| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAC_TJvdcWV=cyszkOURekZGEZP2txvDyZKDyDgKB37+g+eg3hg@mail.gmail.com>
Date: Fri, 2 Oct 2020 18:08:29 -0400
From: Kalesh Singh <kaleshsingh@...gle.com>
To: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Cc: Suren Baghdasaryan <surenb@...gle.com>,
Minchan Kim <minchan@...gle.com>,
Joel Fernandes <joelaf@...gle.com>,
Lokesh Gidra <lokeshgidra@...gle.com>,
"Cc: Android Kernel" <kernel-team@...roid.com>,
kernel test robot <lkp@...el.com>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
"the arch/x86 maintainers" <x86@...nel.org>,
"H. Peter Anvin" <hpa@...or.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Shuah Khan <shuah@...nel.org>,
"Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
Kees Cook <keescook@...omium.org>,
Peter Zijlstra <peterz@...radead.org>,
Sami Tolvanen <samitolvanen@...gle.com>,
Masahiro Yamada <masahiroy@...nel.org>,
Arnd Bergmann <arnd@...db.de>,
Frederic Weisbecker <frederic@...nel.org>,
Krzysztof Kozlowski <krzk@...nel.org>,
Hassan Naveed <hnaveed@...ecomp.com>,
Christian Brauner <christian.brauner@...ntu.com>,
Mark Rutland <mark.rutland@....com>,
Mike Rapoport <rppt@...nel.org>, Gavin Shan <gshan@...hat.com>,
Chris von Recklinghausen <crecklin@...hat.com>,
Jia He <justin.he@....com>, Zhenyu Ye <yezhenyu2@...wei.com>,
John Hubbard <jhubbard@...dia.com>,
Thiago Jung Bauermann <bauerman@...ux.ibm.com>,
William Kucharski <william.kucharski@...cle.com>,
Ram Pai <linuxram@...ibm.com>,
Ralph Campbell <rcampbell@...dia.com>,
Mina Almasry <almasrymina@...gle.com>,
Sandipan Das <sandipan@...ux.ibm.com>,
Dave Hansen <dave.hansen@...el.com>,
Masami Hiramatsu <mhiramat@...nel.org>,
SeongJae Park <sjpark@...zon.de>,
Brian Geffon <bgeffon@...gle.com>,
LKML <linux-kernel@...r.kernel.org>,
"moderated list:ARM64 PORT (AARCH64 ARCHITECTURE)"
<linux-arm-kernel@...ts.infradead.org>,
"open list:MEMORY MANAGEMENT" <linux-mm@...ck.org>,
"open list:KERNEL SELFTEST FRAMEWORK"
<linux-kselftest@...r.kernel.org>
Subject: Re: [PATCH v2 3/6] mm: Speedup mremap on 1GB or larger regions
Hi Kirill, thank you for the feedback.
On Fri, Oct 2, 2020 at 12:51 PM Kirill A. Shutemov
<kirill.shutemov@...ux.intel.com> wrote:
>
> On Fri, Oct 02, 2020 at 04:20:48PM +0000, Kalesh Singh wrote:
> > Android needs to move large memory regions for garbage collection.
> > The GC requires moving physical pages of multi-gigabyte heap
> > using mremap. During this move, the application threads have to
> > be paused for correctness. It is critical to keep this pause as
> > short as possible to avoid jitters during user interaction.
> >
> > Optimize mremap for >= 1GB-sized regions by moving at the PUD/PGD
> > level if the source and destination addresses are PUD-aligned.
> > For CONFIG_PGTABLE_LEVELS == 3, moving at the PUD level in effect moves
> > PGD entries, since the PUD entry is “folded back” onto the PGD entry.
> > Add HAVE_MOVE_PUD so that architectures where moving at the PUD level
> > isn't supported/tested can turn this off by not selecting the config.
> >
> > Fix build test error from v1 of this series reported by
> > kernel test robot in [1].
> >
> > [1] https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org/thread/CKPGL4FH4NG7TGH2CVYX2UX76L25BTA3/
> >
> > Signed-off-by: Kalesh Singh <kaleshsingh@...gle.com>
> > Reported-by: kernel test robot <lkp@...el.com>
> > ---
> > Changes in v2:
> > - Update commit message with description of Android GC's use case.
