From: Peter Zijlstra <peterz@infradead.org>
To: x86@kernel.org
Cc: peterz@infradead.org, linux-kernel@vger.kernel.org,
rostedt@goodmis.org, mhiramat@kernel.org, bristot@redhat.com,
jbaron@akamai.com, torvalds@linux-foundation.org,
tglx@linutronix.de, mingo@kernel.org, namit@vmware.com,
hpa@zytor.com, luto@kernel.org, ard.biesheuvel@linaro.org,
jpoimboe@redhat.com
Subject: [PATCH v2 11/13] static_call: Handle tail-calls
Date: Mon, 07 Oct 2019 10:27:19 +0200 [thread overview]
Message-ID: <20191007083831.15486812.0@infradead.org> (raw)
In-Reply-To: 20191007082708.01393931.1@infradead.org
GCC can turn our static_call(name)(args...) into a tail call, in which
case we get a JMP.d32 into the trampoline (which then does a further
tail-call).
Teach objtool to recognise and mark these in .static_call_sites and
adjust the code patching to deal with this.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
arch/x86/kernel/static_call.c | 4 ++--
include/linux/static_call.h | 4 ++--
include/linux/static_call_types.h | 7 +++++++
kernel/static_call.c | 21 +++++++++++++--------
tools/include/linux/static_call_types.h | 7 +++++++
tools/objtool/check.c | 18 +++++++++++++-----
6 files changed, 44 insertions(+), 17 deletions(-)
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -41,7 +41,7 @@ static void __static_call_transform(void
text_poke_bp(insn, code, size, NULL);
}
-void arch_static_call_transform(void *site, void *tramp, void *func)
+void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
{
mutex_lock(&text_mutex);
@@ -49,7 +49,7 @@ void arch_static_call_transform(void *si
__static_call_transform(tramp, jmp + !func, func);
if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
- __static_call_transform(site, !func, func);
+ __static_call_transform(site, 2*tail + !func, func);
mutex_unlock(&text_mutex);
}
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -64,7 +64,7 @@
/*
* Either @site or @tramp can be NULL.
*/
-extern void arch_static_call_transform(void *site, void *tramp, void *func);
+extern void arch_static_call_transform(void *site, void *tramp, void *func, bool tail);
#endif
@@ -137,7 +137,7 @@ void __static_call_update(struct static_
{
cpus_read_lock();
WRITE_ONCE(key->func, func);
- arch_static_call_transform(NULL, tramp, func);
+ arch_static_call_transform(NULL, tramp, func, false);
cpus_read_unlock();
}
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -13,6 +13,13 @@
#define STATIC_CALL_TRAMP_STR(name) __stringify(STATIC_CALL_TRAMP(name))
/*
+ * Flags in the low bits of static_call_site::key.
+ */
+#define STATIC_CALL_SITE_TAIL 1UL /* tail call */
+#define STATIC_CALL_SITE_INIT 2UL /* init section */
+#define STATIC_CALL_SITE_FLAGS 3UL
+
+/*
* The static call site table needs to be created by external tooling (objtool
* or a compiler plugin).
