Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1670023 > unrolled thread

[PATCH 4/4] percpu: add tracepoint support for percpu memory

Started byDennis Zhou <dennisz@fb.com>
First post2017-06-20 01:30 +0200
Last post2017-06-21 20:00 +0200
Articles 3 — 3 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCH 4/4] percpu: add tracepoint support for percpu memory Dennis Zhou <dennisz@fb.com> - 2017-06-20 01:30 +0200
    Re: [PATCH 4/4] percpu: add tracepoint support for percpu memory "Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com> - 2017-06-21 18:30 +0200
      Re: [PATCH 1/1] percpu: fix early calls for spinlock in pcpu_stats Tejun Heo <tj@kernel.org> - 2017-06-21 20:00 +0200

#1670023 — [PATCH 4/4] percpu: add tracepoint support for percpu memory

FromDennis Zhou <dennisz@fb.com>
Date2017-06-20 01:30 +0200
Subject[PATCH 4/4] percpu: add tracepoint support for percpu memory
Message-ID<tUehj-Na-13@gated-at.bofh.it>
Add support for tracepoints to the following events: chunk allocation,
chunk free, area allocation, area free, and area allocation failure.
This should let us replay percpu memory requests and evaluate
corresponding decisions.

Signed-off-by: Dennis Zhou <dennisz@fb.com>
---
 include/trace/events/percpu.h | 125 ++++++++++++++++++++++++++++++++++++++++++
 mm/percpu-km.c                |   2 +
 mm/percpu-vm.c                |   2 +
 mm/percpu.c                   |  12 ++++
 4 files changed, 141 insertions(+)
 create mode 100644 include/trace/events/percpu.h

diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h
new file mode 100644
index 0000000..ad34b1b
--- /dev/null
+++ b/include/trace/events/percpu.h
@@ -0,0 +1,125 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM percpu
+
+#if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PERCPU_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(percpu_alloc_percpu,
+
+	TP_PROTO(bool reserved, bool is_atomic, size_t size,
+		 size_t align, void *base_addr, int off, void __percpu *ptr),
+
+	TP_ARGS(reserved, is_atomic, size, align, base_addr, off, ptr),
+
+	TP_STRUCT__entry(
+		__field(	bool,			reserved	)
+		__field(	bool,			is_atomic	)
+		__field(	size_t,			size		)
+		__field(	size_t,			align		)
+		__field(	void *,			base_addr	)
+		__field(	int,			off		)
+		__field(	void __percpu *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->reserved	= reserved;
+		__entry->is_atomic	= is_atomic;
+		__entry->size		= size;
+		__entry->align		= align;
+		__entry->base_addr	= base_addr;
+		__entry->off		= off;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p",
+		  __entry->reserved, __entry->is_atomic,
+		  __entry->size, __entry->align,
+		  __entry->base_addr, __entry->off, __entry->ptr)
+);
+
+TRACE_EVENT(percpu_free_percpu,
+
+	TP_PROTO(void *base_addr, int off, void __percpu *ptr),
+
+	TP_ARGS(base_addr, off, ptr),
+
+	TP_STRUCT__entry(
+		__field(	void *,			base_addr	)
+		__field(	int,			off		)
+		__field(	void __percpu *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->base_addr	= base_addr;
+		__entry->off		= off;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("base_addr=%p off=%d ptr=%p",
+		__entry->base_addr, __entry->off, __entry->ptr)
+);
+
+TRACE_EVENT(percpu_alloc_percpu_fail,
+
+	TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align),
+
+	TP_ARGS(reserved, is_atomic, size, align),
+
+	TP_STRUCT__entry(
+		__field(	bool,	reserved	)
+		__field(	bool,	is_atomic	)
+		__field(	size_t,	size		)
+		__field(	size_t, align		)
+	),
+
+	TP_fast_assign(
+		__entry->reserved	= reserved;
+		__entry->is_atomic	= is_atomic;
+		__entry->size		= size;
+		__entry->align		= align;
+	),
+
+	TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu",
+		  __entry->reserved, __entry->is_atomic,
+		  __entry->size, __entry->align)
+);
+
+TRACE_EVENT(percpu_create_chunk,
+
+	TP_PROTO(void *base_addr),
+
+	TP_ARGS(base_addr),
+
+	TP_STRUCT__entry(
+		__field(	void *, base_addr	)
+	),
+
+	TP_fast_assign(
+		__entry->base_addr	= base_addr;
+	),
+
+	TP_printk("base_addr=%p", __entry->base_addr)
+);
+
+TRACE_EVENT(percpu_destroy_chunk,
+
+	TP_PROTO(void *base_addr),
+
+	TP_ARGS(base_addr),
+
+	TP_STRUCT__entry(
+		__field(	void *,	base_addr	)
+	),
+
+	TP_fast_assign(
+		__entry->base_addr	= base_addr;
+	),
+
+	TP_printk("base_addr=%p", __entry->base_addr)
+);
+
+#endif /* _TRACE_PERCPU_H */
+
+#include <trace/define_trace.h>
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index 3bbfa0c..2b79e43 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -73,6 +73,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 	spin_unlock_irq(&pcpu_lock);
 
