The patch titled
cross-memory-attach-v4
has been added to the -mm tree. Its filename is
cross-memory-attach-v4.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: cross-memory-attach-v4
From: Christopher Yeoh <cyeoh@xxxxxxxxxxx>
> You might get some speed benefit by optimising for the small copies
> here. Define a local on-stack array of N page*'s and point
> process_pages at that if the number of pages is <= N. Saves a
> malloc/free and is more cache-friendly. But only if the result is
> measurable!
I have done some benchmarking on this, and it gains about 5-7% on a
microbenchmark with 4kb size copies and about a 1% gain with a more
realistic (but modified for smaller copies) hpcc benchmark. The
performance gain disappears into the noise by about 64kb sized copies.
No measurable overhead for larger copies. So I think its worth including
Included below is the patch (based on v4) - for ease of review the first diff
is just against the latest version of CMA which has been posted here previously.
The second is the entire CMA patch.
Signed-off-by: Chris Yeoh <cyeoh@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: James Morris <jmorris@xxxxxxxxx>
Cc: <linux-man@xxxxxxxxxxxxxxx>
Cc: <linux-arch@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/process_vm_access.c | 25 +++++++++++++++++--------
1 file changed, 17 insertions(+), 8 deletions(-)
diff -puN mm/process_vm_access.c~cross-memory-attach-v4 mm/process_vm_access.c
--- a/mm/process_vm_access.c~cross-memory-attach-v4
+++ a/mm/process_vm_access.c
@@ -221,6 +221,10 @@ static int process_vm_rw_single_vec(unsi
return rc;
}
+/* Maximum number of entries for process pages array
+ which lives on stack */
+#define PVM_MAX_PP_ARRAY_COUNT 16
+
/**
* process_vm_rw_core - core of reading/writing pages from task specified
* @pid: PID of process to read/write from/to
@@ -241,7 +245,8 @@ static ssize_t process_vm_rw_core(pid_t
unsigned long flags, int vm_write)
{
struct task_struct *task;
- struct page **process_pages = NULL;
+ struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT];
+ struct page **process_pages = pp_stack;
struct mm_struct *mm;
unsigned long i;
ssize_t rc = 0;
@@ -271,13 +276,16 @@ static ssize_t process_vm_rw_core(pid_t
if (nr_pages == 0)
return 0;
- /* For reliability don't try to kmalloc more than 2 pages worth */
- process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
- sizeof(struct pages *)*nr_pages),
- GFP_KERNEL);
+ if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) {
+ /* For reliability don't try to kmalloc more than
+ 2 pages worth */
+ process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES,
+ sizeof(struct pages *)*nr_pages),
+ GFP_KERNEL);
- if (!process_pages)
- return -ENOMEM;
+ if (!process_pages)
+ return -ENOMEM;
+ }
/* Get process information */
rcu_read_lock();
@@ -331,7 +339,8 @@ put_task_struct:
put_task_struct(task);
free_proc_pages:
- kfree(process_pages);
+ if (process_pages != pp_stack)
+ kfree(process_pages);
return rc;
}
_
Patches currently in -mm which might be from cyeoh@xxxxxxxxxxx are
cross-memory-attach-v3.patch
cross-memory-attach-update.patch
cross-memory-attach-v4.patch
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
