diff mbox series

[v5,bpf-next,2/5] bpf: use module_alloc_huge for bpf_prog_pack

Message ID 20220624215712.3050672-3-song@kernel.org (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf_prog_pack followup | expand


Context Check Description
netdev/tree_selection success Clearly marked for bpf-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 7 this patch: 7
netdev/cc_maintainers warning 8 maintainers not CCed: songliubraving@fb.com ast@kernel.org bpf@vger.kernel.org yhs@fb.com john.fastabend@gmail.com kafai@fb.com andrii@kernel.org kpsingh@kernel.org
netdev/build_clang success Errors and warnings before: 6 this patch: 6
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 7 this patch: 7
netdev/checkpatch warning WARNING: line length of 88 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-PR fail PR summary
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Kernel LATEST on z15 with gcc
bpf/vmtest-bpf-next-VM_Test-1 fail Logs for Kernel LATEST on ubuntu-latest with gcc
bpf/vmtest-bpf-next-VM_Test-2 fail Logs for Kernel LATEST on ubuntu-latest with llvm-15

Commit Message

Song Liu June 24, 2022, 9:57 p.m. UTC
Use module_alloc_huge for bpf_prog_pack so that BPF programs sit on
PMD_SIZE pages. This benefits system performance by reducing iTLB miss
rate. Benchmark of a real web service workload shows this change gives
another ~0.2% performance boost on top of PAGE_SIZE bpf_prog_pack
(which improve system throughput by ~0.5%).

Also, remove set_vm_flush_reset_perms() from alloc_new_pack() and use
set_memory_[nx|rw] in bpf_prog_pack_free(). This is because
VM_FLUSH_RESET_PERMS does not work with huge pages yet. [1]

[1] https://lore.kernel.org/bpf/aeeeaf0b7ec63fdba55d4834d2f524d8bf05b71b.camel@intel.com/
Suggested-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Song Liu <song@kernel.org>
 kernel/bpf/core.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)
diff mbox series


diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f023cb399e3f..83f5a98517d5 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -857,7 +857,7 @@  static size_t select_bpf_prog_pack_size(void)
 	void *ptr;
 	size = BPF_HPAGE_SIZE * num_online_nodes();
-	ptr = module_alloc(size);
+	ptr = module_alloc_huge(size);
 	/* Test whether we can get huge pages. If not just use PAGE_SIZE
 	 * packs.
@@ -881,7 +881,7 @@  static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
 	if (!pack)
 		return NULL;
-	pack->ptr = module_alloc(bpf_prog_pack_size);
+	pack->ptr = module_alloc_huge(bpf_prog_pack_size);
 	if (!pack->ptr) {
 		return NULL;
@@ -890,7 +890,6 @@  static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
 	bitmap_zero(pack->bitmap, bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE);
 	list_add_tail(&pack->list, &pack_list);
-	set_vm_flush_reset_perms(pack->ptr);
 	set_memory_ro((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);
 	set_memory_x((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);
 	return pack;
@@ -909,10 +908,9 @@  static void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insn
 	if (size > bpf_prog_pack_size) {
 		size = round_up(size, PAGE_SIZE);
-		ptr = module_alloc(size);
+		ptr = module_alloc_huge(size);
 		if (ptr) {
 			bpf_fill_ill_insns(ptr, size);
-			set_vm_flush_reset_perms(ptr);
 			set_memory_ro((unsigned long)ptr, size / PAGE_SIZE);
 			set_memory_x((unsigned long)ptr, size / PAGE_SIZE);
@@ -949,6 +947,8 @@  static void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 	if (hdr->size > bpf_prog_pack_size) {
+		set_memory_nx((unsigned long)hdr, hdr->size / PAGE_SIZE);
+		set_memory_rw((unsigned long)hdr, hdr->size / PAGE_SIZE);
 		goto out;
@@ -975,6 +975,8 @@  static void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 	if (bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0,
 				       bpf_prog_chunk_count(), 0) == 0) {
+		set_memory_nx((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);
+		set_memory_rw((unsigned long)pack->ptr, bpf_prog_pack_size / PAGE_SIZE);