From: Song Liu <song@kernel.org>
To: <bpf@vger.kernel.org>, <netdev@vger.kernel.org>,
<linux-kernel@vger.kernel.org>
Cc: <ast@kernel.org>, <daniel@iogearbox.net>, <andrii@kernel.org>,
<kernel-team@fb.com>, <peterz@infradead.org>, <x86@kernel.org>,
<iii@linux.ibm.com>, Song Liu <songliubraving@fb.com>
Subject: [PATCH v9 bpf-next 9/9] bpf, x86_64: use bpf_jit_binary_pack_alloc
Date: Fri, 4 Feb 2022 10:57:42 -0800 [thread overview]
Message-ID: <20220204185742.271030-10-song@kernel.org> (raw)
In-Reply-To: <20220204185742.271030-1-song@kernel.org>
From: Song Liu <songliubraving@fb.com>
Use bpf_jit_binary_pack_alloc in x86_64 jit. The jit engine first writes
the program to the rw buffer. When the jit is done, the program is copied
to the final location with bpf_jit_binary_pack_finalize.
Note that we need to do bpf_tail_call_direct_fixup after finalize.
Therefore, the text_live = false logic in __bpf_arch_text_poke is no
longer needed.
Signed-off-by: Song Liu <songliubraving@fb.com>
---
arch/x86/net/bpf_jit_comp.c | 58 ++++++++++++++++++++-----------------
1 file changed, 31 insertions(+), 27 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index c13d148f7396..643f38b91e30 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -330,8 +330,7 @@ static int emit_jump(u8 **pprog, void *func, void *ip)
}
static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
- void *old_addr, void *new_addr,
- const bool text_live)
+ void *old_addr, void *new_addr)
{
const u8 *nop_insn = x86_nops[5];
u8 old_insn[X86_PATCH_SIZE];
@@ -365,10 +364,7 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
goto out;
ret = 1;
if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
- if (text_live)
- text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
- else
- memcpy(ip, new_insn, X86_PATCH_SIZE);
+ text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
ret = 0;
}
out:
@@ -384,7 +380,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
/* BPF poking in modules is not supported */
return -EINVAL;
- return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
+ return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
}
#define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8)
@@ -558,24 +554,15 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
mutex_lock(&array->aux->poke_mutex);
target = array->ptrs[poke->tail_call.key];
if (target) {
- /* Plain memcpy is used when image is not live yet
- * and still not locked as read-only. Once poke
- * location is active (poke->tailcall_target_stable),
- * any parallel bpf_arch_text_poke() might occur
- * still on the read-write image until we finally
- * locked it as read-only. Both modifications on
- * the given image are under text_mutex to avoid
- * interference.
- */
ret = __bpf_arch_text_poke(poke->tailcall_target,
BPF_MOD_JUMP, NULL,
(u8 *)target->bpf_func +
- poke->adj_off, false);
+ poke->adj_off);
BUG_ON(ret < 0);
ret = __bpf_arch_text_poke(poke->tailcall_bypass,
BPF_MOD_JUMP,
(u8 *)poke->tailcall_target +
- X86_PATCH_SIZE, NULL, false);
+ X86_PATCH_SIZE, NULL);
BUG_ON(ret < 0);
}
WRITE_ONCE(poke->tailcall_target_stable, true);
@@ -866,7 +853,7 @@ static void emit_nops(u8 **pprog, int len)
#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
-static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
int oldproglen, struct jit_context *ctx, bool jmp_padding)
{
bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
@@ -893,8 +880,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
push_callee_regs(&prog, callee_regs_used);
ilen = prog - temp;
- if (image)
- memcpy(image + proglen, temp, ilen);
+ if (rw_image)
+ memcpy(rw_image + proglen, temp, ilen);
proglen += ilen;
addrs[0] = proglen;
prog = temp;
@@ -1323,6 +1310,9 @@ st: if (is_imm8(insn->off))
pr_err("extable->insn doesn't fit into 32-bit\n");
return -EFAULT;
}
+ /* switch ex to rw buffer for writes */
+ ex = (void *)rw_image + ((void *)ex - (void *)image);
+
ex->insn = delta;
ex->data = EX_TYPE_BPF;
@@ -1705,7 +1695,7 @@ st: if (is_imm8(insn->off))
pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
- memcpy(image + proglen, temp, ilen);
+ memcpy(rw_image + proglen, temp, ilen);
}
proglen += ilen;
addrs[i] = proglen;
@@ -2246,6 +2236,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs)
}
struct x64_jit_data {
+ struct bpf_binary_header *rw_header;
struct bpf_binary_header *header;
int *addrs;
u8 *image;
@@ -2258,6 +2249,7 @@ struct x64_jit_data {
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
+ struct bpf_binary_header *rw_header = NULL;
struct bpf_binary_header *header = NULL;
struct bpf_prog *tmp, *orig_prog = prog;
struct x64_jit_data *jit_data;
@@ -2266,6 +2258,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
bool tmp_blinded = false;
bool extra_pass = false;
bool padding = false;
+ u8 *rw_image = NULL;
u8 *image = NULL;
int *addrs;
int pass;
@@ -2301,6 +2294,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
oldproglen = jit_data->proglen;
image = jit_data->image;
header = jit_data->header;
+ rw_header = jit_data->rw_header;
+ rw_image = (void *)rw_header + ((void *)image - (void *)header);
extra_pass = true;
padding = true;
goto skip_init_addrs;
@@ -2331,12 +2326,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
for (pass = 0; pass < MAX_PASSES || image; pass++) {
if (!padding && pass >= PADDING_PASSES)
padding = true;
- proglen = do_jit(prog, addrs, image, oldproglen, &ctx, padding);
+ proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding);
if (proglen <= 0) {
out_image:
image = NULL;
if (header)
- bpf_jit_binary_free(header);
+ bpf_jit_binary_pack_free(header, rw_header);
prog = orig_prog;
goto out_addrs;
}
@@ -2360,8 +2355,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
sizeof(struct exception_table_entry);
/* allocate module memory for x86 insns and extable */
- header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size,
- &image, align, jit_fill_hole);
+ header = bpf_jit_binary_pack_alloc(roundup(proglen, align) + extable_size,
+ &image, align, &rw_header, &rw_image,
+ jit_fill_hole);
if (!header) {
prog = orig_prog;
goto out_addrs;
@@ -2377,14 +2373,22 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
if (image) {
if (!prog->is_func || extra_pass) {
+ /*
+ * bpf_jit_binary_pack_finalize fails in two scenarios:
+ * 1) header is not pointing to proper module memory;
+ * 2) the arch doesn't support bpf_arch_text_copy().
