Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Song Liu <song@kernel.org>
To:     <linux-kernel@vger.kernel.org>, <bpf@vger.kernel.org>
CC:     <ast@kernel.org>, <daniel@iogearbox.net>, <peterz@infradead.org>,
        <mcgrof@kernel.org>, <torvalds@linux-foundation.org>,
        <rick.p.edgecombe@intel.com>, <kernel-team@fb.com>,
        Song Liu <song@kernel.org>
Subject: [PATCH bpf-next 5/5] bpf: use module_alloc_huge for bpf_prog_pack
Date:   Sun, 15 May 2022 22:40:51 -0700
Message-ID: <20220516054051.114490-6-song@kernel.org>
In-Reply-To: <20220516054051.114490-1-song@kernel.org>
References: <20220516054051.114490-1-song@kernel.org>
Content-Type: text/plain
Content-Transfer-Encoding: 8BIT
MIME-Version: 1.0
Precedence: bulk

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 --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index cacd8684c3c4..b64d91fcb0ba 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
 		       GFP_KERNEL);
 	if (!pack)
 		return NULL;
-	pack->ptr = module_alloc(bpf_prog_pack_size);
+	pack->ptr = module_alloc_huge(bpf_prog_pack_size);
 	if (!pack->ptr) {
 		kfree(pack);
 		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)
 
 	mutex_lock(&pack_mutex);
 	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);
 		module_memfree(hdr);
 		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) {
 		list_del(&pack->list);
+		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);
 		module_memfree(pack->ptr);
 		kfree(pack);
 	}
-- 
2.30.2