Merge tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 confidential computing update from Borislav Petkov:

 - Add support for unaccepted memory as specified in the UEFI spec v2.9.

   The gist of it all is that Intel TDX and AMD SEV-SNP confidential
   computing guests define the notion of accepting memory before using
   it and thus preventing a whole set of attacks against such guests
   like memory replay and the like.

   There are a couple of strategies of how memory should be accepted -
   the current implementation does an on-demand way of accepting.

* tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  virt: sevguest: Add CONFIG_CRYPTO dependency
  x86/efi: Safely enable unaccepted memory in UEFI
  x86/sev: Add SNP-specific unaccepted memory support
  x86/sev: Use large PSC requests if applicable
  x86/sev: Allow for use of the early boot GHCB for PSC requests
  x86/sev: Put PSC struct on the stack in prep for unaccepted memory support
  x86/sev: Fix calculation of end address based on number of pages
  x86/tdx: Add unaccepted memory support
  x86/tdx: Refactor try_accept_one()
  x86/tdx: Make _tdx_hypercall() and __tdx_module_call() available in boot stub
  efi/unaccepted: Avoid load_unaligned_zeropad() stepping into unaccepted memory
  efi: Add unaccepted memory support
  x86/boot/compressed: Handle unaccepted memory
  efi/libstub: Implement support for unaccepted memory
  efi/x86: Get full memory map in allocate_e820()
  mm: Add support for unaccepted memory

2 files changed, 211 insertions, 148 deletions

diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 3a5b0c9c4fcc..2eabccde94fb 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -12,6 +12,9 @@
 #ifndef __BOOT_COMPRESSED
 #define error(v)	pr_err(v)
 #define has_cpuflag(f)	boot_cpu_has(f)
+#else
+#undef WARN
+#define WARN(condition, format...) (!!(condition))
 #endif
 
 /* I/O parameters for CPUID-related helpers */
@@ -991,3 +994,103 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
 			cpuid_ext_range_max = fn->eax;
 	}
 }
+
+static void pvalidate_pages(struct snp_psc_desc *desc)
+{
+	struct psc_entry *e;
+	unsigned long vaddr;
+	unsigned int size;
+	unsigned int i;
+	bool validate;
+	int rc;
+
+	for (i = 0; i <= desc->hdr.end_entry; i++) {
+		e = &desc->entries[i];
+
+		vaddr = (unsigned long)pfn_to_kaddr(e->gfn);
+		size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+		validate = e->operation == SNP_PAGE_STATE_PRIVATE;
+
+		rc = pvalidate(vaddr, size, validate);
+		if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
+			unsigned long vaddr_end = vaddr + PMD_SIZE;
+
+			for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) {
+				rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+				if (rc)
+					break;
+			}
+		}
+
+		if (rc) {
+			WARN(1, "Failed to validate address 0x%lx ret %d", vaddr, rc);
+			sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+		}
+	}
+}
+
+static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
+{
+	int cur_entry, end_entry, ret = 0;
+	struct snp_psc_desc *data;
+	struct es_em_ctxt ctxt;
+
+	vc_ghcb_invalidate(ghcb);
+
+	/* Copy the input desc into GHCB shared buffer */
+	data = (struct snp_psc_desc *)ghcb->shared_buffer;
+	memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
+
+	/*
+	 * As per the GHCB specification, the hypervisor can resume the guest
+	 * before processing all the entries. Check whether all the entries
+	 * are processed. If not, then keep retrying. Note, the hypervisor
+	 * will update the data memory directly to indicate the status, so
+	 * reference the data->hdr everywhere.
+	 *
+	 * The strategy here is to wait for the hypervisor to change the page
+	 * state in the RMP table before guest accesses the memory pages. If the
+	 * page state change was not successful, then later memory access will
+	 * result in a crash.
+	 */
+	cur_entry = data->hdr.cur_entry;
+	end_entry = data->hdr.end_entry;
+
+	while (data->hdr.cur_entry <= data->hdr.end_entry) {
+		ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
+
+		/* This will advance the shared buffer data points to. */
+		ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
+
+		/*
+		 * Page State Change VMGEXIT can pass error code through
+		 * exit_info_2.
+		 */
+		if (WARN(ret || ghcb->save.sw_exit_info_2,
+			 "SNP: PSC failed ret=%d exit_info_2=%llx\n",
+			 ret, ghcb->save.sw_exit_info_2)) {
+			ret = 1;
+			goto out;
+		}
+
+		/* Verify that reserved bit is not set */
+		if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
+			ret = 1;
+			goto out;
+		}
+
+		/*
+		 * Sanity check that entry processing is not going backwards.
+		 * This will happen only if hypervisor is tricking us.
+		 */
+		if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
+"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
+			 end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
+			ret = 1;
+			goto out;
+		}
+	}
+
+out:
+	return ret;
+}
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index d095a5d3c14a..a0af3908ed49 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -119,7 +119,19 @@ static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
 