> > - Move set_pud_at() to a separate patch.
> > - Use switch() instead of ifs in move_pgt_entry()
> > - Fix build test error reported by kernel test robot on x86_64 in [1].
> > Guard move_huge_pmd() with IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE),
> > since this section doesn't get optimized out in the kernel test
> > robot's build test when HAVE_MOVE_PUD is enabled.
> > - Keep WARN_ON_ONCE(1) instead of BUILD_BUG() for the aforementioned
> > reason.
>
> Okay, but IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) on the caller side would
> do the trick, I believe.
I tried moving this to the caller side in move_page_tables(),
- if (extent == HPAGE_PMD_SIZE &&
+ if (extent == HPAGE_PMD_SIZE &&
IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
but it produces the same error as reported by kernel test robot:
ld.lld: error: undefined symbol: move_huge_pmd
I'm not sure why these are different but the kernel test robot
compiler complains.
>
> >
> > arch/Kconfig | 7 ++
> > mm/mremap.c | 220 ++++++++++++++++++++++++++++++++++++++++++++-------
> > 2 files changed, 197 insertions(+), 30 deletions(-)
> >
> > diff --git a/arch/Kconfig b/arch/Kconfig
> > index af14a567b493..5eabaa00bf9b 100644
> > --- a/arch/Kconfig
> > +++ b/arch/Kconfig
> > @@ -602,6 +602,13 @@ config HAVE_IRQ_TIME_ACCOUNTING
> > Archs need to ensure they use a high enough resolution clock to
> > support irq time accounting and then call enable_sched_clock_irqtime().
> >
> > +config HAVE_MOVE_PUD
> > + bool
> > + help
> > + Architectures that select this are able to move page tables at the
> > + PUD level. If there are only 3 page table levels, the move effectively
> > + happens at the PGD level.
> > +
> > config HAVE_MOVE_PMD
> > bool
> > help
> > diff --git a/mm/mremap.c b/mm/mremap.c
> > index 138abbae4f75..c1d6ab667d70 100644
> > --- a/mm/mremap.c
> > +++ b/mm/mremap.c
> > @@ -249,14 +249,176 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
> >
> > return true;
> > }
> > +#else
> > +static inline bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
> > + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
> > +{
> > + return false;
> > +}
> > #endif
> >
> > +#ifdef CONFIG_HAVE_MOVE_PUD
> > +static pud_t *get_old_pud(struct mm_struct *mm, unsigned long addr)
> > +{
> > + pgd_t *pgd;
> > + p4d_t *p4d;
> > + pud_t *pud;
> > +
> > + pgd = pgd_offset(mm, addr);
> > + if (pgd_none_or_clear_bad(pgd))
> > + return NULL;
> > +
> > + p4d = p4d_offset(pgd, addr);
> > + if (p4d_none_or_clear_bad(p4d))
> > + return NULL;
> > +
> > + pud = pud_offset(p4d, addr);
> > + if (pud_none_or_clear_bad(pud))
> > + return NULL;
> > +
> > + return pud;
> > +}
> > +
> > +static pud_t *alloc_new_pud(struct mm_struct *mm, struct vm_area_struct *vma,
> > + unsigned long addr)
> > +{
> > + pgd_t *pgd;
> > + p4d_t *p4d;
> > + pud_t *pud;
> > +
> > + pgd = pgd_offset(mm, addr);
> > + p4d = p4d_alloc(mm, pgd, addr);
> > + if (!p4d)
> > + return NULL;
> > + pud = pud_alloc(mm, p4d, addr);
> > + if (!pud)
> > + return NULL;
> > +
> > + return pud;
> > +}
>
> Looks like a code duplication.
>
> Could you move these two helpers out of #ifdef CONFIG_HAVE_MOVE_PUD and
> make get_old_pmd() and alloc_new_pmd() use them?
Yes, that will be cleaner. I'll update it in the next version.
>
> > +
> > +static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
> > + unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
> > +{
> > + spinlock_t *old_ptl, *new_ptl;
> > + struct mm_struct *mm = vma->vm_mm;
> > + pud_t pud;
> > +
> > + /*
> > + * The destination pud shouldn't be established, free_pgtables()
> > + * should have released it.
