linux/mm/mapping_dirty_helpers.c

340 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
#include <linux/pagewalk.h>
#include <linux/hugetlb.h>
#include <linux/bitops.h>
#include <linux/mmu_notifier.h>
#include <linux/mm_inline.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
/**
* struct wp_walk - Private struct for pagetable walk callbacks
* @range: Range for mmu notifiers
* @tlbflush_start: Address of first modified pte
* @tlbflush_end: Address of last modified pte + 1
* @total: Total number of modified ptes
*/
struct wp_walk {
struct mmu_notifier_range range;
unsigned long tlbflush_start;
unsigned long tlbflush_end;
unsigned long total;
};
/**
* wp_pte - Write-protect a pte
* @pte: Pointer to the pte
* @addr: The start of protecting virtual address
* @end: The end of protecting virtual address
* @walk: pagetable walk callback argument
*
* The function write-protects a pte and records the range in
* virtual address space of touched ptes for efficient range TLB flushes.
*/
static int wp_pte(pte_t *pte, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct wp_walk *wpwalk = walk->private;
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 15:15:45 +00:00
pte_t ptent = ptep_get(pte);
if (pte_write(ptent)) {
pte_t old_pte = ptep_modify_prot_start(walk->vma, addr, pte);
ptent = pte_wrprotect(old_pte);
ptep_modify_prot_commit(walk->vma, addr, pte, old_pte, ptent);
wpwalk->total++;
wpwalk->tlbflush_start = min(wpwalk->tlbflush_start, addr);
wpwalk->tlbflush_end = max(wpwalk->tlbflush_end,
addr + PAGE_SIZE);
}
return 0;
}
/**
* struct clean_walk - Private struct for the clean_record_pte function.
* @base: struct wp_walk we derive from
* @bitmap_pgoff: Address_space Page offset of the first bit in @bitmap
* @bitmap: Bitmap with one bit for each page offset in the address_space range
* covered.
* @start: Address_space page offset of first modified pte relative
* to @bitmap_pgoff
* @end: Address_space page offset of last modified pte relative
* to @bitmap_pgoff
*/
struct clean_walk {
struct wp_walk base;
pgoff_t bitmap_pgoff;
unsigned long *bitmap;
pgoff_t start;
pgoff_t end;
};
#define to_clean_walk(_wpwalk) container_of(_wpwalk, struct clean_walk, base)
/**
* clean_record_pte - Clean a pte and record its address space offset in a
* bitmap
* @pte: Pointer to the pte
* @addr: The start of virtual address to be clean
* @end: The end of virtual address to be clean
* @walk: pagetable walk callback argument
*
* The function cleans a pte and records the range in
* virtual address space of touched ptes for efficient TLB flushes.
* It also records dirty ptes in a bitmap representing page offsets
* in the address_space, as well as the first and last of the bits
* touched.
*/
static int clean_record_pte(pte_t *pte, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct wp_walk *wpwalk = walk->private;
struct clean_walk *cwalk = to_clean_walk(wpwalk);
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 15:15:45 +00:00
pte_t ptent = ptep_get(pte);
if (pte_dirty(ptent)) {
pgoff_t pgoff = ((addr - walk->vma->vm_start) >> PAGE_SHIFT) +
walk->vma->vm_pgoff - cwalk->bitmap_pgoff;
pte_t old_pte = ptep_modify_prot_start(walk->vma, addr, pte);
ptent = pte_mkclean(old_pte);
ptep_modify_prot_commit(walk->vma, addr, pte, old_pte, ptent);
wpwalk->total++;
wpwalk->tlbflush_start = min(wpwalk->tlbflush_start, addr);
wpwalk->tlbflush_end = max(wpwalk->tlbflush_end,
addr + PAGE_SIZE);
__set_bit(pgoff, cwalk->bitmap);
cwalk->start = min(cwalk->start, pgoff);
cwalk->end = max(cwalk->end, pgoff + 1);
}
return 0;
}
/*
* wp_clean_pmd_entry - The pagewalk pmd callback.
*
* Dirty-tracking should take place on the PTE level, so
* WARN() if encountering a dirty huge pmd.
* Furthermore, never split huge pmds, since that currently
* causes dirty info loss. The pagefault handler should do
* that if needed.
