lkml.org 
[lkml]   [2020]   [Sep]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC PATCH v2 20/30] mm: page_vma_walk: teach it about PMD-mapped PUD THP.
Date
From: Zi Yan <ziy@nvidia.com>

We now have PMD-mapped PUD THP and PTE-mapped PUD THP, page_vma_walk
should handle them properly.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
mm/page_vma_mapped.c | 152 +++++++++++++++++++++++++++++++++----------
1 file changed, 118 insertions(+), 34 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index f88e845ad5e6..5a3c1b561ff5 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -7,6 +7,12 @@

#include "internal.h"

+enum check_pmd_result {
+ PVM_NOT_MAPPED = 0,
+ PVM_LEAF_ENTRY,
+ PVM_NONLEAF_ENTRY,
+};
+
static inline bool not_found(struct page_vma_mapped_walk *pvmw)
{
page_vma_mapped_walk_done(pvmw);
@@ -52,6 +58,22 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
return true;
}

+static bool map_pmd(struct page_vma_mapped_walk *pvmw)
+{
+ pmd_t pmde;
+
+ pvmw->pmd = pmd_offset(pvmw->pud, pvmw->address);
+ pmde = READ_ONCE(*pvmw->pmd);
+ if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
+ pvmw->ptl = pmd_lock(pvmw->vma->vm_mm, pvmw->pmd);
+ return true;
+ } else if (!pmd_present(pmde))
+ return false;
+
+ pvmw->ptl = pmd_lock(pvmw->vma->vm_mm, pvmw->pmd);
+ return true;
+}
+
static inline bool pfn_is_match(struct page *page, unsigned long pfn)
{
unsigned long page_pfn = page_to_pfn(page);
@@ -115,6 +137,57 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
return pfn_is_match(pvmw->page, pfn);
}

+/**
+ * check_pmd - check if @pvmw->page is mapped at the @pvmw->pmd
+ *
+ * page_vma_mapped_walk() found a place where @pvmw->page is *potentially*
+ * mapped. check_pmd() has to validate this.
+ *
+ * @pvmw->pmd may point to empty PMD, migraiton PMD, PMD pointing to arbitrary
+ * huge page, or PMD pointing to a PTE page table page.
+ *
+ * If PVMW_MIGRATION flag is set, returns PVM_LEAF_ENTRY if @pvmw->pmd contains
+ * migration entry that points to @pvmw->page.
+ *
+ * If PVMW_MIGRATION flag is not set, returns PVM_LEAF_ENTRY if @pvmw->pmd
+ * points to @pvmw->page.
+ *
+ * If @pvmw->pmd points to a PTE page table page, returns PVM_NONLEAF_ENTRY.
+ *
+ * Otherwise, return PVM_NOT_MAPPED.
+ *
+ */
+static enum check_pmd_result check_pmd(struct page_vma_mapped_walk *pvmw)
+{
+ unsigned long pfn;
+
+ if (likely(pmd_trans_huge(*pvmw->pmd))) {
+ if (pvmw->flags & PVMW_MIGRATION)
+ return 0;
+ pfn = pmd_pfn(*pvmw->pmd);
+ if (!pfn_is_match(pvmw->page, pfn))
+ return PVM_NOT_MAPPED;
+ return PVM_LEAF_ENTRY;
+ } else if (!pmd_present(*pvmw->pmd)) {
+ if (thp_migration_supported()) {
+ if (!(pvmw->flags & PVMW_MIGRATION))
+ return 0;
+ if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
+ swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
+
+ pfn = migration_entry_to_pfn(entry);
+ if (!pfn_is_match(pvmw->page, pfn))
+ return PVM_NOT_MAPPED;
+ return PVM_LEAF_ENTRY;
+ }
+ }
+ return 0;
+ }
+ /* THP pmd was split under us: handle on pte level */
+ spin_unlock(pvmw->ptl);
+ pvmw->ptl = NULL;
+ return PVM_NONLEAF_ENTRY;
+}
/**
* page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at
* @pvmw->address
@@ -146,14 +219,14 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
pgd_t *pgd;
p4d_t *p4d;
pud_t pude;
- pmd_t pmde;
+ enum check_pmd_result pmd_check_res;

if (!pvmw->pte && !pvmw->pmd && pvmw->pud)
return not_found(pvmw);

