From: Laurent Dufour <ldufour@linux.vnet.ibm.com>
To: paulmck@linux.vnet.ibm.com, peterz@infradead.org,
akpm@linux-foundation.org, kirill@shutemov.name,
ak@linux.intel.com, mhocko@kernel.org, dave@stgolabs.net,
jack@suse.cz, Matthew Wilcox <willy@infradead.org>,
benh@kernel.crashing.org, mpe@ellerman.id.au, paulus@samba.org,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
hpa@zytor.com, Will Deacon <will.deacon@arm.com>,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Alexei Starovoitov <alexei.starovoitov@gmail.com>,
kemi.wang@intel.com, sergey.senozhatsky.work@gmail.com
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
haren@linux.vnet.ibm.com, khandual@linux.vnet.ibm.com,
npiggin@gmail.com, bsingharora@gmail.com,
Tim Chen <tim.c.chen@linux.intel.com>,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org
Subject: [PATCH v6 04/24] mm: Prepare for FAULT_FLAG_SPECULATIVE
Date: Fri, 12 Jan 2018 18:25:48 +0100 [thread overview]
Message-ID: <1515777968-867-5-git-send-email-ldufour@linux.vnet.ibm.com> (raw)
In-Reply-To: <1515777968-867-1-git-send-email-ldufour@linux.vnet.ibm.com>
From: Peter Zijlstra <peterz@infradead.org>
When speculating faults (without holding mmap_sem) we need to validate
that the vma against which we loaded pages is still valid when we're
ready to install the new PTE.
Therefore, replace the pte_offset_map_lock() calls that (re)take the
PTL with pte_map_lock() which can fail in case we find the VMA changed
since we started the fault.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[Port to 4.12 kernel]
[Remove the comment about the fault_env structure which has been
implemented as the vm_fault structure in the kernel]
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
include/linux/mm.h | 1 +
mm/memory.c | 56 ++++++++++++++++++++++++++++++++++++++----------------
2 files changed, 41 insertions(+), 16 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 63f7ba111f64..ad299ed7b85c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -302,6 +302,7 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */
#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */
+#define FAULT_FLAG_SPECULATIVE 0x200 /* Speculative fault, not holding mmap_sem */
#define FAULT_FLAG_TRACE \
{ FAULT_FLAG_WRITE, "WRITE" }, \
diff --git a/mm/memory.c b/mm/memory.c
index 259f621345b2..868424ab850c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2438,6 +2438,13 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
+static bool pte_map_lock(struct vm_fault *vmf)
+{
+ vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
+ vmf->address, &vmf->ptl);
+ return true;
+}
+
/*
* Handle the case of a page which we actually need to copy to a new page.
*
@@ -2465,6 +2472,7 @@ static int wp_page_copy(struct vm_fault *vmf)
const unsigned long mmun_start = vmf->address & PAGE_MASK;
const unsigned long mmun_end = mmun_start + PAGE_SIZE;
struct mem_cgroup *memcg;
+ int ret = VM_FAULT_OOM;
if (unlikely(anon_vma_prepare(vma)))
goto oom;
@@ -2492,7 +2500,11 @@ static int wp_page_copy(struct vm_fault *vmf)
/*
* Re-check the pte - we dropped the lock
*/
- vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ mem_cgroup_cancel_charge(new_page, memcg, false);
+ ret = VM_FAULT_RETRY;
+ goto oom_free_new;
+ }
if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
@@ -2584,7 +2596,7 @@ static int wp_page_copy(struct vm_fault *vmf)
oom:
if (old_page)
put_page(old_page);
- return VM_FAULT_OOM;
+ return ret;
}
/**
@@ -2605,8 +2617,8 @@ static int wp_page_copy(struct vm_fault *vmf)
int finish_mkwrite_fault(struct vm_fault *vmf)
{
WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
- vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf))
+ return VM_FAULT_RETRY;
/*
* We might have raced with another page fault while we released the
* pte_offset_map_lock.
@@ -2724,8 +2736,11 @@ static int do_wp_page(struct vm_fault *vmf)
get_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
lock_page(vmf->page);
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
- vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ unlock_page(vmf->page);
+ put_page(vmf->page);
+ return VM_FAULT_RETRY;
+ }
if (!pte_same(*vmf->pte, vmf->orig_pte)) {
unlock_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2953,8 +2968,10 @@ int do_swap_page(struct vm_fault *vmf)
* Back out if somebody else faulted in this pte
* while we released the pte lock.
*/
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
- vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+ return VM_FAULT_RETRY;
+ }
if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
ret = VM_FAULT_OOM;
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
@@ -3010,8 +3027,11 @@ int do_swap_page(struct vm_fault *vmf)
/*
* Back out if somebody else already faulted in this pte.
