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

arch/x86/Kconfig

@@ -887,9 +887,11 @@ config INTEL_TDX_GUEST
 	bool "Intel TDX (Trust Domain Extensions) - Guest Support"
 	depends on X86_64 && CPU_SUP_INTEL
 	depends on X86_X2APIC
+	depends on EFI_STUB
 	select ARCH_HAS_CC_PLATFORM
 	select X86_MEM_ENCRYPT
 	select X86_MCE
+	select UNACCEPTED_MEMORY
 	help
 	  Support running as a guest under Intel TDX.  Without this support,
 	  the guest kernel can not boot or run under TDX.
@@ -1544,11 +1546,13 @@ config X86_MEM_ENCRYPT
 config AMD_MEM_ENCRYPT
 	bool "AMD Secure Memory Encryption (SME) support"
 	depends on X86_64 && CPU_SUP_AMD
+	depends on EFI_STUB
 	select DMA_COHERENT_POOL
 	select ARCH_USE_MEMREMAP_PROT
 	select INSTRUCTION_DECODER
 	select ARCH_HAS_CC_PLATFORM
 	select X86_MEM_ENCRYPT
+	select UNACCEPTED_MEMORY
 	help
 	  Say yes to enable support for the encryption of system memory.
 	  This requires an AMD processor that supports Secure Memory

arch/x86/boot/compressed/Makefile

@@ -106,7 +106,8 @@ ifdef CONFIG_X86_64
 endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
-vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o
+vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o $(obj)/tdx-shared.o
+vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o
 
 vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o

arch/x86/boot/compressed/efi.h

@@ -16,6 +16,7 @@ typedef guid_t efi_guid_t __aligned(__alignof__(u32));
 #define ACPI_TABLE_GUID				EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3,  0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 #define ACPI_20_TABLE_GUID			EFI_GUID(0x8868e871, 0xe4f1, 0x11d3,  0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81)
 #define EFI_CC_BLOB_GUID			EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42)
+#define LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID	EFI_GUID(0xd5d1de3c, 0x105c, 0x44f9,  0x9e, 0xa9, 0xbc, 0xef, 0x98, 0x12, 0x00, 0x31)
 
 #define EFI32_LOADER_SIGNATURE	"EL32"
 #define EFI64_LOADER_SIGNATURE	"EL64"
@@ -32,6 +33,7 @@ typedef	struct {
 } efi_table_hdr_t;
 
 #define EFI_CONVENTIONAL_MEMORY		 7
+#define EFI_UNACCEPTED_MEMORY		15
 
 #define EFI_MEMORY_MORE_RELIABLE \
 				((u64)0x0000000000010000ULL)	/* higher reliability */
@@ -104,6 +106,14 @@ struct efi_setup_data {
 	u64 reserved[8];
 };
 
+struct efi_unaccepted_memory {
+	u32 version;
+	u32 unit_size;
+	u64 phys_base;
+	u64 size;
+	unsigned long bitmap[];
+};
+
 static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right)
 {
 	return memcmp(&left, &right, sizeof (efi_guid_t));

arch/x86/boot/compressed/error.c

@@ -22,3 +22,22 @@ void error(char *m)
 	while (1)
 		asm("hlt");
 }
+
+/* EFI libstub  provides vsnprintf() */
+#ifdef CONFIG_EFI_STUB
+void panic(const char *fmt, ...)
+{
+	static char buf[1024];
+	va_list args;
+	int len;
+
+	va_start(args, fmt);
+	len = vsnprintf(buf, sizeof(buf), fmt, args);
+	va_end(args);
+
+	if (len && buf[len - 1] == '\n')
+		buf[len - 1] = '\0';
+
+	error(buf);
+}
+#endif

arch/x86/boot/compressed/error.h

@@ -6,5 +6,6 @@
 
 void warn(char *m);
 void error(char *m) __noreturn;
+void panic(const char *fmt, ...) __noreturn __cold;
 
 #endif /* BOOT_COMPRESSED_ERROR_H */

arch/x86/boot/compressed/kaslr.c

@@ -672,6 +672,33 @@ static bool process_mem_region(struct mem_vector *region,
 }
 
 #ifdef CONFIG_EFI
+
+/*
+ * Only EFI_CONVENTIONAL_MEMORY and EFI_UNACCEPTED_MEMORY (if supported) are
+ * guaranteed to be free.
+ *
+ * Pick free memory more conservatively than the EFI spec allows: according to
+ * the spec, EFI_BOOT_SERVICES_{CODE|DATA} are also free memory and thus
+ * available to place the kernel image into, but in practice there's firmware
+ * where using that memory leads to crashes. Buggy vendor EFI code registers
+ * for an event that triggers on SetVirtualAddressMap(). The handler assumes
+ * that EFI_BOOT_SERVICES_DATA memory has not been touched by loader yet, which
+ * is probably true for Windows.
+ *
+ * Preserve EFI_BOOT_SERVICES_* regions until after SetVirtualAddressMap().
+ */
+static inline bool memory_type_is_free(efi_memory_desc_t *md)
+{
+	if (md->type == EFI_CONVENTIONAL_MEMORY)
+		return true;
+
+	if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) &&
+	    md->type == EFI_UNACCEPTED_MEMORY)
+		    return true;
+
+	return false;
+}
+
 /*
  * Returns true if we processed the EFI memmap, which we prefer over the E820
  * table if it is available.
@@ -716,18 +743,7 @@ process_efi_entries(unsigned long minimum, unsigned long image_size)
 	for (i = 0; i < nr_desc; i++) {
 		md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i);
 
-		/*
-		 * Here we are more conservative in picking free memory than
-		 * the EFI spec allows:
-		 *
-		 * According to the spec, EFI_BOOT_SERVICES_{CODE|DATA} are also
-		 * free memory and thus available to place the kernel image into,
-		 * but in practice there's firmware where using that memory leads
-		 * to crashes.
-		 *
-		 * Only EFI_CONVENTIONAL_MEMORY is guaranteed to be free.
-		 */
-		if (md->type != EFI_CONVENTIONAL_MEMORY)
+		if (!memory_type_is_free(md))
 			continue;
 
 		if (efi_soft_reserve_enabled() &&

arch/x86/boot/compressed/mem.c

+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "error.h"
+#include "misc.h"
+#include "tdx.h"
+#include "sev.h"
+#include <asm/shared/tdx.h>
+
+/*
+ * accept_memory() and process_unaccepted_memory() called from EFI stub which
+ * runs before decompresser and its early_tdx_detect().
+ *
+ * Enumerate TDX directly from the early users.
+ */
+static bool early_is_tdx_guest(void)
+{
+	static bool once;
+	static bool is_tdx;
+
+	if (!IS_ENABLED(CONFIG_INTEL_TDX_GUEST))
+		return false;
+
+	if (!once) {
+		u32 eax, sig[3];
+
+		cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax,
+			    &sig[0], &sig[2],  &sig[1]);
+		is_tdx = !memcmp(TDX_IDENT, sig, sizeof(sig));
+		once = true;
+	}
+
+	return is_tdx;
+}
+
+void arch_accept_memory(phys_addr_t start, phys_addr_t end)
+{
+	/* Platform-specific memory-acceptance call goes here */
+	if (early_is_tdx_guest()) {
+		if (!tdx_accept_memory(start, end))
+			panic("TDX: Failed to accept memory\n");
+	} else if (sev_snp_enabled()) {
+		snp_accept_memory(start, end);
+	} else {
+		error("Cannot accept memory: unknown platform\n");
+	}
+}
+
+bool init_unaccepted_memory(void)
+{
+	guid_t guid = LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID;
+	struct efi_unaccepted_memory *table;
+	unsigned long cfg_table_pa;
+	unsigned int cfg_table_len;
+	enum efi_type et;
+	int ret;
+
+	et = efi_get_type(boot_params);
+	if (et == EFI_TYPE_NONE)
+		return false;
+
+	ret = efi_get_conf_table(boot_params, &cfg_table_pa, &cfg_table_len);
+	if (ret) {
+		warn("EFI config table not found.");
+		return false;
+	}
+
+	table = (void *)efi_find_vendor_table(boot_params, cfg_table_pa,
+					      cfg_table_len, guid);
+	if (!table)
+		return false;
+
+	if (table->version != 1)
+		error("Unknown version of unaccepted memory table\n");
+
+	/*
+	 * In many cases unaccepted_table is already set by EFI stub, but it
+	 * has to be initialized again to cover cases when the table is not
+	 * allocated by EFI stub or EFI stub copied the kernel image with
+	 * efi_relocate_kernel() before the variable is set.
+	 *
+	 * It must be initialized before the first usage of accept_memory().
+	 */
+	unaccepted_table = table;
+
+	return true;
+}

