* [PATCH 02/20] alpha/mm/fault.c: Port OOM changes to do_page_fault
@ 2012-03-20 13:18 Kautuk Consul
[not found] ` <CAFPAmTTSrDkDLHoh0NQ8iAG-=vBXW3UwhWAXKfBa_Nk0gj07Xw@mail.gmail.com>
0 siblings, 1 reply; 2+ messages in thread
From: Kautuk Consul @ 2012-03-20 13:18 UTC (permalink / raw)
To: Richard Henderson, Ivan Kokshaysky, Matt Turner
Cc: linux-alpha, linux-kernel, Kautuk Consul, Mohd. Faris
Commit d065bd810b6deb67d4897a14bfe21f8eb526ba99
(mm: retry page fault when blocking on disk transfer) and
commit 37b23e0525d393d48a7d59f870b3bc061a30ccdb
(x86,mm: make pagefault killable)
The above commits introduced changes into the x86 pagefault handler
for making the page fault handler retryable as well as killable.
These changes reduce the mmap_sem hold time, which is crucial
during OOM killer invocation.
Port these changes to ALPHA.
Signed-off-by: Mohd. Faris <mohdfarisq2010@gmail.com>
Signed-off-by: Kautuk Consul <consul.kautuk@gmail.com>
---
arch/alpha/mm/fault.c | 37 +++++++++++++++++++++++++++++++------
1 files changed, 31 insertions(+), 6 deletions(-)
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index fadd5f8..eb2bc6d 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -90,6 +90,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
const struct exception_table_entry *fixup;
int fault, si_code = SEGV_MAPERR;
siginfo_t info;
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+ (cause > 0 ? FAULT_FLAG_WRITE : 0);
/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
(or is suppressed by the PALcode). Support that for older CPUs
@@ -115,6 +117,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
goto vmalloc_fault;
#endif
+retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
@@ -145,8 +148,11 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
/* If for any reason at all we couldn't handle the fault,
make sure we exit gracefully rather than endlessly redo
the fault. */
- fault = handle_mm_fault(mm, vma, address, cause > 0 ? FAULT_FLAG_WRITE : 0);
- up_read(&mm->mmap_sem);
+ fault = handle_mm_fault(mm, vma, address, flags);
+
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ return;
+
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
@@ -154,10 +160,27 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
goto do_sigbus;
BUG();
}
- if (fault & VM_FAULT_MAJOR)
- current->maj_flt++;
- else
- current->min_flt++;
+
+ if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (fault & VM_FAULT_MAJOR)
+ current->maj_flt++;
+ else
+ current->min_flt++;
+ if (fault & VM_FAULT_RETRY) {
+ flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+ /*
+ * No need to up_read(&mm->mmap_sem) as we would
+ * have already released it in __lock_page_or_retry
+ * in mm/filemap.c.
+ */
+
+ goto retry;
+ }
+ }
+
+ up_read(&mm->mmap_sem);
+
return;
/* Something tried to access memory that isn't in our memory map.
@@ -187,12 +210,14 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
/* We ran out of memory, or some other thing happened to us that
made us unable to handle the page fault gracefully. */
out_of_memory:
+ up_read(&mm->mmap_sem);
if (!user_mode(regs))
goto no_context;
pagefault_out_of_memory();
return;
do_sigbus:
+ up_read(&mm->mmap_sem);
/* Send a sigbus, regardless of whether we were in kernel
or user mode. */
info.si_signo = SIGBUS;
--
1.7.5.4
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH 02/20] alpha/mm/fault.c: Port OOM changes to do_page_fault
[not found] ` <CAEdQ38GOZi7t5BraBMhETuf=cDBVW7txkDH6guC0kZVXyqG04A@mail.gmail.com>
@ 2012-03-23 16:47 ` Kautuk Consul
0 siblings, 0 replies; 2+ messages in thread
From: Kautuk Consul @ 2012-03-23 16:47 UTC (permalink / raw)
To: Andrew Morton
Cc: Richard Henderson, Ivan Kokshaysky, Matt Turner, linux-alpha,
linux-kernel, Kautuk Consul, Mohd. Faris
Hi Andrew,
On Fri, Mar 23, 2012 at 12:40 PM, Matt Turner <mattst88@gmail.com> wrote:
> On Fri, Mar 23, 2012 at 12:33 PM, Kautuk Consul <consul.kautuk@gmail.com> wrote:
>>>> Can I improve this patch in any way ?
>>>
>>> Sorry, I just don't have time. I imagine that all these patches are
>>> going upstream through the same tree, so feel free to commit this
>>> patch with the rest. If there's a problem, we'll notice it later.
>>>
>>
>> Sorry, I'm quite new to this.
>> What do you mean by : "feel free to commit this patch with the rest" ?
>>
>> Does this mean I request someone on the list (like akpm) to include
>> this patch ?
>
> Yes, exactly. :)
Can you please include this patch into linux-next whenever it is OK with you ?
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2012-03-23 16:47 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2012-03-20 13:18 [PATCH 02/20] alpha/mm/fault.c: Port OOM changes to do_page_fault Kautuk Consul
[not found] ` <CAFPAmTTSrDkDLHoh0NQ8iAG-=vBXW3UwhWAXKfBa_Nk0gj07Xw@mail.gmail.com>
[not found] ` <CAEdQ38G5VVoPKr1ayMZrQ2ba7xa9ofnY+TK4SUqOb8kr5fBsMQ@mail.gmail.com>
[not found] ` <CAFPAmTQfbNv3A-j9OCRswj-VtB79ZLCSDdMC1KqBQdrVO6K54A@mail.gmail.com>
[not found] ` <CAEdQ38GOZi7t5BraBMhETuf=cDBVW7txkDH6guC0kZVXyqG04A@mail.gmail.com>
2012-03-23 16:47 ` Kautuk Consul
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).