 struct sev_config {
 	__u64 debug		: 1,
-	      __reserved	: 63;
+
+	      /*
+	       * A flag used by __set_pages_state() that indicates when the
+	       * per-CPU GHCB has been created and registered and thus can be
+	       * used by the BSP instead of the early boot GHCB.
+	       *
+	       * For APs, the per-CPU GHCB is created before they are started
+	       * and registered upon startup, so this flag can be used globally
+	       * for the BSP and APs.
+	       */
+	      ghcbs_initialized	: 1,
+
+	      __reserved	: 62;
 };
 
 static struct sev_config sev_cfg __read_mostly;
@@ -645,32 +657,26 @@ static u64 __init get_jump_table_addr(void)
 	return ret;
 }
 
-static void pvalidate_pages(unsigned long vaddr, unsigned int npages, bool validate)
-{
-	unsigned long vaddr_end;
-	int rc;
-
-	vaddr = vaddr & PAGE_MASK;
-	vaddr_end = vaddr + (npages << PAGE_SHIFT);
-
-	while (vaddr < vaddr_end) {
-		rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
-		if (WARN(rc, "Failed to validate address 0x%lx ret %d", vaddr, rc))
-			sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
-
-		vaddr = vaddr + PAGE_SIZE;
-	}
-}
-
-static void __init early_set_pages_state(unsigned long paddr, unsigned int npages, enum psc_op op)
+static void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+				  unsigned long npages, enum psc_op op)
 {
 	unsigned long paddr_end;
 	u64 val;
+	int ret;
+
+	vaddr = vaddr & PAGE_MASK;
 
 	paddr = paddr & PAGE_MASK;
 	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;
+		}
+
 		/*
 		 * Use the MSR protocol because this function can be called before
 		 * the GHCB is established.
@@ -691,7 +697,15 @@ static void __init early_set_pages_state(unsigned long paddr, unsigned int npage
 			 paddr, GHCB_MSR_PSC_RESP_VAL(val)))
 			goto e_term;
 
-		paddr = paddr + PAGE_SIZE;
+		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;
+		}
+
+		vaddr += PAGE_SIZE;
+		paddr += PAGE_SIZE;
 	}
 
 	return;
@@ -701,7 +715,7 @@ e_term:
 }
 
 void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
-					 unsigned int npages)
+					 unsigned long npages)
 {
 	/*
 	 * This can be invoked in early boot while running identity mapped, so
@@ -716,14 +730,11 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd
 	  * Ask the hypervisor to mark the memory pages as private in the RMP
 	  * table.
 	  */
-	early_set_pages_state(paddr, npages, SNP_PAGE_STATE_PRIVATE);
-
-	/* Validate the memory pages after they've been added in the RMP table. */
-	pvalidate_pages(vaddr, npages, true);
+	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
 }
 
 void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
-					unsigned int npages)
+					unsigned long npages)
 {
 	/*
 	 * This can be invoked in early boot while running identity mapped, so
@@ -734,11 +745,8 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr
 	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
 		return;
 