arch/x86/boot/compressed/misc.c

@@ -455,6 +455,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 #endif
 
 	debug_putstr("\nDecompressing Linux... ");
+
+	if (init_unaccepted_memory()) {
+		debug_putstr("Accepting memory... ");
+		accept_memory(__pa(output), __pa(output) + needed_size);
+	}
+
 	__decompress(input_data, input_len, NULL, NULL, output, output_len,
 			NULL, error);
 	entry_offset = parse_elf(output);

arch/x86/boot/compressed/misc.h

@@ -247,4 +247,14 @@ static inline unsigned long efi_find_vendor_table(struct boot_params *bp,
 }
 #endif /* CONFIG_EFI */
 
+#ifdef CONFIG_UNACCEPTED_MEMORY
+bool init_unaccepted_memory(void);
+#else
+static inline bool init_unaccepted_memory(void) { return false; }
+#endif
+
+/* Defined in EFI stub */
+extern struct efi_unaccepted_memory *unaccepted_table;
+void accept_memory(phys_addr_t start, phys_addr_t end);
+
 #endif /* BOOT_COMPRESSED_MISC_H */

arch/x86/boot/compressed/sev.c

@@ -115,7 +115,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 /* Include code for early handlers */
 #include "../../kernel/sev-shared.c"
 
-static inline bool sev_snp_enabled(void)
+bool sev_snp_enabled(void)
 {
 	return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
 }
@@ -181,6 +181,58 @@ static bool early_setup_ghcb(void)
 	return true;
 }
 
+static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc,
+				       phys_addr_t pa, phys_addr_t pa_end)
+{
+	struct psc_hdr *hdr;
+	struct psc_entry *e;
+	unsigned int i;
+
+	hdr = &desc->hdr;
+	memset(hdr, 0, sizeof(*hdr));
+
+	e = desc->entries;
+
+	i = 0;
+	while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) {
+		hdr->end_entry = i;
+
+		e->gfn = pa >> PAGE_SHIFT;
+		e->operation = SNP_PAGE_STATE_PRIVATE;
+		if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) {
+			e->pagesize = RMP_PG_SIZE_2M;
+			pa += PMD_SIZE;
+		} else {
+			e->pagesize = RMP_PG_SIZE_4K;
+			pa += PAGE_SIZE;
+		}
+
+		e++;
+		i++;
+	}
+
+	if (vmgexit_psc(boot_ghcb, desc))
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+
+	pvalidate_pages(desc);
+
+	return pa;
+}
+
+void snp_accept_memory(phys_addr_t start, phys_addr_t end)
+{
+	struct snp_psc_desc desc = {};
+	unsigned int i;
+	phys_addr_t pa;
+
+	if (!boot_ghcb && !early_setup_ghcb())
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+
+	pa = start;
+	while (pa < end)
+		pa = __snp_accept_memory(&desc, pa, end);
+}
+
 void sev_es_shutdown_ghcb(void)
 {
 	if (!boot_ghcb)

arch/x86/boot/compressed/sev.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD SEV header for early boot related functions.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ */
+
+#ifndef BOOT_COMPRESSED_SEV_H
+#define BOOT_COMPRESSED_SEV_H
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+
+bool sev_snp_enabled(void);
+void snp_accept_memory(phys_addr_t start, phys_addr_t end);
+
+#else
+
+static inline bool sev_snp_enabled(void) { return false; }
+static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
+
+#endif
+
+#endif

arch/x86/boot/compressed/tdx-shared.c

+#include "error.h"
+#include "../../coco/tdx/tdx-shared.c"

arch/x86/coco/tdx/Makefile

 # SPDX-License-Identifier: GPL-2.0
 
-obj-y += tdx.o tdcall.o
+obj-y += tdx.o tdx-shared.o tdcall.o

arch/x86/coco/tdx/tdx-shared.c

+#include <asm/tdx.h>
+#include <asm/pgtable.h>
+
+static unsigned long try_accept_one(phys_addr_t start, unsigned long len,
+				    enum pg_level pg_level)
+{
+	unsigned long accept_size = page_level_size(pg_level);
+	u64 tdcall_rcx;
+	u8 page_size;
+
+	if (!IS_ALIGNED(start, accept_size))
+		return 0;
+
+	if (len < accept_size)
+		return 0;
+
+	/*
+	 * Pass the page physical address to the TDX module to accept the
+	 * pending, private page.
+	 *
+	 * Bits 2:0 of RCX encode page size: 0 - 4K, 1 - 2M, 2 - 1G.
+	 */
+	switch (pg_level) {
+	case PG_LEVEL_4K:
+		page_size = 0;
+		break;
+	case PG_LEVEL_2M:
+		page_size = 1;
+		break;
+	case PG_LEVEL_1G:
+		page_size = 2;
+		break;
+	default:
+		return 0;
+	}
+
+	tdcall_rcx = start | page_size;
+	if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL))
+		return 0;
+
+	return accept_size;
+}
+
+bool tdx_accept_memory(phys_addr_t start, phys_addr_t end)
+{
+	/*
+	 * For shared->private conversion, accept the page using
+	 * TDX_ACCEPT_PAGE TDX module call.
+	 */
+	while (start < end) {
+		unsigned long len = end - start;
+		unsigned long accept_size;
+
+		/*
+		 * Try larger accepts first. It gives chance to VMM to keep
+		 * 1G/2M Secure EPT entries where possible and speeds up
+		 * process by cutting number of hypercalls (if successful).
+		 */
+
+		accept_size = try_accept_one(start, len, PG_LEVEL_1G);
+		if (!accept_size)
+			accept_size = try_accept_one(start, len, PG_LEVEL_2M);
+		if (!accept_size)
+			accept_size = try_accept_one(start, len, PG_LEVEL_4K);
+		if (!accept_size)
+			return false;
+		start += accept_size;
+	}
+
+	return true;
+}

arch/x86/coco/tdx/tdx.c

@@ -14,20 +14,6 @@
 #include <asm/insn-eval.h>
 #include <asm/pgtable.h>
 
-/* TDX module Call Leaf IDs */
-#define TDX_GET_INFO			1
-#define TDX_GET_VEINFO			3
-#define TDX_GET_REPORT			4
-#define TDX_ACCEPT_PAGE			6
-#define TDX_WR				8
-
-/* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */
-#define TDCS_NOTIFY_ENABLES		0x9100000000000010
-
-/* TDX hypercall Leaf IDs */
-#define TDVMCALL_MAP_GPA		0x10001
-#define TDVMCALL_REPORT_FATAL_ERROR	0x10003
-
 /* MMIO direction */
 #define EPT_READ	0
 #define EPT_WRITE	1
@@ -51,24 +37,6 @@
 
 #define TDREPORT_SUBTYPE_0	0
 
-/*
- * Wrapper for standard use of __tdx_hypercall with no output aside from
- * return code.
- */
-static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15)
-{
-	struct tdx_hypercall_args args = {
-		.r10 = TDX_HYPERCALL_STANDARD,
-		.r11 = fn,
-		.r12 = r12,
-		.r13 = r13,
-		.r14 = r14,
-		.r15 = r15,
-	};
-
-	return __tdx_hypercall(&args);
-}
-
 /* Called from __tdx_hypercall() for unrecoverable failure */
 noinstr void __tdx_hypercall_failed(void)
 {
@@ -745,47 +713,6 @@ static bool tdx_cache_flush_required(void)
 	return true;
 }
 
