Merge branch 'linus' into x86/mm

Bring x86 and selftests up to date

5 files changed, 155 insertions, 45 deletions

diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..c45127265f2f 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -4,6 +4,79 @@
  * included by both the compressed kernel and the regular kernel.
  */
 
+static void free_pte(struct x86_mapping_info *info, pmd_t *pmd)
+{
+	pte_t *pte = pte_offset_kernel(pmd, 0);
+
+	info->free_pgt_page(pte, info->context);
+}
+
+static void free_pmd(struct x86_mapping_info *info, pud_t *pud)
+{
+	pmd_t *pmd = pmd_offset(pud, 0);
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_present(pmd[i]))
+			continue;
+
+		if (pmd_leaf(pmd[i]))
+			continue;
+
+		free_pte(info, &pmd[i]);
+	}
+
+	info->free_pgt_page(pmd, info->context);
+}
+
+static void free_pud(struct x86_mapping_info *info, p4d_t *p4d)
+{
+	pud_t *pud = pud_offset(p4d, 0);
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		if (!pud_present(pud[i]))
+			continue;
+
+		if (pud_leaf(pud[i]))
+			continue;
+
+		free_pmd(info, &pud[i]);
+	}
+
+	info->free_pgt_page(pud, info->context);
+}
+
+static void free_p4d(struct x86_mapping_info *info, pgd_t *pgd)
+{
+	p4d_t *p4d = p4d_offset(pgd, 0);
+	int i;
+
+	for (i = 0; i < PTRS_PER_P4D; i++) {
+		if (!p4d_present(p4d[i]))
+			continue;
+
+		free_pud(info, &p4d[i]);
+	}
+
+	if (pgtable_l5_enabled())
+		info->free_pgt_page(p4d, info->context);
+}
+
+void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PGD; i++) {
+		if (!pgd_present(pgd[i]))
+			continue;
+
+		free_p4d(info, &pgd[i]);
+	}
+
+	info->free_pgt_page(pgd, info->context);
+}
+
 static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
 			   unsigned long addr, unsigned long end)
 {
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7e177856ee4f..d8dbeac8b206 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -469,7 +469,9 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_RESERVED_KERN) &&
+			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+					     E820_TYPE_ACPI))
 				set_pte_init(pte, __pte(0), init);
 			continue;
 		}
@@ -524,7 +526,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_RESERVED_KERN) &&
+			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+					     E820_TYPE_ACPI))
 				set_pmd_init(pmd, __pmd(0), init);
 			continue;
 		}
@@ -611,7 +615,9 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_RESERVED_KERN) &&
+			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+					     E820_TYPE_ACPI))
 				set_pud_init(pud, __pud(0), init);
 			continue;
 		}
@@ -698,7 +704,9 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_RESERVED_KERN) &&
+			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
+					     E820_TYPE_ACPI))
 				set_p4d_init(p4d, __p4d(0), init);
 			continue;
 		}
@@ -980,8 +988,6 @@ static void __meminit free_pagetable(struct page *page, int order)
 
 	/* bootmem page has reserved flag */
 	if (PageReserved(page)) {
-		__ClearPageReserved(page);
-
 		magic = page->index;
 		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
 			while (nr_pages--)
@@ -1354,18 +1360,6 @@ void __init mem_init(void)
 	preallocate_vmalloc_pages();
 }
 
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask)
-{
-	/*
-	 * More CPUs always led to greater speedups on tested systems, up to
-	 * all the nodes' CPUs.  Use all since the system is otherwise idle
-	 * now.
-	 */
-	return max_t(int, cpumask_weight(node_cpumask), 1);
-}
-#endif
-
 int kernel_set_to_readonly;
 
 void mark_rodata_ro(void)
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 422602f6039b..86a476a426c2 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -2,7 +2,7 @@
 /*
  * 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>
  */
@@ -283,7 +283,7 @@ static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc)
 #endif
 }
 
-static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
+static int amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
 {
 	/*
 	 * To maintain the security guarantees of SEV-SNP guests, make sure
@@ -292,11 +292,11 @@ static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool
 	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc)
 		snp_set_memory_shared(vaddr, npages);
 
-	return true;
+	return 0;
 }
 
 /* Return true unconditionally: return value doesn't matter for the SEV side */
-static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
+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
@@ -308,7 +308,7 @@ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool e
 	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
 		enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc);
 
-	return true;
+	return 0;
 }
 
 static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
@@ -510,6 +510,12 @@ void __init sme_early_init(void)
 		 */
 		x86_init.resources.dmi_setup = snp_dmi_setup;
 	}
+
+	/*
+	 * Switch the SVSM CA mapping (if active) from identity mapped to
+	 * kernel mapped.
+	 */
+	snp_update_svsm_ca();
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 19fdfbb171ed..44f7b2ea6a07 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -662,8 +662,9 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
 
 /*
  * Lookup the page table entry for a virtual address in a specific pgd.
- * Return a pointer to the entry, the level of the mapping, and the effective
- * NX and RW bits of all page table levels.
+ * Return a pointer to the entry (or NULL if the entry does not exist),
+ * the level of the entry, and the effective NX and RW bits of all
+ * page table levels.
  */
 pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
 				  unsigned int *level, bool *nx, bool *rw)
@@ -672,13 +673,14 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
 	pud_t *pud;
 	pmd_t *pmd;
 
