1 files changed, 291 insertions, 56 deletions

diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 5e49e4b4a4cc..3f76db3d2769 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -5,6 +5,7 @@
 
 #include <linux/pagewalk.h>
 #include <linux/pgtable.h>
+#include <linux/vmalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/bitops.h>
 #include <asm/set_memory.h>
@@ -25,23 +26,10 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 	return new_val;
 }
 
-static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
-{
-	pgd_t val = READ_ONCE(*pgd);
-
-	if (pgd_leaf(val)) {
-		val = __pgd(set_pageattr_masks(pgd_val(val), walk));
-		set_pgd(pgd, val);
-	}
-
-	return 0;
-}
-
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	p4d_t val = READ_ONCE(*p4d);
+	p4d_t val = p4dp_get(p4d);
 
 	if (p4d_leaf(val)) {
 		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
@@ -54,7 +42,7 @@ static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pud_t val = READ_ONCE(*pud);
+	pud_t val = pudp_get(pud);
 
 	if (pud_leaf(val)) {
 		val = __pud(set_pageattr_masks(pud_val(val), walk));
@@ -67,7 +55,7 @@ static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
 static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pmd_t val = READ_ONCE(*pmd);
+	pmd_t val = pmdp_get(pmd);
 
 	if (pmd_leaf(val)) {
 		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
@@ -80,7 +68,7 @@ static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
 static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
-	pte_t val = READ_ONCE(*pte);
+	pte_t val = ptep_get(pte);
 
 	val = __pte(set_pageattr_masks(pte_val(val), walk));
 	set_pte(pte, val);
@@ -96,20 +84,189 @@ static int pageattr_pte_hole(unsigned long addr, unsigned long next,
 }
 
 static const struct mm_walk_ops pageattr_ops = {
-	.pgd_entry = pageattr_pgd_entry,
 	.p4d_entry = pageattr_p4d_entry,
 	.pud_entry = pageattr_pud_entry,
 	.pmd_entry = pageattr_pmd_entry,
 	.pte_entry = pageattr_pte_entry,
 	.pte_hole = pageattr_pte_hole,
+	.walk_lock = PGWALK_RDLOCK,
 };
 
+#ifdef CONFIG_64BIT
+static int __split_linear_mapping_pmd(pud_t *pudp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pmd_t *pmdp;
+	unsigned long next;
+
+	pmdp = pmd_offset(pudp, vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (next - vaddr >= PMD_SIZE &&
+		    vaddr <= (vaddr & PMD_MASK) && end >= next)
+			continue;
+
+		if (pmd_leaf(pmdp_get(pmdp))) {
+			struct page *pte_page;
+			unsigned long pfn = _pmd_pfn(pmdp_get(pmdp));
+			pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK);
+			pte_t *ptep_new;
+			int i;
+
+			pte_page = alloc_page(GFP_KERNEL);
+			if (!pte_page)
+				return -ENOMEM;
+
+			ptep_new = (pte_t *)page_address(pte_page);
+			for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new)
+				set_pte(ptep_new, pfn_pte(pfn + i, prot));
+
+			smp_wmb();
+
+			set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE));
+		}
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pud(p4d_t *p4dp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pud_t *pudp;
+	unsigned long next;
+	int ret;
+
+	pudp = pud_offset(p4dp, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (next - vaddr >= PUD_SIZE &&
+		    vaddr <= (vaddr & PUD_MASK) && end >= next)
+			continue;
+
+		if (pud_leaf(pudp_get(pudp))) {
+			struct page *pmd_page;
+			unsigned long pfn = _pud_pfn(pudp_get(pudp));
+			pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK);
+			pmd_t *pmdp_new;
+			int i;
+
+			pmd_page = alloc_page(GFP_KERNEL);
+			if (!pmd_page)
+				return -ENOMEM;
+
+			pmdp_new = (pmd_t *)page_address(pmd_page);
+			for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new)
+				set_pmd(pmdp_new,
+					pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot));
+
+			smp_wmb();
+
+			set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pmd(pudp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_p4d(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end)
+{
+	p4d_t *p4dp;
+	unsigned long next;
+	int ret;
+
+	p4dp = p4d_offset(pgdp, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		/*
+		 * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't
+		 * need to split, we'll change the protections on the whole P4D.
+		 */
+		if (next - vaddr >= P4D_SIZE &&
+		    vaddr <= (vaddr & P4D_MASK) && end >= next)
+			continue;
+
+		if (p4d_leaf(p4dp_get(p4dp))) {
+			struct page *pud_page;
+			unsigned long pfn = _p4d_pfn(p4dp_get(p4dp));
+			pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK);
+			pud_t *pudp_new;
+			int i;
+
+			pud_page = alloc_page(GFP_KERNEL);
+			if (!pud_page)
+				return -ENOMEM;
+
+			/*
+			 * Fill the pud level with leaf puds that have the same
+			 * protections as the leaf p4d.
+			 */
+			pudp_new = (pud_t *)page_address(pud_page);
+			for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new)
+				set_pud(pudp_new,
+					pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot));
+
+			/*
+			 * Make sure the pud filling is not reordered with the
+			 * p4d store which could result in seeing a partially
+			 * filled pud level.
+			 */
+			smp_wmb();
+
+			set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pud(p4dp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pgd(pgd_t *pgdp,
+				      unsigned long vaddr,
+				      unsigned long end)
+{
+	unsigned long next;
+	int ret;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+		/* We never use PGD mappings for the linear mapping */
+		ret = __split_linear_mapping_p4d(pgdp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pgdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int split_linear_mapping(unsigned long start, unsigned long end)
+{
+	return __split_linear_mapping_pgd(pgd_offset_k(start), start, end);
+}
+#endif	/* CONFIG_64BIT */
+
 static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 			pgprot_t clear_mask)
 {
 	int ret;
 	unsigned long start = addr;
 	unsigned long end = start + PAGE_SIZE * numpages;
+	unsigned long __maybe_unused lm_start;
+	unsigned long __maybe_unused lm_end;
 	struct pageattr_masks masks = {
 		.set_mask = set_mask,
 		.clear_mask = clear_mask
@@ -118,12 +275,73 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 	if (!numpages)
 		return 0;
 
