| 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: <ZV3IXlxKcyOphMgb@arm.com>
Date: Wed, 22 Nov 2023 09:22:38 +0000
From: Alexandru Elisei <alexandru.elisei@....com>
To: Peter Collingbourne <pcc@...gle.com>
Cc: catalin.marinas@....com, will@...nel.org, oliver.upton@...ux.dev,
maz@...nel.org, james.morse@....com, suzuki.poulose@....com,
yuzenghui@...wei.com, arnd@...db.de, akpm@...ux-foundation.org,
mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
vincent.guittot@...aro.org, dietmar.eggemann@....com,
rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
bristot@...hat.com, vschneid@...hat.com, mhiramat@...nel.org,
rppt@...nel.org, hughd@...gle.com, steven.price@....com,
anshuman.khandual@....com, vincenzo.frascino@....com,
david@...hat.com, eugenis@...gle.com, kcc@...gle.com,
hyesoo.yu@...sung.com, linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org, kvmarm@...ts.linux.dev,
linux-fsdevel@...r.kernel.org, linux-arch@...r.kernel.org,
linux-mm@...ck.org, linux-trace-kernel@...r.kernel.org
Subject: Re: [PATCH RFC v2 20/27] mm: hugepage: Handle huge page fault on
access
Hi Peter,
On Tue, Nov 21, 2023 at 05:28:49PM -0800, Peter Collingbourne wrote:
> On Sun, Nov 19, 2023 at 8:59 AM Alexandru Elisei
> <alexandru.elisei@....com> wrote:
> >
> > Handle PAGE_FAULT_ON_ACCESS faults for huge pages in a similar way to
> > regular pages.
> >
> > Signed-off-by: Alexandru Elisei <alexandru.elisei@....com>
> > ---
> > arch/arm64/include/asm/mte_tag_storage.h | 1 +
> > arch/arm64/include/asm/pgtable.h | 7 ++
> > arch/arm64/mm/fault.c | 81 ++++++++++++++++++++++++
> > include/linux/huge_mm.h | 2 +
> > include/linux/pgtable.h | 5 ++
> > mm/huge_memory.c | 4 +-
> > mm/memory.c | 3 +
> > 7 files changed, 101 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/arm64/include/asm/mte_tag_storage.h b/arch/arm64/include/asm/mte_tag_storage.h
> > index c70ced60a0cd..b97406d369ce 100644
> > --- a/arch/arm64/include/asm/mte_tag_storage.h
> > +++ b/arch/arm64/include/asm/mte_tag_storage.h
> > @@ -35,6 +35,7 @@ void free_tag_storage(struct page *page, int order);
> > bool page_tag_storage_reserved(struct page *page);
> >
> > vm_fault_t handle_page_missing_tag_storage(struct vm_fault *vmf);
> > +vm_fault_t handle_huge_page_missing_tag_storage(struct vm_fault *vmf);
> > #else
> > static inline bool tag_storage_enabled(void)
> > {
> > diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> > index 8cc135f1c112..1704411c096d 100644
> > --- a/arch/arm64/include/asm/pgtable.h
> > +++ b/arch/arm64/include/asm/pgtable.h
> > @@ -477,6 +477,13 @@ static inline vm_fault_t arch_do_page_fault_on_access(struct vm_fault *vmf)
> > return handle_page_missing_tag_storage(vmf);
> > return VM_FAULT_SIGBUS;
> > }
> > +
> > +static inline vm_fault_t arch_do_huge_page_fault_on_access(struct vm_fault *vmf)
> > +{
> > + if (tag_storage_enabled())
> > + return handle_huge_page_missing_tag_storage(vmf);
> > + return VM_FAULT_SIGBUS;
> > +}
> > #endif /* CONFIG_ARCH_HAS_FAULT_ON_ACCESS */
> >
> > #define pmd_present_invalid(pmd) (!!(pmd_val(pmd) & PMD_PRESENT_INVALID))
> > diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
> > index f5fa583acf18..6730a0812a24 100644
> > --- a/arch/arm64/mm/fault.c
> > +++ b/arch/arm64/mm/fault.c
> > @@ -1041,6 +1041,87 @@ vm_fault_t handle_page_missing_tag_storage(struct vm_fault *vmf)
> >
> > return 0;
> >
> > +out_retry:
> > + put_page(page);
> > + if (vmf->flags & FAULT_FLAG_VMA_LOCK)
> > + vma_end_read(vma);
> > + if (fault_flag_allow_retry_first(vmf->flags)) {
> > + err = VM_FAULT_RETRY;
> > + } else {
> > + /* Replay the fault. */
> > + err = 0;
> > + }
> > + return err;
> > +}
> > +
> > +vm_fault_t handle_huge_page_missing_tag_storage(struct vm_fault *vmf)
> > +{
> > + unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> > + struct vm_area_struct *vma = vmf->vma;
> > + pmd_t old_pmd, new_pmd;
> > + bool writable = false;
> > + struct page *page;
> > + vm_fault_t err;
> > + int ret;
> > +
> > + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
> > + if (unlikely(!pmd_same(vmf->orig_pmd, *vmf->pmd))) {
> > + spin_unlock(vmf->ptl);
> > + return 0;
> > + }
> > +
> > + old_pmd = vmf->orig_pmd;
> > + new_pmd = pmd_modify(old_pmd, vma->vm_page_prot);
> > +
> > + /*
> > + * Detect now whether the PMD could be writable; this information
> > + * is only valid while holding the PT lock.