-	*level = PG_LEVEL_NONE;
+	*level = PG_LEVEL_256T;
 	*nx = false;
 	*rw = true;
 
 	if (pgd_none(*pgd))
 		return NULL;
 
+	*level = PG_LEVEL_512G;
 	*nx |= pgd_flags(*pgd) & _PAGE_NX;
 	*rw &= pgd_flags(*pgd) & _PAGE_RW;
 
@@ -686,10 +688,10 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
 	if (p4d_none(*p4d))
 		return NULL;
 
-	*level = PG_LEVEL_512G;
 	if (p4d_leaf(*p4d) || !p4d_present(*p4d))
 		return (pte_t *)p4d;
 
+	*level = PG_LEVEL_1G;
 	*nx |= p4d_flags(*p4d) & _PAGE_NX;
 	*rw &= p4d_flags(*p4d) & _PAGE_RW;
 
@@ -697,10 +699,10 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
 	if (pud_none(*pud))
 		return NULL;
 
-	*level = PG_LEVEL_1G;
 	if (pud_leaf(*pud) || !pud_present(*pud))
 		return (pte_t *)pud;
 
+	*level = PG_LEVEL_2M;
 	*nx |= pud_flags(*pud) & _PAGE_NX;
 	*rw &= pud_flags(*pud) & _PAGE_RW;
 
@@ -708,15 +710,13 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
 	if (pmd_none(*pmd))
 		return NULL;
 
-	*level = PG_LEVEL_2M;
 	if (pmd_leaf(*pmd) || !pmd_present(*pmd))
 		return (pte_t *)pmd;
 
+	*level = PG_LEVEL_4K;
 	*nx |= pmd_flags(*pmd) & _PAGE_NX;
 	*rw &= pmd_flags(*pmd) & _PAGE_RW;
 
-	*level = PG_LEVEL_4K;
-
 	return pte_offset_kernel(pmd, address);
 }
 
@@ -736,9 +736,8 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
  * Lookup the page table entry for a virtual address. Return a pointer
  * to the entry and the level of the mapping.
  *
- * Note: We return pud and pmd either when the entry is marked large
- * or when the present bit is not set. Otherwise we would return a
- * pointer to a nonexisting mapping.
+ * Note: the function returns p4d, pud or pmd either when the entry is marked
+ * large or when the present bit is not set. Otherwise it returns NULL.
  */
 pte_t *lookup_address(unsigned long address, unsigned int *level)
 {
@@ -1120,8 +1119,8 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 		lpinc = PMD_SIZE;
 		/*
 		 * Clear the PSE flags if the PRESENT flag is not set
-		 * otherwise pmd_present/pmd_huge will return true
-		 * even on a non present pmd.
+		 * otherwise pmd_present() will return true even on a non
+		 * present pmd.
 		 */
 		if (!(pgprot_val(ref_prot) & _PAGE_PRESENT))
 			pgprot_val(ref_prot) &= ~_PAGE_PSE;
@@ -2196,7 +2195,8 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 		cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
 
 	/* Notify hypervisor that we are about to set/clr encryption attribute. */
-	if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc))
+	ret = x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
+	if (ret)
 		goto vmm_fail;
 
 	ret = __change_page_attr_set_clr(&cpa, 1);
@@ -2214,24 +2214,61 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 		return ret;
 
 	/* Notify hypervisor that we have successfully set/clr encryption attribute. */
-	if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
+	ret = x86_platform.guest.enc_status_change_finish(addr, numpages, enc);
+	if (ret)
 		goto vmm_fail;
 
 	return 0;
 
 vmm_fail:
-	WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n",
-		  (void *)addr, numpages, enc ? "private" : "shared");
+	WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s: %d\n",
+		  (void *)addr, numpages, enc ? "private" : "shared", ret);
+
+	return ret;
+}
+
+/*
+ * The lock serializes conversions between private and shared memory.
+ *
+ * It is taken for read on conversion. A write lock guarantees that no
+ * concurrent conversions are in progress.
+ */
+static DECLARE_RWSEM(mem_enc_lock);
+
+/*
+ * Stop new private<->shared conversions.
+ *
+ * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete.
+ * The lock is not released to prevent new conversions from being started.
+ */
+bool set_memory_enc_stop_conversion(void)
+{
+	/*
+	 * In a crash scenario, sleep is not allowed. Try to take the lock.
+	 * Failure indicates that there is a race with the conversion.
+	 */
+	if (oops_in_progress)
+		return down_write_trylock(&mem_enc_lock);
+
+	down_write(&mem_enc_lock);
 
-	return -EIO;
+	return true;
 }
 
 static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 {
-	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
-		return __set_memory_enc_pgtable(addr, numpages, enc);
+	int ret = 0;
 
-	return 0;
+	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+		if (!down_read_trylock(&mem_enc_lock))
+			return -EBUSY;
+
+		ret = __set_memory_enc_pgtable(addr, numpages, enc);
+
+		up_read(&mem_enc_lock);
+	}
+
+	return ret;
 }
 
 int set_memory_encrypted(unsigned long addr, int numpages)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 93e54ba91fbf..f5931499c2d6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -110,7 +110,7 @@ static inline void pgd_list_del(pgd_t *pgd)
 #define UNSHARED_PTRS_PER_PGD				\
 	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 #define MAX_UNSHARED_PTRS_PER_PGD			\
-	max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
+	MAX_T(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
 
 
 static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)