summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-03-30 16:17:15 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-03-30 16:17:15 -0700
commit4b9fd8a829a1eec7442e38afff21d610604de56a (patch)
tree32757737b7eecbe8c5be7606d8dcec883d39f1e6
parenta776c270a0b2fad6715cb714187e4290cadb9237 (diff)
parentf1e67e355c2aafeddf1eac31335709236996d2fe (diff)
downloadlinux-4b9fd8a829a1eec7442e38afff21d610604de56a.tar.bz2
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar: "The main changes in this cycle were: - Continued user-access cleanups in the futex code. - percpu-rwsem rewrite that uses its own waitqueue and atomic_t instead of an embedded rwsem. This addresses a couple of weaknesses, but the primary motivation was complications on the -rt kernel. - Introduce raw lock nesting detection on lockdep (CONFIG_PROVE_RAW_LOCK_NESTING=y), document the raw_lock vs. normal lock differences. This too originates from -rt. - Reuse lockdep zapped chain_hlocks entries, to conserve RAM footprint on distro-ish kernels running into the "BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!" depletion of the lockdep chain-entries pool. - Misc cleanups, smaller fixes and enhancements - see the changelog for details" * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits) fs/buffer: Make BH_Uptodate_Lock bit_spin_lock a regular spinlock_t thermal/x86_pkg_temp: Make pkg_temp_lock a raw_spinlock_t Documentation/locking/locktypes: Minor copy editor fixes Documentation/locking/locktypes: Further clarifications and wordsmithing m68knommu: Remove mm.h include from uaccess_no.h x86: get rid of user_atomic_cmpxchg_inatomic() generic arch_futex_atomic_op_inuser() doesn't need access_ok() x86: don't reload after cmpxchg in unsafe_atomic_op2() loop x86: convert arch_futex_atomic_op_inuser() to user_access_begin/user_access_end() objtool: whitelist __sanitizer_cov_trace_switch() [parisc, s390, sparc64] no need for access_ok() in futex handling sh: no need of access_ok() in arch_futex_atomic_op_inuser() futex: arch_futex_atomic_op_inuser() calling conventions change completion: Use lockdep_assert_RT_in_threaded_ctx() in complete_all() lockdep: Add posixtimer context tracing bits lockdep: Annotate irq_work lockdep: Add hrtimer context tracing bits lockdep: Introduce wait-type checks completion: Use simple wait queues sched/swait: Prepare usage in completions ...
-rw-r--r--Documentation/locking/index.rst1
-rw-r--r--Documentation/locking/locktypes.rst347
-rw-r--r--arch/alpha/include/asm/futex.h5
-rw-r--r--arch/arc/include/asm/futex.h5
-rw-r--r--arch/arm/include/asm/futex.h5
-rw-r--r--arch/arm64/include/asm/futex.h5
-rw-r--r--arch/csky/include/asm/uaccess.h1
-rw-r--r--arch/hexagon/include/asm/futex.h5
-rw-r--r--arch/hexagon/include/asm/uaccess.h1
-rw-r--r--arch/ia64/include/asm/futex.h5
-rw-r--r--arch/ia64/include/asm/uaccess.h1
-rw-r--r--arch/ia64/kernel/process.c1
-rw-r--r--arch/ia64/mm/ioremap.c1
-rw-r--r--arch/m68k/include/asm/uaccess_no.h1
-rw-r--r--arch/microblaze/include/asm/futex.h5
-rw-r--r--arch/microblaze/include/asm/uaccess.h1
-rw-r--r--arch/mips/include/asm/futex.h5
-rw-r--r--arch/nds32/include/asm/futex.h6
-rw-r--r--arch/nds32/include/asm/uaccess.h1
-rw-r--r--arch/openrisc/include/asm/futex.h5
-rw-r--r--arch/parisc/include/asm/futex.h2
-rw-r--r--arch/powerpc/include/asm/futex.h5
-rw-r--r--arch/powerpc/platforms/ps3/device-init.c18
-rw-r--r--arch/riscv/include/asm/futex.h5
-rw-r--r--arch/s390/include/asm/futex.h2
-rw-r--r--arch/sh/include/asm/futex.h4
-rw-r--r--arch/sparc/include/asm/futex_64.h4
-rw-r--r--arch/x86/include/asm/futex.h99
-rw-r--r--arch/x86/include/asm/uaccess.h93
-rw-r--r--arch/xtensa/include/asm/futex.h5
-rw-r--r--drivers/net/wireless/intersil/orinoco/orinoco_usb.c21
-rw-r--r--drivers/pci/switch/switchtec.c22
-rw-r--r--drivers/platform/x86/dell-smo8800.c1
-rw-r--r--drivers/platform/x86/wmi.c1
-rw-r--r--drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c1
-rw-r--r--drivers/thermal/intel/x86_pkg_temp_thermal.c24
-rw-r--r--drivers/usb/gadget/function/f_fs.c2
-rw-r--r--drivers/usb/gadget/legacy/inode.c4
-rw-r--r--fs/buffer.c19
-rw-r--r--fs/ext4/page-io.c8
-rw-r--r--fs/ntfs/aops.c9
-rw-r--r--include/acpi/acpi_bus.h2
-rw-r--r--include/asm-generic/bitops.h5
-rw-r--r--include/asm-generic/futex.h2
-rw-r--r--include/linux/buffer_head.h6
-rw-r--r--include/linux/completion.h8
-rw-r--r--include/linux/irq_work.h2
-rw-r--r--include/linux/irqflags.h48
-rw-r--r--include/linux/lockdep.h86
-rw-r--r--include/linux/mutex.h7
-rw-r--r--include/linux/percpu-rwsem.h83
-rw-r--r--include/linux/rcuwait.h12
-rw-r--r--include/linux/rwlock_types.h6
-rw-r--r--include/linux/rwsem.h12
-rw-r--r--include/linux/sched.h2
-rw-r--r--include/linux/spinlock.h35
-rw-r--r--include/linux/spinlock_types.h24
-rw-r--r--include/linux/wait.h1
-rw-r--r--kernel/cpu.c4
-rw-r--r--kernel/exit.c1
-rw-r--r--kernel/futex.c107
-rw-r--r--kernel/irq/handle.c7
-rw-r--r--kernel/irq_work.c2
-rw-r--r--kernel/locking/lockdep.c674
-rw-r--r--kernel/locking/lockdep_internals.h14
-rw-r--r--kernel/locking/lockdep_proc.c31
-rw-r--r--kernel/locking/mutex-debug.c2
-rw-r--r--kernel/locking/percpu-rwsem.c194
-rw-r--r--kernel/locking/rwsem.c9
-rw-r--r--kernel/locking/rwsem.h10
-rw-r--r--kernel/locking/spinlock_debug.c6
-rw-r--r--kernel/rcu/tree.c1
-rw-r--r--kernel/rcu/update.c24
-rw-r--r--kernel/sched/completion.c36
-rw-r--r--kernel/sched/sched.h3
-rw-r--r--kernel/sched/swait.c15
-rw-r--r--kernel/time/hrtimer.c6
-rw-r--r--kernel/time/jiffies.c7
-rw-r--r--kernel/time/posix-cpu-timers.c6
-rw-r--r--kernel/time/tick-common.c10
-rw-r--r--kernel/time/tick-sched.c20
-rw-r--r--kernel/time/timekeeping.c6
-rw-r--r--kernel/time/timekeeping.h3
-rw-r--r--lib/Kconfig.debug17
-rw-r--r--tools/objtool/check.c1
85 files changed, 1611 insertions, 702 deletions
diff --git a/Documentation/locking/index.rst b/Documentation/locking/index.rst
index 626a463f7e42..5d6800a723dc 100644
--- a/Documentation/locking/index.rst
+++ b/Documentation/locking/index.rst
@@ -7,6 +7,7 @@ locking
.. toctree::
:maxdepth: 1
+ locktypes
lockdep-design
lockstat
locktorture
diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst
new file mode 100644
index 000000000000..09f45ce38d26
--- /dev/null
+++ b/Documentation/locking/locktypes.rst
@@ -0,0 +1,347 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. _kernel_hacking_locktypes:
+
+==========================
+Lock types and their rules
+==========================
+
+Introduction
+============
+
+The kernel provides a variety of locking primitives which can be divided
+into two categories:
+
+ - Sleeping locks
+ - Spinning locks
+
+This document conceptually describes these lock types and provides rules
+for their nesting, including the rules for use under PREEMPT_RT.
+
+
+Lock categories
+===============
+
+Sleeping locks
+--------------
+
+Sleeping locks can only be acquired in preemptible task context.
+
+Although implementations allow try_lock() from other contexts, it is
+necessary to carefully evaluate the safety of unlock() as well as of
+try_lock(). Furthermore, it is also necessary to evaluate the debugging
+versions of these primitives. In short, don't acquire sleeping locks from
+other contexts unless there is no other option.
+
+Sleeping lock types:
+
+ - mutex
+ - rt_mutex
+ - semaphore
+ - rw_semaphore
+ - ww_mutex
+ - percpu_rw_semaphore
+
+On PREEMPT_RT kernels, these lock types are converted to sleeping locks:
+
+ - spinlock_t
+ - rwlock_t
+
+Spinning locks
+--------------
+
+ - raw_spinlock_t
+ - bit spinlocks
+
+On non-PREEMPT_RT kernels, these lock types are also spinning locks:
+
+ - spinlock_t
+ - rwlock_t
+
+Spinning locks implicitly disable preemption and the lock / unlock functions
+can have suffixes which apply further protections:
+
+ =================== ====================================================
+ _bh() Disable / enable bottom halves (soft interrupts)
+ _irq() Disable / enable interrupts
+ _irqsave/restore() Save and disable / restore interrupt disabled state
+ =================== ====================================================
+
+Owner semantics
+===============
+
+The aforementioned lock types except semaphores have strict owner
+semantics:
+
+ The context (task) that acquired the lock must release it.
+
+rw_semaphores have a special interface which allows non-owner release for
+readers.
+
+
+rtmutex
+=======
+
+RT-mutexes are mutexes with support for priority inheritance (PI).
+
+PI has limitations on non-PREEMPT_RT kernels due to preemption and
+interrupt disabled sections.
+
+PI clearly cannot preempt preemption-disabled or interrupt-disabled
+regions of code, even on PREEMPT_RT kernels. Instead, PREEMPT_RT kernels
+execute most such regions of code in preemptible task context, especially
+interrupt handlers and soft interrupts. This conversion allows spinlock_t
+and rwlock_t to be implemented via RT-mutexes.
+
+
+semaphore
+=========
+
+semaphore is a counting semaphore implementation.
+
+Semaphores are often used for both serialization and waiting, but new use
+cases should instead use separate serialization and wait mechanisms, such
+as mutexes and completions.
+
+semaphores and PREEMPT_RT
+----------------------------
+
+PREEMPT_RT does not change the semaphore implementation because counting
+semaphores have no concept of owners, thus preventing PREEMPT_RT from
+providing priority inheritance for semaphores. After all, an unknown
+owner cannot be boosted. As a consequence, blocking on semaphores can
+result in priority inversion.
+
+
+rw_semaphore
+============
+
+rw_semaphore is a multiple readers and single writer lock mechanism.
+
+On non-PREEMPT_RT kernels the implementation is fair, thus preventing
+writer starvation.
+
+rw_semaphore complies by default with the strict owner semantics, but there
+exist special-purpose interfaces that allow non-owner release for readers.
+These interfaces work independent of the kernel configuration.
+
+rw_semaphore and PREEMPT_RT
+---------------------------
+
+PREEMPT_RT kernels map rw_semaphore to a separate rt_mutex-based
+implementation, thus changing the fairness:
+
+ Because an rw_semaphore writer cannot grant its priority to multiple
+ readers, a preempted low-priority reader will continue holding its lock,
+ thus starving even high-priority writers. In contrast, because readers
+ can grant their priority to a writer, a preempted low-priority writer will
+ have its priority boosted until it releases the lock, thus preventing that
+ writer from starving readers.
+
+
+raw_spinlock_t and spinlock_t
+=============================
+
+raw_spinlock_t
+--------------
+
+raw_spinlock_t is a strict spinning lock implementation regardless of the
+kernel configuration including PREEMPT_RT enabled kernels.
+
+raw_spinlock_t is a strict spinning lock implementation in all kernels,
+including PREEMPT_RT kernels. Use raw_spinlock_t only in real critical
+core code, low-level interrupt handling and places where disabling
+preemption or interrupts is required, for example, to safely access
+hardware state. raw_spinlock_t can sometimes also be used when the
+critical section is tiny, thus avoiding RT-mutex overhead.
+
+spinlock_t
+----------
+
+The semantics of spinlock_t change with the state of PREEMPT_RT.
+
+On a non-PREEMPT_RT kernel spinlock_t is mapped to raw_spinlock_t and has
+exactly the same semantics.
+
+spinlock_t and PREEMPT_RT
+-------------------------
+
+On a PREEMPT_RT kernel spinlock_t is mapped to a separate implementation
+based on rt_mutex which changes the semantics:
+
+ - Preemption is not disabled.
+
+ - The hard interrupt related suffixes for spin_lock / spin_unlock
+ operations (_irq, _irqsave / _irqrestore) do not affect the CPU's
+ interrupt disabled state.
+
+ - The soft interrupt related suffix (_bh()) still disables softirq
+ handlers.
+
+ Non-PREEMPT_RT kernels disable preemption to get this effect.
+
+ PREEMPT_RT kernels use a per-CPU lock for serialization which keeps
+ preemption disabled. The lock disables softirq handlers and also
+ prevents reentrancy due to task preemption.
+
+PREEMPT_RT kernels preserve all other spinlock_t semantics:
+
+ - Tasks holding a spinlock_t do not migrate. Non-PREEMPT_RT kernels
+ avoid migration by disabling preemption. PREEMPT_RT kernels instead
+ disable migration, which ensures that pointers to per-CPU variables
+ remain valid even if the task is preempted.
+
+ - Task state is preserved across spinlock acquisition, ensuring that the
+ task-state rules apply to all kernel configurations. Non-PREEMPT_RT
+ kernels leave task state untouched. However, PREEMPT_RT must change
+ task state if the task blocks during acquisition. Therefore, it saves
+ the current task state before blocking and the corresponding lock wakeup
+ restores it, as shown below::
+
+ task->state = TASK_INTERRUPTIBLE
+ lock()
+ block()
+ task->saved_state = task->state
+ task->state = TASK_UNINTERRUPTIBLE
+ schedule()
+ lock wakeup
+ task->state = task->saved_state
+
+ Other types of wakeups would normally unconditionally set the task state
+ to RUNNING, but that does not work here because the task must remain
+ blocked until the lock becomes available. Therefore, when a non-lock
+ wakeup attempts to awaken a task blocked waiting for a spinlock, it
+ instead sets the saved state to RUNNING. Then, when the lock
+ acquisition completes, the lock wakeup sets the task state to the saved
+ state, in this case setting it to RUNNING::
+
+ task->state = TASK_INTERRUPTIBLE
+ lock()
+ block()
+ task->saved_state = task->state
+ task->state = TASK_UNINTERRUPTIBLE
+ schedule()
+ non lock wakeup
+ task->saved_state = TASK_RUNNING
+
+ lock wakeup
+ task->state = task->saved_state
+
+ This ensures that the real wakeup cannot be lost.
+
+
+rwlock_t
+========
+
+rwlock_t is a multiple readers and single writer lock mechanism.
+
+Non-PREEMPT_RT kernels implement rwlock_t as a spinning lock and the
+suffix rules of spinlock_t apply accordingly. The implementation is fair,
+thus preventing writer starvation.
+
+rwlock_t and PREEMPT_RT
+-----------------------
+
+PREEMPT_RT kernels map rwlock_t to a separate rt_mutex-based
+implementation, thus changing semantics:
+
+ - All the spinlock_t changes also apply to rwlock_t.
+
+ - Because an rwlock_t writer cannot grant its priority to multiple
+ readers, a preempted low-priority reader will continue holding its lock,
+ thus starving even high-priority writers. In contrast, because readers
+ can grant their priority to a writer, a preempted low-priority writer
+ will have its priority boosted until it releases the lock, thus
+ preventing that writer from starving readers.
+
+
+PREEMPT_RT caveats
+==================
+
+spinlock_t and rwlock_t
+-----------------------
+
+These changes in spinlock_t and rwlock_t semantics on PREEMPT_RT kernels
+have a few implications. For example, on a non-PREEMPT_RT kernel the
+following code sequence works as expected::
+
+ local_irq_disable();
+ spin_lock(&lock);
+
+and is fully equivalent to::
+
+ spin_lock_irq(&lock);
+
+Same applies to rwlock_t and the _irqsave() suffix variants.
+
+On PREEMPT_RT kernel this code sequence breaks because RT-mutex requires a
+fully preemptible context. Instead, use spin_lock_irq() or
+spin_lock_irqsave() and their unlock counterparts. In cases where the
+interrupt disabling and locking must remain separate, PREEMPT_RT offers a
+local_lock mechanism. Acquiring the local_lock pins the task to a CPU,
+allowing things like per-CPU interrupt disabled locks to be acquired.
+However, this approach should be used only where absolutely necessary.
