tmakin/ack-tegra
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

kernel: relay: use __GFP_ZERO in relay_alloc_buf

Browse Source 
Passing the __GFP_ZERO flag to alloc_page should result in less overhead
th= an using memset()

Link: https://lkml.kernel.org/r/20250610225639.314970-3-git@elijahs.space
Signed-off-by: Elijah Wright <git@elijahs.space>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Elijah Wright authored and Andrew Morton committed 2025-07-09 22:57:50 -07:00
1 parent f7b0ff2bc9
commit 0ba5a25ad1
1 file changed
+1 -2
Download Patch File Download Diff File Expand all files Collapse all files
kernel/relay.c
+1 -2
View File
@@ -118,7 +118,7 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
return NULL;
for (i = 0; i < n_pages; i++) {
buf->page_array[i] = alloc_page(GFP_KERNEL);
buf->page_array[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (unlikely(!buf->page_array[i]))
goto depopulate;
set_page_private(buf->page_array[i], (unsigned long)buf);
@@ -127,7 +127,6 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
if (!mem)
goto depopulate;
memset(mem, 0, *size);
buf->page_count = n_pages;
return mem;