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 19/24] mm: Adding speculative page fault failure trace events
Date: Fri, 12 Jan 2018 18:26:03 +0100 [thread overview]
Message-ID: <1515777968-867-20-git-send-email-ldufour@linux.vnet.ibm.com> (raw)
In-Reply-To: <1515777968-867-1-git-send-email-ldufour@linux.vnet.ibm.com>
This patch a set of new trace events to collect the speculative page fault
event failures.
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
include/trace/events/pagefault.h | 87 ++++++++++++++++++++++++++++++++++++++++
mm/memory.c | 62 ++++++++++++++++++++++------
2 files changed, 136 insertions(+), 13 deletions(-)
create mode 100644 include/trace/events/pagefault.h
diff --git a/include/trace/events/pagefault.h b/include/trace/events/pagefault.h
new file mode 100644
index 000000000000..1d793f8c739b
--- /dev/null
+++ b/include/trace/events/pagefault.h
@@ -0,0 +1,87 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM pagefault
+
+#if !defined(_TRACE_PAGEFAULT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PAGEFAULT_H
+
+#include <linux/tracepoint.h>
+#include <linux/mm.h>
+
+DECLARE_EVENT_CLASS(spf,
+
+ TP_PROTO(unsigned long caller,
+ struct vm_area_struct *vma, unsigned long address),
+
+ TP_ARGS(caller, vma, address),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, caller)
+ __field(unsigned long, vm_start)
+ __field(unsigned long, vm_end)
+ __field(unsigned long, address)
+ ),
+
+ TP_fast_assign(
+ __entry->caller = caller;
+ __entry->vm_start = vma->vm_start;
+ __entry->vm_end = vma->vm_end;
+ __entry->address = address;
+ ),
+
+ TP_printk("ip:%lx vma:%lx-%lx address:%lx",
+ __entry->caller, __entry->vm_start, __entry->vm_end,
+ __entry->address)
+);
+
+DEFINE_EVENT(spf, spf_pte_lock,
+
+ TP_PROTO(unsigned long caller,
+ struct vm_area_struct *vma, unsigned long address),
+
+ TP_ARGS(caller, vma, address)
+);
+
+DEFINE_EVENT(spf, spf_vma_changed,
+
+ TP_PROTO(unsigned long caller,
+ struct vm_area_struct *vma, unsigned long address),
+
+ TP_ARGS(caller, vma, address)
+);
+
+DEFINE_EVENT(spf, spf_vma_noanon,
+
+ TP_PROTO(unsigned long caller,
+ struct vm_area_struct *vma, unsigned long address),
+
+ TP_ARGS(caller, vma, address)
+);
+
+DEFINE_EVENT(spf, spf_vma_notsup,
+
+ TP_PROTO(unsigned long caller,
+ struct vm_area_struct *vma, unsigned long address),
+
+ TP_ARGS(caller, vma, address)
+);
+
+DEFINE_EVENT(spf, spf_vma_access,
+
+ TP_PROTO(unsigned long caller,
+ struct vm_area_struct *vma, unsigned long address),
+
+ TP_ARGS(caller, vma, address)
+);
+
+DEFINE_EVENT(spf, spf_pmd_changed,
+
+ TP_PROTO(unsigned long caller,
+ struct vm_area_struct *vma, unsigned long address),
+
+ TP_ARGS(caller, vma, address)
+);
+
+#endif /* _TRACE_PAGEFAULT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/memory.c b/mm/memory.c
index 83640079d407..6ccb1f45473a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -80,6 +80,9 @@
#include "internal.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/pagefault.h>
+
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif
@@ -2460,23 +2463,30 @@ static bool pte_spinlock(struct vm_fault *vmf)
}
local_irq_disable();
- if (vma_has_changed(vmf))
+ if (vma_has_changed(vmf)) {
+ trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address);
goto out;
+ }
/*
* We check if the pmd value is still the same to ensure that there
* is a huge collapse operation in progress in our back.
*/
pmdval = READ_ONCE(*vmf->pmd);
- if (!pmd_same(pmdval, vmf->orig_pmd))
+ if (!pmd_same(pmdval, vmf->orig_pmd)) {
+ trace_spf_pmd_changed(_RET_IP_, vmf->vma, vmf->address);
goto out;
+ }
vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
- if (unlikely(!spin_trylock(vmf->ptl)))
+ if (unlikely(!spin_trylock(vmf->ptl))) {
+ trace_spf_pte_lock(_RET_IP_, vmf->vma, vmf->address);
goto out;
+ }
if (vma_has_changed(vmf)) {
spin_unlock(vmf->ptl);
+ trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address);
goto out;
}
@@ -2516,16 +2526,20 @@ static bool pte_map_lock(struct vm_fault *vmf)
* block on the PTL and thus we're safe.
*/
local_irq_disable();
- if (vma_has_changed(vmf))
+ if (vma_has_changed(vmf)) {
+ trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address);
goto out;
+ }
/*
* We check if the pmd value is still the same to ensure that there
* is a huge collapse operation in progress in our back.
