2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/kernel/jump_label.c

869 lines
21 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* jump label support
*
* Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
* Copyright (C) 2011 Peter Zijlstra
*
*/
#include <linux/memory.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/err.h>
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
#include <linux/static_key.h>
#include <linux/jump_label_ratelimit.h>
#include <linux/bug.h>
#include <linux/cpu.h>
#include <asm/sections.h>
/* mutex to protect coming/going of the jump_label table */
static DEFINE_MUTEX(jump_label_mutex);
void jump_label_lock(void)
{
mutex_lock(&jump_label_mutex);
}
void jump_label_unlock(void)
{
mutex_unlock(&jump_label_mutex);
}
static int jump_label_cmp(const void *a, const void *b)
{
const struct jump_entry *jea = a;
const struct jump_entry *jeb = b;
/*
* Entrires are sorted by key.
*/
if (jump_entry_key(jea) < jump_entry_key(jeb))
return -1;
if (jump_entry_key(jea) > jump_entry_key(jeb))
return 1;
/*
* In the batching mode, entries should also be sorted by the code
* inside the already sorted list of entries, enabling a bsearch in
* the vector.
*/
if (jump_entry_code(jea) < jump_entry_code(jeb))
return -1;
if (jump_entry_code(jea) > jump_entry_code(jeb))
return 1;
return 0;
}
static void jump_label_swap(void *a, void *b, int size)
{
long delta = (unsigned long)a - (unsigned long)b;
struct jump_entry *jea = a;
struct jump_entry *jeb = b;
struct jump_entry tmp = *jea;
jea->code = jeb->code - delta;
jea->target = jeb->target - delta;
jea->key = jeb->key - delta;
jeb->code = tmp.code + delta;
jeb->target = tmp.target + delta;
jeb->key = tmp.key + delta;
}
static void
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
{
unsigned long size;
void *swapfn = NULL;
if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE))
swapfn = jump_label_swap;
size = (((unsigned long)stop - (unsigned long)start)
/ sizeof(struct jump_entry));
sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn);
}
static void jump_label_update(struct static_key *key);
/*
* There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h.
* The use of 'atomic_read()' requires atomic.h and its problematic for some
* kernel headers such as kernel.h and others. Since static_key_count() is not
* used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok
* to have it be a function here. Similarly, for 'static_key_enable()' and
* 'static_key_disable()', which require bug.h. This should allow jump_label.h
* to be included from most/all places for CONFIG_JUMP_LABEL.
*/
int static_key_count(struct static_key *key)
{
/*
* -1 means the first static_key_slow_inc() is in progress.
* static_key_enabled() must return true, so return 1 here.
*/
int n = atomic_read(&key->enabled);
return n >= 0 ? n : 1;
}
EXPORT_SYMBOL_GPL(static_key_count);
void static_key_slow_inc_cpuslocked(struct static_key *key)
{
locking/static_key: Fix concurrent static_key_slow_inc() The following scenario is possible: CPU 1 CPU 2 static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 0, no increment jump_label_lock() atomic_inc_return() -> key.enabled == 1 now static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 1, inc to 2 return ** static key is wrong! jump_label_update() jump_label_unlock() Testing the static key at the point marked by (**) will follow the wrong path for jumps that have not been patched yet. This can actually happen when creating many KVM virtual machines with userspace LAPIC emulation; just run several copies of the following program: #include <fcntl.h> #include <unistd.h> #include <sys/ioctl.h> #include <linux/kvm.h> int main(void) { for (;;) { int kvmfd = open("/dev/kvm", O_RDONLY); int vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); close(ioctl(vmfd, KVM_CREATE_VCPU, 1)); close(vmfd); close(kvmfd); } return 0; } Every KVM_CREATE_VCPU ioctl will attempt a static_key_slow_inc() call. The static key's purpose is to skip NULL pointer checks and indeed one of the processes eventually dereferences NULL. As explained in the commit that introduced the bug: 706249c222f6 ("locking/static_keys: Rework update logic") jump_label_update() needs key.enabled to be true. The solution adopted here is to temporarily make key.enabled == -1, and use go down the slow path when key.enabled <= 0. Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> # v4.3+ Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 706249c222f6 ("locking/static_keys: Rework update logic") Link: http://lkml.kernel.org/r/1466527937-69798-1-git-send-email-pbonzini@redhat.com [ Small stylistic edits to the changelog and the code. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-06-22 00:52:17 +08:00
int v, v1;
locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Jason Baron <jbaron@akamai.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-18 23:24:28 +08:00
STATIC_KEY_CHECK_USE(key);
lockdep_assert_cpus_held();
locking/static_key: Fix concurrent static_key_slow_inc() The following scenario is possible: CPU 1 CPU 2 static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 0, no increment jump_label_lock() atomic_inc_return() -> key.enabled == 1 now static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 1, inc to 2 return ** static key is wrong! jump_label_update() jump_label_unlock() Testing the static key at the point marked by (**) will follow the wrong path for jumps that have not been patched yet. This can actually happen when creating many KVM virtual machines with userspace LAPIC emulation; just run several copies of the following program: #include <fcntl.h> #include <unistd.h> #include <sys/ioctl.h> #include <linux/kvm.h> int main(void) { for (;;) { int kvmfd = open("/dev/kvm", O_RDONLY); int vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); close(ioctl(vmfd, KVM_CREATE_VCPU, 1)); close(vmfd); close(kvmfd); } return 0; } Every KVM_CREATE_VCPU ioctl will attempt a static_key_slow_inc() call. The static key's purpose is to skip NULL pointer checks and indeed one of the processes eventually dereferences NULL. As explained in the commit that introduced the bug: 706249c222f6 ("locking/static_keys: Rework update logic") jump_label_update() needs key.enabled to be true. The solution adopted here is to temporarily make key.enabled == -1, and use go down the slow path when key.enabled <= 0. Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> # v4.3+ Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 706249c222f6 ("locking/static_keys: Rework update logic") Link: http://lkml.kernel.org/r/1466527937-69798-1-git-send-email-pbonzini@redhat.com [ Small stylistic edits to the changelog and the code. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-06-22 00:52:17 +08:00
/*
* Careful if we get concurrent static_key_slow_inc() calls;
* later calls must wait for the first one to _finish_ the
* jump_label_update() process. At the same time, however,
* the jump_label_update() call below wants to see
* static_key_enabled(&key) for jumps to be updated properly.
*
* So give a special meaning to negative key->enabled: it sends
* static_key_slow_inc() down the slow path, and it is non-zero
* so it counts as "enabled" in jump_label_update(). Note that
* atomic_inc_unless_negative() checks >= 0, so roll our own.
