linux_dsm_epyc7002/include/linux/vmstat.h
Steven Rostedt d51d1e6450 mm, vmscan, tracing: use pointer to reclaim_stat struct in trace event
The trace event trace_mm_vmscan_lru_shrink_inactive() currently has 12
parameters! Seven of them are from the reclaim_stat structure.  This
structure is currently local to mm/vmscan.c.  By moving it to the global
vmstat.h header, we can also reference it from the vmscan tracepoints.
In moving it, it brings down the overhead of passing so many arguments
to the trace event.  In the future, we may limit the number of arguments
that a trace event may pass (ideally just 6, but more realistically it
may be 8).

Before this patch, the code to call the trace event is this:

 0f 83 aa fe ff ff       jae    ffffffff811e6261 <shrink_inactive_list+0x1e1>
 48 8b 45 a0             mov    -0x60(%rbp),%rax
 45 8b 64 24 20          mov    0x20(%r12),%r12d
 44 8b 6d d4             mov    -0x2c(%rbp),%r13d
 8b 4d d0                mov    -0x30(%rbp),%ecx
 44 8b 75 cc             mov    -0x34(%rbp),%r14d
 44 8b 7d c8             mov    -0x38(%rbp),%r15d
 48 89 45 90             mov    %rax,-0x70(%rbp)
 8b 83 b8 fe ff ff       mov    -0x148(%rbx),%eax
 8b 55 c0                mov    -0x40(%rbp),%edx
 8b 7d c4                mov    -0x3c(%rbp),%edi
 8b 75 b8                mov    -0x48(%rbp),%esi
 89 45 80                mov    %eax,-0x80(%rbp)
 65 ff 05 e4 f7 e2 7e    incl   %gs:0x7ee2f7e4(%rip)        # 15bd0 <__preempt_count>
 48 8b 05 75 5b 13 01    mov    0x1135b75(%rip),%rax        # ffffffff8231bf68 <__tracepoint_mm_vmscan_lru_shrink_inactive+0x28>
 48 85 c0                test   %rax,%rax
 74 72                   je     ffffffff811e646a <shrink_inactive_list+0x3ea>
 48 89 c3                mov    %rax,%rbx
 4c 8b 10                mov    (%rax),%r10
 89 f8                   mov    %edi,%eax
 48 89 85 68 ff ff ff    mov    %rax,-0x98(%rbp)
 89 f0                   mov    %esi,%eax
 48 89 85 60 ff ff ff    mov    %rax,-0xa0(%rbp)
 89 c8                   mov    %ecx,%eax
 48 89 85 78 ff ff ff    mov    %rax,-0x88(%rbp)
 89 d0                   mov    %edx,%eax
 48 89 85 70 ff ff ff    mov    %rax,-0x90(%rbp)
 8b 45 8c                mov    -0x74(%rbp),%eax
 48 8b 7b 08             mov    0x8(%rbx),%rdi
 48 83 c3 18             add    $0x18,%rbx
 50                      push   %rax
 41 54                   push   %r12
 41 55                   push   %r13
 ff b5 78 ff ff ff       pushq  -0x88(%rbp)
 41 56                   push   %r14
 41 57                   push   %r15
 ff b5 70 ff ff ff       pushq  -0x90(%rbp)
 4c 8b 8d 68 ff ff ff    mov    -0x98(%rbp),%r9
 4c 8b 85 60 ff ff ff    mov    -0xa0(%rbp),%r8
 48 8b 4d 98             mov    -0x68(%rbp),%rcx
 48 8b 55 90             mov    -0x70(%rbp),%rdx
 8b 75 80                mov    -0x80(%rbp),%esi
