All of lore.kernel.org
 help / color / mirror / Atom feed
From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: pasha.tatashin@soleen.com, jmorris@namei.org, sashal@kernel.org,
	ebiederm@xmission.com, kexec@lists.infradead.org,
	linux-kernel@vger.kernel.org, corbet@lwn.net,
	catalin.marinas@arm.com, will@kernel.org,
	linux-arm-kernel@lists.infradead.org, marc.zyngier@arm.com,
	james.morse@arm.com, vladimir.murzin@arm.com,
	matthias.bgg@gmail.com, bhsharma@redhat.com, linux-mm@kvack.org
Subject: [PATCH v2 09/14] arm64, trans_table: complete generalization of trans_tables
Date: Fri, 16 Aug 2019 22:46:24 -0400	[thread overview]
Message-ID: <20190817024629.26611-10-pasha.tatashin@soleen.com> (raw)
In-Reply-To: <20190817024629.26611-1-pasha.tatashin@soleen.com>

Make the last private functions in page table copy path generlized for use
outside of hibernate.

Switch to use the provided allocator, flags, and source page table. Also,
unify all copy function implementations to reduce the possibility of bugs.
All page table levels are implemented symmetrically.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/mm/trans_table.c | 204 ++++++++++++++++++++----------------
 1 file changed, 113 insertions(+), 91 deletions(-)

diff --git a/arch/arm64/mm/trans_table.c b/arch/arm64/mm/trans_table.c
index 815e40bb1316..ce0f24806eaa 100644
--- a/arch/arm64/mm/trans_table.c
+++ b/arch/arm64/mm/trans_table.c
@@ -27,139 +27,161 @@ static void *trans_alloc(struct trans_table_info *info)
 	return page;
 }
 
-static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
+static int trans_table_copy_pte(struct trans_table_info *info, pte_t *dst_ptep,
+				pte_t *src_ptep, unsigned long start,
+				unsigned long end)
 {
-	pte_t pte = READ_ONCE(*src_ptep);
-
-	if (pte_valid(pte)) {
-		/*
-		 * Resume will overwrite areas that may be marked
-		 * read only (code, rodata). Clear the RDONLY bit from
-		 * the temporary mappings we use during restore.
-		 */
-		set_pte(dst_ptep, pte_mkwrite(pte));
-	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
-		/*
-		 * debug_pagealloc will removed the PTE_VALID bit if
-		 * the page isn't in use by the resume kernel. It may have
-		 * been in use by the original kernel, in which case we need
-		 * to put it back in our copy to do the restore.
-		 *
-		 * Before marking this entry valid, check the pfn should
-		 * be mapped.
-		 */
-		BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
-	}
-}
-
-static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
-		    unsigned long end)
-{
-	pte_t *src_ptep;
-	pte_t *dst_ptep;
 	unsigned long addr = start;
+	int i = pte_index(addr);
 
-	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
-	if (!dst_ptep)
-		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
-	dst_ptep = pte_offset_kernel(dst_pmdp, start);
-
-	src_ptep = pte_offset_kernel(src_pmdp, start);
 	do {
-		_copy_pte(dst_ptep, src_ptep, addr);
-	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
+		pte_t src_pte = READ_ONCE(src_ptep[i]);
+
+		if (pte_none(src_pte))
+			continue;
+		if (info->trans_flags & TRANS_MKWRITE)
+			src_pte = pte_mkwrite(src_pte);
+		if (info->trans_flags & TRANS_MKVALID)
+			src_pte = pte_mkpresent(src_pte);
+		if (info->trans_flags & TRANS_CHECKPFN) {
+			if (!pfn_valid(pte_pfn(src_pte)))
+				return -ENXIO;
+		}
+		set_pte(&dst_ptep[i], src_pte);
+	} while (addr += PAGE_SIZE, i++, addr != end && i < PTRS_PER_PTE);
 
 	return 0;
 }
 
-static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
-		    unsigned long end)
+static int trans_table_copy_pmd(struct trans_table_info *info, pmd_t *dst_pmdp,
+				pmd_t *src_pmdp, unsigned long start,
+				unsigned long end)
 {
-	pmd_t *src_pmdp;
-	pmd_t *dst_pmdp;
 	unsigned long next;
 	unsigned long addr = start;
+	int i = pmd_index(addr);
+	int rc;
 
