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:

   - A comprehensive rewrite of the robust/PI futex code's exit handling
     to fix various exit races. (Thomas Gleixner et al)

   - Rework the generic REFCOUNT_FULL implementation using
     atomic_fetch_* operations so that the performance impact of the
     cmpxchg() loops is mitigated for common refcount operations.

     With these performance improvements the generic implementation of
     refcount_t should be good enough for everybody - and this got
     confirmed by performance testing, so remove ARCH_HAS_REFCOUNT and
     REFCOUNT_FULL entirely, leaving the generic implementation enabled
     unconditionally. (Will Deacon)

   - Other misc changes, fixes, cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  lkdtm: Remove references to CONFIG_REFCOUNT_FULL
  locking/refcount: Remove unused 'refcount_error_report()' function
  locking/refcount: Consolidate implementations of refcount_t
  locking/refcount: Consolidate REFCOUNT_{MAX,SATURATED} definitions
  locking/refcount: Move saturation warnings out of line
  locking/refcount: Improve performance of generic REFCOUNT_FULL code
  locking/refcount: Move the bulk of the REFCOUNT_FULL implementation into the <linux/refcount.h> header
  locking/refcount: Remove unused refcount_*_checked() variants
  locking/refcount: Ensure integer operands are treated as signed
  locking/refcount: Define constants for saturation and max refcount values
  futex: Prevent exit livelock
  futex: Provide distinct return value when owner is exiting
  futex: Add mutex around futex exit
  futex: Provide state handling for exec() as well
  futex: Sanitize exit state handling
  futex: Mark the begin of futex exit explicitly
  futex: Set task::futex_state to DEAD right after handling futex exit
  futex: Split futex_mm_release() for exit/exec
  exit/exec: Seperate mm_release()
  futex: Replace PF_EXITPIDONE with a state
  ...

Author: torvalds

arch/Kconfig

@@ -892,27 +892,6 @@ config STRICT_MODULE_RWX
 config ARCH_HAS_PHYS_TO_DMA
 	bool
 
-config ARCH_HAS_REFCOUNT
-	bool
-	help
-	  An architecture selects this when it has implemented refcount_t
-	  using open coded assembly primitives that provide an optimized
-	  refcount_t implementation, possibly at the expense of some full
-	  refcount state checks of CONFIG_REFCOUNT_FULL=y.
-
-	  The refcount overflow check behavior, however, must be retained.
-	  Catching overflows is the primary security concern for protecting
-	  against bugs in reference counts.
-
-config REFCOUNT_FULL
-	bool "Perform full reference count validation at the expense of speed"
-	help
-	  Enabling this switches the refcounting infrastructure from a fast
-	  unchecked atomic_t implementation to a fully state checked
-	  implementation, which can be (slightly) slower but provides protections
-	  against various use-after-free conditions that can be used in
-	  security flaw exploits.
-
 config HAVE_ARCH_COMPILER_H
 	bool
 	help

arch/arm/Kconfig

@@ -117,7 +117,6 @@ config ARM
 	select OLD_SIGSUSPEND3
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC
-	select REFCOUNT_FULL
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
 	# Above selects are sorted alphabetically; please add new ones

arch/arm64/Kconfig

@@ -182,7 +182,6 @@ config ARM64
 	select PCI_SYSCALL if PCI
 	select POWER_RESET
 	select POWER_SUPPLY
-	select REFCOUNT_FULL
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE

arch/s390/configs/debug_defconfig

@@ -62,7 +62,6 @@ CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
 CONFIG_STATIC_KEYS_SELFTEST=y
-CONFIG_REFCOUNT_FULL=y
 CONFIG_LOCK_EVENT_COUNTS=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y

arch/x86/Kconfig

@@ -73,7 +73,6 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
-	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY

arch/x86/include/asm/asm.h

@@ -141,9 +141,6 @@
 # define _ASM_EXTABLE_EX(from, to)				\
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
-# define _ASM_EXTABLE_REFCOUNT(from, to)			\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
-
 # define _ASM_NOKPROBE(entry)					\
 	.pushsection "_kprobe_blacklist","aw" ;			\
 	_ASM_ALIGN ;						\
@@ -172,9 +169,6 @@
 # define _ASM_EXTABLE_EX(from, to)				\
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
-# define _ASM_EXTABLE_REFCOUNT(from, to)			\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
-
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 

arch/x86/include/asm/refcount.h

@@ -44,55 +44,6 @@ __visible bool ex_handler_fault(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL_GPL(ex_handler_fault);
 