*/
for (v = atomic_read(&key->enabled); v > 0; v = v1) {
v1 = atomic_cmpxchg(&key->enabled, v, v + 1);
if (likely(v1 == v))
locking/static_key: Fix concurrent static_key_slow_inc() The following scenario is possible: CPU 1 CPU 2 static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 0, no increment jump_label_lock() atomic_inc_return() -> key.enabled == 1 now static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 1, inc to 2 return ** static key is wrong! jump_label_update() jump_label_unlock() Testing the static key at the point marked by (**) will follow the wrong path for jumps that have not been patched yet. This can actually happen when creating many KVM virtual machines with userspace LAPIC emulation; just run several copies of the following program: #include <fcntl.h> #include <unistd.h> #include <sys/ioctl.h> #include <linux/kvm.h> int main(void) { for (;;) { int kvmfd = open("/dev/kvm", O_RDONLY); int vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); close(ioctl(vmfd, KVM_CREATE_VCPU, 1)); close(vmfd); close(kvmfd); } return 0; } Every KVM_CREATE_VCPU ioctl will attempt a static_key_slow_inc() call. The static key's purpose is to skip NULL pointer checks and indeed one of the processes eventually dereferences NULL. As explained in the commit that introduced the bug: 706249c222f6 ("locking/static_keys: Rework update logic") jump_label_update() needs key.enabled to be true. The solution adopted here is to temporarily make key.enabled == -1, and use go down the slow path when key.enabled <= 0. Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> # v4.3+ Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 706249c222f6 ("locking/static_keys: Rework update logic") Link: http://lkml.kernel.org/r/1466527937-69798-1-git-send-email-pbonzini@redhat.com [ Small stylistic edits to the changelog and the code. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-06-22 00:52:17 +08:00
return;
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label_lock();
locking/static_key: Fix concurrent static_key_slow_inc() The following scenario is possible: CPU 1 CPU 2 static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 0, no increment jump_label_lock() atomic_inc_return() -> key.enabled == 1 now static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 1, inc to 2 return ** static key is wrong! jump_label_update() jump_label_unlock() Testing the static key at the point marked by (**) will follow the wrong path for jumps that have not been patched yet. This can actually happen when creating many KVM virtual machines with userspace LAPIC emulation; just run several copies of the following program: #include <fcntl.h> #include <unistd.h> #include <sys/ioctl.h> #include <linux/kvm.h> int main(void) { for (;;) { int kvmfd = open("/dev/kvm", O_RDONLY); int vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); close(ioctl(vmfd, KVM_CREATE_VCPU, 1)); close(vmfd); close(kvmfd); } return 0; } Every KVM_CREATE_VCPU ioctl will attempt a static_key_slow_inc() call. The static key's purpose is to skip NULL pointer checks and indeed one of the processes eventually dereferences NULL. As explained in the commit that introduced the bug: 706249c222f6 ("locking/static_keys: Rework update logic") jump_label_update() needs key.enabled to be true. The solution adopted here is to temporarily make key.enabled == -1, and use go down the slow path when key.enabled <= 0. Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> # v4.3+ Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 706249c222f6 ("locking/static_keys: Rework update logic") Link: http://lkml.kernel.org/r/1466527937-69798-1-git-send-email-pbonzini@redhat.com [ Small stylistic edits to the changelog and the code. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-06-22 00:52:17 +08:00
if (atomic_read(&key->enabled) == 0) {
atomic_set(&key->enabled, -1);
jump_label_update(key);
/*
* Ensure that if the above cmpxchg loop observes our positive
* value, it must also observe all the text changes.
*/
atomic_set_release(&key->enabled, 1);
locking/static_key: Fix concurrent static_key_slow_inc() The following scenario is possible: CPU 1 CPU 2 static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 0, no increment jump_label_lock() atomic_inc_return() -> key.enabled == 1 now static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 1, inc to 2 return ** static key is wrong! jump_label_update() jump_label_unlock() Testing the static key at the point marked by (**) will follow the wrong path for jumps that have not been patched yet. This can actually happen when creating many KVM virtual machines with userspace LAPIC emulation; just run several copies of the following program: #include <fcntl.h> #include <unistd.h> #include <sys/ioctl.h> #include <linux/kvm.h> int main(void) { for (;;) { int kvmfd = open("/dev/kvm", O_RDONLY); int vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); close(ioctl(vmfd, KVM_CREATE_VCPU, 1)); close(vmfd); close(kvmfd); } return 0; } Every KVM_CREATE_VCPU ioctl will attempt a static_key_slow_inc() call. The static key's purpose is to skip NULL pointer checks and indeed one of the processes eventually dereferences NULL. As explained in the commit that introduced the bug: 706249c222f6 ("locking/static_keys: Rework update logic") jump_label_update() needs key.enabled to be true. The solution adopted here is to temporarily make key.enabled == -1, and use go down the slow path when key.enabled <= 0. Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> # v4.3+ Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 706249c222f6 ("locking/static_keys: Rework update logic") Link: http://lkml.kernel.org/r/1466527937-69798-1-git-send-email-pbonzini@redhat.com [ Small stylistic edits to the changelog and the code. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-06-22 00:52:17 +08:00
} else {
atomic_inc(&key->enabled);
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label_unlock();
}
void static_key_slow_inc(struct static_key *key)
{
cpus_read_lock();
static_key_slow_inc_cpuslocked(key);
cpus_read_unlock();
}
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
EXPORT_SYMBOL_GPL(static_key_slow_inc);
void static_key_enable_cpuslocked(struct static_key *key)
{
locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Jason Baron <jbaron@akamai.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-18 23:24:28 +08:00
STATIC_KEY_CHECK_USE(key);
lockdep_assert_cpus_held();
if (atomic_read(&key->enabled) > 0) {
WARN_ON_ONCE(atomic_read(&key->enabled) != 1);
return;
}
jump_label_lock();
if (atomic_read(&key->enabled) == 0) {
atomic_set(&key->enabled, -1);
jump_label_update(key);
/*
* See static_key_slow_inc().
*/
atomic_set_release(&key->enabled, 1);
}
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked);
void static_key_enable(struct static_key *key)
{
cpus_read_lock();
static_key_enable_cpuslocked(key);
cpus_read_unlock();
}
EXPORT_SYMBOL_GPL(static_key_enable);
void static_key_disable_cpuslocked(struct static_key *key)
{
locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Jason Baron <jbaron@akamai.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-18 23:24:28 +08:00
STATIC_KEY_CHECK_USE(key);
lockdep_assert_cpus_held();
if (atomic_read(&key->enabled) != 1) {
WARN_ON_ONCE(atomic_read(&key->enabled) != 0);
return;
}
jump_label_lock();
if (atomic_cmpxchg(&key->enabled, 1, 0))
jump_label_update(key);
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked);
void static_key_disable(struct static_key *key)
{
cpus_read_lock();
static_key_disable_cpuslocked(key);
cpus_read_unlock();
}
EXPORT_SYMBOL_GPL(static_key_disable);
static bool static_key_slow_try_dec(struct static_key *key)
{
int val;
val = atomic_fetch_add_unless(&key->enabled, -1, 1);
if (val == 1)
return false;
locking/static_key: Fix concurrent static_key_slow_inc() The following scenario is possible: CPU 1 CPU 2 static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 0, no increment jump_label_lock() atomic_inc_return() -> key.enabled == 1 now static_key_slow_inc() atomic_inc_not_zero() -> key.enabled == 1, inc to 2 return ** static key is wrong! jump_label_update() jump_label_unlock() Testing the static key at the point marked by (**) will follow the wrong path for jumps that have not been patched yet. This can actually happen when creating many KVM virtual machines with userspace LAPIC emulation; just run several copies of the following program: #include <fcntl.h> #include <unistd.h> #include <sys/ioctl.h> #include <linux/kvm.h> int main(void) { for (;;) { int kvmfd = open("/dev/kvm", O_RDONLY); int vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0); close(ioctl(vmfd, KVM_CREATE_VCPU, 1)); close(vmfd); close(kvmfd); } return 0; } Every KVM_CREATE_VCPU ioctl will attempt a static_key_slow_inc() call. The static key's purpose is to skip NULL pointer checks and indeed one of the processes eventually dereferences NULL. As explained in the commit that introduced the bug: 706249c222f6 ("locking/static_keys: Rework update logic") jump_label_update() needs key.enabled to be true. The solution adopted here is to temporarily make key.enabled == -1, and use go down the slow path when key.enabled <= 0. Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <stable@vger.kernel.org> # v4.3+ Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 706249c222f6 ("locking/static_keys: Rework update logic") Link: http://lkml.kernel.org/r/1466527937-69798-1-git-send-email-pbonzini@redhat.com [ Small stylistic edits to the changelog and the code. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-06-22 00:52:17 +08:00
/*
* The negative count check is valid even when a negative
* key->enabled is in use by static_key_slow_inc(); a
* __static_key_slow_dec() before the first static_key_slow_inc()
* returns is unbalanced, because all other static_key_slow_inc()
* instances block while the update is in progress.