-	if (pud_none(READ_ONCE(*dst_pudp))) {
-		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pmdp)
-			return -ENOMEM;
-		pud_populate(&init_mm, dst_pudp, dst_pmdp);
-	}
-	dst_pmdp = pmd_offset(dst_pudp, start);
-
-	src_pmdp = pmd_offset(src_pudp, start);
 	do {
-		pmd_t pmd = READ_ONCE(*src_pmdp);
+		pmd_t src_pmd = READ_ONCE(src_pmdp[i]);
+		pmd_t dst_pmd = READ_ONCE(dst_pmdp[i]);
+		pte_t *dst_ptep, *src_ptep;
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		if (pmd_none(src_pmd))
+			continue;
+
+		if (!pmd_table(src_pmd)) {
+			if (info->trans_flags & TRANS_MKWRITE)
+				pmd_val(src_pmd) &= ~PMD_SECT_RDONLY;
+			set_pmd(&dst_pmdp[i], src_pmd);
 			continue;
-		if (pmd_table(pmd)) {
-			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
+		}
+
+		if (pmd_none(dst_pmd)) {
+			pte_t *t = trans_alloc(info);
+
+			if (!t)
 				return -ENOMEM;
-		} else {
-			set_pmd(dst_pmdp,
-				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
+
+			__pmd_populate(&dst_pmdp[i], __pa(t), PTE_TYPE_PAGE);
+			dst_pmd = READ_ONCE(dst_pmdp[i]);
 		}
-	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
+
+		src_ptep = __va(pmd_page_paddr(src_pmd));
+		dst_ptep = __va(pmd_page_paddr(dst_pmd));
+
+		rc = trans_table_copy_pte(info, dst_ptep, src_ptep, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PMD);
 
 	return 0;
 }
 
-static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
-		    unsigned long end)
+static int trans_table_copy_pud(struct trans_table_info *info, pud_t *dst_pudp,
+				pud_t *src_pudp, unsigned long start,
+				unsigned long end)
 {
-	pud_t *dst_pudp;
-	pud_t *src_pudp;
 	unsigned long next;
 	unsigned long addr = start;
+	int i = pud_index(addr);
+	int rc;
 
-	if (pgd_none(READ_ONCE(*dst_pgdp))) {
-		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pudp)
-			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
-	}
-	dst_pudp = pud_offset(dst_pgdp, start);
-
-	src_pudp = pud_offset(src_pgdp, start);
 	do {
-		pud_t pud = READ_ONCE(*src_pudp);
+		pud_t src_pud = READ_ONCE(src_pudp[i]);
+		pud_t dst_pud = READ_ONCE(dst_pudp[i]);
+		pmd_t *dst_pmdp, *src_pmdp;
 
 		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
+		if (pud_none(src_pud))
 			continue;
-		if (pud_table(pud)) {
-			if (copy_pmd(dst_pudp, src_pudp, addr, next))
+
+		if (!pud_table(src_pud)) {
+			if (info->trans_flags & TRANS_MKWRITE)
+				pud_val(src_pud) &= ~PUD_SECT_RDONLY;
+			set_pud(&dst_pudp[i], src_pud);
+			continue;
+		}
+
+		if (pud_none(dst_pud)) {
+			pmd_t *t = trans_alloc(info);
+
+			if (!t)
 				return -ENOMEM;
-		} else {
-			set_pud(dst_pudp,
-				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
+
+			__pud_populate(&dst_pudp[i], __pa(t), PMD_TYPE_TABLE);
+			dst_pud = READ_ONCE(dst_pudp[i]);
 		}
-	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
+
+		src_pmdp = __va(pud_page_paddr(src_pud));
+		dst_pmdp = __va(pud_page_paddr(dst_pud));
+
+		rc = trans_table_copy_pmd(info, dst_pmdp, src_pmdp, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PUD);
 
 	return 0;
 }
 
-static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
-			    unsigned long end)
+static int trans_table_copy_pgd(struct trans_table_info *info, pgd_t *dst_pgdp,
+				pgd_t *src_pgdp, unsigned long start,
+				unsigned long end)
 {
 	unsigned long next;
 	unsigned long addr = start;
-	pgd_t *src_pgdp = pgd_offset_k(start);
+	int i = pgd_index(addr);
+	int rc;
 
