* [patch 1/6] Use EXTRARW_DATA in architectures
2007-05-30 14:03 [patch 0/6] Linux Kernel Markers - for 2.6.22-rc2-mm1 Mathieu Desnoyers
@ 2007-05-30 14:04 ` Mathieu Desnoyers
2007-05-30 14:04 ` [patch 2/6] Linux Kernel Markers, architecture independent code Mathieu Desnoyers
` (4 subsequent siblings)
5 siblings, 0 replies; 8+ messages in thread
From: Mathieu Desnoyers @ 2007-05-30 14:04 UTC (permalink / raw)
To: akpm, linux-kernel; +Cc: Mathieu Desnoyers, linux-arch
[-- Attachment #1: use-extra_rwdata-in-architectures.patch --]
[-- Type: text/plain, Size: 15701 bytes --]
EXTRARW_DATA adds a place to declare rw data that will not be mixed with the
.data content; therefore limiting data cache pollution when data is put in
the EXTRARW_DATA sections.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: <linux-arch@vger.kernel.org>
---
arch/alpha/kernel/vmlinux.lds.S | 1 +
arch/arm/kernel/vmlinux.lds.S | 1 +
arch/arm26/kernel/vmlinux-arm26-xip.lds.in | 1 +
arch/arm26/kernel/vmlinux-arm26.lds.in | 1 +
arch/avr32/kernel/vmlinux.lds.c | 1 +
arch/cris/arch-v10/vmlinux.lds.S | 1 +
arch/cris/arch-v32/vmlinux.lds.S | 1 +
arch/frv/kernel/vmlinux.lds.S | 1 +
arch/h8300/kernel/vmlinux.lds.S | 3 ++-
arch/i386/kernel/vmlinux.lds.S | 1 +
arch/ia64/kernel/vmlinux.lds.S | 1 +
arch/m32r/kernel/vmlinux.lds.S | 1 +
arch/m68k/kernel/vmlinux-std.lds | 1 +
arch/m68k/kernel/vmlinux-sun3.lds | 1 +
arch/m68knommu/kernel/vmlinux.lds.S | 1 +
arch/mips/kernel/vmlinux.lds.S | 3 +--
arch/parisc/kernel/vmlinux.lds.S | 1 +
arch/powerpc/kernel/vmlinux.lds.S | 2 ++
arch/ppc/kernel/vmlinux.lds.S | 1 +
arch/s390/kernel/vmlinux.lds.S | 1 +
arch/sh/kernel/vmlinux.lds.S | 2 +-
arch/sh64/kernel/vmlinux.lds.S | 1 +
arch/sparc/kernel/vmlinux.lds.S | 1 +
arch/sparc64/kernel/vmlinux.lds.S | 1 +
arch/um/kernel/dyn.lds.S | 1 +
arch/um/kernel/uml.lds.S | 1 +
arch/v850/kernel/vmlinux.lds.S | 1 +
arch/x86_64/kernel/vmlinux.lds.S | 1 +
arch/xtensa/kernel/vmlinux.lds.S | 1 +
include/asm-generic/vmlinux.lds.h | 5 +++++
30 files changed, 36 insertions(+), 4 deletions(-)
Index: linux-2.6-lttng/arch/alpha/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/alpha/kernel/vmlinux.lds.S 2007-05-30 08:42:26.000000000 -0400
+++ linux-2.6-lttng/arch/alpha/kernel/vmlinux.lds.S 2007-05-30 08:51:20.000000000 -0400
@@ -90,6 +90,7 @@
_data = .;
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/arm/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/arm/kernel/vmlinux.lds.S 2007-05-30 08:42:27.000000000 -0400
+++ linux-2.6-lttng/arch/arm/kernel/vmlinux.lds.S 2007-05-30 08:51:52.000000000 -0400
@@ -159,6 +159,7 @@
* and the usual data section
*/
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
_edata = .;
Index: linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26-xip.lds.in
===================================================================
--- linux-2.6-lttng.orig/arch/arm26/kernel/vmlinux-arm26-xip.lds.in 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26-xip.lds.in 2007-05-30 08:52:12.000000000 -0400
@@ -112,6 +112,7 @@
* and the usual data section
*/
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
*(.init.data)
Index: linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26.lds.in
===================================================================
--- linux-2.6-lttng.orig/arch/arm26/kernel/vmlinux-arm26.lds.in 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26.lds.in 2007-05-30 08:52:28.000000000 -0400
@@ -107,6 +107,7 @@
* and the usual data section
*/
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
_edata = .;
Index: linux-2.6-lttng/arch/avr32/kernel/vmlinux.lds.c
===================================================================
--- linux-2.6-lttng.orig/arch/avr32/kernel/vmlinux.lds.c 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/avr32/kernel/vmlinux.lds.c 2007-05-30 08:52:45.000000000 -0400
@@ -113,6 +113,7 @@
/* And the rest... */
*(.data.rel*)
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
_edata = .;
Index: linux-2.6-lttng/arch/cris/arch-v10/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/cris/arch-v10/vmlinux.lds.S 2007-05-30 08:27:48.000000000 -0400
+++ linux-2.6-lttng/arch/cris/arch-v10/vmlinux.lds.S 2007-05-30 08:53:15.000000000 -0400
@@ -45,6 +45,7 @@
__Sdata = . ;
.data : { /* Data */
*(.data)
+ EXTRARW_DATA
}
__edata = . ; /* End of data section */
_edata = . ;
Index: linux-2.6-lttng/arch/cris/arch-v32/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/cris/arch-v32/vmlinux.lds.S 2007-05-30 08:42:01.000000000 -0400
+++ linux-2.6-lttng/arch/cris/arch-v32/vmlinux.lds.S 2007-05-30 08:53:28.000000000 -0400
@@ -50,6 +50,7 @@
__Sdata = . ;
.data : { /* Data */
*(.data)
+ EXTRARW_DATA
}
__edata = . ; /* End of data section. */
_edata = . ;
Index: linux-2.6-lttng/arch/frv/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/frv/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/frv/kernel/vmlinux.lds.S 2007-05-30 08:53:58.000000000 -0400
@@ -139,6 +139,7 @@
DATA_DATA
*(.data.*)
*(.exit.data)
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/h8300/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/h8300/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/h8300/kernel/vmlinux.lds.S 2007-05-30 09:01:29.000000000 -0400
@@ -105,7 +105,8 @@
. = ALIGN(0x4) ;
DATA_DATA
. = ALIGN(0x4) ;
- *(.data.*)
+ *(.data.*)
+ EXTRARW_DATA
. = ALIGN(0x4) ;
___init_begin = .;
Index: linux-2.6-lttng/arch/i386/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/i386/kernel/vmlinux.lds.S 2007-05-30 08:42:44.000000000 -0400
+++ linux-2.6-lttng/arch/i386/kernel/vmlinux.lds.S 2007-05-30 08:54:39.000000000 -0400
@@ -77,6 +77,7 @@
. = ALIGN(4096);
.data : AT(ADDR(.data) - LOAD_OFFSET) { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
} :data
Index: linux-2.6-lttng/arch/ia64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/ia64/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/ia64/kernel/vmlinux.lds.S 2007-05-30 08:54:52.000000000 -0400
@@ -216,6 +216,7 @@
.data : AT(ADDR(.data) - LOAD_OFFSET)
{
DATA_DATA
+ EXTRARW_DATA
*(.data1)
*(.gnu.linkonce.d*)
CONSTRUCTORS
Index: linux-2.6-lttng/arch/m32r/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/m32r/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m32r/kernel/vmlinux.lds.S 2007-05-30 08:55:06.000000000 -0400
@@ -51,6 +51,7 @@
*(.spu)
*(.spi)
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/m68k/kernel/vmlinux-std.lds
===================================================================
--- linux-2.6-lttng.orig/arch/m68k/kernel/vmlinux-std.lds 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m68k/kernel/vmlinux-std.lds 2007-05-30 08:55:16.000000000 -0400
@@ -29,6 +29,7 @@
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/m68k/kernel/vmlinux-sun3.lds
===================================================================
--- linux-2.6-lttng.orig/arch/m68k/kernel/vmlinux-sun3.lds 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m68k/kernel/vmlinux-sun3.lds 2007-05-30 08:55:28.000000000 -0400
@@ -24,6 +24,7 @@
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
. = ALIGN(16); /* Exception table */
__start___ex_table = .;
Index: linux-2.6-lttng/arch/m68knommu/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/m68knommu/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m68knommu/kernel/vmlinux.lds.S 2007-05-30 08:55:40.000000000 -0400
@@ -134,6 +134,7 @@
. = ALIGN(4);
_sdata = . ;
DATA_DATA
+ EXTRARW_DATA
. = ALIGN(8192) ;
*(.data.init_task)
_edata = . ;
Index: linux-2.6-lttng/arch/mips/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/mips/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/mips/kernel/vmlinux.lds.S 2007-05-30 08:55:59.000000000 -0400
@@ -61,9 +61,8 @@
*/
. = ALIGN(_PAGE_SIZE);
*(.data.init_task)
-
DATA_DATA
-
+ EXTRARW_DATA
CONSTRUCTORS
}
_gp = . + 0x8000;
Index: linux-2.6-lttng/arch/parisc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/parisc/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/parisc/kernel/vmlinux.lds.S 2007-05-30 08:56:12.000000000 -0400
@@ -92,6 +92,7 @@
. = ALIGN(L1_CACHE_BYTES);
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/powerpc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/powerpc/kernel/vmlinux.lds.S 2007-05-30 08:42:29.000000000 -0400
+++ linux-2.6-lttng/arch/powerpc/kernel/vmlinux.lds.S 2007-05-30 08:56:54.000000000 -0400
@@ -170,11 +170,13 @@
DATA_DATA
*(.sdata)
*(.got.plt) *(.got)
+ EXTRARW_DATA
}
#else
.data : {
*(.data .data.rel* .toc1)
*(.branch_lt)
+ EXTRARW_DATA
}
.opd : {
Index: linux-2.6-lttng/arch/ppc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/ppc/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/ppc/kernel/vmlinux.lds.S 2007-05-30 08:56:47.000000000 -0400
@@ -73,6 +73,7 @@
*(.sdata2)
*(.got.plt) *(.got)
*(.dynamic)
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/s390/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/s390/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/s390/kernel/vmlinux.lds.S 2007-05-30 08:57:08.000000000 -0400
@@ -49,6 +49,7 @@
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/sh/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sh/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sh/kernel/vmlinux.lds.S 2007-05-30 08:57:26.000000000 -0400
@@ -49,7 +49,7 @@
*(.initrd)
. = ALIGN(PAGE_SIZE);
__rd_end = .;
-
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/sh64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sh64/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sh64/kernel/vmlinux.lds.S 2007-05-30 08:57:39.000000000 -0400
@@ -79,6 +79,7 @@
.data : C_PHYS(.data) { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/sparc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sparc/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sparc/kernel/vmlinux.lds.S 2007-05-30 08:57:51.000000000 -0400
@@ -23,6 +23,7 @@
.data :
{
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/sparc64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sparc64/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sparc64/kernel/vmlinux.lds.S 2007-05-30 08:58:01.000000000 -0400
@@ -28,6 +28,7 @@
.data :
{
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/um/kernel/dyn.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/um/kernel/dyn.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/um/kernel/dyn.lds.S 2007-05-30 08:58:15.000000000 -0400
@@ -101,6 +101,7 @@
*(.data.init_irqstack)
DATA_DATA
*(.data.* .gnu.linkonce.d.*)
+ EXTRARW_DATA
SORT(CONSTRUCTORS)
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/um/kernel/uml.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/um/kernel/uml.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/um/kernel/uml.lds.S 2007-05-30 08:58:27.000000000 -0400
@@ -63,6 +63,7 @@
*(.data.init_irqstack)
DATA_DATA
*(.gnu.linkonce.d*)
+ EXTRARW_DATA
CONSTRUCTORS
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/v850/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/v850/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/v850/kernel/vmlinux.lds.S 2007-05-30 08:58:45.000000000 -0400
@@ -116,6 +116,7 @@
DATA_DATA \
*(.exit.data) /* 2.5 convention */ \
*(.data.exit) /* 2.4 convention */ \
+ EXTRARW_DATA \
. = ALIGN (16) ; \
*(.data.cacheline_aligned) \
. = ALIGN (0x2000) ; \
Index: linux-2.6-lttng/arch/x86_64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/x86_64/kernel/vmlinux.lds.S 2007-05-30 08:42:43.000000000 -0400
+++ linux-2.6-lttng/arch/x86_64/kernel/vmlinux.lds.S 2007-05-30 08:58:55.000000000 -0400
@@ -56,6 +56,7 @@
/* Data */
.data : AT(ADDR(.data) - LOAD_OFFSET) {
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
} :data
Index: linux-2.6-lttng/arch/xtensa/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/xtensa/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/xtensa/kernel/vmlinux.lds.S 2007-05-30 08:59:09.000000000 -0400
@@ -146,6 +146,7 @@
.data :
{
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
. = ALIGN(XCHAL_ICACHE_LINESIZE);
*(.data.cacheline_aligned)
Index: linux-2.6-lttng/include/asm-generic/vmlinux.lds.h
===================================================================
--- linux-2.6-lttng.orig/include/asm-generic/vmlinux.lds.h 2007-05-30 08:43:11.000000000 -0400
+++ linux-2.6-lttng/include/asm-generic/vmlinux.lds.h 2007-05-30 09:04:19.000000000 -0400
@@ -150,6 +150,11 @@
\
. = ALIGN(4096);
+/* EXTRARW_DATA adds a place to declare rw data that will not be mixed with the
+ * .data content; therefore limiting data cache pollution when data is put in
+ * the EXTRARW_DATA sections. */
+#define EXTRARW_DATA
+
#define SECURITY_INIT \
.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__security_initcall_start) = .; \
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
^ permalink raw reply [flat|nested] 8+ messages in thread* [patch 1/6] Use EXTRARW_DATA in architectures
@ 2007-05-30 14:04 ` Mathieu Desnoyers
0 siblings, 0 replies; 8+ messages in thread
From: Mathieu Desnoyers @ 2007-05-30 14:04 UTC (permalink / raw)
To: akpm, linux-kernel; +Cc: Mathieu Desnoyers, linux-arch
[-- Attachment #1: use-extra_rwdata-in-architectures.patch --]
[-- Type: text/plain, Size: 15701 bytes --]
EXTRARW_DATA adds a place to declare rw data that will not be mixed with the
.data content; therefore limiting data cache pollution when data is put in
the EXTRARW_DATA sections.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: <linux-arch@vger.kernel.org>
---
arch/alpha/kernel/vmlinux.lds.S | 1 +
arch/arm/kernel/vmlinux.lds.S | 1 +
arch/arm26/kernel/vmlinux-arm26-xip.lds.in | 1 +
arch/arm26/kernel/vmlinux-arm26.lds.in | 1 +
arch/avr32/kernel/vmlinux.lds.c | 1 +
arch/cris/arch-v10/vmlinux.lds.S | 1 +
arch/cris/arch-v32/vmlinux.lds.S | 1 +
arch/frv/kernel/vmlinux.lds.S | 1 +