+
+
+raw_spinlock_t
+--------------
+
+Acquiring a raw_spinlock_t disables preemption and possibly also
+interrupts, so the critical section must avoid acquiring a regular
+spinlock_t or rwlock_t, for example, the critical section must avoid
+allocating memory. Thus, on a non-PREEMPT_RT kernel the following code
+works perfectly::
+
+ raw_spin_lock(&lock);
+ p = kmalloc(sizeof(*p), GFP_ATOMIC);
+
+But this code fails on PREEMPT_RT kernels because the memory allocator is
+fully preemptible and therefore cannot be invoked from truly atomic
+contexts. However, it is perfectly fine to invoke the memory allocator
+while holding normal non-raw spinlocks because they do not disable
+preemption on PREEMPT_RT kernels::
+
+ spin_lock(&lock);
+ p = kmalloc(sizeof(*p), GFP_ATOMIC);
+
+
+bit spinlocks
+-------------
+
+PREEMPT_RT cannot substitute bit spinlocks because a single bit is too
+small to accommodate an RT-mutex. Therefore, the semantics of bit
+spinlocks are preserved on PREEMPT_RT kernels, so that the raw_spinlock_t
+caveats also apply to bit spinlocks.
+
+Some bit spinlocks are replaced with regular spinlock_t for PREEMPT_RT
+using conditional (#ifdef'ed) code changes at the usage site. In contrast,
+usage-site changes are not needed for the spinlock_t substitution.
+Instead, conditionals in header files and the core locking implemementation
+enable the compiler to do the substitution transparently.
+
+
+Lock type nesting rules
+=======================
+
+The most basic rules are:
+
+ - Lock types of the same lock category (sleeping, spinning) can nest
+ arbitrarily as long as they respect the general lock ordering rules to
+ prevent deadlocks.
+
+ - Sleeping lock types cannot nest inside spinning lock types.
+
+ - Spinning lock types can nest inside sleeping lock types.
+
+These constraints apply both in PREEMPT_RT and otherwise.
+
+The fact that PREEMPT_RT changes the lock category of spinlock_t and
+rwlock_t from spinning to sleeping means that they cannot be acquired while
+holding a raw spinlock. This results in the following nesting ordering:
+
+ 1) Sleeping locks
+ 2) spinlock_t and rwlock_t
+ 3) raw_spinlock_t and bit spinlocks
+
+Lockdep will complain if these constraints are violated, both in
+PREEMPT_RT and otherwise.
diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h
index bfd3c01038f8..da67afd578fd 100644
--- a/arch/alpha/include/asm/futex.h
+++ b/arch/alpha/include/asm/futex.h
@@ -31,7 +31,8 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
{
int oldval = 0, ret;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -53,8 +54,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 9d0d070e6c22..607d1c16d4dd 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -75,10 +75,12 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
{
int oldval = 0, ret;
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
+
#ifndef CONFIG_ARC_HAS_LLSC
preempt_disable(); /* to guarantee atomic r-m-w of futex op */
#endif
- pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
@@ -101,7 +103,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
ret = -ENOSYS;
}
- pagefault_enable();
#ifndef CONFIG_ARC_HAS_LLSC
preempt_enable();
#endif
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 83c391b597d4..e133da303a98 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -134,10 +134,12 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret, tmp;
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
+
#ifndef CONFIG_SMP
preempt_disable();
#endif
- pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
@@ -159,7 +161,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
#ifndef CONFIG_SMP
preempt_enable();
#endif
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 6cc26a127819..97f6a63810ec 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -48,7 +48,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
int oldval = 0, ret, tmp;
u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
- pagefault_disable();
+ if (!access_ok(_uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -75,8 +76,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/csky/include/asm/uaccess.h b/arch/csky/include/asm/uaccess.h
index eaa1c3403a42..abefa125b93c 100644
--- a/arch/csky/include/asm/uaccess.h
+++ b/arch/csky/include/asm/uaccess.h
@@ -11,7 +11,6 @@
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sched.h>
-#include <linux/mm.h>
#include <linux/string.h>
#include <linux/version.h>
#include <asm/segment.h>
diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h
index 0191f7c7193e..6b9c554aee78 100644
--- a/arch/hexagon/include/asm/futex.h
+++ b/arch/hexagon/include/asm/futex.h
@@ -36,7 +36,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -62,8 +63,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index 00cb38faad0c..c1019a736ff1 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -10,7 +10,6 @@
/*
* User space memory access functions
*/
-#include <linux/mm.h>
#include <asm/sections.h>
/*
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index 2e106d462196..1db26b432d8c 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -50,7 +50,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -74,8 +75,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 89782ad3fb88..5c7e79eccaee 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -35,7 +35,6 @@
#include <linux/compiler.h>
#include <linux/page-flags.h>
-#include <linux/mm.h>
#include <asm/intrinsics.h>
#include <asm/pgtable.h>
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 968b5f33e725..743aaf528327 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -681,3 +681,4 @@ machine_power_off (void)
machine_halt();
}
+EXPORT_SYMBOL(ia64_delay_loop);
diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c
index a09cfa064536..55fd3eb753ff 100644
--- a/arch/ia64/mm/ioremap.c
+++ b/arch/ia64/mm/ioremap.c
@@ -8,6 +8,7 @@
#include <linux/module.h>
#include <linux/efi.h>
#include <linux/io.h>
+#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <asm/io.h>
#include <asm/meminit.h>
diff --git a/arch/m68k/include/asm/uaccess_no.h b/arch/m68k/include/asm/uaccess_no.h
index 6bc80c35726d..a24cfe4a0d32 100644
--- a/arch/m68k/include/asm/uaccess_no.h
+++ b/arch/m68k/include/asm/uaccess_no.h
@@ -5,7 +5,6 @@
/*
* User space memory access functions
*/
-#include <linux/mm.h>
#include <linux/string.h>
#include <asm/segment.h>
diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h
index 8c90357e5983..86131ed84c9a 100644
--- a/arch/microblaze/include/asm/futex.h
+++ b/arch/microblaze/include/asm/futex.h
@@ -34,7 +34,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -56,8 +57,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index a1f206b90753..4916d5fbea5e 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -12,7 +12,6 @@
#define _ASM_MICROBLAZE_UACCESS_H
#include <linux/kernel.h>
-#include <linux/mm.h>
#include <asm/mmu.h>
#include <asm/page.h>
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index 110220705e97..2bf8f6014579 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -89,7 +89,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -116,8 +117,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/nds32/include/asm/futex.h b/arch/nds32/include/asm/futex.h
index 5213c65c2e0b..4223f473bd36 100644
--- a/arch/nds32/include/asm/futex.h
+++ b/arch/nds32/include/asm/futex.h
@@ -66,8 +66,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret;
-
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
__futex_atomic_op("move %0, %3", ret, oldval, tmp, uaddr,
@@ -93,8 +93,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h
index 8916ad9f9f13..3a9219f53ee0 100644
--- a/arch/nds32/include/asm/uaccess.h
+++ b/arch/nds32/include/asm/uaccess.h
@@ -11,7 +11,6 @@
#include <asm/errno.h>
#include <asm/memory.h>
#include <asm/types.h>
-#include <linux/mm.h>
#define __asmeq(x, y) ".ifnc " x "," y " ; .err ; .endif\n\t"
diff --git a/arch/openrisc/include/asm/futex.h b/arch/openrisc/include/asm/futex.h
index fe894e6331ae..865e9cd0d97b 100644
--- a/arch/openrisc/include/asm/futex.h
+++ b/arch/openrisc/include/asm/futex.h
@@ -35,7 +35,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -57,8 +58,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index d2c3e4106851..c459f656c8c3 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -40,7 +40,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
u32 tmp;
_futex_spin_lock_irqsave(uaddr, &flags);
- pagefault_disable();
ret = -EFAULT;
if (unlikely(get_user(oldval, uaddr) != 0))
@@ -73,7 +72,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -EFAULT;
out_pagefault_enable:
- pagefault_enable();
_futex_spin_unlock_irqrestore(uaddr, &flags);
if (!ret)
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index bc7d9d06a6d9..f187bb5e524e 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -35,8 +35,9 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
{
int oldval = 0, ret;
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
allow_read_write_user(uaddr, uaddr, sizeof(*uaddr));
- pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
@@ -58,8 +59,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
ret = -ENOSYS;
}
- pagefault_enable();
-
*oval = oldval;
prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr));
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 2735ec90414d..e87360a0fb40 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/reboot.h>
+#include <linux/rcuwait.h>
#include <asm/firmware.h>
#include <asm/lv1call.h>
@@ -670,7 +671,8 @@ struct ps3_notification_device {
spinlock_t lock;
u64 tag;
u64 lv1_status;
- struct completion done;
+ struct rcuwait wait;
+ bool done;
};
enum ps3_notify_type {
@@ -712,7 +714,8 @@ static irqreturn_t ps3_notification_interrupt(int irq, void *data)
pr_debug("%s:%u: completed, status 0x%llx\n", __func__,
__LINE__, status);
dev->lv1_status = status;
- complete(&dev->done);
+ dev->done = true;
+ rcuwait_wake_up(&dev->wait);
}
spin_unlock(&dev->lock);
return IRQ_HANDLED;
@@ -725,12 +728,12 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
unsigned long flags;
int res;
- init_completion(&dev->done);
spin_lock_irqsave(&dev->lock, flags);
res = write ? lv1_storage_write(dev->sbd.dev_id, 0, 0, 1, 0, lpar,
&dev->tag)
: lv1_storage_read(dev->sbd.dev_id, 0, 0, 1, 0, lpar,
&dev->tag);
+ dev->done = false;
spin_unlock_irqrestore(&dev->lock, flags);
if (res) {
pr_err("%s:%u: %s failed %d\n", __func__, __LINE__, op, res);
@@ -738,14 +741,10 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
}
pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op);
- res = wait_event_interruptible(dev->done.wait,
- dev->done.done || kthread_should_stop());
+ rcuwait_wait_event(&dev->wait, dev->done || kthread_should_stop(), TASK_IDLE);
+
if (kthread_should_stop())
res = -EINTR;
- if (res) {
- pr_debug("%s:%u: interrupted %s\n", __func__, __LINE__, op);
- return res;
- }
if (dev->lv1_status) {
pr_err("%s:%u: %s not completed, status 0x%llx\n", __func__,
@@ -810,6 +809,7 @@ static int ps3_probe_thread(void *data)
}
spin_lock_init(&dev.lock);
+ rcuwait_init(&dev.wait);
res = request_irq(irq, ps3_notification_interrupt, 0,
"ps3_notification", &dev);
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index fdfaf7f3df7c..1b00badb9f87 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -46,7 +46,8 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
int oldval = 0, ret = 0;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -73,8 +74,6 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 5e97a4353147..26f9144562c9 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -29,7 +29,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
mm_segment_t old_fs;
old_fs = enable_sacf_uaccess();
- pagefault_disable();
switch (op) {
case FUTEX_OP_SET:
__futex_atomic_op("lr %2,%5\n",
@@ -54,7 +53,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
default:
ret = -ENOSYS;
}
- pagefault_enable();
disable_sacf_uaccess(old_fs);
if (!ret)
diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h
index 3190ec89df81..b39cda09fb95 100644
--- a/arch/sh/include/asm/futex.h
+++ b/arch/sh/include/asm/futex.h
@@ -34,8 +34,6 @@ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval,
u32 oldval, newval, prev;
int ret;
- pagefault_disable();
-
do {
ret = get_user(oldval, uaddr);
@@ -67,8 +65,6 @@ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval,
ret = futex_atomic_cmpxchg_inatomic(&prev, uaddr, oldval, newval);
} while (!ret && prev != oldval);
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h
index 0865ce77ec00..72de967318d7 100644
--- a/arch/sparc/include/asm/futex_64.h
+++ b/arch/sparc/include/asm/futex_64.h
@@ -38,8 +38,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
if (unlikely((((unsigned long) uaddr) & 0x3UL)))
return -EINVAL;
- pagefault_disable();
-
switch (op) {
case FUTEX_OP_SET:
__futex_cas_op("mov\t%4, %1", ret, oldval, uaddr, oparg);
@@ -60,8 +58,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 13c83fe97988..f9c00110a69a 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -12,76 +12,103 @@
#include <asm/processor.h>
#include <asm/smap.h>
-#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
- asm volatile("\t" ASM_STAC "\n" \
- "1:\t" insn "\n" \
- "2:\t" ASM_CLAC "\n" \
+#define unsafe_atomic_op1(insn, oval, uaddr, oparg, label) \
+do { \
+ int oldval = 0, ret; \
+ asm volatile("1:\t" insn "\n" \
+ "2:\n" \
"\t.section .fixup,\"ax\"\n" \
"3:\tmov\t%3, %1\n" \
"\tjmp\t2b\n" \
"\t.previous\n" \
_ASM_EXTABLE_UA(1b, 3b) \
: "=r" (oldval), "=r" (ret), "+m" (*uaddr) \
- : "i" (-EFAULT), "0" (oparg), "1" (0))
+ : "i" (-EFAULT), "0" (oparg), "1" (0)); \
+ if (ret) \
+ goto label; \
+ *oval = oldval; \
+} while(0)
-#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \
- asm volatile("\t" ASM_STAC "\n" \
- "1:\tmovl %2, %0\n" \
- "\tmovl\t%0, %3\n" \
+
+#define unsafe_atomic_op2(insn, oval, uaddr, oparg, label) \
+do { \
+ int oldval = 0, ret, tem; \
+ asm volatile("1:\tmovl %2, %0\n" \
+ "2:\tmovl\t%0, %3\n" \
"\t" insn "\n" \
- "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \
- "\tjnz\t1b\n" \
- "3:\t" ASM_CLAC "\n" \
+ "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \
+ "\tjnz\t2b\n" \
+ "4:\n" \
"\t.section .fixup,\"ax\"\n" \
- "4:\tmov\t%5, %1\n" \
- "\tjmp\t3b\n" \
+ "5:\tmov\t%5, %1\n" \
+ "\tjmp\t4b\n" \
"\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 4b) \
- _ASM_EXTABLE_UA(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 5b) \
+ _ASM_EXTABLE_UA(3b, 5b) \
: "=&a" (oldval), "=&r" (ret), \
"+m" (*uaddr), "=&r" (tem) \
- : "r" (oparg), "i" (-EFAULT), "1" (0))
+ : "r" (oparg), "i" (-EFAULT), "1" (0)); \
+ if (ret) \
+ goto label; \
+ *oval = oldval; \
+} while(0)
-static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+static __always_inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
u32 __user *uaddr)
{
- int oldval = 0, ret, tem;
-
- pagefault_disable();
+ if (!user_access_begin(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
- __futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg);
+ unsafe_atomic_op1("xchgl %0, %2", oval, uaddr, oparg, Efault);
break;
case FUTEX_OP_ADD:
- __futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval,
- uaddr, oparg);
+ unsafe_atomic_op1(LOCK_PREFIX "xaddl %0, %2", oval,
+ uaddr, oparg, Efault);
break;
case FUTEX_OP_OR:
- __futex_atomic_op2("orl %4, %3", ret, oldval, uaddr, oparg);
+ unsafe_atomic_op2("orl %4, %3", oval, uaddr, oparg, Efault);
break;
case FUTEX_OP_ANDN:
- __futex_atomic_op2("andl %4, %3", ret, oldval, uaddr, ~oparg);
+ unsafe_atomic_op2("andl %4, %3", oval, uaddr, ~oparg, Efault);
break;
case FUTEX_OP_XOR:
- __futex_atomic_op2("xorl %4, %3", ret, oldval, uaddr, oparg);
+ unsafe_atomic_op2("xorl %4, %3", oval, uaddr, oparg, Efault);
break;
default:
- ret = -ENOSYS;
+ user_access_end();
+ return -ENOSYS;
}
-
- pagefault_enable();
-
- if (!ret)
- *oval = oldval;
-
- return ret;
+ user_access_end();
+ return 0;
+Efault:
+ user_access_end();
+ return -EFAULT;
}
static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
u32 oldval, u32 newval)
{
- return user_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval);
+ int ret = 0;
+
+ if (!user_access_begin(uaddr, sizeof(u32)))
+ return -EFAULT;
+ asm volatile("\n"
+ "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
+ "2:\n"
+ "\t.section .fixup, \"ax\"\n"
+ "3:\tmov %3, %0\n"
+ "\tjmp 2b\n"
+ "\t.previous\n"
+ _ASM_EXTABLE_UA(1b, 3b)
+ : "+r" (ret), "=a" (oldval), "+m" (*uaddr)
+ : "i" (-EFAULT), "r" (newval), "1" (oldval)
+ : "memory"
+ );
+ user_access_end();
+ *uval = oldval;
+ return ret;
}
#endif
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 61d93f062a36..ea6fc643ccfe 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -584,99 +584,6 @@ extern __must_check long strnlen_user(const char __user *str, long n);
unsigned long __must_check clear_user(void __user *mem, unsigned long len);
unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
-extern void __cmpxchg_wrong_size(void)
- __compiletime_error("Bad argument size for cmpxchg");
-
-#define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size) \
-({ \
- int __ret = 0; \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __uaccess_begin_nospec(); \
