From: Laurent Dufour <ldufour@linux.vnet.ibm.com>
To: akpm@linux-foundation.org, mhocko@kernel.org,
peterz@infradead.org, kirill@shutemov.name, ak@linux.intel.com,
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,
Daniel Jordan <daniel.m.jordan@oracle.com>,
David Rientjes <rientjes@google.com>,
Jerome Glisse <jglisse@redhat.com>,
Ganesh Mahendran <opensource.ganesh@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,
paulmck@linux.vnet.ibm.com, Tim Chen <tim.c.chen@linux.intel.com>,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org
Subject: [PATCH v10 04/25] mm: prepare for FAULT_FLAG_SPECULATIVE
Date: Tue, 17 Apr 2018 16:33:10 +0200 [thread overview]
Message-ID: <1523975611-15978-5-git-send-email-ldufour@linux.vnet.ibm.com> (raw)
In-Reply-To: <1523975611-15978-1-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]
[move pte_map_lock()'s definition upper in the file]
[move the define of FAULT_FLAG_SPECULATIVE later in the series]
[review error path in do_swap_page(), do_anonymous_page() and
wp_page_copy()]
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
mm/memory.c | 87 ++++++++++++++++++++++++++++++++++++++++---------------------
1 file changed, 58 insertions(+), 29 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index a1f990e33e38..4528bd584b7a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2288,6 +2288,13 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
}
EXPORT_SYMBOL_GPL(apply_to_page_range);
+static inline 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_pte_fault chooses page fault handler according to an entry which was
* read non-atomically. Before making any commitment, on those architectures
@@ -2477,25 +2484,26 @@ 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;
+ goto out;
if (is_zero_pfn(pte_pfn(vmf->orig_pte))) {
new_page = alloc_zeroed_user_highpage_movable(vma,
vmf->address);
if (!new_page)
- goto oom;
+ goto out;
} else {
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
vmf->address);
if (!new_page)
- goto oom;
+ goto out;
cow_user_page(new_page, old_page, vmf->address, vma);
}
if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
- goto oom_free_new;
+ goto out_free_new;
__SetPageUptodate(new_page);
@@ -2504,7 +2512,10 @@ 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)) {
+ ret = VM_FAULT_RETRY;
+ goto out_uncharge;
+ }
if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
@@ -2591,12 +2602,14 @@ static int wp_page_copy(struct vm_fault *vmf)
put_page(old_page);
}
return page_copied ? VM_FAULT_WRITE : 0;
-oom_free_new:
+out_uncharge:
+ mem_cgroup_cancel_charge(new_page, memcg, false);
+out_free_new:
put_page(new_page);
-oom:
+out:
if (old_page)
put_page(old_page);
- return VM_FAULT_OOM;
+ return ret;
}
/**
@@ -2617,8 +2630,8 @@ 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.
@@ -2736,8 +2749,11 @@ 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);
@@ -2944,11 +2960,15 @@ int do_swap_page(struct vm_fault *vmf)
if (!page) {
/*
- * Back out if somebody else faulted in this pte
- * while we released the pte lock.
+ * Back out if the VMA has changed in our back during
+ * a speculative page fault or 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);
+ ret = VM_FAULT_RETRY;
+ goto out;
+ }
if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
ret = VM_FAULT_OOM;
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
@@ -3001,10 +3021,13 @@ int do_swap_page(struct vm_fault *vmf)
}
/*
- * Back out if somebody else already faulted in this pte.
