This is a note to let you know that I've just added the patch titled locking/barriers: Convert users of lockless_dereference() to READ_ONCE() to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: locking-barriers-convert-users-of-lockless_dereference-to-read_once.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From 3382290ed2d5e275429cef510ab21889d3ccd164 Mon Sep 17 00:00:00 2001 From: Will Deacon <will.deacon@xxxxxxx> Date: Tue, 24 Oct 2017 11:22:48 +0100 Subject: locking/barriers: Convert users of lockless_dereference() to READ_ONCE() From: Will Deacon <will.deacon@xxxxxxx> commit 3382290ed2d5e275429cef510ab21889d3ccd164 upstream. [ Note, this is a Git cherry-pick of the following commit: 506458efaf15 ("locking/barriers: Convert users of lockless_dereference() to READ_ONCE()") ... for easier x86 PTI code testing and back-porting. ] READ_ONCE() now has an implicit smp_read_barrier_depends() call, so it can be used instead of lockless_dereference() without any change in semantics. Signed-off-by: Will Deacon <will.deacon@xxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Link: http://lkml.kernel.org/r/1508840570-22169-4-git-send-email-will.deacon@xxxxxxx Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/x86/events/core.c | 2 +- arch/x86/include/asm/mmu_context.h | 4 ++-- arch/x86/kernel/ldt.c | 2 +- drivers/md/dm-mpath.c | 20 ++++++++++---------- fs/dcache.c | 4 ++-- fs/overlayfs/ovl_entry.h | 2 +- fs/overlayfs/readdir.c | 2 +- include/linux/rculist.h | 4 ++-- include/linux/rcupdate.h | 4 ++-- kernel/events/core.c | 4 ++-- kernel/seccomp.c | 2 +- kernel/task_work.c | 2 +- mm/slab.h | 2 +- 13 files changed, 27 insertions(+), 27 deletions(-) --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2371,7 +2371,7 @@ static unsigned long get_segment_base(un struct ldt_struct *ldt; /* IRQs are off, so this synchronizes with smp_store_release */ - ldt = lockless_dereference(current->active_mm->context.ldt); + ldt = READ_ONCE(current->active_mm->context.ldt); if (!ldt || idx >= ldt->nr_entries) return 0; --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -73,8 +73,8 @@ static inline void load_mm_ldt(struct mm #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - /* lockless_dereference synchronizes with smp_store_release */ - ldt = lockless_dereference(mm->context.ldt); + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); /* * Any change to mm->context.ldt is followed by an IPI to all --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -103,7 +103,7 @@ static void finalize_ldt_struct(struct l static void install_ldt(struct mm_struct *current_mm, struct ldt_struct *ldt) { - /* Synchronizes with lockless_dereference in load_mm_ldt. */ + /* Synchronizes with READ_ONCE in load_mm_ldt. */ smp_store_release(¤t_mm->context.ldt, ldt); /* Activate the LDT for all CPUs using current_mm. */ --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -366,7 +366,7 @@ static struct pgpath *choose_path_in_pg( pgpath = path_to_pgpath(path); - if (unlikely(lockless_dereference(m->current_pg) != pg)) { + if (unlikely(READ_ONCE(m->current_pg) != pg)) { /* Only update current_pgpath if pg changed */ spin_lock_irqsave(&m->lock, flags); m->current_pgpath = pgpath; @@ -390,7 +390,7 @@ static struct pgpath *choose_pgpath(stru } /* Were we instructed to switch PG? */ - if (lockless_dereference(m->next_pg)) { + if (READ_ONCE(m->next_pg)) { spin_lock_irqsave(&m->lock, flags); pg = m->next_pg; if (!pg) { @@ -406,7 +406,7 @@ static struct pgpath *choose_pgpath(stru /* Don't change PG until it has no remaining paths */ check_current_pg: - pg = lockless_dereference(m->current_pg); + pg = READ_ONCE(m->current_pg); if (pg) { pgpath = choose_path_in_pg(m, pg, nr_bytes); if (!IS_ERR_OR_NULL(pgpath)) @@ -473,7 +473,7 @@ static int multipath_clone_and_map(struc