[PATCH] x86/mm/dump_pagetables: Speed up page tables dump for CONFIG_KASAN=y

[Andrey Ryabinin]

KASAN fills kernel page tables with repeated values to map several
TBs of the virtual memory to the single kasan_zero_page:
  kasan_zero_p4d ->
    kasan_zero_pud ->
        kasan_zero_pmd->
            kasan_zero_pte->
                kasan_zero_page

Walking the whole KASAN shadow range takes a lot of time, especially
with 5-level page tables. Since we already know that all kasan page tables
eventually point to the kasan_zero_page we could call note_page()
right and avoid walking lower levels of the page tables.
This will not affect the output of the kernel_page_tables file,
but let us avoid spending time in page table walkers:

Before:
time cat /sys/kernel/debug/kernel_page_tables > /dev/null

real    0m55.855s
user    0m0.000s
sys     0m55.840s

After:
time cat /sys/kernel/debug/kernel_page_tables > /dev/null

real    0m0.054s
user    0m0.000s
sys     0m0.054s

Signed-off-by: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
---
 arch/x86/mm/dump_pagetables.c | 64 +++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 23 deletions(-)

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index b371ab68f2d4..5e3ac6fe6c9e 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -13,12 +13,12 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/kasan.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 
-#include <asm/kasan.h>
 #include <asm/pgtable.h>
 
 /*
@@ -302,23 +302,53 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
 		start++;
 	}
 }
+#ifdef CONFIG_KASAN
+
+/*
+ * This is an optimization for KASAN=y case. Since all kasan page tables
+ * eventually point to the kasan_zero_page we could call note_page()
+ * right away without walking through lower level page tables. This saves
+ * us dozens of seconds (minutes for 5-level config) while checking for
+ * W+X mapping or reading kernel_page_tables debugfs file.
+ */
+static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
+				void *pt)
+{
+	if (__pa(pt) == __pa(kasan_zero_pmd) ||
+#ifdef CONFIG_X86_5LEVEL
+	    __pa(pt) == __pa(kasan_zero_p4d) ||
+#endif
+	    __pa(pt) == __pa(kasan_zero_pud)) {
+		pgprotval_t prot = pte_flags(kasan_zero_pte[0]);
+		note_page(m, st, __pgprot(prot), 5);
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
+				void *pt)
+{
+	return false;
+}
+#endif
 
 #if PTRS_PER_PMD > 1
 
 static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P)
 {
 	int i;
-	pmd_t *start;
+	pmd_t *start, *pmd_start;
 	pgprotval_t prot;
 
-	start = (pmd_t *)pud_page_vaddr(addr);
+	pmd_start = start = (pmd_t *)pud_page_vaddr(addr);
 	for (i = 0; i < PTRS_PER_PMD; i++) {
 		st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
 		if (!pmd_none(*start)) {
 			if (pmd_large(*start) || !pmd_present(*start)) {
 				prot = pmd_flags(*start);
 				note_page(m, st, __pgprot(prot), 4);
-			} else {
+			} else if (!kasan_page_table(m, st, pmd_start)) {
 				walk_pte_level(m, st, *start,
 					       P + i * PMD_LEVEL_MULT);
 			}
@@ -336,34 +366,22 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
 
 #if PTRS_PER_PUD > 1
 
-/*
- * This is an optimization for CONFIG_DEBUG_WX=y + CONFIG_KASAN=y
- * KASAN fills page tables with the same values. Since there is no
- * point in checking page table more than once we just skip repeated
- * entries. This saves us dozens of seconds during boot.
- */
-static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx)
-{
-	return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud));
-}
-
 static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P)
 {
 	int i;
-	pud_t *start;
+	pud_t *start, *pud_start;
 	pgprotval_t prot;
 	pud_t *prev_pud = NULL;
 
-	start = (pud_t *)p4d_page_vaddr(addr);
+	pud_start = start = (pud_t *)p4d_page_vaddr(addr);
 
 	for (i = 0; i < PTRS_PER_PUD; i++) {
 		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
-		if (!pud_none(*start) &&
-		    !pud_already_checked(prev_pud, start, st->check_wx)) {
+		if (!pud_none(*start)) {
 			if (pud_large(*start) || !pud_present(*start)) {
 				prot = pud_flags(*start);
 				note_page(m, st, __pgprot(prot), 3);
-			} else {
+			} else if (!kasan_page_table(m, st, pud_start)) {
 				walk_pmd_level(m, st, *start,
 					       P + i * PUD_LEVEL_MULT);
 			}
@@ -386,10 +404,10 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr,
 static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P)
 {
 	int i;
-	p4d_t *start;
+	p4d_t *start, *p4d_start;
 	pgprotval_t prot;
 
-	start = (p4d_t *)pgd_page_vaddr(addr);
+	p4d_start = start = (p4d_t *)pgd_page_vaddr(addr);
 
 	for (i = 0; i < PTRS_PER_P4D; i++) {
 		st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT);
@@ -397,7 +415,7 @@ static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 			if (p4d_large(*start) || !p4d_present(*start)) {
 				prot = p4d_flags(*start);
 				note_page(m, st, __pgprot(prot), 2);
-			} else {
+			} else if (!kasan_page_table(m, st, p4d_start)) {
 				walk_pud_level(m, st, *start,
 					       P + i * P4D_LEVEL_MULT);
 			}
-- 
2.13.0