-	dst_pgdp = pgd_offset_raw(dst_pgdp, start);
 	do {
+		pgd_t src_pgd;
+		pgd_t dst_pgd;
+		pud_t *dst_pudp, *src_pudp;
+
+		src_pgd = READ_ONCE(src_pgdp[i]);
+		dst_pgd = READ_ONCE(dst_pgdp[i]);
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(READ_ONCE(*src_pgdp)))
+		if (pgd_none(src_pgd))
 			continue;
-		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
-			return -ENOMEM;
-	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
+
+		if (pgd_none(dst_pgd)) {
+			pud_t *t = trans_alloc(info);
+
+			if (!t)
+				return -ENOMEM;
+
+			__pgd_populate(&dst_pgdp[i], __pa(t), PUD_TYPE_TABLE);
+			dst_pgd = READ_ONCE(dst_pgdp[i]);
+		}
+
+		src_pudp = __va(pgd_page_paddr(src_pgd));
+		dst_pudp = __va(pgd_page_paddr(dst_pgd));
+
+		rc = trans_table_copy_pud(info, dst_pudp, src_pudp, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PGD);
 
 	return 0;
 }
@@ -186,7 +208,7 @@ int trans_table_create_copy(struct trans_table_info *info, pgd_t **trans_table,
 	if (rc)
 		return rc;
 
-	return copy_page_tables(*trans_table, start, end);
+	return trans_table_copy_pgd(info, *trans_table, from_table, start, end);
 }
 
 int trans_table_map_page(struct trans_table_info *info, pgd_t *trans_table,
-- 
2.22.1


WARNING: multiple messages have this Message-ID (diff)
From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: pasha.tatashin@soleen.com, jmorris@namei.org, sashal@kernel.org,
	ebiederm@xmission.com, kexec@lists.infradead.org,
	linux-kernel@vger.kernel.org, corbet@lwn.net,
	catalin.marinas@arm.com, will@kernel.org,
	linux-arm-kernel@lists.infradead.org, marc.zyngier@arm.com,
	james.morse@arm.com, vladimir.murzin@arm.com,
	matthias.bgg@gmail.com, bhsharma@redhat.com, linux-mm@kvack.org
Subject: [PATCH v2 09/14] arm64, trans_table: complete generalization of trans_tables
Date: Fri, 16 Aug 2019 22:46:24 -0400	[thread overview]
Message-ID: <20190817024629.26611-10-pasha.tatashin@soleen.com> (raw)
In-Reply-To: <20190817024629.26611-1-pasha.tatashin@soleen.com>

Make the last private functions in page table copy path generlized for use
outside of hibernate.

Switch to use the provided allocator, flags, and source page table. Also,
unify all copy function implementations to reduce the possibility of bugs.
All page table levels are implemented symmetrically.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/mm/trans_table.c | 204 ++++++++++++++++++++----------------
 1 file changed, 113 insertions(+), 91 deletions(-)

diff --git a/arch/arm64/mm/trans_table.c b/arch/arm64/mm/trans_table.c
index 815e40bb1316..ce0f24806eaa 100644
--- a/arch/arm64/mm/trans_table.c
+++ b/arch/arm64/mm/trans_table.c
@@ -27,139 +27,161 @@ static void *trans_alloc(struct trans_table_info *info)
 	return page;
 }
 
-static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
+static int trans_table_copy_pte(struct trans_table_info *info, pte_t *dst_ptep,
+				pte_t *src_ptep, unsigned long start,
+				unsigned long end)
 {
-	pte_t pte = READ_ONCE(*src_ptep);
-
-	if (pte_valid(pte)) {
-		/*
-		 * Resume will overwrite areas that may be marked
-		 * read only (code, rodata). Clear the RDONLY bit from
-		 * the temporary mappings we use during restore.
-		 */
-		set_pte(dst_ptep, pte_mkwrite(pte));
-	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
-		/*
-		 * debug_pagealloc will removed the PTE_VALID bit if
-		 * the page isn't in use by the resume kernel. It may have
-		 * been in use by the original kernel, in which case we need
-		 * to put it back in our copy to do the restore.
-		 *
-		 * Before marking this entry valid, check the pfn should
-		 * be mapped.
-		 */
-		BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
-	}
-}
-
-static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
-		    unsigned long end)
-{
-	pte_t *src_ptep;
-	pte_t *dst_ptep;
 	unsigned long addr = start;
+	int i = pte_index(addr);
 
