1 files changed, 220 insertions, 89 deletions

diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 2b2d018ea345..2f8c32173972 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -2,13 +2,11 @@
 /*
  * AMD Memory Encryption Support
  *
- * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ * Copyright (C) 2016-2024 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  */
 
-#define DISABLE_BRANCH_PROFILING
-
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/mm.h>
@@ -19,18 +17,20 @@
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/dma-mapping.h>
-#include <linux/virtio_config.h>
 #include <linux/cc_platform.h>
 
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
 #include <asm/setup.h>
+#include <asm/mem_encrypt.h>
 #include <asm/bootparam.h>
 #include <asm/set_memory.h>
 #include <asm/cacheflush.h>
 #include <asm/processor-flags.h>
 #include <asm/msr.h>
 #include <asm/cmdline.h>
+#include <asm/sev.h>
+#include <asm/ia32.h>
 
 #include "mm_internal.h"
 
@@ -40,7 +40,9 @@
  * section is later cleared.
  */
 u64 sme_me_mask __section(".data") = 0;
+SYM_PIC_ALIAS(sme_me_mask);
 u64 sev_status __section(".data") = 0;
+SYM_PIC_ALIAS(sev_status);
 u64 sev_check_data __section(".data") = 0;
 EXPORT_SYMBOL(sme_me_mask);
 
@@ -48,6 +50,36 @@ EXPORT_SYMBOL(sme_me_mask);
 static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
 
 /*
+ * SNP-specific routine which needs to additionally change the page state from
+ * private to shared before copying the data from the source to destination and
+ * restore after the copy.
+ */
+static inline void __init snp_memcpy(void *dst, void *src, size_t sz,
+				     unsigned long paddr, bool decrypt)
+{
+	unsigned long npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+
+	if (decrypt) {
+		/*
+		 * @paddr needs to be accessed decrypted, mark the page shared in
+		 * the RMP table before copying it.
+		 */
+		early_snp_set_memory_shared((unsigned long)__va(paddr), paddr, npages);
+
+		memcpy(dst, src, sz);
+
+		/* Restore the page state after the memcpy. */
+		early_snp_set_memory_private((unsigned long)__va(paddr), paddr, npages);
+	} else {
+		/*
+		 * @paddr need to be accessed encrypted, no need for the page state
+		 * change.
+		 */
+		memcpy(dst, src, sz);
+	}
+}
+
+/*
  * This routine does not change the underlying encryption setting of the
  * page(s) that map this memory. It assumes that eventually the memory is
  * meant to be accessed as either encrypted or decrypted but the contents
@@ -95,8 +127,13 @@ static void __init __sme_early_enc_dec(resource_size_t paddr,
 		 * Use a temporary buffer, of cache-line multiple size, to
 		 * avoid data corruption as documented in the APM.
 		 */
-		memcpy(sme_early_buffer, src, len);
-		memcpy(dst, sme_early_buffer, len);
+		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) {
+			snp_memcpy(sme_early_buffer, src, len, paddr, enc);
+			snp_memcpy(dst, sme_early_buffer, len, paddr, !enc);
+		} else {
+			memcpy(sme_early_buffer, src, len);
+			memcpy(dst, sme_early_buffer, len);
+		}
 
 		early_memunmap(dst, len);
 		early_memunmap(src, len);
@@ -177,56 +214,6 @@ void __init sme_map_bootdata(char *real_mode_data)
 	__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true);
 }
 
-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]);
-
-	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		swiotlb_force = SWIOTLB_FORCE;
-}
-
-void __init sev_setup_arch(void)
-{
-	phys_addr_t total_mem = memblock_phys_mem_size();
-	unsigned long size;
-
-	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		return;
-
-	/*
-	 * For SEV, all DMA has to occur via shared/unencrypted pages.
-	 * SEV uses SWIOTLB to make this happen without changing device
-	 * drivers. However, depending on the workload being run, the
-	 * default 64MB of SWIOTLB may not be enough and SWIOTLB may
-	 * run out of buffers for DMA, resulting in I/O errors and/or
-	 * performance degradation especially with high I/O workloads.
-	 *
-	 * Adjust the default size of SWIOTLB for SEV guests using
-	 * a percentage of guest memory for SWIOTLB buffers.
-	 * Also, as the SWIOTLB bounce buffer memory is allocated
-	 * from low memory, ensure that the adjusted size is within
-	 * the limits of low available memory.
-	 *
-	 * The percentage of guest memory used here for SWIOTLB buffers
-	 * is more of an approximation of the static adjustment which
-	 * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
-	 */
-	size = total_mem * 6 / 100;
-	size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
-	swiotlb_adjust_size(size);
-}
-
 static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
 {
 	unsigned long pfn = 0;
@@ -256,11 +243,20 @@ static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
 	return pfn;
 }
 
