[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CA+ZOyaij0A3XCDNSYxp9a3bKO8TVkxCTkQpcCBfiBo_hRszc6g@mail.gmail.com>
Date: Thu, 24 Oct 2019 21:07:20 +0800
From: Zong Li <zongbox@...il.com>
To: Steven Price <steven.price@....com>
Cc: linux-mm@...ck.org, Andy Lutomirski <luto@...nel.org>,
Ard Biesheuvel <ard.biesheuvel@...aro.org>,
Arnd Bergmann <arnd@...db.de>, Borislav Petkov <bp@...en8.de>,
Catalin Marinas <catalin.marinas@....com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Ingo Molnar <mingo@...hat.com>,
James Morse <james.morse@....com>,
Jérôme Glisse <jglisse@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Will Deacon <will@...nel.org>, x86@...nel.org,
"H. Peter Anvin" <hpa@...or.com>,
linux-arm-kernel@...ts.infradead.org,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Mark Rutland <Mark.Rutland@....com>,
"Liang, Kan" <kan.liang@...ux.intel.com>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: [PATCH v12 14/22] mm: pagewalk: Add 'depth' parameter to pte_hole
Steven Price <steven.price@....com> 於 2019年10月19日 週六 下午4:13寫道:
>
> The pte_hole() callback is called at multiple levels of the page tables.
> Code dumping the kernel page tables needs to know what at what depth
> the missing entry is. Add this is an extra parameter to pte_hole().
> When the depth isn't know (e.g. processing a vma) then -1 is passed.
>
> The depth that is reported is the actual level where the entry is
> missing (ignoring any folding that is in place), i.e. any levels where
> PTRS_PER_P?D is set to 1 are ignored.
>
> Note that depth starts at 0 for a PGD so that PUD/PMD/PTE retain their
> natural numbers as levels 2/3/4.
>
> Signed-off-by: Steven Price <steven.price@....com>
> ---
> fs/proc/task_mmu.c | 4 ++--
> include/linux/pagewalk.h | 7 +++++--
> mm/hmm.c | 8 ++++----
> mm/migrate.c | 5 +++--
> mm/mincore.c | 1 +
> mm/pagewalk.c | 31 +++++++++++++++++++++++++------
> 6 files changed, 40 insertions(+), 16 deletions(-)
>
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 9442631fd4af..3ba9ae83bff5 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -505,7 +505,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
>
> #ifdef CONFIG_SHMEM
> static int smaps_pte_hole(unsigned long addr, unsigned long end,
> - struct mm_walk *walk)
> + __always_unused int depth, struct mm_walk *walk)
> {
> struct mem_size_stats *mss = walk->private;
>
> @@ -1282,7 +1282,7 @@ static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
> }
>
> static int pagemap_pte_hole(unsigned long start, unsigned long end,
> - struct mm_walk *walk)
> + __always_unused int depth, struct mm_walk *walk)
> {
> struct pagemapread *pm = walk->private;
> unsigned long addr = start;
> diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
> index df424197a25a..90466d60f87a 100644
> --- a/include/linux/pagewalk.h
> +++ b/include/linux/pagewalk.h
> @@ -17,7 +17,10 @@ struct mm_walk;
> * split_huge_page() instead of handling it explicitly.
> * @pte_entry: if set, called for each non-empty PTE (lowest-level)
> * entry
> - * @pte_hole: if set, called for each hole at all levels
> + * @pte_hole: if set, called for each hole at all levels,
> + * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD
> + * 4:PTE. Any folded depths (where PTRS_PER_P?D is equal
> + * to 1) are skipped.
> * @hugetlb_entry: if set, called for each hugetlb entry
> * @test_walk: caller specific callback function to determine whether
> * we walk over the current vma or not. Returning 0 means
> @@ -45,7 +48,7 @@ struct mm_walk_ops {
> int (*pte_entry)(pte_t *pte, unsigned long addr,
> unsigned long next, struct mm_walk *walk);
> int (*pte_hole)(unsigned long addr, unsigned long next,
> - struct mm_walk *walk);
> + int depth, struct mm_walk *walk);
> int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
> unsigned long addr, unsigned long next,
> struct mm_walk *walk);
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 902f5fa6bf93..df3d531c8f2d 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -376,7 +376,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
> }
>
> static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
> - struct mm_walk *walk)
> + __always_unused int depth, struct mm_walk *walk)
> {
> struct hmm_vma_walk *hmm_vma_walk = walk->private;
> struct hmm_range *range = hmm_vma_walk->range;
> @@ -564,7 +564,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
> again:
> pmd = READ_ONCE(*pmdp);
> if (pmd_none(pmd))
> - return hmm_vma_walk_hole(start, end, walk);
> + return hmm_vma_walk_hole(start, end, -1, walk);
>
> if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
> bool fault, write_fault;
> @@ -666,7 +666,7 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
> again:
> pud = READ_ONCE(*pudp);
> if (pud_none(pud))
> - return hmm_vma_walk_hole(start, end, walk);
> + return hmm_vma_walk_hole(start, end, -1, walk);
>
> if (pud_huge(pud) && pud_devmap(pud)) {
> unsigned long i, npages, pfn;
> @@ -674,7 +674,7 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