arch/h8300/kernel/vmlinux.lds.S | 3 ++-
arch/i386/kernel/vmlinux.lds.S | 1 +
arch/ia64/kernel/vmlinux.lds.S | 1 +
arch/m32r/kernel/vmlinux.lds.S | 1 +
arch/m68k/kernel/vmlinux-std.lds | 1 +
arch/m68k/kernel/vmlinux-sun3.lds | 1 +
arch/m68knommu/kernel/vmlinux.lds.S | 1 +
arch/mips/kernel/vmlinux.lds.S | 3 +--
arch/parisc/kernel/vmlinux.lds.S | 1 +
arch/powerpc/kernel/vmlinux.lds.S | 2 ++
arch/ppc/kernel/vmlinux.lds.S | 1 +
arch/s390/kernel/vmlinux.lds.S | 1 +
arch/sh/kernel/vmlinux.lds.S | 2 +-
arch/sh64/kernel/vmlinux.lds.S | 1 +
arch/sparc/kernel/vmlinux.lds.S | 1 +
arch/sparc64/kernel/vmlinux.lds.S | 1 +
arch/um/kernel/dyn.lds.S | 1 +
arch/um/kernel/uml.lds.S | 1 +
arch/v850/kernel/vmlinux.lds.S | 1 +
arch/x86_64/kernel/vmlinux.lds.S | 1 +
arch/xtensa/kernel/vmlinux.lds.S | 1 +
include/asm-generic/vmlinux.lds.h | 5 +++++
30 files changed, 36 insertions(+), 4 deletions(-)
Index: linux-2.6-lttng/arch/alpha/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/alpha/kernel/vmlinux.lds.S 2007-05-30 08:42:26.000000000 -0400
+++ linux-2.6-lttng/arch/alpha/kernel/vmlinux.lds.S 2007-05-30 08:51:20.000000000 -0400
@@ -90,6 +90,7 @@
_data = .;
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/arm/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/arm/kernel/vmlinux.lds.S 2007-05-30 08:42:27.000000000 -0400
+++ linux-2.6-lttng/arch/arm/kernel/vmlinux.lds.S 2007-05-30 08:51:52.000000000 -0400
@@ -159,6 +159,7 @@
* and the usual data section
*/
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
_edata = .;
Index: linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26-xip.lds.in
===================================================================
--- linux-2.6-lttng.orig/arch/arm26/kernel/vmlinux-arm26-xip.lds.in 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26-xip.lds.in 2007-05-30 08:52:12.000000000 -0400
@@ -112,6 +112,7 @@
* and the usual data section
*/
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
*(.init.data)
Index: linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26.lds.in
===================================================================
--- linux-2.6-lttng.orig/arch/arm26/kernel/vmlinux-arm26.lds.in 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/arm26/kernel/vmlinux-arm26.lds.in 2007-05-30 08:52:28.000000000 -0400
@@ -107,6 +107,7 @@
* and the usual data section
*/
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
_edata = .;
Index: linux-2.6-lttng/arch/avr32/kernel/vmlinux.lds.c
===================================================================
--- linux-2.6-lttng.orig/arch/avr32/kernel/vmlinux.lds.c 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/avr32/kernel/vmlinux.lds.c 2007-05-30 08:52:45.000000000 -0400
@@ -113,6 +113,7 @@
/* And the rest... */
*(.data.rel*)
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
_edata = .;
Index: linux-2.6-lttng/arch/cris/arch-v10/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/cris/arch-v10/vmlinux.lds.S 2007-05-30 08:27:48.000000000 -0400
+++ linux-2.6-lttng/arch/cris/arch-v10/vmlinux.lds.S 2007-05-30 08:53:15.000000000 -0400
@@ -45,6 +45,7 @@
__Sdata = . ;
.data : { /* Data */
*(.data)
+ EXTRARW_DATA
}
__edata = . ; /* End of data section */
_edata = . ;
Index: linux-2.6-lttng/arch/cris/arch-v32/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/cris/arch-v32/vmlinux.lds.S 2007-05-30 08:42:01.000000000 -0400
+++ linux-2.6-lttng/arch/cris/arch-v32/vmlinux.lds.S 2007-05-30 08:53:28.000000000 -0400
@@ -50,6 +50,7 @@
__Sdata = . ;
.data : { /* Data */
*(.data)
+ EXTRARW_DATA
}
__edata = . ; /* End of data section. */
_edata = . ;
Index: linux-2.6-lttng/arch/frv/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/frv/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/frv/kernel/vmlinux.lds.S 2007-05-30 08:53:58.000000000 -0400
@@ -139,6 +139,7 @@
DATA_DATA
*(.data.*)
*(.exit.data)
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/h8300/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/h8300/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/h8300/kernel/vmlinux.lds.S 2007-05-30 09:01:29.000000000 -0400
@@ -105,7 +105,8 @@
. = ALIGN(0x4) ;
DATA_DATA
. = ALIGN(0x4) ;
- *(.data.*)
+ *(.data.*)
+ EXTRARW_DATA
. = ALIGN(0x4) ;
___init_begin = .;
Index: linux-2.6-lttng/arch/i386/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/i386/kernel/vmlinux.lds.S 2007-05-30 08:42:44.000000000 -0400
+++ linux-2.6-lttng/arch/i386/kernel/vmlinux.lds.S 2007-05-30 08:54:39.000000000 -0400
@@ -77,6 +77,7 @@
. = ALIGN(4096);
.data : AT(ADDR(.data) - LOAD_OFFSET) { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
} :data
Index: linux-2.6-lttng/arch/ia64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/ia64/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/ia64/kernel/vmlinux.lds.S 2007-05-30 08:54:52.000000000 -0400
@@ -216,6 +216,7 @@
.data : AT(ADDR(.data) - LOAD_OFFSET)
{
DATA_DATA
+ EXTRARW_DATA
*(.data1)
*(.gnu.linkonce.d*)
CONSTRUCTORS
Index: linux-2.6-lttng/arch/m32r/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/m32r/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m32r/kernel/vmlinux.lds.S 2007-05-30 08:55:06.000000000 -0400
@@ -51,6 +51,7 @@
*(.spu)
*(.spi)
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/m68k/kernel/vmlinux-std.lds
===================================================================
--- linux-2.6-lttng.orig/arch/m68k/kernel/vmlinux-std.lds 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m68k/kernel/vmlinux-std.lds 2007-05-30 08:55:16.000000000 -0400
@@ -29,6 +29,7 @@
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/m68k/kernel/vmlinux-sun3.lds
===================================================================
--- linux-2.6-lttng.orig/arch/m68k/kernel/vmlinux-sun3.lds 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m68k/kernel/vmlinux-sun3.lds 2007-05-30 08:55:28.000000000 -0400
@@ -24,6 +24,7 @@
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
. = ALIGN(16); /* Exception table */
__start___ex_table = .;
Index: linux-2.6-lttng/arch/m68knommu/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/m68knommu/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/m68knommu/kernel/vmlinux.lds.S 2007-05-30 08:55:40.000000000 -0400
@@ -134,6 +134,7 @@
. = ALIGN(4);
_sdata = . ;
DATA_DATA
+ EXTRARW_DATA
. = ALIGN(8192) ;
*(.data.init_task)
_edata = . ;
Index: linux-2.6-lttng/arch/mips/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/mips/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/mips/kernel/vmlinux.lds.S 2007-05-30 08:55:59.000000000 -0400
@@ -61,9 +61,8 @@
*/
. = ALIGN(_PAGE_SIZE);
*(.data.init_task)
-
DATA_DATA
-
+ EXTRARW_DATA
CONSTRUCTORS
}
_gp = . + 0x8000;
Index: linux-2.6-lttng/arch/parisc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/parisc/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/parisc/kernel/vmlinux.lds.S 2007-05-30 08:56:12.000000000 -0400
@@ -92,6 +92,7 @@
. = ALIGN(L1_CACHE_BYTES);
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/powerpc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/powerpc/kernel/vmlinux.lds.S 2007-05-30 08:42:29.000000000 -0400
+++ linux-2.6-lttng/arch/powerpc/kernel/vmlinux.lds.S 2007-05-30 08:56:54.000000000 -0400
@@ -170,11 +170,13 @@
DATA_DATA
*(.sdata)
*(.got.plt) *(.got)
+ EXTRARW_DATA
}
#else
.data : {
*(.data .data.rel* .toc1)
*(.branch_lt)
+ EXTRARW_DATA
}
.opd : {
Index: linux-2.6-lttng/arch/ppc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/ppc/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/ppc/kernel/vmlinux.lds.S 2007-05-30 08:56:47.000000000 -0400
@@ -73,6 +73,7 @@
*(.sdata2)
*(.got.plt) *(.got)
*(.dynamic)
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/s390/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/s390/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/s390/kernel/vmlinux.lds.S 2007-05-30 08:57:08.000000000 -0400
@@ -49,6 +49,7 @@
.data : { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/sh/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sh/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sh/kernel/vmlinux.lds.S 2007-05-30 08:57:26.000000000 -0400
@@ -49,7 +49,7 @@
*(.initrd)
. = ALIGN(PAGE_SIZE);
__rd_end = .;
-
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/sh64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sh64/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sh64/kernel/vmlinux.lds.S 2007-05-30 08:57:39.000000000 -0400
@@ -79,6 +79,7 @@
.data : C_PHYS(.data) { /* Data */
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
Index: linux-2.6-lttng/arch/sparc/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sparc/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sparc/kernel/vmlinux.lds.S 2007-05-30 08:57:51.000000000 -0400
@@ -23,6 +23,7 @@
.data :
{
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/sparc64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/sparc64/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/sparc64/kernel/vmlinux.lds.S 2007-05-30 08:58:01.000000000 -0400
@@ -28,6 +28,7 @@
.data :
{
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/um/kernel/dyn.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/um/kernel/dyn.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/um/kernel/dyn.lds.S 2007-05-30 08:58:15.000000000 -0400
@@ -101,6 +101,7 @@
*(.data.init_irqstack)
DATA_DATA
*(.data.* .gnu.linkonce.d.*)
+ EXTRARW_DATA
SORT(CONSTRUCTORS)
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/um/kernel/uml.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/um/kernel/uml.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/um/kernel/uml.lds.S 2007-05-30 08:58:27.000000000 -0400
@@ -63,6 +63,7 @@
*(.data.init_irqstack)
DATA_DATA
*(.gnu.linkonce.d*)
+ EXTRARW_DATA
CONSTRUCTORS
}
.data1 : { *(.data1) }
Index: linux-2.6-lttng/arch/v850/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/v850/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/v850/kernel/vmlinux.lds.S 2007-05-30 08:58:45.000000000 -0400
@@ -116,6 +116,7 @@
DATA_DATA \
*(.exit.data) /* 2.5 convention */ \
*(.data.exit) /* 2.4 convention */ \
+ EXTRARW_DATA \
. = ALIGN (16) ; \
*(.data.cacheline_aligned) \
. = ALIGN (0x2000) ; \
Index: linux-2.6-lttng/arch/x86_64/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/x86_64/kernel/vmlinux.lds.S 2007-05-30 08:42:43.000000000 -0400
+++ linux-2.6-lttng/arch/x86_64/kernel/vmlinux.lds.S 2007-05-30 08:58:55.000000000 -0400
@@ -56,6 +56,7 @@
/* Data */
.data : AT(ADDR(.data) - LOAD_OFFSET) {
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
} :data
Index: linux-2.6-lttng/arch/xtensa/kernel/vmlinux.lds.S
===================================================================
--- linux-2.6-lttng.orig/arch/xtensa/kernel/vmlinux.lds.S 2007-05-30 08:42:28.000000000 -0400
+++ linux-2.6-lttng/arch/xtensa/kernel/vmlinux.lds.S 2007-05-30 08:59:09.000000000 -0400
@@ -146,6 +146,7 @@
.data :
{
DATA_DATA
+ EXTRARW_DATA
CONSTRUCTORS
. = ALIGN(XCHAL_ICACHE_LINESIZE);
*(.data.cacheline_aligned)
Index: linux-2.6-lttng/include/asm-generic/vmlinux.lds.h
===================================================================
--- linux-2.6-lttng.orig/include/asm-generic/vmlinux.lds.h 2007-05-30 08:43:11.000000000 -0400
+++ linux-2.6-lttng/include/asm-generic/vmlinux.lds.h 2007-05-30 09:04:19.000000000 -0400
@@ -150,6 +150,11 @@
\
. = ALIGN(4096);
+/* EXTRARW_DATA adds a place to declare rw data that will not be mixed with the
+ * .data content; therefore limiting data cache pollution when data is put in
+ * the EXTRARW_DATA sections. */
+#define EXTRARW_DATA
+
#define SECURITY_INIT \
.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__security_initcall_start) = .; \
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
^ permalink raw reply [flat|nested] 8+ messages in thread
* [patch 2/6] Linux Kernel Markers, architecture independent code.
2007-05-30 14:03 [patch 0/6] Linux Kernel Markers - for 2.6.22-rc2-mm1 Mathieu Desnoyers
2007-05-30 14:04 ` Mathieu Desnoyers
@ 2007-05-30 14:04 ` Mathieu Desnoyers
2007-05-30 14:04 ` [patch 3/6] Linux Kernel Markers - Hash Table Mathieu Desnoyers
` (3 subsequent siblings)
5 siblings, 0 replies; 8+ messages in thread
From: Mathieu Desnoyers @ 2007-05-30 14:04 UTC (permalink / raw)
To: akpm, linux-kernel; +Cc: Mathieu Desnoyers
[-- Attachment #1: linux-kernel-markers-architecture-independent-code.patch --]
[-- Type: text/plain, Size: 16623 bytes --]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
---
include/asm-generic/vmlinux.lds.h | 6
include/linux/marker.h | 99 +++++++++++
include/linux/module.h | 3
kernel/module.c | 330 ++++++++++++++++++++++++++++++++++++++
4 files changed, 437 insertions(+), 1 deletion(-)
Index: linux-2.6-lttng/include/asm-generic/vmlinux.lds.h
===================================================================
--- linux-2.6-lttng.orig/include/asm-generic/vmlinux.lds.h 2007-05-30 09:08:06.000000000 -0400
+++ linux-2.6-lttng/include/asm-generic/vmlinux.lds.h 2007-05-30 09:09:21.000000000 -0400
@@ -153,7 +153,11 @@
/* EXTRARW_DATA adds a place to declare rw data that will not be mixed with the
* .data content; therefore limiting data cache pollution when data is put in
* the EXTRARW_DATA sections. */
-#define EXTRARW_DATA
+#define EXTRARW_DATA \
+ . = ALIGN(8); \
+ VMLINUX_SYMBOL(__start___markers) = .; \
+ *(__markers) \
+ VMLINUX_SYMBOL(__stop___markers) = .;
#define SECURITY_INIT \
.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
Index: linux-2.6-lttng/include/linux/marker.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6-lttng/include/linux/marker.h 2007-05-30 09:08:16.000000000 -0400
@@ -0,0 +1,99 @@
+#ifndef _LINUX_MARKER_H
+#define _LINUX_MARKER_H
+
+/*
+ * Code markup for dynamic and static tracing.