-	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
-	if (!dst_ptep)
-		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
-	dst_ptep = pte_offset_kernel(dst_pmdp, start);
-
-	src_ptep = pte_offset_kernel(src_pmdp, start);
 	do {
-		_copy_pte(dst_ptep, src_ptep, addr);
-	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
+		pte_t src_pte = READ_ONCE(src_ptep[i]);
+
+		if (pte_none(src_pte))
+			continue;
+		if (info->trans_flags & TRANS_MKWRITE)
+			src_pte = pte_mkwrite(src_pte);
+		if (info->trans_flags & TRANS_MKVALID)
+			src_pte = pte_mkpresent(src_pte);
+		if (info->trans_flags & TRANS_CHECKPFN) {
+			if (!pfn_valid(pte_pfn(src_pte)))
+				return -ENXIO;
+		}
+		set_pte(&dst_ptep[i], src_pte);
+	} while (addr += PAGE_SIZE, i++, addr != end && i < PTRS_PER_PTE);
 
 	return 0;
 }
 
-static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
-		    unsigned long end)
+static int trans_table_copy_pmd(struct trans_table_info *info, pmd_t *dst_pmdp,
+				pmd_t *src_pmdp, unsigned long start,
+				unsigned long end)
 {
-	pmd_t *src_pmdp;
-	pmd_t *dst_pmdp;
 	unsigned long next;
 	unsigned long addr = start;
+	int i = pmd_index(addr);
+	int rc;
 
-	if (pud_none(READ_ONCE(*dst_pudp))) {
-		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pmdp)
-			return -ENOMEM;
-		pud_populate(&init_mm, dst_pudp, dst_pmdp);
-	}
-	dst_pmdp = pmd_offset(dst_pudp, start);
-
-	src_pmdp = pmd_offset(src_pudp, start);
 	do {
-		pmd_t pmd = READ_ONCE(*src_pmdp);
+		pmd_t src_pmd = READ_ONCE(src_pmdp[i]);
+		pmd_t dst_pmd = READ_ONCE(dst_pmdp[i]);
+		pte_t *dst_ptep, *src_ptep;
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		if (pmd_none(src_pmd))
+			continue;
+
+		if (!pmd_table(src_pmd)) {
+			if (info->trans_flags & TRANS_MKWRITE)
+				pmd_val(src_pmd) &= ~PMD_SECT_RDONLY;
+			set_pmd(&dst_pmdp[i], src_pmd);
 			continue;
-		if (pmd_table(pmd)) {
-			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
+		}
+
+		if (pmd_none(dst_pmd)) {
+			pte_t *t = trans_alloc(info);
+
+			if (!t)
 				return -ENOMEM;
-		} else {
-			set_pmd(dst_pmdp,
-				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
+
+			__pmd_populate(&dst_pmdp[i], __pa(t), PTE_TYPE_PAGE);
+			dst_pmd = READ_ONCE(dst_pmdp[i]);
 		}
-	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
+
+		src_ptep = __va(pmd_page_paddr(src_pmd));
+		dst_ptep = __va(pmd_page_paddr(dst_pmd));
+
+		rc = trans_table_copy_pte(info, dst_ptep, src_ptep, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PMD);
 
 	return 0;
 }
 
-static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
-		    unsigned long end)
+static int trans_table_copy_pud(struct trans_table_info *info, pud_t *dst_pudp,
+				pud_t *src_pudp, unsigned long start,
+				unsigned long end)
 {
-	pud_t *dst_pudp;
-	pud_t *src_pudp;
 	unsigned long next;
 	unsigned long addr = start;
+	int i = pud_index(addr);
+	int rc;
 