> > + */
> > + writable = pmd_write(new_pmd);
> > + if (!writable && vma_wants_manual_pte_write_upgrade(vma) &&
> > + can_change_pmd_writable(vma, vmf->address, new_pmd))
> > + writable = true;
> > +
> > + page = vm_normal_page_pmd(vma, haddr, new_pmd);
> > + if (!page)
> > + goto out_map;
> > +
> > + if (!(vma->vm_flags & VM_MTE))
> > + goto out_map;
> > +
> > + get_page(page);
> > + vma_set_access_pid_bit(vma);
> > +
> > + spin_unlock(vmf->ptl);
> > + writable = false;
> > +
> > + if (unlikely(is_migrate_isolate_page(page)))
> > + goto out_retry;
> > +
> > + ret = reserve_tag_storage(page, HPAGE_PMD_ORDER, GFP_HIGHUSER_MOVABLE);
> > + if (ret)
> > + goto out_retry;
> > +
> > + put_page(page);
> > +
> > + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
> > + if (unlikely(!pmd_same(old_pmd, *vmf->pmd))) {
> > + spin_unlock(vmf->ptl);
> > + return 0;
> > + }
> > +
> > +out_map:
> > + /* Restore the PMD */
> > + new_pmd = pmd_modify(old_pmd, vma->vm_page_prot);
> > + new_pmd = pmd_mkyoung(new_pmd);
> > + if (writable)
> > + new_pmd = pmd_mkwrite(new_pmd, vma);
> > + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, new_pmd);
> > + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
> > + spin_unlock(vmf->ptl);
> > +
> > + return 0;
> > +
> > out_retry:
> > put_page(page);
> > if (vmf->flags & FAULT_FLAG_VMA_LOCK)
> > diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> > index fa0350b0812a..bb84291f9231 100644
> > --- a/include/linux/huge_mm.h
> > +++ b/include/linux/huge_mm.h
> > @@ -36,6 +36,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
> > int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
> > pmd_t *pmd, unsigned long addr, pgprot_t newprot,
> > unsigned long cp_flags);
> > +bool can_change_pmd_writable(struct vm_area_struct *vma, unsigned long addr,
> > + pmd_t pmd);
> >
> > vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
> > vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
> > diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> > index e2c761dd6c41..de45f475bf8d 100644
> > --- a/include/linux/pgtable.h
> > +++ b/include/linux/pgtable.h
> > @@ -1473,6 +1473,11 @@ static inline vm_fault_t arch_do_page_fault_on_access(struct vm_fault *vmf)
> > {
> > return VM_FAULT_SIGBUS;
> > }
> > +
> > +static inline vm_fault_t arch_do_huge_page_fault_on_access(struct vm_fault *vmf)
> > +{
> > + return VM_FAULT_SIGBUS;
> > +}
> > #endif
> >
> > #endif /* CONFIG_MMU */
> > diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> > index 9beead961a65..d1402b43ea39 100644
> > --- a/mm/huge_memory.c
> > +++ b/mm/huge_memory.c
> > @@ -1406,8 +1406,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
> > return VM_FAULT_FALLBACK;
> > }
> >
> > -static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
> > - unsigned long addr, pmd_t pmd)
> > +inline bool can_change_pmd_writable(struct vm_area_struct *vma,
>
> Remove inline keyword here.
Indeed, as it does nothing now that the function is not static.
Thanks,
Alex
>
> Peter
>
> > + unsigned long addr, pmd_t pmd)
> > {
> > struct page *page;
> >
> > diff --git a/mm/memory.c b/mm/memory.c
> > index a04a971200b9..46b926625503 100644
> > --- a/mm/memory.c
> > +++ b/mm/memory.c
> > @@ -5168,6 +5168,9 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
> > return 0;
> > }
> > if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
> > + if (fault_on_access_pmd(vmf.orig_pmd) && vma_is_accessible(vma))
> > + return arch_do_huge_page_fault_on_access(&vmf);
> > +
> > if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
> > return do_huge_pmd_numa_page(&vmf);
> >
> > --
> > 2.42.1
> >
Powered by blists - more mailing lists