+ *
+ * See Documentation/marker.txt.
+ *
+ * (C) Copyright 2006 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#ifdef __KERNEL__
+
+#include <linux/condcall.h>
+
+struct __mark_marker;
+
+typedef void marker_probe_func(const struct __mark_marker *mdata,
+ const char *fmt, ...);
+
+struct __mark_marker {
+ const char *name;
+ const char *format;
+ const char *args;
+ int flags;
+ marker_probe_func *call;
+ void *pdata;
+} __attribute__((packed));
+
+#ifdef CONFIG_MARKERS
+
+/* Macro calling the callback. Placed inside the cond_call() parameters. */
+#define trace_mark_call(func, name, format, args...) \
+ ({ \
+ preempt_disable(); \
+ (func)(name, format, ## args); \
+ preempt_enable(); \
+ })
+
+/* Generic marker flavor always available.
+ * Note : the empty asm volatile with read constraint is used here instead of a
+ * "used" attribute to fix a gcc 4.1.x bug. */
+#define _trace_mark(flags, name, format, args...) \
+ do { \
+ static const char __mstrtab_name_##name[] \
+ __attribute__((section("__cond_call_strings"))) \
+ = #name; \
+ static const char __mstrtab_format_##name[] \
+ __attribute__((section("__cond_call_strings"))) \
+ = format; \
+ static const char __mstrtab_args_##name[] \
+ __attribute__((section("__cond_call_strings"))) \
+ = #args; \
+ static struct __mark_marker __mark_##name \
+ __attribute__((section("__markers"))) = \
+ { __mstrtab_name_##name, __mstrtab_format_##name, \
+ __mstrtab_args_##name, (flags), __mark_empty_function, NULL }; \
+ asm volatile ( "" : : "i" (&__mark_##name)); \
+ __mark_check_format(format, ## args); \
+ _cond_call((flags), name, \
+ trace_mark_call(*__mark_##name.call, \
+ &__mark_##name, format, ## args)); \
+ } while (0)
+
+/* Marker with default behavior */
+#define trace_mark(name, format, args...) \
+ _trace_mark(CF_DEFAULT, name, format, ## args)
+
+#else /* !CONFIG_MARKERS */
+#define trace_mark(flags, name, format, args...) \
+ __mark_check_format(format, ## args)
+#endif /* CONFIG_MARKERS */
+
+#define MARK_MAX_FORMAT_LEN 1024
+/* Pass this as a format string for a marker with no argument */
+#define MARK_NOARGS " "
+
+/* To be used for string format validity checking with sparse */
+static inline
+void __mark_check_format(const char *fmt, ...)
+{ }
+
+extern marker_probe_func __mark_empty_function;
+
+extern int _marker_arm_probe(int flags, const char *name, const char *format,
+ marker_probe_func *probe, void *pdata);
+
+#define marker_arm_probe(name, format, probe, pdata) \
+ _marker_arm_probe(CF_DEFAULT, name, format, probe, pdata)
+
+extern int marker_disarm_probe(const char *name);
+extern int marker_list_probe(marker_probe_func *probe);
+const struct __mark_marker *marker_query(const char *name, int instance);
+
+#endif /* __KERNEL__ */
+#endif
Index: linux-2.6-lttng/include/linux/module.h
===================================================================
--- linux-2.6-lttng.orig/include/linux/module.h 2007-05-30 08:43:11.000000000 -0400
+++ linux-2.6-lttng/include/linux/module.h 2007-05-30 09:08:16.000000000 -0400
@@ -16,6 +16,7 @@
#include <linux/kobject.h>
#include <linux/moduleparam.h>
#include <linux/condcall.h>
+#include <linux/marker.h>
#include <asm/local.h>
#include <asm/module.h>
@@ -358,6 +359,8 @@
const struct __cond_call_struct *cond_calls;
unsigned int num_cond_calls;
+ struct __mark_marker *markers;
+ unsigned int num_markers;
};
#ifndef MODULE_ARCH_INIT
#define MODULE_ARCH_INIT {}
Index: linux-2.6-lttng/kernel/module.c
===================================================================
--- linux-2.6-lttng.orig/kernel/module.c 2007-05-30 08:43:11.000000000 -0400
+++ linux-2.6-lttng/kernel/module.c 2007-05-30 09:08:16.000000000 -0400
@@ -33,6 +33,7 @@
#include <linux/moduleparam.h>
#include <linux/errno.h>
#include <linux/condcall.h>
+#include <linux/marker.h>
#include <linux/jhash.h>
#include <linux/list.h>
#include <linux/err.h>
@@ -160,6 +161,8 @@
extern const unsigned long __start___kcrctab_unused_gpl[];
extern const struct __cond_call_struct __start___cond_call[];
extern const struct __cond_call_struct __stop___cond_call[];
+extern const struct __mark_marker __start___markers[];
+extern const struct __mark_marker __stop___markers[];
#ifndef CONFIG_MODVERSIONS
#define symversion(base, idx) NULL
@@ -577,6 +580,313 @@
}
#endif
+#ifdef CONFIG_MARKERS
+
+/* Empty callback provided as a probe to the markers. By providing this to a
+ * disabled marker, we makes sure the execution flow is always valid even
+ * though the function pointer change and the marker enabling are two distinct
+ * operations that modifies the execution flow of preemptible code. */
+void __mark_empty_function(const struct __mark_marker_data *mdata,
+ const char *fmt, ...)
+{
+}
+EXPORT_SYMBOL_GPL(__mark_empty_function);
+
+/* Sets the probe callback corresponding to a range of markers.
+ */
+static int _marker_set_probe_range(int flags, const char *name,
+ const char *format,
+ marker_probe_func *probe,
+ void *pdata,
+ const struct __mark_marker *begin,
+ const struct __mark_marker *end)
+{
+ const struct __mark_marker *iter;
+ int found = 0;
+
+ for (iter = begin; iter < end; iter++) {
+ if (strcmp(name, iter->mdata->name) != 0)
+ continue;
+
+ if (format) {
+ if (strcmp(format, iter->mdata->format) != 0) {
+ printk(KERN_NOTICE
+ "Format mismatch for probe %s "
+ "(%s), marker (%s)\n",
+ name,
+ format,
+ iter->mdata->format);
+ continue;
+ }
+ } else
+ format = iter->mdata->format;
+
+ if (flags & CF_LOCKDEP
+ && !(iter->mdata->flags & CF_LOCKDEP)) {
+ printk(KERN_NOTICE
+ "Incompatible lockdep flags for "
+ "probe %s\n",
+ name);
+ continue;
+ }
+ if (flags & CF_PRINTK
+ && !(iter->mdata->flags & CF_PRINTK)) {
+ printk(KERN_NOTICE
+ "Incompatible printk flags for "
+ "probe %s\n",
+ name);
+ continue;
+ }
+ if (probe == __mark_empty_function) {
+ if (iter->mdata->call != __mark_empty_function)
+ iter->mdata->call = __mark_empty_function;
+ } else {
+ if (iter->mdata->call != __mark_empty_function) {
+ if (iter->mdata->call != probe) {
+ printk(KERN_NOTICE
+ "Marker %s busy, "
+ "probe %p already "
+ "installed\n",
+ name,
+ iter->mdata->call);
+ continue;
+ }
+ } else
+ iter->mdata->call = probe;
+ iter->mdata->pdata = pdata;
+ }
+ found++;
+ }
+ return found;
+}
+
+/* Sets a range of markers to a disabled state : unset the enable bit and
+ * provide the empty callback.
+ * Keep a count of other markers connected to the same module as the one
+ * provided as parameter. */
+static int marker_remove_probe_range(const char *name,
+ struct module *probe_module,
+ int *ref_count,
+ const struct __mark_marker *begin,
+ const struct __mark_marker *end)
+{
+ const struct __mark_marker *iter;
+ int found = 0;
+
+ for (iter = begin; iter < end; iter++) {
+ if (strcmp(name, iter->mdata->name) != 0) {
+ if (probe_module)
+ if (__module_text_address(
+ (unsigned long)iter->mdata->call)
+ == probe_module)
+ (*ref_count)++;
+ continue;
+ }
+ iter->mdata->call = __mark_empty_function;
+ found++;
+ }
+ return found;
+}
+
+/* Provides a listing of the markers present in the kernel along with their
+ * callback and format string. */
+static int marker_list_probe_range(marker_probe_func *probe,
+ const struct __mark_marker *begin,
+ const struct __mark_marker *end)
+{
+ const struct __mark_marker *iter;
+ int found = 0;
+
+ for (iter = begin; iter < end; iter++) {
+ if (probe)
+ if (probe != iter->mdata->call) continue;
+ printk("name %s func 0x%p format \"%s\"\n",
+ iter->mdata->name,
+ iter->mdata->call, iter->mdata->format);
+ found++;
+ }
+ return found;
+}
+
+/* Get the module to which the probe handler's text belongs.
+ * Called with module_mutex taken.
+ * Returns NULL if the probe handler is not in a module. */
+static struct module *__marker_get_probe_module(const char *name)
+{
+ struct module *mod;
+ const struct __mark_marker *iter;
+
+ list_for_each_entry(mod, &modules, list) {
+ if (mod->taints)
+ continue;
+ for (iter = mod->markers;
+ iter < mod->markers+mod->num_markers; iter++) {
+ if (strcmp(name, iter->mdata->name) != 0)
+ continue;
+ if (iter->mdata->call)
+ return __module_text_address(
+ (unsigned long)iter->mdata->call);
+ }
+ }
+ return NULL;
+}
+
+/* Looks up a marker by its name and instance number within the specificed
+ * range and returns the associated data structure. */
+const struct __mark_marker_data *marker_query_range(const char *name,
+ int instance,
+ const struct __mark_marker *begin,
+ const struct __mark_marker *end)
+{
+ const struct __mark_marker *iter;
+ int found = 0;
+
+ for (iter = begin; iter < end; iter++) {
+ if (strcmp(name, iter->mdata->name) != 0)
+ continue;
+
+ if (found++ == instance)
+ return iter->mdata;
+ }
+ return NULL;
+}
+
+/* Calls _marker_set_probe_range for the core markers and modules markers.
+ * Marker arm uses the modlist_lock to synchronise. */
+static int marker_set_probe(int flags, const char *name, const char *format,
+ marker_probe_func *probe,
+ void *pdata)
+{
+ struct module *mod;
+ int found = 0;
+
+ mutex_lock(&module_mutex);
+ /* Core kernel markers */
+ found += _marker_set_probe_range(flags, name, format, probe,
+ pdata,
+ __start___markers, __stop___markers);
+ /* Markers in modules. */
+ list_for_each_entry(mod, &modules, list) {
+ if (!mod->taints)
+ found += _marker_set_probe_range(flags, name, format,
+ probe, pdata,
+ mod->markers, mod->markers+mod->num_markers);
+ }
+ mutex_unlock(&module_mutex);
+ return found;
+}
+
+/* Calls _marker_remove_probe_range for the core markers and modules markers.
+ * Marker enabling/disabling use the modlist_lock to synchronise.
+ * ref_count is the number of markers still connected to the same module
+ * as the one in which sits the probe handler currently removed, excluding the
+ * one currently removed. If the count is 0, we issue a synchronize_sched() to
+ * make sure the module can safely unload. */
+static int marker_remove_probe(const char *name)
+{
+ struct module *mod, *probe_module;
+ int found = 0;
+ int ref_count = 0;
+
+ mutex_lock(&module_mutex);
+ /* In what module is the probe handler ? */
+ probe_module = __marker_get_probe_module(name);
+ /* Core kernel markers */
+ found += marker_remove_probe_range(name, probe_module, &ref_count,
+ __start___markers, __stop___markers);
+ /* Markers in modules. */
+ list_for_each_entry(mod, &modules, list) {
+ if (!mod->taints)
+ found += marker_remove_probe_range(name, probe_module,
+ &ref_count,
+ mod->markers, mod->markers+mod->num_markers);
+ }
+ mutex_unlock(&module_mutex);
+ if (!ref_count)
+ synchronize_sched();
+ return found;
+}
+
+/* Arming a probe (set handler, enable cond_call). */
+int _marker_arm_probe(int flags, const char *name, const char *format,
+ marker_probe_func *probe, void *pdata)
+{
+ int ret;
+
+ ret = marker_set_probe(flags, name, format, probe, pdata);
+ if (ret)
+ ret = cond_call_arm(name);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(_marker_arm_probe);
+
+/* Disarm a probe (disable cond_call, remove handler). */
+int marker_disarm_probe(const char *name)
+{
+ int ret;
+
+ ret = cond_call_disarm(name);
+ if (ret)
+ ret = marker_remove_probe(name);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(marker_disarm_probe);
+
+/* Calls _marker_list_probe_range for the core markers and modules markers.
+ * Marker listing uses the modlist_lock to synchronise.