> > + */
> > + if (WARN_ON_ONCE(!pud_none(*new_pud)))
> > + return false;
> > +
> > + /*
> > + * We don't have to worry about the ordering of src and dst
> > + * ptlocks because exclusive mmap_lock prevents deadlock.
> > + */
> > + old_ptl = pud_lock(vma->vm_mm, old_pud);
> > + new_ptl = pud_lockptr(mm, new_pud);
> > + if (new_ptl != old_ptl)
> > + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
> > +
> > + /* Clear the pud */
> > + pud = *old_pud;
> > + pud_clear(old_pud);
> > +
> > + VM_BUG_ON(!pud_none(*new_pud));
> > +
> > + /* Set the new pud */
> > + set_pud_at(mm, new_addr, new_pud, pud);
> > + flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE);
> > + if (new_ptl != old_ptl)
> > + spin_unlock(new_ptl);
> > + spin_unlock(old_ptl);
> > +
> > + return true;
> > +}
> > +#else
> > +static inline bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
> > + unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
> > +{
> > + return false;
> > +}
> > +#endif
> > +
> > +enum pgt_entry {
> > + NORMAL_PMD,
> > + HPAGE_PMD,
> > + NORMAL_PUD,
> > +};
> > +
> > +/*
> > + * Returns an extent of the corresponding size for the pgt_entry specified if valid.
> > + * Else returns a smaller extent bounded by the end of the source and destination
> > + * pgt_entry. Returns 0 if an invalid pgt_entry is specified.
> > + */
> > +static unsigned long get_extent(enum pgt_entry entry, unsigned long old_addr,
> > + unsigned long old_end, unsigned long new_addr)
> > +{
> > + unsigned long next, extent, mask, size;
> > +
> > + if (entry == NORMAL_PMD || entry == HPAGE_PMD) {
> > + mask = PMD_MASK;
> > + size = PMD_SIZE;
> > + } else if (entry == NORMAL_PUD) {
> > + mask = PUD_MASK;
> > + size = PUD_SIZE;
> > + } else
> > + return 0;
>
> Em. Who would ever specify invalid pgt_entry? It's bug.
> Again, switch()?
Sounds good. I'll use BUG() and switch() instead.
>
> > +
> > + next = (old_addr + size) & mask;
> > + /* even if next overflowed, extent below will be ok */
> > + extent = (next > old_end) ? old_end - old_addr : next - old_addr;
> > + next = (new_addr + size) & mask;
> > + if (extent > next - new_addr)
> > + extent = next - new_addr;
> > + return extent;
> > +}
> > +
> > +/*
> > + * Attempts to speedup the move by moving entry at the level corresponding to
> > + * pgt_entry. Returns true if the move was successful, else false.
> > + */
> > +static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma,
> > + unsigned long old_addr, unsigned long new_addr, void *old_entry,
> > + void *new_entry, bool need_rmap_locks)
> > +{
> > + bool moved = false;
> > +
> > + /* See comment in move_ptes() */
> > + if (need_rmap_locks)
> > + take_rmap_locks(vma);
> > +
> > + switch (entry) {
> > + case NORMAL_PMD:
> > + moved = move_normal_pmd(vma, old_addr, new_addr, old_entry, new_entry);
>
> Nit: here and below, double space after '='. Why?
Sorry, editing mistake on my end. I'll clean this up before resending.