-static bool try_accept_one(phys_addr_t *start, unsigned long len,
-			  enum pg_level pg_level)
-{
-	unsigned long accept_size = page_level_size(pg_level);
-	u64 tdcall_rcx;
-	u8 page_size;
-
-	if (!IS_ALIGNED(*start, accept_size))
-		return false;
-
-	if (len < accept_size)
-		return false;
-
-	/*
-	 * Pass the page physical address to the TDX module to accept the
-	 * pending, private page.
-	 *
-	 * Bits 2:0 of RCX encode page size: 0 - 4K, 1 - 2M, 2 - 1G.
-	 */
-	switch (pg_level) {
-	case PG_LEVEL_4K:
-		page_size = 0;
-		break;
-	case PG_LEVEL_2M:
-		page_size = 1;
-		break;
-	case PG_LEVEL_1G:
-		page_size = 2;
-		break;
-	default:
-		return false;
-	}
-
-	tdcall_rcx = *start | page_size;
-	if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL))
-		return false;
-
-	*start += accept_size;
-	return true;
-}
-
 /*
  * Inform the VMM of the guest's intent for this physical page: shared with
  * the VMM or private to the guest.  The VMM is expected to change its mapping
@@ -810,32 +737,9 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
 	if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0))
 		return false;
 
-	/* private->shared conversion  requires only MapGPA call */
-	if (!enc)
-		return true;
-
-	/*
-	 * For shared->private conversion, accept the page using
-	 * TDX_ACCEPT_PAGE TDX module call.
-	 */
-	while (start < end) {
-		unsigned long len = end - start;
-
-		/*
-		 * Try larger accepts first. It gives chance to VMM to keep
-		 * 1G/2M SEPT entries where possible and speeds up process by
-		 * cutting number of hypercalls (if successful).
-		 */
-
-		if (try_accept_one(&start, len, PG_LEVEL_1G))
-			continue;
-
-		if (try_accept_one(&start, len, PG_LEVEL_2M))
-			continue;
-
-		if (!try_accept_one(&start, len, PG_LEVEL_4K))
-			return false;
-	}
+	/* shared->private conversion requires memory to be accepted before use */
+	if (enc)
+		return tdx_accept_memory(start, end);
 
 	return true;
 }

arch/x86/include/asm/efi.h

@@ -31,6 +31,8 @@ extern unsigned long efi_mixed_mode_stack_pa;
 
 #define ARCH_EFI_IRQ_FLAGS_MASK	X86_EFLAGS_IF
 
+#define EFI_UNACCEPTED_UNIT_SIZE PMD_SIZE
+
 /*
  * The EFI services are called through variadic functions in many cases. These
  * functions are implemented in assembler and support only a fixed number of

arch/x86/include/asm/sev-common.h

@@ -106,8 +106,13 @@ enum psc_op {
 #define GHCB_HV_FT_SNP			BIT_ULL(0)
 #define GHCB_HV_FT_SNP_AP_CREATION	BIT_ULL(1)
 
-/* SNP Page State Change NAE event */
-#define VMGEXIT_PSC_MAX_ENTRY		253
+/*
+ * SNP Page State Change NAE event
+ *   The VMGEXIT_PSC_MAX_ENTRY determines the size of the PSC structure, which
+ *   is a local stack variable in set_pages_state(). Do not increase this value
+ *   without evaluating the impact to stack usage.
+ */
+#define VMGEXIT_PSC_MAX_ENTRY		64
 
 struct psc_hdr {
 	u16 cur_entry;

arch/x86/include/asm/sev.h

@@ -80,11 +80,15 @@ extern void vc_no_ghcb(void);
 extern void vc_boot_ghcb(void);
 extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 
+/* PVALIDATE return codes */
+#define PVALIDATE_FAIL_SIZEMISMATCH	6
+
 /* Software defined (when rFlags.CF = 1) */
 #define PVALIDATE_FAIL_NOUPDATE		255
 
 /* RMP page size */
 #define RMP_PG_SIZE_4K			0
+#define RMP_PG_SIZE_2M			1
 
 #define RMPADJUST_VMSA_PAGE_BIT		BIT(16)
 
@@ -192,16 +196,17 @@ struct snp_guest_request_ioctl;
 
 void setup_ghcb(void);
 void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
-					 unsigned int npages);
+					 unsigned long npages);
 void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
-					unsigned int npages);
+					unsigned long npages);
 void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
-void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
-void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
+void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
+void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
 void snp_set_wakeup_secondary_cpu(void);
 bool snp_init(struct boot_params *bp);
 void __init __noreturn snp_abort(void);
 int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
+void snp_accept_memory(phys_addr_t start, phys_addr_t end);
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
 static inline void sev_es_ist_exit(void) { }
@@ -212,12 +217,12 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
 static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; }
 static inline void setup_ghcb(void) { }
 static inline void __init
-early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned int npages) { }
+early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
 static inline void __init
-early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { }
+early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
 static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { }
-static inline void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) { }
-static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npages) { }
+static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { }
+static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { }
 static inline void snp_set_wakeup_secondary_cpu(void) { }
 static inline bool snp_init(struct boot_params *bp) { return false; }
 static inline void snp_abort(void) { }
@@ -225,6 +230,8 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
 {
 	return -ENOTTY;
 }
+
+static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
 #endif
 
 #endif

arch/x86/include/asm/shared/tdx.h

@@ -10,6 +10,20 @@
 #define TDX_CPUID_LEAF_ID	0x21
 #define TDX_IDENT		"IntelTDX    "
 
+/* TDX module Call Leaf IDs */
+#define TDX_GET_INFO			1
+#define TDX_GET_VEINFO			3
+#define TDX_GET_REPORT			4
+#define TDX_ACCEPT_PAGE			6
+#define TDX_WR				8
+
+/* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */
+#define TDCS_NOTIFY_ENABLES		0x9100000000000010
+
+/* TDX hypercall Leaf IDs */
+#define TDVMCALL_MAP_GPA		0x10001
+#define TDVMCALL_REPORT_FATAL_ERROR	0x10003
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -37,8 +51,47 @@ struct tdx_hypercall_args {
 u64 __tdx_hypercall(struct tdx_hypercall_args *args);
 u64 __tdx_hypercall_ret(struct tdx_hypercall_args *args);
 
+/*
+ * Wrapper for standard use of __tdx_hypercall with no output aside from
+ * return code.
+ */
+static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = fn,
+		.r12 = r12,
+		.r13 = r13,
+		.r14 = r14,
+		.r15 = r15,
+	};
+
+	return __tdx_hypercall(&args);
+}
+
+
 /* Called from __tdx_hypercall() for unrecoverable failure */
 void __tdx_hypercall_failed(void);
 
+/*
+ * Used in __tdx_module_call() to gather the output registers' values of the
+ * TDCALL instruction when requesting services from the TDX module. This is a
+ * software only structure and not part of the TDX module/VMM ABI
+ */
+struct tdx_module_output {
+	u64 rcx;
+	u64 rdx;
+	u64 r8;
+	u64 r9;
+	u64 r10;
+	u64 r11;
+};
+
+/* Used to communicate with the TDX module */
+u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
+		      struct tdx_module_output *out);
+
+bool tdx_accept_memory(phys_addr_t start, phys_addr_t end);
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_SHARED_TDX_H */

arch/x86/include/asm/tdx.h

@@ -5,6 +5,8 @@
 
 #include <linux/init.h>
 #include <linux/bits.h>
+
+#include <asm/errno.h>
 #include <asm/ptrace.h>
 #include <asm/shared/tdx.h>
 