+ * TODO : should output this listing to a procfs file. */
+int marker_list_probe(marker_probe_func *probe)
+{
+ struct module *mod;
+ int found = 0;
+
+ mutex_lock(&module_mutex);
+ /* Core kernel markers */
+ printk("Listing kernel markers\n");
+ found += marker_list_probe_range(probe,
+ __start___markers, __stop___markers);
+ /* Markers in modules. */
+ printk("Listing module markers\n");
+ list_for_each_entry(mod, &modules, list) {
+ if (!mod->taints) {
+ printk("Listing markers for module %s\n", mod->name);
+ found += marker_list_probe_range(probe,
+ mod->markers, mod->markers+mod->num_markers);
+ }
+ }
+ mutex_unlock(&module_mutex);
+ return found;
+}
+EXPORT_SYMBOL_GPL(marker_list_probe);
+
+/* Looks up a marker by its name and instance number and returns the
+ * associated data structure. */
+const struct __mark_marker_data *marker_query(const char *name, int instance)
+{
+ struct module *mod;
+ const struct __mark_marker_data *mdata;
+
+ mutex_lock(&module_mutex);
+ /* Core kernel markers */
+ mdata = marker_query_range(name, instance,
+ __start___markers, __stop___markers);
+ if (!mdata) {
+ /* Markers in modules. */
+ list_for_each_entry(mod, &modules, list)
+ if (!mod->taints) {
+ mdata = marker_query_range(name, instance,
+ mod->markers,
+ mod->markers+mod->num_markers);
+ if (mdata)
+ break;
+ }
+ }
+ mutex_unlock(&module_mutex);
+ return mdata;
+}
+EXPORT_SYMBOL_GPL(marker_query);
+#endif
+
#ifdef CONFIG_SMP
/* Number of blocks used and allocated. */
static unsigned int pcpu_num_used, pcpu_num_allocated;
@@ -1856,6 +2166,8 @@
unsigned int unusedgplcrcindex;
unsigned int condcallindex;
unsigned int condcallstringsindex;
+ unsigned int markersindex;
+ unsigned int markersdataindex;
struct module *mod;
long err = 0;
void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
@@ -1954,6 +2266,8 @@
#endif
condcallindex = find_sec(hdr, sechdrs, secstrings, "__cond_call");
condcallstringsindex = find_sec(hdr, sechdrs, secstrings, "__cond_call_strings");
+ markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
+ markersdataindex = find_sec(hdr, sechdrs, secstrings, "__markers_data");
/* Don't keep modinfo section */
sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
@@ -1976,6 +2290,17 @@
sechdrs[condcallstringsindex].sh_flags
&= ~(unsigned long)SHF_ALLOC;
#endif
+#ifdef CONFIG_MARKERS
+ if (markersindex)
+ sechdrs[markersindex].sh_flags |= SHF_ALLOC;
+ if (markersdataindex)
+ sechdrs[markersdataindex].sh_flags |= SHF_ALLOC;
+#else
+ if (markersindex)
+ sechdrs[markersindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
+ if (markersdataindex)
+ sechdrs[markersdataindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
+#endif
/* Check module struct version now, before we try to use module. */
if (!check_modstruct_version(sechdrs, versindex, mod)) {
@@ -2121,6 +2446,11 @@
mod->num_cond_calls =
sechdrs[condcallindex].sh_size / sizeof(*mod->cond_calls);
}
+ if (markersindex) {
+ mod->markers = (void *)sechdrs[markersindex].sh_addr;
+ mod->num_markers =
+ sechdrs[markersindex].sh_size / sizeof(*mod->markers);
+ }
mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr;
if (unusedcrcindex)
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
^ permalink raw reply [flat|nested] 8+ messages in thread* [patch 3/6] Linux Kernel Markers - Hash Table
2007-05-30 14:03 [patch 0/6] Linux Kernel Markers - for 2.6.22-rc2-mm1 Mathieu Desnoyers
2007-05-30 14:04 ` Mathieu Desnoyers
2007-05-30 14:04 ` [patch 2/6] Linux Kernel Markers, architecture independent code Mathieu Desnoyers
@ 2007-05-30 14:04 ` Mathieu Desnoyers
2007-05-30 14:04 ` [patch 4/6] Linux Kernel Markers - Add kconfig menus for the marker code Mathieu Desnoyers
` (2 subsequent siblings)
5 siblings, 0 replies; 8+ messages in thread
From: Mathieu Desnoyers @ 2007-05-30 14:04 UTC (permalink / raw)
To: akpm, linux-kernel; +Cc: Mathieu Desnoyers
[-- Attachment #1: linux-kernel-markers-hash-table.patch --]
[-- Type: text/plain, Size: 19892 bytes --]
Rewrite of the markers using a hash table as a basic container for the enabled
probes. It permits to first arm a probe and then load modules containing
markers for this probe and still be coherent.
At module load time, each marker is checked for an active probe in the hash
table.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
---
include/linux/marker.h | 2
kernel/module.c | 485 +++++++++++++++++++++++++++----------------------
2 files changed, 277 insertions(+), 210 deletions(-)
Index: linux-2.6-lttng/include/linux/marker.h
===================================================================
--- linux-2.6-lttng.orig/include/linux/marker.h 2007-05-17 00:52:36.000000000 -0400
+++ linux-2.6-lttng/include/linux/marker.h 2007-05-17 00:53:06.000000000 -0400
@@ -91,7 +91,7 @@
#define marker_arm_probe(name, format, probe, pdata) \
_marker_arm_probe(CF_DEFAULT, name, format, probe, pdata)
-extern int marker_disarm_probe(const char *name);
+extern void marker_disarm_probe(const char *name);
extern int marker_list_probe(marker_probe_func *probe);
const struct __mark_marker *marker_query(const char *name, int instance);
Index: linux-2.6-lttng/kernel/module.c
===================================================================
--- linux-2.6-lttng.orig/kernel/module.c 2007-05-17 00:52:36.000000000 -0400
+++ linux-2.6-lttng/kernel/module.c 2007-05-17 00:53:40.000000000 -0400
@@ -88,6 +88,24 @@
static struct hlist_head cond_call_table[COND_CALL_TABLE_SIZE];
#endif //CONFIG_COND_CALL
+#ifdef CONFIG_MARKERS
+/* Marker hash table, containing the active markers.
+ * Protected by module_mutex. */
+#define MARKER_HASH_BITS 6
+#define MARKER_TABLE_SIZE (1 << MARKER_HASH_BITS)
+
+struct marker_entry {
+ struct hlist_node hlist;
+ int flags;
+ char *format;
+ marker_probe_func *probe;
+ void *pdata;
+ char name[0]; /* Contains name'\0'format'\0' */
+};
+
+static struct hlist_head marker_table[MARKER_TABLE_SIZE];
+#endif //CONFIG_MARKERS
+
int register_module_notifier(struct notifier_block * nb)
{
return blocking_notifier_chain_register(&module_notify_list, nb);
@@ -161,8 +179,8 @@
extern const unsigned long __start___kcrctab_unused_gpl[];
extern const struct __cond_call_struct __start___cond_call[];
extern const struct __cond_call_struct __stop___cond_call[];
-extern const struct __mark_marker __start___markers[];
-extern const struct __mark_marker __stop___markers[];
+extern struct __mark_marker __start___markers[];
+extern struct __mark_marker __stop___markers[];
#ifndef CONFIG_MODVERSIONS
#define symversion(base, idx) NULL
@@ -581,159 +599,267 @@
#endif
#ifdef CONFIG_MARKERS
-
/* Empty callback provided as a probe to the markers. By providing this to a
* disabled marker, we makes sure the execution flow is always valid even
* though the function pointer change and the marker enabling are two distinct
* operations that modifies the execution flow of preemptible code. */
-void __mark_empty_function(const struct __mark_marker_data *mdata,
+void __mark_empty_function(const struct __mark_marker *mdata,
const char *fmt, ...)
{
}
EXPORT_SYMBOL_GPL(__mark_empty_function);
-/* Sets the probe callback corresponding to a range of markers.
- */
-static int _marker_set_probe_range(int flags, const char *name,
- const char *format,
- marker_probe_func *probe,
- void *pdata,
- const struct __mark_marker *begin,
- const struct __mark_marker *end)
+/* Get marker if the marker is present in the hash table.
+ * Returns NULL if not present. */
+static struct marker_entry *hash_get_marker(const char *name)
{
- const struct __mark_marker *iter;
- int found = 0;
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct marker_entry *e;
+ size_t len = strlen(name);
+ u32 hash = jhash(name, len, 0);
- for (iter = begin; iter < end; iter++) {
- if (strcmp(name, iter->mdata->name) != 0)
- continue;
+ head = &marker_table[hash & ((1 << MARKER_HASH_BITS)-1)];
+ hlist_for_each_entry(e, node, head, hlist)
+ if (!strcmp(name, e->name))
+ return e;
+ return NULL;
+}
- if (format) {
- if (strcmp(format, iter->mdata->format) != 0) {
- printk(KERN_NOTICE
- "Format mismatch for probe %s "
- "(%s), marker (%s)\n",
- name,
- format,
- iter->mdata->format);
- continue;
- }
- } else
- format = iter->mdata->format;
+/* Add the marker to the hash table. Must be called with mutex_lock held. */
+static int hash_add_marker(int flags, const char *name,
+ const char *format, marker_probe_func *probe, void *pdata)
+{
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct marker_entry *e;
+ size_t name_len = strlen(name);
+ size_t format_len = strlen(format);
+ u32 hash = jhash(name, name_len, 0);
- if (flags & CF_LOCKDEP
- && !(iter->mdata->flags & CF_LOCKDEP)) {
- printk(KERN_NOTICE
- "Incompatible lockdep flags for "
- "probe %s\n",
- name);
- continue;
- }
- if (flags & CF_PRINTK
- && !(iter->mdata->flags & CF_PRINTK)) {
+ head = &marker_table[hash & ((1 << MARKER_HASH_BITS)-1)];
+ hlist_for_each_entry(e, node, head, hlist)
+ if (!strcmp(name, e->name)) {
printk(KERN_NOTICE
- "Incompatible printk flags for "
- "probe %s\n",
- name);
- continue;
+ "Marker %s busy, probe %p already installed\n",
+ name, e->probe);
+ return -EBUSY; /* Already there */
}
- if (probe == __mark_empty_function) {
- if (iter->mdata->call != __mark_empty_function)
- iter->mdata->call = __mark_empty_function;
- } else {
- if (iter->mdata->call != __mark_empty_function) {
- if (iter->mdata->call != probe) {
- printk(KERN_NOTICE
- "Marker %s busy, "
- "probe %p already "
- "installed\n",
- name,
- iter->mdata->call);
- continue;
- }
- } else
- iter->mdata->call = probe;
- iter->mdata->pdata = pdata;
+ /* Using kmalloc here to allocate a variable length element. Could
+ * cause some memory fragmentation if overused. */
+ e = kmalloc(sizeof(struct marker_entry) + name_len + 1 + format_len + 1,
+ GFP_KERNEL);
+ if (!e)
+ return -ENOMEM;
+ memcpy(&e->name[0], name, name_len + 1);
+ e->format = &e->name[name_len + 1];
+ memcpy(e->format, format, format_len + 1);
+ e->flags = flags;
+ e->probe = probe;
+ e->pdata = pdata;
+ hlist_add_head(&e->hlist, head);
+ return 0;
+}
+
+/* Remove the marker from the hash table. Must be called with mutex_lock
+ * held. */
+static void hash_remove_marker(const char *name)
+{
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct marker_entry *e;
+ int found = 0;
+ size_t len = strlen(name);
+ u32 hash = jhash(name, len, 0);
+
+ head = &marker_table[hash & ((1 << MARKER_HASH_BITS)-1)];
+ hlist_for_each_entry(e, node, head, hlist)
+ if (!strcmp(name, e->name)) {
+ found = 1;
+ break;
}
- found++;
+ if (found) {
+ hlist_del(&e->hlist);
+ kfree(e);
}
- return found;
}
-/* Sets a range of markers to a disabled state : unset the enable bit and
- * provide the empty callback.
- * Keep a count of other markers connected to the same module as the one
- * provided as parameter. */
-static int marker_remove_probe_range(const char *name,
+/* Sets the probe callback corresponding to one marker.
+ */
+static int set_marker(int flags, const char *name, const char *format,
+ marker_probe_func *probe, void *pdata,
+ struct __mark_marker *elem)
+{
+ BUG_ON(strcmp(name, elem->name) != 0);
+
+ if (format)
+ if (strcmp(format, elem->format) != 0) {
+ printk(KERN_NOTICE
+ "Format mismatch for probe %s "
+ "(%s), marker (%s)\n",
+ name,
+ format,
+ elem->format);
+ return -EPERM;
+ }
+ if (flags & CF_LOCKDEP
+ && !(elem->flags & CF_LOCKDEP)) {
+ printk(KERN_NOTICE
+ "Incompatible lockdep flags for "
+ "probe %s\n",
+ name);
+ return -EPERM;
+ }
+ if (flags & CF_PRINTK
+ && !(elem->flags & CF_PRINTK)) {
+ printk(KERN_NOTICE
+ "Incompatible printk flags for "
+ "probe %s\n",
+ name);
+ return -EPERM;
+ }
+ elem->call = probe;
+ elem->pdata = pdata;
+ return 0;
+}
+
+static void disable_marker(struct __mark_marker *elem)
+{
+ elem->call = __mark_empty_function;
+ /* Leave the pdata there, because removal is racy and should be done
+ * only after a synchronize_sched(). It's never used anyway. */
+}
+
+/* Updates the probe callback corresponding to a range of markers. */
+static int marker_update_probe_range(
+ struct __mark_marker *begin,
+ struct __mark_marker *end,
struct module *probe_module,
- int *ref_count,
- const struct __mark_marker *begin,
- const struct __mark_marker *end)
+ int *refcount)
{
- const struct __mark_marker *iter;
- int found = 0;
+ struct __mark_marker *iter;
+ struct marker_entry *hash_mark;
+ int ret;
for (iter = begin; iter < end; iter++) {
- if (strcmp(name, iter->mdata->name) != 0) {
+ hash_mark = hash_get_marker(iter->name);
+ if (hash_mark) {
+ ret = set_marker(hash_mark->flags,
+ hash_mark->name, hash_mark->format,
+ hash_mark->probe, hash_mark->pdata,
+ iter);
+ if (ret)
+ return ret;
if (probe_module)
- if (__module_text_address(
- (unsigned long)iter->mdata->call)
- == probe_module)
- (*ref_count)++;
- continue;
+ if (probe_module ==
+ __module_text_address((unsigned long)hash_mark->probe))
+ (*refcount)++;
+ } else {
+ disable_marker(iter);
}
- iter->mdata->call = __mark_empty_function;
- found++;
}
- return found;
+ return 0;
}
-/* Provides a listing of the markers present in the kernel along with their
- * callback and format string. */
-static int marker_list_probe_range(marker_probe_func *probe,
- const struct __mark_marker *begin,
- const struct __mark_marker *end)
+/* Update probes, removing the faulty probes.
