| Message ID | 20230116162522.4072-1-ubizjak@gmail.com (mailing list archive) |
|---|---|
| State | Handled Elsewhere, archived |
| Headers | show |
| Series | x86/ACPI/boot: use try_cmpxchg in __acpi_{acquire,release}_global_lock | expand |
On Mon, Jan 16, 2023 at 5:25 PM Uros Bizjak <ubizjak@gmail.com> wrote: > > Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in > __acpi_{acquire,release}_global_lock. x86 CMPXCHG instruction returns > success in ZF flag, so this change saves a compare after cmpxchg > (and related move instruction in front of cmpxchg). > > Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg > fails. There is no need to re-read the value in the loop. > > Note that the value from *ptr should be read using READ_ONCE to prevent > the compiler from merging, refetching or reordering the read. > > No functional change intended. > > Signed-off-by: Uros Bizjak <ubizjak@gmail.com> > Cc: "Rafael J. Wysocki" <rafael@kernel.org> > Cc: Len Brown <len.brown@intel.com> > Cc: Pavel Machek <pavel@ucw.cz> > Cc: Thomas Gleixner <tglx@linutronix.de> > Cc: Ingo Molnar <mingo@redhat.com> > Cc: Borislav Petkov <bp@alien8.de> > Cc: Dave Hansen <dave.hansen@linux.intel.com> > Cc: "H. Peter Anvin" <hpa@zytor.com> Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> but please CC linux-acpi on all ACPI-related changes in the future. > --- > arch/x86/kernel/acpi/boot.c | 16 ++++++++-------- > 1 file changed, 8 insertions(+), 8 deletions(-) > > diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c > index 907cc98b1938..4177577c173b 100644 > --- a/arch/x86/kernel/acpi/boot.c > +++ b/arch/x86/kernel/acpi/boot.c > @@ -1840,23 +1840,23 @@ early_param("acpi_sci", setup_acpi_sci); > > int __acpi_acquire_global_lock(unsigned int *lock) > { > - unsigned int old, new, val; > + unsigned int old, new; > + > + old = READ_ONCE(*lock); > do { > - old = *lock; > new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); > - val = cmpxchg(lock, old, new); > - } while (unlikely (val != old)); > + } while (!try_cmpxchg(lock, &old, new)); > return ((new & 0x3) < 3) ? -1 : 0; > } > > int __acpi_release_global_lock(unsigned int *lock) > { > - unsigned int old, new, val; > + unsigned int old, new; > + > + old = READ_ONCE(*lock); > do { > - old = *lock; > new = old & ~0x3; > - val = cmpxchg(lock, old, new); > - } while (unlikely (val != old)); > + } while (!try_cmpxchg(lock, &old, new)); > return old & 0x1; > } > > -- > 2.39.0 >
* Rafael J. Wysocki <rafael@kernel.org> wrote: > On Mon, Jan 16, 2023 at 5:25 PM Uros Bizjak <ubizjak@gmail.com> wrote: > > > > Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in > > __acpi_{acquire,release}_global_lock. x86 CMPXCHG instruction returns > > success in ZF flag, so this change saves a compare after cmpxchg > > (and related move instruction in front of cmpxchg). > > > > Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg > > fails. There is no need to re-read the value in the loop. > > > > Note that the value from *ptr should be read using READ_ONCE to prevent > > the compiler from merging, refetching or reordering the read. > > > > No functional change intended. > > > > Signed-off-by: Uros Bizjak <ubizjak@gmail.com> > > Cc: "Rafael J. Wysocki" <rafael@kernel.org> > > Cc: Len Brown <len.brown@intel.com> > > Cc: Pavel Machek <pavel@ucw.cz> > > Cc: Thomas Gleixner <tglx@linutronix.de> > > Cc: Ingo Molnar <mingo@redhat.com> > > Cc: Borislav Petkov <bp@alien8.de> > > Cc: Dave Hansen <dave.hansen@linux.intel.com> > > Cc: "H. Peter Anvin" <hpa@zytor.com> > > Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > but please CC linux-acpi on all ACPI-related changes in the future. Thanks Rafael - I'll take this patch through the locking tree, if that's fine with you. Thanks, Ingo
On Thu, Jan 26, 2023 at 11:48 AM Ingo Molnar <mingo@kernel.org> wrote: > > > * Rafael J. Wysocki <rafael@kernel.org> wrote: > > > On Mon, Jan 16, 2023 at 5:25 PM Uros Bizjak <ubizjak@gmail.com> wrote: > > > > > > Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in > > > __acpi_{acquire,release}_global_lock. x86 CMPXCHG instruction returns > > > success in ZF flag, so this change saves a compare after cmpxchg > > > (and related move instruction in front of cmpxchg). > > > > > > Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg > > > fails. There is no need to re-read the value in the loop. > > > > > > Note that the value from *ptr should be read using READ_ONCE to prevent > > > the compiler from merging, refetching or reordering the read. > > > > > > No functional change intended. > > > > > > Signed-off-by: Uros Bizjak <ubizjak@gmail.com> > > > Cc: "Rafael J. Wysocki" <rafael@kernel.org> > > > Cc: Len Brown <len.brown@intel.com> > > > Cc: Pavel Machek <pavel@ucw.cz> > > > Cc: Thomas Gleixner <tglx@linutronix.de> > > > Cc: Ingo Molnar <mingo@redhat.com> > > > Cc: Borislav Petkov <bp@alien8.de> > > > Cc: Dave Hansen <dave.hansen@linux.intel.com> > > > Cc: "H. Peter Anvin" <hpa@zytor.com> > > > > Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > > > but please CC linux-acpi on all ACPI-related changes in the future. > > Thanks Rafael - I'll take this patch through the locking tree, if that's > fine with you. It is, thanks!
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 907cc98b1938..4177577c173b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1840,23 +1840,23 @@ early_param("acpi_sci", setup_acpi_sci); int __acpi_acquire_global_lock(unsigned int *lock) { - unsigned int old, new, val; + unsigned int old, new; + + old = READ_ONCE(*lock); do { - old = *lock; new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); - val = cmpxchg(lock, old, new); - } while (unlikely (val != old)); + } while (!try_cmpxchg(lock, &old, new)); return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) { - unsigned int old, new, val; + unsigned int old, new; + + old = READ_ONCE(*lock); do { - old = *lock; new = old & ~0x3; - val = cmpxchg(lock, old, new); - } while (unlikely (val != old)); + } while (!try_cmpxchg(lock, &old, new)); return old & 0x1; }
Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in __acpi_{acquire,release}_global_lock. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails. There is no need to re-read the value in the loop. Note that the value from *ptr should be read using READ_ONCE to prevent the compiler from merging, refetching or reordering the read. No functional change intended. Signed-off-by: Uros Bizjak <ubizjak@gmail.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> --- arch/x86/kernel/acpi/boot.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)