Received-SPF: pass (google.com: domain of linux-kernel+bounces-40743-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From: Tom Lendacky <thomas.lendacky@amd.com>
To: <linux-kernel@vger.kernel.org>, <x86@kernel.org>
CC: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
	Borislav Petkov <bp@alien8.de>, Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>, Andy Lutomirski <luto@kernel.org>, "Peter
 Zijlstra" <peterz@infradead.org>, Dan Williams <dan.j.williams@intel.com>,
	Michael Roth <michael.roth@amd.com>, Ashish Kalra <ashish.kalra@amd.com>
Subject: [PATCH 05/11] x86/sev: Perform PVALIDATE using the SVSM when not at VMPL0
Date: Fri, 26 Jan 2024 16:15:58 -0600
Message-ID: <d89b9ebb592a2436a1969304f826ddf3866682bc.1706307364.git.thomas.lendacky@amd.com>
In-Reply-To: <cover.1706307364.git.thomas.lendacky@amd.com>
References: <cover.1706307364.git.thomas.lendacky@amd.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 26 Jan 2024 22:16:47.2355
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 9a5753c0-cd2b-464a-b234-08dc1ebc7c9f
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource:
	DS2PEPF00003440.namprd02.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SJ0PR12MB6942

The PVALIDATE instruction can only be performed at VMPL0. An SVSM will
be present when running at VMPL1 or a lower privilege level.

When an SVSM is present, use the SVSM_CORE_PVALIDATE call to perform
memory validation instead of issuing the PVALIDATE instruction directly.

The validation of a single 4K page is now explicitly identified as such
in the function name, pvalidate_4k_page(). The pvalidate_pages() function
is used for validating 1 or more pages at either 4K or 2M in size. Each
function, however, determines whether it can issue the PVALIDATE directly
or whether the SVSM needs to be invoked.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
---
 arch/x86/boot/compressed/sev.c |  42 +++++++-
 arch/x86/include/asm/sev.h     |  22 +++++
 arch/x86/kernel/sev-shared.c   | 176 ++++++++++++++++++++++++++++++++-
 arch/x86/kernel/sev.c          |  25 +++--
 4 files changed, 247 insertions(+), 18 deletions(-)

diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 5d2403914ceb..3fbb614c31e0 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -38,6 +38,16 @@ static u8 vmpl __section(".data");
 static u64 boot_svsm_caa_pa __section(".data");
 static struct svsm_ca *boot_svsm_caa __section(".data");
 
+static struct svsm_ca *__svsm_get_caa(void)
+{
+	return boot_svsm_caa;
+}
+
+static u64 __svsm_get_caa_pa(void)
+{
+	return boot_svsm_caa_pa;
+}
+
 /*
  * Copy a version of this function here - insn-eval.c can't be used in
  * pre-decompression code.
@@ -135,6 +145,24 @@ static bool fault_in_kernel_space(unsigned long address)
 /* Include code for early handlers */
 #include "../../kernel/sev-shared.c"
 
+static int svsm_protocol(struct svsm_call *call)
+{
+	struct ghcb *ghcb;
+	int ret;
+
+	if (boot_ghcb)
+		ghcb = boot_ghcb;
+	else
+		ghcb = NULL;
+
+	do {
+		ret = ghcb ? __svsm_ghcb_protocol(ghcb, call)
+			   : __svsm_msr_protocol(call);
+	} while (ret == SVSM_ERR_BUSY);
+
+	return ret;
+}
+
 bool sev_snp_enabled(void)
 {
 	return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
@@ -151,8 +179,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	 * If private -> shared then invalidate the page before requesting the
 	 * state change in the RMP table.
 	 */
-	if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0))
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+	if (op == SNP_PAGE_STATE_SHARED)
+		pvalidate_4k_page(paddr, paddr, 0);
 
 	/* Issue VMGEXIT to change the page state in RMP table. */
 	sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
@@ -167,8 +195,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	 * Now that page state is changed in the RMP table, validate it so that it is
 	 * consistent with the RMP entry.
 	 */
-	if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1))
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+	if (op == SNP_PAGE_STATE_PRIVATE)
+		pvalidate_4k_page(paddr, paddr, 1);
 }
 
 void snp_set_page_private(unsigned long paddr)
@@ -261,6 +289,12 @@ void sev_es_shutdown_ghcb(void)
 	if (!sev_es_check_cpu_features())
 		error("SEV-ES CPU Features missing.");
 