@@ -20,21 +22,6 @@
 
 #ifndef __ASSEMBLY__
 
-/*
- * Used to gather the output registers values of the TDCALL and SEAMCALL
- * instructions when requesting services from the TDX module.
- *
- * This is a software only structure and not part of the TDX module/VMM ABI.
- */
-struct tdx_module_output {
-	u64 rcx;
-	u64 rdx;
-	u64 r8;
-	u64 r9;
-	u64 r10;
-	u64 r11;
-};
-
 /*
  * Used by the #VE exception handler to gather the #VE exception
  * info from the TDX module. This is a software only structure
@@ -55,10 +42,6 @@ struct ve_info {
 
 void __init tdx_early_init(void);
 
-/* Used to communicate with the TDX module */
-u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
-		      struct tdx_module_output *out);
-
 void tdx_get_ve_info(struct ve_info *ve);
 
 bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve);

arch/x86/include/asm/unaccepted_memory.h

+#ifndef _ASM_X86_UNACCEPTED_MEMORY_H
+#define _ASM_X86_UNACCEPTED_MEMORY_H
+
+#include <linux/efi.h>
+#include <asm/tdx.h>
+#include <asm/sev.h>
+
+static inline void arch_accept_memory(phys_addr_t start, phys_addr_t end)
+{
+	/* Platform-specific memory-acceptance call goes here */
+	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
+		if (!tdx_accept_memory(start, end))
+			panic("TDX: Failed to accept memory\n");
+	} else if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) {
+		snp_accept_memory(start, end);
+	} else {
+		panic("Cannot accept memory: unknown platform\n");
+	}
+}
+
+static inline struct efi_unaccepted_memory *efi_get_unaccepted_table(void)
+{
+	if (efi.unaccepted == EFI_INVALID_TABLE_ADDR)
+		return NULL;
+	return __va(efi.unaccepted);
+}
+#endif

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;
+}

arch/x86/platform/efi/efi.c

@@ -96,6 +96,9 @@ static const unsigned long * const efi_tables[] = {
 #ifdef CONFIG_EFI_COCO_SECRET
 	&efi.coco_secret,
 #endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	&efi.unaccepted,
+#endif
 };
 
 u64 efi_setup;		/* efi setup_data physical address */

drivers/base/node.c

@@ -448,6 +448,9 @@ static ssize_t node_read_meminfo(struct device *dev,
 			     "Node %d ShmemPmdMapped: %8lu kB\n"
 			     "Node %d FileHugePages: %8lu kB\n"
 			     "Node %d FilePmdMapped: %8lu kB\n"
+#endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+			     "Node %d Unaccepted:     %8lu kB\n"
 #endif
 			     ,
 			     nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
@@ -477,6 +480,10 @@ static ssize_t node_read_meminfo(struct device *dev,
 			     nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
 			     nid, K(node_page_state(pgdat, NR_FILE_THPS)),
 			     nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED))
+#endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+			     ,
+			     nid, K(sum_zone_node_page_state(nid, NR_UNACCEPTED))
 #endif
 			    );
 	len += hugetlb_report_node_meminfo(buf, len, nid);

drivers/firmware/efi/Kconfig

@@ -269,6 +269,20 @@ config EFI_COCO_SECRET
 	  virt/coco/efi_secret module to access the secrets, which in turn
 	  allows userspace programs to access the injected secrets.
 
+config UNACCEPTED_MEMORY
+	bool
+	depends on EFI_STUB
+	help
+	   Some Virtual Machine platforms, such as Intel TDX, require
+	   some memory to be "accepted" by the guest before it can be used.
+	   This mechanism helps prevent malicious hosts from making changes
+	   to guest memory.
+
+	   UEFI specification v2.9 introduced EFI_UNACCEPTED_MEMORY memory type.
+
+	   This option adds support for unaccepted memory and makes such memory
+	   usable by the kernel.
+
 config EFI_EMBEDDED_FIRMWARE
 	bool
 	select CRYPTO_LIB_SHA256

drivers/firmware/efi/Makefile

@@ -41,3 +41,4 @@ obj-$(CONFIG_EFI_CAPSULE_LOADER)	+= capsule-loader.o
 obj-$(CONFIG_EFI_EARLYCON)		+= earlycon.o
 obj-$(CONFIG_UEFI_CPER_ARM)		+= cper-arm.o
 obj-$(CONFIG_UEFI_CPER_X86)		+= cper-x86.o
+obj-$(CONFIG_UNACCEPTED_MEMORY)		+= unaccepted_memory.o

drivers/firmware/efi/efi.c

@@ -50,6 +50,9 @@ struct efi __read_mostly efi = {
 #ifdef CONFIG_EFI_COCO_SECRET
 	.coco_secret		= EFI_INVALID_TABLE_ADDR,
 #endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	.unaccepted		= EFI_INVALID_TABLE_ADDR,
+#endif
 };
 EXPORT_SYMBOL(efi);
 
@@ -584,6 +587,9 @@ static const efi_config_table_type_t common_tables[] __initconst = {
 #ifdef CONFIG_EFI_COCO_SECRET
 	{LINUX_EFI_COCO_SECRET_AREA_GUID,	&efi.coco_secret,	"CocoSecret"	},
 #endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	{LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID,	&efi.unaccepted,	"Unaccepted"	},
+#endif
 #ifdef CONFIG_EFI_GENERIC_STUB
 	{LINUX_EFI_SCREEN_INFO_TABLE_GUID,	&screen_info_table			},
 #endif
@@ -738,6 +744,25 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables,
 		}
 	}
 
+	if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) &&
+	    efi.unaccepted != EFI_INVALID_TABLE_ADDR) {
+		struct efi_unaccepted_memory *unaccepted;
+
+		unaccepted = early_memremap(efi.unaccepted, sizeof(*unaccepted));
+		if (unaccepted) {
+			unsigned long size;
+
+			if (unaccepted->version == 1) {
+				size = sizeof(*unaccepted) + unaccepted->size;
+				memblock_reserve(efi.unaccepted, size);
+			} else {
+				efi.unaccepted = EFI_INVALID_TABLE_ADDR;
+			}
+
+			early_memunmap(unaccepted, sizeof(*unaccepted));
+		}
+	}
+
 	return 0;
 }
 
@@ -822,6 +847,7 @@ static __initdata char memory_type_name[][13] = {
 	"MMIO Port",
 	"PAL Code",
 	"Persistent",
+	"Unaccepted",
 };
 
 char * __init efi_md_typeattr_format(char *buf, size_t size,

drivers/firmware/efi/libstub/Makefile

@@ -96,6 +96,8 @@ CFLAGS_arm32-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 zboot-obj-$(CONFIG_RISCV)	:= lib-clz_ctz.o lib-ashldi3.o
 lib-$(CONFIG_EFI_ZBOOT)		+= zboot.o $(zboot-obj-y)
 
+lib-$(CONFIG_UNACCEPTED_MEMORY) += unaccepted_memory.o bitmap.o find.o
+
 extra-y				:= $(lib-y)
 lib-y				:= $(patsubst %.o,%.stub.o,$(lib-y))
 

drivers/firmware/efi/libstub/bitmap.c

+#include <linux/bitmap.h>
+
+void __bitmap_set(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_set >= 0) {
+		*p |= mask_to_set;
+		len -= bits_to_set;
+		bits_to_set = BITS_PER_LONG;
+		mask_to_set = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+		*p |= mask_to_set;
+	}
+}
+
+void __bitmap_clear(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}

drivers/firmware/efi/libstub/efistub.h

@@ -1136,4 +1136,10 @@ void efi_remap_image(unsigned long image_base, unsigned alloc_size,
 asmlinkage efi_status_t __efiapi
 efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab);
 