+ *
+ * Both cases are serious bugs that we should not continue.
+ */
+ BUG_ON(bpf_jit_binary_pack_finalize(prog, header, rw_header));
bpf_tail_call_direct_fixup(prog);
- bpf_jit_binary_lock_ro(header);
} else {
jit_data->addrs = addrs;
jit_data->ctx = ctx;
jit_data->proglen = proglen;
jit_data->image = image;
jit_data->header = header;
+ jit_data->rw_header = rw_header;
}
prog->bpf_func = (void *)image;
prog->jited = 1;
--
2.30.2
next prev parent reply other threads:[~2022-02-04 19:01 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-04 18:57 [PATCH v9 bpf-next 0/9] bpf_prog_pack allocator Song Liu
2022-02-04 18:57 ` [PATCH v9 bpf-next 1/9] x86/Kconfig: select HAVE_ARCH_HUGE_VMALLOC with HAVE_ARCH_HUGE_VMAP Song Liu
2022-03-26 0:06 ` Edgecombe, Rick P
2022-03-28 23:27 ` Song Liu
2022-03-29 0:18 ` Edgecombe, Rick P
2022-03-29 8:23 ` Song Liu
2022-03-29 18:39 ` Edgecombe, Rick P
2022-03-29 19:13 ` Song Liu
2022-03-29 21:36 ` Edgecombe, Rick P
2022-03-29 22:12 ` Song Liu
2022-03-26 18:46 ` BUG: Bad page state in process systemd-udevd (was: [PATCH v9 bpf-next 1/9] x86/Kconfig: select HAVE_ARCH_HUGE_VMALLOC with HAVE_ARCH_HUGE_VMAP) Paul Menzel
2022-03-27 10:36 ` Paul Menzel
2022-03-28 6:37 ` Song Liu
2022-03-28 6:51 ` Paul Menzel
2022-03-28 19:24 ` Song Liu
2022-03-28 20:14 ` Paul Menzel
2022-03-28 21:57 ` Song Liu
2022-03-28 19:21 ` Edgecombe, Rick P
2022-02-04 18:57 ` [PATCH v9 bpf-next 2/9] bpf: use bytes instead of pages for bpf_jit_[charge|uncharge]_modmem Song Liu
2022-02-04 18:57 ` [PATCH v9 bpf-next 3/9] bpf: use size instead of pages in bpf_binary_header Song Liu
2022-02-04 18:57 ` [PATCH v9 bpf-next 4/9] bpf: use prog->jited_len in bpf_prog_ksym_set_addr() Song Liu
2022-02-04 18:57 ` [PATCH v9 bpf-next 5/9] x86/alternative: introduce text_poke_copy Song Liu
2022-02-04 18:57 ` [PATCH v9 bpf-next 6/9] bpf: introduce bpf_arch_text_copy Song Liu
2022-02-04 18:57 ` [PATCH v9 bpf-next 7/9] bpf: introduce bpf_prog_pack allocator Song Liu
2022-02-04 18:57 ` [PATCH v9 bpf-next 8/9] bpf: introduce bpf_jit_binary_pack_[alloc|finalize|free] Song Liu
2022-02-04 18:57 ` Song Liu [this message]
2022-02-08 2:24 ` [PATCH v9 bpf-next 9/9] bpf, x86_64: use bpf_jit_binary_pack_alloc Alexei Starovoitov
2022-07-03 3:02 ` Andres Freund
2022-07-03 3:03 ` Alexei Starovoitov
2022-07-03 3:14 ` Andres Freund
2022-02-08 2:30 ` [PATCH v9 bpf-next 0/9] bpf_prog_pack allocator patchwork-bot+netdevbpf
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=20220204185742.271030-10-song@kernel.org \
--to=song@kernel.org \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=iii@linux.ibm.com \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=songliubraving@fb.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).