*/
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -15,8 +15,6 @@ extern struct static_call_site __start_s
static bool static_call_initialized;
-#define STATIC_CALL_INIT 1UL
-
/* mutex to protect key modules/sites */
static DEFINE_MUTEX(static_call_mutex);
@@ -39,18 +37,23 @@ static inline void *static_call_addr(str
static inline struct static_call_key *static_call_key(const struct static_call_site *site)
{
return (struct static_call_key *)
- (((long)site->key + (long)&site->key) & ~STATIC_CALL_INIT);
+ (((long)site->key + (long)&site->key) & ~STATIC_CALL_SITE_FLAGS);
}
/* These assume the key is word-aligned. */
static inline bool static_call_is_init(struct static_call_site *site)
{
- return ((long)site->key + (long)&site->key) & STATIC_CALL_INIT;
+ return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_INIT;
+}
+
+static inline bool static_call_is_tail(struct static_call_site *site)
+{
+ return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_TAIL;
}
static inline void static_call_set_init(struct static_call_site *site)
{
- site->key = ((long)static_call_key(site) | STATIC_CALL_INIT) -
+ site->key = ((long)static_call_key(site) | STATIC_CALL_SITE_INIT) -
(long)&site->key;
}
@@ -104,7 +107,7 @@ void __static_call_update(struct static_
key->func = func;
- arch_static_call_transform(NULL, tramp, func);
+ arch_static_call_transform(NULL, tramp, func, false);
/*
* If uninitialized, we'll not update the callsites, but they still
@@ -153,7 +156,8 @@ void __static_call_update(struct static_
continue;
}
- arch_static_call_transform(site_addr, NULL, func);
+ arch_static_call_transform(site_addr, NULL, func,
+ static_call_is_tail(site));
}
}
@@ -197,7 +201,8 @@ static int __static_call_init(struct mod
key->next = site_mod;
}
- arch_static_call_transform(site_addr, NULL, key->func);
+ arch_static_call_transform(site_addr, NULL, key->func,
+ static_call_is_tail(site));
}
return 0;
--- a/tools/include/linux/static_call_types.h
+++ b/tools/include/linux/static_call_types.h
@@ -13,6 +13,13 @@
#define STATIC_CALL_TRAMP_STR(name) __stringify(STATIC_CALL_TRAMP(name))
/*
+ * Flags in the low bits of static_call_site::key.
+ */
+#define STATIC_CALL_SITE_TAIL 1UL /* tail call */
+#define STATIC_CALL_SITE_INIT 2UL /* init section */
+#define STATIC_CALL_SITE_FLAGS 3UL
+
+/*
* The static call site table needs to be created by external tooling (objtool
* or a compiler plugin).
*/
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -585,6 +585,10 @@ static int add_jump_destinations(struct
} else {
/* external sibling call */
insn->call_dest = rela->sym;
+ if (insn->call_dest->static_call_tramp) {
+ list_add_tail(&insn->static_call_node,
+ &file->static_call_list);
+ }
continue;
}
@@ -636,6 +640,10 @@ static int add_jump_destinations(struct
/* internal sibling call */
insn->call_dest = insn->jump_dest->func;
+ if (insn->call_dest->static_call_tramp) {
+ list_add_tail(&insn->static_call_node,
+ &file->static_call_list);
+ }
}
}
}
@@ -1348,6 +1356,10 @@ static int decode_sections(struct objtoo
if (ret)
return ret;
+ ret = read_static_call_tramps(file);
+ if (ret)
+ return ret;
+
ret = add_jump_destinations(file);
if (ret)
return ret;
@@ -1372,10 +1384,6 @@ static int decode_sections(struct objtoo
if (ret)
return ret;
- ret = read_static_call_tramps(file);
- if (ret)
- return ret;
-
return 0;
}
@@ -2505,7 +2513,7 @@ static int create_static_call_sections(s
}
memset(rela, 0, sizeof(*rela));
rela->sym = key_sym;
- rela->addend = 0;
+ rela->addend = is_sibling_call(insn) ? STATIC_CALL_SITE_TAIL : 0;
rela->type = R_X86_64_PC32;
rela->offset = idx * sizeof(struct static_call_site) + 4;
list_add_tail(&rela->list, &rela_sec->rela_list);