*/
static int wp_clean_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pmd_t pmdval = pmdp_get_lockless(pmd);
mm/vmwgfx: simplify pmd & pud mapping dirty helpers wp_clean_pmd_entry() need not check pmd_trans_unstable() or pmd_none(), wp_clean_pud_entry() need not check pud_trans_unstable() or pud_none(): it's just the ACTION_CONTINUE when trans_huge or devmap that's needed to prevent splitting, and we're hoping to remove pmd_trans_unstable(). Is that PUD #ifdef necessary? Maybe some configs are missing a stub. Link: https://lkml.kernel.org/r/d3379c7-65db-26d3-1764-8e866490925f@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:20:04 +00:00
/* Do not split a huge pmd, present or migrated */
if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval)) {
WARN_ON(pmd_write(pmdval) || pmd_dirty(pmdval));
mm/vmwgfx: simplify pmd & pud mapping dirty helpers wp_clean_pmd_entry() need not check pmd_trans_unstable() or pmd_none(), wp_clean_pud_entry() need not check pud_trans_unstable() or pud_none(): it's just the ACTION_CONTINUE when trans_huge or devmap that's needed to prevent splitting, and we're hoping to remove pmd_trans_unstable(). Is that PUD #ifdef necessary? Maybe some configs are missing a stub. Link: https://lkml.kernel.org/r/d3379c7-65db-26d3-1764-8e866490925f@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:20:04 +00:00
walk->action = ACTION_CONTINUE;
}
return 0;
}
/*
* wp_clean_pud_entry - The pagewalk pud callback.
*
* Dirty-tracking should take place on the PTE level, so
* WARN() if encountering a dirty huge puds.
* Furthermore, never split huge puds, since that currently
* causes dirty info loss. The pagefault handler should do
* that if needed.
*/
static int wp_clean_pud_entry(pud_t *pud, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
mm/vmwgfx: simplify pmd & pud mapping dirty helpers wp_clean_pmd_entry() need not check pmd_trans_unstable() or pmd_none(), wp_clean_pud_entry() need not check pud_trans_unstable() or pud_none(): it's just the ACTION_CONTINUE when trans_huge or devmap that's needed to prevent splitting, and we're hoping to remove pmd_trans_unstable(). Is that PUD #ifdef necessary? Maybe some configs are missing a stub. Link: https://lkml.kernel.org/r/d3379c7-65db-26d3-1764-8e866490925f@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:20:04 +00:00
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
pud_t pudval = READ_ONCE(*pud);
mm/vmwgfx: simplify pmd & pud mapping dirty helpers wp_clean_pmd_entry() need not check pmd_trans_unstable() or pmd_none(), wp_clean_pud_entry() need not check pud_trans_unstable() or pud_none(): it's just the ACTION_CONTINUE when trans_huge or devmap that's needed to prevent splitting, and we're hoping to remove pmd_trans_unstable(). Is that PUD #ifdef necessary? Maybe some configs are missing a stub. Link: https://lkml.kernel.org/r/d3379c7-65db-26d3-1764-8e866490925f@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:20:04 +00:00
/* Do not split a huge pud */
if (pud_trans_huge(pudval) || pud_devmap(pudval)) {
WARN_ON(pud_write(pudval) || pud_dirty(pudval));
mm/vmwgfx: simplify pmd & pud mapping dirty helpers wp_clean_pmd_entry() need not check pmd_trans_unstable() or pmd_none(), wp_clean_pud_entry() need not check pud_trans_unstable() or pud_none(): it's just the ACTION_CONTINUE when trans_huge or devmap that's needed to prevent splitting, and we're hoping to remove pmd_trans_unstable(). Is that PUD #ifdef necessary? Maybe some configs are missing a stub. Link: https://lkml.kernel.org/r/d3379c7-65db-26d3-1764-8e866490925f@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Christoph Hellwig <hch@infradead.org> Cc: David Hildenbrand <david@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Song Liu <song@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zack Rusin <zackr@vmware.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 01:20:04 +00:00
walk->action = ACTION_CONTINUE;
}
#endif
return 0;
}
/*
* wp_clean_pre_vma - The pagewalk pre_vma callback.
*
* The pre_vma callback performs the cache flush, stages the tlb flush
* and calls the necessary mmu notifiers.
*/
static int wp_clean_pre_vma(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct wp_walk *wpwalk = walk->private;
wpwalk->tlbflush_start = end;
wpwalk->tlbflush_end = start;
mmu_notifier_range_init(&wpwalk->range, MMU_NOTIFY_PROTECTION_PAGE, 0,
walk->mm, start, end);
mmu_notifier_invalidate_range_start(&wpwalk->range);
flush_cache_range(walk->vma, start, end);
/*
* We're not using tlb_gather_mmu() since typically
* only a small subrange of PTEs are affected, whereas
* tlb_gather_mmu() records the full range.
*/
inc_tlb_flush_pending(walk->mm);
return 0;
}
/*
* wp_clean_post_vma - The pagewalk post_vma callback.
*
* The post_vma callback performs the tlb flush and calls necessary mmu
* notifiers.
*/
static void wp_clean_post_vma(struct mm_walk *walk)
{
struct wp_walk *wpwalk = walk->private;
if (mm_tlb_flush_nested(walk->mm))
flush_tlb_range(walk->vma, wpwalk->range.start,
wpwalk->range.end);
else if (wpwalk->tlbflush_end > wpwalk->tlbflush_start)
flush_tlb_range(walk->vma, wpwalk->tlbflush_start,
wpwalk->tlbflush_end);
mmu_notifier_invalidate_range_end(&wpwalk->range);
dec_tlb_flush_pending(walk->mm);
}
/*
* wp_clean_test_walk - The pagewalk test_walk callback.