- switch (size) { \
- case 1: \
- { \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "q" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- case 2: \
- { \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "r" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- case 4: \
- { \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "r" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- case 8: \
- { \
- if (!IS_ENABLED(CONFIG_X86_64)) \
- __cmpxchg_wrong_size(); \
- \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "r" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- default: \
- __cmpxchg_wrong_size(); \
- } \
- __uaccess_end(); \
- *(uval) = __old; \
- __ret; \
-})
-
-#define user_atomic_cmpxchg_inatomic(uval, ptr, old, new) \
-({ \
- access_ok((ptr), sizeof(*(ptr))) ? \
- __user_atomic_cmpxchg_inatomic((uval), (ptr), \
- (old), (new), sizeof(*(ptr))) : \
- -EFAULT; \
-})
-
/*
* movsl can be slow when source and dest are not both 8-byte aligned
*/
diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h
index 964611083224..a1a27b2ea460 100644
--- a/arch/xtensa/include/asm/futex.h
+++ b/arch/xtensa/include/asm/futex.h
@@ -72,7 +72,8 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
#if XCHAL_HAVE_S32C1I || XCHAL_HAVE_EXCLUSIVE
int oldval = 0, ret;
- pagefault_disable();
+ if (!access_ok(uaddr, sizeof(u32)))
+ return -EFAULT;
switch (op) {
case FUTEX_OP_SET:
@@ -99,8 +100,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
ret = -ENOSYS;
}
- pagefault_enable();
-
if (!ret)
*oval = oldval;
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index e753f43e0162..0e42de291803 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -365,17 +365,6 @@ static struct request_context *ezusb_alloc_ctx(struct ezusb_priv *upriv,
return ctx;
}
-
-/* Hopefully the real complete_all will soon be exported, in the mean
- * while this should work. */
-static inline void ezusb_complete_all(struct completion *comp)
-{
- complete(comp);
- complete(comp);
- complete(comp);
- complete(comp);
-}
-
static void ezusb_ctx_complete(struct request_context *ctx)
{
struct ezusb_priv *upriv = ctx->upriv;
@@ -409,7 +398,7 @@ static void ezusb_ctx_complete(struct request_context *ctx)
netif_wake_queue(dev);
}
- ezusb_complete_all(&ctx->done);
+ complete_all(&ctx->done);
ezusb_request_context_put(ctx);
break;
@@ -419,7 +408,7 @@ static void ezusb_ctx_complete(struct request_context *ctx)
/* This is normal, as all request contexts get flushed
* when the device is disconnected */
err("Called, CTX not terminating, but device gone");
- ezusb_complete_all(&ctx->done);
+ complete_all(&ctx->done);
ezusb_request_context_put(ctx);
break;
}
@@ -690,11 +679,11 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
* get the chance to run themselves. So we make sure
* that we don't sleep for ever */
int msecs = DEF_TIMEOUT * (1000 / HZ);
- while (!ctx->done.done && msecs--)
+
+ while (!try_wait_for_completion(&ctx->done) && msecs--)
udelay(1000);
} else {
- wait_event_interruptible(ctx->done.wait,
- ctx->done.done);
+ wait_for_completion(&ctx->done);
}
break;
default:
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index a823b4b8ef8a..e69cac84b605 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -52,10 +52,11 @@ struct switchtec_user {
enum mrpc_state state;
- struct completion comp;
+ wait_queue_head_t cmd_comp;
struct kref kref;
struct list_head list;
+ bool cmd_done;
u32 cmd;
u32 status;
u32 return_code;
@@ -77,7 +78,7 @@ static struct switchtec_user *stuser_create(struct switchtec_dev *stdev)
stuser->stdev = stdev;
kref_init(&stuser->kref);
INIT_LIST_HEAD(&stuser->list);
- init_completion(&stuser->comp);
+ init_waitqueue_head(&stuser->cmd_comp);
stuser->event_cnt = atomic_read(&stdev->event_cnt);
dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser);
@@ -175,7 +176,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser)
kref_get(&stuser->kref);
stuser->read_len = sizeof(stuser->data);
stuser_set_state(stuser, MRPC_QUEUED);
- init_completion(&stuser->comp);
+ stuser->cmd_done = false;
list_add_tail(&stuser->list, &stdev->mrpc_queue);
mrpc_cmd_submit(stdev);
@@ -222,7 +223,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev)
memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data,
stuser->read_len);
out:
- complete_all(&stuser->comp);
+ stuser->cmd_done = true;
+ wake_up_interruptible(&stuser->cmd_comp);
list_del_init(&stuser->list);
stuser_put(stuser);
stdev->mrpc_busy = 0;
@@ -529,10 +531,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data,
mutex_unlock(&stdev->mrpc_mutex);
if (filp->f_flags & O_NONBLOCK) {
- if (!try_wait_for_completion(&stuser->comp))
+ if (!stuser->cmd_done)
return -EAGAIN;
} else {
- rc = wait_for_completion_interruptible(&stuser->comp);
+ rc = wait_event_interruptible(stuser->cmd_comp,
+ stuser->cmd_done);
if (rc < 0)
return rc;
}
@@ -580,7 +583,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait)
struct switchtec_dev *stdev = stuser->stdev;
__poll_t ret = 0;
- poll_wait(filp, &stuser->comp.wait, wait);
+ poll_wait(filp, &stuser->cmd_comp, wait);
poll_wait(filp, &stdev->event_wq, wait);
if (lock_mutex_and_test_alive(stdev))
@@ -588,7 +591,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait)
mutex_unlock(&stdev->mrpc_mutex);
- if (try_wait_for_completion(&stuser->comp))
+ if (stuser->cmd_done)
ret |= EPOLLIN | EPOLLRDNORM;
if (stuser->event_cnt != atomic_read(&stdev->event_cnt))
@@ -1272,7 +1275,8 @@ static void stdev_kill(struct switchtec_dev *stdev)
/* Wake up and kill any users waiting on an MRPC request */
list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) {
- complete_all(&stuser->comp);
+ stuser->cmd_done = true;
+ wake_up_interruptible(&stuser->cmd_comp);
list_del_init(&stuser->list);
stuser_put(stuser);
}
diff --git a/drivers/platform/x86/dell-smo8800.c b/drivers/platform/x86/dell-smo8800.c
index bfcc1d1b9b96..b531fe8ab7e0 100644
--- a/drivers/platform/x86/dell-smo8800.c
+++ b/drivers/platform/x86/dell-smo8800.c
@@ -16,6 +16,7 @@
#include <linux/interrupt.h>
#include <linux/miscdevice.h>
#include <linux/uaccess.h>
+#include <linux/fs.h>
struct smo8800_device {
u32 irq; /* acpi device irq */
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index dc2e966a5c25..941739db7199 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -29,6 +29,7 @@
#include <linux/uaccess.h>
#include <linux/uuid.h>
#include <linux/wmi.h>
+#include <linux/fs.h>
#include <uapi/linux/wmi.h>
ACPI_MODULE_NAME("wmi");
diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
index 7130e90773ed..a478cff8162a 100644
--- a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
+++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
@@ -19,6 +19,7 @@
#include <linux/acpi.h>
#include <linux/uaccess.h>
#include <linux/miscdevice.h>
+#include <linux/fs.h>
#include "acpi_thermal_rel.h"
static acpi_handle acpi_thermal_rel_handle;
diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c
index ddb4a973c698..e18758a8e911 100644
--- a/drivers/thermal/intel/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c
@@ -63,7 +63,7 @@ static int max_id __read_mostly;
/* Array of zone pointers */
static struct zone_device **zones;
/* Serializes interrupt notification, work and hotplug */
-static DEFINE_SPINLOCK(pkg_temp_lock);
+static DEFINE_RAW_SPINLOCK(pkg_temp_lock);
/* Protects zone operation in the work function against hotplug removal */
static DEFINE_MUTEX(thermal_zone_mutex);
@@ -266,12 +266,12 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
u64 msr_val, wr_val;
mutex_lock(&thermal_zone_mutex);
- spin_lock_irq(&pkg_temp_lock);
+ raw_spin_lock_irq(&pkg_temp_lock);
++pkg_work_cnt;
zonedev = pkg_temp_thermal_get_dev(cpu);
if (!zonedev) {
- spin_unlock_irq(&pkg_temp_lock);
+ raw_spin_unlock_irq(&pkg_temp_lock);
mutex_unlock(&thermal_zone_mutex);
return;
}
@@ -285,7 +285,7 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
}
enable_pkg_thres_interrupt();
- spin_unlock_irq(&pkg_temp_lock);
+ raw_spin_unlock_irq(&pkg_temp_lock);
/*
* If tzone is not NULL, then thermal_zone_mutex will prevent the
@@ -310,7 +310,7 @@ static int pkg_thermal_notify(u64 msr_val)
struct zone_device *zonedev;
unsigned long flags;
- spin_lock_irqsave(&pkg_temp_lock, flags);
+ raw_spin_lock_irqsave(&pkg_temp_lock, flags);
++pkg_interrupt_cnt;
disable_pkg_thres_interrupt();
@@ -322,7 +322,7 @@ static int pkg_thermal_notify(u64 msr_val)
pkg_thermal_schedule_work(zonedev->cpu, &zonedev->work);
}
- spin_unlock_irqrestore(&pkg_temp_lock, flags);
+ raw_spin_unlock_irqrestore(&pkg_temp_lock, flags);
return 0;
}
@@ -368,9 +368,9 @@ static int pkg_temp_thermal_device_add(unsigned int cpu)
zonedev->msr_pkg_therm_high);
cpumask_set_cpu(cpu, &zonedev->cpumask);
- spin_lock_irq(&pkg_temp_lock);
+ raw_spin_lock_irq(&pkg_temp_lock);
zones[id] = zonedev;
- spin_unlock_irq(&pkg_temp_lock);
+ raw_spin_unlock_irq(&pkg_temp_lock);
return 0;
}
@@ -407,7 +407,7 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
}
/* Protect against work and interrupts */
- spin_lock_irq(&pkg_temp_lock);
+ raw_spin_lock_irq(&pkg_temp_lock);
/*
* Check whether this cpu was the current target and store the new
@@ -439,9 +439,9 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
* To cancel the work we need to drop the lock, otherwise
* we might deadlock if the work needs to be flushed.
*/
- spin_unlock_irq(&pkg_temp_lock);
+ raw_spin_unlock_irq(&pkg_temp_lock);
cancel_delayed_work_sync(&zonedev->work);
- spin_lock_irq(&pkg_temp_lock);
+ raw_spin_lock_irq(&pkg_temp_lock);
/*
* If this is not the last cpu in the package and the work
* did not run after we dropped the lock above, then we
@@ -452,7 +452,7 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
pkg_thermal_schedule_work(target, &zonedev->work);
}
- spin_unlock_irq(&pkg_temp_lock);
+ raw_spin_unlock_irq(&pkg_temp_lock);
/* Final cleanup if this is the last cpu */
if (lastcpu)
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 767f30b86645..c81023b195c3 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1704,7 +1704,7 @@ static void ffs_data_put(struct ffs_data *ffs)
pr_info("%s(): freeing\n", __func__);
ffs_data_clear(ffs);
BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
- waitqueue_active(&ffs->ep0req_completion.wait) ||
+ swait_active(&ffs->ep0req_completion.wait) ||
waitqueue_active(&ffs->wait));
destroy_workqueue(ffs->io_completion_wq);
kfree(ffs->dev_name);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index e3dfc2180555..aa0de9e35afa 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -344,7 +344,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
spin_unlock_irq (&epdata->dev->lock);
if (likely (value == 0)) {
- value = wait_event_interruptible (done.wait, done.done);
+ value = wait_for_completion_interruptible(&done);
if (value != 0) {
spin_lock_irq (&epdata->dev->lock);
if (likely (epdata->ep != NULL)) {
@@ -353,7 +353,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
usb_ep_dequeue (epdata->ep, epdata->req);
spin_unlock_irq (&epdata->dev->lock);
- wait_event (done.wait, done.done);
+ wait_for_completion(&done);
if (epdata->status == -ECONNRESET)
epdata->status = -EINTR;
} else {
diff --git a/fs/buffer.c b/fs/buffer.c
index 3f5758e01e40..f73276d746bb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -274,8 +274,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
* decide that the page is now completely done.
*/
first = page_buffers(page);
- local_irq_save(flags);
- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+ spin_lock_irqsave(&first->b_uptodate_lock, flags);
clear_buffer_async_read(bh);
unlock_buffer(bh);
tmp = bh;
@@ -288,8 +287,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
}
tmp = tmp->b_this_page;
} while (tmp != bh);
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
/*
* If none of the buffers had errors and they are all
@@ -301,8 +299,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
return;
still_busy:
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
return;
}
@@ -371,8 +368,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
}
first = page_buffers(page);
- local_irq_save(flags);
- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+ spin_lock_irqsave(&first->b_uptodate_lock, flags);
clear_buffer_async_write(bh);
unlock_buffer(bh);
@@ -384,14 +380,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
}
tmp = tmp->b_this_page;
}
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
end_page_writeback(page);
return;
still_busy:
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
return;
}
EXPORT_SYMBOL(end_buffer_async_write);
@@ -3342,6 +3336,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
if (ret) {
INIT_LIST_HEAD(&ret->b_assoc_buffers);
+ spin_lock_init(&ret->b_uptodate_lock);
preempt_disable();
__this_cpu_inc(bh_accounting.nr);
recalc_bh_state();
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 68b39e75446a..de6fe969f773 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -125,11 +125,10 @@ static void ext4_finish_bio(struct bio *bio)
}
bh = head = page_buffers(page);
/*
- * We check all buffers in the page under BH_Uptodate_Lock
+ * We check all buffers in the page under b_uptodate_lock
* to avoid races with other end io clearing async_write flags
*/
- local_irq_save(flags);
- bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
+ spin_lock_irqsave(&head->b_uptodate_lock, flags);
do {
if (bh_offset(bh) < bio_start ||
bh_offset(bh) + bh->b_size > bio_end) {
@@ -141,8 +140,7 @@ static void ext4_finish_bio(struct bio *bio)
if (bio->bi_status)
buffer_io_error(bh);
} while ((bh = bh->b_this_page) != head);
- bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&head->b_uptodate_lock, flags);
if (!under_io) {
fscrypt_free_bounce_page(bounce_page);
end_page_writeback(page);
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 7202a1e39d70..554b744f41bf 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -92,8 +92,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
"0x%llx.", (unsigned long long)bh->b_blocknr);
}
first = page_buffers(page);
- local_irq_save(flags);
- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+ spin_lock_irqsave(&first->b_uptodate_lock, flags);
clear_buffer_async_read(bh);
unlock_buffer(bh);
tmp = bh;
@@ -108,8 +107,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
}
tmp = tmp->b_this_page;
} while (tmp != bh);
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
/*
* If none of the buffers had errors then we can set the page uptodate,
* but we first have to perform the post read mst fixups, if the
@@ -142,8 +140,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
unlock_page(page);
return;
still_busy:
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
return;
}
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 0c23fd0548d1..a92bea7184a8 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -80,7 +80,7 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv);
#ifdef CONFIG_ACPI
-#include <linux/proc_fs.h>
+struct proc_dir_entry;
#define ACPI_BUS_FILE_ROOT "acpi"
extern struct proc_dir_entry *acpi_root_dir;
diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h
index bfc96bf6606e..df9b5bc3d282 100644
--- a/include/asm-generic/bitops.h
+++ b/include/asm-generic/bitops.h
@@ -4,8 +4,9 @@
/*
* For the benefit of those who are trying to port Linux to another
- * architecture, here are some C-language equivalents. You should
- * recode these in the native assembly language, if at all possible.
+ * architecture, here are some C-language equivalents. They should
+ * generate reasonable code, so take a look at what your compiler spits
+ * out before rolling your own buggy implementation in assembly language.
*
* C language equivalents written by Theodore Ts'o, 9/26/92
*/
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 02970b11f71f..f4c3470480c7 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -34,7 +34,6 @@ arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
u32 tmp;
preempt_disable();
- pagefault_disable();
ret = -EFAULT;
if (unlikely(get_user(oldval, uaddr) != 0))
@@ -67,7 +66,6 @@ arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
ret = -EFAULT;
out_pagefault_enable:
- pagefault_enable();
preempt_enable();
if (ret == 0)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 7b73ef7f902d..e0b020eaf32e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -22,9 +22,6 @@ enum bh_state_bits {
BH_Dirty, /* Is dirty */
BH_Lock, /* Is locked */
BH_Req, /* Has been submitted for I/O */
- BH_Uptodate_Lock,/* Used by the first bh in a page, to serialise
- * IO completion of other buffers in the page
- */
BH_Mapped, /* Has a disk mapping */
BH_New, /* Disk mapping was newly created by get_block */
@@ -76,6 +73,9 @@ struct buffer_head {
struct address_space *b_assoc_map; /* mapping this buffer is
associated with */
atomic_t b_count; /* users using this buffer_head */
+ spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to
+ * serialise IO completion of other
+ * buffers in the page */
};
/*
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 519e94915d18..bf8e77001f18 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -9,7 +9,7 @@
* See kernel/sched/completion.c for details.