-	if (pgd_none(READ_ONCE(*dst_pgdp))) {
-		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pudp)
-			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
-	}
-	dst_pudp = pud_offset(dst_pgdp, start);
-
-	src_pudp = pud_offset(src_pgdp, start);
 	do {
-		pud_t pud = READ_ONCE(*src_pudp);
+		pud_t src_pud = READ_ONCE(src_pudp[i]);
+		pud_t dst_pud = READ_ONCE(dst_pudp[i]);
+		pmd_t *dst_pmdp, *src_pmdp;
 
 		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
+		if (pud_none(src_pud))
 			continue;
-		if (pud_table(pud)) {
-			if (copy_pmd(dst_pudp, src_pudp, addr, next))
+
+		if (!pud_table(src_pud)) {
+			if (info->trans_flags & TRANS_MKWRITE)
+				pud_val(src_pud) &= ~PUD_SECT_RDONLY;
+			set_pud(&dst_pudp[i], src_pud);
+			continue;
+		}
+
+		if (pud_none(dst_pud)) {
+			pmd_t *t = trans_alloc(info);
+
+			if (!t)
 				return -ENOMEM;
-		} else {
-			set_pud(dst_pudp,
-				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
+
+			__pud_populate(&dst_pudp[i], __pa(t), PMD_TYPE_TABLE);
+			dst_pud = READ_ONCE(dst_pudp[i]);
 		}
-	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
+
+		src_pmdp = __va(pud_page_paddr(src_pud));
+		dst_pmdp = __va(pud_page_paddr(dst_pud));
+
+		rc = trans_table_copy_pmd(info, dst_pmdp, src_pmdp, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PUD);
 
 	return 0;
 }
 
-static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
-			    unsigned long end)
+static int trans_table_copy_pgd(struct trans_table_info *info, pgd_t *dst_pgdp,
+				pgd_t *src_pgdp, unsigned long start,
+				unsigned long end)
 {
 	unsigned long next;
 	unsigned long addr = start;
-	pgd_t *src_pgdp = pgd_offset_k(start);
+	int i = pgd_index(addr);
+	int rc;
 
-	dst_pgdp = pgd_offset_raw(dst_pgdp, start);
 	do {
+		pgd_t src_pgd;
+		pgd_t dst_pgd;
+		pud_t *dst_pudp, *src_pudp;
+
+		src_pgd = READ_ONCE(src_pgdp[i]);
+		dst_pgd = READ_ONCE(dst_pgdp[i]);
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(READ_ONCE(*src_pgdp)))
+		if (pgd_none(src_pgd))
 			continue;
-		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
-			return -ENOMEM;
-	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
+
+		if (pgd_none(dst_pgd)) {
+			pud_t *t = trans_alloc(info);
+
+			if (!t)
+				return -ENOMEM;
+
+			__pgd_populate(&dst_pgdp[i], __pa(t), PUD_TYPE_TABLE);
+			dst_pgd = READ_ONCE(dst_pgdp[i]);
+		}
+
+		src_pudp = __va(pgd_page_paddr(src_pgd));
+		dst_pudp = __va(pgd_page_paddr(dst_pgd));
+
+		rc = trans_table_copy_pud(info, dst_pudp, src_pudp, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PGD);
 
 	return 0;
 }
@@ -186,7 +208,7 @@ int trans_table_create_copy(struct trans_table_info *info, pgd_t **trans_table,
 	if (rc)
 		return rc;
 
-	return copy_page_tables(*trans_table, start, end);
+	return trans_table_copy_pgd(info, *trans_table, from_table, start, end);
 }
 
 int trans_table_map_page(struct trans_table_info *info, pgd_t *trans_table,
-- 
2.22.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

WARNING: multiple messages have this Message-ID (diff)
From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: pasha.tatashin@soleen.com, jmorris@namei.org, sashal@kernel.org,
	ebiederm@xmission.com, kexec@lists.infradead.org,
	linux-kernel@vger.kernel.org, corbet@lwn.net,
	catalin.marinas@arm.com, will@kernel.org,
	linux-arm-kernel@lists.infradead.org, marc.zyngier@arm.com,
	james.morse@arm.com, vladimir.murzin@arm.com,
	matthias.bgg@gmail.com, bhsharma@redhat.com, linux-mm@kvack.org
Subject: [PATCH v2 09/14] arm64, trans_table: complete generalization of trans_tables
Date: Fri, 16 Aug 2019 22:46:24 -0400	[thread overview]
Message-ID: <20190817024629.26611-10-pasha.tatashin@soleen.com> (raw)
In-Reply-To: <20190817024629.26611-1-pasha.tatashin@soleen.com>

Make the last private functions in page table copy path generlized for use
outside of hibernate.

