enum page_cache_mode {
 #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_EXEC_NOENC	__pgprot(__PAGE_KERNEL_EXEC)
 #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)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index cb0a30473c23..9cf8daacc046 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -87,7 +87,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
 	}
 	pte = pte_offset_kernel(pmd, vaddr);
-	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
 	return 0;
 err:
 	free_transition_pgtable(image);
@@ -115,6 +115,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 		.alloc_pgt_page	= alloc_pgt_page,
 		.context	= image,
 		.page_flag	= __PAGE_KERNEL_LARGE_EXEC,
+		.kernpg_flag	= _KERNPG_TABLE_NOENC,
 	};
 	unsigned long mstart, mend;
 	pgd_t *level4p;
@@ -602,3 +603,22 @@ void arch_kexec_unprotect_crashkres(void)
 {
 	kexec_mark_crashkres(false);
 }
+
+int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
+{
+	/*
+	 * If SME is active we need to be sure that kexec pages are
+	 * not encrypted because when we boot to the new kernel the
+	 * pages won't be accessed encrypted (initially).
+	 */
+	return set_memory_decrypted((unsigned long)vaddr, pages);
+}
+
+void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
+{
+	/*
+	 * If SME is active we need to reset the pages back to being
+	 * an encrypted mapping before freeing them.
+	 */
+	set_memory_encrypted((unsigned long)vaddr, pages);
+}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3ca198080ea9..bd6b85fac666 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -355,6 +355,7 @@ bool xen_set_default_idle(void)
 	return ret;
 }
 #endif
+
 void stop_this_cpu(void *dummy)
 {
 	local_irq_disable();
@@ -365,8 +366,20 @@ void stop_this_cpu(void *dummy)
 	disable_local_APIC();
 	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 
-	for (;;)
-		halt();
+	for (;;) {
+		/*
+		 * Use wbinvd followed by hlt to stop the processor. This
+		 * provides support for kexec on a processor that supports
+		 * SME. With kexec, going from SME inactive to SME active
+		 * requires clearing cache entries so that addresses without
+		 * the encryption bit set don't corrupt the same physical
+		 * address that has the encryption bit set when caches are
+		 * flushed. To achieve this a wbinvd is performed followed by
+		 * a hlt. Even if the processor is not in the kexec/SME
+		 * scenario this only adds a wbinvd to a halting processor.
+		 */
+		asm volatile("wbinvd; hlt" : : : "memory");
+	}
 }
 
 /*
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index adab1595f4bd..31cea988fa36 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -51,7 +51,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 		if (!pmd)
 			return -ENOMEM;
 		ident_pmd_init(info, pmd, addr, next);
-		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+		set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag));
 	}
 
 	return 0;
@@ -79,7 +79,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
 		if (!pud)
 			return -ENOMEM;
 		ident_pud_init(info, pud, addr, next);
-		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
+		set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag));
 	}
 
 	return 0;
@@ -93,6 +93,10 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 	unsigned long next;
 	int result;
 
+	/* Set the default pagetable flags if not supplied */
+	if (!info->kernpg_flag)
+		info->kernpg_flag = _KERNPG_TABLE;
+
 	for (; addr < end; addr = next) {
 		pgd_t *pgd = pgd_page + pgd_index(addr);
 		p4d_t *p4d;
@@ -116,14 +120,14 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		if (result)
 			return result;
 		if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-			set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
+			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
 		} else {
 			/*
 			 * With p4d folded, pgd is equal to p4d.
 			 * The pgd entry has to point to the pud page table in this case.
 			 */
 			pud_t *pud = pud_offset(p4d, 0);
-			set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+			set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag));
 		}
 	}