All of lore.kernel.org
 help / color / mirror / Atom feed
From: Song Liu <song@kernel.org>
To: <bpf@vger.kernel.org>, <linux-mm@kvack.org>,
	<linux-kernel@vger.kernel.org>
Cc: <ast@kernel.org>, <daniel@iogearbox.net>, <kernel-team@fb.com>,
	<akpm@linux-foundation.org>, <rick.p.edgecombe@intel.com>,
	<hch@infradead.org>, <imbrenda@linux.ibm.com>,
	<mcgrof@kernel.org>, Song Liu <song@kernel.org>
Subject: [PATCH v4 bpf 4/4] bpf: use module_alloc_huge for bpf_prog_pack
Date: Fri, 15 Apr 2022 09:44:13 -0700	[thread overview]
Message-ID: <20220415164413.2727220-5-song@kernel.org> (raw)
In-Reply-To: <20220415164413.2727220-1-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.

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.

Signed-off-by: Song Liu <song@kernel.org>
---
 kernel/bpf/core.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 13e9dbeeedf3..b2a634d0f842 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(void)
 		       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;
@@ -889,7 +889,6 @@ static struct bpf_prog_pack *alloc_new_pack(void)
 	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;
@@ -970,6 +969,8 @@ 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



  parent reply	other threads:[~2022-04-15 16:55 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-15 16:44 [PATCH v4 bpf 0/4] vmalloc: bpf: introduce VM_ALLOW_HUGE_VMAP Song Liu
2022-04-15 16:44 ` [PATCH v4 bpf 1/4] vmalloc: replace VM_NO_HUGE_VMAP with VM_ALLOW_HUGE_VMAP Song Liu
2022-04-15 17:43   ` Rik van Riel
2022-04-15 16:44 ` [PATCH v4 bpf 2/4] page_alloc: use vmalloc_huge for large system hash Song Liu
2022-04-15 17:43   ` Rik van Riel
2022-04-25  7:07     ` Geert Uytterhoeven
2022-04-25  8:17       ` Linus Torvalds
2022-04-25  8:24         ` Geert Uytterhoeven
2022-04-15 16:44 ` [PATCH v4 bpf 3/4] module: introduce module_alloc_huge Song Liu
2022-04-15 18:06   ` Rik van Riel
2022-06-16 16:10   ` Dave Hansen
2022-04-15 16:44 ` Song Liu [this message]
2022-04-15 19:05 ` [PATCH v4 bpf 0/4] vmalloc: bpf: introduce VM_ALLOW_HUGE_VMAP Luis Chamberlain
2022-04-16  1:34   ` Song Liu
2022-04-16  1:42     ` Luis Chamberlain
2022-04-16  1:43       ` Luis Chamberlain
2022-04-16  5:08   ` Christoph Hellwig
2022-04-16 19:55     ` Song Liu
2022-04-16 20:30       ` Linus Torvalds
2022-04-16 22:26         ` Song Liu
2022-04-18 10:06           ` Mike Rapoport
2022-04-19  0:44             ` Luis Chamberlain
2022-04-19  1:56               ` Edgecombe, Rick P
2022-04-19  5:36                 ` Song Liu
2022-04-19 18:42                   ` Mike Rapoport
2022-04-19 19:20                     ` Linus Torvalds
2022-04-20  2:03                       ` Alexei Starovoitov
2022-04-20  2:18                         ` Linus Torvalds
2022-04-20 14:42                           ` Song Liu
2022-04-20 18:28                             ` Luis Chamberlain
2022-04-21  7:29                             ` Song Liu
2022-04-21  3:25                       ` Nicholas Piggin
2022-04-21  5:48                         ` Linus Torvalds
2022-04-21  6:02                           ` Linus Torvalds
2022-04-21  9:07                             ` Nicholas Piggin
2022-04-21  8:57                           ` Nicholas Piggin
2022-04-21 15:44                             ` Linus Torvalds
2022-04-21 23:30                               ` Nicholas Piggin
2022-04-22  0:49                                 ` Linus Torvalds
2022-04-22  1:51                                   ` Nicholas Piggin
2022-04-22  2:31                                     ` Linus Torvalds
2022-04-22  2:57                                       ` Nicholas Piggin
2022-04-21 15:47                             ` Edgecombe, Rick P
2022-04-21 16:15                               ` Linus Torvalds
2022-04-22  0:12                                 ` Nicholas Piggin
2022-04-22  2:29                                   ` Edgecombe, Rick P
2022-04-22  2:47                                     ` Linus Torvalds
2022-04-22 16:54                                       ` Edgecombe, Rick P
2022-04-22  3:08                                     ` Nicholas Piggin
2022-04-22  4:31                                       ` Nicholas Piggin
2022-04-22 17:10                                         ` Edgecombe, Rick P
2022-04-22 20:22                                           ` Edgecombe, Rick P
2022-04-22  3:33                                     ` Nicholas Piggin
2022-04-21  9:47                           ` Nicholas Piggin
2022-04-19 21:24                 ` Luis Chamberlain
2022-04-19 23:58                   ` Edgecombe, Rick P
2022-04-20  7:58                   ` Petr Mladek
2022-04-19 18:20               ` Mike Rapoport
2022-04-24 17:43       ` Linus Torvalds
2022-04-25  6:48         ` Song Liu
2022-04-21  3:19     ` Nicholas Piggin

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=20220415164413.2727220-5-song@kernel.org \
    --to=song@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=hch@infradead.org \
    --cc=imbrenda@linux.ibm.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 \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.