*/
-#include <linux/wait.h>
+#include <linux/swait.h>
/*
* struct completion - structure used to maintain state for a "completion"
@@ -25,7 +25,7 @@
*/
struct completion {
unsigned int done;
- wait_queue_head_t wait;
+ struct swait_queue_head wait;
};
#define init_completion_map(x, m) __init_completion(x)
@@ -34,7 +34,7 @@ static inline void complete_acquire(struct completion *x) {}
static inline void complete_release(struct completion *x) {}
#define COMPLETION_INITIALIZER(work) \
- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
#define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \
(*({ init_completion_map(&(work), &(map)); &(work); }))
@@ -85,7 +85,7 @@ static inline void complete_release(struct completion *x) {}
static inline void __init_completion(struct completion *x)
{
x->done = 0;
- init_waitqueue_head(&x->wait);
+ init_swait_queue_head(&x->wait);
}
/**
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 02da997ad12c..3b752e80c017 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -18,6 +18,8 @@
/* Doesn't want IPI, wait for tick: */
#define IRQ_WORK_LAZY BIT(2)
+/* Run hard IRQ context, even on RT */
+#define IRQ_WORK_HARD_IRQ BIT(3)
#define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY)
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 21619c92c377..a16adbb58f66 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -37,7 +37,12 @@
# define trace_softirqs_enabled(p) ((p)->softirqs_enabled)
# define trace_hardirq_enter() \
do { \
- current->hardirq_context++; \
+ if (!current->hardirq_context++) \
+ current->hardirq_threaded = 0; \
+} while (0)
+# define trace_hardirq_threaded() \
+do { \
+ current->hardirq_threaded = 1; \
} while (0)
# define trace_hardirq_exit() \
do { \
@@ -51,6 +56,40 @@ do { \
do { \
current->softirq_context--; \
} while (0)
+
+# define lockdep_hrtimer_enter(__hrtimer) \
+ do { \
+ if (!__hrtimer->is_hard) \
+ current->irq_config = 1; \
+ } while (0)
+
+# define lockdep_hrtimer_exit(__hrtimer) \
+ do { \
+ if (!__hrtimer->is_hard) \
+ current->irq_config = 0; \
+ } while (0)
+
+# define lockdep_posixtimer_enter() \
+ do { \
+ current->irq_config = 1; \
+ } while (0)
+
+# define lockdep_posixtimer_exit() \
+ do { \
+ current->irq_config = 0; \
+ } while (0)
+
+# define lockdep_irq_work_enter(__work) \
+ do { \
+ if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\
+ current->irq_config = 1; \
+ } while (0)
+# define lockdep_irq_work_exit(__work) \
+ do { \
+ if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\
+ current->irq_config = 0; \
+ } while (0)
+
#else
# define trace_hardirqs_on() do { } while (0)
# define trace_hardirqs_off() do { } while (0)
@@ -59,9 +98,16 @@ do { \
# define trace_hardirqs_enabled(p) 0
# define trace_softirqs_enabled(p) 0
# define trace_hardirq_enter() do { } while (0)
+# define trace_hardirq_threaded() do { } while (0)
# define trace_hardirq_exit() do { } while (0)
# define lockdep_softirq_enter() do { } while (0)
# define lockdep_softirq_exit() do { } while (0)
+# define lockdep_hrtimer_enter(__hrtimer) do { } while (0)
+# define lockdep_hrtimer_exit(__hrtimer) do { } while (0)
+# define lockdep_posixtimer_enter() do { } while (0)
+# define lockdep_posixtimer_exit() do { } while (0)
+# define lockdep_irq_work_enter(__work) do { } while (0)
+# define lockdep_irq_work_exit(__work) do { } while (0)
#endif
#if defined(CONFIG_IRQSOFF_TRACER) || \
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 664f52c6dd4c..206774ac6946 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -21,6 +21,22 @@ extern int lock_stat;
#include <linux/types.h>
+enum lockdep_wait_type {
+ LD_WAIT_INV = 0, /* not checked, catch all */
+
+ LD_WAIT_FREE, /* wait free, rcu etc.. */
+ LD_WAIT_SPIN, /* spin loops, raw_spinlock_t etc.. */
+
+#ifdef CONFIG_PROVE_RAW_LOCK_NESTING
+ LD_WAIT_CONFIG, /* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */
+#else
+ LD_WAIT_CONFIG = LD_WAIT_SPIN,
+#endif
+ LD_WAIT_SLEEP, /* sleeping locks, mutex_t etc.. */
+
+ LD_WAIT_MAX, /* must be last */
+};
+
#ifdef CONFIG_LOCKDEP
#include <linux/linkage.h>
@@ -111,6 +127,9 @@ struct lock_class {
int name_version;
const char *name;
+ short wait_type_inner;
+ short wait_type_outer;
+
#ifdef CONFIG_LOCK_STAT
unsigned long contention_point[LOCKSTAT_POINTS];
unsigned long contending_point[LOCKSTAT_POINTS];
@@ -158,6 +177,8 @@ struct lockdep_map {
struct lock_class_key *key;
struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES];
const char *name;
+ short wait_type_outer; /* can be taken in this context */
+ short wait_type_inner; /* presents this context */
#ifdef CONFIG_LOCK_STAT
int cpu;
unsigned long ip;
@@ -299,8 +320,21 @@ extern void lockdep_unregister_key(struct lock_class_key *key);
* to lockdep:
*/
-extern void lockdep_init_map(struct lockdep_map *lock, const char *name,
- struct lock_class_key *key, int subclass);
+extern void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
+ struct lock_class_key *key, int subclass, short inner, short outer);
+
+static inline void
+lockdep_init_map_wait(struct lockdep_map *lock, const char *name,
+ struct lock_class_key *key, int subclass, short inner)
+{
+ lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV);
+}
+
+static inline void lockdep_init_map(struct lockdep_map *lock, const char *name,
+ struct lock_class_key *key, int subclass)
+{
+ lockdep_init_map_wait(lock, name, key, subclass, LD_WAIT_INV);
+}
/*
* Reinitialize a lock key - for cases where there is special locking or
@@ -308,18 +342,29 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name,
* of dependencies wrong: they are either too broad (they need a class-split)
* or they are too narrow (they suffer from a false class-split):
*/
-#define lockdep_set_class(lock, key) \
- lockdep_init_map(&(lock)->dep_map, #key, key, 0)
-#define lockdep_set_class_and_name(lock, key, name) \
- lockdep_init_map(&(lock)->dep_map, name, key, 0)
-#define lockdep_set_class_and_subclass(lock, key, sub) \
- lockdep_init_map(&(lock)->dep_map, #key, key, sub)
-#define lockdep_set_subclass(lock, sub) \
- lockdep_init_map(&(lock)->dep_map, #lock, \
- (lock)->dep_map.key, sub)
+#define lockdep_set_class(lock, key) \
+ lockdep_init_map_waits(&(lock)->dep_map, #key, key, 0, \
+ (lock)->dep_map.wait_type_inner, \
+ (lock)->dep_map.wait_type_outer)
+
+#define lockdep_set_class_and_name(lock, key, name) \
+ lockdep_init_map_waits(&(lock)->dep_map, name, key, 0, \
+ (lock)->dep_map.wait_type_inner, \
+ (lock)->dep_map.wait_type_outer)
+
+#define lockdep_set_class_and_subclass(lock, key, sub) \
+ lockdep_init_map_waits(&(lock)->dep_map, #key, key, sub,\
+ (lock)->dep_map.wait_type_inner, \
+ (lock)->dep_map.wait_type_outer)
+
+#define lockdep_set_subclass(lock, sub) \
+ lockdep_init_map_waits(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\
+ (lock)->dep_map.wait_type_inner, \
+ (lock)->dep_map.wait_type_outer)
#define lockdep_set_novalidate_class(lock) \
lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock)
+
/*
* Compare locking classes
*/
@@ -432,6 +477,10 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
# define lock_set_class(l, n, k, s, i) do { } while (0)
# define lock_set_subclass(l, s, i) do { } while (0)
# define lockdep_init() do { } while (0)
+# define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \
+ do { (void)(name); (void)(key); } while (0)
+# define lockdep_init_map_wait(lock, name, key, sub, inner) \
+ do { (void)(name); (void)(key); } while (0)
# define lockdep_init_map(lock, name, key, sub) \
do { (void)(name); (void)(key); } while (0)
# define lockdep_set_class(lock, key) do { (void)(key); } while (0)
@@ -662,6 +711,21 @@ do { \
# define lockdep_assert_in_irq() do { } while (0)
#endif
+#ifdef CONFIG_PROVE_RAW_LOCK_NESTING
+
+# define lockdep_assert_RT_in_threaded_ctx() do { \
+ WARN_ONCE(debug_locks && !current->lockdep_recursion && \
+ current->hardirq_context && \
+ !(current->hardirq_threaded || current->irq_config), \
+ "Not in threaded context on PREEMPT_RT as expected\n"); \
+} while (0)
+
+#else
+
+# define lockdep_assert_RT_in_threaded_ctx() do { } while (0)
+
+#endif
+
#ifdef CONFIG_LOCKDEP
void lockdep_rcu_suspicious(const char *file, const int line, const char *s);
#else
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index aca8f36dfac9..ae197cc00cc8 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -109,8 +109,11 @@ do { \
} while (0)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
- , .dep_map = { .name = #lockname }
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
+ , .dep_map = { \
+ .name = #lockname, \
+ .wait_type_inner = LD_WAIT_SLEEP, \
+ }
#else
# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
#endif
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index ad2ca2a89d5b..5e033fe1ff4e 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -3,41 +3,52 @@
#define _LINUX_PERCPU_RWSEM_H
#include <linux/atomic.h>
-#include <linux/rwsem.h>
#include <linux/percpu.h>
#include <linux/rcuwait.h>
+#include <linux/wait.h>
#include <linux/rcu_sync.h>
#include <linux/lockdep.h>
struct percpu_rw_semaphore {
struct rcu_sync rss;
unsigned int __percpu *read_count;
- struct rw_semaphore rw_sem; /* slowpath */
- struct rcuwait writer; /* blocked writer */
- int readers_block;
+ struct rcuwait writer;
+ wait_queue_head_t waiters;
+ atomic_t block;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif
};
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname },
+#else
+#define __PERCPU_RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
#define __DEFINE_PERCPU_RWSEM(name, is_static) \
static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \
is_static struct percpu_rw_semaphore name = { \
.rss = __RCU_SYNC_INITIALIZER(name.rss), \
.read_count = &__percpu_rwsem_rc_##name, \
- .rw_sem = __RWSEM_INITIALIZER(name.rw_sem), \
.writer = __RCUWAIT_INITIALIZER(name.writer), \
+ .waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters), \
+ .block = ATOMIC_INIT(0), \
+ __PERCPU_RWSEM_DEP_MAP_INIT(name) \
}
+
#define DEFINE_PERCPU_RWSEM(name) \
__DEFINE_PERCPU_RWSEM(name, /* not static */)
#define DEFINE_STATIC_PERCPU_RWSEM(name) \
__DEFINE_PERCPU_RWSEM(name, static)
-extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
-extern void __percpu_up_read(struct percpu_rw_semaphore *);
+extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool);
static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
{
might_sleep();
- rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 0, _RET_IP_);
+ rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
preempt_disable();
/*
@@ -48,8 +59,9 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
* and that once the synchronize_rcu() is done, the writer will see
* anything we did within this RCU-sched read-size critical section.
*/
- __this_cpu_inc(*sem->read_count);
- if (unlikely(!rcu_sync_is_idle(&sem->rss)))
+ if (likely(rcu_sync_is_idle(&sem->rss)))
+ __this_cpu_inc(*sem->read_count);
+ else
__percpu_down_read(sem, false); /* Unconditional memory barrier */
/*
* The preempt_enable() prevents the compiler from
@@ -58,16 +70,17 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
preempt_enable();
}
-static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
+static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
{
- int ret = 1;
+ bool ret = true;
preempt_disable();
/*
* Same as in percpu_down_read().
*/
- __this_cpu_inc(*sem->read_count);
- if (unlikely(!rcu_sync_is_idle(&sem->rss)))
+ if (likely(rcu_sync_is_idle(&sem->rss)))
+ __this_cpu_inc(*sem->read_count);
+ else
ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */
preempt_enable();
/*
@@ -76,24 +89,36 @@ static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
*/
if (ret)
- rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 1, _RET_IP_);
+ rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
return ret;
}
static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
{
+ rwsem_release(&sem->dep_map, _RET_IP_);
+
preempt_disable();
/*
* Same as in percpu_down_read().
*/
- if (likely(rcu_sync_is_idle(&sem->rss)))
+ if (likely(rcu_sync_is_idle(&sem->rss))) {
__this_cpu_dec(*sem->read_count);
- else
- __percpu_up_read(sem); /* Unconditional memory barrier */
+ } else {
+ /*
+ * slowpath; reader will only ever wake a single blocked
+ * writer.
+ */
+ smp_mb(); /* B matches C */
+ /*
+ * In other words, if they see our decrement (presumably to
+ * aggregate zero, as that is the only time it matters) they
+ * will also see our critical section.
+ */
+ __this_cpu_dec(*sem->read_count);
+ rcuwait_wake_up(&sem->writer);
+ }
preempt_enable();
-
- rwsem_release(&sem->rw_sem.dep_map, _RET_IP_);
}
extern void percpu_down_write(struct percpu_rw_semaphore *);
@@ -110,29 +135,19 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
__percpu_init_rwsem(sem, #sem, &rwsem_key); \
})
-#define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem)
-
-#define percpu_rwsem_assert_held(sem) \
- lockdep_assert_held(&(sem)->rw_sem)
+#define percpu_rwsem_is_held(sem) lockdep_is_held(sem)
+#define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem)
static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
bool read, unsigned long ip)
{
- lock_release(&sem->rw_sem.dep_map, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
- if (!read)
- atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
-#endif
+ lock_release(&sem->dep_map, ip);
}
static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
bool read, unsigned long ip)
{
- lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
- if (!read)
- atomic_long_set(&sem->rw_sem.owner, (long)current);
-#endif
+ lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip);
}
#endif
diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h
index 75c97e4bbc57..2ffe1ee6d482 100644
--- a/include/linux/rcuwait.h
+++ b/include/linux/rcuwait.h
@@ -3,6 +3,7 @@
#define _LINUX_RCUWAIT_H_
#include <linux/rcupdate.h>
+#include <linux/sched/signal.h>
/*
* rcuwait provides a way of blocking and waking up a single
@@ -30,23 +31,30 @@ extern void rcuwait_wake_up(struct rcuwait *w);
* The caller is responsible for locking around rcuwait_wait_event(),
* such that writes to @task are properly serialized.
*/
-#define rcuwait_wait_event(w, condition) \
+#define rcuwait_wait_event(w, condition, state) \
({ \
+ int __ret = 0; \
rcu_assign_pointer((w)->task, current); \
for (;;) { \
/* \
* Implicit barrier (A) pairs with (B) in \
* rcuwait_wake_up(). \
*/ \
- set_current_state(TASK_UNINTERRUPTIBLE); \
+ set_current_state(state); \
if (condition) \
break; \
\
+ if (signal_pending_state(state, current)) { \
+ __ret = -EINTR; \
+ break; \
+ } \
+ \
schedule(); \
} \
\
WRITE_ONCE((w)->task, NULL); \
__set_current_state(TASK_RUNNING); \
+ __ret; \
})
#endif /* _LINUX_RCUWAIT_H_ */
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index 857a72ceb794..3bd03e18061c 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -22,7 +22,11 @@ typedef struct {
#define RWLOCK_MAGIC 0xdeaf1eed
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
+# define RW_DEP_MAP_INIT(lockname) \
+ .dep_map = { \
+ .name = #lockname, \
+ .wait_type_inner = LD_WAIT_CONFIG, \
+ }
#else
# define RW_DEP_MAP_INIT(lockname)
#endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 00d6054687dd..7e5b2a4eb560 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -53,12 +53,6 @@ struct rw_semaphore {
#endif
};
-/*
- * Setting all bits of the owner field except bit 0 will indicate
- * that the rwsem is writer-owned with an unknown owner.