-	mmap_read_lock(&init_mm);
-	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+	mmap_write_lock(&init_mm);
+
+#ifdef CONFIG_64BIT
+	/*
+	 * We are about to change the permissions of a kernel mapping, we must
+	 * apply the same changes to its linear mapping alias, which may imply
+	 * splitting a huge mapping.
+	 */
+
+	if (is_vmalloc_or_module_addr((void *)start)) {
+		struct vm_struct *area = NULL;
+		int i, page_start;
+
+		area = find_vm_area((void *)start);
+		page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT;
+
+		for (i = page_start; i < page_start + numpages; ++i) {
+			lm_start = (unsigned long)page_address(area->pages[i]);
+			lm_end = lm_start + PAGE_SIZE;
+
+			ret = split_linear_mapping(lm_start, lm_end);
+			if (ret)
+				goto unlock;
+
+			ret = walk_kernel_page_table_range(lm_start, lm_end,
+						    &pageattr_ops, NULL, &masks);
+			if (ret)
+				goto unlock;
+		}
+	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
+		if (is_kernel_mapping(start)) {
+			lm_start = (unsigned long)lm_alias(start);
+			lm_end = (unsigned long)lm_alias(end);
+		} else {
+			lm_start = start;
+			lm_end = end;
+		}
+
+		ret = split_linear_mapping(lm_start, lm_end);
+		if (ret)
+			goto unlock;
+
+		ret = walk_kernel_page_table_range(lm_start, lm_end,
+					    &pageattr_ops, NULL, &masks);
+		if (ret)
+			goto unlock;
+	}
+
+	ret =  walk_kernel_page_table_range(start, end, &pageattr_ops, NULL,
 				     &masks);
-	mmap_read_unlock(&init_mm);
+
+unlock:
+	mmap_write_unlock(&init_mm);
+
+	/*
+	 * We can't use flush_tlb_kernel_range() here as we may have split a
+	 * hugepage that is larger than that, so let's flush everything.
+	 */
+	flush_tlb_all();
+#else
+	ret =  walk_kernel_page_table_range(start, end, &pageattr_ops, NULL,
+				     &masks);
+
+	mmap_write_unlock(&init_mm);
 
 	flush_tlb_kernel_range(start, end);
+#endif
 
 	return ret;
 }
@@ -158,50 +376,59 @@ int set_memory_nx(unsigned long addr, int numpages)
 
 int set_direct_map_invalid_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = __pgprot(0),
-		.clear_mask = __pgprot(_PAGE_PRESENT)
-	};
-
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return __set_memory((unsigned long)page_address(page), 1,
+			    __pgprot(0), __pgprot(_PAGE_PRESENT));
 }
 
 int set_direct_map_default_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = PAGE_KERNEL,
-		.clear_mask = __pgprot(0)
-	};
+	return __set_memory((unsigned long)page_address(page), 1,
+			    PAGE_KERNEL, __pgprot(_PAGE_EXEC));
+}
 
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
+int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid)
+{
+	pgprot_t set, clear;
+
+	if (valid) {
+		set = PAGE_KERNEL;
+		clear = __pgprot(_PAGE_EXEC);
+	} else {
+		set = __pgprot(0);
+		clear = __pgprot(_PAGE_PRESENT);
+	}
 
-	return ret;
+	return __set_memory((unsigned long)page_address(page), nr, set, clear);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
+static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data)
+{
+	int enable = *(int *)data;
+
+	unsigned long val = pte_val(ptep_get(pte));
+
+	if (enable)
+		val |= _PAGE_PRESENT;
+	else
+		val &= ~_PAGE_PRESENT;
+
+	set_pte(pte, __pte(val));
+
+	return 0;
+}
+
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (!debug_pagealloc_enabled())
 		return;
 
-	if (enable)
-		__set_memory((unsigned long)page_address(page), numpages,
-			     __pgprot(_PAGE_PRESENT), __pgprot(0));
-	else
-		__set_memory((unsigned long)page_address(page), numpages,
-			     __pgprot(0), __pgprot(_PAGE_PRESENT));
+	unsigned long start = (unsigned long)page_address(page);
+	unsigned long size = PAGE_SIZE * numpages;
+
+	apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable);
+
+	flush_tlb_kernel_range(start, start + size);
 }
 #endif
 
@@ -215,21 +442,29 @@ bool kernel_page_present(struct page *page)
 	pte_t *pte;
 
 	pgd = pgd_offset_k(addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return false;
+	if (pgd_leaf(pgdp_get(pgd)))
+		return true;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return false;
+	if (p4d_leaf(p4dp_get(p4d)))
+		return true;
 
 	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return false;
+	if (pud_leaf(pudp_get(pud)))
+		return true;
 
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return false;
+	if (pmd_leaf(pmdp_get(pmd)))
+		return true;
 
 	pte = pte_offset_kernel(pmd, addr);
-	return pte_present(*pte);
+	return pte_present(ptep_get(pte));
 }