From 09eaf695861920af444b0905e41e3cb0bfdb9e43 Mon Sep 17 00:00:00 2001 From: Christopher Yeoh Date: Wed, 5 Oct 2011 11:42:44 +1100 Subject: [PATCH] cross-memory-attach-v4 > 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 Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: Arnd Bergmann Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: David Howells Cc: James Morris Cc: Cc: Signed-off-by: Andrew Morton --- mm/process_vm_access.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 5ac8abc0d09b..e920aa3ce104 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -221,6 +221,10 @@ static int process_vm_rw_single_vec(unsigned long addr, 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 pid, const struct iovec *lvec, 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 pid, const struct iovec *lvec, 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; } -- 2.39.5