From 91710728d1725de51d06b40674abf6e860d592c7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 27 May 2020 22:11:13 +0200 Subject: locking: Introduce local_lock() preempt_disable() and local_irq_disable/save() are in principle per CPU big kernel locks. This has several downsides: - The protection scope is unknown - Violation of protection rules is hard to detect by instrumentation - For PREEMPT_RT such sections, unless in low level critical code, can violate the preemptability constraints. To address this PREEMPT_RT introduced the concept of local_locks which are strictly per CPU. The lock operations map to preempt_disable(), local_irq_disable/save() and the enabling counterparts on non RT enabled kernels. If lockdep is enabled local locks gain a lock map which tracks the usage context. This will catch cases where an area is protected by preempt_disable() but the access also happens from interrupt context. local locks have identified quite a few such issues over the years, the most recent example is: b7d5dc21072cd ("random: add a spinlock_t to struct batched_entropy") Aside of the lockdep coverage this also improves code readability as it precisely annotates the protection scope. PREEMPT_RT substitutes these local locks with 'sleeping' spinlocks to protect such sections while maintaining preemtability and CPU locality. local locks can replace: - preempt_enable()/disable() pairs - local_irq_disable/enable() pairs - local_irq_save/restore() pairs They are also used to replace code which implicitly disables preemption like: - get_cpu()/put_cpu() - get_cpu_var()/put_cpu_var() with PREEMPT_RT friendly constructs. Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-2-bigeasy@linutronix.de --- include/linux/local_lock.h | 54 ++++++++++++++++++++++ include/linux/local_lock_internal.h | 90 +++++++++++++++++++++++++++++++++++++ 2 files changed, 144 insertions(+) create mode 100644 include/linux/local_lock.h create mode 100644 include/linux/local_lock_internal.h (limited to 'include/linux') diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h new file mode 100644 index 000000000000..e55010fa7329 --- /dev/null +++ b/include/linux/local_lock.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LOCAL_LOCK_H +#define _LINUX_LOCAL_LOCK_H + +#include + +/** + * local_lock_init - Runtime initialize a lock instance + */ +#define local_lock_init(lock) __local_lock_init(lock) + +/** + * local_lock - Acquire a per CPU local lock + * @lock: The lock variable + */ +#define local_lock(lock) __local_lock(lock) + +/** + * local_lock_irq - Acquire a per CPU local lock and disable interrupts + * @lock: The lock variable + */ +#define local_lock_irq(lock) __local_lock_irq(lock) + +/** + * local_lock_irqsave - Acquire a per CPU local lock, save and disable + * interrupts + * @lock: The lock variable + * @flags: Storage for interrupt flags + */ +#define local_lock_irqsave(lock, flags) \ + __local_lock_irqsave(lock, flags) + +/** + * local_unlock - Release a per CPU local lock + * @lock: The lock variable + */ +#define local_unlock(lock) __local_unlock(lock) + +/** + * local_unlock_irq - Release a per CPU local lock and enable interrupts + * @lock: The lock variable + */ +#define local_unlock_irq(lock) __local_unlock_irq(lock) + +/** + * local_unlock_irqrestore - Release a per CPU local lock and restore + * interrupt flags + * @lock: The lock variable + * @flags: Interrupt flags to restore + */ +#define local_unlock_irqrestore(lock, flags) \ + __local_unlock_irqrestore(lock, flags) + +#endif diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h new file mode 100644 index 000000000000..4a8795b21d77 --- /dev/null +++ b/include/linux/local_lock_internal.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LOCAL_LOCK_H +# error "Do not include directly, include linux/local_lock.h" +#endif + +#include +#include + +typedef struct { +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; + struct task_struct *owner; +#endif +} local_lock_t; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define LL_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_CONFIG, \ + } +#else +# define LL_DEP_MAP_INIT(lockname) +#endif + +#define INIT_LOCAL_LOCK(lockname) { LL_DEP_MAP_INIT(lockname) } + +#define __local_lock_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\ +} while (0) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline void local_lock_acquire(local_lock_t *l) +{ + lock_map_acquire(&l->dep_map); + DEBUG_LOCKS_WARN_ON(l->owner); + l->owner = current; +} + +static inline void local_lock_release(local_lock_t *l) +{ + DEBUG_LOCKS_WARN_ON(l->owner != current); + l->owner = NULL; + lock_map_release(&l->dep_map); +} + +#else /* CONFIG_DEBUG_LOCK_ALLOC */ +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ + +#define __local_lock(lock) \ + do { \ + preempt_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_lock_irq(lock) \ + do { \ + local_irq_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_lock_irqsave(lock, flags) \ + do { \ + local_irq_save(flags); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + preempt_enable(); \ + } while (0) + +#define __local_unlock_irq(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + local_irq_enable(); \ + } while (0) + +#define __local_unlock_irqrestore(lock, flags) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + local_irq_restore(flags); \ + } while (0) -- cgit v1.2.3 From cfa6705d89b6562f79c40c249f8d94073c4276e4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 27 May 2020 22:11:14 +0200 Subject: radix-tree: Use local_lock for protection The radix-tree and idr preload mechanisms use preempt_disable() to protect the complete operation between xxx_preload() and xxx_preload_end(). As the code inside the preempt disabled section acquires regular spinlocks, which are converted to 'sleeping' spinlocks on a PREEMPT_RT kernel and eventually calls into a memory allocator, this conflicts with the RT semantics. Convert it to a local_lock which allows RT kernels to substitute them with a real per CPU lock. On non RT kernels this maps to preempt_disable() as before, but provides also lockdep coverage of the critical region. No functional change. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-3-bigeasy@linutronix.de --- include/linux/idr.h | 2 +- include/linux/radix-tree.h | 11 ++++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index ac6e946b6767..3ade03e5c7af 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -171,7 +171,7 @@ static inline bool idr_is_empty(const struct idr *idr) */ static inline void idr_preload_end(void) { - preempt_enable(); + local_unlock(&radix_tree_preloads.lock); } /** diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 63e62372443a..c2a9f7c90727 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -16,11 +16,20 @@ #include #include #include +#include /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node +struct radix_tree_preload { + local_lock_t lock; + unsigned nr; + /* nodes->parent points to next preallocated node */ + struct radix_tree_node *nodes; +}; +DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); + /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: @@ -245,7 +254,7 @@ int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { - preempt_enable(); + local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, -- cgit v1.2.3 From b01b2141999936ac3e4746b7f76c0f204ae4b445 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 27 May 2020 22:11:15 +0200 Subject: mm/swap: Use local_lock for protection The various struct pagevec per CPU variables are protected by disabling either preemption or interrupts across the critical sections. Inside these sections spinlocks have to be acquired. These spinlocks are regular spinlock_t types which are converted to "sleeping" spinlocks on PREEMPT_RT enabled kernels. Obviously sleeping locks cannot be acquired in preemption or interrupt disabled sections. local locks provide a trivial way to substitute preempt and interrupt disable instances. On a non PREEMPT_RT enabled kernel local_lock() maps to preempt_disable() and local_lock_irq() to local_irq_disable(). Create lru_rotate_pvecs containing the pagevec and the locallock. Create lru_pvecs containing the remaining pagevecs and the locallock. Add lru_add_drain_cpu_zone() which is used from compact_zone() to avoid exporting the pvec structure. Change the relevant call sites to acquire these locks instead of using preempt_disable() / get_cpu() / get_cpu_var() and local_irq_disable() / local_irq_save(). There is neither a functional change nor a change in the generated binary code for non PREEMPT_RT enabled non-debug kernels. When lockdep is enabled local locks have lockdep maps embedded. These allow lockdep to validate the protections, i.e. inappropriate usage of a preemption only protected sections would result in a lockdep warning while the same problem would not be noticed with a plain preempt_disable() based protection. local locks also improve readability as they provide a named scope for the protections while preempt/interrupt disable are opaque scopeless. Finally local locks allow PREEMPT_RT to substitute them with real locking primitives to ensure the correctness of operation in a fully preemptible kernel. [ bigeasy: Adopted to use local_lock ] Signed-off-by: Ingo Molnar Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-4-bigeasy@linutronix.de --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e1bbf7a16b27..25181d2dd0b9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -337,6 +337,7 @@ extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); +extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); -- cgit v1.2.3