 	pcpu_stats_chunk_alloc();
+	trace_percpu_create_chunk(chunk->base_addr);
 
 	return chunk;
 }
@@ -82,6 +83,7 @@ static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
 	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
 
 	pcpu_stats_chunk_dealloc();
+	trace_percpu_destroy_chunk(chunk->base_addr);
 
 	if (chunk && chunk->data)
 		__free_pages(chunk->data, order_base_2(nr_pages));
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 5915a22..7ad9d94 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -345,6 +345,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 	chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
 
 	pcpu_stats_chunk_alloc();
+	trace_percpu_create_chunk(chunk->base_addr);
 
 	return chunk;
 }
@@ -352,6 +353,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
 {
 	pcpu_stats_chunk_dealloc();
+	trace_percpu_destroy_chunk(chunk->base_addr);
 
 	if (chunk && chunk->data)
 		pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
diff --git a/mm/percpu.c b/mm/percpu.c
index 25b4ba5..7a1707a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -76,6 +76,9 @@
 #include <asm/tlbflush.h>
 #include <asm/io.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/percpu.h>
+
 #include "percpu-internal.h"
 
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
@@ -1015,11 +1018,17 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 
 	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
 	kmemleak_alloc_percpu(ptr, size, gfp);
+
+	trace_percpu_alloc_percpu(reserved, is_atomic, size, align,
+			chunk->base_addr, off, ptr);
+
 	return ptr;
 
 fail_unlock:
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 fail:
+	trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);
+
 	if (!is_atomic && warn_limit) {
 		pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
 			size, align, is_atomic, err);
@@ -1269,6 +1278,8 @@ void free_percpu(void __percpu *ptr)
 			}
 	}
 
+	trace_percpu_free_percpu(chunk->base_addr, off, ptr);
+
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 }
 EXPORT_SYMBOL_GPL(free_percpu);
@@ -1719,6 +1730,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	pcpu_stats_chunk_alloc();
+	trace_percpu_create_chunk(base_addr);
 
 	/* we're done */
 	pcpu_base_addr = base_addr;
-- 
2.9.3

[toc] | [next] | [standalone]

#1671758

From"Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com>
Date2017-06-21 18:30 +0200
Message-ID<tUQFY-8uH-13@gated-at.bofh.it>
In reply to#1670023
On Mon, Jun 19, 2017 at 07:28:32PM -0400, Dennis Zhou wrote:
>Add support for tracepoints to the following events: chunk allocation,
>chunk free, area allocation, area free, and area allocation failure.
>This should let us replay percpu memory requests and evaluate
>corresponding decisions.

