From: Jia He <justin.he@arm.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
James Morse <james.morse@arm.com>, Marc Zyngier <maz@kernel.org>,
Matthew Wilcox <willy@infradead.org>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Suzuki Poulose <Suzuki.Poulose@arm.com>
Cc: "Punit Agrawal" <punitagrawal@gmail.com>,
"Anshuman Khandual" <anshuman.khandual@arm.com>,
"Alex Van Brunt" <avanbrunt@nvidia.com>,
"Robin Murphy" <robin.murphy@arm.com>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Ralph Campbell" <rcampbell@nvidia.com>,
hejianet@gmail.com, "Kaly Xin" <Kaly.Xin@arm.com>,
nd@arm.com, "Jia He" <justin.he@arm.com>
Subject: [PATCH v8 3/3] mm: fix double page fault on arm64 if PTE_AF is cleared
Date: Sat, 21 Sep 2019 21:50:54 +0800 [thread overview]
Message-ID: <20190921135054.142360-4-justin.he@arm.com> (raw)
In-Reply-To: <20190921135054.142360-1-justin.he@arm.com>
When we tested pmdk unit test [1] vmmalloc_fork TEST1 in arm64 guest, there
will be a double page fault in __copy_from_user_inatomic of cow_user_page.
Below call trace is from arm64 do_page_fault for debugging purpose
[ 110.016195] Call trace:
[ 110.016826] do_page_fault+0x5a4/0x690
[ 110.017812] do_mem_abort+0x50/0xb0
[ 110.018726] el1_da+0x20/0xc4
[ 110.019492] __arch_copy_from_user+0x180/0x280
[ 110.020646] do_wp_page+0xb0/0x860
[ 110.021517] __handle_mm_fault+0x994/0x1338
[ 110.022606] handle_mm_fault+0xe8/0x180
[ 110.023584] do_page_fault+0x240/0x690
[ 110.024535] do_mem_abort+0x50/0xb0
[ 110.025423] el0_da+0x20/0x24
The pte info before __copy_from_user_inatomic is (PTE_AF is cleared):
[ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3
As told by Catalin: "On arm64 without hardware Access Flag, copying from
user will fail because the pte is old and cannot be marked young. So we
always end up with zeroed page after fork() + CoW for pfn mappings. we
don't always have a hardware-managed access flag on arm64."
This patch fix it by calling pte_mkyoung. Also, the parameter is
changed because vmf should be passed to cow_user_page()
Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error
in case there can be some obscure use-case.(by Kirill)
[1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork
Reported-by: Yibo Cai <Yibo.Cai@arm.com>
Signed-off-by: Jia He <justin.he@arm.com>
---
mm/memory.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 61 insertions(+), 6 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index e2bb51b6242e..ae09b070b04d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -118,6 +118,13 @@ int randomize_va_space __read_mostly =
2;
#endif
+#ifndef arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+ return false;
+}
+#endif
+
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
@@ -2140,8 +2147,13 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
return same;
}
-static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
+static inline bool cow_user_page(struct page *dst, struct page *src,
+ struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long addr = vmf->address;
+
debug_dma_assert_idle(src);
/*
@@ -2151,21 +2163,53 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
* fails, we just zero-fill it. Live with it.
*/
if (unlikely(!src)) {
- void *kaddr = kmap_atomic(dst);
- void __user *uaddr = (void __user *)(va & PAGE_MASK);
+ void *kaddr;
+ pte_t entry;
+ void __user *uaddr = (void __user *)(addr & PAGE_MASK);
+ /* On architectures with software "accessed" bits, we would
+ * take a double page fault, so mark it accessed here.
+ */
+ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
+ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr,
+ &vmf->ptl);
+ if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+ entry = pte_mkyoung(vmf->orig_pte);
+ if (ptep_set_access_flags(vma, addr,
+ vmf->pte, entry, 0))
+ update_mmu_cache(vma, addr, vmf->pte);
+ } else {
+ /* Other thread has already handled the fault
+ * and we don't need to do anything. If it's
+ * not the case, the fault will be triggered
+ * again on the same address.
+ */
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ return false;
+ }
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ }
+
+ kaddr = kmap_atomic(dst);
/*
* This really shouldn't fail, because the page is there
* in the page tables. But it might just be unreadable,
* in which case we just give up and fill the result with
* zeroes.
*/
- if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
+ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+ /* Give a warn in case there can be some obscure
+ * use-case
+ */
+ WARN_ON_ONCE(1);
clear_page(kaddr);
+ }
kunmap_atomic(kaddr);
flush_dcache_page(dst);
} else
- copy_user_highpage(dst, src, va, vma);
+ copy_user_highpage(dst, src, addr, vma);
+
+ return true;
}
static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
@@ -2318,7 +2362,18 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
vmf->address);
if (!new_page)
goto oom;
- cow_user_page(new_page, old_page, vmf->address, vma);
+
+ if (!cow_user_page(new_page, old_page, vmf)) {
+ /* COW failed, if the fault was solved by other,
+ * it's fine. If not, userspace would re-fault on
+ * the same address and we will handle the fault
+ * from the second attempt.
+ */
+ put_page(new_page);
+ if (old_page)
+ put_page(old_page);
+ return 0;
+ }
}
if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
--
2.17.1
next prev parent reply other threads:[~2019-09-21 13:51 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-21 13:50 [PATCH v8 0/3] fix double page fault on arm64 Jia He
2019-09-21 13:50 ` [PATCH v8 1/3] arm64: cpufeature: introduce helper cpu_has_hw_af() Jia He
2019-09-23 16:07 ` Catalin Marinas
2019-09-24 1:50 ` Justin He (Arm Technology China)
2019-09-21 13:50 ` [PATCH v8 2/3] arm64: mm: implement arch_faults_on_old_pte() on arm64 Jia He
2019-09-23 16:18 ` Catalin Marinas
2019-09-24 2:17 ` Justin He (Arm Technology China)
2019-09-21 13:50 ` Jia He [this message]
2019-09-21 15:31 ` [PATCH v8 3/3] mm: fix double page fault on arm64 if PTE_AF is cleared Matthew Wilcox
2019-09-23 8:28 ` Kirill A. Shutemov
2019-09-23 17:04 ` Catalin Marinas
2019-09-24 6:43 ` Justin He (Arm Technology China)
2019-09-24 10:33 ` Catalin Marinas
2019-09-24 11:59 ` Kirill A. Shutemov
2019-09-24 15:29 ` Jia He
2019-09-24 16:35 ` Catalin Marinas
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190921135054.142360-4-justin.he@arm.com \
--to=justin.he@arm.com \
--cc=Kaly.Xin@arm.com \
--cc=Suzuki.Poulose@arm.com \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.com \
--cc=avanbrunt@nvidia.com \
--cc=catalin.marinas@arm.com \
--cc=hejianet@gmail.com \
--cc=james.morse@arm.com \
--cc=jglisse@redhat.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mark.rutland@arm.com \
--cc=maz@kernel.org \
--cc=nd@arm.com \
--cc=punitagrawal@gmail.com \
--cc=rcampbell@nvidia.com \
--cc=robin.murphy@arm.com \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).