/* The only possible pmd mapping has been handled on last iteration */
if (pvmw->pmd && !pvmw->pte)
- return not_found(pvmw);
+ goto next_pmd;

if (pvmw->pte)
goto next_pte;
@@ -202,42 +275,47 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
} else if (!pud_present(pude))
return false;

- pvmw->pmd = pmd_offset(pvmw->pud, pvmw->address);
- /*
- * Make sure the pmd value isn't cached in a register by the
- * compiler and used as a stale value after we've observed a
- * subsequent update.
- */
- pmde = READ_ONCE(*pvmw->pmd);
- if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
- pvmw->ptl = pmd_lock(mm, pvmw->pmd);
- if (likely(pmd_trans_huge(*pvmw->pmd))) {
- if (pvmw->flags & PVMW_MIGRATION)
- return not_found(pvmw);
- if (pmd_page(*pvmw->pmd) != page)
- return not_found(pvmw);
+ if (!map_pmd(pvmw))
+ goto next_pmd;
+ /* pmd locked after map_pmd */
+ while (1) {
+ pmd_check_res = check_pmd(pvmw);
+ if (pmd_check_res == PVM_LEAF_ENTRY)
return true;
- } else if (!pmd_present(*pvmw->pmd)) {
- if (thp_migration_supported()) {
- if (!(pvmw->flags & PVMW_MIGRATION))
- return not_found(pvmw);
- if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
- swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
-
- if (migration_entry_to_page(entry) != page)
- return not_found(pvmw);
- return true;
+ else if (pmd_check_res == PVM_NONLEAF_ENTRY)
+ goto pte_level;
+next_pmd:
+ /* Only PMD-mapped PUD THP has next pmd. */
+ if (!(PageTransHuge(pvmw->page) && compound_order(pvmw->page) == HPAGE_PUD_ORDER))
+ return not_found(pvmw);
+ do {
+ pvmw->address += HPAGE_PMD_SIZE;
+ if (pvmw->address >= pvmw->vma->vm_end ||
+ pvmw->address >=
+ __vma_address(pvmw->page, pvmw->vma) +
+ thp_nr_pages(pvmw->page) * PAGE_SIZE)
+ return not_found(pvmw);
+ /* Did we cross page table boundary? */
+ if (pvmw->address % PUD_SIZE == 0) {
+ /*
+ * Reset pmd here, so we will no stay at PMD
+ * level after restart.
+ */
+ pvmw->pmd = NULL;
+ if (pvmw->ptl) {
+ spin_unlock(pvmw->ptl);
+ pvmw->ptl = NULL;
}
+ goto restart;
+ } else {
+ pvmw->pmd++;
}
- return not_found(pvmw);
- } else {
- /* THP pmd was split under us: handle on pte level */
- spin_unlock(pvmw->ptl);
- pvmw->ptl = NULL;
- }
- } else if (!pmd_present(pmde)) {
- return false;
+ } while (pmd_none(*pvmw->pmd));
+
+ if (!pvmw->ptl)
+ pvmw->ptl = pmd_lock(mm, pvmw->pmd);
}
+pte_level:
if (!map_pte(pvmw))
goto next_pte;
while (1) {
@@ -257,6 +335,12 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
/* Did we cross page table boundary? */
if (pvmw->address % PMD_SIZE == 0) {
pte_unmap(pvmw->pte);
+ /*
+ * In the case of PTE-mapped PUD THP, next entry
+ * can be PMD. Reset pte here, so we will not
+ * stay at PTE level after restart.
+ */
+ pvmw->pte = NULL;
if (pvmw->ptl) {
spin_unlock(pvmw->ptl);
pvmw->ptl = NULL;
--
2.28.0
\
 
 \ /
  Last update: 2020-09-28 20:03    [W:0.216 / U:0.308 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site