Switch to use the provided allocator, flags, and source page table. Also,
unify all copy function implementations to reduce the possibility of bugs.
All page table levels are implemented symmetrically.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
---
 arch/arm64/mm/trans_table.c | 204 ++++++++++++++++++++----------------
 1 file changed, 113 insertions(+), 91 deletions(-)

diff --git a/arch/arm64/mm/trans_table.c b/arch/arm64/mm/trans_table.c
index 815e40bb1316..ce0f24806eaa 100644
--- a/arch/arm64/mm/trans_table.c
+++ b/arch/arm64/mm/trans_table.c
@@ -27,139 +27,161 @@ static void *trans_alloc(struct trans_table_info *info)
 	return page;
 }
 
-static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
+static int trans_table_copy_pte(struct trans_table_info *info, pte_t *dst_ptep,
+				pte_t *src_ptep, unsigned long start,
+				unsigned long end)
 {
-	pte_t pte = READ_ONCE(*src_ptep);
-
-	if (pte_valid(pte)) {
-		/*
-		 * Resume will overwrite areas that may be marked
-		 * read only (code, rodata). Clear the RDONLY bit from
-		 * the temporary mappings we use during restore.
-		 */
-		set_pte(dst_ptep, pte_mkwrite(pte));
-	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
-		/*
-		 * debug_pagealloc will removed the PTE_VALID bit if
-		 * the page isn't in use by the resume kernel. It may have
-		 * been in use by the original kernel, in which case we need
-		 * to put it back in our copy to do the restore.
-		 *
-		 * Before marking this entry valid, check the pfn should
-		 * be mapped.
-		 */
-		BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
-	}
-}
-
-static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
-		    unsigned long end)
-{
-	pte_t *src_ptep;
-	pte_t *dst_ptep;
 	unsigned long addr = start;
+	int i = pte_index(addr);
 
-	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
-	if (!dst_ptep)
-		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
-	dst_ptep = pte_offset_kernel(dst_pmdp, start);
-
-	src_ptep = pte_offset_kernel(src_pmdp, start);
 	do {
-		_copy_pte(dst_ptep, src_ptep, addr);
-	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
+		pte_t src_pte = READ_ONCE(src_ptep[i]);
+
+		if (pte_none(src_pte))
+			continue;
+		if (info->trans_flags & TRANS_MKWRITE)
+			src_pte = pte_mkwrite(src_pte);
+		if (info->trans_flags & TRANS_MKVALID)
+			src_pte = pte_mkpresent(src_pte);
+		if (info->trans_flags & TRANS_CHECKPFN) {
+			if (!pfn_valid(pte_pfn(src_pte)))
+				return -ENXIO;
+		}
+		set_pte(&dst_ptep[i], src_pte);
+	} while (addr += PAGE_SIZE, i++, addr != end && i < PTRS_PER_PTE);
 
 	return 0;
 }
 
-static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
-		    unsigned long end)
+static int trans_table_copy_pmd(struct trans_table_info *info, pmd_t *dst_pmdp,
+				pmd_t *src_pmdp, unsigned long start,
+				unsigned long end)
 {
-	pmd_t *src_pmdp;
-	pmd_t *dst_pmdp;
 	unsigned long next;
 	unsigned long addr = start;
+	int i = pmd_index(addr);
+	int rc;
 