 41 ff d2                callq  *%r10

After the patch:

 0f 83 a8 fe ff ff       jae    ffffffff811e626d <shrink_inactive_list+0x1cd>
 8b 9b b8 fe ff ff       mov    -0x148(%rbx),%ebx
 45 8b 64 24 20          mov    0x20(%r12),%r12d
 4c 8b 6d a0             mov    -0x60(%rbp),%r13
 65 ff 05 f5 f7 e2 7e    incl   %gs:0x7ee2f7f5(%rip)        # 15bd0 <__preempt_count>
 4c 8b 35 86 5b 13 01    mov    0x1135b86(%rip),%r14        # ffffffff8231bf68 <__tracepoint_mm_vmscan_lru_shrink_inactive+0x28>
 4d 85 f6                test   %r14,%r14
 74 2a                   je     ffffffff811e6411 <shrink_inactive_list+0x371>
 49 8b 06                mov    (%r14),%rax
 8b 4d 8c                mov    -0x74(%rbp),%ecx
 49 8b 7e 08             mov    0x8(%r14),%rdi
 49 83 c6 18             add    $0x18,%r14
 4c 89 ea                mov    %r13,%rdx
 45 89 e1                mov    %r12d,%r9d
 4c 8d 45 b8             lea    -0x48(%rbp),%r8
 89 de                   mov    %ebx,%esi
 51                      push   %rcx
 48 8b 4d 98             mov    -0x68(%rbp),%rcx
 ff d0                   callq  *%rax

Link: http://lkml.kernel.org/r/2559d7cb-ec60-1200-2362-04fa34fd02bb@fb.com
Link: http://lkml.kernel.org/r/20180322121003.4177af15@gandalf.local.home
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reported-by: Alexei Starovoitov <ast@fb.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexei Starovoitov <ast@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-11 10:28:30 -07:00

390 lines
11 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_VMSTAT_H
#define _LINUX_VMSTAT_H
#include <linux/types.h>
#include <linux/percpu.h>
#include <linux/mmzone.h>
#include <linux/vm_event_item.h>
#include <linux/atomic.h>
#include <linux/static_key.h>
extern int sysctl_stat_interval;
#ifdef CONFIG_NUMA
#define ENABLE_NUMA_STAT 1
#define DISABLE_NUMA_STAT 0
extern int sysctl_vm_numa_stat;
DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key);
extern int sysctl_vm_numa_stat_handler(struct ctl_table *table,
int write, void __user *buffer, size_t *length, loff_t *ppos);
#endif
struct reclaim_stat {
unsigned nr_dirty;
unsigned nr_unqueued_dirty;
unsigned nr_congested;
unsigned nr_writeback;
unsigned nr_immediate;
unsigned nr_activate;
unsigned nr_ref_keep;
unsigned nr_unmap_fail;
};
#ifdef CONFIG_VM_EVENT_COUNTERS
/*
* Light weight per cpu counter implementation.
*
* Counters should only be incremented and no critical kernel component
* should rely on the counter values.
*
* Counters are handled completely inline. On many platforms the code
* generated will simply be the increment of a global address.
*/
struct vm_event_state {
unsigned long event[NR_VM_EVENT_ITEMS];
};
DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
/*
* vm counters are allowed to be racy. Use raw_cpu_ops to avoid the
* local_irq_disable overhead.