+ * Issues a synchronize_sched() when no reference to the module passed
+ * as parameter is found in the probes so the probe module can be
+ * safely unloaded from now on. */
+static int marker_update_probes(struct module *probe_module)
{
- const struct __mark_marker *iter;
- int found = 0;
+ struct module *mod;
+ int ret;
+ int refcount = 0;
- for (iter = begin; iter < end; iter++) {
- if (probe)
- if (probe != iter->mdata->call) continue;
- printk("name %s func 0x%p format \"%s\"\n",
- iter->mdata->name,
- iter->mdata->call, iter->mdata->format);
- found++;
+ mutex_lock(&module_mutex);
+ /* Core kernel markers */
+ ret = marker_update_probe_range(__start___markers,
+ __stop___markers, probe_module, &refcount);
+ if (ret)
+ goto end;
+ /* Markers in modules. */
+ list_for_each_entry(mod, &modules, list)
+ if (!mod->taints) {
+ ret = marker_update_probe_range(mod->markers,
+ mod->markers+mod->num_markers,
+ probe_module, &refcount);
+ if (ret)
+ goto end;
+ }
+end:
+ mutex_unlock(&module_mutex);
+ if (!ret && probe_module && refcount == 0)
+ synchronize_sched();
+ return ret;
+}
+
+/* Setup the marker according to the data present in the marker hash
+ * upon module load. If an error occur during the set probe range,
+ * refuse to load the module. */
+static int module_marker_update(struct module *mod)
+{
+ if (!mod->taints)
+ return marker_update_probe_range(mod->markers,
+ mod->markers+mod->num_markers, NULL, NULL);
+ return 0;
+}
+
+/* Arm the probe : set the callback for each marker and arm the cond_call.
+ * If the marker update fails, remove the probe and refresh the markers. */
+int _marker_arm_probe(int flags, const char *name, const char *format,
+ marker_probe_func *probe, void *pdata)
+{
+ int ret = 0;
+
+ ret = hash_add_marker(flags, name,
+ format, probe, pdata);
+ if (ret)
+ return ret;
+ ret = marker_update_probes(NULL);
+ if (ret) {
+ hash_remove_marker(name);
+ ret = marker_update_probes(NULL);
+ BUG_ON(ret);
}
- return found;
+ ret = cond_call_arm(name);
+ return ret;
}
+EXPORT_SYMBOL_GPL(_marker_arm_probe);
/* Get the module to which the probe handler's text belongs.
* Called with module_mutex taken.
* Returns NULL if the probe handler is not in a module. */
static struct module *__marker_get_probe_module(const char *name)
{
- struct module *mod;
- const struct __mark_marker *iter;
+ struct marker_entry *hash_mark;
- list_for_each_entry(mod, &modules, list) {
- if (mod->taints)
- continue;
- for (iter = mod->markers;
- iter < mod->markers+mod->num_markers; iter++) {
- if (strcmp(name, iter->mdata->name) != 0)
- continue;
- if (iter->mdata->call)
- return __module_text_address(
- (unsigned long)iter->mdata->call);
- }
- }
+ hash_mark = hash_get_marker(name);
+ if (hash_mark)
+ return __module_text_address((unsigned long)hash_mark->probe);
return NULL;
}
+/* Disarm the probe : disarm the con_call and set the empty callback for each
+ * marker. */
+void marker_disarm_probe(const char *name)
+{
+ struct module *probe_module;
+ int ret;
+
+ cond_call_disarm(name);
+
+ /* In what module is the probe handler ? */
+ probe_module = __marker_get_probe_module(name);
+
+ hash_remove_marker(name);
+ ret = marker_update_probes(probe_module);
+ BUG_ON(ret);
+}
+EXPORT_SYMBOL_GPL(marker_disarm_probe);
+
/* Looks up a marker by its name and instance number within the specificed
* range and returns the associated data structure. */
-const struct __mark_marker_data *marker_query_range(const char *name,
+static const struct __mark_marker *marker_query_range(const char *name,
int instance,
const struct __mark_marker *begin,
const struct __mark_marker *end)
@@ -742,96 +868,61 @@
int found = 0;
for (iter = begin; iter < end; iter++) {
- if (strcmp(name, iter->mdata->name) != 0)
+ if (strcmp(name, iter->name) != 0)
continue;
-
if (found++ == instance)
- return iter->mdata;
+ return iter;
}
return NULL;
}
-/* Calls _marker_set_probe_range for the core markers and modules markers.
- * Marker arm uses the modlist_lock to synchronise. */
-static int marker_set_probe(int flags, const char *name, const char *format,
- marker_probe_func *probe,
- void *pdata)
+/* Looks up a marker by its name and instance number and returns the
+ * associated data structure. */
+const struct __mark_marker *marker_query(const char *name, int instance)
{
struct module *mod;
- int found = 0;
+ const struct __mark_marker *mdata;
mutex_lock(&module_mutex);
/* Core kernel markers */
- found += _marker_set_probe_range(flags, name, format, probe,
- pdata,
+ mdata = marker_query_range(name, instance,
__start___markers, __stop___markers);
- /* Markers in modules. */
- list_for_each_entry(mod, &modules, list) {
- if (!mod->taints)
- found += _marker_set_probe_range(flags, name, format,
- probe, pdata,
- mod->markers, mod->markers+mod->num_markers);
+ if (!mdata) {
+ /* Markers in modules. */
+ list_for_each_entry(mod, &modules, list)
+ if (!mod->taints) {
+ mdata = marker_query_range(name, instance,
+ mod->markers,
+ mod->markers+mod->num_markers);
+ if (mdata)
+ break;
+ }
}
mutex_unlock(&module_mutex);
- return found;
+ return mdata;
}
+EXPORT_SYMBOL_GPL(marker_query);
-/* Calls _marker_remove_probe_range for the core markers and modules markers.
- * Marker enabling/disabling use the modlist_lock to synchronise.
- * ref_count is the number of markers still connected to the same module
- * as the one in which sits the probe handler currently removed, excluding the
- * one currently removed. If the count is 0, we issue a synchronize_sched() to
- * make sure the module can safely unload. */
-static int marker_remove_probe(const char *name)
+/* Provides a listing of the markers present in the kernel along with their
+ * callback and format string. */
+static int marker_list_probe_range(marker_probe_func *probe,
+ const struct __mark_marker *begin,
+ const struct __mark_marker *end)
{
- struct module *mod, *probe_module;
+ const struct __mark_marker *iter;
int found = 0;
- int ref_count = 0;
- mutex_lock(&module_mutex);
- /* In what module is the probe handler ? */
- probe_module = __marker_get_probe_module(name);
- /* Core kernel markers */
- found += marker_remove_probe_range(name, probe_module, &ref_count,
- __start___markers, __stop___markers);
- /* Markers in modules. */
- list_for_each_entry(mod, &modules, list) {
- if (!mod->taints)
- found += marker_remove_probe_range(name, probe_module,
- &ref_count,
- mod->markers, mod->markers+mod->num_markers);
+ for (iter = begin; iter < end; iter++) {
+ if (probe)
+ if (probe != iter->call) continue;
+ printk("name %s func 0x%p format \"%s\"\n",
+ iter->name,
+ iter->call, iter->format);
+ found++;
}
- mutex_unlock(&module_mutex);
- if (!ref_count)
- synchronize_sched();
return found;
}
-/* Arming a probe (set handler, enable cond_call). */
-int _marker_arm_probe(int flags, const char *name, const char *format,
- marker_probe_func *probe, void *pdata)
-{
- int ret;
-
- ret = marker_set_probe(flags, name, format, probe, pdata);
- if (ret)
- ret = cond_call_arm(name);
- return ret;
-}
-EXPORT_SYMBOL_GPL(_marker_arm_probe);
-
-/* Disarm a probe (disable cond_call, remove handler). */
-int marker_disarm_probe(const char *name)
-{
- int ret;
-
- ret = cond_call_disarm(name);
- if (ret)
- ret = marker_remove_probe(name);
- return ret;
-}
-EXPORT_SYMBOL_GPL(marker_disarm_probe);
-
/* Calls _marker_list_probe_range for the core markers and modules markers.
* Marker listing uses the modlist_lock to synchronise.
* TODO : should output this listing to a procfs file. */
@@ -858,33 +949,11 @@
return found;
}
EXPORT_SYMBOL_GPL(marker_list_probe);
-
-/* Looks up a marker by its name and instance number and returns the
- * associated data structure. */
-const struct __mark_marker_data *marker_query(const char *name, int instance)
+#else
+static int module_marker_update(struct module *mod)
{
- struct module *mod;
- const struct __mark_marker_data *mdata;
-
- mutex_lock(&module_mutex);
- /* Core kernel markers */
- mdata = marker_query_range(name, instance,
- __start___markers, __stop___markers);
- if (!mdata) {
- /* Markers in modules. */
- list_for_each_entry(mod, &modules, list)
- if (!mod->taints) {
- mdata = marker_query_range(name, instance,
- mod->markers,
- mod->markers+mod->num_markers);
- if (mdata)
- break;
- }
- }
- mutex_unlock(&module_mutex);
- return mdata;
+ return 0;
}
-EXPORT_SYMBOL_GPL(marker_query);
#endif
#ifdef CONFIG_SMP
@@ -2247,7 +2316,6 @@
unsigned int condcallindex;
unsigned int condcallstringsindex;
unsigned int markersindex;
- unsigned int markersdataindex;
struct module *mod;
long err = 0;
void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
@@ -2347,7 +2415,6 @@
condcallindex = find_sec(hdr, sechdrs, secstrings, "__cond_call");
condcallstringsindex = find_sec(hdr, sechdrs, secstrings, "__cond_call_strings");
markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
- markersdataindex = find_sec(hdr, sechdrs, secstrings, "__markers_data");
/* Don't keep modinfo section */
sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
@@ -2373,13 +2440,9 @@
#ifdef CONFIG_MARKERS
if (markersindex)
sechdrs[markersindex].sh_flags |= SHF_ALLOC;
- if (markersdataindex)
- sechdrs[markersdataindex].sh_flags |= SHF_ALLOC;
#else
if (markersindex)
sechdrs[markersindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
- if (markersdataindex)
- sechdrs[markersdataindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
#endif
/* Check module struct version now, before we try to use module. */
@@ -2590,6 +2653,10 @@
add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
+ err = module_marker_update(mod);
+ if (err < 0)
+ goto cleanup;
+
module_cond_call_setup(mod);
err = module_finalize(hdr, sechdrs, mod);
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
^ permalink raw reply [flat|nested] 8+ messages in thread* [patch 4/6] Linux Kernel Markers - Add kconfig menus for the marker code
2007-05-30 14:03 [patch 0/6] Linux Kernel Markers - for 2.6.22-rc2-mm1 Mathieu Desnoyers
` (2 preceding siblings ...)
2007-05-30 14:04 ` [patch 3/6] Linux Kernel Markers - Hash Table Mathieu Desnoyers
@ 2007-05-30 14:04 ` Mathieu Desnoyers
2007-05-30 14:04 ` [patch 5/6] Linux Kernel Markers - Documentation Mathieu Desnoyers
2007-05-30 14:04 ` [patch 6/6] Port of blktrace to the Linux Kernel Markers Mathieu Desnoyers
5 siblings, 0 replies; 8+ messages in thread
From: Mathieu Desnoyers @ 2007-05-30 14:04 UTC (permalink / raw)
To: akpm, linux-kernel; +Cc: Mathieu Desnoyers, Adrian Bunk
[-- Attachment #1: linux-kernel-markers-kconfig-menus.patch --]
[-- Type: text/plain, Size: 21494 bytes --]
With the increasing complexity of today's user-space application and the wide
deployment of SMP systems, the users need an increasing understanding of the
behavior and performance of a system across multiple processes/different
execution contexts/multiple CPUs. In applications such as large clusters
(Google, IBM), video acquisition (Autodesk), embedded real-time systems (Wind
River, Monta Vista, Sony) or sysadmin/programmer-type tasks (SystemTAP from
Redhat), a tool that permits tracing of kernel-user space interaction becomes
necessary.
Usage of such tools have been made to successfully pinpoint problems such as:
latency issues in a user-space video acquisition application, slowdown
problems in large clusters due to a switch to a different filesystems with a
different cache size, abnormal Linux scheduler latency (just to name a few
that I have personally investigated).
The currently existing solutions does not give a system-wide overview of what
- and when - things are happening on the system. Ptracing a program works
with few processes, but quickly becomes useless when it comes to keeping track
of many processes.
Bugs occuring because of bad interaction of such complex systems can be very
hard to find due to the fact that they occur rarely (sometimes once a week on
hundreds of machines). One can therefore only hope at having the best
conditions to statistically reproduce the bug while extracting information
from the system. Some bugs have been successfully found at Google using their
ktrace tracer only because they could enable it on production machines and
therefore recreate the same context where the bug happened.
Therefore, it makes sense to offer an instrumentation set of the most relevant
events occurring in the Linux that can have the smallest performance cost
possible when not active while not requiring a reboot of a production system
to activate. This is essentially what the markers are providing.
Since we cannot limit the growth of the Linux kernel, nor can we pre-determine
each and every "interesting" instrumentation within each subsystem and driver,
it is sensible to let this task to the persons who knows the best their code.
Adding instrumentation should therefore be as easy as adding and maintaining a
"printk" in the kernel code from the developer's point of view.
Towards a complete tracing mechanism in the Linux kernel, the markers are only
one step forward. The following step is to connect probes to those markers
that will record the tracing information in buffers exported to user-space,
organized in timestamped "events". Probe callbacks are responsible for
serializing the information passed as parameter to the markers (described by
the format string) into the events. A control mechanism to activate/stop the
tracing is required, as well as a daemon that maps the buffers to write them
to disk or send them through the network.
Keeping track of the events also requires a centralized infrastructure : the
idea is to assign a unique ID to each event so they can be later recognized in
the trace. Keeping in mind that recording the complete instrumentation site
name string for each event would be more that inefficient, assigning a numeric
unique identifier makes sense.
Finally, support for gathering events coming from user-space, with a minimal
performance impact, is very useful to see the interaction between the system's
execution contexts.
The last steps are currently implemented in Linux Trace Toolkit Next
Generation (LTTng).
The SystemTAP project could clearly benefit from such an infrastructure for
tracing. In addition, they would be providing support for dynamic addition of
kernel probes through breakpoints/jumps when possible, with the associated
restrictions (accessing local variables, reentrancy, speed).
This marker infrastructure is a hook-callback mechanism. It is meant to have
an impact as low as possible on the system performances when no callback
(probe) is connected so markers (hooks) can be compiled into a production
kernel without noticeable slowdown.
Why use the markers instead of kprobes?