- */
-#define RWSEM_OWNER_UNKNOWN (-2L)
-
/* In all implementations count != 0 means locked */
static inline int rwsem_is_locked(struct rw_semaphore *sem)
{
@@ -71,7 +65,11 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
/* Common initializer macros and functions */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+# define __RWSEM_DEP_MAP_INIT(lockname) \
+ , .dep_map = { \
+ .name = #lockname, \
+ .wait_type_inner = LD_WAIT_SLEEP, \
+ }
#else
# define __RWSEM_DEP_MAP_INIT(lockname)
#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 04278493bf15..933914cdf219 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -970,6 +970,7 @@ struct task_struct {
#ifdef CONFIG_TRACE_IRQFLAGS
unsigned int irq_events;
+ unsigned int hardirq_threaded;
unsigned long hardirq_enable_ip;
unsigned long hardirq_disable_ip;
unsigned int hardirq_enable_event;
@@ -982,6 +983,7 @@ struct task_struct {
unsigned int softirq_enable_event;
int softirqs_enabled;
int softirq_context;
+ int irq_config;
#endif
#ifdef CONFIG_LOCKDEP
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 031ce8617df8..d3770b3f9d9a 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -93,12 +93,13 @@
#ifdef CONFIG_DEBUG_SPINLOCK
extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
- struct lock_class_key *key);
-# define raw_spin_lock_init(lock) \
-do { \
- static struct lock_class_key __key; \
- \
- __raw_spin_lock_init((lock), #lock, &__key); \
+ struct lock_class_key *key, short inner);
+
+# define raw_spin_lock_init(lock) \
+do { \
+ static struct lock_class_key __key; \
+ \
+ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \
} while (0)
#else
@@ -327,12 +328,26 @@ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock)
return &lock->rlock;
}
-#define spin_lock_init(_lock) \
-do { \
- spinlock_check(_lock); \
- raw_spin_lock_init(&(_lock)->rlock); \
+#ifdef CONFIG_DEBUG_SPINLOCK
+
+# define spin_lock_init(lock) \
+do { \
+ static struct lock_class_key __key; \
+ \
+ __raw_spin_lock_init(spinlock_check(lock), \
+ #lock, &__key, LD_WAIT_CONFIG); \
+} while (0)
+
+#else
+
+# define spin_lock_init(_lock) \
+do { \
+ spinlock_check(_lock); \
+ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \
} while (0)
+#endif
+
static __always_inline void spin_lock(spinlock_t *lock)
{
raw_spin_lock(&lock->rlock);
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 24b4e6f2c1a2..6102e6bff3ae 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -33,8 +33,18 @@ typedef struct raw_spinlock {
#define SPINLOCK_OWNER_INIT ((void *)-1L)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
+# define RAW_SPIN_DEP_MAP_INIT(lockname) \
+ .dep_map = { \
+ .name = #lockname, \
+ .wait_type_inner = LD_WAIT_SPIN, \
+ }
+# define SPIN_DEP_MAP_INIT(lockname) \
+ .dep_map = { \
+ .name = #lockname, \
+ .wait_type_inner = LD_WAIT_CONFIG, \
+ }
#else
+# define RAW_SPIN_DEP_MAP_INIT(lockname)
# define SPIN_DEP_MAP_INIT(lockname)
#endif
@@ -51,7 +61,7 @@ typedef struct raw_spinlock {
{ \
.raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \
SPIN_DEBUG_INIT(lockname) \
- SPIN_DEP_MAP_INIT(lockname) }
+ RAW_SPIN_DEP_MAP_INIT(lockname) }
#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \
(raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
@@ -72,11 +82,17 @@ typedef struct spinlock {
};
} spinlock_t;
+#define ___SPIN_LOCK_INITIALIZER(lockname) \
+ { \
+ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \
+ SPIN_DEBUG_INIT(lockname) \
+ SPIN_DEP_MAP_INIT(lockname) }
+
#define __SPIN_LOCK_INITIALIZER(lockname) \
- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
+ { { .rlock = ___SPIN_LOCK_INITIALIZER(lockname) } }
#define __SPIN_LOCK_UNLOCKED(lockname) \
- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
+ (spinlock_t) __SPIN_LOCK_INITIALIZER(lockname)
#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3283c8d02137..feeb6be5cad6 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -20,6 +20,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int
#define WQ_FLAG_EXCLUSIVE 0x01
#define WQ_FLAG_WOKEN 0x02
#define WQ_FLAG_BOOKMARK 0x04
+#define WQ_FLAG_CUSTOM 0x08
/*
* A single wait-queue entry structure:
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9c706af713fb..221bf6a9e98a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -331,12 +331,12 @@ void lockdep_assert_cpus_held(void)
static void lockdep_acquire_cpus_lock(void)
{
- rwsem_acquire(&cpu_hotplug_lock.rw_sem.dep_map, 0, 0, _THIS_IP_);
+ rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_);
}
static void lockdep_release_cpus_lock(void)
{
- rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, _THIS_IP_);
+ rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_);
}
/*
diff --git a/kernel/exit.c b/kernel/exit.c
index 0b81b26a872a..764960fabfa1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -258,6 +258,7 @@ void rcuwait_wake_up(struct rcuwait *w)
wake_up_process(task);
rcu_read_unlock();
}
+EXPORT_SYMBOL_GPL(rcuwait_wake_up);
/*
* Determine if a process group is "orphaned", according to the POSIX
diff --git a/kernel/futex.c b/kernel/futex.c
index 82dfacb3250e..b59532862bc0 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -135,8 +135,7 @@
*
* Where (A) orders the waiters increment and the futex value read through
* atomic operations (see hb_waiters_inc) and where (B) orders the write
- * to futex and the waiters read -- this is done by the barriers for both
- * shared and private futexes in get_futex_key_refs().
+ * to futex and the waiters read (see hb_waiters_pending()).
*
* This yields the following case (where X:=waiters, Y:=futex):
*
@@ -331,17 +330,6 @@ static void compat_exit_robust_list(struct task_struct *curr);
static inline void compat_exit_robust_list(struct task_struct *curr) { }
#endif
-static inline void futex_get_mm(union futex_key *key)
-{
- mmgrab(key->private.mm);
- /*
- * Ensure futex_get_mm() implies a full barrier such that
- * get_futex_key() implies a full barrier. This is relied upon
- * as smp_mb(); (B), see the ordering comment above.
- */
- smp_mb__after_atomic();
-}
-
/*
* Reflects a new waiter being added to the waitqueue.
*/
@@ -370,6 +358,10 @@ static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
+ /*
+ * Full barrier (B), see the ordering comment above.
+ */
+ smp_mb();
return atomic_read(&hb->waiters);
#else
return 1;
@@ -407,69 +399,6 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
&& key1->both.offset == key2->both.offset);
}
-/*
- * Take a reference to the resource addressed by a key.
- * Can be called while holding spinlocks.
- *
- */
-static void get_futex_key_refs(union futex_key *key)
-{
- if (!key->both.ptr)
- return;
-
- /*
- * On MMU less systems futexes are always "private" as there is no per
- * process address space. We need the smp wmb nevertheless - yes,
- * arch/blackfin has MMU less SMP ...
- */
- if (!IS_ENABLED(CONFIG_MMU)) {
- smp_mb(); /* explicit smp_mb(); (B) */
- return;
- }
-
- switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
- case FUT_OFF_INODE:
- smp_mb(); /* explicit smp_mb(); (B) */
- break;
- case FUT_OFF_MMSHARED:
- futex_get_mm(key); /* implies smp_mb(); (B) */
- break;
- default:
- /*
- * Private futexes do not hold reference on an inode or
- * mm, therefore the only purpose of calling get_futex_key_refs
- * is because we need the barrier for the lockless waiter check.
- */
- smp_mb(); /* explicit smp_mb(); (B) */
- }
-}
-
-/*
- * Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held. This is
- * a no-op for private futexes, see comment in the get
- * counterpart.
- */
-static void drop_futex_key_refs(union futex_key *key)
-{
- if (!key->both.ptr) {
- /* If we're here then we tried to put a key we failed to get */
- WARN_ON_ONCE(1);
- return;
- }
-
- if (!IS_ENABLED(CONFIG_MMU))
- return;
-
- switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
- case FUT_OFF_INODE:
- break;
- case FUT_OFF_MMSHARED:
- mmdrop(key->private.mm);
- break;
- }
-}
-
enum futex_access {
FUTEX_READ,
FUTEX_WRITE
@@ -601,7 +530,6 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a
if (!fshared) {
key->private.mm = mm;
key->private.address = address;
- get_futex_key_refs(key); /* implies smp_mb(); (B) */
return 0;
}
@@ -741,8 +669,6 @@ again:
rcu_read_unlock();
}
- get_futex_key_refs(key); /* implies smp_mb(); (B) */
-
out:
put_page(page);
return err;
@@ -750,7 +676,6 @@ out:
static inline void put_futex_key(union futex_key *key)
{
- drop_futex_key_refs(key);
}
/**
@@ -1740,10 +1665,9 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
oparg = 1 << oparg;
}
- if (!access_ok(uaddr, sizeof(u32)))
- return -EFAULT;
-
+ pagefault_disable();
ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
+ pagefault_enable();
if (ret)
return ret;
@@ -1885,7 +1809,6 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
plist_add(&q->list, &hb2->chain);
q->lock_ptr = &hb2->lock;
}
- get_futex_key_refs(key2);
q->key = *key2;
}
@@ -1907,7 +1830,6 @@ static inline
void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
struct futex_hash_bucket *hb)
{
- get_futex_key_refs(key);
q->key = *key;
__unqueue_futex(q);
@@ -2018,7 +1940,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
u32 *cmpval, int requeue_pi)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
- int drop_count = 0, task_count = 0, ret;
+ int task_count = 0, ret;
struct futex_pi_state *pi_state = NULL;
struct futex_hash_bucket *hb1, *hb2;
struct futex_q *this, *next;
@@ -2139,7 +2061,6 @@ retry_private:
*/
if (ret > 0) {
WARN_ON(pi_state);
- drop_count++;
task_count++;
/*
* If we acquired the lock, then the user space value
@@ -2259,7 +2180,6 @@ retry_private:
* doing so.
*/
requeue_pi_wake_futex(this, &key2, hb2);
- drop_count++;
continue;
} else if (ret) {
/*
@@ -2280,7 +2200,6 @@ retry_private:
}
}
requeue_futex(this, hb1, hb2, &key2);
- drop_count++;
}
/*
@@ -2295,15 +2214,6 @@ out_unlock:
wake_up_q(&wake_q);
hb_waiters_dec(hb2);
- /*
- * drop_futex_key_refs() must be called outside the spinlocks. During
- * the requeue we moved futex_q's from the hash bucket at key1 to the
- * one at key2 and updated their key pointer. We no longer need to
- * hold the references to key1.
- */
- while (--drop_count >= 0)
- drop_futex_key_refs(&key1);
-
out_put_keys:
put_futex_key(&key2);
out_put_key1:
@@ -2433,7 +2343,6 @@ retry:
ret = 1;
}
- drop_futex_key_refs(&q->key);
return ret;
}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a4ace611f47f..16ee716e8291 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -145,6 +145,13 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags
for_each_action_of_desc(desc, action) {
irqreturn_t res;
+ /*
+ * If this IRQ would be threaded under force_irqthreads, mark it so.
+ */
+ if (irq_settings_can_thread(desc) &&
+ !(action->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)))
+ trace_hardirq_threaded();
+
trace_irq_handler_entry(irq, action);
res = action->handler(irq, action->dev_id);
trace_irq_handler_exit(irq, action, res);
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 828cc30774bc..48b5d1b6af4d 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -153,7 +153,9 @@ static void irq_work_run_list(struct llist_head *list)
*/
flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
+ lockdep_irq_work_enter(work);
work->func(work);
+ lockdep_irq_work_exit(work);
/*
* Clear the BUSY bit and return to the free state if
* no-one else claimed it meanwhile.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 32406ef0d6a2..0ebf9807d971 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -84,12 +84,39 @@ module_param(lock_stat, int, 0644);
* to use a raw spinlock - we really dont want the spinlock
* code to recurse back into the lockdep code...
*/
-static arch_spinlock_t lockdep_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t __lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+static struct task_struct *__owner;
+
+static inline void lockdep_lock(void)
+{
+ DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
+ arch_spin_lock(&__lock);
+ __owner = current;
+ current->lockdep_recursion++;
+}
+
+static inline void lockdep_unlock(void)
+{
+ if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current))
+ return;
+
+ current->lockdep_recursion--;
+ __owner = NULL;
+ arch_spin_unlock(&__lock);
+}
+
+static inline bool lockdep_assert_locked(void)
+{
+ return DEBUG_LOCKS_WARN_ON(__owner != current);
+}
+
static struct task_struct *lockdep_selftest_task_struct;
+
static int graph_lock(void)
{
- arch_spin_lock(&lockdep_lock);
+ lockdep_lock();
/*
* Make sure that if another CPU detected a bug while
* walking the graph we dont change it (while the other
@@ -97,27 +124,15 @@ static int graph_lock(void)
* dropped already)
*/
if (!debug_locks) {
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
return 0;
}
- /* prevent any recursions within lockdep from causing deadlocks */
- current->lockdep_recursion++;
return 1;
}
-static inline int graph_unlock(void)
+static inline void graph_unlock(void)
{
- if (debug_locks && !arch_spin_is_locked(&lockdep_lock)) {
- /*
- * The lockdep graph lock isn't locked while we expect it to
- * be, we're confused now, bye!
- */
- return DEBUG_LOCKS_WARN_ON(1);
- }
-
- current->lockdep_recursion--;
- arch_spin_unlock(&lockdep_lock);
- return 0;
+ lockdep_unlock();
}
/*
@@ -128,7 +143,7 @@ static inline int debug_locks_off_graph_unlock(void)
{
int ret = debug_locks_off();
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
return ret;
}
@@ -147,6 +162,7 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
#define KEYHASH_SIZE (1UL << KEYHASH_BITS)
static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
unsigned long nr_lock_classes;
+unsigned long nr_zapped_classes;
#ifndef CONFIG_DEBUG_LOCKDEP
static
#endif
@@ -377,18 +393,31 @@ void lockdep_init_task(struct task_struct *task)
task->lockdep_recursion = 0;
}
+/*
+ * Split the recrursion counter in two to readily detect 'off' vs recursion.
+ */
+#define LOCKDEP_RECURSION_BITS 16
+#define LOCKDEP_OFF (1U << LOCKDEP_RECURSION_BITS)
+#define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1)
+
void lockdep_off(void)
{
- current->lockdep_recursion++;
+ current->lockdep_recursion += LOCKDEP_OFF;
}
EXPORT_SYMBOL(lockdep_off);
void lockdep_on(void)
{
- current->lockdep_recursion--;
+ current->lockdep_recursion -= LOCKDEP_OFF;
}
EXPORT_SYMBOL(lockdep_on);
+static inline void lockdep_recursion_finish(void)
+{
+ if (WARN_ON_ONCE(--current->lockdep_recursion))
+ current->lockdep_recursion = 0;
+}
+
void lockdep_set_selftest_task(struct task_struct *task)
{
lockdep_selftest_task_struct = task;
@@ -575,6 +604,7 @@ static const char *usage_str[] =
#include "lockdep_states.h"
#undef LOCKDEP_STATE
[LOCK_USED] = "INITIAL USE",
+ [LOCK_USAGE_STATES] = "IN-NMI",
};
#endif
@@ -653,7 +683,9 @@ static void print_lock_name(struct lock_class *class)
printk(KERN_CONT " (");
__print_lock_name(class);
- printk(KERN_CONT "){%s}", usage);
+ printk(KERN_CONT "){%s}-{%hd:%hd}", usage,
+ class->wait_type_outer ?: class->wait_type_inner,
+ class->wait_type_inner);
}
static void print_lockdep_cache(struct lockdep_map *lock)
@@ -787,6 +819,7 @@ static int count_matching_names(struct lock_class *new_class)
return count + 1;
}
+/* used from NMI context -- must be lockless */
static inline struct lock_class *
look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
{
@@ -1070,13 +1103,15 @@ static inline void check_data_structures(void) { }
#endif /* CONFIG_DEBUG_LOCKDEP */
+static void init_chain_block_buckets(void);
+
/*
* Initialize the lock_classes[] array elements, the free_lock_classes list
* and also the delayed_free structure.
*/
static void init_data_structures_once(void)
{
- static bool ds_initialized, rcu_head_initialized;
+ static bool __read_mostly ds_initialized, rcu_head_initialized;
int i;
if (likely(rcu_head_initialized))
@@ -1100,6 +1135,7 @@ static void init_data_structures_once(void)
INIT_LIST_HEAD(&lock_classes[i].locks_after);
INIT_LIST_HEAD(&lock_classes[i].locks_before);
}
+ init_chain_block_buckets();
}
static inline struct hlist_head *keyhashentry(const struct lock_class_key *key)
@@ -1230,6 +1266,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
WARN_ON_ONCE(!list_empty(&class->locks_before));
WARN_ON_ONCE(!list_empty(&class->locks_after));
class->name_version = count_matching_names(class);
+ class->wait_type_inner = lock->wait_type_inner;
+ class->wait_type_outer = lock->wait_type_outer;
/*
* We use RCU's safe list-add method to make
* parallel walking of the hash-list safe:
@@ -1469,6 +1507,8 @@ static int __bfs(struct lock_list *source_entry,
struct circular_queue *cq = &lock_cq;
int ret = 1;
+ lockdep_assert_locked();
+
if (match(source_entry, data)) {
*target_entry = source_entry;
ret = 0;
@@ -1491,8 +1531,6 @@ static int __bfs(struct lock_list *source_entry,
head = get_dep_list(lock, offset);
- DEBUG_LOCKS_WARN_ON(!irqs_disabled());
-
list_for_each_entry_rcu(entry, head, entry) {
if (!lock_accessed(entry)) {
unsigned int cq_depth;
@@ -1719,9 +1757,9 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
this.class = class;
raw_local_irq_save(flags);
- arch_spin_lock(&lockdep_lock);
+ lockdep_lock();
ret = __lockdep_count_forward_deps(&this);
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
raw_local_irq_restore(flags);
return ret;
@@ -1746,9 +1784,9 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
this.class = class;
raw_local_irq_save(flags);
- arch_spin_lock(&lockdep_lock);
+ lockdep_lock();
ret = __lockdep_count_backward_deps(&this);
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
raw_local_irq_restore(flags);
return ret;
@@ -2298,18 +2336,6 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
return 0;
}
-static void inc_chains(void)
-{
- if (current->hardirq_context)
- nr_hardirq_chains++;
- else {
- if (current->softirq_context)
- nr_softirq_chains++;
- else
- nr_process_chains++;
- }
-}
-
#else
static inline int check_irq_usage(struct task_struct *curr,
@@ -2317,13 +2343,27 @@ static inline int check_irq_usage(struct task_struct *curr,
{
return 1;
}
+#endif /* CONFIG_TRACE_IRQFLAGS */
-static inline void inc_chains(void)
+static void inc_chains(int irq_context)
{
- nr_process_chains++;
+ if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT)
+ nr_hardirq_chains++;
+ else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT)
+ nr_softirq_chains++;
+ else
+ nr_process_chains++;
}
-#endif /* CONFIG_TRACE_IRQFLAGS */
+static void dec_chains(int irq_context)
+{
+ if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT)
+ nr_hardirq_chains--;
+ else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT)
+ nr_softirq_chains--;
+ else
+ nr_process_chains--;
+}
static void
print_deadlock_scenario(struct held_lock *nxt, struct held_lock *prv)
@@ -2622,8 +2662,235 @@ out_bug:
struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
static DECLARE_BITMAP(lock_chains_in_use, MAX_LOCKDEP_CHAINS);
-int nr_chain_hlocks;
static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS];
+unsigned long nr_zapped_lock_chains;
+unsigned int nr_free_chain_hlocks; /* Free chain_hlocks in buckets */
+unsigned int nr_lost_chain_hlocks; /* Lost chain_hlocks */
+unsigned int nr_large_chain_blocks; /* size > MAX_CHAIN_BUCKETS */
+
+/*
+ * The first 2 chain_hlocks entries in the chain block in the bucket
+ * list contains the following meta data:
+ *
+ * entry[0]:
+ * Bit 15 - always set to 1 (it is not a class index)
+ * Bits 0-14 - upper 15 bits of the next block index
+ * entry[1] - lower 16 bits of next block index
+ *
+ * A next block index of all 1 bits means it is the end of the list.