*/
static inline void __count_vm_event(enum vm_event_item item)
{
raw_cpu_inc(vm_event_states.event[item]);
}
static inline void count_vm_event(enum vm_event_item item)
{
this_cpu_inc(vm_event_states.event[item]);
}
static inline void __count_vm_events(enum vm_event_item item, long delta)
{
raw_cpu_add(vm_event_states.event[item], delta);
}
static inline void count_vm_events(enum vm_event_item item, long delta)
{
this_cpu_add(vm_event_states.event[item], delta);
}
extern void all_vm_events(unsigned long *);
extern void vm_events_fold_cpu(int cpu);
#else
/* Disable counters */
static inline void count_vm_event(enum vm_event_item item)
{
}
static inline void count_vm_events(enum vm_event_item item, long delta)
{
}
static inline void __count_vm_event(enum vm_event_item item)
{
}
static inline void __count_vm_events(enum vm_event_item item, long delta)
{
}
static inline void all_vm_events(unsigned long *ret)
{
}
static inline void vm_events_fold_cpu(int cpu)
{
}
#endif /* CONFIG_VM_EVENT_COUNTERS */
#ifdef CONFIG_NUMA_BALANCING
#define count_vm_numa_event(x) count_vm_event(x)
#define count_vm_numa_events(x, y) count_vm_events(x, y)
#else
#define count_vm_numa_event(x) do {} while (0)
#define count_vm_numa_events(x, y) do { (void)(y); } while (0)
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_DEBUG_TLBFLUSH
#define count_vm_tlb_event(x) count_vm_event(x)
#define count_vm_tlb_events(x, y) count_vm_events(x, y)
#else
#define count_vm_tlb_event(x) do {} while (0)
#define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
#endif
#ifdef CONFIG_DEBUG_VM_VMACACHE
#define count_vm_vmacache_event(x) count_vm_event(x)
#else
#define count_vm_vmacache_event(x) do {} while (0)
#endif
#define __count_zid_vm_events(item, zid, delta) \
__count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
/*
* Zone and node-based page accounting with per cpu differentials.
*/
extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
#ifdef CONFIG_NUMA
static inline void zone_numa_state_add(long x, struct zone *zone,
enum numa_stat_item item)
{
atomic_long_add(x, &zone->vm_numa_stat[item]);
atomic_long_add(x, &vm_numa_stat[item]);
}
static inline unsigned long global_numa_state(enum numa_stat_item item)
{
long x = atomic_long_read(&vm_numa_stat[item]);
return x;
}
static inline unsigned long zone_numa_state_snapshot(struct zone *zone,
enum numa_stat_item item)
{
long x = atomic_long_read(&zone->vm_numa_stat[item]);
int cpu;
for_each_online_cpu(cpu)
x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item];
return x;
}
#endif /* CONFIG_NUMA */
static inline void zone_page_state_add(long x, struct zone *zone,
enum zone_stat_item item)
{
atomic_long_add(x, &zone->vm_stat[item]);
atomic_long_add(x, &vm_zone_stat[item]);
}
static inline void node_page_state_add(long x, struct pglist_data *pgdat,
enum node_stat_item item)
{
atomic_long_add(x, &pgdat->vm_stat[item]);
atomic_long_add(x, &vm_node_stat[item]);
}
static inline unsigned long global_zone_page_state(enum zone_stat_item item)
{
long x = atomic_long_read(&vm_zone_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static inline unsigned long global_node_page_state(enum node_stat_item item)
{
long x = atomic_long_read(&vm_node_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static inline unsigned long zone_page_state(struct zone *zone,
enum zone_stat_item item)
{
long x = atomic_long_read(&zone->vm_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
/*
* More accurate version that also considers the currently pending
* deltas. For that we need to loop over all cpus to find the current
* deltas. There is no synchronization so the result cannot be
* exactly accurate either.