+efi_status_t allocate_unaccepted_bitmap(__u32 nr_desc,
+					struct efi_boot_memmap *map);
+void process_unaccepted_memory(u64 start, u64 end);
+void accept_memory(phys_addr_t start, phys_addr_t end);
+void arch_accept_memory(phys_addr_t start, phys_addr_t end);
+
 #endif

drivers/firmware/efi/libstub/find.c

+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/bitmap.h>
+#include <linux/math.h>
+#include <linux/minmax.h>
+
+/*
+ * Common helper for find_next_bit() function family
+ * @FETCH: The expression that fetches and pre-processes each word of bitmap(s)
+ * @MUNGE: The expression that post-processes a word containing found bit (may be empty)
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ */
+#define FIND_NEXT_BIT(FETCH, MUNGE, size, start)				\
+({										\
+	unsigned long mask, idx, tmp, sz = (size), __start = (start);		\
+										\
+	if (unlikely(__start >= sz))						\
+		goto out;							\
+										\
+	mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start));				\
+	idx = __start / BITS_PER_LONG;						\
+										\
+	for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) {			\
+		if ((idx + 1) * BITS_PER_LONG >= sz)				\
+			goto out;						\
+		idx++;								\
+	}									\
+										\
+	sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz);			\
+out:										\
+	sz;									\
+})
+
+unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start)
+{
+	return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start);
+}
+
+unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
+					 unsigned long start)
+{
+	return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start);
+}

drivers/firmware/efi/libstub/unaccepted_memory.c

+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/efi.h>
+#include <asm/efi.h>
+#include "efistub.h"
+
+struct efi_unaccepted_memory *unaccepted_table;
+
+efi_status_t allocate_unaccepted_bitmap(__u32 nr_desc,
+					struct efi_boot_memmap *map)
+{
+	efi_guid_t unaccepted_table_guid = LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID;
+	u64 unaccepted_start = ULLONG_MAX, unaccepted_end = 0, bitmap_size;
+	efi_status_t status;
+	int i;
+
+	/* Check if the table is already installed */
+	unaccepted_table = get_efi_config_table(unaccepted_table_guid);
+	if (unaccepted_table) {
+		if (unaccepted_table->version != 1) {
+			efi_err("Unknown version of unaccepted memory table\n");
+			return EFI_UNSUPPORTED;
+		}
+		return EFI_SUCCESS;
+	}
+
+	/* Check if there's any unaccepted memory and find the max address */
+	for (i = 0; i < nr_desc; i++) {
+		efi_memory_desc_t *d;
+		unsigned long m = (unsigned long)map->map;
+
+		d = efi_early_memdesc_ptr(m, map->desc_size, i);
+		if (d->type != EFI_UNACCEPTED_MEMORY)
+			continue;
+
+		unaccepted_start = min(unaccepted_start, d->phys_addr);
+		unaccepted_end = max(unaccepted_end,
+				     d->phys_addr + d->num_pages * PAGE_SIZE);
+	}
+
+	if (unaccepted_start == ULLONG_MAX)
+		return EFI_SUCCESS;
+
+	unaccepted_start = round_down(unaccepted_start,
+				      EFI_UNACCEPTED_UNIT_SIZE);
+	unaccepted_end = round_up(unaccepted_end, EFI_UNACCEPTED_UNIT_SIZE);
+
+	/*
+	 * If unaccepted memory is present, allocate a bitmap to track what
+	 * memory has to be accepted before access.
+	 *
+	 * One bit in the bitmap represents 2MiB in the address space:
+	 * A 4k bitmap can track 64GiB of physical address space.
+	 *
+	 * In the worst case scenario -- a huge hole in the middle of the
+	 * address space -- It needs 256MiB to handle 4PiB of the address
+	 * space.
+	 *
+	 * The bitmap will be populated in setup_e820() according to the memory
+	 * map after efi_exit_boot_services().
+	 */
+	bitmap_size = DIV_ROUND_UP(unaccepted_end - unaccepted_start,
+				   EFI_UNACCEPTED_UNIT_SIZE * BITS_PER_BYTE);
+
+	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA,
+			     sizeof(*unaccepted_table) + bitmap_size,
+			     (void **)&unaccepted_table);
+	if (status != EFI_SUCCESS) {
+		efi_err("Failed to allocate unaccepted memory config table\n");
+		return status;
+	}
+
+	unaccepted_table->version = 1;
+	unaccepted_table->unit_size = EFI_UNACCEPTED_UNIT_SIZE;
+	unaccepted_table->phys_base = unaccepted_start;
+	unaccepted_table->size = bitmap_size;
+	memset(unaccepted_table->bitmap, 0, bitmap_size);
+
+	status = efi_bs_call(install_configuration_table,
+			     &unaccepted_table_guid, unaccepted_table);
+	if (status != EFI_SUCCESS) {
+		efi_bs_call(free_pool, unaccepted_table);
+		efi_err("Failed to install unaccepted memory config table!\n");
+	}
+
+	return status;
+}
+
+/*
+ * The accepted memory bitmap only works at unit_size granularity.  Take
+ * unaligned start/end addresses and either:
+ *  1. Accepts the memory immediately and in its entirety
+ *  2. Accepts unaligned parts, and marks *some* aligned part unaccepted
+ *
+ * The function will never reach the bitmap_set() with zero bits to set.
+ */
+void process_unaccepted_memory(u64 start, u64 end)
+{
+	u64 unit_size = unaccepted_table->unit_size;
+	u64 unit_mask = unaccepted_table->unit_size - 1;
+	u64 bitmap_size = unaccepted_table->size;
+
+	/*
+	 * Ensure that at least one bit will be set in the bitmap by
+	 * immediately accepting all regions under 2*unit_size.  This is
+	 * imprecise and may immediately accept some areas that could
+	 * have been represented in the bitmap.  But, results in simpler
+	 * code below
+	 *
+	 * Consider case like this (assuming unit_size == 2MB):
+	 *
+	 * | 4k | 2044k |    2048k   |
+	 * ^ 0x0        ^ 2MB        ^ 4MB
+	 *
+	 * Only the first 4k has been accepted. The 0MB->2MB region can not be
+	 * represented in the bitmap. The 2MB->4MB region can be represented in
+	 * the bitmap. But, the 0MB->4MB region is <2*unit_size and will be
+	 * immediately accepted in its entirety.
+	 */
+	if (end - start < 2 * unit_size) {
+		arch_accept_memory(start, end);
+		return;
+	}
+
+	/*
+	 * No matter how the start and end are aligned, at least one unaccepted
+	 * unit_size area will remain to be marked in the bitmap.
+	 */
+
+	/* Immediately accept a <unit_size piece at the start: */
+	if (start & unit_mask) {
+		arch_accept_memory(start, round_up(start, unit_size));
+		start = round_up(start, unit_size);
+	}
+
+	/* Immediately accept a <unit_size piece at the end: */
+	if (end & unit_mask) {
+		arch_accept_memory(round_down(end, unit_size), end);
+		end = round_down(end, unit_size);
+	}
+
+	/*
+	 * Accept part of the range that before phys_base and cannot be recorded
+	 * into the bitmap.
+	 */
+	if (start < unaccepted_table->phys_base) {
+		arch_accept_memory(start,
+				   min(unaccepted_table->phys_base, end));
+		start = unaccepted_table->phys_base;
+	}
+
+	/* Nothing to record */
+	if (end < unaccepted_table->phys_base)
+		return;
+
+	/* Translate to offsets from the beginning of the bitmap */
+	start -= unaccepted_table->phys_base;
+	end -= unaccepted_table->phys_base;
+
+	/* Accept memory that doesn't fit into bitmap */
+	if (end > bitmap_size * unit_size * BITS_PER_BYTE) {
+		unsigned long phys_start, phys_end;
+
+		phys_start = bitmap_size * unit_size * BITS_PER_BYTE +
+			     unaccepted_table->phys_base;
+		phys_end = end + unaccepted_table->phys_base;
+
+		arch_accept_memory(phys_start, phys_end);
+		end = bitmap_size * unit_size * BITS_PER_BYTE;
+	}
+
+	/*
+	 * 'start' and 'end' are now both unit_size-aligned.
+	 * Record the range as being unaccepted:
+	 */
+	bitmap_set(unaccepted_table->bitmap,
+		   start / unit_size, (end - start) / unit_size);
+}
+
+void accept_memory(phys_addr_t start, phys_addr_t end)
+{
+	unsigned long range_start, range_end;
+	unsigned long bitmap_size;
+	u64 unit_size;
+
+	if (!unaccepted_table)
+		return;
+
+	unit_size = unaccepted_table->unit_size;
+
+	/*
+	 * Only care for the part of the range that is represented
+	 * in the bitmap.
+	 */
+	if (start < unaccepted_table->phys_base)
+		start = unaccepted_table->phys_base;
+	if (end < unaccepted_table->phys_base)
+		return;
+
+	/* Translate to offsets from the beginning of the bitmap */
+	start -= unaccepted_table->phys_base;
+	end -= unaccepted_table->phys_base;
+
+	/* Make sure not to overrun the bitmap */
+	if (end > unaccepted_table->size * unit_size * BITS_PER_BYTE)
+		end = unaccepted_table->size * unit_size * BITS_PER_BYTE;
+
+	range_start = start / unit_size;
+	bitmap_size = DIV_ROUND_UP(end, unit_size);
+
+	for_each_set_bitrange_from(range_start, range_end,
+				   unaccepted_table->bitmap, bitmap_size) {
+		unsigned long phys_start, phys_end;
+
+		phys_start = range_start * unit_size + unaccepted_table->phys_base;
+		phys_end = range_end * unit_size + unaccepted_table->phys_base;
+
+		arch_accept_memory(phys_start, phys_end);
+		bitmap_clear(unaccepted_table->bitmap,
+			     range_start, range_end - range_start);
+	}
+}