+ *
+ * On the unsized bucket (bucket-0), the 3rd and 4th entries contain
+ * the chain block size:
+ *
+ * entry[2] - upper 16 bits of the chain block size
+ * entry[3] - lower 16 bits of the chain block size
+ */
+#define MAX_CHAIN_BUCKETS 16
+#define CHAIN_BLK_FLAG (1U << 15)
+#define CHAIN_BLK_LIST_END 0xFFFFU
+
+static int chain_block_buckets[MAX_CHAIN_BUCKETS];
+
+static inline int size_to_bucket(int size)
+{
+ if (size > MAX_CHAIN_BUCKETS)
+ return 0;
+
+ return size - 1;
+}
+
+/*
+ * Iterate all the chain blocks in a bucket.
+ */
+#define for_each_chain_block(bucket, prev, curr) \
+ for ((prev) = -1, (curr) = chain_block_buckets[bucket]; \
+ (curr) >= 0; \
+ (prev) = (curr), (curr) = chain_block_next(curr))
+
+/*
+ * next block or -1
+ */
+static inline int chain_block_next(int offset)
+{
+ int next = chain_hlocks[offset];
+
+ WARN_ON_ONCE(!(next & CHAIN_BLK_FLAG));
+
+ if (next == CHAIN_BLK_LIST_END)
+ return -1;
+
+ next &= ~CHAIN_BLK_FLAG;
+ next <<= 16;
+ next |= chain_hlocks[offset + 1];
+
+ return next;
+}
+
+/*
+ * bucket-0 only
+ */
+static inline int chain_block_size(int offset)
+{
+ return (chain_hlocks[offset + 2] << 16) | chain_hlocks[offset + 3];
+}
+
+static inline void init_chain_block(int offset, int next, int bucket, int size)
+{
+ chain_hlocks[offset] = (next >> 16) | CHAIN_BLK_FLAG;
+ chain_hlocks[offset + 1] = (u16)next;
+
+ if (size && !bucket) {
+ chain_hlocks[offset + 2] = size >> 16;
+ chain_hlocks[offset + 3] = (u16)size;
+ }
+}
+
+static inline void add_chain_block(int offset, int size)
+{
+ int bucket = size_to_bucket(size);
+ int next = chain_block_buckets[bucket];
+ int prev, curr;
+
+ if (unlikely(size < 2)) {
+ /*
+ * We can't store single entries on the freelist. Leak them.
+ *
+ * One possible way out would be to uniquely mark them, other
+ * than with CHAIN_BLK_FLAG, such that we can recover them when
+ * the block before it is re-added.
+ */
+ if (size)
+ nr_lost_chain_hlocks++;
+ return;
+ }
+
+ nr_free_chain_hlocks += size;
+ if (!bucket) {
+ nr_large_chain_blocks++;
+
+ /*
+ * Variable sized, sort large to small.
+ */
+ for_each_chain_block(0, prev, curr) {
+ if (size >= chain_block_size(curr))
+ break;
+ }
+ init_chain_block(offset, curr, 0, size);
+ if (prev < 0)
+ chain_block_buckets[0] = offset;
+ else
+ init_chain_block(prev, offset, 0, 0);
+ return;
+ }
+ /*
+ * Fixed size, add to head.
+ */
+ init_chain_block(offset, next, bucket, size);
+ chain_block_buckets[bucket] = offset;
+}
+
+/*
+ * Only the first block in the list can be deleted.
+ *
+ * For the variable size bucket[0], the first block (the largest one) is
+ * returned, broken up and put back into the pool. So if a chain block of
+ * length > MAX_CHAIN_BUCKETS is ever used and zapped, it will just be
+ * queued up after the primordial chain block and never be used until the
+ * hlock entries in the primordial chain block is almost used up. That
+ * causes fragmentation and reduce allocation efficiency. That can be
+ * monitored by looking at the "large chain blocks" number in lockdep_stats.
+ */
+static inline void del_chain_block(int bucket, int size, int next)
+{
+ nr_free_chain_hlocks -= size;
+ chain_block_buckets[bucket] = next;
+
+ if (!bucket)
+ nr_large_chain_blocks--;
+}
+
+static void init_chain_block_buckets(void)
+{
+ int i;
+
+ for (i = 0; i < MAX_CHAIN_BUCKETS; i++)
+ chain_block_buckets[i] = -1;
+
+ add_chain_block(0, ARRAY_SIZE(chain_hlocks));
+}
+
+/*
+ * Return offset of a chain block of the right size or -1 if not found.
+ *
+ * Fairly simple worst-fit allocator with the addition of a number of size
+ * specific free lists.
+ */
+static int alloc_chain_hlocks(int req)
+{
+ int bucket, curr, size;
+
+ /*
+ * We rely on the MSB to act as an escape bit to denote freelist
+ * pointers. Make sure this bit isn't set in 'normal' class_idx usage.
+ */
+ BUILD_BUG_ON((MAX_LOCKDEP_KEYS-1) & CHAIN_BLK_FLAG);
+
+ init_data_structures_once();
+
+ if (nr_free_chain_hlocks < req)
+ return -1;
+
+ /*
+ * We require a minimum of 2 (u16) entries to encode a freelist
+ * 'pointer'.
+ */
+ req = max(req, 2);
+ bucket = size_to_bucket(req);
+ curr = chain_block_buckets[bucket];
+
+ if (bucket) {
+ if (curr >= 0) {
+ del_chain_block(bucket, req, chain_block_next(curr));
+ return curr;
+ }
+ /* Try bucket 0 */
+ curr = chain_block_buckets[0];
+ }
+
+ /*
+ * The variable sized freelist is sorted by size; the first entry is
+ * the largest. Use it if it fits.
+ */
+ if (curr >= 0) {
+ size = chain_block_size(curr);
+ if (likely(size >= req)) {
+ del_chain_block(0, size, chain_block_next(curr));
+ add_chain_block(curr + req, size - req);
+ return curr;
+ }
+ }
+
+ /*
+ * Last resort, split a block in a larger sized bucket.
+ */
+ for (size = MAX_CHAIN_BUCKETS; size > req; size--) {
+ bucket = size_to_bucket(size);
+ curr = chain_block_buckets[bucket];
+ if (curr < 0)
+ continue;
+
+ del_chain_block(bucket, size, chain_block_next(curr));
+ add_chain_block(curr + req, size - req);
+ return curr;
+ }
+
+ return -1;
+}
+
+static inline void free_chain_hlocks(int base, int size)
+{
+ add_chain_block(base, max(size, 2));
+}
struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i)
{
@@ -2803,7 +3070,7 @@ static inline int add_chain_cache(struct task_struct *curr,
* disabled to make this an IRQ-safe lock.. for recursion reasons
* lockdep won't complain about its own locking errors.
*/
- if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+ if (lockdep_assert_locked())
return 0;
chain = alloc_lock_chain();
@@ -2824,15 +3091,8 @@ static inline int add_chain_cache(struct task_struct *curr,
BUILD_BUG_ON((1UL << 6) <= ARRAY_SIZE(curr->held_locks));
BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes));
- if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
- chain->base = nr_chain_hlocks;
- for (j = 0; j < chain->depth - 1; j++, i++) {
- int lock_id = curr->held_locks[i].class_idx;
- chain_hlocks[chain->base + j] = lock_id;
- }
- chain_hlocks[chain->base + j] = class - lock_classes;
- nr_chain_hlocks += chain->depth;
- } else {
+ j = alloc_chain_hlocks(chain->depth);
+ if (j < 0) {
if (!debug_locks_off_graph_unlock())
return 0;
@@ -2841,9 +3101,16 @@ static inline int add_chain_cache(struct task_struct *curr,
return 0;
}
+ chain->base = j;
+ for (j = 0; j < chain->depth - 1; j++, i++) {
+ int lock_id = curr->held_locks[i].class_idx;
+
+ chain_hlocks[chain->base + j] = lock_id;
+ }
+ chain_hlocks[chain->base + j] = class - lock_classes;
hlist_add_head_rcu(&chain->entry, hash_head);
debug_atomic_inc(chain_lookup_misses);
- inc_chains();
+ inc_chains(chain->irq_context);
return 1;
}
@@ -2987,6 +3254,8 @@ static inline int validate_chain(struct task_struct *curr,
{
return 1;
}
+
+static void init_chain_block_buckets(void) { }
#endif /* CONFIG_PROVE_LOCKING */
/*
@@ -3429,9 +3698,9 @@ void lockdep_hardirqs_on(unsigned long ip)
if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
return;
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
__trace_hardirqs_on_caller(ip);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
}
NOKPROBE_SYMBOL(lockdep_hardirqs_on);
@@ -3487,7 +3756,7 @@ void trace_softirqs_on(unsigned long ip)
return;
}
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
/*
* We'll do an OFF -> ON transition:
*/
@@ -3502,7 +3771,7 @@ void trace_softirqs_on(unsigned long ip)
*/
if (curr->hardirqs_enabled)
mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
}
/*
@@ -3596,7 +3865,8 @@ lock_used:
static inline unsigned int task_irq_context(struct task_struct *task)
{
- return 2 * !!task->hardirq_context + !!task->softirq_context;
+ return LOCK_CHAIN_HARDIRQ_CONTEXT * !!task->hardirq_context +
+ LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context;
}
static int separate_irq_context(struct task_struct *curr,
@@ -3682,6 +3952,113 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
return ret;
}
+static int
+print_lock_invalid_wait_context(struct task_struct *curr,
+ struct held_lock *hlock)
+{
+ if (!debug_locks_off())
+ return 0;
+ if (debug_locks_silent)
+ return 0;
+
+ pr_warn("\n");
+ pr_warn("=============================\n");
+ pr_warn("[ BUG: Invalid wait context ]\n");
+ print_kernel_ident();
+ pr_warn("-----------------------------\n");
+
+ pr_warn("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr));
+ print_lock(hlock);
+
+ pr_warn("other info that might help us debug this:\n");
+ lockdep_print_held_locks(curr);
+
+ pr_warn("stack backtrace:\n");
+ dump_stack();
+
+ return 0;
+}
+
+/*
+ * Verify the wait_type context.
+ *
+ * This check validates we takes locks in the right wait-type order; that is it
+ * ensures that we do not take mutexes inside spinlocks and do not attempt to
+ * acquire spinlocks inside raw_spinlocks and the sort.
+ *
+ * The entire thing is slightly more complex because of RCU, RCU is a lock that
+ * can be taken from (pretty much) any context but also has constraints.
+ * However when taken in a stricter environment the RCU lock does not loosen
+ * the constraints.
+ *
+ * Therefore we must look for the strictest environment in the lock stack and
+ * compare that to the lock we're trying to acquire.
+ */
+static int check_wait_context(struct task_struct *curr, struct held_lock *next)
+{
+ short next_inner = hlock_class(next)->wait_type_inner;
+ short next_outer = hlock_class(next)->wait_type_outer;
+ short curr_inner;
+ int depth;
+
+ if (!curr->lockdep_depth || !next_inner || next->trylock)
+ return 0;
+
+ if (!next_outer)
+ next_outer = next_inner;
+
+ /*
+ * Find start of current irq_context..
+ */
+ for (depth = curr->lockdep_depth - 1; depth >= 0; depth--) {
+ struct held_lock *prev = curr->held_locks + depth;
+ if (prev->irq_context != next->irq_context)
+ break;
+ }
+ depth++;
+
+ /*
+ * Set appropriate wait type for the context; for IRQs we have to take
+ * into account force_irqthread as that is implied by PREEMPT_RT.
+ */
+ if (curr->hardirq_context) {
+ /*
+ * Check if force_irqthreads will run us threaded.
+ */
+ if (curr->hardirq_threaded || curr->irq_config)
+ curr_inner = LD_WAIT_CONFIG;
+ else
+ curr_inner = LD_WAIT_SPIN;
+ } else if (curr->softirq_context) {
+ /*
+ * Softirqs are always threaded.
+ */
+ curr_inner = LD_WAIT_CONFIG;
+ } else {
+ curr_inner = LD_WAIT_MAX;
+ }
+
+ for (; depth < curr->lockdep_depth; depth++) {
+ struct held_lock *prev = curr->held_locks + depth;
+ short prev_inner = hlock_class(prev)->wait_type_inner;
+
+ if (prev_inner) {
+ /*
+ * We can have a bigger inner than a previous one
+ * when outer is smaller than inner, as with RCU.
+ *
+ * Also due to trylocks.
+ */
+ curr_inner = min(curr_inner, prev_inner);
+ }
+ }
+
+ if (next_outer > curr_inner)
+ return print_lock_invalid_wait_context(curr, next);
+
+ return 0;
+}
+
#else /* CONFIG_PROVE_LOCKING */
static inline int
@@ -3701,13 +4078,20 @@ static inline int separate_irq_context(struct task_struct *curr,
return 0;
}
+static inline int check_wait_context(struct task_struct *curr,
+ struct held_lock *next)
+{
+ return 0;
+}
+
#endif /* CONFIG_PROVE_LOCKING */
/*
* Initialize a lock instance's lock-class mapping info:
*/
-void lockdep_init_map(struct lockdep_map *lock, const char *name,
- struct lock_class_key *key, int subclass)
+void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
+ struct lock_class_key *key, int subclass,
+ short inner, short outer)
{
int i;
@@ -3728,6 +4112,9 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
lock->name = name;
+ lock->wait_type_outer = outer;
+ lock->wait_type_inner = inner;
+
/*
* No key, no joy, we need to hash something.
*/
@@ -3755,13 +4142,13 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
return;
raw_local_irq_save(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
register_lock_class(lock, subclass, 1);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
}
-EXPORT_SYMBOL_GPL(lockdep_init_map);
+EXPORT_SYMBOL_GPL(lockdep_init_map_waits);
struct lock_class_key __lockdep_no_validate__;
EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
@@ -3862,7 +4249,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
class_idx = class - lock_classes;
- if (depth) {
+ if (depth) { /* we're holding locks */
hlock = curr->held_locks + depth - 1;
if (hlock->class_idx == class_idx && nest_lock) {
if (!references)
@@ -3904,6 +4291,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
#endif
hlock->pin_count = pin_count;
+ if (check_wait_context(curr, hlock))
+ return 0;
+
/* Initialize the lock usage bit */
if (!mark_usage(curr, hlock, check))
return 0;
@@ -4139,7 +4529,9 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
return 0;
}
- lockdep_init_map(lock, name, key, 0);
+ lockdep_init_map_waits(lock, name, key, 0,
+ lock->wait_type_inner,
+ lock->wait_type_outer);
class = register_lock_class(lock, subclass, 0);
hlock->class_idx = class - lock_classes;
@@ -4437,11 +4829,11 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
return;
raw_local_irq_save(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
check_flags(flags);
if (__lock_set_class(lock, name, key, subclass, ip))
check_chain_key(current);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_set_class);
@@ -4454,15 +4846,45 @@ void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
return;
raw_local_irq_save(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
check_flags(flags);
if (__lock_downgrade(lock, ip))
check_chain_key(current);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_downgrade);
+/* NMI context !!! */
+static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock, int subclass)
+{
+#ifdef CONFIG_PROVE_LOCKING
+ struct lock_class *class = look_up_lock_class(lock, subclass);
+
+ /* if it doesn't have a class (yet), it certainly hasn't been used yet */
+ if (!class)
+ return;
+
+ if (!(class->usage_mask & LOCK_USED))
+ return;
+
+ hlock->class_idx = class - lock_classes;
+
+ print_usage_bug(current, hlock, LOCK_USED, LOCK_USAGE_STATES);
+#endif
+}
+
+static bool lockdep_nmi(void)
+{
+ if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+ return false;
+
+ if (!in_nmi())
+ return false;
+
+ return true;
+}
+
/*
* We are not always called with irqs disabled - do that here,
* and also avoid lockdep recursion:
@@ -4473,17 +4895,34 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
{
unsigned long flags;
- if (unlikely(current->lockdep_recursion))
+ if (unlikely(current->lockdep_recursion)) {
+ /* XXX allow trylock from NMI ?!? */
+ if (lockdep_nmi() && !trylock) {
+ struct held_lock hlock;
+
+ hlock.acquire_ip = ip;
+ hlock.instance = lock;
+ hlock.nest_lock = nest_lock;
+ hlock.irq_context = 2; // XXX
+ hlock.trylock = trylock;
+ hlock.read = read;
+ hlock.check = check;
+ hlock.hardirqs_off = true;
+ hlock.references = 0;
+
+ verify_lock_unused(lock, &hlock, subclass);
+ }
return;
+ }
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
__lock_acquire(lock, subclass, trylock, read, check,
irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_acquire);
@@ -4497,11 +4936,11 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
trace_lock_release(lock, ip);
if (__lock_release(lock, ip))
check_chain_key(current);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_release);
@@ -4517,9 +4956,9 @@ int lock_is_held_type(const struct lockdep_map *lock, int read)
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
ret = __lock_is_held(lock, read);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
return ret;
@@ -4538,9 +4977,9 @@ struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
cookie = __lock_pin_lock(lock);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
return cookie;
@@ -4557,9 +4996,9 @@ void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
__lock_repin_lock(lock, cookie);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_repin_lock);
@@ -4574,9 +5013,9 @@ void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
__lock_unpin_lock(lock, cookie);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_unpin_lock);
@@ -4712,10 +5151,10 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
trace_lock_contended(lock, ip);
__lock_contended(lock, ip);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_contended);
@@ -4732,9 +5171,9 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
raw_local_irq_save(flags);
check_flags(flags);
- current->lockdep_recursion = 1;
+ current->lockdep_recursion++;
__lock_acquired(lock, ip);
- current->lockdep_recursion = 0;
+ lockdep_recursion_finish();
raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(lock_acquired);
@@ -4768,57 +5207,33 @@ static void remove_class_from_lock_chain(struct pending_free *pf,
struct lock_class *class)
{
#ifdef CONFIG_PROVE_LOCKING
- struct lock_chain *new_chain;
- u64 chain_key;
int i;
for (i = chain->base; i < chain->base + chain->depth; i++) {
if (chain_hlocks[i] != class - lock_classes)
continue;
- /* The code below leaks one chain_hlock[] entry. */
- if (--chain->depth > 0) {
- memmove(&chain_hlocks[i], &chain_hlocks[i + 1],
- (chain->base + chain->depth - i) *
- sizeof(chain_hlocks[0]));
- }
/*
* Each lock class occurs at most once in a lock chain so once
* we found a match we can break out of this loop.
