1 files changed, 115 insertions, 53 deletions

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 495b732d5af3..ea6695d53fb9 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -25,6 +25,7 @@
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/kfence.h>
+#include <linux/pkeys.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
@@ -109,38 +110,23 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 static phys_addr_t __init early_pgtable_alloc(int shift)
 {
 	phys_addr_t phys;
-	void *ptr;
 
 	phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0,
 					 MEMBLOCK_ALLOC_NOLEAKTRACE);
 	if (!phys)
 		panic("Failed to allocate page table page\n");
 
-	/*
-	 * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE
-	 * slot will be free, so we can (ab)use the FIX_PTE slot to initialise
-	 * any level of table.
-	 */
-	ptr = pte_set_fixmap(phys);
-
-	memset(ptr, 0, PAGE_SIZE);
-
-	/*
-	 * Implicit barriers also ensure the zeroed page is visible to the page
-	 * table walker
-	 */
-	pte_clear_fixmap();
-
 	return phys;
 }
 
-bool pgattr_change_is_safe(u64 old, u64 new)
+bool pgattr_change_is_safe(pteval_t old, pteval_t new)
 {
 	/*
 	 * The following mapping attributes may be updated in live
 	 * kernel mappings without the need for break-before-make.
 	 */
-	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG |
+			PTE_SWBITS_MASK;
 
 	/* creating or taking down mappings is always safe */
 	if (!pte_valid(__pte(old)) || !pte_valid(__pte(new)))
@@ -172,16 +158,25 @@ bool pgattr_change_is_safe(u64 old, u64 new)
 	return ((old ^ new) & ~mask) == 0;
 }
 
-static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
-		     phys_addr_t phys, pgprot_t prot)
+static void init_clear_pgtable(void *table)
 {
-	pte_t *ptep;
+	clear_page(table);
 
-	ptep = pte_set_fixmap_offset(pmdp, addr);
+	/* Ensure the zeroing is observed by page table walks. */
+	dsb(ishst);
+}
+
+static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
+		     phys_addr_t phys, pgprot_t prot)
+{
 	do {
 		pte_t old_pte = __ptep_get(ptep);
 
-		__set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+		/*
+		 * Required barriers to make this visible to the table walker
+		 * are deferred to the end of alloc_init_cont_pte().
+		 */
+		__set_pte_nosync(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
@@ -192,8 +187,6 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 		phys += PAGE_SIZE;
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	pte_clear_fixmap();
 }
 
 static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
@@ -204,20 +197,25 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 {
 	unsigned long next;
 	pmd_t pmd = READ_ONCE(*pmdp);
+	pte_t *ptep;
 
 	BUG_ON(pmd_sect(pmd));
 	if (pmd_none(pmd)) {
-		pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
+		pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF;
 		phys_addr_t pte_phys;
 
 		if (flags & NO_EXEC_MAPPINGS)
 			pmdval |= PMD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pte_phys = pgtable_alloc(PAGE_SHIFT);
+		ptep = pte_set_fixmap(pte_phys);
+		init_clear_pgtable(ptep);
+		ptep += pte_index(addr);
 		__pmd_populate(pmdp, pte_phys, pmdval);
-		pmd = READ_ONCE(*pmdp);
+	} else {
+		BUG_ON(pmd_bad(pmd));
+		ptep = pte_set_fixmap_offset(pmdp, addr);
 	}
-	BUG_ON(pmd_bad(pmd));
 
 	do {
 		pgprot_t __prot = prot;
@@ -229,20 +227,26 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pte(pmdp, addr, next, phys, __prot);
+		init_pte(ptep, addr, next, phys, __prot);
 
+		ptep += pte_index(next) - pte_index(addr);
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	/*
+	 * Note: barriers and maintenance necessary to clear the fixmap slot
+	 * ensure that all previous pgtable writes are visible to the table
+	 * walker.
+	 */
+	pte_clear_fixmap();
 }
 
-static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
+static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
 		     phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
-	pmd_t *pmdp;
 
-	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
 		pmd_t old_pmd = READ_ONCE(*pmdp);
 
@@ -268,8 +272,6 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		}
 		phys += next - addr;
 	} while (pmdp++, addr = next, addr != end);
-
-	pmd_clear_fixmap();
 }
 
 static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
@@ -279,23 +281,28 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 {
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
+	pmd_t *pmdp;
 
 	/*
 	 * Check for initial section mappings in the pgd/pud.
 	 */
 	BUG_ON(pud_sect(pud));
 	if (pud_none(pud)) {
-		pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
+		pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF;
 		phys_addr_t pmd_phys;
 
 		if (flags & NO_EXEC_MAPPINGS)
 			pudval |= PUD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pmd_phys = pgtable_alloc(PMD_SHIFT);
+		pmdp = pmd_set_fixmap(pmd_phys);
+		init_clear_pgtable(pmdp);
+		pmdp += pmd_index(addr);
 		__pud_populate(pudp, pmd_phys, pudval);
-		pud = READ_ONCE(*pudp);
+	} else {
+		BUG_ON(pud_bad(pud));
+		pmdp = pmd_set_fixmap_offset(pudp, addr);
 	}
-	BUG_ON(pud_bad(pud));
 
 	do {
 		pgprot_t __prot = prot;
@@ -307,10 +314,13 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
+		init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags);
 