*
* Won't perform dirty-tracking on COW, read-only or HUGETLB vmas.
*/
static int wp_clean_test_walk(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
unsigned long vm_flags = READ_ONCE(walk->vma->vm_flags);
/* Skip non-applicable VMAs */
if ((vm_flags & (VM_SHARED | VM_MAYWRITE | VM_HUGETLB)) !=
(VM_SHARED | VM_MAYWRITE))
return 1;
return 0;
}
static const struct mm_walk_ops clean_walk_ops = {
.pte_entry = clean_record_pte,
.pmd_entry = wp_clean_pmd_entry,
.pud_entry = wp_clean_pud_entry,
.test_walk = wp_clean_test_walk,
.pre_vma = wp_clean_pre_vma,
.post_vma = wp_clean_post_vma
};
static const struct mm_walk_ops wp_walk_ops = {
.pte_entry = wp_pte,
.pmd_entry = wp_clean_pmd_entry,
.pud_entry = wp_clean_pud_entry,
.test_walk = wp_clean_test_walk,
.pre_vma = wp_clean_pre_vma,
.post_vma = wp_clean_post_vma
};
/**
* wp_shared_mapping_range - Write-protect all ptes in an address space range
* @mapping: The address_space we want to write protect
* @first_index: The first page offset in the range
* @nr: Number of incremental page offsets to cover
*
* Note: This function currently skips transhuge page-table entries, since
* it's intended for dirty-tracking on the PTE level. It will warn on
* encountering transhuge write-enabled entries, though, and can easily be
* extended to handle them as well.
*
* Return: The number of ptes actually write-protected. Note that
* already write-protected ptes are not counted.
*/
unsigned long wp_shared_mapping_range(struct address_space *mapping,
pgoff_t first_index, pgoff_t nr)
{
struct wp_walk wpwalk = { .total = 0 };
i_mmap_lock_read(mapping);
WARN_ON(walk_page_mapping(mapping, first_index, nr, &wp_walk_ops,
&wpwalk));
i_mmap_unlock_read(mapping);
return wpwalk.total;
}
EXPORT_SYMBOL_GPL(wp_shared_mapping_range);
/**
* clean_record_shared_mapping_range - Clean and record all ptes in an
* address space range
* @mapping: The address_space we want to clean
* @first_index: The first page offset in the range
* @nr: Number of incremental page offsets to cover
* @bitmap_pgoff: The page offset of the first bit in @bitmap
* @bitmap: Pointer to a bitmap of at least @nr bits. The bitmap needs to
* cover the whole range @first_index..@first_index + @nr.
* @start: Pointer to number of the first set bit in @bitmap.
* is modified as new bits are set by the function.
* @end: Pointer to the number of the last set bit in @bitmap.
* none set. The value is modified as new bits are set by the function.
*
* When this function returns there is no guarantee that a CPU has
* not already dirtied new ptes. However it will not clean any ptes not
* reported in the bitmap. The guarantees are as follows:
*
* * All ptes dirty when the function starts executing will end up recorded
* in the bitmap.
* * All ptes dirtied after that will either remain dirty, be recorded in the
* bitmap or both.
*
* If a caller needs to make sure all dirty ptes are picked up and none
* additional are added, it first needs to write-protect the address-space
* range and make sure new writers are blocked in page_mkwrite() or
* pfn_mkwrite(). And then after a TLB flush following the write-protection
* pick up all dirty bits.
*
* This function currently skips transhuge page-table entries, since
* it's intended for dirty-tracking on the PTE level. It will warn on
* encountering transhuge dirty entries, though, and can easily be extended
* to handle them as well.
*
* Return: The number of dirty ptes actually cleaned.
*/
unsigned long clean_record_shared_mapping_range(struct address_space *mapping,
pgoff_t first_index, pgoff_t nr,
pgoff_t bitmap_pgoff,
unsigned long *bitmap,
pgoff_t *start,
pgoff_t *end)
{
bool none_set = (*start >= *end);
struct clean_walk cwalk = {
.base = { .total = 0 },
.bitmap_pgoff = bitmap_pgoff,
.bitmap = bitmap,
.start = none_set ? nr : *start,
.end = none_set ? 0 : *end,
};
i_mmap_lock_read(mapping);
WARN_ON(walk_page_mapping(mapping, first_index, nr, &clean_walk_ops,
&cwalk.base));
i_mmap_unlock_read(mapping);
*start = cwalk.start;
*end = cwalk.end;
return cwalk.base.total;
}
EXPORT_SYMBOL_GPL(clean_record_shared_mapping_range);