The rationale behind this mechanism the following :
1 - It makes sense to have instrumentation (for tracing, profiling)
within the kernel source tree so that it can follow its evolution.
Other options, such as kprobes, imply maintaining an external set of
instrumentation that must be adapted to each kernel version.
Although it may make sense for distributions, it is not well suited
for kernel developers, since they rarely work on a major
distribution image.
2 - kprobes, although being a very good attempt at providing a dynamic
hooking mechanism that has no impact when disabled, suffers from
important limitations :
a - It cannot access local variables of a function at a particular
point within its body that will be consistent thorough the kernel
versions without involving a lot of recurrent hair-pulling.
b - Kprobes is slow, since it involves going though a trap each time
a probe site is executed. Even though the djprobes project made a
good effort to make things faster, it cannot currently instrument
fully-preemptible kernels and does not solve (1), (2a) and (2c).
c - On the reentrancy side, going though a trap (thus playing with
interrupt enable/disable) and taking spinlocks are not suited to
some code paths, i.e. :
kernel/lockdep.c, printk (within the lockdep_on()/lockdep_off()).
It must be understood that some code paths interesting for
instrumentation often present a particular reentrancy challenge.
Some more details :
The probe callback connection to its markers is done dynamically. A predicted
branch (see the conditional call infrastructure) is used to skip the hook stack
setup and function call when the marker is "disabled" (no probe is connected).
Further optimizations can be implemented for each architecture to make this
branch faster.
Instrumentation of a subsystem becomes therefore a straightforward task. One
has to add instrumentation within the key locations of the kernel code in the
following form :
trace_mark(subsystem_event, "%d %p", myint, myptr);
Jim Keniston <jkenisto@us.ibm.com> adds:
kprobes remains a vital foundation for SystemTap. But markers are attactive
as an alternate source of trace/debug info. Here's why:
1. Markers will live in the kernel and presumably be kept up to date by
the maintainers of the enclosing code. We have a growing set of tapsets
(probe libraries), each of which "knows" the source code for a certain area
of the kernel. Whenever the underlying kernel code changes (e.g., a
function or one of its args disappears or is renamed), there's a chance
that the tapset will become invalid until we bring it back in sync with the
kernel. As you can imagine, maintaining tapsets separate from the kernel
source is a maintenance headache. Markers could mitigate this.
2. Because the kernel code is highly optimized, the kernel's dwarf info
doesn't always accurately reflect which variables have which values on
which lines (sometimes even upon entry to a function). A marker is a way
to ensure that values of interest are available to SystemTap at marked
points.
3. Sometimes the overhead of a kprobe probepoint is too much (either in
terms of time or locking) for the particular hotspot we want to probe.
In OLS2006 proceedings, vol. 1
http://www.linuxsymposium.org/2006/linuxsymposium_procv1.pdf
Frank C. Eigler, from SystemTAP, presents its "static probing markers"
(pp. 261-268) in his paper "Problem Solving With Systemtap".
He explains the advantages :
"In exchange for this effort, systemtap marker-based probes are faster and
more precise than kprobes. The better precision comes from not having to
covet the compiler's favours. Such fickle favours include retaining
clean boundaries in the instruction stream between interesting statements,
and precisely describing positions of variables in the stack frame. Since
markers don't rely on debugging information, neither favour is required,
and the compiler can channel its charms into unabated optimization. The
speed advantage comes from using direct call instructions rather than int 3
breakpoints to dispatch to the systemtap handlers. We will see below just
how big a difference this makes."
He does a comparison of his "simple" marker solution with kprobes (his simple
solution looks like my generic markers, but with a major race condition). I
also posted numbers about the markers performance impact a few months ago in
the initial thread. I can dig into my emails to find them for you if you
consider it important for the Changelog.
He concludes with :
"To the extent that is true, we propose that these groups consider using a
shared pool of static markers as the basic kernel-side instrumentation
mechanism. If they prove to have as low dormant cost and as high active
performance as initial experience suggests, perhaps this could motivate the
various tracing efforts and kernel subsystem developers to finally join
forces. Let's designate standard trace/probe points once and for all.
Tracing backends can attach to these markers the same way systemtap would.
There would be no need for them to maintain kernel patches any more.
Let's think about it."
This patch:
Add Kconfig menus for the marker code.
[bunk@stusta.de: Never ever select MODULES]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
CC: Adrian Bunk <bunk@stusta.de>
---
arch/alpha/Kconfig | 2 ++
arch/arm/Kconfig | 2 ++
arch/arm26/Kconfig | 2 ++
arch/avr32/Kconfig.debug | 7 +++++++
arch/cris/Kconfig | 2 ++
arch/frv/Kconfig | 2 ++
arch/h8300/Kconfig | 2 ++
arch/i386/Kconfig | 2 ++
arch/ia64/Kconfig | 2 ++
arch/m32r/Kconfig | 2 ++
arch/m68k/Kconfig | 2 ++
arch/m68knommu/Kconfig | 2 ++
arch/mips/Kconfig | 2 ++
arch/parisc/Kconfig | 2 ++
arch/powerpc/Kconfig | 2 ++
arch/ppc/Kconfig | 2 ++
arch/s390/Kconfig | 2 ++
arch/sh/Kconfig | 2 ++
arch/sh64/Kconfig | 2 ++
arch/sparc/Kconfig | 2 ++
arch/sparc64/Kconfig | 2 ++
arch/um/Kconfig | 2 ++
arch/v850/Kconfig | 2 ++
arch/x86_64/Kconfig | 2 ++
arch/xtensa/Kconfig | 2 ++
kernel/Kconfig.marker | 8 ++++++++
26 files changed, 63 insertions(+)
Index: linux-2.6-lttng/arch/alpha/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/alpha/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/alpha/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -657,6 +657,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/alpha/Kconfig.debug"
Index: linux-2.6-lttng/arch/arm/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/arm/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/arm/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -1046,6 +1046,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/arm/Kconfig.debug"
Index: linux-2.6-lttng/arch/arm26/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/arm26/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/arm26/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -245,6 +245,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/arm26/Kconfig.debug"
Index: linux-2.6-lttng/arch/cris/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/cris/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/cris/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -202,6 +202,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/cris/Kconfig.debug"
Index: linux-2.6-lttng/arch/frv/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/frv/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/frv/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -379,6 +379,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/frv/Kconfig.debug"
Index: linux-2.6-lttng/arch/h8300/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/h8300/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/h8300/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -224,6 +224,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/h8300/Kconfig.debug"
Index: linux-2.6-lttng/arch/i386/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/i386/Kconfig 2007-05-30 08:44:45.000000000 -0400
+++ linux-2.6-lttng/arch/i386/Kconfig 2007-05-30 09:35:47.000000000 -0400
@@ -1235,6 +1235,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endif # INSTRUMENTATION
source "arch/i386/Kconfig.debug"
Index: linux-2.6-lttng/arch/ia64/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/ia64/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/ia64/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -593,6 +593,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/ia64/Kconfig.debug"
Index: linux-2.6-lttng/arch/m32r/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/m32r/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/m32r/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -409,6 +409,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/m32r/Kconfig.debug"
Index: linux-2.6-lttng/arch/m68k/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/m68k/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/m68k/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -674,6 +674,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/m68k/Kconfig.debug"
Index: linux-2.6-lttng/arch/m68knommu/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/m68knommu/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/m68knommu/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -672,6 +672,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/m68knommu/Kconfig.debug"
Index: linux-2.6-lttng/arch/mips/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/mips/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/mips/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -1961,6 +1961,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/mips/Kconfig.debug"
Index: linux-2.6-lttng/arch/parisc/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/parisc/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/parisc/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -273,6 +273,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/parisc/Kconfig.debug"
Index: linux-2.6-lttng/arch/powerpc/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/powerpc/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/powerpc/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -906,6 +906,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/powerpc/Kconfig.debug"
Index: linux-2.6-lttng/arch/ppc/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/ppc/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/ppc/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -1457,6 +1457,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/ppc/Kconfig.debug"
Index: linux-2.6-lttng/arch/s390/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/s390/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/s390/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -551,6 +551,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/s390/Kconfig.debug"
Index: linux-2.6-lttng/arch/sh/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/sh/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/sh/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -725,6 +725,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/sh/Kconfig.debug"
Index: linux-2.6-lttng/arch/sh64/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/sh64/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/sh64/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -288,6 +288,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/sh64/Kconfig.debug"
Index: linux-2.6-lttng/arch/sparc/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/sparc/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/sparc/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -308,6 +308,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/sparc/Kconfig.debug"
Index: linux-2.6-lttng/arch/sparc64/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/sparc64/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/sparc64/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -441,6 +441,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/sparc64/Kconfig.debug"
Index: linux-2.6-lttng/arch/um/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/um/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/um/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -340,6 +340,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/um/Kconfig.debug"
Index: linux-2.6-lttng/arch/v850/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/v850/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/v850/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -335,6 +335,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/v850/Kconfig.debug"
Index: linux-2.6-lttng/arch/x86_64/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/x86_64/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/x86_64/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -797,6 +797,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/x86_64/Kconfig.debug"
Index: linux-2.6-lttng/arch/xtensa/Kconfig
===================================================================
--- linux-2.6-lttng.orig/arch/xtensa/Kconfig 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/xtensa/Kconfig 2007-05-30 09:35:19.000000000 -0400
@@ -255,6 +255,8 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
endmenu
source "arch/xtensa/Kconfig.debug"
Index: linux-2.6-lttng/kernel/Kconfig.marker
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6-lttng/kernel/Kconfig.marker 2007-05-30 09:09:35.000000000 -0400
@@ -0,0 +1,8 @@
+# Code markers configuration
+
+config MARKERS
+ bool "Activate markers"
+ depends on MODULES && COND_CALL
+ help
+ Place an empty function call at each marker site. Can be
+ dynamically changed for a probe function.
Index: linux-2.6-lttng/arch/avr32/Kconfig.debug
===================================================================
--- linux-2.6-lttng.orig/arch/avr32/Kconfig.debug 2007-05-30 08:43:43.000000000 -0400
+++ linux-2.6-lttng/arch/avr32/Kconfig.debug 2007-05-30 09:35:19.000000000 -0400
@@ -9,6 +9,9 @@
menu "Instrumentation Support"
depends on EXPERIMENTAL
+menu "Instrumentation Support"
+ depends on EXPERIMENTAL
+
config KPROBES
bool "Kprobes"
depends on DEBUG_KERNEL
@@ -21,6 +24,10 @@
source "kernel/Kconfig.condcall"
+source "kernel/Kconfig.marker"
+
+endmenu
+
endmenu
endmenu
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
^ permalink raw reply [flat|nested] 8+ messages in thread* [patch 5/6] Linux Kernel Markers - Documentation
2007-05-30 14:03 [patch 0/6] Linux Kernel Markers - for 2.6.22-rc2-mm1 Mathieu Desnoyers
` (3 preceding siblings ...)
2007-05-30 14:04 ` [patch 4/6] Linux Kernel Markers - Add kconfig menus for the marker code Mathieu Desnoyers
@ 2007-05-30 14:04 ` Mathieu Desnoyers
2007-05-30 14:04 ` [patch 6/6] Port of blktrace to the Linux Kernel Markers Mathieu Desnoyers
5 siblings, 0 replies; 8+ messages in thread
From: Mathieu Desnoyers @ 2007-05-30 14:04 UTC (permalink / raw)
To: akpm, linux-kernel; +Cc: Mathieu Desnoyers
[-- Attachment #1: linux-kernel-markers-documentation.patch --]
[-- Type: text/plain, Size: 8143 bytes --]
Here is some documentation explaining what is/how to use the Linux
Kernel Markers.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
---
Documentation/marker.txt | 253 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 253 insertions(+)
Index: linux-2.6-lttng/Documentation/marker.txt
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6-lttng/Documentation/marker.txt 2007-05-29 14:08:27.000000000 -0400
@@ -0,0 +1,253 @@
+ Using the Linux Kernel Markers
+
+ Mathieu Desnoyers
+
+
+This document introduces Linux Kernel Markers and their use. It provides
+examples of how to insert markers in the kernel and connect probe functions to
+them and provides some examples of probe functions.
+
+
+* Purpose of markers
+
+A marker placed in your code provides a hook to call a function (probe) that
+you can provide at runtime. A marker can be "on" (a probe is connected to it)
+or "off" (no probe is attached). When a marker is "off" it has no
+effect. When a marker is "on", the function you provide is called each
+time the marker is executed, in the execution context of the
+caller. When the function provided ends its execution, it returns to the
+caller (continuing from the marker site).
+
+You can put markers at important locations in the code. Markers are
+lightweight hooks that can pass an arbitrary number of parameters,
+described in a printk-like format string, to the attached probe function.
+
+They can be used for tracing and performance accounting.
+
+
+* Usage
+
+In order to use the macro trace_mark, you should include linux/marker.h.
+
+#include <linux/marker.h>
+
+Add, in your code :
+
+trace_mark(subsystem_event, "%d %s", someint, somestring);
+Where :
+- subsystem_event is an identifier unique to your event
+ - subsystem is the name of your subsystem.
+ - event is the name of the event to mark.
+- "%d %s" is the formatted string for the serializer.
+- someint is an integer.
+- somestring is a char pointer.
+
+Connecting a function (probe) to a marker is done by providing a probe
+(function to call) for the specific marker through marker_arm_probe(). It will
+automatically connect the function and enable the marker site. Removing a probe
+is done through marker_disarm_probe(). Probe removal is preempt-safe because
+preemption is disabled around the probe call. See the "Probe example" section
+below for a sample probe module.
+
+The marker mechanism supports inserting multiple instances of the same marker.
+Markers can be put in inline functions, inlined static functions, and
+unrolled loops.
+
+Note: It is safe to put markers within preempt-safe code : preempt_enable()
+will not call the scheduler due to the tests in preempt_schedule().
+
+
+* Optimization for a given architecture
+
+One can implement optimized markers for a given architecture by replacing
+asm-$ARCH/marker.h.
+
+The CF_* flags can be used to control the type of marker. See the
+include/linux/condcall.h header for the list of flags. They can be specified as
+the first parameter of the _trace_mark() macro, as in the following example,
+which is safe with respect to lockdep.c (useful for marking lockdep.c and printk
+functions).
+
+_trace_mark(CF_DEFAULT | ~CF_LOCKDEP, subsystem_eventb, MARK_NOARGS);
+
+Another example is to specify that a specific marker must never call printk:
+_trace_mark(CF_DEFAULT | ~CF_PRINTK, subsystem_eventc,
+ "%d %s", someint, somestring);
+
+Flag compatibility is checked before connecting the probe to the marker: the
+right flags must be given to _marker_arm_probe().