+	/*
+	 * Ensure that the boot GHCB isn't used for the PVALIDATE when running
+	 * under an SVSM.
+	 */
+	boot_ghcb = NULL;
+
 	/*
 	 * GHCB Page must be flushed from the cache and mapped encrypted again.
 	 * Otherwise the running kernel will see strange cache effects when
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 2f1e583769fc..dbd7fd041689 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -172,6 +172,27 @@ struct svsm_ca {
 #define SVSM_ERR_INVALID_PARAMETER		0x80000005
 #define SVSM_ERR_INVALID_REQUEST		0x80000006
 #define SVSM_ERR_BUSY				0x80000007
+#define SVSM_PVALIDATE_FAIL_SIZEMISMATCH	0x80001006
+
+/*
+ * The SVSM PVALIDATE related structures
+ */
+struct svsm_pvalidate_entry {
+	u64 page_size		: 2,
+	    action		: 1,
+	    ignore_cf		: 1,
+	    rsvd		: 8,
+	    pfn			: 52;
+};
+
+struct svsm_pvalidate_call {
+	u16 entries;
+	u16 next;
+
+	u8 rsvd1[4];
+
+	struct svsm_pvalidate_entry entry[];
+};
 
 /*
  * SVSM protocol structure
@@ -192,6 +213,7 @@ struct svsm_call {
 
 #define SVSM_CORE_CALL(x)		((0ULL << 32) | (x))
 #define SVSM_CORE_REMAP_CA		0
+#define SVSM_CORE_PVALIDATE		1
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 extern void __sev_es_ist_enter(struct pt_regs *regs);
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 7e9fa5d8889b..f26e872bc5d0 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -81,6 +81,8 @@ static u32 cpuid_std_range_max __ro_after_init;
 static u32 cpuid_hyp_range_max __ro_after_init;
 static u32 cpuid_ext_range_max __ro_after_init;
 
+static int svsm_protocol(struct svsm_call *call);
+
 static bool __init sev_es_check_cpu_features(void)
 {
 	if (!has_cpuflag(X86_FEATURE_RDRAND)) {
@@ -1181,7 +1183,65 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
 	}
 }
 
-static void pvalidate_pages(struct snp_psc_desc *desc)
+static int base_pvalidate_4k_page(unsigned long vaddr, bool validate)
+{
+	return pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+}
+
+static int svsm_pvalidate_4k_page(unsigned long paddr, bool validate)
+{
+	struct svsm_pvalidate_call *pvalidate_call;
+	struct svsm_call call = {};
+	u64 pvalidate_call_pa;
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * This can be called very early in the boot, use native functions in
+	 * order to avoid paravirt issues.
+	 */
+	flags = native_save_fl();
+	if (flags & X86_EFLAGS_IF)
+		native_irq_disable();
+
+	call.caa = __svsm_get_caa();
+
+	pvalidate_call = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+	pvalidate_call_pa = __svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+	pvalidate_call->entries = 1;
+	pvalidate_call->next    = 0;
+	pvalidate_call->entry[0].page_size = RMP_PG_SIZE_4K;
+	pvalidate_call->entry[0].action    = validate;
+	pvalidate_call->entry[0].ignore_cf = 0;
+	pvalidate_call->entry[0].pfn       = paddr >> PAGE_SHIFT;
+
+	/* Protocol 0, Call ID 1 */
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+	call.rcx = pvalidate_call_pa;
+
+	ret = svsm_protocol(&call);
+
+	if (flags & X86_EFLAGS_IF)
+		native_irq_enable();
+
+	return ret;
+}
+
+static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool validate)
+{
+	int ret;
+
+	ret = vmpl ? svsm_pvalidate_4k_page(paddr, validate)
+		   : base_pvalidate_4k_page(vaddr, validate);
+
+	if (ret) {
+		WARN(1, "Failed to validate address 0x%lx ret %d", vaddr, ret);
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+	}
+}
+
+static void base_pvalidate_pages(struct snp_psc_desc *desc)
 {
 	struct psc_entry *e;
 	unsigned long vaddr;
@@ -1215,6 +1275,120 @@ static void pvalidate_pages(struct snp_psc_desc *desc)
 	}
 }
 