>
> > + break;
> > + case NORMAL_PUD:
> > + moved = move_normal_pud(vma, old_addr, new_addr, old_entry, new_entry);
> > + break;
> > + case HPAGE_PMD:
> > + moved = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
> > + move_huge_pmd(vma, old_addr, new_addr, old_entry, new_entry);
> > + break;
> > + default:
> > + WARN_ON_ONCE(1);
> > + break;
> > + }
> > +
> > + if (need_rmap_locks)
> > + drop_rmap_locks(vma);
> > +
> > + return moved;
> > +}
> > +
> > unsigned long move_page_tables(struct vm_area_struct *vma,
> > unsigned long old_addr, struct vm_area_struct *new_vma,
> > unsigned long new_addr, unsigned long len,
> > bool need_rmap_locks)
> > {
> > - unsigned long extent, next, old_end;
> > + unsigned long extent, old_end;
> > struct mmu_notifier_range range;
> > pmd_t *old_pmd, *new_pmd;
> >
> > @@ -269,14 +431,27 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
> >
> > for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
> > cond_resched();
> > - next = (old_addr + PMD_SIZE) & PMD_MASK;
> > - /* even if next overflowed, extent below will be ok */
> > - extent = next - old_addr;
> > - if (extent > old_end - old_addr)
> > - extent = old_end - old_addr;
> > - next = (new_addr + PMD_SIZE) & PMD_MASK;
> > - if (extent > next - new_addr)
> > - extent = next - new_addr;
> > +#ifdef CONFIG_HAVE_MOVE_PUD
>
> Any chance if (IS_ENABLED(CONFIG_HAVE_MOVE_PUD)) would work here?
Once we move get_old_put() and alloc_new_pud() out of the #ifdefs as
you suggested
above, it should work. It would also now be possible to replace the
#ifdef CONFIG_HAVE_MOVE_PMD in move_page_tables() with
IS_ENABLED(CONFIG_HAVE_MOVE_PMD).
Thanks,
Kalesh
>
> > + /*
> > + * If extent is PUD-sized try to speed up the move by moving at the
> > + * PUD level if possible.
> > + */
> > + extent = get_extent(NORMAL_PUD, old_addr, old_end, new_addr);
> > + if (extent == PUD_SIZE) {
> > + pud_t *old_pud, *new_pud;
> > +
> > + old_pud = get_old_pud(vma->vm_mm, old_addr);
> > + if (!old_pud)
> > + continue;
> > + new_pud = alloc_new_pud(vma->vm_mm, vma, new_addr);
> > + if (!new_pud)
> > + break;
> > + if (move_pgt_entry(NORMAL_PUD, vma, old_addr, new_addr,
> > + old_pud, new_pud, need_rmap_locks))
> > + continue;
> > + }
> > +#endif
> > + extent = get_extent(NORMAL_PMD, old_addr, old_end, new_addr);
> > old_pmd = get_old_pmd(vma->vm_mm, old_addr);
> > if (!old_pmd)
> > continue;
> > @@ -284,18 +459,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
> > if (!new_pmd)
> > break;
> > if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) || pmd_devmap(*old_pmd)) {
> > - if (extent == HPAGE_PMD_SIZE) {
> > - bool moved;
> > - /* See comment in move_ptes() */
> > - if (need_rmap_locks)
> > - take_rmap_locks(vma);
> > - moved = move_huge_pmd(vma, old_addr, new_addr,
> > - old_pmd, new_pmd);
> > - if (need_rmap_locks)
> > - drop_rmap_locks(vma);
> > - if (moved)
> > - continue;
> > - }
> > + if (extent == HPAGE_PMD_SIZE &&
> > + move_pgt_entry(HPAGE_PMD, vma, old_addr, new_addr, old_pmd,
> > + new_pmd, need_rmap_locks))
> > + continue;
> > split_huge_pmd(vma, old_pmd, old_addr);
> > if (pmd_trans_unstable(old_pmd))
> > continue;
> > @@ -305,15 +472,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
> > * If the extent is PMD-sized, try to speed the move by
> > * moving at the PMD level if possible.
> > */
> > - bool moved;
> > -
> > - if (need_rmap_locks)
> > - take_rmap_locks(vma);
> > - moved = move_normal_pmd(vma, old_addr, new_addr,
> > - old_pmd, new_pmd);
> > - if (need_rmap_locks)
> > - drop_rmap_locks(vma);
> > - if (moved)
> > + if (move_pgt_entry(NORMAL_PMD, vma, old_addr, new_addr, old_pmd,
> > + new_pmd, need_rmap_locks))
> > continue;
> > #endif
> > }
> > --
> > 2.28.0.806.g8561365e88-goog
> >
>
> --
> Kirill A. Shutemov
>
> --
> To unsubscribe from this group and stop receiving emails from it, send an email to kernel-team+unsubscribe@...roid.com.
>
Powered by blists - more mailing lists