drivers/firmware/efi/libstub/x86-stub.c

@@ -26,6 +26,17 @@ const efi_dxe_services_table_t *efi_dxe_table;
 u32 image_offset __section(".data");
 static efi_loaded_image_t *image = NULL;
 
+typedef union sev_memory_acceptance_protocol sev_memory_acceptance_protocol_t;
+union sev_memory_acceptance_protocol {
+	struct {
+		efi_status_t (__efiapi * allow_unaccepted_memory)(
+			sev_memory_acceptance_protocol_t *);
+	};
+	struct {
+		u32 allow_unaccepted_memory;
+	} mixed_mode;
+};
+
 static efi_status_t
 preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 {
@@ -310,6 +321,29 @@ setup_memory_protection(unsigned long image_base, unsigned long image_size)
 #endif
 }
 
+static void setup_unaccepted_memory(void)
+{
+	efi_guid_t mem_acceptance_proto = OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID;
+	sev_memory_acceptance_protocol_t *proto;
+	efi_status_t status;
+
+	if (!IS_ENABLED(CONFIG_UNACCEPTED_MEMORY))
+		return;
+
+	/*
+	 * Enable unaccepted memory before calling exit boot services in order
+	 * for the UEFI to not accept all memory on EBS.
+	 */
+	status = efi_bs_call(locate_protocol, &mem_acceptance_proto, NULL,
+			     (void **)&proto);
+	if (status != EFI_SUCCESS)
+		return;
+
+	status = efi_call_proto(proto, allow_unaccepted_memory);
+	if (status != EFI_SUCCESS)
+		efi_err("Memory acceptance protocol failed\n");
+}
+
 static const efi_char16_t apple[] = L"Apple";
 
 static void setup_quirks(struct boot_params *boot_params,
@@ -613,6 +647,16 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s
 			e820_type = E820_TYPE_PMEM;
 			break;
 
+		case EFI_UNACCEPTED_MEMORY:
+			if (!IS_ENABLED(CONFIG_UNACCEPTED_MEMORY)) {
+				efi_warn_once(
+"The system has unaccepted memory,  but kernel does not support it\nConsider enabling CONFIG_UNACCEPTED_MEMORY\n");
+				continue;
+			}
+			e820_type = E820_TYPE_RAM;
+			process_unaccepted_memory(d->phys_addr,
+						  d->phys_addr + PAGE_SIZE * d->num_pages);
+			break;
 		default:
 			continue;
 		}
@@ -681,28 +725,27 @@ static efi_status_t allocate_e820(struct boot_params *params,
 				  struct setup_data **e820ext,
 				  u32 *e820ext_size)
 {
-	unsigned long map_size, desc_size, map_key;
+	struct efi_boot_memmap *map;
 	efi_status_t status;
-	__u32 nr_desc, desc_version;
-
-	/* Only need the size of the mem map and size of each mem descriptor */
-	map_size = 0;
-	status = efi_bs_call(get_memory_map, &map_size, NULL, &map_key,
-			     &desc_size, &desc_version);
-	if (status != EFI_BUFFER_TOO_SMALL)
-		return (status != EFI_SUCCESS) ? status : EFI_UNSUPPORTED;
+	__u32 nr_desc;
 
-	nr_desc = map_size / desc_size + EFI_MMAP_NR_SLACK_SLOTS;
+	status = efi_get_memory_map(&map, false);
+	if (status != EFI_SUCCESS)
+		return status;
 
-	if (nr_desc > ARRAY_SIZE(params->e820_table)) {
-		u32 nr_e820ext = nr_desc - ARRAY_SIZE(params->e820_table);
+	nr_desc = map->map_size / map->desc_size;
+	if (nr_desc > ARRAY_SIZE(params->e820_table) - EFI_MMAP_NR_SLACK_SLOTS) {
+		u32 nr_e820ext = nr_desc - ARRAY_SIZE(params->e820_table) +
+				 EFI_MMAP_NR_SLACK_SLOTS;
 
 		status = alloc_e820ext(nr_e820ext, e820ext, e820ext_size);
-		if (status != EFI_SUCCESS)
-			return status;
 	}
 
-	return EFI_SUCCESS;
+	if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) && status == EFI_SUCCESS)
+		status = allocate_unaccepted_bitmap(nr_desc, map);
+
+	efi_bs_call(free_pool, map);
+	return status;
 }
 
 struct exit_boot_struct {
@@ -899,6 +942,8 @@ asmlinkage unsigned long efi_main(efi_handle_t handle,
 
 	setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start);
 
+	setup_unaccepted_memory();
+
 	status = exit_boot(boot_params, handle);
 	if (status != EFI_SUCCESS) {
 		efi_err("exit_boot() failed!\n");