*/
- goto recalc;
+ goto free_lock_chain;
}
/* Since the chain has not been modified, return. */
return;
-recalc:
- chain_key = INITIAL_CHAIN_KEY;
- for (i = chain->base; i < chain->base + chain->depth; i++)
- chain_key = iterate_chain_key(chain_key, chain_hlocks[i]);
- if (chain->depth && chain->chain_key == chain_key)
- return;
+free_lock_chain:
+ free_chain_hlocks(chain->base, chain->depth);
/* Overwrite the chain key for concurrent RCU readers. */
- WRITE_ONCE(chain->chain_key, chain_key);
+ WRITE_ONCE(chain->chain_key, INITIAL_CHAIN_KEY);
+ dec_chains(chain->irq_context);
+
/*
* Note: calling hlist_del_rcu() from inside a
* hlist_for_each_entry_rcu() loop is safe.
*/
hlist_del_rcu(&chain->entry);
__set_bit(chain - lock_chains, pf->lock_chains_being_freed);
- if (chain->depth == 0)
- return;
- /*
- * If the modified lock chain matches an existing lock chain, drop
- * the modified lock chain.
- */
- if (lookup_chain_cache(chain_key))
- return;
- new_chain = alloc_lock_chain();
- if (WARN_ON_ONCE(!new_chain)) {
- debug_locks_off();
- return;
- }
- *new_chain = *chain;
- hlist_add_head_rcu(&new_chain->entry, chainhashentry(chain_key));
+ nr_zapped_lock_chains++;
#endif
}
@@ -4874,6 +5289,7 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
}
remove_class_from_lock_chains(pf, class);
+ nr_zapped_classes++;
}
static void reinit_class(struct lock_class *class)
@@ -4958,8 +5374,7 @@ static void free_zapped_rcu(struct rcu_head *ch)
return;
raw_local_irq_save(flags);
- arch_spin_lock(&lockdep_lock);
- current->lockdep_recursion = 1;
+ lockdep_lock();
/* closed head */
pf = delayed_free.pf + (delayed_free.index ^ 1);
@@ -4971,8 +5386,7 @@ static void free_zapped_rcu(struct rcu_head *ch)
*/
call_rcu_zapped(delayed_free.pf + delayed_free.index);
- current->lockdep_recursion = 0;
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
raw_local_irq_restore(flags);
}
@@ -5017,13 +5431,11 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
init_data_structures_once();
raw_local_irq_save(flags);
- arch_spin_lock(&lockdep_lock);
- current->lockdep_recursion = 1;
+ lockdep_lock();
pf = get_pending_free();
__lockdep_free_key_range(pf, start, size);
call_rcu_zapped(pf);
- current->lockdep_recursion = 0;
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
raw_local_irq_restore(flags);
/*
@@ -5045,10 +5457,10 @@ static void lockdep_free_key_range_imm(void *start, unsigned long size)
init_data_structures_once();
raw_local_irq_save(flags);
- arch_spin_lock(&lockdep_lock);
+ lockdep_lock();
__lockdep_free_key_range(pf, start, size);
__free_zapped_classes(pf);
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
raw_local_irq_restore(flags);
}
@@ -5144,10 +5556,10 @@ static void lockdep_reset_lock_imm(struct lockdep_map *lock)
unsigned long flags;
raw_local_irq_save(flags);
- arch_spin_lock(&lockdep_lock);
+ lockdep_lock();
__lockdep_reset_lock(pf, lock);
__free_zapped_classes(pf);
- arch_spin_unlock(&lockdep_lock);
+ lockdep_unlock();
raw_local_irq_restore(flags);
}
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 18d85aebbb57..baca699b94e9 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -106,6 +106,12 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
#define STACK_TRACE_HASH_SIZE 16384
#endif
+/*
+ * Bit definitions for lock_chain.irq_context
+ */
+#define LOCK_CHAIN_SOFTIRQ_CONTEXT (1 << 0)
+#define LOCK_CHAIN_HARDIRQ_CONTEXT (1 << 1)
+
#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS)
#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
@@ -124,17 +130,21 @@ extern const char *__get_key_name(const struct lockdep_subclass_key *key,
struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i);
extern unsigned long nr_lock_classes;
+extern unsigned long nr_zapped_classes;
+extern unsigned long nr_zapped_lock_chains;
extern unsigned long nr_list_entries;
long lockdep_next_lockchain(long i);
unsigned long lock_chain_count(void);
-extern int nr_chain_hlocks;
extern unsigned long nr_stack_trace_entries;
extern unsigned int nr_hardirq_chains;
extern unsigned int nr_softirq_chains;
extern unsigned int nr_process_chains;
-extern unsigned int max_lockdep_depth;
+extern unsigned int nr_free_chain_hlocks;
+extern unsigned int nr_lost_chain_hlocks;
+extern unsigned int nr_large_chain_blocks;
+extern unsigned int max_lockdep_depth;
extern unsigned int max_bfs_queue_depth;
#ifdef CONFIG_PROVE_LOCKING
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 231684cfc5ae..5525cd3ba0c8 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -128,15 +128,22 @@ static int lc_show(struct seq_file *m, void *v)
struct lock_chain *chain = v;
struct lock_class *class;
int i;
+ static const char * const irq_strs[] = {
+ [0] = "0",
+ [LOCK_CHAIN_HARDIRQ_CONTEXT] = "hardirq",
+ [LOCK_CHAIN_SOFTIRQ_CONTEXT] = "softirq",
+ [LOCK_CHAIN_SOFTIRQ_CONTEXT|
+ LOCK_CHAIN_HARDIRQ_CONTEXT] = "hardirq|softirq",
+ };
if (v == SEQ_START_TOKEN) {
- if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)
+ if (!nr_free_chain_hlocks)
seq_printf(m, "(buggered) ");
seq_printf(m, "all lock chains:\n");
return 0;
}
- seq_printf(m, "irq_context: %d\n", chain->irq_context);
+ seq_printf(m, "irq_context: %s\n", irq_strs[chain->irq_context]);
for (i = 0; i < chain->depth; i++) {
class = lock_chain_get_class(chain, i);
@@ -271,8 +278,12 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
#ifdef CONFIG_PROVE_LOCKING
seq_printf(m, " dependency chains: %11lu [max: %lu]\n",
lock_chain_count(), MAX_LOCKDEP_CHAINS);
- seq_printf(m, " dependency chain hlocks: %11d [max: %lu]\n",
- nr_chain_hlocks, MAX_LOCKDEP_CHAIN_HLOCKS);
+ seq_printf(m, " dependency chain hlocks used: %11lu [max: %lu]\n",
+ MAX_LOCKDEP_CHAIN_HLOCKS -
+ (nr_free_chain_hlocks + nr_lost_chain_hlocks),
+ MAX_LOCKDEP_CHAIN_HLOCKS);
+ seq_printf(m, " dependency chain hlocks lost: %11u\n",
+ nr_lost_chain_hlocks);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -336,6 +347,18 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
seq_printf(m, " debug_locks: %11u\n",
debug_locks);
+ /*
+ * Zappped classes and lockdep data buffers reuse statistics.
+ */
+ seq_puts(m, "\n");
+ seq_printf(m, " zapped classes: %11lu\n",
+ nr_zapped_classes);
+#ifdef CONFIG_PROVE_LOCKING
+ seq_printf(m, " zapped lock chains: %11lu\n",
+ nr_zapped_lock_chains);
+ seq_printf(m, " large chain blocks: %11u\n",
+ nr_large_chain_blocks);
+#endif
return 0;
}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 771d4ca96dda..a7276aaf2abc 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -85,7 +85,7 @@ void debug_mutex_init(struct mutex *lock, const char *name,
* Make sure we are not reinitializing a held lock:
*/
debug_check_no_locks_freed((void *)lock, sizeof(*lock));
- lockdep_init_map(&lock->dep_map, name, key, 0);
+ lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP);
#endif
lock->magic = lock;
}
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 364d38a0c444..a008a1ba21a7 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -1,27 +1,29 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/atomic.h>
-#include <linux/rwsem.h>
#include <linux/percpu.h>
+#include <linux/wait.h>
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
+#include <linux/sched/task.h>
#include <linux/errno.h>
-#include "rwsem.h"
-
int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
- const char *name, struct lock_class_key *rwsem_key)
+ const char *name, struct lock_class_key *key)
{
sem->read_count = alloc_percpu(int);
if (unlikely(!sem->read_count))
return -ENOMEM;
- /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
rcu_sync_init(&sem->rss);
- __init_rwsem(&sem->rw_sem, name, rwsem_key);
rcuwait_init(&sem->writer);
- sem->readers_block = 0;
+ init_waitqueue_head(&sem->waiters);
+ atomic_set(&sem->block, 0);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+ lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
return 0;
}
EXPORT_SYMBOL_GPL(__percpu_init_rwsem);
@@ -41,73 +43,139 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *sem)
}
EXPORT_SYMBOL_GPL(percpu_free_rwsem);
-int __percpu_down_read(struct percpu_rw_semaphore *sem, int try)
+static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
{
+ __this_cpu_inc(*sem->read_count);
+
/*
* Due to having preemption disabled the decrement happens on
* the same CPU as the increment, avoiding the
* increment-on-one-CPU-and-decrement-on-another problem.
*
- * If the reader misses the writer's assignment of readers_block, then
- * the writer is guaranteed to see the reader's increment.
+ * If the reader misses the writer's assignment of sem->block, then the
+ * writer is guaranteed to see the reader's increment.
*
* Conversely, any readers that increment their sem->read_count after
- * the writer looks are guaranteed to see the readers_block value,
- * which in turn means that they are guaranteed to immediately
- * decrement their sem->read_count, so that it doesn't matter that the
- * writer missed them.
+ * the writer looks are guaranteed to see the sem->block value, which
+ * in turn means that they are guaranteed to immediately decrement
+ * their sem->read_count, so that it doesn't matter that the writer
+ * missed them.
*/
smp_mb(); /* A matches D */
/*
- * If !readers_block the critical section starts here, matched by the
+ * If !sem->block the critical section starts here, matched by the
* release in percpu_up_write().
*/
- if (likely(!smp_load_acquire(&sem->readers_block)))
+ if (likely(!atomic_read_acquire(&sem->block)))
+ return true;
+
+ __this_cpu_dec(*sem->read_count);
+
+ /* Prod writer to re-evaluate readers_active_check() */
+ rcuwait_wake_up(&sem->writer);
+
+ return false;
+}
+
+static inline bool __percpu_down_write_trylock(struct percpu_rw_semaphore *sem)
+{
+ if (atomic_read(&sem->block))
+ return false;
+
+ return atomic_xchg(&sem->block, 1) == 0;
+}
+
+static bool __percpu_rwsem_trylock(struct percpu_rw_semaphore *sem, bool reader)
+{
+ if (reader) {
+ bool ret;
+
+ preempt_disable();
+ ret = __percpu_down_read_trylock(sem);
+ preempt_enable();
+
+ return ret;
+ }
+ return __percpu_down_write_trylock(sem);
+}
+
+/*
+ * The return value of wait_queue_entry::func means:
+ *
+ * <0 - error, wakeup is terminated and the error is returned
+ * 0 - no wakeup, a next waiter is tried
+ * >0 - woken, if EXCLUSIVE, counted towards @nr_exclusive.
+ *
+ * We use EXCLUSIVE for both readers and writers to preserve FIFO order,
+ * and play games with the return value to allow waking multiple readers.
+ *
+ * Specifically, we wake readers until we've woken a single writer, or until a
+ * trylock fails.
+ */
+static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry,
+ unsigned int mode, int wake_flags,
+ void *key)
+{
+ struct task_struct *p = get_task_struct(wq_entry->private);
+ bool reader = wq_entry->flags & WQ_FLAG_CUSTOM;
+ struct percpu_rw_semaphore *sem = key;
+
+ /* concurrent against percpu_down_write(), can get stolen */
+ if (!__percpu_rwsem_trylock(sem, reader))
return 1;
- /*
- * Per the above comment; we still have preemption disabled and
- * will thus decrement on the same CPU as we incremented.
- */
- __percpu_up_read(sem);
+ list_del_init(&wq_entry->entry);
+ smp_store_release(&wq_entry->private, NULL);
- if (try)
- return 0;
+ wake_up_process(p);
+ put_task_struct(p);
- /*
- * We either call schedule() in the wait, or we'll fall through
- * and reschedule on the preempt_enable() in percpu_down_read().
- */
- preempt_enable_no_resched();
+ return !reader; /* wake (readers until) 1 writer */
+}
+
+static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
+{
+ DEFINE_WAIT_FUNC(wq_entry, percpu_rwsem_wake_function);
+ bool wait;
+ spin_lock_irq(&sem->waiters.lock);
/*
- * Avoid lockdep for the down/up_read() we already have them.
+ * Serialize against the wakeup in percpu_up_write(), if we fail
+ * the trylock, the wakeup must see us on the list.
*/
- __down_read(&sem->rw_sem);
- this_cpu_inc(*sem->read_count);
- __up_read(&sem->rw_sem);
+ wait = !__percpu_rwsem_trylock(sem, reader);
+ if (wait) {
+ wq_entry.flags |= WQ_FLAG_EXCLUSIVE | reader * WQ_FLAG_CUSTOM;
+ __add_wait_queue_entry_tail(&sem->waiters, &wq_entry);
+ }
+ spin_unlock_irq(&sem->waiters.lock);
- preempt_disable();
- return 1;
+ while (wait) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (!smp_load_acquire(&wq_entry.private))
+ break;
+ schedule();
+ }
+ __set_current_state(TASK_RUNNING);
}
-EXPORT_SYMBOL_GPL(__percpu_down_read);
-void __percpu_up_read(struct percpu_rw_semaphore *sem)
+bool __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
{
- smp_mb(); /* B matches C */
- /*
- * In other words, if they see our decrement (presumably to aggregate
- * zero, as that is the only time it matters) they will also see our
- * critical section.
- */
- __this_cpu_dec(*sem->read_count);
+ if (__percpu_down_read_trylock(sem))
+ return true;
- /* Prod writer to recheck readers_active */
- rcuwait_wake_up(&sem->writer);
+ if (try)
+ return false;
+
+ preempt_enable();
+ percpu_rwsem_wait(sem, /* .reader = */ true);
+ preempt_disable();
+
+ return true;
}
-EXPORT_SYMBOL_GPL(__percpu_up_read);
+EXPORT_SYMBOL_GPL(__percpu_down_read);
#define per_cpu_sum(var) \
({ \
@@ -124,6 +192,8 @@ EXPORT_SYMBOL_GPL(__percpu_up_read);
* zero. If this sum is zero, then it is stable due to the fact that if any
* newly arriving readers increment a given counter, they will immediately
* decrement that same counter.
+ *
+ * Assumes sem->block is set.
