arm64: hibernate: move page handling function to new trans_pgd.c

Now, that we abstracted the required functions move them to a new home.
Later, we will generalize these function in order to be useful outside
of hibernation.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: James Morse <james.morse@arm.com>
Link: https://lore.kernel.org/r/20210125191923.1060122-4-pasha.tatashin@soleen.com
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 250 insertions, 0 deletions

diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
new file mode 100644
index 000000000000..e048d1f5c912
--- /dev/null
+++ b/arch/arm64/mm/trans_pgd.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Transitional page tables for kexec and hibernate
+ *
+ * This file derived from: arch/arm64/kernel/hibernate.c
+ *
+ * Copyright (c) 2020, Microsoft Corporation.
+ * Pavel Tatashin <pasha.tatashin@soleen.com>
+ *
+ */
+
+/*
+ * Transitional tables are used during system transferring from one world to
+ * another: such as during hibernate restore, and kexec reboots. During these
+ * phases one cannot rely on page table not being overwritten. This is because
+ * hibernate and kexec can overwrite the current page tables during transition.
+ */
+
+#include <asm/trans_pgd.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <linux/suspend.h>
+#include <linux/bug.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+
+static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
+{
+	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;
+
+	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);
+
+	return 0;
+}
+
+static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
+		    unsigned long end)
+{
+	pmd_t *src_pmdp;
+	pmd_t *dst_pmdp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	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);
+
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(pmd))
+			continue;
+		if (pmd_table(pmd)) {
+			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pmd(dst_pmdp,
+				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
+		}
+	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_pud(p4d_t *dst_p4dp, p4d_t *src_p4dp, unsigned long start,
+		    unsigned long end)
+{
+	pud_t *dst_pudp;
+	pud_t *src_pudp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	if (p4d_none(READ_ONCE(*dst_p4dp))) {
+		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pudp)
+			return -ENOMEM;
+		p4d_populate(&init_mm, dst_p4dp, dst_pudp);
+	}
+	dst_pudp = pud_offset(dst_p4dp, start);
+
+	src_pudp = pud_offset(src_p4dp, start);
+	do {
+		pud_t pud = READ_ONCE(*src_pudp);
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			continue;
+		if (pud_table(pud)) {
+			if (copy_pmd(dst_pudp, src_pudp, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pud(dst_pudp,
+				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
+		}
+	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_p4d(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
+		    unsigned long end)
+{
+	p4d_t *dst_p4dp;
+	p4d_t *src_p4dp;
+	unsigned long next;
+	unsigned long addr = start;
+
+	dst_p4dp = p4d_offset(dst_pgdp, start);
+	src_p4dp = p4d_offset(src_pgdp, start);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(READ_ONCE(*src_p4dp)))
+			continue;
+		if (copy_pud(dst_p4dp, src_p4dp, addr, next))
+			return -ENOMEM;
+	} while (dst_p4dp++, src_p4dp++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
+			    unsigned long end)
+{
+	unsigned long next;
+	unsigned long addr = start;
+	pgd_t *src_pgdp = pgd_offset_k(start);
+
+	dst_pgdp = pgd_offset_pgd(dst_pgdp, start);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(READ_ONCE(*src_pgdp)))
+			continue;
+		if (copy_p4d(dst_pgdp, src_pgdp, addr, next))
+			return -ENOMEM;
+	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
+
+	return 0;
+}
+
+int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
+			  unsigned long end)
+{
+	int rc;
+	pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
+
+	if (!trans_pgd) {
+		pr_err("Failed to allocate memory for temporary page tables.\n");
+		return -ENOMEM;
+	}
+
+	rc = copy_page_tables(trans_pgd, start, end);
+	if (!rc)
+		*dst_pgdp = trans_pgd;
+
+	return rc;
+}
+
+int trans_pgd_map_page(pgd_t *trans_pgd, void *page,
+		       unsigned long dst_addr,
+		       pgprot_t pgprot)
+{
+	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	pgdp = pgd_offset_pgd(trans_pgd, dst_addr);
+	if (pgd_none(READ_ONCE(*pgdp))) {
+		p4dp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pgdp)
+			return -ENOMEM;
+		pgd_populate(&init_mm, pgdp, p4dp);
+	}
+
+	p4dp = p4d_offset(pgdp, dst_addr);
+	if (p4d_none(READ_ONCE(*p4dp))) {
+		pudp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pudp)
+			return -ENOMEM;
+		p4d_populate(&init_mm, p4dp, pudp);
+	}
+
+	pudp = pud_offset(p4dp, dst_addr);
+	if (pud_none(READ_ONCE(*pudp))) {
+		pmdp = (void *)get_safe_page(GFP_ATOMIC);
+		if (!pmdp)
+			return -ENOMEM;
+		pud_populate(&init_mm, pudp, pmdp);
+	}
+
+	pmdp = pmd_offset(pudp, dst_addr);
+	if (pmd_none(READ_ONCE(*pmdp))) {
+		ptep = (void *)get_safe_page(GFP_ATOMIC);
+		if (!ptep)
+			return -ENOMEM;
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
+	}
+
+	ptep = pte_offset_kernel(pmdp, dst_addr);
+	set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
+
+	return 0;
+}