drivers/firmware/efi/unaccepted_memory.c

+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/efi.h>
+#include <linux/memblock.h>
+#include <linux/spinlock.h>
+#include <asm/unaccepted_memory.h>
+
+/* Protects unaccepted memory bitmap */
+static DEFINE_SPINLOCK(unaccepted_memory_lock);
+
+/*
+ * accept_memory() -- Consult bitmap and accept the memory if needed.
+ *
+ * Only memory that is explicitly marked as unaccepted in the bitmap requires
+ * an action. All the remaining memory is implicitly accepted and doesn't need
+ * acceptance.
+ *
+ * No need to accept:
+ *  - anything if the system has no unaccepted table;
+ *  - memory that is below phys_base;
+ *  - memory that is above the memory that addressable by the bitmap;
+ */
+void accept_memory(phys_addr_t start, phys_addr_t end)
+{
+	struct efi_unaccepted_memory *unaccepted;
+	unsigned long range_start, range_end;
+	unsigned long flags;
+	u64 unit_size;
+
+	unaccepted = efi_get_unaccepted_table();
+	if (!unaccepted)
+		return;
+
+	unit_size = unaccepted->unit_size;
+
+	/*
+	 * Only care for the part of the range that is represented
+	 * in the bitmap.
+	 */
+	if (start < unaccepted->phys_base)
+		start = unaccepted->phys_base;
+	if (end < unaccepted->phys_base)
+		return;
+
+	/* Translate to offsets from the beginning of the bitmap */
+	start -= unaccepted->phys_base;
+	end -= unaccepted->phys_base;
+
+	/*
+	 * load_unaligned_zeropad() can lead to unwanted loads across page
+	 * boundaries. The unwanted loads are typically harmless. But, they
+	 * might be made to totally unrelated or even unmapped memory.
+	 * load_unaligned_zeropad() relies on exception fixup (#PF, #GP and now
+	 * #VE) to recover from these unwanted loads.
+	 *
+	 * But, this approach does not work for unaccepted memory. For TDX, a
+	 * load from unaccepted memory will not lead to a recoverable exception
+	 * within the guest. The guest will exit to the VMM where the only
+	 * recourse is to terminate the guest.
+	 *
+	 * There are two parts to fix this issue and comprehensively avoid
+	 * access to unaccepted memory. Together these ensure that an extra
+	 * "guard" page is accepted in addition to the memory that needs to be
+	 * used:
+	 *
+	 * 1. Implicitly extend the range_contains_unaccepted_memory(start, end)
+	 *    checks up to end+unit_size if 'end' is aligned on a unit_size
+	 *    boundary.
+	 *
+	 * 2. Implicitly extend accept_memory(start, end) to end+unit_size if
+	 *    'end' is aligned on a unit_size boundary. (immediately following
+	 *    this comment)
+	 */
+	if (!(end % unit_size))
+		end += unit_size;
+
+	/* Make sure not to overrun the bitmap */
+	if (end > unaccepted->size * unit_size * BITS_PER_BYTE)
+		end = unaccepted->size * unit_size * BITS_PER_BYTE;
+
+	range_start = start / unit_size;
+
+	spin_lock_irqsave(&unaccepted_memory_lock, flags);
+	for_each_set_bitrange_from(range_start, range_end, unaccepted->bitmap,
+				   DIV_ROUND_UP(end, unit_size)) {
+		unsigned long phys_start, phys_end;
+		unsigned long len = range_end - range_start;
+
+		phys_start = range_start * unit_size + unaccepted->phys_base;
+		phys_end = range_end * unit_size + unaccepted->phys_base;
+
+		arch_accept_memory(phys_start, phys_end);
+		bitmap_clear(unaccepted->bitmap, range_start, len);
+	}
+	spin_unlock_irqrestore(&unaccepted_memory_lock, flags);
+}
+
+bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end)
+{
+	struct efi_unaccepted_memory *unaccepted;
+	unsigned long flags;
+	bool ret = false;
+	u64 unit_size;
+
+	unaccepted = efi_get_unaccepted_table();
+	if (!unaccepted)
+		return false;
+
+	unit_size = unaccepted->unit_size;
+
+	/*
+	 * Only care for the part of the range that is represented
+	 * in the bitmap.
+	 */
+	if (start < unaccepted->phys_base)
+		start = unaccepted->phys_base;
+	if (end < unaccepted->phys_base)
+		return false;
+
+	/* Translate to offsets from the beginning of the bitmap */
+	start -= unaccepted->phys_base;
+	end -= unaccepted->phys_base;
+
+	/*
+	 * Also consider the unaccepted state of the *next* page. See fix #1 in
+	 * the comment on load_unaligned_zeropad() in accept_memory().
+	 */
+	if (!(end % unit_size))
+		end += unit_size;
+
+	/* Make sure not to overrun the bitmap */
+	if (end > unaccepted->size * unit_size * BITS_PER_BYTE)
+		end = unaccepted->size * unit_size * BITS_PER_BYTE;
+
+	spin_lock_irqsave(&unaccepted_memory_lock, flags);
+	while (start < end) {
+		if (test_bit(start / unit_size, unaccepted->bitmap)) {
+			ret = true;
+			break;
+		}
+
+		start += unit_size;
+	}
+	spin_unlock_irqrestore(&unaccepted_memory_lock, flags);
+
+	return ret;
+}

drivers/virt/coco/sev-guest/Kconfig

@@ -2,6 +2,7 @@ config SEV_GUEST
 	tristate "AMD SEV Guest driver"
 	default m
 	depends on AMD_MEM_ENCRYPT
+	select CRYPTO
 	select CRYPTO_AEAD2
 	select CRYPTO_GCM
 	help

fs/proc/meminfo.c

@@ -168,6 +168,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		    global_zone_page_state(NR_FREE_CMA_PAGES));
 #endif
 
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	show_val_kb(m, "Unaccepted:     ",
+		    global_zone_page_state(NR_UNACCEPTED));
+#endif
+
 	hugetlb_report_meminfo(m);
 
 	arch_report_meminfo(m);

include/linux/efi.h

@@ -108,7 +108,8 @@ typedef	struct {
 #define EFI_MEMORY_MAPPED_IO_PORT_SPACE	12
 #define EFI_PAL_CODE			13
 #define EFI_PERSISTENT_MEMORY		14
-#define EFI_MAX_MEMORY_TYPE		15
+#define EFI_UNACCEPTED_MEMORY		15
+#define EFI_MAX_MEMORY_TYPE		16
 
 /* Attribute values: */
 #define EFI_MEMORY_UC		((u64)0x0000000000000001ULL)	/* uncached */
@@ -417,6 +418,7 @@ void efi_native_runtime_setup(void);
 #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID	EFI_GUID(0xc451ed2b, 0x9694, 0x45d3,  0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89)
 #define LINUX_EFI_COCO_SECRET_AREA_GUID		EFI_GUID(0xadf956ad, 0xe98c, 0x484c,  0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47)
 #define LINUX_EFI_BOOT_MEMMAP_GUID		EFI_GUID(0x800f683f, 0xd08b, 0x423a,  0xa2, 0x93, 0x96, 0x5c, 0x3c, 0x6f, 0xe2, 0xb4)
+#define LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID	EFI_GUID(0xd5d1de3c, 0x105c, 0x44f9,  0x9e, 0xa9, 0xbc, 0xef, 0x98, 0x12, 0x00, 0x31)
 
 #define RISCV_EFI_BOOT_PROTOCOL_GUID		EFI_GUID(0xccd15fec, 0x6f73, 0x4eec,  0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf)
 
@@ -435,6 +437,9 @@ void efi_native_runtime_setup(void);
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
 #define AMD_SEV_MEM_ENCRYPT_GUID		EFI_GUID(0x0cf29b71, 0x9e51, 0x433a,  0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75)
 
+/* OVMF protocol GUIDs */
+#define OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID	EFI_GUID(0xc5a010fe, 0x38a7, 0x4531,  0x8a, 0x4a, 0x05, 0x00, 0xd2, 0xfd, 0x16, 0x49)
+
 typedef struct {
 	efi_guid_t guid;
 	u64 table;
@@ -534,6 +539,14 @@ struct efi_boot_memmap {
 	efi_memory_desc_t	map[];
 };
 
+struct efi_unaccepted_memory {
+	u32 version;
+	u32 unit_size;
+	u64 phys_base;
+	u64 size;
+	unsigned long bitmap[];
+};
+
 /*
  * Architecture independent structure for describing a memory map for the
  * benefit of efi_memmap_init_early(), and for passing context between
@@ -636,6 +649,7 @@ extern struct efi {
 	unsigned long			tpm_final_log;		/* TPM2 Final Events Log table */
 	unsigned long			mokvar_table;		/* MOK variable config table */
 	unsigned long			coco_secret;		/* Confidential computing secret table */
+	unsigned long			unaccepted;		/* Unaccepted memory table */
 
 	efi_get_time_t			*get_time;
 	efi_set_time_t			*set_time;

include/linux/mm.h

@@ -3839,4 +3839,23 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
+#ifdef CONFIG_UNACCEPTED_MEMORY
+
+bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end);
+void accept_memory(phys_addr_t start, phys_addr_t end);
+
+#else
+
+static inline bool range_contains_unaccepted_memory(phys_addr_t start,
+						    phys_addr_t end)
+{
+	return false;
+}
+
+static inline void accept_memory(phys_addr_t start, phys_addr_t end)
+{
+}
+
+#endif
+
 #endif /* _LINUX_MM_H */

include/linux/mmzone.h

@@ -143,6 +143,9 @@ enum zone_stat_item {
 	NR_ZSPAGES,		/* allocated in zsmalloc */
 #endif
 	NR_FREE_CMA_PAGES,
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	NR_UNACCEPTED,
+#endif
 	NR_VM_ZONE_STAT_ITEMS };
 
 enum node_stat_item {
@@ -910,6 +913,11 @@ struct zone {
 	/* free areas of different sizes */
 	struct free_area	free_area[MAX_ORDER + 1];
 
