mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
948f83768a
check_prev_add_irq() tests all incompatible scenarios one after the
other while adding a lock (@next) to a tree dependency (@prev):
LOCK_USED_IN_HARDIRQ vs LOCK_ENABLED_HARDIRQ
LOCK_USED_IN_HARDIRQ_READ vs LOCK_ENABLED_HARDIRQ
LOCK_USED_IN_SOFTIRQ vs LOCK_ENABLED_SOFTIRQ
LOCK_USED_IN_SOFTIRQ_READ vs LOCK_ENABLED_SOFTIRQ
Also for these four scenarios, we must at least iterate the @prev
backward dependency. Then if it matches the relevant LOCK_USED_* bit,
we must also iterate the @next forward dependency.
Therefore in the best case we iterate 4 times, in the worst case 8 times.
A different approach can let us divide the number of branch iterations
by 4:
1) Iterate through @prev backward dependencies and accumulate all the IRQ
uses in a single mask. In the best case where the current lock hasn't
been used in IRQ, we stop here.
2) Iterate through @next forward dependencies and try to find a lock
whose usage is exclusive to the accumulated usages gathered in the
previous step. If we find one (call it @lockA), we have found an
incompatible use, otherwise we stop here. Only bad locking scenario
go further. So a sane verification stop here.
3) Iterate again through @prev backward dependency and find the lock
whose usage matches @lockA in term of incompatibility. Call that
lock @lockB.
4) Report the incompatible usages of @lockA and @lockB
If no incompatible use is found, the verification never goes beyond
step 2 which means at most two iterations.
The following compares the execution measurements of the function
check_prev_add_irq():
Number of calls | Avg (ns) | Stdev (ns) | Total time (ns)
------------------------------------------------------------------------
Mainline 8452 | 2652 | 11962 | 22415143
This patch 8452 | 1518 | 7090 | 12835602
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Link: https://lkml.kernel.org/r/20190402160244.32434-5-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
242 lines
6.4 KiB
C
242 lines
6.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* kernel/lockdep_internals.h
|
|
*
|
|
* Runtime locking correctness validator
|
|
*
|
|
* lockdep subsystem internal functions and variables.
|
|
*/
|
|
|
|
/*
|
|
* Lock-class usage-state bits:
|
|
*/
|
|
enum lock_usage_bit {
|
|
#define LOCKDEP_STATE(__STATE) \
|
|
LOCK_USED_IN_##__STATE, \
|
|
LOCK_USED_IN_##__STATE##_READ, \
|
|
LOCK_ENABLED_##__STATE, \
|
|
LOCK_ENABLED_##__STATE##_READ,
|
|
#include "lockdep_states.h"
|
|
#undef LOCKDEP_STATE
|
|
LOCK_USED,
|
|
LOCK_USAGE_STATES
|
|
};
|
|
|
|
#define LOCK_USAGE_READ_MASK 1
|
|
#define LOCK_USAGE_DIR_MASK 2
|
|
#define LOCK_USAGE_STATE_MASK (~(LOCK_USAGE_READ_MASK | LOCK_USAGE_DIR_MASK))
|
|
|
|
/*
|
|
* Usage-state bitmasks:
|
|
*/
|
|
#define __LOCKF(__STATE) LOCKF_##__STATE = (1 << LOCK_##__STATE),
|
|
|
|
enum {
|
|
#define LOCKDEP_STATE(__STATE) \
|
|
__LOCKF(USED_IN_##__STATE) \
|
|
__LOCKF(USED_IN_##__STATE##_READ) \
|
|
__LOCKF(ENABLED_##__STATE) \
|
|
__LOCKF(ENABLED_##__STATE##_READ)
|
|
#include "lockdep_states.h"
|
|
#undef LOCKDEP_STATE
|
|
__LOCKF(USED)
|
|
};
|
|
|
|
#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE |
|
|
static const unsigned long LOCKF_ENABLED_IRQ =
|
|
#include "lockdep_states.h"
|
|
0;
|
|
#undef LOCKDEP_STATE
|
|
|
|
#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE |
|
|
static const unsigned long LOCKF_USED_IN_IRQ =
|
|
#include "lockdep_states.h"
|
|
0;
|
|
#undef LOCKDEP_STATE
|
|
|
|
#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE##_READ |
|
|
static const unsigned long LOCKF_ENABLED_IRQ_READ =
|
|
#include "lockdep_states.h"
|
|
0;
|
|
#undef LOCKDEP_STATE
|
|
|
|
#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE##_READ |
|
|
static const unsigned long LOCKF_USED_IN_IRQ_READ =
|
|
#include "lockdep_states.h"
|
|
0;
|
|
#undef LOCKDEP_STATE
|
|
|
|
#define LOCKF_ENABLED_IRQ_ALL (LOCKF_ENABLED_IRQ | LOCKF_ENABLED_IRQ_READ)
|
|
#define LOCKF_USED_IN_IRQ_ALL (LOCKF_USED_IN_IRQ | LOCKF_USED_IN_IRQ_READ)
|
|
|
|
#define LOCKF_IRQ (LOCKF_ENABLED_IRQ | LOCKF_USED_IN_IRQ)
|
|
#define LOCKF_IRQ_READ (LOCKF_ENABLED_IRQ_READ | LOCKF_USED_IN_IRQ_READ)
|
|
|
|
/*
|
|
* CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text,
|
|
* .data and .bss to fit in required 32MB limit for the kernel. With
|
|
* CONFIG_LOCKDEP we could go over this limit and cause system boot-up problems.
|
|
* So, reduce the static allocations for lockdeps related structures so that
|
|
* everything fits in current required size limit.