-/*
- * Handler for UD0 exception following a failed test against the
- * result of a refcount inc/dec/add/sub.
- */
-__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
-				   struct pt_regs *regs, int trapnr,
-				   unsigned long error_code,
-				   unsigned long fault_addr)
-{
-	/* First unconditionally saturate the refcount. */
-	*(int *)regs->cx = INT_MIN / 2;
-
-	/*
-	 * Strictly speaking, this reports the fixup destination, not
-	 * the fault location, and not the actually overflowing
-	 * instruction, which is the instruction before the "js", but
-	 * since that instruction could be a variety of lengths, just
-	 * report the location after the overflow, which should be close
-	 * enough for finding the overflow, as it's at least back in
-	 * the function, having returned from .text.unlikely.
-	 */
-	regs->ip = ex_fixup_addr(fixup);
-
-	/*
-	 * This function has been called because either a negative refcount
-	 * value was seen by any of the refcount functions, or a zero
-	 * refcount value was seen by refcount_dec().
-	 *
-	 * If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result
-	 * wrapped around) will be set. Additionally, seeing the refcount
-	 * reach 0 will set ZF (Zero Flag: result was zero). In each of
-	 * these cases we want a report, since it's a boundary condition.
-	 * The SF case is not reported since it indicates post-boundary
-	 * manipulations below zero or above INT_MAX. And if none of the
-	 * flags are set, something has gone very wrong, so report it.
-	 */
-	if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) {
-		bool zero = regs->flags & X86_EFLAGS_ZF;
-
-		refcount_error_report(regs, zero ? "hit zero" : "overflow");
-	} else if ((regs->flags & X86_EFLAGS_SF) == 0) {
-		/* Report if none of OF, ZF, nor SF are set. */
-		refcount_error_report(regs, "unexpected saturation");
-	}
-
-	return true;
-}
-EXPORT_SYMBOL(ex_handler_refcount);
-
 /*
  * Handler for when we fail to restore a task's FPU state.  We should never get
  * here because the FPU state of a task using the FPU (task->thread.fpu.state)

arch/x86/mm/extable.c

@@ -719,7 +719,7 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter)
 		__drm_connector_put_safe(iter->conn);
 		spin_unlock_irqrestore(&config->connector_list_lock, flags);
 	}
-	lock_release(&connector_list_iter_dep_map, 0, _RET_IP_);
+	lock_release(&connector_list_iter_dep_map, _RET_IP_);
 }
 EXPORT_SYMBOL(drm_connector_list_iter_end);
 

drivers/gpu/drm/drm_connector.c

@@ -22,7 +22,6 @@ config DRM_I915_DEBUG
         depends on DRM_I915
         select DEBUG_FS
         select PREEMPT_COUNT
-        select REFCOUNT_FULL
         select I2C_CHARDEV
         select STACKDEPOT
         select DRM_DP_AUX_CHARDEV

drivers/gpu/drm/i915/Kconfig.debug

@@ -509,14 +509,14 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
 		      I915_MM_SHRINKER, 0, _RET_IP_);
 
 	mutex_acquire(&mutex->dep_map, 0, 0, _RET_IP_);
-	mutex_release(&mutex->dep_map, 0, _RET_IP_);
+	mutex_release(&mutex->dep_map, _RET_IP_);
 
-	mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_);
+	mutex_release(&i915->drm.struct_mutex.dep_map, _RET_IP_);
 
 	fs_reclaim_release(GFP_KERNEL);
 
 	if (unlock)
-		mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_);
+		mutex_release(&i915->drm.struct_mutex.dep_map, _RET_IP_);
 }
 
