From: Song Liu <song@kernel.org>
To: <bpf@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<linux-mm@kvack.org>
Cc: <daniel@iogearbox.net>, <kernel-team@fb.com>, <x86@kernel.org>,
<dave.hansen@linux.intel.com>, <rick.p.edgecombe@intel.com>,
<mcgrof@kernel.org>, Song Liu <song@kernel.org>
Subject: [PATCH v6 bpf-next 2/5] bpf: use module_alloc_huge for bpf_prog_pack
Date: Thu, 7 Jul 2022 15:35:43 -0700 [thread overview]
Message-ID: <20220707223546.4124919-3-song@kernel.org> (raw)
In-Reply-To: <20220707223546.4124919-1-song@kernel.org>
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 805c2ad5c793..d1f32ac354d3 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -860,7 +860,7 @@ 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.
@@ -884,7 +884,7 @@ 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;
@@ -893,7 +893,6 @@ 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;
@@ -912,10 +911,9 @@ 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);
}
@@ -952,6 +950,8 @@ 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;
}
@@ -978,6 +978,8 @@ 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
next prev parent reply other threads:[~2022-07-07 22:36 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-07 22:35 [PATCH v6 bpf-next 0/5] bpf_prog_pack followup Song Liu
2022-07-07 22:35 ` [PATCH v6 bpf-next 1/5] module: introduce module_alloc_huge Song Liu
2022-07-07 22:35 ` Song Liu [this message]
2022-07-07 22:35 ` [PATCH v6 bpf-next 3/5] vmalloc: WARN for set_vm_flush_reset_perms() on huge pages Song Liu
2022-07-07 22:35 ` [PATCH v6 bpf-next 4/5] vmalloc: introduce huge_vmalloc_supported Song Liu
2022-07-07 22:35 ` [PATCH v6 bpf-next 5/5] bpf: simplify select_bpf_prog_pack_size Song Liu
2022-07-07 22:59 ` [PATCH v6 bpf-next 0/5] bpf_prog_pack followup Luis Chamberlain
2022-07-07 23:52 ` Song Liu
2022-07-08 0:53 ` Luis Chamberlain
2022-07-08 1:36 ` Song Liu
2022-07-08 15:58 ` Luis Chamberlain
2022-07-08 19:58 ` Song Liu
2022-07-08 22:24 ` Luis Chamberlain
2022-07-09 1:14 ` Song Liu
2022-07-12 4:18 ` Luis Chamberlain
2022-07-12 4:24 ` Luis Chamberlain
2022-07-12 5:49 ` Song Liu
2022-07-12 19:04 ` Luis Chamberlain
2022-07-12 23:12 ` Song Liu
2022-07-12 23:42 ` Luis Chamberlain
2022-07-13 1:00 ` Song Liu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220707223546.4124919-3-song@kernel.org \
--to=song@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=dave.hansen@linux.intel.com \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mcgrof@kernel.org \
--cc=rick.p.edgecombe@intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).