*/
WARN(val < 0, "jump label: negative count!\n");
return true;
}
static void __static_key_slow_dec_cpuslocked(struct static_key *key)
{
lockdep_assert_cpus_held();
if (static_key_slow_try_dec(key))
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
return;
jump_label_lock();
if (atomic_dec_and_test(&key->enabled))
jump_label_update(key);
jump_label_unlock();
}
static void __static_key_slow_dec(struct static_key *key)
{
cpus_read_lock();
__static_key_slow_dec_cpuslocked(key);
cpus_read_unlock();
}
void jump_label_update_timeout(struct work_struct *work)
{
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct static_key_deferred *key =
container_of(work, struct static_key_deferred, work.work);
__static_key_slow_dec(&key->key);
}
EXPORT_SYMBOL_GPL(jump_label_update_timeout);
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
void static_key_slow_dec(struct static_key *key)
{
locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Jason Baron <jbaron@akamai.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-18 23:24:28 +08:00
STATIC_KEY_CHECK_USE(key);
__static_key_slow_dec(key);
}
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
EXPORT_SYMBOL_GPL(static_key_slow_dec);
void static_key_slow_dec_cpuslocked(struct static_key *key)
{
STATIC_KEY_CHECK_USE(key);
__static_key_slow_dec_cpuslocked(key);
}
void __static_key_slow_dec_deferred(struct static_key *key,
struct delayed_work *work,
unsigned long timeout)
{
locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Jason Baron <jbaron@akamai.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-18 23:24:28 +08:00
STATIC_KEY_CHECK_USE(key);
if (static_key_slow_try_dec(key))
return;
schedule_delayed_work(work, timeout);
}
EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred);
void __static_key_deferred_flush(void *key, struct delayed_work *work)
{
locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Jason Baron <jbaron@akamai.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-18 23:24:28 +08:00
STATIC_KEY_CHECK_USE(key);
flush_delayed_work(work);
}
EXPORT_SYMBOL_GPL(__static_key_deferred_flush);
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
locking/static_keys: Improve uninitialized key warning Right now it says: static_key_disable_cpuslocked used before call to jump_label_init ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:161 static_key_disable_cpuslocked+0x68/0x70 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.0-rc5+ #1 Hardware name: SGI.COM C2112-4GP3/X10DRT-P-Series, BIOS 2.0a 05/09/2016 task: ffffffff81c0e480 task.stack: ffffffff81c00000 RIP: 0010:static_key_disable_cpuslocked+0x68/0x70 RSP: 0000:ffffffff81c03ef0 EFLAGS: 00010096 ORIG_RAX: 0000000000000000 RAX: 0000000000000041 RBX: ffffffff81c32680 RCX: ffffffff81c5cbf8 RDX: 0000000000000001 RSI: 0000000000000092 RDI: 0000000000000002 RBP: ffff88807fffd240 R08: 726f666562206465 R09: 0000000000000136 R10: 0000000000000000 R11: 696e695f6c656261 R12: ffffffff82158900 R13: ffffffff8215f760 R14: 0000000000000001 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff883f7f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88807ffff000 CR3: 0000000001c09000 CR4: 00000000000606b0 Call Trace: static_key_disable+0x16/0x20 start_kernel+0x15a/0x45d ? load_ucode_intel_bsp+0x11/0x2d secondary_startup_64+0xa5/0xb0 Code: 48 c7 c7 a0 15 cf 81 e9 47 53 4b 00 48 89 df e8 5f fc ff ff eb e8 48 c7 c6 \ c0 97 83 81 48 c7 c7 d0 ff a2 81 31 c0 e8 c5 9d f5 ff <0f> ff eb a7 0f ff eb \ b0 e8 eb a2 4b 00 53 48 89 fb e8 42 0e f0 but it doesn't tell me which key it is. So dump the key's name too: static_key_disable_cpuslocked(): static key 'virt_spin_lock_key' used before call to jump_label_init() And that makes pinpointing which key is causing that a lot easier. include/linux/jump_label.h | 14 +++++++------- include/linux/jump_label_ratelimit.h | 6 +++--- kernel/jump_label.c | 14 +++++++------- 3 files changed, 17 insertions(+), 17 deletions(-) Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Jason Baron <jbaron@akamai.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20171018152428.ffjgak4o25f7ept6@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-18 23:24:28 +08:00
STATIC_KEY_CHECK_USE(key);
key->timeout = rl;
INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
}
EXPORT_SYMBOL_GPL(jump_label_rate_limit);
static int addr_conflict(struct jump_entry *entry, void *start, void *end)
{
if (jump_entry_code(entry) <= (unsigned long)end &&
jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start)
return 1;
return 0;
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
static int __jump_label_text_reserved(struct jump_entry *iter_start,
struct jump_entry *iter_stop, void *start, void *end, bool init)
{
struct jump_entry *iter;
iter = iter_start;
while (iter < iter_stop) {
if (init || !jump_entry_is_init(iter)) {
if (addr_conflict(iter, start, end))
return 1;
}
iter++;
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
return 0;
}
/*
* Update code which is definitely not currently executing.
* Architectures which need heavyweight synchronization to modify
* running code can override this to make the non-live update case
* cheaper.
*/
void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry *entry,
enum jump_label_type type)
{
arch_jump_label_transform(entry, type);
}
static inline struct jump_entry *static_key_entries(struct static_key *key)
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
{
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED);
return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK);
}
static inline bool static_key_type(struct static_key *key)
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
{
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
return key->type & JUMP_TYPE_TRUE;
}
static inline bool static_key_linked(struct static_key *key)
{
return key->type & JUMP_TYPE_LINKED;
}
static inline void static_key_clear_linked(struct static_key *key)
{
key->type &= ~JUMP_TYPE_LINKED;
}
static inline void static_key_set_linked(struct static_key *key)
{
key->type |= JUMP_TYPE_LINKED;
}
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
/***
* A 'struct static_key' uses a union such that it either points directly
* to a table of 'struct jump_entry' or to a linked list of modules which in
* turn point to 'struct jump_entry' tables.
*
* The two lower bits of the pointer are used to keep track of which pointer
* type is in use and to store the initial branch direction, we use an access
* function which preserves these bits.