+		pmdp += pmd_index(next) - pmd_index(addr);
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	pmd_clear_fixmap();
 }
 
 static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
@@ -323,19 +333,22 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 	pud_t *pudp;
 
 	if (p4d_none(p4d)) {
-		p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN;
+		p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN | P4D_TABLE_AF;
 		phys_addr_t pud_phys;
 
 		if (flags & NO_EXEC_MAPPINGS)
 			p4dval |= P4D_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		pud_phys = pgtable_alloc(PUD_SHIFT);
+		pudp = pud_set_fixmap(pud_phys);
+		init_clear_pgtable(pudp);
+		pudp += pud_index(addr);
 		__p4d_populate(p4dp, pud_phys, p4dval);
-		p4d = READ_ONCE(*p4dp);
+	} else {
+		BUG_ON(p4d_bad(p4d));
+		pudp = pud_set_fixmap_offset(p4dp, addr);
 	}
-	BUG_ON(p4d_bad(p4d));
 
-	pudp = pud_set_fixmap_offset(p4dp, addr);
 	do {
 		pud_t old_pud = READ_ONCE(*pudp);
 
@@ -378,19 +391,22 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	p4d_t *p4dp;
 
 	if (pgd_none(pgd)) {
-		pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN;
+		pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN | PGD_TABLE_AF;
 		phys_addr_t p4d_phys;
 
 		if (flags & NO_EXEC_MAPPINGS)
 			pgdval |= PGD_TABLE_PXN;
 		BUG_ON(!pgtable_alloc);
 		p4d_phys = pgtable_alloc(P4D_SHIFT);
+		p4dp = p4d_set_fixmap(p4d_phys);
+		init_clear_pgtable(p4dp);
+		p4dp += p4d_index(addr);
 		__pgd_populate(pgdp, p4d_phys, pgdval);
-		pgd = READ_ONCE(*pgdp);
+	} else {
+		BUG_ON(pgd_bad(pgd));
+		p4dp = p4d_set_fixmap_offset(pgdp, addr);
 	}
-	BUG_ON(pgd_bad(pgd));
 
-	p4dp = p4d_set_fixmap_offset(pgdp, addr);
 	do {
 		p4d_t old_p4d = READ_ONCE(*p4dp);
 
@@ -457,11 +473,10 @@ void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
 
 static phys_addr_t __pgd_pgtable_alloc(int shift)
 {
-	void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL);
-	BUG_ON(!ptr);
+	/* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */
+	void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL & ~__GFP_ZERO);
 
-	/* Ensure the zeroed page is visible to the page table walker */
-	dsb(ishst);
+	BUG_ON(!ptr);
 	return __pa(ptr);
 }
 
@@ -1154,15 +1169,19 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
 				unsigned long addr, unsigned long next)
 {
 	vmemmap_verify((pte_t *)pmdp, node, addr, next);
-	return 1;
+
+	return pmd_sect(READ_ONCE(*pmdp));
 }
 
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+	/* [start, end] should be within one section */
+	WARN_ON_ONCE(end - start > PAGES_PER_SECTION * sizeof(struct page));
 
-	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES))
+	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) ||
+	    (end - start < PAGES_PER_SECTION * sizeof(struct page)))
 		return vmemmap_populate_basepages(start, end, node, altmap);
 	else
 		return vmemmap_populate_hugepages(start, end, node, altmap);
@@ -1342,7 +1361,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
 		__remove_pgd_mapping(swapper_pg_dir,
 				     __phys_to_virt(start), size);
 	else {
-		max_pfn = PFN_UP(start + size);
+		/* Address of hotplugged memory can be smaller */
+		max_pfn = max(max_pfn, PFN_UP(start + size));
 		max_low_pfn = max_pfn;
 	}
 
@@ -1535,3 +1555,45 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp)
 
 	cpu_uninstall_idmap();
 }
+
+#ifdef CONFIG_ARCH_HAS_PKEYS
+int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val)
+{
+	u64 new_por;
+	u64 old_por;
+
+	if (!system_supports_poe())
+		return -ENOSPC;
+
+	/*
+	 * This code should only be called with valid 'pkey'
+	 * values originating from in-kernel users.  Complain
+	 * if a bad value is observed.
+	 */
+	if (WARN_ON_ONCE(pkey >= arch_max_pkey()))
+		return -EINVAL;
+
+	/* Set the bits we need in POR:  */
+	new_por = POE_RWX;
+	if (init_val & PKEY_DISABLE_WRITE)
+		new_por &= ~POE_W;
+	if (init_val & PKEY_DISABLE_ACCESS)
+		new_por &= ~POE_RW;
+	if (init_val & PKEY_DISABLE_READ)
+		new_por &= ~POE_R;
+	if (init_val & PKEY_DISABLE_EXECUTE)
+		new_por &= ~POE_X;
+
+	/* Shift the bits in to the correct place in POR for pkey: */
+	new_por = POR_ELx_PERM_PREP(pkey, new_por);
+
+	/* Get old POR and mask off any old bits in place: */
+	old_por = read_sysreg_s(SYS_POR_EL0);
+	old_por &= ~(POE_MASK << POR_ELx_PERM_SHIFT(pkey));
+
+	/* Write old part along with new part: */
+	write_sysreg_s(old_por | new_por, SYS_POR_EL0);
+
+	return 0;
+}
+#endif