This patch breaks boot for me:

[    0.000000] DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled))
[    0.000000] ------------[ cut here ]------------
[    0.000000] WARNING: CPU: 0 PID: 0 at kernel/locking/lockdep.c:2741 trace_hardirqs_on_caller.cold.58+0x47/0x4e
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 4.12.0-rc6-next-20170621+ #155
[    0.000000] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014
[    0.000000] task: ffffffffb7831180 task.stack: ffffffffb7800000
[    0.000000] RIP: 0010:trace_hardirqs_on_caller.cold.58+0x47/0x4e
[    0.000000] RSP: 0000:ffffffffb78079d0 EFLAGS: 00010086 ORIG_RAX: 0000000000000000
[    0.000000] RAX: 0000000000000037 RBX: 0000000000000003 RCX: 0000000000000000
[    0.000000] RDX: 0000000000000000 RSI: 0000000000000001 RDI: 1ffffffff6f00ef6
[    0.000000] RBP: ffffffffb78079e0 R08: 0000000000000000 R09: ffffffffb7831180
[    0.000000] R10: 0000000000000000 R11: ffffffffb24e96ce R12: ffffffffb6b39b87
[    0.000000] R13: 00000000001f0001 R14: ffffffffb85603a0 R15: 0000000000002000
[    0.000000] FS:  0000000000000000(0000) GS:ffffffffb81be000(0000) knlGS:0000000000000000
[    0.000000] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    0.000000] CR2: ffff88007fbff000 CR3: 000000006b828000 CR4: 00000000000406b0
[    0.000000] Call Trace:
[    0.000000]  trace_hardirqs_on+0xd/0x10
[    0.000000]  _raw_spin_unlock_irq+0x27/0x50
[    0.000000]  pcpu_setup_first_chunk+0x19c2/0x1c27
[    0.000000]  ? pcpu_free_alloc_info+0x4b/0x4b
[    0.000000]  ? vprintk_emit+0x403/0x480
[    0.000000]  ? __down_trylock_console_sem+0xb7/0xc0
[    0.000000]  ? __down_trylock_console_sem+0x6e/0xc0
[    0.000000]  ? vprintk_emit+0x362/0x480
[    0.000000]  ? vprintk_default+0x28/0x30
[    0.000000]  ? printk+0xb2/0xdd
[    0.000000]  ? snapshot_ioctl.cold.1+0x19/0x19
[    0.000000]  ? __alloc_bootmem_node_nopanic+0x88/0x96
[    0.000000]  pcpu_embed_first_chunk+0x7b0/0x8ef
[    0.000000]  ? pcpup_populate_pte+0xb/0xb
[    0.000000]  setup_per_cpu_areas+0x105/0x6d9
[    0.000000]  ? find_last_bit+0xa6/0xd0
[    0.000000]  start_kernel+0x25e/0x78f
[    0.000000]  ? thread_stack_cache_init+0xb/0xb
[    0.000000]  ? early_idt_handler_common+0x3b/0x52
[    0.000000]  ? early_idt_handler_array+0x120/0x120
[    0.000000]  ? early_idt_handler_array+0x120/0x120
[    0.000000]  x86_64_start_reservations+0x24/0x26
[    0.000000]  x86_64_start_kernel+0x143/0x166
[    0.000000]  secondary_startup_64+0x9f/0x9f
[    0.000000] Code: c6 a0 49 c6 b6 48 c7 c7 e0 49 c6 b6 e8 43 34 00 00 0f ff e9 ed 71 ce ff 48 c7 c6 c0 79 c6 b6 48 c7 c7 e0 49 c6 b6 e8 29 34 00 00 <0f> ff e9 d3 71 ce ff 48 c7 c6 20 7c c6 b6 48 c7 c7 e0 49 c6 b6 
[    0.000000] random: print_oops_end_marker+0x30/0x50 get_random_bytes called with crng_init=0
[    0.000000] ---[ end trace f68728a0d3053b52 ]---
[    0.000000] BUG: unable to handle kernel paging request at 00000000ffffffff
[    0.000000] IP: native_write_msr+0x6/0x30
[    0.000000] PGD 0 
[    0.000000] P4D 0 
[    0.000000] 
[    0.000000] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Tainted: G        W       4.12.0-rc6-next-20170621+ #155
[    0.000000] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014
[    0.000000] task: ffffffffb7831180 task.stack: ffffffffb7800000
[    0.000000] RIP: 0010:native_write_msr+0x6/0x30
[    0.000000] RSP: 0000:ffffffffb7807dc8 EFLAGS: 00010202
[    0.000000] RAX: 000000003ea15d43 RBX: ffff88003ea15d40 RCX: 000000004b564d02
[    0.000000] RDX: 0000000000000000 RSI: 000000003ea15d43 RDI: 000000004b564d02
[    0.000000] RBP: ffffffffb7807df0 R08: 0000000000000040 R09: 0000000000000000
[    0.000000] R10: 0000000000007100 R11: 000000007ffd6f00 R12: 0000000000000000
[    0.000000] R13: 1ffffffff6f00fc3 R14: ffffffffb7807eb8 R15: dffffc0000000000
[    0.000000] FS:  0000000000000000(0000) GS:ffff88003ea00000(0000) knlGS:0000000000000000
[    0.000000] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    0.000000] CR2: 00000000ffffffff CR3: 000000006b828000 CR4: 00000000000406b0
[    0.000000] Call Trace:
[    0.000000]  ? kvm_guest_cpu_init+0x155/0x220
[    0.000000]  kvm_smp_prepare_boot_cpu+0x9/0x10
[    0.000000]  start_kernel+0x28c/0x78f
[    0.000000]  ? thread_stack_cache_init+0xb/0xb
[    0.000000]  ? early_idt_handler_common+0x3b/0x52
[    0.000000]  ? early_idt_handler_array+0x120/0x120
[    0.000000]  ? early_idt_handler_array+0x120/0x120
[    0.000000]  x86_64_start_reservations+0x24/0x26
[    0.000000]  x86_64_start_kernel+0x143/0x166
[    0.000000]  secondary_startup_64+0x9f/0x9f
[    0.000000] Code: c3 0f 21 c8 5d c3 0f 21 d0 5d c3 0f 21 d8 5d c3 0f 21 f0 5d c3 0f 0b 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 89 f9 89 f0 0f 30 <0f> 1f 44 00 00 c3 48 89 d6 55 89 c2 48 c1 e6 20 48 89 e5 48 09 
[    0.000000] RIP: native_write_msr+0x6/0x30 RSP: ffffffffb7807dc8
[    0.000000] CR2: 00000000ffffffff
[    0.000000] ---[ end trace f68728a0d3053b53 ]---
[    0.000000] Kernel panic - not syncing: Fatal exception
[    0.000000] ---[ end Kernel panic - not syncing: Fatal exception