 #define obj_to_i915(obj__) to_i915((obj__)->base.dev)

drivers/gpu/drm/i915/gem/i915_gem_shrinker.c

@@ -52,7 +52,7 @@ static inline unsigned long __timeline_mark_lock(struct intel_context *ce)
 static inline void __timeline_mark_unlock(struct intel_context *ce,
 					  unsigned long flags)
 {
-	mutex_release(&ce->timeline->mutex.dep_map, 0, _THIS_IP_);
+	mutex_release(&ce->timeline->mutex.dep_map, _THIS_IP_);
 	local_irq_restore(flags);
 }
 

drivers/gpu/drm/i915/gt/intel_engine_pm.c

@@ -1495,7 +1495,7 @@ long i915_request_wait(struct i915_request *rq,
 	dma_fence_remove_callback(&rq->fence, &wait.cb);
 
 out:
-	mutex_release(&rq->engine->gt->reset.mutex.dep_map, 0, _THIS_IP_);
+	mutex_release(&rq->engine->gt->reset.mutex.dep_map, _THIS_IP_);
 	trace_i915_request_wait_end(rq);
 	return timeout;
 }

drivers/gpu/drm/i915/i915_request.c

@@ -6,14 +6,6 @@
 #include "lkdtm.h"
 #include <linux/refcount.h>
 
-#ifdef CONFIG_REFCOUNT_FULL
-#define REFCOUNT_MAX		(UINT_MAX - 1)
-#define REFCOUNT_SATURATED	UINT_MAX
-#else
-#define REFCOUNT_MAX		INT_MAX
-#define REFCOUNT_SATURATED	(INT_MIN / 2)
-#endif
-
 static void overflow_check(refcount_t *ref)
 {
 	switch (refcount_read(ref)) {
@@ -127,7 +119,7 @@ void lkdtm_REFCOUNT_DEC_ZERO(void)
 static void check_negative(refcount_t *ref, int start)
 {
 	/*
-	 * CONFIG_REFCOUNT_FULL refuses to move a refcount at all on an
+	 * refcount_t refuses to move a refcount at all on an
 	 * over-sub, so we have to track our starting position instead of
 	 * looking only at zero-pinning.
 	 */
@@ -210,7 +202,6 @@ static void check_from_zero(refcount_t *ref)
 
 /*
  * A refcount_inc() from zero should pin to zero or saturate and may WARN.
- * Only CONFIG_REFCOUNT_FULL provides this protection currently.
  */
 void lkdtm_REFCOUNT_INC_ZERO(void)
 {

drivers/misc/lkdtm/refcount.c

@@ -303,7 +303,7 @@ static int __ldsem_down_read_nested(struct ld_semaphore *sem,
 	if (count <= 0) {
 		lock_contended(&sem->dep_map, _RET_IP_);
 		if (!down_read_failed(sem, count, timeout)) {
-			rwsem_release(&sem->dep_map, 1, _RET_IP_);
+			rwsem_release(&sem->dep_map, _RET_IP_);
 			return 0;
 		}
 	}
@@ -322,7 +322,7 @@ static int __ldsem_down_write_nested(struct ld_semaphore *sem,
 	if ((count & LDSEM_ACTIVE_MASK) != LDSEM_ACTIVE_BIAS) {
 		lock_contended(&sem->dep_map, _RET_IP_);
 		if (!down_write_failed(sem, count, timeout)) {
-			rwsem_release(&sem->dep_map, 1, _RET_IP_);
+			rwsem_release(&sem->dep_map, _RET_IP_);
 			return 0;
 		}
 	}
@@ -390,7 +390,7 @@ void ldsem_up_read(struct ld_semaphore *sem)
 {
 	long count;
 
-	rwsem_release(&sem->dep_map, 1, _RET_IP_);
+	rwsem_release(&sem->dep_map, _RET_IP_);
 
 	count = atomic_long_add_return(-LDSEM_READ_BIAS, &sem->count);
 	if (count < 0 && (count & LDSEM_ACTIVE_MASK) == 0)
@@ -404,7 +404,7 @@ void ldsem_up_write(struct ld_semaphore *sem)
 {
 	long count;
 
-	rwsem_release(&sem->dep_map, 1, _RET_IP_);
+	rwsem_release(&sem->dep_map, _RET_IP_);
 
 	count = atomic_long_add_return(-LDSEM_WRITE_BIAS, &sem->count);
 	if (count < 0)

drivers/tty/tty_ldsem.c

@@ -1319,7 +1319,7 @@ static void d_walk(struct dentry *parent, void *data,
 
 		if (!list_empty(&dentry->d_subdirs)) {
 			spin_unlock(&this_parent->d_lock);
-			spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
+			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
 			this_parent = dentry;
 			spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
 			goto repeat;