[PATCH v3 08/17] arm64, trans_pgd: make trans_pgd_map_page generic

From: Pavel Tatashin
Date: Wed Aug 21 2019 - 14:32:23 EST


Currently, trans_pgd_map_page has assumptions that are relevant to
hibernate. But, to make it generic we must allow it to use any allocator
and also, can't assume that entries do not exist in the page table
already. Also, we can't use init_mm here.

Also, add "flags" for trans_pgd_info, they are going to be used
in copy functions once they are generalized.

Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
---
arch/arm64/include/asm/trans_pgd.h | 39 +++++++++++++-
arch/arm64/kernel/hibernate.c | 13 ++++-
arch/arm64/mm/trans_pgd.c | 82 +++++++++++++++++++++---------
3 files changed, 107 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/include/asm/trans_pgd.h b/arch/arm64/include/asm/trans_pgd.h
index c7b5402b7d87..e3d022b1b526 100644
--- a/arch/arm64/include/asm/trans_pgd.h
+++ b/arch/arm64/include/asm/trans_pgd.h
@@ -11,10 +11,45 @@
#include <linux/bits.h>
#include <asm/pgtable-types.h>

+/*
+ * trans_alloc_page
+ * - Allocator that should return exactly one uninitilaized page, if this
+ * allocator fails, trans_pgd returns -ENOMEM error.
+ *
+ * trans_alloc_arg
+ * - Passed to trans_alloc_page as an argument
+ *
+ * trans_flags
+ * - bitmap with flags that control how page table is filled.
+ * TRANS_MKWRITE: during page table copy make PTE, PME, and PUD page
+ * writeable by removing RDONLY flag from PTE.
+ * TRANS_MKVALID: during page table copy, if PTE present, but not valid,
+ * make it valid.
+ * TRANS_CHECKPFN: During page table copy, for every PTE entry check that
+ * PFN that this PTE points to is valid. Otherwise return
+ * -ENXIO
+ */
+
+#define TRANS_MKWRITE BIT(0)
+#define TRANS_MKVALID BIT(1)
+#define TRANS_CHECKPFN BIT(2)
+
+struct trans_pgd_info {
+ void * (*trans_alloc_page)(void *arg);
+ void *trans_alloc_arg;
+ unsigned long trans_flags;
+};
+
int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
unsigned long end);

-int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
- pgprot_t pgprot);
+/*
+ * Add map entry to trans_pgd for a base-size page at PTE level.
+ * page: page to be mapped.
+ * dst_addr: new VA address for the pages
+ * pgprot: protection for the page.
+ */
+int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
+ void *page, unsigned long dst_addr, pgprot_t pgprot);

#endif /* _ASM_TRANS_TABLE_H */
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 6ee81bbaa37f..17426dc8cb54 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -179,6 +179,12 @@ int arch_hibernation_header_restore(void *addr)
}
EXPORT_SYMBOL(arch_hibernation_header_restore);

+static void *
+hibernate_page_alloc(void *arg)
+{
+ return (void *)get_safe_page((gfp_t)(unsigned long)arg);
+}
+
/*
* Copies length bytes, starting at src_start into an new page,
* perform cache maintentance, then maps it at the specified address low
@@ -195,6 +201,11 @@ static int create_safe_exec_page(void *src_start, size_t length,
unsigned long dst_addr,
phys_addr_t *phys_dst_addr)
{
+ struct trans_pgd_info trans_info = {
+ .trans_alloc_page = hibernate_page_alloc,
+ .trans_alloc_arg = (void *)GFP_ATOMIC,
+ .trans_flags = 0,
+ };
void *page = (void *)get_safe_page(GFP_ATOMIC);
pgd_t *trans_pgd;
int rc;
@@ -209,7 +220,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
if (!trans_pgd)
return -ENOMEM;

- rc = trans_pgd_map_page(trans_pgd, page, dst_addr,
+ rc = trans_pgd_map_page(&trans_info, trans_pgd, page, dst_addr,
PAGE_KERNEL_EXEC);
if (rc)
return rc;
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index 00b62d8640c2..dbabccd78cc4 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -17,6 +17,16 @@
#include <asm/pgtable.h>
#include <linux/suspend.h>