struct request *clone; /* Do we need to select a new pgpath? */ - pgpath = lockless_dereference(m->current_pgpath); + pgpath = READ_ONCE(m->current_pgpath); if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags)) pgpath = choose_pgpath(m, nr_bytes); @@ -533,7 +533,7 @@ static int __multipath_map_bio(struct mu bool queue_io; /* Do we need to select a new pgpath? */ - pgpath = lockless_dereference(m->current_pgpath); + pgpath = READ_ONCE(m->current_pgpath); queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags); if (!pgpath || !queue_io) pgpath = choose_pgpath(m, nr_bytes); @@ -1802,7 +1802,7 @@ static int multipath_prepare_ioctl(struc struct pgpath *current_pgpath; int r; - current_pgpath = lockless_dereference(m->current_pgpath); + current_pgpath = READ_ONCE(m->current_pgpath); if (!current_pgpath) current_pgpath = choose_pgpath(m, 0); @@ -1824,7 +1824,7 @@ static int multipath_prepare_ioctl(struc } if (r == -ENOTCONN) { - if (!lockless_dereference(m->current_pg)) { + if (!READ_ONCE(m->current_pg)) { /* Path status changed, redo selection */ (void) choose_pgpath(m, 0); } @@ -1893,9 +1893,9 @@ static int multipath_busy(struct dm_targ return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED); /* Guess which priority_group will be used at next mapping time */ - pg = lockless_dereference(m->current_pg); - next_pg = lockless_dereference(m->next_pg); - if (unlikely(!lockless_dereference(m->current_pgpath) && next_pg)) + pg = READ_ONCE(m->current_pg); + next_pg = READ_ONCE(m->next_pg); + if (unlikely(!READ_ONCE(m->current_pgpath) && next_pg)) pg = next_pg; if (!pg) { --- a/fs/dcache.c +++ b/fs/dcache.c @@ -231,7 +231,7 @@ static inline int dentry_cmp(const struc { /* * Be careful about RCU walk racing with rename: - * use 'lockless_dereference' to fetch the name pointer. + * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The @@ -245,7 +245,7 @@ static inline int dentry_cmp(const struc * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ - const unsigned char *cs = lockless_dereference(dentry->d_name.name); + const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -77,5 +77,5 @@ static inline struct ovl_inode *OVL_I(st static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi) { - return lockless_dereference(oi->__upperdentry); + return READ_ONCE(oi->__upperdentry); } --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -757,7 +757,7 @@ static int ovl_dir_fsync(struct file *fi if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) { struct inode *inode = file_inode(file); - realfile = lockless_dereference(od->upperfile); + realfile = READ_ONCE(od->upperfile); if (!realfile) { struct path upperpath; --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -275,7 +275,7 @@ static inline void list_splice_tail_init * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ - container_of(lockless_dereference(ptr), type, member) + container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? @@ -368,7 +368,7 @@ static inline void list_splice_tail_init * example is when items are added to the list, but never deleted. */ #define list_entry_lockless(ptr, type, member) \ - container_of((typeof(ptr))lockless_dereference(ptr), type, member) + container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -346,7 +346,7 @@ static inline void rcu_preempt_sleep_che #define __rcu_dereference_check(p, c, space) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \ + typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ @@ -360,7 +360,7 @@ static inline void rcu_preempt_sleep_che #define rcu_dereference_raw(p) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(p) ________p1 = lockless_dereference(p); \ + typeof(p) ________p1 = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4233,7 +4233,7 @@ static void perf_remove_from_owner(struc * indeed free this event, otherwise we need to serialize on * owner->perf_event_mutex. */ - owner = lockless_dereference(event->owner); + owner = READ_ONCE(event->owner); if (owner) { /* * Since delayed_put_task_struct() also drops the last @@ -4330,7 +4330,7 @@ again: * Cannot change, child events are not migrated, see the * comment with perf_event_ctx_lock_nested(). */ - ctx = lockless_dereference(child->ctx); + ctx = READ_ONCE(child->ctx); /* * Since child_mutex nests inside ctx::mutex, we must jump * through hoops. We start by grabbing a reference on the ctx. --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -190,7 +190,7 @@ static u32 seccomp_run_filters(const str u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = - lockless_dereference(current->seccomp.filter); + READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (unlikely(WARN_ON(f == NULL))) --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -68,7 +68,7 @@ task_work_cancel(struct task_struct *tas * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); - while ((work = lockless_dereference(*pprev))) { + while ((work = READ_ONCE(*pprev))) { if (work->func != func) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) --- a/mm/slab.h +++ b/mm/slab.h @@ -259,7 +259,7 @@ cache_from_memcg_idx(struct kmem_cache * * memcg_caches issues a write barrier to match this (see * memcg_create_kmem_cache()). */ - cachep = lockless_dereference(arr->entries[idx]); + cachep = READ_ONCE(arr->entries[idx]); rcu_read_unlock(); return cachep; Patches currently in stable-queue which might be from will.deacon@xxxxxxx are queue-4.14/locking-barriers-add-implicit-smp_read_barrier_depends-to-read_once.patch queue-4.14/x86-entry-64-move-the-ist-stacks-into-struct-cpu_entry_area.patch queue-4.14/x86-dumpstack-add-get_stack_info-support-for-the-sysenter-stack.patch queue-4.14/x86-entry-remap-the-tss-into-the-cpu-entry-area.patch queue-4.14/x86-entry-64-paravirt-use-paravirt-safe-macro-to-access-eflags.patch queue-4.14/x86-mm-fixmap-generalize-the-gdt-fixmap-mechanism-introduce-struct-cpu_entry_area.patch queue-4.14/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.14/locking-barriers-convert-users-of-lockless_dereference-to-read_once.patch queue-4.14/x86-dumpstack-handle-stack-overflow-on-all-stacks.patch queue-4.14/x86-entry-64-return-to-userspace-from-the-trampoline-stack.patch queue-4.14/x86-paravirt-provide-a-way-to-check-for-hypervisors.patch queue-4.14/x86-entry-64-create-a-per-cpu-syscall-entry-trampoline.patch queue-4.14/x86-entry-64-use-a-per-cpu-trampoline-stack-for-idt-entries.patch queue-4.14/acpi-apei-replace-ioremap_page_range-with-fixmap.patch queue-4.14/x86-cpufeatures-make-cpu-bugs-sticky.patch queue-4.14/x86-espfix-64-stop-assuming-that-pt_regs-is-on-the-entry-stack.patch queue-4.14/x86-entry-move-sysenter_stack-to-the-beginning-of-struct-tss_struct.patch queue-4.14/x86-entry-64-allocate-and-enable-the-sysenter-stack.patch queue-4.14/x86-unwinder-orc-dont-bail-on-stack-overflow.patch queue-4.14/x86-kasan-64-teach-kasan-about-the-cpu_entry_area.patch queue-4.14/x86-entry-64-remove-the-sysenter-stack-canary.patch queue-4.14/x86-mm-kasan-don-t-use-vmemmap_populate-to-initialize-shadow.patch queue-4.14/x86-entry-gdt-put-per-cpu-gdt-remaps-in-ascending-order.patch queue-4.14/x86-entry-fix-assumptions-that-the-hw-tss-is-at-the-beginning-of-cpu_tss.patch queue-4.14/x86-entry-64-make-cpu_entry_area.tss-read-only.patch queue-4.14/x86-unwinder-handle-stack-overflows-more-gracefully.patch queue-4.14/x86-irq-64-print-the-offending-ip-in-the-stack-overflow-warning.patch queue-4.14/x86-entry-clean-up-the-sysenter_stack-code.patch queue-4.14/x86-entry-64-separate-cpu_current_top_of_stack-from-tss.sp0.patch queue-4.14/x86-irq-remove-an-old-outdated-comment-about-context-tracking-races.patch