+
+
+* Probe example
+
+You can build the kernel modules, probe-example.ko and marker-example.ko,
+using the following Makefile:
+------------------------------ CUT -------------------------------------
+obj-m := probe-example.o marker-example.o
+KDIR := /lib/modules/$(shell uname -r)/build
+PWD := $(shell pwd)
+default:
+ $(MAKE) -C $(KDIR) SUBDIRS=$(PWD) modules
+clean:
+ rm -f *.mod.c *.ko *.o
+------------------------------ CUT -------------------------------------
+/* probe-example.c
+ *
+ * Connects two functions to marker call sites.
+ *
+ * (C) Copyright 2007 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/marker.h>
+#include <asm/atomic.h>
+
+struct probe_data {
+ const char *name;
+ const char *format;
+ marker_probe_func *probe_func;
+};
+
+void probe_subsystem_event(const struct __mark_marker_c *mdata,
+ const char *format, ...)
+{
+ va_list ap;
+ /* Declare args */
+ unsigned int value;
+ const char *mystr;
+
+ /* Assign args */
+ va_start(ap, format);
+ value = va_arg(ap, typeof(value));
+ mystr = va_arg(ap, typeof(mystr));
+
+ /* Call printk */
+ printk("Value %u, string %s\n", value, mystr);
+
+ /* or count, check rights, serialize data in a buffer */
+
+ va_end(ap);
+}
+
+atomic_t eventb_count = ATOMIC_INIT(0);
+
+void probe_subsystem_eventb(const struct __mark_marker_c *mdata,
+ const char *format, ...)
+{
+ /* Increment counter */
+ atomic_inc(&eventb_count);
+}
+
+static struct probe_data probe_array[] =
+{
+ { .name = "subsystem_event",
+ .format = "%d %s",
+ .probe_func = probe_subsystem_event },
+ { .name = "subsystem_eventb",
+ .format = MARK_NOARGS,
+ .probe_func = probe_subsystem_eventb },
+};
+
+static int __init probe_init(void)
+{
+ int result;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(probe_array); i++) {
+ result = marker_arm_probe(probe_array[i].name,
+ probe_array[i].format,
+ probe_array[i].probe_func, &probe_array[i]);
+ if (result)
+ printk(KERN_INFO "Unable to register probe %s\n",
+ probe_array[i].name);
+ }
+ return 0;
+}
+
+static void __exit probe_fini(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(probe_array); i++) {
+ marker_disarm_probe(probe_array[i].name);
+ }
+ printk("Number of event b : %u\n", atomic_read(&eventb_count));
+}
+
+module_init(probe_init);
+module_exit(probe_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mathieu Desnoyers");
+MODULE_DESCRIPTION("SUBSYSTEM Probe");
+------------------------------ CUT -------------------------------------
+/* marker-example.c
+ *
+ * Executes a marker when /proc/marker-example is opened.
+ *
+ * (C) Copyright 2007 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/marker.h>
+#include <linux/sched.h>
+#include <linux/proc_fs.h>
+
+struct proc_dir_entry *pentry_example = NULL;
+
+static int my_open(struct inode *inode, struct file *file)
+{
+ int i;
+
+ trace_mark(subsystem_event, "%d %s", 123, "example string");
+ for (i=0; i<10; i++) {
+ trace_mark(subsystem_eventb, MARK_NOARGS);
+ }
+ return -EPERM;
+}
+
+static struct file_operations mark_ops = {
+ .open = my_open,
+};
+
+static int example_init(void)
+{
+ printk(KERN_ALERT "example init\n");
+ pentry_example = create_proc_entry("marker-example", 0444, NULL);
+ if (pentry_example)
+ pentry_example->proc_fops = &mark_ops;
+ else
+ return -EPERM;
+ return 0;
+}
+
+static void example_exit(void)
+{
+ printk(KERN_ALERT "example exit\n");
+ remove_proc_entry("marker-example", NULL);
+}
+
+module_init(example_init)
+module_exit(example_exit)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mathieu Desnoyers");
+MODULE_DESCRIPTION("Linux Trace Toolkit example");
+------------------------------ CUT -------------------------------------
+Sequence of operations : (as root)
+make
+insmod marker-example.ko
+insmod probe-example.ko
+ (it is important to load the probe after the marked code)
+cat /proc/marker-example (returns an expected error)
+rmmod marker-example probe-example
+dmesg
+------------------------------ CUT -------------------------------------
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
^ permalink raw reply [flat|nested] 8+ messages in thread* [patch 6/6] Port of blktrace to the Linux Kernel Markers.
2007-05-30 14:03 [patch 0/6] Linux Kernel Markers - for 2.6.22-rc2-mm1 Mathieu Desnoyers
` (4 preceding siblings ...)
2007-05-30 14:04 ` [patch 5/6] Linux Kernel Markers - Documentation Mathieu Desnoyers
@ 2007-05-30 14:04 ` Mathieu Desnoyers
5 siblings, 0 replies; 8+ messages in thread
From: Mathieu Desnoyers @ 2007-05-30 14:04 UTC (permalink / raw)
To: akpm, linux-kernel; +Cc: Mathieu Desnoyers
[-- Attachment #1: linux-kernel-markers-port-blktrace-to-markers.patch --]
[-- Type: text/plain, Size: 23819 bytes --]
Here is a proof of concept patch, for demonstration purpose, of moving
blktrace to the markers.
A few remarks : this patch has the positive effect of removing some code
from the block io tracing hot paths, minimizing the i-cache impact in a
system where the io tracing is compiled in but inactive.
It also moves the blk tracing code from a header (and therefore from the
body of the instrumented functions) to a separate C file.
There, as soon as one device has to be traced, every devices have to
fall into the tracing function call. This is slower than the previous
inline function which tested the condition quickly. If it becomes a
show stopper, it could be fixed by having the possibility to test a
supplementary condition, dependant of the marker context, at the marker
site, just after the enable/disable test.
It does not make the code smaller, since I left all the specialized
tracing functions for requests, bio, generic, remap, which would go away
once a generic infrastructure is in place to serialize the information
passed to the marker. This is mostly why I consider it a proof a
concept.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
---
block/Kconfig | 1
block/blktrace.c | 281 ++++++++++++++++++++++++++++++++++++++++++-
block/elevator.c | 6
block/ll_rw_blk.c | 27 ++--
drivers/block/cciss.c | 4
drivers/md/dm.c | 14 +-
fs/bio.c | 4
include/linux/blktrace_api.h | 146 +---------------------
mm/bounce.c | 4
mm/highmem.c | 2
10 files changed, 322 insertions(+), 167 deletions(-)
Index: linux-2.6-lttng/block/elevator.c
===================================================================
--- linux-2.6-lttng.orig/block/elevator.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/block/elevator.c 2007-05-17 02:14:05.000000000 -0400
@@ -32,7 +32,7 @@
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/delay.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
#include <linux/hash.h>
#include <asm/uaccess.h>
@@ -551,7 +551,7 @@
unsigned ordseq;
int unplug_it = 1;
- blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+ trace_mark(blk_request_insert, "%p %p", q, rq);
rq->q = q;
@@ -730,7 +730,7 @@
* not be passed by new incoming requests
*/
rq->cmd_flags |= REQ_STARTED;
- blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+ trace_mark(blk_request_issue, "%p %p", q, rq);
}
if (!q->boundary_rq || q->boundary_rq == rq) {
Index: linux-2.6-lttng/block/ll_rw_blk.c
===================================================================
--- linux-2.6-lttng.orig/block/ll_rw_blk.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/block/ll_rw_blk.c 2007-05-17 02:14:05.000000000 -0400
@@ -28,6 +28,7 @@
#include <linux/task_io_accounting_ops.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
+#include <linux/marker.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
@@ -1551,7 +1552,7 @@
if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
- blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
+ trace_mark(blk_plug_device, "%p %p %d", q, NULL, 0);
}
}
@@ -1617,7 +1618,7 @@
* devices don't necessarily have an ->unplug_fn defined
*/
if (q->unplug_fn) {
- blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+ trace_mark(blk_pdu_unplug_io, "%p %p %d", q, NULL,
q->rq.count[READ] + q->rq.count[WRITE]);
q->unplug_fn(q);
@@ -1628,7 +1629,7 @@
{
request_queue_t *q = container_of(work, request_queue_t, unplug_work);
- blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+ trace_mark(blk_pdu_unplug_io, "%p %p %d", q, NULL,
q->rq.count[READ] + q->rq.count[WRITE]);
q->unplug_fn(q);
@@ -1638,7 +1639,7 @@
{
request_queue_t *q = (request_queue_t *)data;
- blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL,
+ trace_mark(blk_pdu_unplug_timer, "%p %p %d", q, NULL,
q->rq.count[READ] + q->rq.count[WRITE]);
kblockd_schedule_work(&q->unplug_work);
@@ -2150,7 +2151,7 @@
rq_init(q, rq);
- blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
+ trace_mark(blk_get_request, "%p %p %d", q, bio, rw);
out:
return rq;
}
@@ -2180,7 +2181,7 @@
if (!rq) {
struct io_context *ioc;
- blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);
+ trace_mark(blk_sleep_request, "%p %p %d", q, bio, rw);
__generic_unplug_device(q);
spin_unlock_irq(q->queue_lock);
@@ -2254,7 +2255,7 @@
*/
void blk_requeue_request(request_queue_t *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+ trace_mark(blk_requeue, "%p %p", q, rq);
if (blk_rq_tagged(rq))
blk_queue_end_tag(q, rq);
@@ -2940,7 +2941,7 @@
if (!ll_back_merge_fn(q, req, bio))
break;
- blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+ trace_mark(blk_bio_backmerge, "%p %p", q, bio);
req->biotail->bi_next = bio;
req->biotail = bio;
@@ -2957,7 +2958,7 @@
if (!ll_front_merge_fn(q, req, bio))
break;
- blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+ trace_mark(blk_bio_frontmerge, "%p %p", q, bio);
bio->bi_next = req->bio;
req->bio = bio;
@@ -3187,10 +3188,10 @@
blk_partition_remap(bio);
if (old_sector != -1)
- blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
- old_sector);
+ trace_mark(blk_remap, "%p %p %u %llu %llu", q, bio, old_dev,
+ (u64)bio->bi_sector, (u64)old_sector);
- blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+ trace_mark(blk_bio_queue, "%p %p", q, bio);
old_sector = bio->bi_sector;
old_dev = bio->bi_bdev->bd_dev;
@@ -3383,7 +3384,7 @@
int total_bytes, bio_nbytes, error, next_idx = 0;
struct bio *bio;
- blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE);
+ trace_mark(blk_request_complete, "%p %p", req->q, req);
/*
* extend uptodate bool to allow < 0 value to be direct io error
Index: linux-2.6-lttng/block/Kconfig
===================================================================
--- linux-2.6-lttng.orig/block/Kconfig 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/block/Kconfig 2007-05-17 02:14:05.000000000 -0400
@@ -32,6 +32,7 @@
depends on SYSFS
select RELAY
select DEBUG_FS
+ select MARKERS
help
Say Y here, if you want to be able to trace the block layer actions
on a given queue. Tracing allows you to see any traffic happening
Index: linux-2.6-lttng/block/blktrace.c
===================================================================
--- linux-2.6-lttng.orig/block/blktrace.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/block/blktrace.c 2007-05-17 02:14:05.000000000 -0400
@@ -23,11 +23,19 @@
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/time.h>
+#include <linux/marker.h>
#include <asm/uaccess.h>
static DEFINE_PER_CPU(unsigned long long, blk_trace_cpu_offset) = { 0, };
static unsigned int blktrace_seq __read_mostly = 1;
+/* Global reference count of probes */
+static DEFINE_MUTEX(blk_probe_mutex);
+static int blk_probes_ref;
+
+int blk_probe_arm(void);
+void blk_probe_disarm(void);
+
/*
* Send out a notify message.
*/
@@ -179,7 +187,7 @@
EXPORT_SYMBOL_GPL(__blk_add_trace);
static struct dentry *blk_tree_root;
-static struct mutex blk_tree_mutex;
+static DEFINE_MUTEX(blk_tree_mutex);
static unsigned int root_users;
static inline void blk_remove_root(void)
@@ -229,6 +237,10 @@
blk_remove_tree(bt->dir);
free_percpu(bt->sequence);
kfree(bt);
+ mutex_lock(&blk_probe_mutex);
+ if (--blk_probes_ref == 0)
+ blk_probe_disarm();
+ mutex_unlock(&blk_probe_mutex);
}
static int blk_trace_remove(request_queue_t *q)
@@ -386,6 +398,11 @@
goto err;
}
+ mutex_lock(&blk_probe_mutex);
+ if (!blk_probes_ref++)
+ blk_probe_arm();
+ mutex_unlock(&blk_probe_mutex);
+
return 0;
err:
if (dir)
@@ -549,9 +566,269 @@
#endif
}
+/**
+ * blk_add_trace_rq - Add a trace for a request oriented action
+ * Expected variable arguments :
+ * @q: queue the io is for
+ * @rq: the source request
+ *
+ * Description:
+ * Records an action against a request. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_rq(const struct __mark_marker *mdata,
+ const char *fmt, ...)
+{
+ va_list args;
+ u32 what;
+ struct blk_trace *bt;
+ int rw;
+ struct blk_probe_data *pinfo = mdata->pdata;
+ struct request_queue *q;
+ struct request *rq;
+
+ va_start(args, fmt);
+ q = va_arg(args, struct request_queue *);
+ rq = va_arg(args, struct request *);
+ va_end(args);
+
+ what = pinfo->flags;
+ bt = q->blk_trace;
+ rw = rq->cmd_flags & 0x03;
+
+ if (likely(!bt))
+ return;
+
+ if (blk_pc_request(rq)) {
+ what |= BLK_TC_ACT(BLK_TC_PC);
+ __blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors, sizeof(rq->cmd), rq->cmd);
+ } else {
+ what |= BLK_TC_ACT(BLK_TC_FS);
+ __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9, rw, what, rq->errors, 0, NULL);
+ }
+}
+
+/**
+ * blk_add_trace_bio - Add a trace for a bio oriented action
+ * Expected variable arguments :
+ * @q: queue the io is for
+ * @bio: the source bio
+ *
+ * Description:
+ * Records an action against a bio. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_bio(const struct __mark_marker *mdata,
+ const char *fmt, ...)