*/
static inline unsigned long zone_page_state_snapshot(struct zone *zone,
enum zone_stat_item item)
{
long x = atomic_long_read(&zone->vm_stat[item]);
#ifdef CONFIG_SMP
int cpu;
for_each_online_cpu(cpu)
x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item];
if (x < 0)
x = 0;
#endif
return x;
}
#ifdef CONFIG_NUMA
extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item);
extern unsigned long sum_zone_node_page_state(int node,
enum zone_stat_item item);
extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
extern unsigned long node_page_state(struct pglist_data *pgdat,
enum node_stat_item item);
#else
#define sum_zone_node_page_state(node, item) global_zone_page_state(item)
#define node_page_state(node, item) global_node_page_state(item)
#endif /* CONFIG_NUMA */
#define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
#define add_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, __d)
#define sub_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, -(__d))
#ifdef CONFIG_SMP
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
void __inc_zone_page_state(struct page *, enum zone_stat_item);
void __dec_zone_page_state(struct page *, enum zone_stat_item);
void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long);
void __inc_node_page_state(struct page *, enum node_stat_item);
void __dec_node_page_state(struct page *, enum node_stat_item);
void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
void inc_zone_page_state(struct page *, enum zone_stat_item);
void dec_zone_page_state(struct page *, enum zone_stat_item);
void mod_node_page_state(struct pglist_data *, enum node_stat_item, long);
void inc_node_page_state(struct page *, enum node_stat_item);
void dec_node_page_state(struct page *, enum node_stat_item);
extern void inc_node_state(struct pglist_data *, enum node_stat_item);
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
extern void __inc_node_state(struct pglist_data *, enum node_stat_item);
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_node_state(struct pglist_data *, enum node_stat_item);
void quiet_vmstat(void);
void cpu_vm_stats_fold(int cpu);
void refresh_zone_stat_thresholds(void);
struct ctl_table;
int vmstat_refresh(struct ctl_table *, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
int calculate_pressure_threshold(struct zone *zone);
int calculate_normal_threshold(struct zone *zone);
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
int (*calculate_pressure)(struct zone *));
#else /* CONFIG_SMP */
/*
* We do not maintain differentials in a single processor configuration.
* The functions directly modify the zone and global counters.
*/
static inline void __mod_zone_page_state(struct zone *zone,
enum zone_stat_item item, long delta)
{
zone_page_state_add(delta, zone, item);
}
static inline void __mod_node_page_state(struct pglist_data *pgdat,
enum node_stat_item item, int delta)
{
node_page_state_add(delta, pgdat, item);
}
static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
atomic_long_inc(&zone->vm_stat[item]);
atomic_long_inc(&vm_zone_stat[item]);
}
static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
atomic_long_inc(&pgdat->vm_stat[item]);
atomic_long_inc(&vm_node_stat[item]);
}
static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
atomic_long_dec(&zone->vm_stat[item]);
atomic_long_dec(&vm_zone_stat[item]);
}
static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
atomic_long_dec(&pgdat->vm_stat[item]);
atomic_long_dec(&vm_node_stat[item]);
}
static inline void __inc_zone_page_state(struct page *page,
enum zone_stat_item item)
{
__inc_zone_state(page_zone(page), item);
}
static inline void __inc_node_page_state(struct page *page,
enum node_stat_item item)
{
__inc_node_state(page_pgdat(page), item);
}
static inline void __dec_zone_page_state(struct page *page,
enum zone_stat_item item)
{
__dec_zone_state(page_zone(page), item);
}
static inline void __dec_node_page_state(struct page *page,
enum node_stat_item item)
{
__dec_node_state(page_pgdat(page), item);
}
/*
* We only use atomic operations to update counters. So there is no need to
* disable interrupts.
*/
#define inc_zone_page_state __inc_zone_page_state
#define dec_zone_page_state __dec_zone_page_state
#define mod_zone_page_state __mod_zone_page_state
#define inc_node_page_state __inc_node_page_state
#define dec_node_page_state __dec_node_page_state
#define mod_node_page_state __mod_node_page_state
#define inc_zone_state __inc_zone_state
#define inc_node_state __inc_node_state
#define dec_zone_state __dec_zone_state
#define set_pgdat_percpu_threshold(pgdat, callback) { }
static inline void refresh_zone_stat_thresholds(void) { }
static inline void cpu_vm_stats_fold(int cpu) { }
static inline void quiet_vmstat(void) { }
static inline void drain_zonestat(struct zone *zone,
struct per_cpu_pageset *pset) { }
#endif /* CONFIG_SMP */
static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
int migratetype)
{
__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
if (is_migrate_cma(migratetype))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
}
extern const char * const vmstat_text[];
#endif /* _LINUX_VMSTAT_H */