-	if (pud_none(READ_ONCE(*dst_pudp))) {
-		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pmdp)
-			return -ENOMEM;
-		pud_populate(&init_mm, dst_pudp, dst_pmdp);
-	}
-	dst_pmdp = pmd_offset(dst_pudp, start);
-
-	src_pmdp = pmd_offset(src_pudp, start);
 	do {
-		pmd_t pmd = READ_ONCE(*src_pmdp);
+		pmd_t src_pmd = READ_ONCE(src_pmdp[i]);
+		pmd_t dst_pmd = READ_ONCE(dst_pmdp[i]);
+		pte_t *dst_ptep, *src_ptep;
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		if (pmd_none(src_pmd))
+			continue;
+
+		if (!pmd_table(src_pmd)) {
+			if (info->trans_flags & TRANS_MKWRITE)
+				pmd_val(src_pmd) &= ~PMD_SECT_RDONLY;
+			set_pmd(&dst_pmdp[i], src_pmd);
 			continue;
-		if (pmd_table(pmd)) {
-			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
+		}
+
+		if (pmd_none(dst_pmd)) {
+			pte_t *t = trans_alloc(info);
+
+			if (!t)
 				return -ENOMEM;
-		} else {
-			set_pmd(dst_pmdp,
-				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
+
+			__pmd_populate(&dst_pmdp[i], __pa(t), PTE_TYPE_PAGE);
+			dst_pmd = READ_ONCE(dst_pmdp[i]);
 		}
-	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
+
+		src_ptep = __va(pmd_page_paddr(src_pmd));
+		dst_ptep = __va(pmd_page_paddr(dst_pmd));
+
+		rc = trans_table_copy_pte(info, dst_ptep, src_ptep, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PMD);
 
 	return 0;
 }
 
-static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
-		    unsigned long end)
+static int trans_table_copy_pud(struct trans_table_info *info, pud_t *dst_pudp,
+				pud_t *src_pudp, unsigned long start,
+				unsigned long end)
 {
-	pud_t *dst_pudp;
-	pud_t *src_pudp;
 	unsigned long next;
 	unsigned long addr = start;
+	int i = pud_index(addr);
+	int rc;
 
-	if (pgd_none(READ_ONCE(*dst_pgdp))) {
-		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pudp)
-			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
-	}
-	dst_pudp = pud_offset(dst_pgdp, start);
-
-	src_pudp = pud_offset(src_pgdp, start);
 	do {
-		pud_t pud = READ_ONCE(*src_pudp);
+		pud_t src_pud = READ_ONCE(src_pudp[i]);
+		pud_t dst_pud = READ_ONCE(dst_pudp[i]);
+		pmd_t *dst_pmdp, *src_pmdp;
 
 		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
+		if (pud_none(src_pud))
 			continue;
-		if (pud_table(pud)) {
-			if (copy_pmd(dst_pudp, src_pudp, addr, next))
+
+		if (!pud_table(src_pud)) {
+			if (info->trans_flags & TRANS_MKWRITE)
+				pud_val(src_pud) &= ~PUD_SECT_RDONLY;
+			set_pud(&dst_pudp[i], src_pud);
+			continue;
+		}
+
+		if (pud_none(dst_pud)) {
+			pmd_t *t = trans_alloc(info);
+
+			if (!t)
 				return -ENOMEM;
-		} else {
-			set_pud(dst_pudp,
-				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
+
+			__pud_populate(&dst_pudp[i], __pa(t), PMD_TYPE_TABLE);
+			dst_pud = READ_ONCE(dst_pudp[i]);
 		}
-	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
+
+		src_pmdp = __va(pud_page_paddr(src_pud));
+		dst_pmdp = __va(pud_page_paddr(dst_pud));
+
+		rc = trans_table_copy_pmd(info, dst_pmdp, src_pmdp, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PUD);
 
 	return 0;
 }
 
-static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
-			    unsigned long end)
+static int trans_table_copy_pgd(struct trans_table_info *info, pgd_t *dst_pgdp,
+				pgd_t *src_pgdp, unsigned long start,
+				unsigned long end)
 {
 	unsigned long next;
 	unsigned long addr = start;
-	pgd_t *src_pgdp = pgd_offset_k(start);
+	int i = pgd_index(addr);
+	int rc;
 