-- 

Thanks,
Sasha

[toc] | [prev] | [next] | [standalone]

#1671865 — Re: [PATCH 1/1] percpu: fix early calls for spinlock in pcpu_stats

FromTejun Heo <tj@kernel.org>
Date2017-06-21 20:00 +0200
SubjectRe: [PATCH 1/1] percpu: fix early calls for spinlock in pcpu_stats
Message-ID<tUS55-VR-27@gated-at.bofh.it>
In reply to#1671758
On Wed, Jun 21, 2017 at 01:52:46PM -0400, Dennis Zhou wrote:
> From 2c06e795162cb306c9707ec51d3e1deadb37f573 Mon Sep 17 00:00:00 2001
> From: Dennis Zhou <dennisz@fb.com>
> Date: Wed, 21 Jun 2017 10:17:09 -0700
> 
> Commit 30a5b5367ef9 ("percpu: expose statistics about percpu memory via
> debugfs") introduces percpu memory statistics. pcpu_stats_chunk_alloc
> takes the spin lock and disables/enables irqs on creation of a chunk. Irqs
> are not enabled when the first chunk is initialized and thus kernels are
> failing to boot with kernel debugging enabled. Fixed by changing _irq to
> _irqsave and _irqrestore.
> 
> Fixes: 30a5b5367ef9 ("percpu: expose statistics about percpu memory via debugfs")
> Signed-off-by: Dennis Zhou <dennisz@fb.com>
> Reported-by: Alexander Levin <alexander.levin@verizon.com>

Applied to percpu/for-4.13.

Thanks.

-- 
tejun

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web