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	/* Pages to be accepted. All pages on the list are MAX_ORDER */
+	struct list_head	unaccepted_pages;
+#endif
+
 	/* zone flags, see below */
 	unsigned long		flags;
 

mm/memblock.c

@@ -1436,6 +1436,15 @@ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 		 */
 		kmemleak_alloc_phys(found, size, 0);
 
+	/*
+	 * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP,
+	 * require memory to be accepted before it can be used by the
+	 * guest.
+	 *
+	 * Accept the memory of the allocated buffer.
+	 */
+	accept_memory(found, found + size);
+
 	return found;
 }
 

mm/mm_init.c

@@ -1375,6 +1375,10 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 		INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
 		zone->free_area[order].nr_free = 0;
 	}
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	INIT_LIST_HEAD(&zone->unaccepted_pages);
+#endif
 }
 
 void __meminit init_currently_empty_zone(struct zone *zone,
@@ -1960,6 +1964,9 @@ static void __init deferred_free_range(unsigned long pfn,
 		return;
 	}
 
+	/* Accept chunks smaller than MAX_ORDER upfront */
+	accept_memory(PFN_PHYS(pfn), PFN_PHYS(pfn + nr_pages));
+
 	for (i = 0; i < nr_pages; i++, page++, pfn++) {
 		if (pageblock_aligned(pfn))
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);

mm/page_alloc.c

@@ -387,6 +387,12 @@ EXPORT_SYMBOL(nr_node_ids);
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
+static bool page_contains_unaccepted(struct page *page, unsigned int order);
+static void accept_page(struct page *page, unsigned int order);
+static bool try_to_accept_memory(struct zone *zone, unsigned int order);
+static inline bool has_unaccepted_memory(void);
+static bool __free_unaccepted(struct page *page);
+
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -1481,6 +1487,13 @@ void __free_pages_core(struct page *page, unsigned int order)
 
 	atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
 
+	if (page_contains_unaccepted(page, order)) {
+		if (order == MAX_ORDER && __free_unaccepted(page))
+			return;
+
+		accept_page(page, order);
+	}
+
 	/*
 	 * Bypass PCP and place fresh pages right to the tail, primarily
 	 * relevant for memory onlining.
@@ -3159,6 +3172,9 @@ static inline long __zone_watermark_unusable_free(struct zone *z,
 	if (!(alloc_flags & ALLOC_CMA))
 		unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	unusable_free += zone_page_state(z, NR_UNACCEPTED);
+#endif
 
 	return unusable_free;
 }
@@ -3458,6 +3474,11 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 				       gfp_mask)) {
 			int ret;
 
+			if (has_unaccepted_memory()) {
+				if (try_to_accept_memory(zone, order))
+					goto try_this_zone;
+			}
+
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 			/*
 			 * Watermark failed for this zone, but see if we can
@@ -3510,6 +3531,11 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 
 			return page;
 		} else {
+			if (has_unaccepted_memory()) {
+				if (try_to_accept_memory(zone, order))
+					goto try_this_zone;
+			}
+
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 			/* Try again if zone has deferred pages */
 			if (deferred_pages_enabled()) {
@@ -7215,3 +7241,150 @@ bool has_managed_dma(void)
 	return false;
 }
 #endif /* CONFIG_ZONE_DMA */
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+
+/* Counts number of zones with unaccepted pages. */
+static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
+
+static bool lazy_accept = true;
+
+static int __init accept_memory_parse(char *p)
+{
+	if (!strcmp(p, "lazy")) {
+		lazy_accept = true;
+		return 0;
+	} else if (!strcmp(p, "eager")) {
+		lazy_accept = false;
+		return 0;
+	} else {
+		return -EINVAL;
+	}
+}
+early_param("accept_memory", accept_memory_parse);
+
+static bool page_contains_unaccepted(struct page *page, unsigned int order)
+{
+	phys_addr_t start = page_to_phys(page);
+	phys_addr_t end = start + (PAGE_SIZE << order);
+
+	return range_contains_unaccepted_memory(start, end);
+}
+
+static void accept_page(struct page *page, unsigned int order)
+{
+	phys_addr_t start = page_to_phys(page);
+
+	accept_memory(start, start + (PAGE_SIZE << order));
+}
+
+static bool try_to_accept_memory_one(struct zone *zone)
+{
+	unsigned long flags;
+	struct page *page;
+	bool last;
+
+	if (list_empty(&zone->unaccepted_pages))
+		return false;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	page = list_first_entry_or_null(&zone->unaccepted_pages,
+					struct page, lru);
+	if (!page) {
+		spin_unlock_irqrestore(&zone->lock, flags);
+		return false;
+	}
+
+	list_del(&page->lru);
+	last = list_empty(&zone->unaccepted_pages);
+
+	__mod_zone_freepage_state(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
+	__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
+	spin_unlock_irqrestore(&zone->lock, flags);
+
+	accept_page(page, MAX_ORDER);
+
+	__free_pages_ok(page, MAX_ORDER, FPI_TO_TAIL);
+
+	if (last)
+		static_branch_dec(&zones_with_unaccepted_pages);
+
+	return true;
+}
+
+static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+{
+	long to_accept;
+	int ret = false;
+
+	/* How much to accept to get to high watermark? */
+	to_accept = high_wmark_pages(zone) -
+		    (zone_page_state(zone, NR_FREE_PAGES) -
+		    __zone_watermark_unusable_free(zone, order, 0));
+
+	/* Accept at least one page */
+	do {
+		if (!try_to_accept_memory_one(zone))
+			break;
+		ret = true;
+		to_accept -= MAX_ORDER_NR_PAGES;
+	} while (to_accept > 0);
+
+	return ret;
+}
+
+static inline bool has_unaccepted_memory(void)
+{
+	return static_branch_unlikely(&zones_with_unaccepted_pages);
+}
+
+static bool __free_unaccepted(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long flags;
+	bool first = false;
+
+	if (!lazy_accept)
+		return false;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	first = list_empty(&zone->unaccepted_pages);
+	list_add_tail(&page->lru, &zone->unaccepted_pages);
+	__mod_zone_freepage_state(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
+	__mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES);
+	spin_unlock_irqrestore(&zone->lock, flags);
+
+	if (first)
+		static_branch_inc(&zones_with_unaccepted_pages);
+
+	return true;
+}
+
+#else
+
+static bool page_contains_unaccepted(struct page *page, unsigned int order)
+{
+	return false;
+}
+
+static void accept_page(struct page *page, unsigned int order)
+{
+}
+
+static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+{
+	return false;
+}
+
+static inline bool has_unaccepted_memory(void)
+{
+	return false;
+}
+
+static bool __free_unaccepted(struct page *page)
+{
+	BUILD_BUG();
+	return false;
+}
+
+#endif /* CONFIG_UNACCEPTED_MEMORY */

mm/vmstat.c

@@ -1180,6 +1180,9 @@ const char * const vmstat_text[] = {
 	"nr_zspages",
 #endif
 	"nr_free_cma",
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	"nr_unaccepted",
+#endif
 
 	/* enum numa_stat_item counters */
 #ifdef CONFIG_NUMA