-	dst_pgdp = pgd_offset_raw(dst_pgdp, start);
 	do {
+		pgd_t src_pgd;
+		pgd_t dst_pgd;
+		pud_t *dst_pudp, *src_pudp;
+
+		src_pgd = READ_ONCE(src_pgdp[i]);
+		dst_pgd = READ_ONCE(dst_pgdp[i]);
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(READ_ONCE(*src_pgdp)))
+		if (pgd_none(src_pgd))
 			continue;
-		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
-			return -ENOMEM;
-	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
+
+		if (pgd_none(dst_pgd)) {
+			pud_t *t = trans_alloc(info);
+
+			if (!t)
+				return -ENOMEM;
+
+			__pgd_populate(&dst_pgdp[i], __pa(t), PUD_TYPE_TABLE);
+			dst_pgd = READ_ONCE(dst_pgdp[i]);
+		}
+
+		src_pudp = __va(pgd_page_paddr(src_pgd));
+		dst_pudp = __va(pgd_page_paddr(dst_pgd));
+
+		rc = trans_table_copy_pud(info, dst_pudp, src_pudp, addr, next);
+		if (rc)
+			return rc;
+	} while (addr = next, i++, addr != end && i < PTRS_PER_PGD);
 
 	return 0;
 }
@@ -186,7 +208,7 @@ int trans_table_create_copy(struct trans_table_info *info, pgd_t **trans_table,
 	if (rc)
 		return rc;
 
-	return copy_page_tables(*trans_table, start, end);
+	return trans_table_copy_pgd(info, *trans_table, from_table, start, end);
 }
 
 int trans_table_map_page(struct trans_table_info *info, pgd_t *trans_table,
-- 
2.22.1


_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

  parent reply	other threads:[~2019-08-17  2:47 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-17  2:46 [PATCH v2 00/14] arm64: MMU enabled kexec relocation Pavel Tatashin
2019-08-17  2:46 ` Pavel Tatashin
2019-08-17  2:46 ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 01/14] kexec: quiet down kexec reboot Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 02/14] arm64, hibernate: create_safe_exec_page cleanup Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-19 15:50   ` Mark Rutland
2019-08-19 15:50     ` Mark Rutland
2019-08-19 15:50     ` Mark Rutland
2019-08-19 16:25     ` Pavel Tatashin
2019-08-19 16:25       ` Pavel Tatashin
2019-08-19 16:25       ` Pavel Tatashin
2019-08-19 16:25       ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 03/14] arm64, hibernate: add trans_table public functions Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-19 15:58   ` Mark Rutland
2019-08-19 15:58     ` Mark Rutland
2019-08-19 15:58     ` Mark Rutland
2019-08-19 16:33     ` Pavel Tatashin
2019-08-19 16:33       ` Pavel Tatashin
2019-08-19 16:33       ` Pavel Tatashin
2019-08-19 16:33       ` Pavel Tatashin
2019-08-20 11:30       ` Mark Rutland
2019-08-20 11:30         ` Mark Rutland
2019-08-20 11:30         ` Mark Rutland
2019-08-20 11:41         ` Pavel Tatashin
2019-08-20 11:41           ` Pavel Tatashin
2019-08-20 11:41           ` Pavel Tatashin
2019-08-20 11:41           ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 04/14] arm64, hibernate: move page handling function to new trans_table.c Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 05/14] arm64, trans_table: make trans_table_map_page generic Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 06/14] arm64, trans_table: add trans_table_create_empty Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 07/14] arm64, trans_table: adjust trans_table_create_copy interface Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 08/14] arm64, trans_table: add PUD_SECT_RDONLY Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` Pavel Tatashin [this message]
2019-08-17  2:46   ` [PATCH v2 09/14] arm64, trans_table: complete generalization of trans_tables Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 10/14] kexec: add machine_kexec_post_load() Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 11/14] arm64, kexec: move relocation function setup and clean up Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 12/14] arm64, kexec: add expandable argument to relocation function Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 13/14] arm64, kexec: configure transitional page table for kexec Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46 ` [PATCH v2 14/14] arm64, kexec: enable MMU during kexec relocation Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin
2019-08-17  2:46   ` Pavel Tatashin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190817024629.26611-10-pasha.tatashin@soleen.com \
    --to=pasha.tatashin@soleen.com \
    --cc=bhsharma@redhat.com \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=ebiederm@xmission.com \
    --cc=james.morse@arm.com \
    --cc=jmorris@namei.org \
    --cc=kexec@lists.infradead.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=marc.zyngier@arm.com \
    --cc=matthias.bgg@gmail.com \
    --cc=sashal@kernel.org \
    --cc=vladimir.murzin@arm.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.