From f2ae67941138a1e53cb1bc6a1b5878a8bdc74d26 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 12 Jun 2018 18:16:19 +0200 Subject: alpha: Remove custom dec_and_lock() implementation Alpha provides a custom implementation of dec_and_lock(). The functions is split into two parts: - atomic_add_unless() + return 0 (fast path in assembly) - remaining part including locking (slow path in C) Comparing the result of the alpha implementation with the generic implementation compiled by gcc it looks like the fast path is optimized by avoiding a stack frame (and reloading the GP), register store and all this. This is only done in the slowpath. After marking the slowpath (atomic_dec_and_lock_1()) as "noinline" and doing the slowpath in C (the atomic_add_unless(atomic, -1, 1) part) I noticed differences in the resulting assembly: - the GP is still reloaded - atomic_add_unless() adds more memory barriers compared to the custom assembly - the custom assembly here does "load, sub, beq" while atomic_add_unless() does "load, cmpeq, add, bne". This is okay because it compares against zero after subtraction while the generic code compares against 1 before. I'm not sure if avoiding the stack frame (and GP reloading) brings a lot in terms of performance. Regarding the different barriers, Peter Zijlstra says: |refcount decrement needs to be a RELEASE operation, such that all the |load/stores to the object happen before we decrement the refcount. | |Otherwise things like: | | obj->foo = 5; | refcnt_dec(&obj->ref); | |can be re-ordered, which then allows fun scenarios like: | | CPU0 CPU1 | | refcnt_dec(&obj->ref); | if (dec_and_test(&obj->ref)) | free(obj); | obj->foo = 5; // oops UaF | | |This means (for alpha) that there should be a memory barrier _before_ |the decrement, however the dec_and_lock asm thing only has one _after_, |which, per the above, is too late. | |The generic version using add_unless will result in memory barrier |before and after (because that is the rule for atomic ops with a return |value) which is strictly too many barriers for the refcount story, but |who knows what other ordering requirements code has. Remove the custom alpha implementation of dec_and_lock() and if it is an issue (performance wise) then the fast path could still be inlined. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: linux-alpha@vger.kernel.org Link: https://lkml.kernel.org/r/20180606115918.GG12198@hirez.programming.kicks-ass.net Link: https://lkml.kernel.org/r20180612161621.22645-2-bigeasy@linutronix.de --- lib/Makefile | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 84c6dcb31fbb..8b59f4a7c0e2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -23,7 +23,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ sha1.o chacha20.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ - earlycpio.o seq_buf.o siphash.o \ + earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ nmi_backtrace.o nodemask.o win_minmax.o lib-$(CONFIG_PRINTK) += dump_stack.o @@ -98,10 +98,6 @@ obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o obj-$(CONFIG_DEBUG_LIST) += list_debug.o obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o -ifneq ($(CONFIG_HAVE_DEC_LOCK),y) - lib-y += dec_and_lock.o -endif - obj-$(CONFIG_BITREVERSE) += bitrev.o obj-$(CONFIG_RATIONAL) += rational.o obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o -- cgit v1.2.3 From ccfbb5bed407053b27492a9adc06064d949a9aa6 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Tue, 12 Jun 2018 18:16:20 +0200 Subject: atomic: Add irqsave variant of atomic_dec_and_lock() There are in-tree users of atomic_dec_and_lock() which must acquire the spin lock with interrupts disabled. To workaround the lack of an irqsave variant of atomic_dec_and_lock() they use local_irq_save() at the call site. This causes extra code and creates in some places unneeded long interrupt disabled times. These places need also extra treatment for PREEMPT_RT due to the disconnect of the irq disabling and the lock function. Implement the missing irqsave variant of the function. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r20180612161621.22645-3-bigeasy@linutronix.de --- include/linux/spinlock.h | 5 +++++ lib/dec_and_lock.c | 16 ++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'lib') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1e8a46435838..fd57888d4942 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -427,6 +427,11 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) +extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, + unsigned long *flags); +#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ + __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) + int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp); diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c index 347fa7ac2e8a..9555b68bb774 100644 --- a/lib/dec_and_lock.c +++ b/lib/dec_and_lock.c @@ -33,3 +33,19 @@ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) } EXPORT_SYMBOL(_atomic_dec_and_lock); + +int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, + unsigned long *flags) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + spin_lock_irqsave(lock, *flags); + if (atomic_dec_and_test(atomic)) + return 1; + spin_unlock_irqrestore(lock, *flags); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); -- cgit v1.2.3 From 7ea959c45769612aa92557fb6464679f5fec7d9e Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Tue, 12 Jun 2018 18:16:21 +0200 Subject: locking/refcounts: Implement refcount_dec_and_lock_irqsave() There are in-tree users of refcount_dec_and_lock() which must acquire the spin lock with interrupts disabled. To workaround the lack of an irqsave variant of refcount_dec_and_lock() they use local_irq_save() at the call site. This causes extra code and creates in some places unneeded long interrupt disabled times. These places need also extra treatment for PREEMPT_RT due to the disconnect of the irq disabling and the lock function. Implement the missing irqsave variant of the function. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r20180612161621.22645-4-bigeasy@linutronix.de [bigeasy: s@atomic_dec_and_lock@refcount_dec_and_lock@g] --- include/linux/refcount.h | 4 +++- lib/refcount.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 4193c41e383a..a685da2c4522 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -98,5 +98,7 @@ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); - +extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, + spinlock_t *lock, + unsigned long *flags); #endif /* _LINUX_REFCOUNT_H */ diff --git a/lib/refcount.c b/lib/refcount.c index 0eb48353abe3..d3b81cefce91 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -350,3 +350,31 @@ bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) } EXPORT_SYMBOL(refcount_dec_and_lock); +/** + * refcount_dec_and_lock_irqsave - return holding spinlock with disabled + * interrupts if able to decrement refcount to 0 + * @r: the refcount + * @lock: the spinlock to be locked + * @flags: saved IRQ-flags if the is acquired + * + * Same as refcount_dec_and_lock() above except that the spinlock is acquired + * with disabled interupts. + * + * Return: true and hold spinlock if able to decrement refcount to 0, false + * otherwise + */ +bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, + unsigned long *flags) +{ + if (refcount_dec_not_one(r)) + return false; + + spin_lock_irqsave(lock, *flags); + if (!refcount_dec_and_test(r)) { + spin_unlock_irqrestore(lock, *flags); + return false; + } + + return true; +} +EXPORT_SYMBOL(refcount_dec_and_lock_irqsave); -- cgit v1.2.3