-void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc)
+static bool amd_enc_tlb_flush_required(bool enc)
+{
+	return true;
+}
+
+static bool amd_enc_cache_flush_required(void)
+{
+	return !cpu_feature_enabled(X86_FEATURE_SME_COHERENT);
+}
+
+static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc)
 {
 #ifdef CONFIG_PARAVIRT
-	unsigned long sz = npages << PAGE_SHIFT;
-	unsigned long vaddr_end = vaddr + sz;
+	unsigned long vaddr_end = vaddr + size;
 
 	while (vaddr < vaddr_end) {
 		int psize, pmask, level;
@@ -287,47 +283,112 @@ void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc)
 #endif
 }
 
-static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+static int amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
 {
-	pgprot_t old_prot, new_prot;
-	unsigned long pfn, pa, size;
-	pte_t new_pte;
+	/*
+	 * To maintain the security guarantees of SEV-SNP guests, make sure
+	 * to invalidate the memory before encryption attribute is cleared.
+	 */
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc)
+		snp_set_memory_shared(vaddr, npages);
 
-	pfn = pg_level_to_pfn(level, kpte, &old_prot);
-	if (!pfn)
-		return;
+	return 0;
+}
 
-	new_prot = old_prot;
-	if (enc)
-		pgprot_val(new_prot) |= _PAGE_ENC;
+/* Return true unconditionally: return value doesn't matter for the SEV side */
+static int amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
+{
+	/*
+	 * After memory is mapped encrypted in the page table, validate it
+	 * so that it is consistent with the page table updates.
+	 */
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && enc)
+		snp_set_memory_private(vaddr, npages);
+
+	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc);
+
+	return 0;
+}
+
+int prepare_pte_enc(struct pte_enc_desc *d)
+{
+	pgprot_t old_prot;
+
+	d->pfn = pg_level_to_pfn(d->pte_level, d->kpte, &old_prot);
+	if (!d->pfn)
+		return 1;
+
+	d->new_pgprot = old_prot;
+	if (d->encrypt)
+		pgprot_val(d->new_pgprot) |= _PAGE_ENC;
 	else
-		pgprot_val(new_prot) &= ~_PAGE_ENC;
+		pgprot_val(d->new_pgprot) &= ~_PAGE_ENC;
 
 	/* If prot is same then do nothing. */
-	if (pgprot_val(old_prot) == pgprot_val(new_prot))
-		return;
+	if (pgprot_val(old_prot) == pgprot_val(d->new_pgprot))
+		return 1;
 
-	pa = pfn << PAGE_SHIFT;
-	size = page_level_size(level);
+	d->pa = d->pfn << PAGE_SHIFT;
+	d->size = page_level_size(d->pte_level);
 
 	/*
-	 * We are going to perform in-place en-/decryption and change the
-	 * physical page attribute from C=1 to C=0 or vice versa. Flush the
-	 * caches to ensure that data gets accessed with the correct C-bit.
+	 * In-place en-/decryption and physical page attribute change
+	 * from C=1 to C=0 or vice versa will be performed. Flush the
+	 * caches to ensure that data gets accessed with the correct
+	 * C-bit.
 	 */
-	clflush_cache_range(__va(pa), size);
-
-	/* Encrypt/decrypt the contents in-place */
-	if (enc)
-		sme_early_encrypt(pa, size);
+	if (d->va)
+		clflush_cache_range(d->va, d->size);
 	else
-		sme_early_decrypt(pa, size);
+		clflush_cache_range(__va(d->pa), d->size);
+
+	return 0;
+}
+
+void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot)
+{
+	pte_t new_pte;
 
 	/* Change the page encryption mask. */
 	new_pte = pfn_pte(pfn, new_prot);
 	set_pte_atomic(kpte, new_pte);
 }
 