*/
pmdval = READ_ONCE(*vmf->pmd);
- if (!pmd_same(pmdval, vmf->orig_pmd))
+ if (!pmd_same(pmdval, vmf->orig_pmd)) {
+ trace_spf_pmd_changed(_RET_IP_, vmf->vma, vmf->address);
goto out;
+ }
/*
* Same as pte_offset_map_lock() except that we call
@@ -2538,11 +2552,13 @@ static bool pte_map_lock(struct vm_fault *vmf)
pte = pte_offset_map(vmf->pmd, vmf->address);
if (unlikely(!spin_trylock(ptl))) {
pte_unmap(pte);
+ trace_spf_pte_lock(_RET_IP_, vmf->vma, vmf->address);
goto out;
}
if (vma_has_changed(vmf)) {
pte_unmap_unlock(pte, ptl);
+ trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address);
goto out;
}
@@ -4297,47 +4313,60 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address,
return ret;
seq = raw_read_seqcount(&vma->vm_sequence); /* rmb <-> seqlock,vma_rb_erase() */
- if (seq & 1)
+ if (seq & 1) {
+ trace_spf_vma_changed(_RET_IP_, vma, address);
goto out_put;
+ }
/*
* Can't call vm_ops service has we don't know what they would do
* with the VMA.
* This include huge page from hugetlbfs.
*/
- if (vma->vm_ops)
+ if (vma->vm_ops) {
+ trace_spf_vma_notsup(_RET_IP_, vma, address);
goto out_put;
+ }
/*
* __anon_vma_prepare() requires the mmap_sem to be held
* because vm_next and vm_prev must be safe. This can't be guaranteed
* in the speculative path.
*/
- if (unlikely(!vma->anon_vma))
+ if (unlikely(!vma->anon_vma)) {
+ trace_spf_vma_notsup(_RET_IP_, vma, address);
goto out_put;
+ }
vmf.vma_flags = READ_ONCE(vma->vm_flags);
vmf.vma_page_prot = READ_ONCE(vma->vm_page_prot);
/* Can't call userland page fault handler in the speculative path */
- if (unlikely(vmf.vma_flags & VM_UFFD_MISSING))
+ if (unlikely(vmf.vma_flags & VM_UFFD_MISSING)) {
+ trace_spf_vma_notsup(_RET_IP_, vma, address);
goto out_put;
+ }
- if (vmf.vma_flags & VM_GROWSDOWN || vmf.vma_flags & VM_GROWSUP)
+ if (vmf.vma_flags & VM_GROWSDOWN || vmf.vma_flags & VM_GROWSUP) {
/*
* This could be detected by the check address against VMA's
* boundaries but we want to trace it as not supported instead
* of changed.
*/
+ trace_spf_vma_notsup(_RET_IP_, vma, address);
goto out_put;
+ }
if (address < READ_ONCE(vma->vm_start)
- || READ_ONCE(vma->vm_end) <= address)
+ || READ_ONCE(vma->vm_end) <= address) {
+ trace_spf_vma_changed(_RET_IP_, vma, address);
goto out_put;
+ }
if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
flags & FAULT_FLAG_INSTRUCTION,
flags & FAULT_FLAG_REMOTE)) {
+ trace_spf_vma_access(_RET_IP_, vma, address);
ret = VM_FAULT_SIGSEGV;
goto out_put;
}
@@ -4345,10 +4374,12 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address,
/* This is one is required to check that the VMA has write access set */
if (flags & FAULT_FLAG_WRITE) {
if (unlikely(!(vmf.vma_flags & VM_WRITE))) {
+ trace_spf_vma_access(_RET_IP_, vma, address);
ret = VM_FAULT_SIGSEGV;
goto out_put;
}
} else if (unlikely(!(vmf.vma_flags & (VM_READ|VM_EXEC|VM_WRITE)))) {
+ trace_spf_vma_access(_RET_IP_, vma, address);
ret = VM_FAULT_SIGSEGV;
goto out_put;
}
@@ -4361,8 +4392,10 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address,
pol = __get_vma_policy(vma, address);
if (!pol)
pol = get_task_policy(current);
- if (pol && pol->mode == MPOL_INTERLEAVE)
+ if (pol && pol->mode == MPOL_INTERLEAVE) {
+ trace_spf_vma_notsup(_RET_IP_, vma, address);
goto out_put;
+ }
#endif
/*
@@ -4435,8 +4468,10 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address,
* We need to re-validate the VMA after checking the bounds, otherwise
* we might have a false positive on the bounds.
*/
- if (read_seqcount_retry(&vma->vm_sequence, seq))
+ if (read_seqcount_retry(&vma->vm_sequence, seq)) {
+ trace_spf_vma_changed(_RET_IP_, vma, address);
goto out_put;
+ }
mem_cgroup_oom_enable();
ret = handle_pte_fault(&vmf);
@@ -4455,6 +4490,7 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address,
return ret;
out_walk:
+ trace_spf_vma_notsup(_RET_IP_, vma, address);
local_irq_enable();
out_put:
put_vma(vma);
--
2.7.4
next prev parent reply other threads:[~2018-01-12 17:27 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 ` [PATCH v6 04/24] mm: Prepare for FAULT_FLAG_SPECULATIVE Laurent Dufour
2018-01-12 17:25 ` [PATCH v6 05/24] mm: Introduce pte_spinlock " 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 ` Laurent Dufour [this message]
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=1515777968-867-20-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).