*/
static bool readers_active_check(struct percpu_rw_semaphore *sem)
{
@@ -142,32 +212,36 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem)
void percpu_down_write(struct percpu_rw_semaphore *sem)
{
+ might_sleep();
+ rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
+
/* Notify readers to take the slow path. */
rcu_sync_enter(&sem->rss);
- down_write(&sem->rw_sem);
-
/*
- * Notify new readers to block; up until now, and thus throughout the
- * longish rcu_sync_enter() above, new readers could still come in.
+ * Try set sem->block; this provides writer-writer exclusion.
+ * Having sem->block set makes new readers block.
*/
- WRITE_ONCE(sem->readers_block, 1);
+ if (!__percpu_down_write_trylock(sem))
+ percpu_rwsem_wait(sem, /* .reader = */ false);
- smp_mb(); /* D matches A */
+ /* smp_mb() implied by __percpu_down_write_trylock() on success -- D matches A */
/*
- * If they don't see our writer of readers_block, then we are
- * guaranteed to see their sem->read_count increment, and therefore
- * will wait for them.
+ * If they don't see our store of sem->block, then we are guaranteed to
+ * see their sem->read_count increment, and therefore will wait for
+ * them.
*/
- /* Wait for all now active readers to complete. */
- rcuwait_wait_event(&sem->writer, readers_active_check(sem));
+ /* Wait for all active readers to complete. */
+ rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL_GPL(percpu_down_write);
void percpu_up_write(struct percpu_rw_semaphore *sem)
{
+ rwsem_release(&sem->dep_map, _RET_IP_);
+
/*
* Signal the writer is done, no fast path yet.
*
@@ -178,12 +252,12 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
* Therefore we force it through the slow path which guarantees an
* acquire and thereby guarantees the critical section's consistency.
*/
- smp_store_release(&sem->readers_block, 0);
+ atomic_set_release(&sem->block, 0);
/*
- * Release the write lock, this will allow readers back in the game.
+ * Prod any pending reader/writer to make progress.
*/
- up_write(&sem->rw_sem);
+ __wake_up(&sem->waiters, TASK_NORMAL, 1, sem);
/*
* Once this completes (at least one RCU-sched grace period hence) the
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 0d9b6be9ecc8..f11b9bd3431d 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -28,7 +28,6 @@
#include <linux/rwsem.h>
#include <linux/atomic.h>
-#include "rwsem.h"
#include "lock_events.h"
/*
@@ -329,7 +328,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
* Make sure we are not reinitializing a held semaphore:
*/
debug_check_no_locks_freed((void *)sem, sizeof(*sem));
- lockdep_init_map(&sem->dep_map, name, key, 0);
+ lockdep_init_map_wait(&sem->dep_map, name, key, 0, LD_WAIT_SLEEP);
#endif
#ifdef CONFIG_DEBUG_RWSEMS
sem->magic = sem;
@@ -660,8 +659,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem,
unsigned long flags;
bool ret = true;
- BUILD_BUG_ON(!(RWSEM_OWNER_UNKNOWN & RWSEM_NONSPINNABLE));
-
if (need_resched()) {
lockevent_inc(rwsem_opt_fail);
return false;
@@ -1338,7 +1335,7 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
/*
* lock for reading
*/
-inline void __down_read(struct rw_semaphore *sem)
+static inline void __down_read(struct rw_semaphore *sem)
{
if (!rwsem_read_trylock(sem)) {
rwsem_down_read_slowpath(sem, TASK_UNINTERRUPTIBLE);
@@ -1426,7 +1423,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
/*
* unlock after reading
*/
-inline void __up_read(struct rw_semaphore *sem)
+static inline void __up_read(struct rw_semaphore *sem)
{
long tmp;
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 2534ce49f648..e69de29bb2d1 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef __INTERNAL_RWSEM_H
-#define __INTERNAL_RWSEM_H
-#include <linux/rwsem.h>
-
-extern void __down_read(struct rw_semaphore *sem);
-extern void __up_read(struct rw_semaphore *sem);
-
-#endif /* __INTERNAL_RWSEM_H */
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 472dd462a40c..b9d93087ee66 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -14,14 +14,14 @@
#include <linux/export.h>
void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
- struct lock_class_key *key)
+ struct lock_class_key *key, short inner)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* Make sure we are not reinitializing a held lock:
*/
debug_check_no_locks_freed((void *)lock, sizeof(*lock));
- lockdep_init_map(&lock->dep_map, name, key, 0);
+ lockdep_init_map_wait(&lock->dep_map, name, key, 0, inner);
#endif
lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
lock->magic = SPINLOCK_MAGIC;
@@ -39,7 +39,7 @@ void __rwlock_init(rwlock_t *lock, const char *name,
* Make sure we are not reinitializing a held lock:
*/
debug_check_no_locks_freed((void *)lock, sizeof(*lock));
- lockdep_init_map(&lock->dep_map, name, key, 0);
+ lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_CONFIG);
#endif
lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED;
lock->magic = RWLOCK_MAGIC;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 550193a9ce76..06548e2ebb72 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1124,6 +1124,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
!rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
+ atomic_set(&rdp->rcu_iw.flags, IRQ_WORK_HARD_IRQ);
rdp->rcu_iw_pending = true;
rdp->rcu_iw_gp_seq = rnp->gp_seq;
irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index a4ad8e0406c7..28a8bdc5072f 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -239,18 +239,30 @@ core_initcall(rcu_set_runtime_mode);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
-struct lockdep_map rcu_lock_map =
- STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
+struct lockdep_map rcu_lock_map = {
+ .name = "rcu_read_lock",
+ .key = &rcu_lock_key,
+ .wait_type_outer = LD_WAIT_FREE,
+ .wait_type_inner = LD_WAIT_CONFIG, /* XXX PREEMPT_RCU ? */
+};
EXPORT_SYMBOL_GPL(rcu_lock_map);
static struct lock_class_key rcu_bh_lock_key;
-struct lockdep_map rcu_bh_lock_map =
- STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);
+struct lockdep_map rcu_bh_lock_map = {
+ .name = "rcu_read_lock_bh",
+ .key = &rcu_bh_lock_key,
+ .wait_type_outer = LD_WAIT_FREE,
+ .wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_LOCK also makes BH preemptible */
+};
EXPORT_SYMBOL_GPL(rcu_bh_lock_map);
static struct lock_class_key rcu_sched_lock_key;
-struct lockdep_map rcu_sched_lock_map =
- STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
+struct lockdep_map rcu_sched_lock_map = {
+ .name = "rcu_read_lock_sched",
+ .key = &rcu_sched_lock_key,
+ .wait_type_outer = LD_WAIT_FREE,
+ .wait_type_inner = LD_WAIT_SPIN,
+};
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
static struct lock_class_key rcu_callback_key;
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a1ad5b7d5521..a778554f9dad 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -29,12 +29,12 @@ void complete(struct completion *x)
{
unsigned long flags;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
if (x->done != UINT_MAX)
x->done++;
- __wake_up_locked(&x->wait, TASK_NORMAL, 1);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ swake_up_locked(&x->wait);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);
@@ -58,10 +58,12 @@ void complete_all(struct completion *x)
{
unsigned long flags;
- spin_lock_irqsave(&x->wait.lock, flags);
+ lockdep_assert_RT_in_threaded_ctx();
+
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
x->done = UINT_MAX;
- __wake_up_locked(&x->wait, TASK_NORMAL, 0);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ swake_up_all_locked(&x->wait);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);
@@ -70,20 +72,20 @@ do_wait_for_common(struct completion *x,
long (*action)(long), long timeout, int state)
{
if (!x->done) {
- DECLARE_WAITQUEUE(wait, current);
+ DECLARE_SWAITQUEUE(wait);
- __add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
do {
if (signal_pending_state(state, current)) {
timeout = -ERESTARTSYS;
break;
}
+ __prepare_to_swait(&x->wait, &wait);
__set_current_state(state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);
timeout = action(timeout);
- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
} while (!x->done && timeout);
- __remove_wait_queue(&x->wait, &wait);
+ __finish_swait(&x->wait, &wait);
if (!x->done)
return timeout;
}
@@ -100,9 +102,9 @@ __wait_for_common(struct completion *x,
complete_acquire(x);
- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
timeout = do_wait_for_common(x, action, timeout, state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);
complete_release(x);
@@ -291,12 +293,12 @@ bool try_wait_for_completion(struct completion *x)
if (!READ_ONCE(x->done))
return false;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
if (!x->done)
ret = false;
else if (x->done != UINT_MAX)
x->done--;
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return ret;
}
EXPORT_SYMBOL(try_wait_for_completion);
@@ -322,8 +324,8 @@ bool completion_done(struct completion *x)
* otherwise we can end up freeing the completion before complete()
* is done referencing it.
*/
- spin_lock_irqsave(&x->wait.lock, flags);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return true;
}
EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9ea647835fd6..fdc77e796324 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2492,3 +2492,6 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
return true;
}
#endif
+
+void swake_up_all_locked(struct swait_queue_head *q);
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index e83a3f8449f6..e1c655f928c7 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,6 +32,19 @@ void swake_up_locked(struct swait_queue_head *q)
}
EXPORT_SYMBOL(swake_up_locked);
+/*
+ * Wake up all waiters. This is an interface which is solely exposed for
+ * completions and not for general usage.
+ *
+ * It is intentionally different from swake_up_all() to allow usage from
+ * hard interrupt context and interrupt disabled regions.
+ */
+void swake_up_all_locked(struct swait_queue_head *q)
+{
+ while (!list_empty(&q->task_list))
+ swake_up_locked(q);
+}
+
void swake_up_one(struct swait_queue_head *q)
{
unsigned long flags;
@@ -69,7 +82,7 @@ void swake_up_all(struct swait_queue_head *q)
}
EXPORT_SYMBOL(swake_up_all);
-static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
{
wait->task = current;
if (list_empty(&wait->task_list))
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3a609e7344f3..8cce72501aea 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1404,7 +1404,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0;
base += hrtimer_clockid_to_base(clock_id);
timer->is_soft = softtimer;
- timer->is_hard = !softtimer;
+ timer->is_hard = !!(mode & HRTIMER_MODE_HARD);
timer->base = &cpu_base->clock_base[base];
timerqueue_init(&timer->node);
}
@@ -1514,7 +1514,11 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
*/
raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
trace_hrtimer_expire_entry(timer, now);
+ lockdep_hrtimer_enter(timer);
+
restart = fn(timer);
+
+ lockdep_hrtimer_exit(timer);
trace_hrtimer_expire_exit(timer);
raw_spin_lock_irq(&cpu_base->lock);
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index d23b434c2ca7..eddcf4970444 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -58,7 +58,8 @@ static struct clocksource clocksource_jiffies = {
.max_cycles = 10,
};
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
+__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock);
+__cacheline_aligned_in_smp seqcount_t jiffies_seq;
#if (BITS_PER_LONG < 64)
u64 get_jiffies_64(void)
@@ -67,9 +68,9 @@ u64 get_jiffies_64(void)
u64 ret;
do {
- seq = read_seqbegin(&jiffies_lock);
+ seq = read_seqcount_begin(&jiffies_seq);
ret = jiffies_64;
- } while (read_seqretry(&jiffies_lock, seq));
+ } while (read_seqcount_retry(&jiffies_seq, seq));
return ret;
}
EXPORT_SYMBOL(get_jiffies_64);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 8ff6da77a01f..2c48a7233b19 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1126,8 +1126,11 @@ void run_posix_cpu_timers(void)
if (!fastpath_timer_check(tsk))
return;
- if (!lock_task_sighand(tsk, &flags))
+ lockdep_posixtimer_enter();
+ if (!lock_task_sighand(tsk, &flags)) {
+ lockdep_posixtimer_exit();
return;
+ }
/*
* Here we take off tsk->signal->cpu_timers[N] and
* tsk->cpu_timers[N] all the timers that are firing, and
@@ -1169,6 +1172,7 @@ void run_posix_cpu_timers(void)
cpu_timer_fire(timer);
spin_unlock(&timer->it_lock);
}
+ lockdep_posixtimer_exit();
}
/*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 7e5d3524e924..6c9c342dd0e5 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -84,13 +84,15 @@ int tick_is_oneshot_available(void)
static void tick_periodic(int cpu)
{
if (tick_do_timer_cpu == cpu) {
- write_seqlock(&jiffies_lock);
+ raw_spin_lock(&jiffies_lock);
+ write_seqcount_begin(&jiffies_seq);
/* Keep track of the next tick event */
tick_next_period = ktime_add(tick_next_period, tick_period);
do_timer(1);
- write_sequnlock(&jiffies_lock);
+ write_seqcount_end(&jiffies_seq);
+ raw_spin_unlock(&jiffies_lock);
update_wall_time();
}
@@ -162,9 +164,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
ktime_t next;
do {
- seq = read_seqbegin(&jiffies_lock);
+ seq = read_seqcount_begin(&jiffies_seq);
next = tick_next_period;
- } while (read_seqretry(&jiffies_lock, seq));
+ } while (read_seqcount_retry(&jiffies_seq, seq));
clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a792d21cac64..3e2dc9b8858c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -65,7 +65,8 @@ static void tick_do_update_jiffies64(ktime_t now)
return;
/* Reevaluate with jiffies_lock held */
- write_seqlock(&jiffies_lock);
+ raw_spin_lock(&jiffies_lock);
+ write_seqcount_begin(&jiffies_seq);
delta = ktime_sub(now, last_jiffies_update);
if (delta >= tick_period) {
@@ -91,10 +92,12 @@ static void tick_do_update_jiffies64(ktime_t now)
/* Keep the tick_next_period variable up to date */
tick_next_period = ktime_add(last_jiffies_update, tick_period);
} else {
- write_sequnlock(&jiffies_lock);
+ write_seqcount_end(&jiffies_seq);
+ raw_spin_unlock(&jiffies_lock);
return;
}
- write_sequnlock(&jiffies_lock);
+ write_seqcount_end(&jiffies_seq);
+ raw_spin_unlock(&jiffies_lock);
update_wall_time();
}
@@ -105,12 +108,14 @@ static ktime_t tick_init_jiffy_update(void)
{
ktime_t period;
- write_seqlock(&jiffies_lock);
+ raw_spin_lock(&jiffies_lock);
+ write_seqcount_begin(&jiffies_seq);
/* Did we start the jiffies update yet ? */
if (last_jiffies_update == 0)
last_jiffies_update = tick_next_period;
period = last_jiffies_update;
- write_sequnlock(&jiffies_lock);
+ write_seqcount_end(&jiffies_seq);
+ raw_spin_unlock(&jiffies_lock);
return period;
}
@@ -240,6 +245,7 @@ static void nohz_full_kick_func(struct irq_work *work)
static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
.func = nohz_full_kick_func,
+ .flags = ATOMIC_INIT(IRQ_WORK_HARD_IRQ),
};
/*
@@ -676,10 +682,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
/* Read jiffies and the time when jiffies were updated last */
do {
- seq = read_seqbegin(&jiffies_lock);
+ seq = read_seqcount_begin(&jiffies_seq);
basemono = last_jiffies_update;
basejiff = jiffies;
- } while (read_seqretry(&jiffies_lock, seq));
+ } while (read_seqcount_retry(&jiffies_seq, seq));
ts->last_jiffies = basejiff;
ts->timer_expires_base = basemono;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ca69290bee2a..856280d2cbd4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2397,8 +2397,10 @@ EXPORT_SYMBOL(hardpps);
*/
void xtime_update(unsigned long ticks)
{
- write_seqlock(&jiffies_lock);
+ raw_spin_lock(&jiffies_lock);
+ write_seqcount_begin(&jiffies_seq);
do_timer(ticks);
- write_sequnlock(&jiffies_lock);
+ write_seqcount_end(&jiffies_seq);
+ raw_spin_unlock(&jiffies_lock);
update_wall_time();
}
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 141ab3ab0354..099737f6f10c 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -25,7 +25,8 @@ static inline void sched_clock_resume(void) { }
extern void do_timer(unsigned long ticks);
extern void update_wall_time(void);
-extern seqlock_t jiffies_lock;
+extern raw_spinlock_t jiffies_lock;
+extern seqcount_t jiffies_seq;
#define CS_NAME_LEN 32
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 69def4a9df00..70813e39f911 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1086,6 +1086,23 @@ config PROVE_LOCKING
For more details, see Documentation/locking/lockdep-design.rst.
+config PROVE_RAW_LOCK_NESTING
+ bool "Enable raw_spinlock - spinlock nesting checks"
+ depends on PROVE_LOCKING
+ default n
+ help
+ Enable the raw_spinlock vs. spinlock nesting checks which ensure
+ that the lock nesting rules for PREEMPT_RT enabled kernels are
+ not violated.
+
+ NOTE: There are known nesting problems. So if you enable this
+ option expect lockdep splats until these problems have been fully
+ addressed which is work in progress. This config switch allows to
+ identify and analyze these problems. It will be removed and the
+ check permanentely enabled once the main issues have been fixed.
+
+ If unsure, select N.
+
config LOCK_STAT
bool "Lock usage statistics"
depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 0bfcb390ca73..8dd01f986fbb 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -488,6 +488,7 @@ static const char *uaccess_safe_builtin[] = {
"__sanitizer_cov_trace_cmp2",
"__sanitizer_cov_trace_cmp4",
"__sanitizer_cov_trace_cmp8",
+ "__sanitizer_cov_trace_switch",
/* UBSAN */
"ubsan_type_mismatch_common",
"__ubsan_handle_type_mismatch",