*/
static void static_key_set_entries(struct static_key *key,
struct jump_entry *entries)
{
unsigned long type;
WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK);
type = key->type & JUMP_TYPE_MASK;
key->entries = entries;
key->type |= type;
}
static enum jump_label_type jump_label_type(struct jump_entry *entry)
{
struct static_key *key = jump_entry_key(entry);
bool enabled = static_key_enabled(key);
bool branch = jump_entry_is_branch(entry);
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
locking/static_keys: Add a new static_key interface There are various problems and short-comings with the current static_key interface: - static_key_{true,false}() read like a branch depending on the key value, instead of the actual likely/unlikely branch depending on init value. - static_key_{true,false}() are, as stated above, tied to the static_key init values STATIC_KEY_INIT_{TRUE,FALSE}. - we're limited to the 2 (out of 4) possible options that compile to a default NOP because that's what our arch_static_branch() assembly emits. So provide a new static_key interface: DEFINE_STATIC_KEY_TRUE(name); DEFINE_STATIC_KEY_FALSE(name); Which define a key of different types with an initial true/false value. Then allow: static_branch_likely() static_branch_unlikely() to take a key of either type and emit the right instruction for the case. This means adding a second arch_static_branch_jump() assembly helper which emits a JMP per default. In order to determine the right instruction for the right state, encode the branch type in the LSB of jump_entry::key. This is the final step in removing the naming confusion that has led to a stream of avoidable bugs such as: a833581e372a ("x86, perf: Fix static_key bug in load_mm_cr4()") ... but it also allows new static key combinations that will give us performance enhancements in the subsequent patches. Tested-by: Rabin Vincent <rabin@rab.in> # arm Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390 Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-24 21:09:55 +08:00
/* See the comment in linux/jump_label.h */
return enabled ^ branch;
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
}
static bool jump_label_can_update(struct jump_entry *entry, bool init)
{
/*
* Cannot update code that was in an init text area.
*/
if (!init && jump_entry_is_init(entry))
return false;
if (!kernel_text_address(jump_entry_code(entry))) {
/*
* This skips patching built-in __exit, which
* is part of init_section_contains() but is
* not part of kernel_text_address().
*
* Skipping built-in __exit is fine since it
* will never be executed.
*/
WARN_ONCE(!jump_entry_is_init(entry),
"can't patch jump_label at %pS",
(void *)jump_entry_code(entry));
return false;
}
return true;
}
jump_label: Batch updates if arch supports it If the architecture supports the batching of jump label updates, use it! An easy way to see the benefits of this patch is switching the schedstats on and off. For instance: -------------------------- %< ---------------------------- #!/bin/sh while [ true ]; do sysctl -w kernel.sched_schedstats=1 sleep 2 sysctl -w kernel.sched_schedstats=0 sleep 2 done -------------------------- >% ---------------------------- while watching the IPI count: -------------------------- %< ---------------------------- # watch -n1 "cat /proc/interrupts | grep Function" -------------------------- >% ---------------------------- With the current mode, it is possible to see +- 168 IPIs each 2 seconds, while with this patch the number of IPIs goes to 3 each 2 seconds. Regarding the performance impact of this patch set, I made two measurements: The time to update a key (the task that is causing the change) The time to run the int3 handler (the side effect on a thread that hits the code being changed) The schedstats static key was chosen as the key to being switched on and off. The reason being is that it is used in more than 56 places, in a hot path. The change in the schedstats static key will be done with the following command: while [ true ]; do sysctl -w kernel.sched_schedstats=1 usleep 500000 sysctl -w kernel.sched_schedstats=0 usleep 500000 done In this way, they key will be updated twice per second. To force the hit of the int3 handler, the system will also run a kernel compilation with two jobs per CPU. The test machine is a two nodes/24 CPUs box with an Intel Xeon processor @2.27GHz. Regarding the update part, on average, the regular kernel takes 57 ms to update the schedstats key, while the kernel with the batch updates takes just 1.4 ms on average. Although it seems to be too good to be true, it makes sense: the schedstats key is used in 56 places, so it was expected that it would take around 56 times to update the keys with the current implementation, as the IPIs are the most expensive part of the update. Regarding the int3 handler, the non-batch handler takes 45 ns on average, while the batch version takes around 180 ns. At first glance, it seems to be a high value. But it is not, considering that it is doing 56 updates, rather than one! It is taking four times more, only. This gain is possible because the patch uses a binary search in the vector: log2(56)=5.8. So, it was expected to have an overhead within four times. (voice of tv propaganda) But, that is not all! As the int3 handler keeps on for a shorter period (because the update part is on for a shorter time), the number of hits in the int3 handler decreased by 10%. The question then is: Is it worth paying the price of "135 ns" more in the int3 handler? Considering that, in this test case, we are saving the handling of 53 IPIs, that takes more than these 135 ns, it seems to be a meager price to be paid. Moreover, the test case was forcing the hit of the int3, in practice, it does not take that often. While the IPI takes place on all CPUs, hitting the int3 handler or not! For instance, in an isolated CPU with a process running in user-space (nohz_full use-case), the chances of hitting the int3 handler is barely zero, while there is no way to avoid the IPIs. By bounding the IPIs, we are improving a lot this scenario. Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Chris von Recklinghausen <crecklin@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jason Baron <jbaron@akamai.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott Wood <swood@redhat.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/acc891dbc2dbc9fd616dd680529a2337b1d1274c.1560325897.git.bristot@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-06-12 17:57:30 +08:00
#ifndef HAVE_JUMP_LABEL_BATCH
static void __jump_label_update(struct static_key *key,
struct jump_entry *entry,
jump_label: Annotate entries that operate on __init code earlier Jump table entries are mostly read-only, with the exception of the init and module loader code that defuses entries that point into init code when the code being referred to is freed. For robustness, it would be better to move these entries into the ro_after_init section, but clearing the 'code' member of each jump table entry referring to init code at module load time races with the module_enable_ro() call that remaps the ro_after_init section read only, so we'd like to do it earlier. So given that whether such an entry refers to init code can be decided much earlier, we can pull this check forward. Since we may still need the code entry at this point, let's switch to setting a low bit in the 'key' member just like we do to annotate the default state of a jump table entry. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jessica Yu <jeyu@kernel.org> Link: https://lkml.kernel.org/r/20180919065144.25010-8-ard.biesheuvel@linaro.org
2018-09-19 14:51:42 +08:00
struct jump_entry *stop,
bool init)
{
for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
if (jump_label_can_update(entry, init))
arch_jump_label_transform(entry, jump_label_type(entry));
}
}
jump_label: Batch updates if arch supports it If the architecture supports the batching of jump label updates, use it! An easy way to see the benefits of this patch is switching the schedstats on and off. For instance: -------------------------- %< ---------------------------- #!/bin/sh while [ true ]; do sysctl -w kernel.sched_schedstats=1 sleep 2 sysctl -w kernel.sched_schedstats=0 sleep 2 done -------------------------- >% ---------------------------- while watching the IPI count: -------------------------- %< ---------------------------- # watch -n1 "cat /proc/interrupts | grep Function" -------------------------- >% ---------------------------- With the current mode, it is possible to see +- 168 IPIs each 2 seconds, while with this patch the number of IPIs goes to 3 each 2 seconds. Regarding the performance impact of this patch set, I made two measurements: The time to update a key (the task that is causing the change) The time to run the int3 handler (the side effect on a thread that hits the code being changed) The schedstats static key was chosen as the key to being switched on and off. The reason being is that it is used in more than 56 places, in a hot path. The change in the schedstats static key will be done with the following command: while [ true ]; do sysctl -w kernel.sched_schedstats=1 usleep 500000 sysctl -w kernel.sched_schedstats=0 usleep 500000 done In this way, they key will be updated twice per second. To force the hit of the int3 handler, the system will also run a kernel compilation with two jobs per CPU. The test machine is a two nodes/24 CPUs box with an Intel Xeon processor @2.27GHz. Regarding the update part, on average, the regular kernel takes 57 ms to update the schedstats key, while the kernel with the batch updates takes just 1.4 ms on average. Although it seems to be too good to be true, it makes sense: the schedstats key is used in 56 places, so it was expected that it would take around 56 times to update the keys with the current implementation, as the IPIs are the most expensive part of the update. Regarding the int3 handler, the non-batch handler takes 45 ns on average, while the batch version takes around 180 ns. At first glance, it seems to be a high value. But it is not, considering that it is doing 56 updates, rather than one! It is taking four times more, only. This gain is possible because the patch uses a binary search in the vector: log2(56)=5.8. So, it was expected to have an overhead within four times. (voice of tv propaganda) But, that is not all! As the int3 handler keeps on for a shorter period (because the update part is on for a shorter time), the number of hits in the int3 handler decreased by 10%. The question then is: Is it worth paying the price of "135 ns" more in the int3 handler? Considering that, in this test case, we are saving the handling of 53 IPIs, that takes more than these 135 ns, it seems to be a meager price to be paid. Moreover, the test case was forcing the hit of the int3, in practice, it does not take that often. While the IPI takes place on all CPUs, hitting the int3 handler or not! For instance, in an isolated CPU with a process running in user-space (nohz_full use-case), the chances of hitting the int3 handler is barely zero, while there is no way to avoid the IPIs. By bounding the IPIs, we are improving a lot this scenario. Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Chris von Recklinghausen <crecklin@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jason Baron <jbaron@akamai.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott Wood <swood@redhat.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/acc891dbc2dbc9fd616dd680529a2337b1d1274c.1560325897.git.bristot@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-06-12 17:57:30 +08:00
#else
static void __jump_label_update(struct static_key *key,
struct jump_entry *entry,
struct jump_entry *stop,
bool init)
{
for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
if (!jump_label_can_update(entry, init))
continue;
if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) {
/*
* Queue is full: Apply the current queue and try again.