*/
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ ret = VM_FAULT_RETRY;
+ mem_cgroup_cancel_charge(page, memcg, false);
+ goto out_page;
+ }
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte)))
goto out_nomap;
@@ -3140,8 +3160,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
!mm_forbids_zeropage(vma->vm_mm)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
vma->vm_page_prot));
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
- vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf))
+ return VM_FAULT_RETRY;
if (!pte_none(*vmf->pte))
goto unlock;
ret = check_stable_address_space(vma->vm_mm);
@@ -3176,8 +3196,11 @@ static int do_anonymous_page(struct vm_fault *vmf)
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ mem_cgroup_cancel_charge(page, memcg, false);
+ put_page(page);
+ return VM_FAULT_RETRY;
+ }
if (!pte_none(*vmf->pte))
goto release;
@@ -3301,8 +3324,9 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
* pte_none() under vmf->ptl protection when we return to
* alloc_set_pte().
*/
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf))
+ return VM_FAULT_RETRY;
+
return 0;
}
--
2.7.4
next prev parent reply other threads:[~2018-01-12 17:26 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-12 17:25 [PATCH v6 00/24] Speculative page faults Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 01/24] x86/mm: Define CONFIG_SPF Laurent Dufour
2018-01-12 18:57 ` Thomas Gleixner
2018-01-15 17:37 ` Laurent Dufour
2018-01-15 17:49 ` Thomas Gleixner
2018-01-15 18:37 ` Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 02/24] powerpc/mm: " Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 03/24] mm: Dont assume page-table invariance during faults Laurent Dufour
2018-01-17 3:04 ` Andi Kleen
2018-01-17 8:57 ` Laurent Dufour
2018-01-12 17:25 ` Laurent Dufour [this message]
2018-01-12 17:25 ` [PATCH v6 05/24] mm: Introduce pte_spinlock for FAULT_FLAG_SPECULATIVE Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 06/24] mm: VMA sequence count Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 07/24] mm: Protect VMA modifications using " Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 08/24] mm: protect mremap() against SPF hanlder Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 09/24] mm: Protect SPF handler against anon_vma changes Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 10/24] mm: Cache some VMA fields in the vm_fault structure Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 11/24] mm/migrate: Pass vm_fault pointer to migrate_misplaced_page() Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 12/24] mm: Introduce __lru_cache_add_active_or_unevictable Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 13/24] mm: Introduce __maybe_mkwrite() Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 14/24] mm: Introduce __vm_normal_page() Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 15/24] mm: Introduce __page_add_new_anon_rmap() Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 16/24] mm: Protect mm_rb tree with a rwlock Laurent Dufour
2018-01-12 18:48 ` Matthew Wilcox
2018-01-15 17:42 ` Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 17/24] mm: Provide speculative fault infrastructure Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 18/24] mm: Try spin lock in speculative path Laurent Dufour
2018-01-12 18:18 ` Matthew Wilcox
2018-01-16 13:24 ` Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 19/24] mm: Adding speculative page fault failure trace events Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 20/24] perf: Add a speculative page fault sw event Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 21/24] perf tools: Add support for the SPF perf event Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 22/24] mm: Speculative page fault handler return VMA Laurent Dufour
2018-01-12 19:02 ` Matthew Wilcox
2018-01-13 4:23 ` Matthew Wilcox
2018-01-16 14:47 ` Laurent Dufour
2018-01-16 14:58 ` Matthew Wilcox
2018-01-12 17:26 ` [PATCH v6 23/24] x86/mm: Add speculative pagefault handling Laurent Dufour
2018-01-12 17:26 ` [PATCH v6 24/24] powerpc/mm: Add speculative page fault Laurent Dufour
2018-01-16 15:11 ` [PATCH v6 00/24] Speculative page faults Kirill A. Shutemov
2018-01-17 15:15 ` Laurent Dufour
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=1515777968-867-5-git-send-email-ldufour@linux.vnet.ibm.com \
--to=ldufour@linux.vnet.ibm.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=alexei.starovoitov@gmail.com \
--cc=benh@kernel.crashing.org \
--cc=bsingharora@gmail.com \
--cc=dave@stgolabs.net \
--cc=haren@linux.vnet.ibm.com \
--cc=hpa@zytor.com \
--cc=jack@suse.cz \
--cc=kemi.wang@intel.com \
--cc=khandual@linux.vnet.ibm.com \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mhocko@kernel.org \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=sergey.senozhatsky.work@gmail.com \
--cc=sergey.senozhatsky@gmail.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=will.deacon@arm.com \
--cc=willy@infradead.org \
--cc=x86@kernel.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).