diff options
61 files changed, 915 insertions, 342 deletions
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst index c9c957c85bac..93d899d53258 100644 --- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst @@ -277,7 +277,7 @@ the following access functions: Again, only one request in a given batch need actually carry out a grace-period operation, which means there must be an efficient way to -identify which of many concurrent reqeusts will initiate the grace +identify which of many concurrent requests will initiate the grace period, and that there be an efficient way for the remaining requests to wait for that grace period to complete. However, that is the topic of the next section. @@ -405,7 +405,7 @@ Use of Workqueues In earlier implementations, the task requesting the expedited grace period also drove it to completion. This straightforward approach had the disadvantage of needing to account for POSIX signals sent to user -tasks, so more recent implemementations use the Linux kernel's +tasks, so more recent implementations use the Linux kernel's workqueues (see Documentation/core-api/workqueue.rst). The requesting task still does counter snapshotting and funnel-lock @@ -465,7 +465,7 @@ corresponding disadvantage that workqueues cannot be used until they are initialized, which does not happen until some time after the scheduler spawns the first task. Given that there are parts of the kernel that really do want to execute grace periods during this mid-boot “dead -zone”, expedited grace periods must do something else during thie time. +zone”, expedited grace periods must do something else during this time. What they do is to fall back to the old practice of requiring that the requesting task drive the expedited grace period, as was the case before diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst index 7fdf151a8680..5750f125361b 100644 --- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst +++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst @@ -168,7 +168,7 @@ an ``atomic_add_return()`` of zero) to detect idle CPUs. +-----------------------------------------------------------------------+ The approach must be extended to handle one final case, that of waking a -task blocked in ``synchronize_rcu()``. This task might be affinitied to +task blocked in ``synchronize_rcu()``. This task might be affined to a CPU that is not yet aware that the grace period has ended, and thus might not yet be subject to the grace period's memory ordering. Therefore, there is an ``smp_mb()`` after the return from diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt index 588d97366a46..db8f16b392aa 100644 --- a/Documentation/RCU/RTFP.txt +++ b/Documentation/RCU/RTFP.txt @@ -201,7 +201,7 @@ work looked at debugging uses of RCU [Seyster:2011:RFA:2075416.2075425]. In 2012, Josh Triplett received his Ph.D. with his dissertation covering RCU-protected resizable hash tables and the relationship between memory barriers and read-side traversal order: If the updater -is making changes in the opposite direction from the read-side traveral +is making changes in the opposite direction from the read-side traversal order, the updater need only execute a memory-barrier instruction, but if in the same direction, the updater needs to wait for a grace period between the individual updates [JoshTriplettPhD]. Also in 2012, @@ -1245,7 +1245,7 @@ Oregon Health and Sciences University" [Viewed September 5, 2005]" ,annotation={ First posting showing how RCU can be safely adapted for - preemptable RCU read side critical sections. + preemptible RCU read side critical sections. } } @@ -1888,7 +1888,7 @@ Revised: \url{https://lore.kernel.org/r/20070910183004.GA3299@linux.vnet.ibm.com} [Viewed October 25, 2007]" ,annotation={ - Final patch for preemptable RCU to -rt. (Later patches were + Final patch for preemptible RCU to -rt. (Later patches were to mainline, eventually incorporated.) } } @@ -2275,7 +2275,7 @@ lot of {Linux} into your technology!!!" \url{https://lore.kernel.org/r/20090724001429.GA17374@linux.vnet.ibm.com} [Viewed August 15, 2009]" ,annotation={ - First posting of simple and fast preemptable RCU. + First posting of simple and fast preemptible RCU. } } @@ -2639,7 +2639,7 @@ lot of {Linux} into your technology!!!" RCU-protected hash tables, barriers vs. read-side traversal order. . If the updater