*/
arch_jump_label_transform_apply();
BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry)));
}
}
arch_jump_label_transform_apply();
}
#endif
void __init jump_label_init(void)
{
struct jump_entry *iter_start = __start___jump_table;
struct jump_entry *iter_stop = __stop___jump_table;
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct static_key *key = NULL;
struct jump_entry *iter;
/*
* Since we are initializing the static_key.enabled field with
* with the 'raw' int values (to avoid pulling in atomic.h) in
* jump_label.h, let's make sure that is safe. There are only two
* cases to check since we initialize to 0 or 1.
*/
BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0);
BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1);
if (static_key_initialized)
return;
cpus_read_lock();
jump_label_lock();
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct static_key *iterk;
bool in_init;
locking/static_keys: Add a new static_key interface There are various problems and short-comings with the current static_key interface: - static_key_{true,false}() read like a branch depending on the key value, instead of the actual likely/unlikely branch depending on init value. - static_key_{true,false}() are, as stated above, tied to the static_key init values STATIC_KEY_INIT_{TRUE,FALSE}. - we're limited to the 2 (out of 4) possible options that compile to a default NOP because that's what our arch_static_branch() assembly emits. So provide a new static_key interface: DEFINE_STATIC_KEY_TRUE(name); DEFINE_STATIC_KEY_FALSE(name); Which define a key of different types with an initial true/false value. Then allow: static_branch_likely() static_branch_unlikely() to take a key of either type and emit the right instruction for the case. This means adding a second arch_static_branch_jump() assembly helper which emits a JMP per default. In order to determine the right instruction for the right state, encode the branch type in the LSB of jump_entry::key. This is the final step in removing the naming confusion that has led to a stream of avoidable bugs such as: a833581e372a ("x86, perf: Fix static_key bug in load_mm_cr4()") ... but it also allows new static key combinations that will give us performance enhancements in the subsequent patches. Tested-by: Rabin Vincent <rabin@rab.in> # arm Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390 Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-24 21:09:55 +08:00
/* rewrite NOPs */
if (jump_label_type(iter) == JUMP_LABEL_NOP)
arch_jump_label_transform_static(iter, JUMP_LABEL_NOP);
in_init = init_section_contains((void *)jump_entry_code(iter), 1);
jump_entry_set_init(iter, in_init);
jump_label: Annotate entries that operate on __init code earlier Jump table entries are mostly read-only, with the exception of the init and module loader code that defuses entries that point into init code when the code being referred to is freed. For robustness, it would be better to move these entries into the ro_after_init section, but clearing the 'code' member of each jump table entry referring to init code at module load time races with the module_enable_ro() call that remaps the ro_after_init section read only, so we'd like to do it earlier. So given that whether such an entry refers to init code can be decided much earlier, we can pull this check forward. Since we may still need the code entry at this point, let's switch to setting a low bit in the 'key' member just like we do to annotate the default state of a jump table entry. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jessica Yu <jeyu@kernel.org> Link: https://lkml.kernel.org/r/20180919065144.25010-8-ard.biesheuvel@linaro.org
2018-09-19 14:51:42 +08:00
iterk = jump_entry_key(iter);
if (iterk == key)
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
continue;
key = iterk;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
static_key_set_entries(key, iter);
}
static_key_initialized = true;
jump_label_unlock();
cpus_read_unlock();
}
#ifdef CONFIG_MODULES
locking/static_keys: Add a new static_key interface There are various problems and short-comings with the current static_key interface: - static_key_{true,false}() read like a branch depending on the key value, instead of the actual likely/unlikely branch depending on init value. - static_key_{true,false}() are, as stated above, tied to the static_key init values STATIC_KEY_INIT_{TRUE,FALSE}. - we're limited to the 2 (out of 4) possible options that compile to a default NOP because that's what our arch_static_branch() assembly emits. So provide a new static_key interface: DEFINE_STATIC_KEY_TRUE(name); DEFINE_STATIC_KEY_FALSE(name); Which define a key of different types with an initial true/false value. Then allow: static_branch_likely() static_branch_unlikely() to take a key of either type and emit the right instruction for the case. This means adding a second arch_static_branch_jump() assembly helper which emits a JMP per default. In order to determine the right instruction for the right state, encode the branch type in the LSB of jump_entry::key. This is the final step in removing the naming confusion that has led to a stream of avoidable bugs such as: a833581e372a ("x86, perf: Fix static_key bug in load_mm_cr4()") ... but it also allows new static key combinations that will give us performance enhancements in the subsequent patches. Tested-by: Rabin Vincent <rabin@rab.in> # arm Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390 Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-24 21:09:55 +08:00
static enum jump_label_type jump_label_init_type(struct jump_entry *entry)
{
struct static_key *key = jump_entry_key(entry);
bool type = static_key_type(key);
bool branch = jump_entry_is_branch(entry);
locking/static_keys: Add a new static_key interface There are various problems and short-comings with the current static_key interface: - static_key_{true,false}() read like a branch depending on the key value, instead of the actual likely/unlikely branch depending on init value. - static_key_{true,false}() are, as stated above, tied to the static_key init values STATIC_KEY_INIT_{TRUE,FALSE}. - we're limited to the 2 (out of 4) possible options that compile to a default NOP because that's what our arch_static_branch() assembly emits. So provide a new static_key interface: DEFINE_STATIC_KEY_TRUE(name); DEFINE_STATIC_KEY_FALSE(name); Which define a key of different types with an initial true/false value. Then allow: static_branch_likely() static_branch_unlikely() to take a key of either type and emit the right instruction for the case. This means adding a second arch_static_branch_jump() assembly helper which emits a JMP per default. In order to determine the right instruction for the right state, encode the branch type in the LSB of jump_entry::key. This is the final step in removing the naming confusion that has led to a stream of avoidable bugs such as: a833581e372a ("x86, perf: Fix static_key bug in load_mm_cr4()") ... but it also allows new static key combinations that will give us performance enhancements in the subsequent patches. Tested-by: Rabin Vincent <rabin@rab.in> # arm Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390 Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-24 21:09:55 +08:00
/* See the comment in linux/jump_label.h */
return type ^ branch;
}
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct static_key_mod {
struct static_key_mod *next;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
struct jump_entry *entries;
struct module *mod;
};
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
static inline struct static_key_mod *static_key_mod(struct static_key *key)
{
WARN_ON_ONCE(!static_key_linked(key));
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK);
}
/***
* key->type and key->next are the same via union.