+static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+{
+	struct pte_enc_desc d = {
+		.kpte	     = kpte,
+		.pte_level   = level,
+		.encrypt     = enc
+	};
+
+	if (prepare_pte_enc(&d))
+		return;
+
+	/* Encrypt/decrypt the contents in-place */
+	if (enc) {
+		sme_early_encrypt(d.pa, d.size);
+	} else {
+		sme_early_decrypt(d.pa, d.size);
+
+		/*
+		 * ON SNP, the page state in the RMP table must happen
+		 * before the page table updates.
+		 */
+		early_snp_set_memory_shared((unsigned long)__va(d.pa), d.pa, 1);
+	}
+
+	set_pte_enc_mask(kpte, d.pfn, d.new_pgprot);
+
+	/*
+	 * If page is set encrypted in the page table, then update the RMP table to
+	 * add this page as private.
+	 */
+	if (enc)
+		early_snp_set_memory_private((unsigned long)__va(d.pa), d.pa, 1);
+}
+
 static int __init early_set_memory_enc_dec(unsigned long vaddr,
 					   unsigned long size, bool enc)
 {
@@ -392,7 +453,7 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr,
 
 	ret = 0;
 
-	notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc);
+	early_set_mem_enc_dec_hypercall(start, size, enc);
 out:
 	__flush_tlb_all();
 	return ret;
@@ -408,9 +469,75 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
 	return early_set_memory_enc_dec(vaddr, size, true);
 }
 
-void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
+void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc)
+{
+	enc_dec_hypercall(vaddr, size, enc);
+}
+
+void __init sme_early_init(void)
 {
-	notify_range_enc_status_changed(vaddr, npages, enc);
+	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 */
+	add_encrypt_protection_map();
+
+	x86_platform.guest.enc_status_change_prepare = amd_enc_status_change_prepare;
+	x86_platform.guest.enc_status_change_finish  = amd_enc_status_change_finish;
+	x86_platform.guest.enc_tlb_flush_required    = amd_enc_tlb_flush_required;
+	x86_platform.guest.enc_cache_flush_required  = amd_enc_cache_flush_required;
+	x86_platform.guest.enc_kexec_begin	     = snp_kexec_begin;
+	x86_platform.guest.enc_kexec_finish	     = snp_kexec_finish;
+
+	/*
+	 * AMD-SEV-ES intercepts the RDMSR to read the X2APIC ID in the
+	 * parallel bringup low level code. That raises #VC which cannot be
+	 * handled there.
+	 * It does not provide a RDMSR GHCB protocol so the early startup
+	 * code cannot directly communicate with the secure firmware. The
+	 * alternative solution to retrieve the APIC ID via CPUID(0xb),
+	 * which is covered by the GHCB protocol, is not viable either
+	 * because there is no enforcement of the CPUID(0xb) provided
+	 * "initial" APIC ID to be the same as the real APIC ID.
+	 * Disable parallel bootup.
+	 */
+	if (sev_status & MSR_AMD64_SEV_ES_ENABLED)
+		x86_cpuinit.parallel_bringup = false;
+
+	/*
+	 * The VMM is capable of injecting interrupt 0x80 and triggering the
+	 * compatibility syscall path.
+	 *
+	 * By default, the 32-bit emulation is disabled in order to ensure
+	 * the safety of the VM.
+	 */
+	if (sev_status & MSR_AMD64_SEV_ENABLED)
+		ia32_disable();
+
+	/*
+	 * Override init functions that scan the ROM region in SEV-SNP guests,
+	 * as this memory is not pre-validated and would thus cause a crash.
+	 */
+	if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+		x86_init.mpparse.find_mptable = x86_init_noop;
+		x86_init.pci.init_irq = x86_init_noop;
+		x86_init.resources.probe_roms = x86_init_noop;
+
+		/*
+		 * DMI setup behavior for SEV-SNP guests depends on
+		 * efi_enabled(EFI_CONFIG_TABLES), which hasn't been
+		 * parsed yet. snp_dmi_setup() will run after that
+		 * parsing has happened.
+		 */
+		x86_init.resources.dmi_setup = snp_dmi_setup;
+	}
+
+	if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
@@ -423,10 +550,14 @@ void __init mem_encrypt_free_decrypted_mem(void)
 	npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
 
 	/*
-	 * The unused memory range was mapped decrypted, change the encryption
-	 * attribute from decrypted to encrypted before freeing it.
+	 * If the unused memory range was mapped decrypted, change the encryption
+	 * attribute from decrypted to encrypted before freeing it. Base the
+	 * re-encryption on the same condition used for the decryption in
+	 * sme_postprocess_startup(). Higher level abstractions, such as
+	 * CC_ATTR_MEM_ENCRYPT, aren't necessarily equivalent in a Hyper-V VM
+	 * using vTOM, where sme_me_mask is always zero.
 	 */
-	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+	if (sme_me_mask) {
 		r = set_memory_encrypted(vaddr, npages);
 		if (r) {
 			pr_warn("failed to free unused decrypted pages\n");