+static void *trans_alloc(struct trans_pgd_info *info)
+{
+ void *page = info->trans_alloc_page(info->trans_alloc_arg);
+
+ if (page)
+ clear_page(page);
+
+ return page;
+}
+
static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
{
pte_t pte = READ_ONCE(*src_ptep);
@@ -172,40 +182,64 @@ int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start,
return rc;
}

-int trans_pgd_map_page(pgd_t *trans_pgd, void *page, unsigned long dst_addr,
- pgprot_t pgprot)
+int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
+ void *page, unsigned long dst_addr, pgprot_t pgprot)
{
- pgd_t *pgdp;
- pud_t *pudp;
- pmd_t *pmdp;
- pte_t *ptep;
-
- pgdp = pgd_offset_raw(trans_pgd, dst_addr);
- if (pgd_none(READ_ONCE(*pgdp))) {
- pudp = (void *)get_safe_page(GFP_ATOMIC);
- if (!pudp)
+ int pgd_idx = pgd_index(dst_addr);
+ int pud_idx = pud_index(dst_addr);
+ int pmd_idx = pmd_index(dst_addr);
+ int pte_idx = pte_index(dst_addr);
+ pgd_t *pgdp = trans_pgd;
+ pgd_t pgd = READ_ONCE(pgdp[pgd_idx]);
+ pud_t *pudp, pud;
+ pmd_t *pmdp, pmd;
+ pte_t *ptep, pte;
+
+ if (pgd_none(pgd)) {
+ pud_t *t = trans_alloc(info);
+
+ if (!t)
return -ENOMEM;
- pgd_populate(&init_mm, pgdp, pudp);
+
+ __pgd_populate(&pgdp[pgd_idx], __pa(t), PUD_TYPE_TABLE);
+ pgd = READ_ONCE(pgdp[pgd_idx]);
}

- pudp = pud_offset(pgdp, dst_addr);
- if (pud_none(READ_ONCE(*pudp))) {
- pmdp = (void *)get_safe_page(GFP_ATOMIC);
- if (!pmdp)
+ pudp = __va(pgd_page_paddr(pgd));
+ pud = READ_ONCE(pudp[pud_idx]);
+ if (pud_sect(pud)) {
+ return -ENXIO;
+ } else if (pud_none(pud) || pud_sect(pud)) {
+ pmd_t *t = trans_alloc(info);
+
+ if (!t)
return -ENOMEM;
- pud_populate(&init_mm, pudp, pmdp);
+
+ __pud_populate(&pudp[pud_idx], __pa(t), PMD_TYPE_TABLE);
+ pud = READ_ONCE(pudp[pud_idx]);
}

- pmdp = pmd_offset(pudp, dst_addr);
- if (pmd_none(READ_ONCE(*pmdp))) {
- ptep = (void *)get_safe_page(GFP_ATOMIC);
- if (!ptep)
+ pmdp = __va(pud_page_paddr(pud));
+ pmd = READ_ONCE(pmdp[pmd_idx]);
+ if (pmd_sect(pmd)) {
+ return -ENXIO;
+ } else if (pmd_none(pmd) || pmd_sect(pmd)) {
+ pte_t *t = trans_alloc(info);
+
+ if (!t)
return -ENOMEM;
- pmd_populate_kernel(&init_mm, pmdp, ptep);
+
+ __pmd_populate(&pmdp[pmd_idx], __pa(t), PTE_TYPE_PAGE);
+ pmd = READ_ONCE(pmdp[pmd_idx]);
}

- ptep = pte_offset_kernel(pmdp, dst_addr);
- set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC));
+ ptep = __va(pmd_page_paddr(pmd));
+ pte = READ_ONCE(ptep[pte_idx]);
+
+ if (!pte_none(pte))
+ return -ENXIO;
+
+ set_pte(&ptep[pte_idx], pfn_pte(virt_to_pfn(page), pgprot));

return 0;
}
--
2.23.0