* This sets key->next and preserves the type bits.
*
* See additional comments above static_key_set_entries().
*/
static void static_key_set_mod(struct static_key *key,
struct static_key_mod *mod)
{
unsigned long type;
WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK);
type = key->type & JUMP_TYPE_MASK;
key->next = mod;
key->type |= type;
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
static int __jump_label_mod_text_reserved(void *start, void *end)
{
struct module *mod;
int ret;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
preempt_disable();
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
mod = __module_text_address((unsigned long)start);
WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
if (!try_module_get(mod))
mod = NULL;
preempt_enable();
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
if (!mod)
return 0;
ret = __jump_label_text_reserved(mod->jump_entries,
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
mod->jump_entries + mod->num_jump_entries,
start, end, mod->state == MODULE_STATE_COMING);
module_put(mod);
return ret;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
}
static void __jump_label_mod_update(struct static_key *key)
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
{
struct static_key_mod *mod;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
for (mod = static_key_mod(key); mod; mod = mod->next) {
struct jump_entry *stop;
struct module *m;
/*
* NULL if the static_key is defined in a module
* that does not use it
*/
if (!mod->entries)
continue;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
m = mod->mod;
if (!m)
stop = __stop___jump_table;
else
stop = m->jump_entries + m->num_jump_entries;
jump_label: Annotate entries that operate on __init code earlier Jump table entries are mostly read-only, with the exception of the init and module loader code that defuses entries that point into init code when the code being referred to is freed. For robustness, it would be better to move these entries into the ro_after_init section, but clearing the 'code' member of each jump table entry referring to init code at module load time races with the module_enable_ro() call that remaps the ro_after_init section read only, so we'd like to do it earlier. So given that whether such an entry refers to init code can be decided much earlier, we can pull this check forward. Since we may still need the code entry at this point, let's switch to setting a low bit in the 'key' member just like we do to annotate the default state of a jump table entry. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jessica Yu <jeyu@kernel.org> Link: https://lkml.kernel.org/r/20180919065144.25010-8-ard.biesheuvel@linaro.org
2018-09-19 14:51:42 +08:00
__jump_label_update(key, mod->entries, stop,
m && m->state == MODULE_STATE_COMING);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
}
}
/***
* apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
* @mod: module to patch
*
* Allow for run-time selection of the optimal nops. Before the module
* loads patch these with arch_get_jump_label_nop(), which is specified by
* the arch specific jump label code.
*/
void jump_label_apply_nops(struct module *mod)
{
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
/* if the module doesn't have jump label entries, just return */
if (iter_start == iter_stop)
return;
locking/static_keys: Add a new static_key interface There are various problems and short-comings with the current static_key interface: - static_key_{true,false}() read like a branch depending on the key value, instead of the actual likely/unlikely branch depending on init value. - static_key_{true,false}() are, as stated above, tied to the static_key init values STATIC_KEY_INIT_{TRUE,FALSE}. - we're limited to the 2 (out of 4) possible options that compile to a default NOP because that's what our arch_static_branch() assembly emits. So provide a new static_key interface: DEFINE_STATIC_KEY_TRUE(name); DEFINE_STATIC_KEY_FALSE(name); Which define a key of different types with an initial true/false value. Then allow: static_branch_likely() static_branch_unlikely() to take a key of either type and emit the right instruction for the case. This means adding a second arch_static_branch_jump() assembly helper which emits a JMP per default. In order to determine the right instruction for the right state, encode the branch type in the LSB of jump_entry::key. This is the final step in removing the naming confusion that has led to a stream of avoidable bugs such as: a833581e372a ("x86, perf: Fix static_key bug in load_mm_cr4()") ... but it also allows new static key combinations that will give us performance enhancements in the subsequent patches. Tested-by: Rabin Vincent <rabin@rab.in> # arm Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390 Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-24 21:09:55 +08:00
for (iter = iter_start; iter < iter_stop; iter++) {
/* Only write NOPs for arch_branch_static(). */
if (jump_label_init_type(iter) == JUMP_LABEL_NOP)
arch_jump_label_transform_static(iter, JUMP_LABEL_NOP);
}
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
static int jump_label_add_module(struct module *mod)
{
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct static_key *key = NULL;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
struct static_key_mod *jlm, *jlm2;
/* if the module doesn't have jump label entries, just return */
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
if (iter_start == iter_stop)
return 0;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct static_key *iterk;
bool in_init;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
in_init = within_module_init(jump_entry_code(iter), mod);
jump_entry_set_init(iter, in_init);
jump_label: Annotate entries that operate on __init code earlier Jump table entries are mostly read-only, with the exception of the init and module loader code that defuses entries that point into init code when the code being referred to is freed. For robustness, it would be better to move these entries into the ro_after_init section, but clearing the 'code' member of each jump table entry referring to init code at module load time races with the module_enable_ro() call that remaps the ro_after_init section read only, so we'd like to do it earlier. So given that whether such an entry refers to init code can be decided much earlier, we can pull this check forward. Since we may still need the code entry at this point, let's switch to setting a low bit in the 'key' member just like we do to annotate the default state of a jump table entry. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jessica Yu <jeyu@kernel.org> Link: https://lkml.kernel.org/r/20180919065144.25010-8-ard.biesheuvel@linaro.org
2018-09-19 14:51:42 +08:00
iterk = jump_entry_key(iter);
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
if (iterk == key)
continue;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
key = iterk;
if (within_module((unsigned long)key, mod)) {
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
static_key_set_entries(key, iter);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
continue;
}
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
if (!jlm)
return -ENOMEM;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
if (!static_key_linked(key)) {
jlm2 = kzalloc(sizeof(struct static_key_mod),
GFP_KERNEL);
if (!jlm2) {
kfree(jlm);
return -ENOMEM;
}
preempt_disable();
jlm2->mod = __module_address((unsigned long)key);
preempt_enable();
jlm2->entries = static_key_entries(key);
jlm2->next = NULL;
static_key_set_mod(key, jlm2);
static_key_set_linked(key);
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jlm->mod = mod;
jlm->entries = iter;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
jlm->next = static_key_mod(key);
static_key_set_mod(key, jlm);
static_key_set_linked(key);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