-	/* Invalidate the memory pages before they are marked shared in the RMP table. */
-	pvalidate_pages(vaddr, npages, false);
-
 	 /* Ask hypervisor to mark the memory pages shared in the RMP table. */
-	early_set_pages_state(paddr, npages, SNP_PAGE_STATE_SHARED);
+	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
 }
 
 void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op)
@@ -756,96 +764,16 @@ void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op
 		WARN(1, "invalid memory op %d\n", op);
 }
 
-static int vmgexit_psc(struct snp_psc_desc *desc)
+static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
+				       unsigned long vaddr_end, int op)
 {
-	int cur_entry, end_entry, ret = 0;
-	struct snp_psc_desc *data;
 	struct ghcb_state state;
-	struct es_em_ctxt ctxt;
-	unsigned long flags;
-	struct ghcb *ghcb;
-
-	/*
-	 * __sev_get_ghcb() needs to run with IRQs disabled because it is using
-	 * a per-CPU GHCB.
-	 */
-	local_irq_save(flags);
-
-	ghcb = __sev_get_ghcb(&state);
-	if (!ghcb) {
-		ret = 1;
-		goto out_unlock;
-	}
-
-	/* Copy the input desc into GHCB shared buffer */
-	data = (struct snp_psc_desc *)ghcb->shared_buffer;
-	memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
-
-	/*
-	 * As per the GHCB specification, the hypervisor can resume the guest
-	 * before processing all the entries. Check whether all the entries
-	 * are processed. If not, then keep retrying. Note, the hypervisor
-	 * will update the data memory directly to indicate the status, so
-	 * reference the data->hdr everywhere.
-	 *
-	 * The strategy here is to wait for the hypervisor to change the page
-	 * state in the RMP table before guest accesses the memory pages. If the
-	 * page state change was not successful, then later memory access will
-	 * result in a crash.
-	 */
-	cur_entry = data->hdr.cur_entry;
-	end_entry = data->hdr.end_entry;
-
-	while (data->hdr.cur_entry <= data->hdr.end_entry) {
-		ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
-
-		/* This will advance the shared buffer data points to. */
-		ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
-
-		/*
-		 * Page State Change VMGEXIT can pass error code through
-		 * exit_info_2.
-		 */
-		if (WARN(ret || ghcb->save.sw_exit_info_2,
-			 "SNP: PSC failed ret=%d exit_info_2=%llx\n",
-			 ret, ghcb->save.sw_exit_info_2)) {
-			ret = 1;
-			goto out;
-		}
-
-		/* Verify that reserved bit is not set */
-		if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
-			ret = 1;
-			goto out;
-		}
-
-		/*
-		 * Sanity check that entry processing is not going backwards.
-		 * This will happen only if hypervisor is tricking us.
-		 */
-		if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
-"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
-			 end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
-			ret = 1;
-			goto out;
-		}
-	}
-
-out:
-	__sev_put_ghcb(&state);
-
-out_unlock:
-	local_irq_restore(flags);
-
-	return ret;
-}
-
-static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
-			      unsigned long vaddr_end, int op)
-{
+	bool use_large_entry;
 	struct psc_hdr *hdr;
 	struct psc_entry *e;
+	unsigned long flags;
 	unsigned long pfn;
+	struct ghcb *ghcb;
 	int i;
 
 	hdr = &data->hdr;
@@ -854,74 +782,104 @@ static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
 	memset(data, 0, sizeof(*data));
 	i = 0;
 
-	while (vaddr < vaddr_end) {
-		if (is_vmalloc_addr((void *)vaddr))
+	while (vaddr < vaddr_end && i < ARRAY_SIZE(data->entries)) {
+		hdr->end_entry = i;
+
+		if (is_vmalloc_addr((void *)vaddr)) {
 			pfn = vmalloc_to_pfn((void *)vaddr);
-		else
+			use_large_entry = false;
+		} else {
 			pfn = __pa(vaddr) >> PAGE_SHIFT;
+			use_large_entry = true;
+		}
 
 		e->gfn = pfn;
 		e->operation = op;
-		hdr->end_entry = i;
 