is making changes in the opposite direction from - the read-side traveral order, the updater need only execute a + the read-side traversal order, the updater need only execute a memory-barrier instruction, but if in the same direction, the updater needs to wait for a grace period between the individual updates. diff --git a/Documentation/RCU/UP.rst b/Documentation/RCU/UP.rst index 8b20fd45f255..4060d7a2f62a 100644 --- a/Documentation/RCU/UP.rst +++ b/Documentation/RCU/UP.rst @@ -107,7 +107,7 @@ UP systems, including PREEMPT SMP builds running on UP systems. Quick Quiz #3: Why can't synchronize_rcu() return immediately on UP systems running - preemptable RCU? + preemptible RCU? .. _answer_quick_quiz_up: @@ -143,7 +143,7 @@ Answer to Quick Quiz #2: Answer to Quick Quiz #3: Why can't synchronize_rcu() return immediately on UP systems - running preemptable RCU? + running preemptible RCU? Because some other task might have been preempted in the middle of an RCU read-side critical section. If synchronize_rcu() diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst index cc361fb01ed4..bd3c58c44bef 100644 --- a/Documentation/RCU/checklist.rst +++ b/Documentation/RCU/checklist.rst @@ -70,7 +70,7 @@ over a rather long period of time, but improvements are always welcome! can serve as rcu_read_lock_sched(), but is less readable and prevents lockdep from detecting locking issues. - Please not that you *cannot* rely on code known to be built + Please note that you *cannot* rely on code known to be built only in non-preemptible kernels. Such code can and will break, especially in kernels built with CONFIG_PREEMPT_COUNT=y. diff --git a/Documentation/RCU/lockdep.rst b/Documentation/RCU/lockdep.rst index 2749f43ec1b0..69e73a39bd11 100644 --- a/Documentation/RCU/lockdep.rst +++ b/Documentation/RCU/lockdep.rst @@ -65,7 +65,7 @@ checking of rcu_dereference() primitives: rcu_access_pointer(p): Return the value of the pointer and omit all barriers, but retain the compiler constraints that prevent duplicating - or coalescsing. This is useful when testing the + or coalescing. This is useful when testing the value of the pointer itself, for example, against NULL. The rcu_dereference_check() check expression can be any boolean diff --git a/Documentation/RCU/torture.rst b/Documentation/RCU/torture.rst index 0316ba0c6922..b3b6dfa85248 100644 --- a/Documentation/RCU/torture.rst +++ b/Documentation/RCU/torture.rst @@ -216,7 +216,7 @@ Kernel boot arguments can also be supplied, for example, to control rcutorture's module parameters. For example, to test a change to RCU's CPU stall-warning code, use "--bootargs 'rcutorture.stall_cpu=30'". This will of course result in the scripting reporting a failure, namely -the resuling RCU CPU stall warning. As noted above, reducing memory may +the resulting RCU CPU stall warning. As noted above, reducing memory may require disabling rcutorture's callback-flooding tests:: kvm.sh --cpus 448 --configs '56*TREE04' --memory 128M \ @@ -370,5 +370,5 @@ You can also re-run a previous remote run in a manner similar to kvm.sh: tools/testing/selftests/rcutorture/res/2022.11.03-11.26.28-remote \ --duration 24h -In this case, most of the kvm-again.sh parmeters may be supplied following +In this case, most of the kvm-again.sh parameters may be supplied following the pathname of the old run-results directory. diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst index 2c5563a91998..8eddef28d3a1 100644 --- a/Documentation/RCU/whatisRCU.rst +++ b/Documentation/RCU/whatisRCU.rst @@ -597,10 +597,10 @@ to avoid having to write your own callback:: If the occasional sleep is permitted, the single-argument form may be used, omitting the rcu_head structure from struct foo. - kfree_rcu(old_fp); + kfree_rcu_mightsleep(old_fp); -This variant of kfree_rcu() almost never blocks, but might do so by -invoking synchronize_rcu() in response to memory-allocation failure. +This variant almost never blocks, but might do so by invoking +synchronize_rcu() in response to memory-allocation failure. Again, see checklist.rst for additional rules governing the use of RCU. diff --git a/MAINTAINERS b/MAINTAINERS index 456285afd716..d172ca02a1d5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17636,11 +17636,13 @@ READ-COPY UPDATE (RCU) M: "Paul E. McKenney" <paulmck@kernel.org> M: Frederic Weisbecker <frederic@kernel.org> (kernel/rcu/tree_nocb.h) M: Neeraj Upadhyay <quic_neeraju@quicinc.com> (kernel/rcu/tasks.h) +M: Joel Fernandes <joel@joelfernandes.org> M: Josh Triplett <josh@joshtriplett.org> +M: Boqun Feng <boqun.feng@gmail.com> R: Steven Rostedt <rostedt@goodmis.org> R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> R: Lai Jiangshan <jiangshanlai@gmail.com> -R: Joel Fernandes <joel@joelfernandes.org> +R: Zqiang <qiang1.zhang@intel.com> L: rcu@vger.kernel.org S: Supported W: http://www.rdrop.com/users/paulmck/RCU/ diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index ca6eadeb7d1a..f531da6b362e 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -29,7 +29,6 @@ menuconfig KVM select KVM_MMIO select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_XFER_TO_GUEST_WORK - select SRCU select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index 29e51649203b..a8cdba75f98d 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -26,7 +26,6 @@ config KVM select HAVE_KVM_VCPU_ASYNC_IOCTL select KVM_MMIO select MMU_NOTIFIER - select SRCU select INTERVAL_TREE select KVM_GENERIC_HARDWARE_ENABLING help diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index a9f57dad6d91..902611954200 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -22,7 +22,6 @@ config KVM select PREEMPT_NOTIFIERS select HAVE_KVM_EVENTFD select HAVE_KVM_VCPU_ASYNC_IOCTL - select SRCU select KVM_VFIO select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index d5a658a047a7..5682d8c017b3 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -28,7 +28,6 @@ config KVM select KVM_XFER_TO_GUEST_WORK select HAVE_KVM_VCPU_ASYNC_IOCTL select HAVE_KVM_EVENTFD - select SRCU help Support hosting virtualized guest machines. diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 33f4ff909476..45fdf2a9b2e3 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -31,7 +31,6 @@ config KVM select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_INVALID_WAKEUPS select HAVE_KVM_NO_POLL - select SRCU select KVM_VFIO select INTERVAL_TREE select MMU_NOTIFIER diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a825bf031f49..947e24714c28 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -283,7 +283,6 @@ config X86 select RTC_LIB select RTC_MC146818_LIB select SPARSE_IRQ - select SRCU select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT @@ -1938,7 +1937,6 @@ config X86_SGX depends on X86_64 && CPU_SUP_INTEL && X86_X2APIC depends on CRYPTO=y depends on CRYPTO_SHA256=y - select SRCU select MMU_NOTIFIER select NUMA_KEEP_MEMINFO if NUMA select XARRAY_MULTI diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 8e578311ca9d..89ca7f4c1464 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -46,7 +46,6 @@ config KVM select KVM_XFER_TO_GUEST_WORK select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO - select SRCU select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM select KVM_GENERIC_HARDWARE_ENABLING diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 182c6122f815..c1815b9dae68 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -487,7 +487,8 @@ static const struct attribute_group *cpu_root_attr_groups[] = { bool cpu_is_hotpluggable(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); - return dev && container_of(dev, struct cpu, dev)->hotpluggable; + return dev && container_of(dev, struct cpu, dev)->hotpluggable + && tick_nohz_cpu_hotpluggable(cpu); } EXPORT_SYMBOL_GPL(cpu_is_hotpluggable); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 60757ac31701..f49f2a5282e1 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1615,7 +1615,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) drbd_send_sync_param(peer_device); } - kvfree_rcu(old_disk_conf); + kvfree_rcu_mightsleep(old_disk_conf); kfree(old_plan); mod_timer(&device->request_timer, jiffies + HZ); goto success; @@ -2446,7 +2446,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) mutex_unlock(&connection->resource->conf_update); mutex_unlock(&connection->data.mutex); - kvfree_rcu(old_net_conf); + kvfree_rcu_mightsleep(old_net_conf); if (connection->cstate >= C_WF_REPORT_PARAMS) { struct drbd_peer_device *peer_device; @@ -2860,7 +2860,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) new_disk_conf->disk_size = (sector_t)rs.resize_size; rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&device->resource->conf_update); - kvfree_rcu(old_disk_conf); + kvfree_rcu_mightsleep(old_disk_conf); new_disk_conf = NULL; } diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 757f4692b5bd..e197b2a465d2 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -3759,7 +3759,7 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in drbd_info(connection, "peer data-integrity-alg: %s\n", integrity_alg[0] ? integrity_alg : "(none)"); - kvfree_rcu(old_net_conf); + kvfree_rcu_mightsleep(old_net_conf); return 0; disconnect_rcu_unlock: @@ -4127,7 +4127,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&connection->resource->conf_update); - kvfree_rcu(old_disk_conf); + kvfree_rcu_mightsleep(old_disk_conf); drbd_info(device, "Peer sets u_size to %lu sectors (old: %lu)\n", (unsigned long)p_usize, (unsigned long)my_usize); diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 75d13ea0024f..2aeea295fa28 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -2071,7 +2071,7 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused) conn_free_crypto(connection); mutex_unlock(&connection->resource->conf_update); - kvfree_rcu(old_conf); + kvfree_rcu_mightsleep(old_conf); } if (ns_max.susp_fen) { diff --git a/drivers/misc/vmw_vmci/vmci_context.c b/drivers/misc/vmw_vmci/vmci_context.c index 172696abce31..f22b44827e92 100644 --- a/drivers/misc/vmw_vmci/vmci_context.c +++ b/drivers/misc/vmw_vmci/vmci_context.c @@ -687,7 +687,7 @@ int vmci_ctx_remove_notification(u32 context_id, u32 remote_cid) spin_unlock(&context->lock); if (notifier) - kvfree_rcu(notifier); + kvfree_rcu_mightsleep(notifier); vmci_ctx_put(context); diff --git a/drivers/misc/vmw_vmci/vmci_event.c b/drivers/misc/vmw_vmci/vmci_event.c index 2100297c94ad..5d7ac07623c2 100644 --- a/drivers/misc/vmw_vmci/vmci_event.c +++ b/drivers/misc/vmw_vmci/vmci_event.c @@ -209,7 +209,7 @@ int vmci_event_unsubscribe(u32 sub_id) if (!s) return VMCI_ERROR_NOT_FOUND; - kvfree_rcu(s); + kvfree_rcu_mightsleep(s); return VMCI_SUCCESS; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c index ca834bbcb44f..8afcec0c5d3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c @@ -242,7 +242,7 @@ mlx5e_int_port_remove(struct mlx5e_tc_int_port_priv *priv, mlx5_del_flow_rules(int_port->rx_rule); mapping_remove(ctx, int_port->mapping); mlx5e_int_port_metadata_free(priv, int_port->match_metadata); - kfree_rcu(int_port); + kfree_rcu_mightsleep(int_port); priv->num_ports--; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 33b3620ea45c..51f1cd8364c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -670,7 +670,7 @@ static int mlx5e_macsec_del_txsa(struct macsec_context *ctx) mlx5e_macsec_cleanup_sa(macsec, tx_sa, true); mlx5_destroy_encryption_key(macsec->mdev, tx_sa->enc_key_id); - kfree_rcu(tx_sa); + kfree_rcu_mightsleep(tx_sa); macsec_device->tx_sa[assoc_num] = NULL; out: @@ -849,7 +849,7 @@ static void macsec_del_rxsc_ctx(struct mlx5e_macsec *macsec, struct mlx5e_macsec xa_erase(&macsec->sc_xarray, rx_sc->sc_xarray_element->fs_id); metadata_dst_free(rx_sc->md_dst); kfree(rx_sc->sc_xarray_element); - kfree_rcu(rx_sc); + kfree_rcu_mightsleep(rx_sc); } static int mlx5e_macsec_del_rxsc(struct macsec_context *ctx) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f43e526112ae..76d1ef0efbf4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2500,7 +2500,7 @@ static void ext4_apply_quota_options(struct fs_context *fc, qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, lockdep_is_held(&sb->s_umount)); if (qname) - kfree_rcu(qname); + kfree_rcu_mightsleep(qname); } } diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1023f349af71..b32256e9e944 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -134,7 +134,8 @@ struct held_lock { unsigned int read:2; /* see lock_acquire() comment */ unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; - unsigned int references:12; /* 32 bits */ + unsigned int sync:1; + unsigned int references:11; /* 32 bits */ unsigned int pin_count; }; @@ -268,6 +269,10 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, unsigned long ip); +extern void lock_sync(struct lockdep_map *lock, unsigned int subclass, + int read, int check, struct lockdep_map *nest_lock, + unsigned long ip); + /* lock_is_held_type() returns */ #define LOCK_STATE_UNKNOWN -1 #define LOCK_STATE_NOT_HELD 0 @@ -554,6 +559,7 @@ do { \ #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) +#define lock_ |