locking/static_keys: Add a new static_key interface There are various problems and short-comings with the current static_key interface: - static_key_{true,false}() read like a branch depending on the key value, instead of the actual likely/unlikely branch depending on init value. - static_key_{true,false}() are, as stated above, tied to the static_key init values STATIC_KEY_INIT_{TRUE,FALSE}. - we're limited to the 2 (out of 4) possible options that compile to a default NOP because that's what our arch_static_branch() assembly emits. So provide a new static_key interface: DEFINE_STATIC_KEY_TRUE(name); DEFINE_STATIC_KEY_FALSE(name); Which define a key of different types with an initial true/false value. Then allow: static_branch_likely() static_branch_unlikely() to take a key of either type and emit the right instruction for the case. This means adding a second arch_static_branch_jump() assembly helper which emits a JMP per default. In order to determine the right instruction for the right state, encode the branch type in the LSB of jump_entry::key. This is the final step in removing the naming confusion that has led to a stream of avoidable bugs such as: a833581e372a ("x86, perf: Fix static_key bug in load_mm_cr4()") ... but it also allows new static key combinations that will give us performance enhancements in the subsequent patches. Tested-by: Rabin Vincent <rabin@rab.in> # arm Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390 Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-24 21:09:55 +08:00
/* Only update if we've changed from our initial state */
if (jump_label_type(iter) != jump_label_init_type(iter))
jump_label: Annotate entries that operate on __init code earlier Jump table entries are mostly read-only, with the exception of the init and module loader code that defuses entries that point into init code when the code being referred to is freed. For robustness, it would be better to move these entries into the ro_after_init section, but clearing the 'code' member of each jump table entry referring to init code at module load time races with the module_enable_ro() call that remaps the ro_after_init section read only, so we'd like to do it earlier. So given that whether such an entry refers to init code can be decided much earlier, we can pull this check forward. Since we may still need the code entry at this point, let's switch to setting a low bit in the 'key' member just like we do to annotate the default state of a jump table entry. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jessica Yu <jeyu@kernel.org> Link: https://lkml.kernel.org/r/20180919065144.25010-8-ard.biesheuvel@linaro.org
2018-09-19 14:51:42 +08:00
__jump_label_update(key, iter, iter_stop, true);
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
return 0;
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
static void jump_label_del_module(struct module *mod)
{
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct static_key *key = NULL;
struct static_key_mod *jlm, **prev;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
for (iter = iter_start; iter < iter_stop; iter++) {
if (jump_entry_key(iter) == key)
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
continue;
key = jump_entry_key(iter);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
if (within_module((unsigned long)key, mod))
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
continue;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
/* No memory during module load */
if (WARN_ON(!static_key_linked(key)))
continue;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
prev = &key->next;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
jlm = static_key_mod(key);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
while (jlm && jlm->mod != mod) {
prev = &jlm->next;
jlm = jlm->next;
}
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
/* No memory during module load */
if (WARN_ON(!jlm))
continue;
if (prev == &key->next)
static_key_set_mod(key, jlm->next);
else
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
*prev = jlm->next;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
kfree(jlm);
jlm = static_key_mod(key);
/* if only one etry is left, fold it back into the static_key */
if (jlm->next == NULL) {
static_key_set_entries(key, jlm->entries);
static_key_clear_linked(key);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
kfree(jlm);
}
}
}
static int
jump_label_module_notify(struct notifier_block *self, unsigned long val,
void *data)
{
struct module *mod = data;
int ret = 0;
cpus_read_lock();
jump_label_lock();
switch (val) {
case MODULE_STATE_COMING:
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
ret = jump_label_add_module(mod);
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
if (ret) {
WARN(1, "Failed to allocate memory: jump_label may not work properly.\n");
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label_del_module(mod);
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
}
break;
case MODULE_STATE_GOING:
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
jump_label_del_module(mod);
break;
}
jump_label_unlock();
cpus_read_unlock();
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
return notifier_from_errno(ret);
}
static struct notifier_block jump_label_module_nb = {
.notifier_call = jump_label_module_notify,
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
.priority = 1, /* higher than tracepoints */
};
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
static __init int jump_label_init_module(void)
{
return register_module_notifier(&jump_label_module_nb);
}
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
early_initcall(jump_label_init_module);
#endif /* CONFIG_MODULES */
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
/***
* jump_label_text_reserved - check if addr range is reserved
* @start: start text addr
* @end: end text addr
*
* checks if the text addr located between @start and @end
* overlaps with any of the jump label patch addresses. Code
* that wants to modify kernel text should first verify that
* it does not overlap with any of the jump label addresses.
* Caller must hold jump_label_mutex.
*
* returns 1 if there is an overlap, 0 otherwise
*/
int jump_label_text_reserved(void *start, void *end)
{
bool init = system_state < SYSTEM_RUNNING;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
int ret = __jump_label_text_reserved(__start___jump_table,
__stop___jump_table, start, end, init);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
if (ret)
return ret;
#ifdef CONFIG_MODULES
ret = __jump_label_mod_text_reserved(start, end);
#endif
return ret;
}
static void jump_label_update(struct static_key *key)
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
{
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 15:31:31 +08:00
struct jump_entry *stop = __stop___jump_table;
bool init = system_state < SYSTEM_RUNNING;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
struct jump_entry *entry;
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
#ifdef CONFIG_MODULES
module, jump_label: Fix module locking As per the module core lockdep annotations in the coming patch: [ 18.034047] ---[ end trace 9294429076a9c673 ]--- [ 18.047760] Hardware name: Intel Corporation S2600GZ/S2600GZ, BIOS SE5C600.86B.02.02.0002.122320131210 12/23/2013 [ 18.059228] ffffffff817d8676 ffff880036683c38 ffffffff8157e98b 0000000000000001 [ 18.067541] 0000000000000000 ffff880036683c78 ffffffff8105fbc7 ffff880036683c68 [ 18.075851] ffffffffa0046b08 0000000000000000 ffffffffa0046d00 ffffffffa0046cc8 [ 18.084173] Call Trace: [ 18.086906] [<ffffffff8157e98b>] dump_stack+0x4f/0x7b [ 18.092649] [<ffffffff8105fbc7>] warn_slowpath_common+0x97/0xe0 [ 18.099361] [<ffffffff8105fc2a>] warn_slowpath_null+0x1a/0x20 [ 18.105880] [<ffffffff810ee502>] __module_address+0x1d2/0x1e0 [ 18.112400] [<ffffffff81161153>] jump_label_module_notify+0x143/0x1e0 [ 18.119710] [<ffffffff810814bf>] notifier_call_chain+0x4f/0x70 [ 18.126326] [<ffffffff8108160e>] __blocking_notifier_call_chain+0x5e/0x90 [ 18.134009] [<ffffffff81081656>] blocking_notifier_call_chain+0x16/0x20 [ 18.141490] [<ffffffff810f0f00>] load_module+0x1b50/0x2660 [ 18.147720] [<ffffffff810f1ade>] SyS_init_module+0xce/0x100 [ 18.154045] [<ffffffff81587429>] system_call_fastpath+0x12/0x17 [ 18.160748] ---[ end trace 9294429076a9c674 ]--- Jump labels is not doing it right; fix this. Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Jason Baron <jbaron@akamai.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2015-05-27 09:39:35 +08:00