+static void svsm_pvalidate_pages(struct snp_psc_desc *desc)
+{
+	struct svsm_pvalidate_call *pvalidate_call;
+	struct svsm_pvalidate_entry *pe;
+	unsigned int call_count, i;
+	struct svsm_call call = {};
+	u64 pvalidate_call_pa;
+	struct psc_entry *e;
+	unsigned long flags;
+	unsigned long vaddr;
+	bool action;
+	int ret;
+
+	/*
+	 * This can be called very early in the boot, use native functions in
+	 * order to avoid paravirt issues.
+	 */
+	flags = native_save_fl();
+	if (flags & X86_EFLAGS_IF)
+		native_irq_disable();
+
+	call.caa = __svsm_get_caa();
+
+	pvalidate_call = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+	pvalidate_call_pa = __svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+	/* Calculate how many entries the CA buffer can hold */
+	call_count = sizeof(call.caa->svsm_buffer);
+	call_count -= offsetof(struct svsm_pvalidate_call, entry);
+	call_count /= sizeof(pvalidate_call->entry[0]);
+
+	/* Protocol 0, Call ID 1 */
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+	call.rcx = pvalidate_call_pa;
+
+	pvalidate_call->entries = 0;
+	pvalidate_call->next    = 0;
+
+	for (i = 0; i <= desc->hdr.end_entry; i++) {
+		e = &desc->entries[i];
+		pe = &pvalidate_call->entry[pvalidate_call->entries];
+
+		pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+		pe->action    = e->operation == SNP_PAGE_STATE_PRIVATE;
+		pe->ignore_cf = 0;
+		pe->pfn       = e->gfn;
+
+		pvalidate_call->entries++;
+		if (pvalidate_call->entries < call_count && i != desc->hdr.end_entry)
+			continue;
+
+		ret = svsm_protocol(&call);
+		if (ret == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
+		    pvalidate_call->entry[pvalidate_call->next].page_size == RMP_PG_SIZE_2M) {
+			u64 pfn, pfn_end;
+
+			/*
+			 * The "next" field is the index of the failed entry. Calculate the
+			 * index of the entry after the failed entry before the fields are
+			 * cleared so that processing can continue on from that point (take
+			 * into account the for loop adding 1 to the entry).
+			 */
+			i -= pvalidate_call->entries - pvalidate_call->next;
+			i += 1;
+
+			action = pvalidate_call->entry[pvalidate_call->next].action;
+			pfn = pvalidate_call->entry[pvalidate_call->next].pfn;
+			pfn_end = pfn + 511;
+
+			pvalidate_call->entries = 0;
+			pvalidate_call->next    = 0;
+			for (; pfn <= pfn_end; pfn++) {
+				pe = &pvalidate_call->entry[pvalidate_call->entries];
+
+				pe->page_size = RMP_PG_SIZE_4K;
+				pe->action    = action;
+				pe->ignore_cf = 0;
+				pe->pfn       = pfn;
+
+				pvalidate_call->entries++;
+				if (pvalidate_call->entries < call_count && pfn != pfn_end)
+					continue;
+
+				ret = svsm_protocol(&call);
+				if (ret != SVSM_SUCCESS)
+					break;
+
+				pvalidate_call->entries = 0;
+				pvalidate_call->next    = 0;
+			}
+		}
+
+		if (ret != SVSM_SUCCESS) {
+			pe = &pvalidate_call->entry[pvalidate_call->next];
+			vaddr = (unsigned long)pfn_to_kaddr(pe->pfn);
+
+			WARN(1, "Failed to validate address %lx ret=%#x (%d)", vaddr, ret, ret);
+			sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+		}
+
+		pvalidate_call->entries = 0;
+		pvalidate_call->next    = 0;
+	}
+
+	if (flags & X86_EFLAGS_IF)
+		native_irq_enable();
+}
+
+static void pvalidate_pages(struct snp_psc_desc *desc)
+{
+	vmpl ? svsm_pvalidate_pages(desc)
+	     : base_pvalidate_pages(desc);
+}
+
 static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
 {
 	int cur_entry, end_entry, ret = 0;
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 3bd7860fbfe1..2fd21090ef6b 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -161,6 +161,12 @@ static struct svsm_ca *__svsm_get_caa(void)
 				       : boot_svsm_caa;
 }
 
+static u64 __svsm_get_caa_pa(void)
+{
+	return sev_cfg.cas_initialized ? this_cpu_read(svsm_caa_pa)
+				       : boot_svsm_caa_pa;
+}
+
 static __always_inline bool on_vc_stack(struct pt_regs *regs)
 {
 	unsigned long sp = regs->sp;
@@ -777,7 +783,6 @@ static void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
 {
 	unsigned long paddr_end;
 	u64 val;
-	int ret;
 
 	vaddr = vaddr & PAGE_MASK;
 
@@ -785,12 +790,9 @@ static void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
 	paddr_end = paddr + (npages << PAGE_SHIFT);
 
 	while (paddr < paddr_end) {
-		if (op == SNP_PAGE_STATE_SHARED) {
-			/* Page validation must be rescinded before changing to shared */
-			ret = pvalidate(vaddr, RMP_PG_SIZE_4K, false);
-			if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret))
-				goto e_term;
-		}
+		/* Page validation must be rescinded before changing to shared */
+		if (op == SNP_PAGE_STATE_SHARED)
+			pvalidate_4k_page(vaddr, paddr, false);
 
 		/*
 		 * Use the MSR protocol because this function can be called before
@@ -812,12 +814,9 @@ static void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
 			 paddr, GHCB_MSR_PSC_RESP_VAL(val)))
 			goto e_term;
 
-		if (op == SNP_PAGE_STATE_PRIVATE) {
-			/* Page validation must be performed after changing to private */
-			ret = pvalidate(vaddr, RMP_PG_SIZE_4K, true);
-			if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret))
-				goto e_term;
-		}
+		/* Page validation must be performed after changing to private */
+		if (op == SNP_PAGE_STATE_PRIVATE)
+			pvalidate_4k_page(vaddr, paddr, true);
 
 		vaddr += PAGE_SIZE;
 		paddr += PAGE_SIZE;
-- 
2.42.0