linux_dsm_epyc7002/include/trace/events/kmem.h
Shreyas B. Prabhu 649b8de2f7 tracing/mm: don't trace mm_page_pcpu_drain on offline cpus
Since tracepoints use RCU for protection, they must not be called on
offline cpus.  trace_mm_page_pcpu_drain can be called on an offline cpu
in this scenario caught by LOCKDEP:

     ===============================
     [ INFO: suspicious RCU usage. ]
     4.1.0-rc1+ #9 Not tainted
     -------------------------------
     include/trace/events/kmem.h:265 suspicious rcu_dereference_check() usage!

    other info that might help us debug this:

    RCU used illegally from offline CPU!
    rcu_scheduler_active = 1, debug_locks = 1
     1 lock held by swapper/5/0:
      #0:  (&(&zone->lock)->rlock){..-...}, at: [<c0000000002073b0>] .free_pcppages_bulk+0x70/0x920

    stack backtrace:
     CPU: 5 PID: 0 Comm: swapper/5 Not tainted 4.1.0-rc1+ #9
     Call Trace:
       .dump_stack+0x98/0xd4 (unreliable)
       .lockdep_rcu_suspicious+0x108/0x170
       .free_pcppages_bulk+0x60c/0x920
       .free_hot_cold_page+0x208/0x280
       .destroy_context+0x90/0xd0
       .__mmdrop+0x58/0x160
       .idle_task_exit+0xf0/0x100
       .pnv_smp_cpu_kill_self+0x58/0x2c0
       .cpu_die+0x34/0x50
       .arch_cpu_idle_dead+0x20/0x40
       .cpu_startup_entry+0x708/0x7a0
       .start_secondary+0x36c/0x3a0
       start_secondary_prolog+0x10/0x14

Fix this by converting mm_page_pcpu_drain trace point into
TRACE_EVENT_CONDITION where condition is cpu_online(smp_processor_id())

Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-05-28 18:25:18 -07:00

358 lines
8.8 KiB
C

#undef TRACE_SYSTEM
#define TRACE_SYSTEM kmem
#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_KMEM_H
#include <linux/types.h>
#include <linux/tracepoint.h>
#include <trace/events/gfpflags.h>
DECLARE_EVENT_CLASS(kmem_alloc,
TP_PROTO(unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
gfp_t gfp_flags),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
__field( size_t, bytes_req )
__field( size_t, bytes_alloc )
__field( gfp_t, gfp_flags )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
__entry->bytes_req = bytes_req;
__entry->bytes_alloc = bytes_alloc;
__entry->gfp_flags = gfp_flags;
),
TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
__entry->call_site,
__entry->ptr,
__entry->bytes_req,
__entry->bytes_alloc,
show_gfp_flags(__entry->gfp_flags))
);
DEFINE_EVENT(kmem_alloc, kmalloc,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
);
DEFINE_EVENT(kmem_alloc, kmem_cache_alloc,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
);
DECLARE_EVENT_CLASS(kmem_alloc_node,
TP_PROTO(unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
gfp_t gfp_flags,
int node),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
__field( size_t, bytes_req )
__field( size_t, bytes_alloc )
__field( gfp_t, gfp_flags )
__field( int, node )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
__entry->bytes_req = bytes_req;
__entry->bytes_alloc = bytes_alloc;
__entry->gfp_flags = gfp_flags;
__entry->node = node;
),
TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
__entry->call_site,
__entry->ptr,
__entry->bytes_req,
__entry->bytes_alloc,
show_gfp_flags(__entry->gfp_flags),
__entry->node)
);
DEFINE_EVENT(kmem_alloc_node, kmalloc_node,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc,
gfp_t gfp_flags, int node),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
);
DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node,
TP_PROTO(unsigned long call_site, const void *ptr,
size_t bytes_req, size_t bytes_alloc,
gfp_t gfp_flags, int node),
TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
);
DECLARE_EVENT_CLASS(kmem_free,
TP_PROTO(unsigned long call_site, const void *ptr),
TP_ARGS(call_site, ptr),
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
),
TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
);
DEFINE_EVENT(kmem_free, kfree,
TP_PROTO(unsigned long call_site, const void *ptr),
TP_ARGS(call_site, ptr)
);
DEFINE_EVENT_CONDITION(kmem_free, kmem_cache_free,
TP_PROTO(unsigned long call_site, const void *ptr),
TP_ARGS(call_site, ptr),
/*
* This trace can be potentially called from an offlined cpu.
* Since trace points use RCU and RCU should not be used from
* offline cpus, filter such calls out.
* While this trace can be called from a preemptable section,
* it has no impact on the condition since tasks can migrate
* only from online cpus to other online cpus. Thus its safe
* to use raw_smp_processor_id.
*/
TP_CONDITION(cpu_online(raw_smp_processor_id()))
);
TRACE_EVENT_CONDITION(mm_page_free,
TP_PROTO(struct page *page, unsigned int order),
TP_ARGS(page, order),
/*
* This trace can be potentially called from an offlined cpu.
* Since trace points use RCU and RCU should not be used from
* offline cpus, filter such calls out.
* While this trace can be called from a preemptable section,
* it has no impact on the condition since tasks can migrate
* only from online cpus to other online cpus. Thus its safe
* to use raw_smp_processor_id.
*/
TP_CONDITION(cpu_online(raw_smp_processor_id())),
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( unsigned int, order )
),
TP_fast_assign(
__entry->pfn = page_to_pfn(page);
__entry->order = order;
),
TP_printk("page=%p pfn=%lu order=%d",
pfn_to_page(__entry->pfn),
__entry->pfn,
__entry->order)
);
TRACE_EVENT(mm_page_free_batched,
TP_PROTO(struct page *page, int cold),
TP_ARGS(page, cold),
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( int, cold )
),
TP_fast_assign(
__entry->pfn = page_to_pfn(page);
__entry->cold = cold;
),
TP_printk("page=%p pfn=%lu order=0 cold=%d",
pfn_to_page(__entry->pfn),
__entry->pfn,
__entry->cold)
);
TRACE_EVENT(mm_page_alloc,
TP_PROTO(struct page *page, unsigned int order,
gfp_t gfp_flags, int migratetype),
TP_ARGS(page, order, gfp_flags, migratetype),
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( unsigned int, order )
__field( gfp_t, gfp_flags )
__field( int, migratetype )
),
TP_fast_assign(
__entry->pfn = page ? page_to_pfn(page) : -1UL;
__entry->order = order;
__entry->gfp_flags = gfp_flags;
__entry->migratetype = migratetype;
),
TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s",
__entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL,
__entry->pfn != -1UL ? __entry->pfn : 0,
__entry->order,
__entry->migratetype,
show_gfp_flags(__entry->gfp_flags))
);
DECLARE_EVENT_CLASS(mm_page,
TP_PROTO(struct page *page, unsigned int order, int migratetype),
TP_ARGS(page, order, migratetype),
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( unsigned int, order )
__field( int, migratetype )
),
TP_fast_assign(
__entry->pfn = page ? page_to_pfn(page) : -1UL;
__entry->order = order;
__entry->migratetype = migratetype;
),
TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d",
__entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL,
__entry->pfn != -1UL ? __entry->pfn : 0,
__entry->order,
__entry->migratetype,
__entry->order == 0)
);
DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
TP_PROTO(struct page *page, unsigned int order, int migratetype),
TP_ARGS(page, order, migratetype)
);
TRACE_EVENT_CONDITION(mm_page_pcpu_drain,
TP_PROTO(struct page *page, unsigned int order, int migratetype),
TP_ARGS(page, order, migratetype),
/*
* This trace can be potentially called from an offlined cpu.
* Since trace points use RCU and RCU should not be used from
* offline cpus, filter such calls out.
* While this trace can be called from a preemptable section,
* it has no impact on the condition since tasks can migrate
* only from online cpus to other online cpus. Thus its safe
* to use raw_smp_processor_id.
*/
TP_CONDITION(cpu_online(raw_smp_processor_id())),
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( unsigned int, order )
__field( int, migratetype )
),
TP_fast_assign(
__entry->pfn = page ? page_to_pfn(page) : -1UL;
__entry->order = order;
__entry->migratetype = migratetype;
),
TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
pfn_to_page(__entry->pfn), __entry->pfn,
__entry->order, __entry->migratetype)
);
TRACE_EVENT(mm_page_alloc_extfrag,
TP_PROTO(struct page *page,
int alloc_order, int fallback_order,
int alloc_migratetype, int fallback_migratetype),
TP_ARGS(page,
alloc_order, fallback_order,
alloc_migratetype, fallback_migratetype),
TP_STRUCT__entry(
__field( unsigned long, pfn )
__field( int, alloc_order )
__field( int, fallback_order )
__field( int, alloc_migratetype )
__field( int, fallback_migratetype )
__field( int, change_ownership )
),
TP_fast_assign(
__entry->pfn = page_to_pfn(page);
__entry->alloc_order = alloc_order;
__entry->fallback_order = fallback_order;
__entry->alloc_migratetype = alloc_migratetype;
__entry->fallback_migratetype = fallback_migratetype;
__entry->change_ownership = (alloc_migratetype ==
get_pageblock_migratetype(page));
),
TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
pfn_to_page(__entry->pfn),
__entry->pfn,
__entry->alloc_order,
__entry->fallback_order,
pageblock_order,
__entry->alloc_migratetype,
__entry->fallback_migratetype,
__entry->fallback_order < pageblock_order,
__entry->change_ownership)
);
#endif /* _TRACE_KMEM_H */
/* This part must be outside protection */
#include <trace/define_trace.h>