struct module *mod;
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
if (static_key_linked(key)) {
__jump_label_mod_update(key);
return;
}
module, jump_label: Fix module locking As per the module core lockdep annotations in the coming patch: [ 18.034047] ---[ end trace 9294429076a9c673 ]--- [ 18.047760] Hardware name: Intel Corporation S2600GZ/S2600GZ, BIOS SE5C600.86B.02.02.0002.122320131210 12/23/2013 [ 18.059228] ffffffff817d8676 ffff880036683c38 ffffffff8157e98b 0000000000000001 [ 18.067541] 0000000000000000 ffff880036683c78 ffffffff8105fbc7 ffff880036683c68 [ 18.075851] ffffffffa0046b08 0000000000000000 ffffffffa0046d00 ffffffffa0046cc8 [ 18.084173] Call Trace: [ 18.086906] [<ffffffff8157e98b>] dump_stack+0x4f/0x7b [ 18.092649] [<ffffffff8105fbc7>] warn_slowpath_common+0x97/0xe0 [ 18.099361] [<ffffffff8105fc2a>] warn_slowpath_null+0x1a/0x20 [ 18.105880] [<ffffffff810ee502>] __module_address+0x1d2/0x1e0 [ 18.112400] [<ffffffff81161153>] jump_label_module_notify+0x143/0x1e0 [ 18.119710] [<ffffffff810814bf>] notifier_call_chain+0x4f/0x70 [ 18.126326] [<ffffffff8108160e>] __blocking_notifier_call_chain+0x5e/0x90 [ 18.134009] [<ffffffff81081656>] blocking_notifier_call_chain+0x16/0x20 [ 18.141490] [<ffffffff810f0f00>] load_module+0x1b50/0x2660 [ 18.147720] [<ffffffff810f1ade>] SyS_init_module+0xce/0x100 [ 18.154045] [<ffffffff81587429>] system_call_fastpath+0x12/0x17 [ 18.160748] ---[ end trace 9294429076a9c674 ]--- Jump labels is not doing it right; fix this. Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Jason Baron <jbaron@akamai.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2015-05-27 09:39:35 +08:00
preempt_disable();
mod = __module_address((unsigned long)key);
if (mod) {
stop = mod->jump_entries + mod->num_jump_entries;
init = mod->state == MODULE_STATE_COMING;
}
module, jump_label: Fix module locking As per the module core lockdep annotations in the coming patch: [ 18.034047] ---[ end trace 9294429076a9c673 ]--- [ 18.047760] Hardware name: Intel Corporation S2600GZ/S2600GZ, BIOS SE5C600.86B.02.02.0002.122320131210 12/23/2013 [ 18.059228] ffffffff817d8676 ffff880036683c38 ffffffff8157e98b 0000000000000001 [ 18.067541] 0000000000000000 ffff880036683c78 ffffffff8105fbc7 ffff880036683c68 [ 18.075851] ffffffffa0046b08 0000000000000000 ffffffffa0046d00 ffffffffa0046cc8 [ 18.084173] Call Trace: [ 18.086906] [<ffffffff8157e98b>] dump_stack+0x4f/0x7b [ 18.092649] [<ffffffff8105fbc7>] warn_slowpath_common+0x97/0xe0 [ 18.099361] [<ffffffff8105fc2a>] warn_slowpath_null+0x1a/0x20 [ 18.105880] [<ffffffff810ee502>] __module_address+0x1d2/0x1e0 [ 18.112400] [<ffffffff81161153>] jump_label_module_notify+0x143/0x1e0 [ 18.119710] [<ffffffff810814bf>] notifier_call_chain+0x4f/0x70 [ 18.126326] [<ffffffff8108160e>] __blocking_notifier_call_chain+0x5e/0x90 [ 18.134009] [<ffffffff81081656>] blocking_notifier_call_chain+0x16/0x20 [ 18.141490] [<ffffffff810f0f00>] load_module+0x1b50/0x2660 [ 18.147720] [<ffffffff810f1ade>] SyS_init_module+0xce/0x100 [ 18.154045] [<ffffffff81587429>] system_call_fastpath+0x12/0x17 [ 18.160748] ---[ end trace 9294429076a9c674 ]--- Jump labels is not doing it right; fix this. Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Jason Baron <jbaron@akamai.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2015-05-27 09:39:35 +08:00
preempt_enable();
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
#endif
jump_label: Reduce the size of struct static_key The static_key->next field goes mostly unused. The field is used for associating module uses with a static key. Most uses of struct static_key define a static key in the core kernel and make use of it entirely within the core kernel, or define the static key in a module and make use of it only from within that module. In fact, of the ~3,000 static keys defined, I found only about 5 or so that did not fit this pattern. Thus, we can remove the static_key->next field entirely and overload the static_key->entries field. That is, when all the static_key uses are contained within the same module, static_key->entries continues to point to those uses. However, if the static_key uses are not contained within the module where the static_key is defined, then we allocate a struct static_key_mod, store a pointer to the uses within that struct static_key_mod, and have the static key point at the static_key_mod. This does incur some extra memory usage when a static_key is used in a module that does not define it, but since there are only a handful of such cases there is a net savings. In order to identify if the static_key->entries pointer contains a struct static_key_mod or a struct jump_entry pointer, bit 1 of static_key->entries is set to 1 if it points to a struct static_key_mod and is 0 if it points to a struct jump_entry. We were already using bit 0 in a similar way to store the initial value of the static_key. This does mean that allocations of struct static_key_mod and that the struct jump_entry tables need to be at least 4-byte aligned in memory. As far as I can tell all arches meet this criteria. For my .config, the patch increased the text by 778 bytes, but reduced the data + bss size by 14912, for a net savings of 14,134 bytes. text data bss dec hex filename 8092427 5016512 790528 13899467 d416cb vmlinux.pre 8093205 5001600 790528 13885333 d3df95 vmlinux.post Link: http://lkml.kernel.org/r/1486154544-4321-1-git-send-email-jbaron@akamai.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Joe Perches <joe@perches.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-02-04 04:42:24 +08:00
entry = static_key_entries(key);
/* if there are no users, entry can be NULL */
if (entry)
__jump_label_update(key, entry, stop, init);
jump label: Introduce static_branch() interface Introduce: static __always_inline bool static_branch(struct jump_label_key *key); instead of the old JUMP_LABEL(key, label) macro. In this way, jump labels become really easy to use: Define: struct jump_label_key jump_key; Can be used as: if (static_branch(&jump_key)) do unlikely code enable/disale via: jump_label_inc(&jump_key); jump_label_dec(&jump_key); that's it! For the jump labels disabled case, the static_branch() becomes an atomic_read(), and jump_label_inc()/dec() are simply atomic_inc(), atomic_dec() operations. We show testing results for this change below. Thanks to H. Peter Anvin for suggesting the 'static_branch()' construct. Since we now require a 'struct jump_label_key *key', we can store a pointer into the jump table addresses. In this way, we can enable/disable jump labels, in basically constant time. This change allows us to completely remove the previous hashtable scheme. Thanks to Peter Zijlstra for this re-write. Testing: I ran a series of 'tbench 20' runs 5 times (with reboots) for 3 configurations, where tracepoints were disabled. jump label configured in avg: 815.6 jump label *not* configured in (using atomic reads) avg: 800.1 jump label *not* configured in (regular reads) avg: 803.4 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20110316212947.GA8792@redhat.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Suggested-by: H. Peter Anvin <hpa@linux.intel.com> Tested-by: David Daney <ddaney@caviumnetworks.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-03-17 05:29:47 +08:00
}
#ifdef CONFIG_STATIC_KEYS_SELFTEST
static DEFINE_STATIC_KEY_TRUE(sk_true);
static DEFINE_STATIC_KEY_FALSE(sk_false);
static __init int jump_label_test(void)
{
int i;
for (i = 0; i < 2; i++) {
WARN_ON(static_key_enabled(&sk_true.key) != true);
WARN_ON(static_key_enabled(&sk_false.key) != false);
WARN_ON(!static_branch_likely(&sk_true));
WARN_ON(!static_branch_unlikely(&sk_true));
WARN_ON(static_branch_likely(&sk_false));
WARN_ON(static_branch_unlikely(&sk_false));
static_branch_disable(&sk_true);
static_branch_enable(&sk_false);
WARN_ON(static_key_enabled(&sk_true.key) == true);
WARN_ON(static_key_enabled(&sk_false.key) == false);
WARN_ON(static_branch_likely(&sk_true));
WARN_ON(static_branch_unlikely(&sk_true));
WARN_ON(!static_branch_likely(&sk_false));
WARN_ON(!static_branch_unlikely(&sk_false));
static_branch_enable(&sk_true);
static_branch_disable(&sk_false);
}
return 0;
}
early_initcall(jump_label_test);
#endif /* STATIC_KEYS_SELFTEST */