|
|
*/
|
|
#ifdef CONFIG_LOCKDEP_SMALL
|
|
/*
|
|
* MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies
|
|
* we track.
|
|
*
|
|
* We use the per-lock dependency maps in two ways: we grow it by adding
|
|
* every to-be-taken lock to all currently held lock's own dependency
|
|
* table (if it's not there yet), and we check it for lock order
|
|
* conflicts and deadlocks.
|
|
*/
|
|
#define MAX_LOCKDEP_ENTRIES 16384UL
|
|
#define MAX_LOCKDEP_CHAINS_BITS 15
|
|
#define MAX_STACK_TRACE_ENTRIES 262144UL
|
|
#else
|
|
#define MAX_LOCKDEP_ENTRIES 32768UL
|
|
|
|
#define MAX_LOCKDEP_CHAINS_BITS 16
|
|
|
|
/*
|
|
* Stack-trace: tightly packed array of stack backtrace
|
|
* addresses. Protected by the hash_lock.
|
|
*/
|
|
#define MAX_STACK_TRACE_ENTRIES 524288UL
|
|
#endif
|
|
|
|
#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS)
|
|
|
|
#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
|
|
|
|
extern struct list_head all_lock_classes;
|
|
extern struct lock_chain lock_chains[];
|
|
|
|
#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2)
|
|
|
|
extern void get_usage_chars(struct lock_class *class,
|
|
char usage[LOCK_USAGE_CHARS]);
|
|
|
|
extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str);
|
|
|
|
struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i);
|
|
|
|
extern unsigned long nr_lock_classes;
|
|
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 max_recursion_depth;
|
|
|
|
extern unsigned int max_bfs_queue_depth;
|
|
|
|
#ifdef CONFIG_PROVE_LOCKING
|
|
extern unsigned long lockdep_count_forward_deps(struct lock_class *);
|
|
extern unsigned long lockdep_count_backward_deps(struct lock_class *);
|
|
#else
|
|
static inline unsigned long
|
|
lockdep_count_forward_deps(struct lock_class *class)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline unsigned long
|
|
lockdep_count_backward_deps(struct lock_class *class)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_DEBUG_LOCKDEP
|
|
|
|
#include <asm/local.h>
|
|
/*
|
|
* Various lockdep statistics.
|
|
* We want them per cpu as they are often accessed in fast path
|
|
* and we want to avoid too much cache bouncing.
|
|
*/
|
|
struct lockdep_stats {
|
|
int chain_lookup_hits;
|
|
int chain_lookup_misses;
|
|
int hardirqs_on_events;
|
|
int hardirqs_off_events;
|
|
int redundant_hardirqs_on;
|
|
int redundant_hardirqs_off;
|
|
int softirqs_on_events;
|
|
int softirqs_off_events;
|
|
int redundant_softirqs_on;
|
|
int redundant_softirqs_off;
|
|
int nr_unused_locks;
|
|
int nr_redundant_checks;
|
|
int nr_redundant;
|
|
int nr_cyclic_checks;
|
|
int nr_cyclic_check_recursions;
|
|
int nr_find_usage_forwards_checks;
|
|
int nr_find_usage_forwards_recursions;
|
|
int nr_find_usage_backwards_checks;
|
|
int nr_find_usage_backwards_recursions;
|
|
|
|
/*
|
|
* Per lock class locking operation stat counts
|
|
*/
|
|
unsigned long lock_class_ops[MAX_LOCKDEP_KEYS];
|
|
};
|
|
|
|
DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
|
|
extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
|
|
|
|
#define __debug_atomic_inc(ptr) \
|
|
this_cpu_inc(lockdep_stats.ptr);
|
|
|
|
#define debug_atomic_inc(ptr) { \
|
|
WARN_ON_ONCE(!irqs_disabled()); \
|
|
__this_cpu_inc(lockdep_stats.ptr); \
|
|
}
|
|
|
|
#define debug_atomic_dec(ptr) { \
|
|
WARN_ON_ONCE(!irqs_disabled()); \
|
|
__this_cpu_dec(lockdep_stats.ptr); \
|
|
}
|
|
|
|
#define debug_atomic_read(ptr) ({ \
|
|
struct lockdep_stats *__cpu_lockdep_stats; \
|
|
unsigned long long __total = 0; \
|
|
int __cpu; \
|
|
for_each_possible_cpu(__cpu) { \
|
|
__cpu_lockdep_stats = &per_cpu(lockdep_stats, __cpu); \
|
|
__total += __cpu_lockdep_stats->ptr; \
|
|
} \
|
|
__total; \
|
|
})
|
|
|
|
static inline void debug_class_ops_inc(struct lock_class *class)
|
|
{
|
|
int idx;
|
|
|
|
idx = class - lock_classes;
|
|
__debug_atomic_inc(lock_class_ops[idx]);
|
|
}
|
|
|
|
static inline unsigned long debug_class_ops_read(struct lock_class *class)
|
|
{
|
|
int idx, cpu;
|
|
unsigned long ops = 0;
|
|
|
|
idx = class - lock_classes;
|
|
for_each_possible_cpu(cpu)
|
|
ops += per_cpu(lockdep_stats.lock_class_ops[idx], cpu);
|
|
return ops;
|
|
}
|
|
|
|
#else
|
|
# define __debug_atomic_inc(ptr) do { } while (0)
|
|
# define debug_atomic_inc(ptr) do { } while (0)
|
|
# define debug_atomic_dec(ptr) do { } while (0)
|
|
# define debug_atomic_read(ptr) 0
|
|
# define debug_class_ops_inc(ptr) do { } while (0)
|
|
#endif
|