> bool fault, write_fault;
>
> if (!pud_present(pud))
> - return hmm_vma_walk_hole(start, end, walk);
> + return hmm_vma_walk_hole(start, end, -1, walk);
>
> i = (addr - range->start) >> PAGE_SHIFT;
> npages = (end - addr) >> PAGE_SHIFT;
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 4fe45d1428c8..435258df9a36 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -2123,6 +2123,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
> #ifdef CONFIG_DEVICE_PRIVATE
> static int migrate_vma_collect_hole(unsigned long start,
> unsigned long end,
> + __always_unused int depth,
> struct mm_walk *walk)
> {
> struct migrate_vma *migrate = walk->private;
> @@ -2167,7 +2168,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
>
> again:
> if (pmd_none(*pmdp))
> - return migrate_vma_collect_hole(start, end, walk);
> + return migrate_vma_collect_hole(start, end, -1, walk);
>
> if (pmd_trans_huge(*pmdp)) {
> struct page *page;
> @@ -2200,7 +2201,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
> return migrate_vma_collect_skip(start, end,
> walk);
> if (pmd_none(*pmdp))
> - return migrate_vma_collect_hole(start, end,
> + return migrate_vma_collect_hole(start, end, -1,
> walk);
> }
> }
> diff --git a/mm/mincore.c b/mm/mincore.c
> index 49b6fa2f6aa1..0e6dd9948f1a 100644
> --- a/mm/mincore.c
> +++ b/mm/mincore.c
> @@ -112,6 +112,7 @@ static int __mincore_unmapped_range(unsigned long addr, unsigned long end,
> }
>
> static int mincore_unmapped_range(unsigned long addr, unsigned long end,
> + __always_unused int depth,
> struct mm_walk *walk)
> {
> walk->private += __mincore_unmapped_range(addr, end,
> diff --git a/mm/pagewalk.c b/mm/pagewalk.c
> index 43acffefd43f..b67400dc1def 100644
> --- a/mm/pagewalk.c
> +++ b/mm/pagewalk.c
> @@ -4,6 +4,22 @@
> #include <linux/sched.h>
> #include <linux/hugetlb.h>
>
> +/*
> + * We want to know the real level where a entry is located ignoring any
> + * folding of levels which may be happening. For example if p4d is folded then
> + * a missing entry found at level 1 (p4d) is actually at level 0 (pgd).
> + */
> +static int real_depth(int depth)
> +{
> + if (depth == 3 && PTRS_PER_PMD == 1)
> + depth = 2;
> + if (depth == 2 && PTRS_PER_PUD == 1)
> + depth = 1;
> + if (depth == 1 && PTRS_PER_P4D == 1)
> + depth = 0;
> + return depth;
> +}
> +
> static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
> struct mm_walk *walk)
> {
> @@ -33,6 +49,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
> unsigned long next;
> const struct mm_walk_ops *ops = walk->ops;
> int err = 0;
> + int depth = real_depth(3);
>
> if (ops->test_pmd) {
> err = ops->test_pmd(addr, end, pmd_offset(pud, 0UL), walk);
> @@ -48,7 +65,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
> next = pmd_addr_end(addr, end);
> if (pmd_none(*pmd)) {
> if (ops->pte_hole)
> - err = ops->pte_hole(addr, next, walk);
> + err = ops->pte_hole(addr, next, depth, walk);
> if (err)
> break;
> continue;
> @@ -92,6 +109,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
> unsigned long next;
> const struct mm_walk_ops *ops = walk->ops;
> int err = 0;
> + int depth = real_depth(2);
>
> if (ops->test_pud) {
> err = ops->test_pud(addr, end, pud_offset(p4d, 0UL), walk);
> @@ -107,7 +125,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
> next = pud_addr_end(addr, end);
> if (pud_none(*pud)) {
> if (ops->pte_hole)
> - err = ops->pte_hole(addr, next, walk);
> + err = ops->pte_hole(addr, next, depth, walk);
> if (err)
> break;
> continue;
> @@ -143,6 +161,7 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
> unsigned long next;
> const struct mm_walk_ops *ops = walk->ops;
> int err = 0;
> + int depth = real_depth(1);
>
> if (ops->test_p4d) {
> err = ops->test_p4d(addr, end, p4d_offset(pgd, 0UL), walk);
> @@ -157,7 +176,7 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
> next = p4d_addr_end(addr, end);
> if (p4d_none_or_clear_bad(p4d)) {
> if (ops->pte_hole)
> - err = ops->pte_hole(addr, next, walk);
> + err = ops->pte_hole(addr, next, depth, walk);
> if (err)
> break;
> continue;
> @@ -189,7 +208,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
> next = pgd_addr_end(addr, end);
> if (pgd_none_or_clear_bad(pgd)) {
> if (ops->pte_hole)
> - err = ops->pte_hole(addr, next, walk);
> + err = ops->pte_hole(addr, next, 0, walk);
> if (err)
> break;
> continue;
> @@ -236,7 +255,7 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end,
> if (pte)
> err = ops->hugetlb_entry(pte, hmask, addr, next, walk);
> else if (ops->pte_hole)
> - err = ops->pte_hole(addr, next, walk);
> + err = ops->pte_hole(addr, next, -1, walk);
>
> if (err)
> break;
> @@ -280,7 +299,7 @@ static int walk_page_test(unsigned long start, unsigned long end,
> if (vma->vm_flags & VM_PFNMAP) {
> int err = 1;
> if (ops->pte_hole)
> - err = ops->pte_hole(start, end, walk);
> + err = ops->pte_hole(start, end, -1, walk);
> return err ? err : 1;
> }
> return 0;
> --
> 2.20.1
>
It's good to me.
Tested-by: Zong Li <zong.li@...ive.com>
Powered by blists - more mailing lists