-		/*
-		 * Current SNP implementation doesn't keep track of the RMP page
-		 * size so use 4K for simplicity.
-		 */
-		e->pagesize = RMP_PG_SIZE_4K;
+		if (use_large_entry && IS_ALIGNED(vaddr, PMD_SIZE) &&
+		    (vaddr_end - vaddr) >= PMD_SIZE) {
+			e->pagesize = RMP_PG_SIZE_2M;
+			vaddr += PMD_SIZE;
+		} else {
+			e->pagesize = RMP_PG_SIZE_4K;
+			vaddr += PAGE_SIZE;
+		}
 
-		vaddr = vaddr + PAGE_SIZE;
 		e++;
 		i++;
 	}
 
-	if (vmgexit_psc(data))
+	/* Page validation must be rescinded before changing to shared */
+	if (op == SNP_PAGE_STATE_SHARED)
+		pvalidate_pages(data);
+
+	local_irq_save(flags);
+
+	if (sev_cfg.ghcbs_initialized)
+		ghcb = __sev_get_ghcb(&state);
+	else
+		ghcb = boot_ghcb;
+
+	/* Invoke the hypervisor to perform the page state changes */
+	if (!ghcb || vmgexit_psc(ghcb, data))
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+
+	if (sev_cfg.ghcbs_initialized)
+		__sev_put_ghcb(&state);
+
+	local_irq_restore(flags);
+
+	/* Page validation must be performed after changing to private */
+	if (op == SNP_PAGE_STATE_PRIVATE)
+		pvalidate_pages(data);
+
+	return vaddr;
 }
 
-static void set_pages_state(unsigned long vaddr, unsigned int npages, int op)
+static void set_pages_state(unsigned long vaddr, unsigned long npages, int op)
 {
-	unsigned long vaddr_end, next_vaddr;
-	struct snp_psc_desc *desc;
+	struct snp_psc_desc desc;
+	unsigned long vaddr_end;
 
-	desc = kmalloc(sizeof(*desc), GFP_KERNEL_ACCOUNT);
-	if (!desc)
-		panic("SNP: failed to allocate memory for PSC descriptor\n");
+	/* Use the MSR protocol when a GHCB is not available. */
+	if (!boot_ghcb)
+		return early_set_pages_state(vaddr, __pa(vaddr), npages, op);
 
 	vaddr = vaddr & PAGE_MASK;
 	vaddr_end = vaddr + (npages << PAGE_SHIFT);
 
-	while (vaddr < vaddr_end) {
-		/* Calculate the last vaddr that fits in one struct snp_psc_desc. */
-		next_vaddr = min_t(unsigned long, vaddr_end,
-				   (VMGEXIT_PSC_MAX_ENTRY * PAGE_SIZE) + vaddr);
-
-		__set_pages_state(desc, vaddr, next_vaddr, op);
-
-		vaddr = next_vaddr;
-	}
-
-	kfree(desc);
+	while (vaddr < vaddr_end)
+		vaddr = __set_pages_state(&desc, vaddr, vaddr_end, op);
 }
 
-void snp_set_memory_shared(unsigned long vaddr, unsigned int npages)
+void snp_set_memory_shared(unsigned long vaddr, unsigned long npages)
 {
 	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
 		return;
 
-	pvalidate_pages(vaddr, npages, false);
-
 	set_pages_state(vaddr, npages, SNP_PAGE_STATE_SHARED);
 }
 
-void snp_set_memory_private(unsigned long vaddr, unsigned int npages)
+void snp_set_memory_private(unsigned long vaddr, unsigned long npages)
 {
 	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
 		return;
 
 	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
+}
+
+void snp_accept_memory(phys_addr_t start, phys_addr_t end)
+{
+	unsigned long vaddr;
+	unsigned int npages;
 
-	pvalidate_pages(vaddr, npages, true);
+	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		return;
+
+	vaddr = (unsigned long)__va(start);
+	npages = (end - start) >> PAGE_SHIFT;
+
+	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
 }
 
 static int snp_set_vmsa(void *va, bool vmsa)
@@ -1267,6 +1225,8 @@ void setup_ghcb(void)
 		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
 			snp_register_per_cpu_ghcb();
 
+		sev_cfg.ghcbs_initialized = true;
+
 		return;
 	}