next prev parent reply other threads:[~2019-10-07 11:25 UTC|newest]
Thread overview: 128+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-07 9:02 [RESEND] everything text-poke: ftrace, modules, static_call and jump_label Peter Zijlstra
2019-10-07 8:17 ` [PATCH v3 0/6] Rewrite x86/ftrace to use text_poke() Peter Zijlstra
2019-10-07 8:17 ` [PATCH v3 1/6] x86/alternatives: Teach text_poke_bp() to emulate instructions Peter Zijlstra
2019-10-08 14:29 ` Borislav Petkov
2019-10-08 14:40 ` Steven Rostedt
2019-10-08 14:50 ` Borislav Petkov
2019-10-08 14:48 ` Peter Zijlstra
2019-10-08 14:54 ` Borislav Petkov
2019-10-08 15:04 ` Steven Rostedt
2019-10-08 15:24 ` Borislav Petkov
2019-10-09 12:03 ` Daniel Bristot de Oliveira
2019-10-07 8:17 ` [PATCH v3 2/6] x86/alternatives: Update int3_emulate_push() comment Peter Zijlstra
2019-10-07 8:17 ` [PATCH v3 3/6] x86/alternatives,jump_label: Provide better text_poke() batching interface Peter Zijlstra
2019-10-09 12:04 ` Daniel Bristot de Oliveira
2019-10-07 8:17 ` [PATCH v3 4/6] x86/alternatives: Add and use text_gen_insn() helper Peter Zijlstra
2019-10-08 6:23 ` Masami Hiramatsu
2019-10-08 8:15 ` Peter Zijlstra
2019-10-07 8:17 ` [PATCH v3 5/6] x86/ftrace: Use text_poke() Peter Zijlstra
2019-10-08 14:43 ` Steven Rostedt
2019-10-08 17:11 ` Peter Zijlstra
2019-10-08 17:27 ` Steven Rostedt
2019-10-10 2:41 ` Steven Rostedt
2019-10-10 9:20 ` Peter Zijlstra
2019-10-10 13:19 ` Steven Rostedt
2019-10-10 14:05 ` Peter Zijlstra
2019-10-10 15:54 ` Steven Rostedt
2019-10-10 17:28 ` Peter Zijlstra
2019-10-10 17:48 ` Steven Rostedt
2019-10-11 10:45 ` Peter Zijlstra
2019-10-11 10:47 ` Peter Zijlstra
2019-10-11 10:50 ` Peter Zijlstra
2019-10-11 12:59 ` Peter Zijlstra
2019-10-11 13:33 ` Steven Rostedt
2019-10-11 13:45 ` Peter Zijlstra
2019-10-15 13:07 ` Jessica Yu
2019-10-15 13:56 ` Peter Zijlstra
2019-10-15 14:11 ` Peter Zijlstra
2019-10-15 14:13 ` Miroslav Benes
2019-10-15 15:06 ` Joe Lawrence
2019-10-15 15:31 ` Jessica Yu
2019-10-15 22:17 ` Joe Lawrence
2019-10-15 22:27 ` Steven Rostedt
2019-10-16 7:42 ` Peter Zijlstra
2019-10-16 10:15 ` Miroslav Benes
2019-10-21 15:05 ` Josh Poimboeuf
2020-01-20 16:50 ` Josh Poimboeuf
2020-01-21 8:35 ` Miroslav Benes
2020-01-21 16:10 ` Josh Poimboeuf
2020-01-22 10:09 ` Miroslav Benes
2020-01-22 21:42 ` Josh Poimboeuf
2020-01-28 9:28 ` Miroslav Benes
2020-01-28 15:00 ` Josh Poimboeuf
2020-01-28 15:40 ` Petr Mladek
2020-01-28 17:02 ` Josh Poimboeuf
2020-01-29 0:46 ` Jiri Kosina
2020-01-29 2:17 ` Josh Poimboeuf
2020-01-29 3:14 ` Jiri Kosina
2020-01-29 12:28 ` Miroslav Benes
2020-01-29 15:59 ` Josh Poimboeuf
2020-01-30 9:53 ` Petr Mladek
2020-01-30 14:17 ` Josh Poimboeuf
2020-01-31 7:17 ` Petr Mladek
2020-01-22 12:15 ` Miroslav Benes
2020-01-22 15:05 ` Miroslav Benes
2020-01-22 22:03 ` Josh Poimboeuf
2020-01-23 10:19 ` Martin Jambor
2019-10-16 7:49 ` Peter Zijlstra
2019-10-16 10:20 ` Miroslav Benes
2019-10-16 13:29 ` Miroslav Benes
2019-10-18 13:03 ` Jessica Yu
2019-10-18 13:40 ` Petr Mladek
2019-10-21 14:14 ` Jessica Yu
2019-10-21 15:31 ` Josh Poimboeuf
2019-10-22 8:27 ` Miroslav Benes
2019-10-22 14:31 ` Josh Poimboeuf
2019-10-23 9:04 ` Miroslav Benes
2019-10-16 6:51 ` Miroslav Benes
2019-10-16 9:23 ` Peter Zijlstra
2019-10-16 9:36 ` Jessica Yu
2019-10-16 9:51 ` Peter Zijlstra
2019-10-16 12:39 ` Peter Zijlstra
2019-10-22 8:45 ` Miroslav Benes
2019-10-15 14:42 ` Peter Zijlstra
2019-10-15 18:31 ` Peter Zijlstra
2019-10-15 15:51 ` Jessica Yu
2019-10-15 13:28 ` Steven Rostedt
2019-10-15 13:42 ` Peter Zijlstra
2019-10-15 16:09 ` Jessica Yu
2019-10-07 8:17 ` [PATCH v3 6/6] x86/mm: Remove set_kernel_text_r[ow]() Peter Zijlstra
2019-10-08 15:07 ` [PATCH v3 0/6] Rewrite x86/ftrace to use text_poke() Steven Rostedt
