Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
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
Cc: "Punit Agrawal" <punitagrawal@gmail.com>,
	"Anshuman Khandual" <anshuman.khandual@arm.com>,
	"Jun Yao" <yaojun8558363@gmail.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, "Jia He" <justin.he@arm.com>
Subject: [PATCH v3 2/2] mm: fix double page fault on arm64 if PTE_AF is cleared
Date: Sat, 14 Sep 2019 00:32:39 +0800
Message-ID: <20190913163239.125108-3-justin.he@arm.com> (raw)
In-Reply-To: <20190913163239.125108-1-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()

[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 | 30 +++++++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index e2bb51b6242e..a64af6495f71 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;
@@ -2140,7 +2147,8 @@ 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 void cow_user_page(struct page *dst, struct page *src,
+				struct vm_fault *vmf)
 {
 	debug_dma_assert_idle(src);
 
@@ -2152,20 +2160,32 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
 	 */
 	if (unlikely(!src)) {
 		void *kaddr = kmap_atomic(dst);
-		void __user *uaddr = (void __user *)(va & PAGE_MASK);
+		void __user *uaddr = (void __user *)(vmf->address & PAGE_MASK);
+		pte_t entry;
 
 		/*
 		 * 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.
+		 * zeroes. If PTE_AF is cleared on arm64, it might
+		 * cause double page fault. So makes pte young here
 		 */
+		if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
+			spin_lock(vmf->ptl);
+			entry = pte_mkyoung(vmf->orig_pte);
+			if (ptep_set_access_flags(vmf->vma, vmf->address,
+						  vmf->pte, entry, 0))
+				update_mmu_cache(vmf->vma, vmf->address,
+						 vmf->pte);
+			spin_unlock(vmf->ptl);
+		}
+
 		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
 			clear_page(kaddr);
 		kunmap_atomic(kaddr);
 		flush_dcache_page(dst);
 	} else
-		copy_user_highpage(dst, src, va, vma);
+		copy_user_highpage(dst, src, vmf->address, vmf->vma);
 }
 
 static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
@@ -2318,7 +2338,7 @@ 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);
+		cow_user_page(new_page, old_page, vmf);
 	}
 
 	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
-- 
2.17.1



  parent reply index

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-13 16:32 [PATCH v3 0/2] fix double page fault on arm64 Jia He
2019-09-13 16:32 ` [PATCH v3 1/2] arm64: mm: implement arch_faults_on_old_pte() " Jia He
2019-09-16  9:20   ` Kirill A. Shutemov
2019-09-13 16:32 ` Jia He [this message]
2019-09-16  9:16   ` [PATCH v3 2/2] mm: fix double page fault on arm64 if PTE_AF is cleared Kirill A. Shutemov
2019-09-16  9:35     ` Justin He (Arm Technology China)
2019-09-16 14:16       ` Kirill A. Shutemov

Reply instructions:

You may reply publically 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=20190913163239.125108-3-justin.he@arm.com \
    --to=justin.he@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=punitagrawal@gmail.com \
    --cc=rcampbell@nvidia.com \
    --cc=robin.murphy@arm.com \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=yaojun8558363@gmail.com \
    /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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org linux-mm@archiver.kernel.org
	public-inbox-index linux-mm


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/ public-inbox