+ * Back out if the VMA has changed in our back during a speculative
+ * page fault or 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;
+ goto out_cancel_cgroup;
+ }
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte)))
goto out_nomap;
@@ -3082,8 +3105,9 @@ int do_swap_page(struct vm_fault *vmf)
out:
return ret;
out_nomap:
- mem_cgroup_cancel_charge(page, memcg, false);
pte_unmap_unlock(vmf->pte, vmf->ptl);
+out_cancel_cgroup:
+ mem_cgroup_cancel_charge(page, memcg, false);
out_page:
unlock_page(page);
out_release:
@@ -3134,8 +3158,8 @@ 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);
@@ -3170,14 +3194,16 @@ 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_none(*vmf->pte))
+ if (!pte_map_lock(vmf)) {
+ ret = VM_FAULT_RETRY;
goto release;
+ }
+ if (!pte_none(*vmf->pte))
+ goto unlock_and_release;
ret = check_stable_address_space(vma->vm_mm);
if (ret)
- goto release;
+ goto unlock_and_release;
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
@@ -3199,10 +3225,12 @@ static int do_anonymous_page(struct vm_fault *vmf)
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
+unlock_and_release:
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
release:
mem_cgroup_cancel_charge(page, memcg, false);
put_page(page);
- goto unlock;
+ return ret;
oom_free_page:
put_page(page);
oom:
@@ -3295,8 +3323,9 @@ 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:[~2018-04-17 14:34 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-17 14:33 [PATCH v10 00/25] Speculative page faults Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 01/25] mm: introduce CONFIG_SPECULATIVE_PAGE_FAULT Laurent Dufour
2018-04-23 5:58 ` Minchan Kim
2018-04-23 15:10 ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 02/25] x86/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Laurent Dufour
2018-05-08 11:04 ` Punit Agrawal
2018-05-14 14:47 ` Laurent Dufour
2018-05-14 15:05 ` Punit Agrawal
2018-04-17 14:33 ` [PATCH v10 03/25] powerpc/mm: set ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Laurent Dufour
2018-04-17 14:33 ` Laurent Dufour [this message]
2018-04-17 14:33 ` [PATCH v10 05/25] mm: introduce pte_spinlock for FAULT_FLAG_SPECULATIVE Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 06/25] mm: make pte_unmap_same compatible with SPF Laurent Dufour
2018-04-23 6:31 ` Minchan Kim
2018-04-30 14:07 ` Laurent Dufour
2018-05-01 13:04 ` Minchan Kim
2018-05-10 16:15 ` vinayak menon
2018-05-14 15:09 ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 07/25] mm: introduce INIT_VMA() Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 08/25] mm: VMA sequence count Laurent Dufour
2018-04-23 6:42 ` Minchan Kim
2018-04-30 15:14 ` Laurent Dufour
2018-05-01 13:16 ` Minchan Kim
2018-05-03 14:45 ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 09/25] mm: protect VMA modifications using " Laurent Dufour
2018-04-23 7:19 ` Minchan Kim
2018-05-14 15:25 ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 10/25] mm: protect mremap() against SPF hanlder Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 11/25] mm: protect SPF handler against anon_vma changes Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 12/25] mm: cache some VMA fields in the vm_fault structure Laurent Dufour
2018-04-23 7:42 ` Minchan Kim
2018-05-03 12:25 ` Laurent Dufour
2018-05-03 15:42 ` Minchan Kim
2018-05-04 9:10 ` Laurent Dufour
2018-05-08 10:56 ` Minchan Kim
2018-04-17 14:33 ` [PATCH v10 13/25] mm/migrate: Pass vm_fault pointer to migrate_misplaced_page() Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 14/25] mm: introduce __lru_cache_add_active_or_unevictable Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 15/25] mm: introduce __vm_normal_page() Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 16/25] mm: introduce __page_add_new_anon_rmap() Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 17/25] mm: protect mm_rb tree with a rwlock Laurent Dufour
2018-04-30 18:47 ` Punit Agrawal
2018-05-02 6:37 ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 18/25] mm: provide speculative fault infrastructure Laurent Dufour
2018-05-15 13:09 ` vinayak menon
2018-05-15 14:07 ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 19/25] mm: adding speculative page fault failure trace events Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 20/25] perf: add a speculative page fault sw event Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 21/25] perf tools: add support for the SPF perf event Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 22/25] mm: speculative page fault handler return VMA Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 23/25] mm: add speculative page fault vmstats Laurent Dufour
2018-05-16 2:50 ` Ganesh Mahendran
2018-05-16 6:42 ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 24/25] x86/mm: add speculative pagefault handling Laurent Dufour
2018-04-30 18:43 ` Punit Agrawal
2018-05-03 14:59 ` Laurent Dufour
2018-05-04 15:55 ` Punit Agrawal
2018-04-17 14:33 ` [PATCH v10 25/25] powerpc/mm: add speculative page fault Laurent Dufour
2018-04-17 16:51 ` [PATCH v10 00/25] Speculative page faults Christopher Lameter
2018-05-02 14:17 ` Punit Agrawal
2018-05-02 14:45 ` Laurent Dufour
2018-05-02 15:50 ` Punit Agrawal
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=1523975611-15978-5-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=daniel.m.jordan@oracle.com \
--cc=dave@stgolabs.net \
--cc=haren@linux.vnet.ibm.com \
--cc=hpa@zytor.com \
--cc=jack@suse.cz \
--cc=jglisse@redhat.com \
--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=opensource.ganesh@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=rientjes@google.com \
--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).