2019-10-07 8:25 ` [PATCH v2 0/4] Propagate module notifier errors Peter Zijlstra
2019-10-07 8:25 ` [PATCH v2 1/4] notifier: Fix broken error handling pattern Peter Zijlstra
2019-10-10 22:01 ` Rafael J. Wysocki
2019-10-07 8:25 ` [PATCH v2 2/4] module: Fix up module_notifier return values Peter Zijlstra
2019-10-23 19:25 ` Steven Rostedt
2019-10-07 8:25 ` [PATCH v2 3/4] module: Properly propagate MODULE_STATE_COMING failure Peter Zijlstra
2019-10-08 13:08 ` Miroslav Benes
2019-10-07 8:25 ` [PATCH v2 4/4] jump_label,module: Fix module lifetime for __jump_label_mod_text_reserved Peter Zijlstra
2019-10-23 19:29 ` Steven Rostedt
2019-10-07 8:27 ` [PATCH v2 00/13] Add static_call() Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 01/13] compiler.h: Make __ADDRESSABLE() symbol truly unique Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 02/13] static_call: Add basic static call infrastructure Peter Zijlstra
2019-10-07 11:33 ` Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 03/13] static_call: Add inline " Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 04/13] static_call: Avoid kprobes on inline static_call()s Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 05/13] x86/static_call: Add out-of-line static call implementation Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 06/13] x86/static_call: Add inline static call implementation for x86-64 Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 07/13] static_call: Simple self-test Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 08/13] tracepoints: Use static_call Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 09/13] x86/alternatives: Teach text_poke_bp() to emulate RET Peter Zijlstra
2019-10-07 8:27 ` [PATCH v2 10/13] static_call: Add static_cond_call() Peter Zijlstra
2019-10-07 8:27 ` Peter Zijlstra [this message]
2019-10-07 8:27 ` [PATCH v2 12/13] static_call: Allow early init Peter Zijlstra
2019-10-07 8:27 ` [RFC][PATCH v2 13/13] x86/perf, static_call: Optimize x86_pmu methods Peter Zijlstra
2019-10-07 11:33 ` [PATCH v2 00/13] Add static_call() Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 0/9] Variable size jump_label support Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 1/9] jump_label, x86: Strip ASM " Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 2/9] jump_label, x86: Factor out the __jump_table generation Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 3/9] jump_label, x86: Remove init NOP optimization Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 4/9] jump_label, x86: Improve error when we fail expected text Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 5/9] jump_label, x86: Introduce jump_entry_size() Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 6/9] jump_label, x86: Add variable length patching support Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 7/9] jump_label,objtool: Validate variable size jump labels Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 8/9] jump_label,objtool: Generate possible statistics Peter Zijlstra
2019-10-07 8:44 ` [RFC][PATCH 9/9] jump_label, x86: Enable JMP8/NOP2 support Peter Zijlstra
2019-10-07 12:07 ` [RFC][PATCH 0/9] Variable size jump_label support Peter Zijlstra
2019-10-07 12:55 ` Ingo Molnar
2019-10-07 15:08 ` Steven Rostedt
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=20191007083831.15486812.0@infradead.org \
--to=peterz@infradead.org \
--cc=ard.biesheuvel@linaro.org \
--cc=bristot@redhat.com \
--cc=hpa@zytor.com \
--cc=jbaron@akamai.com \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mhiramat@kernel.org \
--cc=mingo@kernel.org \
--cc=namit@vmware.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--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).