+{
+ va_list args;
+ u32 what;
+ struct blk_trace *bt;
+ struct blk_probe_data *pinfo = mdata->pdata;
+ struct request_queue *q;
+ struct bio *bio;
+
+ va_start(args, fmt);
+ q = va_arg(args, struct request_queue *);
+ bio = va_arg(args, struct bio *);
+ va_end(args);
+
+ what = pinfo->flags;
+ bt = q->blk_trace;
+
+ if (likely(!bt))
+ return;
+
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), 0, NULL);
+}
+
+/**
+ * blk_add_trace_generic - Add a trace for a generic action
+ * Expected variable arguments :
+ * @q: queue the io is for
+ * @bio: the source bio
+ * @rw: the data direction
+ *
+ * Description:
+ * Records a simple trace
+ *
+ **/
+static void blk_add_trace_generic(const struct __mark_marker *mdata,
+ const char *fmt, ...)
+{
+ va_list args;
+ struct blk_trace *bt;
+ u32 what;
+ struct blk_probe_data *pinfo = mdata->pdata;
+ struct request_queue *q;
+ struct bio *bio;
+ int rw;
+
+ va_start(args, fmt);
+ q = va_arg(args, struct request_queue *);
+ bio = va_arg(args, struct bio *);
+ rw = va_arg(args, int);
+ va_end(args);
+
+ what = pinfo->flags;
+ bt = q->blk_trace;
+
+ if (likely(!bt))
+ return;
+
+ if (bio)
+ blk_add_trace_bio(mdata, "%p %p", q, bio);
+ else
+ __blk_add_trace(bt, 0, 0, rw, what, 0, 0, NULL);
+}
+
+/**
+ * blk_add_trace_pdu_int - Add a trace for a bio with an integer payload
+ * Expected variable arguments :
+ * @q: queue the io is for
+ * @bio: the source bio
+ * @pdu: the integer payload
+ *
+ * Description:
+ * Adds a trace with some integer payload. This might be an unplug
+ * option given as the action, with the depth at unplug time given
+ * as the payload
+ *
+ **/
+static void blk_add_trace_pdu_int(const struct __mark_marker *mdata,
+ const char *fmt, ...)
+{
+ va_list args;
+ struct blk_trace *bt;
+ u32 what;
+ struct blk_probe_data *pinfo = mdata->pdata;
+ struct request_queue *q;
+ struct bio *bio;
+ unsigned int pdu;
+ __be64 rpdu;
+
+ va_start(args, fmt);
+ q = va_arg(args, struct request_queue *);
+ bio = va_arg(args, struct bio *);
+ pdu = va_arg(args, unsigned int);
+ va_end(args);
+
+ what = pinfo->flags;
+ bt = q->blk_trace;
+ rpdu = cpu_to_be64(pdu);
+
+ if (likely(!bt))
+ return;
+
+ if (bio)
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), sizeof(rpdu), &rpdu);
+ else
+ __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
+}
+
+/**
+ * blk_add_trace_remap - Add a trace for a remap operation
+ * Expected variable arguments :
+ * @q: queue the io is for
+ * @bio: the source bio
+ * @dev: target device
+ * @from: source sector
+ * @to: target sector
+ *
+ * Description:
+ * Device mapper or raid target sometimes need to split a bio because
+ * it spans a stripe (or similar). Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_remap(const struct __mark_marker *mdata,
+ const char *fmt, ...)
+{
+ va_list args;
+ struct blk_trace *bt;
+ struct blk_io_trace_remap r;
+ u32 what;
+ struct blk_probe_data *pinfo = mdata->pdata;
+ struct request_queue *q;
+ struct bio *bio;
+ u64 dev, from, to;
+
+ va_start(args, fmt);
+ q = va_arg(args, struct request_queue *);
+ bio = va_arg(args, struct bio *);
+ dev = va_arg(args, u64);
+ from = va_arg(args, u64);
+ to = va_arg(args, u64);
+ va_end(args);
+
+ what = pinfo->flags;
+ bt = q->blk_trace;
+
+ if (likely(!bt))
+ return;
+
+ r.device = cpu_to_be32(dev);
+ r.sector = cpu_to_be64(to);
+
+ __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
+}
+
+#define FACILITY_NAME "blk"
+
+static struct blk_probe_data probe_array[] =
+{
+ { "blk_bio_queue", "%p %p", BLK_TA_QUEUE, blk_add_trace_bio },
+ { "blk_bio_backmerge", "%p %p", BLK_TA_BACKMERGE, blk_add_trace_bio },
+ { "blk_bio_frontmerge", "%p %p", BLK_TA_FRONTMERGE, blk_add_trace_bio },
+ { "blk_get_request", "%p %p %d", BLK_TA_GETRQ, blk_add_trace_generic },
+ { "blk_sleep_request", "%p %p %d", BLK_TA_SLEEPRQ,
+ blk_add_trace_generic },
+ { "blk_requeue", "%p %p", BLK_TA_REQUEUE, blk_add_trace_rq },
+ { "blk_request_issue", "%p %p", BLK_TA_ISSUE, blk_add_trace_rq },
+ { "blk_request_complete", "%p %p", BLK_TA_COMPLETE, blk_add_trace_rq },
+ { "blk_plug_device", "%p %p %d", BLK_TA_PLUG, blk_add_trace_generic },
+ { "blk_pdu_unplug_io", "%p %p %d", BLK_TA_UNPLUG_IO,
+ blk_add_trace_pdu_int },
+ { "blk_pdu_unplug_timer", "%p %p %d", BLK_TA_UNPLUG_TIMER,
+ blk_add_trace_pdu_int },
+ { "blk_request_insert", "%p %p", BLK_TA_INSERT,
+ blk_add_trace_rq },
+ { "blk_pdu_split", "%p %p %d", BLK_TA_SPLIT,
+ blk_add_trace_pdu_int },
+ { "blk_bio_bounce", "%p %p", BLK_TA_BOUNCE, blk_add_trace_bio },
+ { "blk_remap", "%p %p %u %llu %llu", BLK_TA_REMAP,
+ blk_add_trace_remap },
+};
+
+
+int blk_probe_arm(void)
+{
+ int result;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(probe_array); i++) {
+ result = marker_arm_probe(probe_array[i].name,
+ probe_array[i].format,
+ probe_array[i].callback, &probe_array[i]);
+ if (result)
+ printk(KERN_INFO
+ "blktrace unable to register probe %s\n",
+ probe_array[i].name);
+ }
+ return 0;
+}
+
+void blk_probe_disarm(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(probe_array); i++) {
+ marker_disarm_probe(probe_array[i].name);
+ }
+}
+
+
static __init int blk_trace_init(void)
{
- mutex_init(&blk_tree_mutex);
on_each_cpu(blk_trace_check_cpu_time, NULL, 1, 1);
blk_trace_set_ht_offsets();
Index: linux-2.6-lttng/include/linux/blktrace_api.h
===================================================================
--- linux-2.6-lttng.orig/include/linux/blktrace_api.h 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/include/linux/blktrace_api.h 2007-05-17 02:14:05.000000000 -0400
@@ -3,6 +3,7 @@
#include <linux/blkdev.h>
#include <linux/relay.h>
+#include <linux/marker.h>
/*
* Trace categories
@@ -142,149 +143,24 @@
u32 pid;
};
+/* Probe data used for probe-marker connection */
+struct blk_probe_data {
+ const char *name;
+ const char *format;
+ u32 flags;
+ marker_probe_func *callback;
+};
+
#if defined(CONFIG_BLK_DEV_IO_TRACE)
extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
extern void blk_trace_shutdown(request_queue_t *);
extern void __blk_add_trace(struct blk_trace *, sector_t, int, int, u32, int, int, void *);
-
-/**
- * blk_add_trace_rq - Add a trace for a request oriented action
- * @q: queue the io is for
- * @rq: the source request
- * @what: the action
- *
- * Description:
- * Records an action against a request. Will log the bio offset + size.
- *
- **/
-static inline void blk_add_trace_rq(struct request_queue *q, struct request *rq,
- u32 what)
-{
- struct blk_trace *bt = q->blk_trace;
- int rw = rq->cmd_flags & 0x03;
-
- if (likely(!bt))
- return;
-
- if (blk_pc_request(rq)) {
- what |= BLK_TC_ACT(BLK_TC_PC);
- __blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors, sizeof(rq->cmd), rq->cmd);
- } else {
- what |= BLK_TC_ACT(BLK_TC_FS);
- __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9, rw, what, rq->errors, 0, NULL);
- }
-}
-
-/**
- * blk_add_trace_bio - Add a trace for a bio oriented action
- * @q: queue the io is for
- * @bio: the source bio
- * @what: the action
- *
- * Description:
- * Records an action against a bio. Will log the bio offset + size.
- *
- **/
-static inline void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
- u32 what)
-{
- struct blk_trace *bt = q->blk_trace;
-
- if (likely(!bt))
- return;
-
- __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), 0, NULL);
-}
-
-/**
- * blk_add_trace_generic - Add a trace for a generic action
- * @q: queue the io is for
- * @bio: the source bio
- * @rw: the data direction
- * @what: the action
- *
- * Description:
- * Records a simple trace
- *
- **/
-static inline void blk_add_trace_generic(struct request_queue *q,
- struct bio *bio, int rw, u32 what)
-{
- struct blk_trace *bt = q->blk_trace;
-
- if (likely(!bt))
- return;
-
- if (bio)
- blk_add_trace_bio(q, bio, what);
- else
- __blk_add_trace(bt, 0, 0, rw, what, 0, 0, NULL);
-}
-
-/**
- * blk_add_trace_pdu_int - Add a trace for a bio with an integer payload
- * @q: queue the io is for
- * @what: the action
- * @bio: the source bio
- * @pdu: the integer payload
- *
- * Description:
- * Adds a trace with some integer payload. This might be an unplug
- * option given as the action, with the depth at unplug time given
- * as the payload
- *
- **/
-static inline void blk_add_trace_pdu_int(struct request_queue *q, u32 what,
- struct bio *bio, unsigned int pdu)
-{
- struct blk_trace *bt = q->blk_trace;
- __be64 rpdu = cpu_to_be64(pdu);
-
- if (likely(!bt))
- return;
-
- if (bio)
- __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), sizeof(rpdu), &rpdu);
- else
- __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
-}
-
-/**
- * blk_add_trace_remap - Add a trace for a remap operation
- * @q: queue the io is for
- * @bio: the source bio
- * @dev: target device
- * @from: source sector
- * @to: target sector
- *
- * Description:
- * Device mapper or raid target sometimes need to split a bio because
- * it spans a stripe (or similar). Add a trace for that action.
- *
- **/
-static inline void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
- dev_t dev, sector_t from, sector_t to)
-{
- struct blk_trace *bt = q->blk_trace;
- struct blk_io_trace_remap r;
-
- if (likely(!bt))
- return;
-
- r.device = cpu_to_be32(dev);
- r.sector = cpu_to_be64(to);
-
- __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
-}
+extern int blk_probe_connect(void);
+extern void blk_probe_disconnect(void);
#else /* !CONFIG_BLK_DEV_IO_TRACE */
#define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY)
#define blk_trace_shutdown(q) do { } while (0)
-#define blk_add_trace_rq(q, rq, what) do { } while (0)
-#define blk_add_trace_bio(q, rq, what) do { } while (0)
-#define blk_add_trace_generic(q, rq, rw, what) do { } while (0)
-#define blk_add_trace_pdu_int(q, what, bio, pdu) do { } while (0)
-#define blk_add_trace_remap(q, bio, dev, f, t) do {} while (0)
#endif /* CONFIG_BLK_DEV_IO_TRACE */
#endif
Index: linux-2.6-lttng/mm/bounce.c
===================================================================
--- linux-2.6-lttng.orig/mm/bounce.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/mm/bounce.c 2007-05-17 02:14:05.000000000 -0400
@@ -13,7 +13,7 @@
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
#include <asm/tlbflush.h>
#define POOL_SIZE 64
@@ -237,7 +237,7 @@
if (!bio)
return;
- blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
+ trace_mark(blk_bio_bounce, "%p %p", q, *bio_orig);
/*
* at least one page was bounced, fill in possible non-highmem
Index: linux-2.6-lttng/mm/highmem.c
===================================================================
--- linux-2.6-lttng.orig/mm/highmem.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/mm/highmem.c 2007-05-17 02:14:05.000000000 -0400
@@ -26,7 +26,7 @@
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
#include <asm/tlbflush.h>
/*
Index: linux-2.6-lttng/fs/bio.c
===================================================================
--- linux-2.6-lttng.orig/fs/bio.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/fs/bio.c 2007-05-17 02:14:05.000000000 -0400
@@ -25,7 +25,7 @@
#include <linux/module.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
#include <scsi/sg.h> /* for struct sg_iovec */
#define BIO_POOL_SIZE 2
@@ -1081,7 +1081,7 @@
if (!bp)
return bp;
- blk_add_trace_pdu_int(bdev_get_queue(bi->bi_bdev), BLK_TA_SPLIT, bi,
+ trace_mark(blk_pdu_split, "%p %p %d", bdev_get_queue(bi->bi_bdev), bi,
bi->bi_sector + first_sectors);
BUG_ON(bi->bi_vcnt != 1);
Index: linux-2.6-lttng/drivers/block/cciss.c
===================================================================
--- linux-2.6-lttng.orig/drivers/block/cciss.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/drivers/block/cciss.c 2007-05-17 02:14:05.000000000 -0400
@@ -37,7 +37,7 @@
#include <linux/hdreg.h>
#include <linux/spinlock.h>
#include <linux/compat.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
#include <asm/uaccess.h>
#include <asm/io.h>
@@ -2502,7 +2502,7 @@
}
cmd->rq->data_len = 0;
cmd->rq->completion_data = cmd;
- blk_add_trace_rq(cmd->rq->q, cmd->rq, BLK_TA_COMPLETE);
+ trace_mark(blk_request_complete, "%p %p", cmd->rq->q, cmd->rq);
blk_complete_request(cmd->rq);
}
Index: linux-2.6-lttng/drivers/md/dm.c
===================================================================
--- linux-2.6-lttng.orig/drivers/md/dm.c 2007-05-17 02:13:19.000000000 -0400
+++ linux-2.6-lttng/drivers/md/dm.c 2007-05-17 02:14:05.000000000 -0400
@@ -19,7 +19,7 @@
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/hdreg.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
#include <linux/smp_lock.h>
#define DM_MSG_PREFIX "core"
@@ -485,8 +485,8 @@
wake_up(&io->md->wait);
if (io->error != DM_ENDIO_REQUEUE) {
- blk_add_trace_bio(io->md->queue, io->bio,
- BLK_TA_COMPLETE);
+ trace_mark(blk_request_complete, "%p %p",
+ io->md->queue, io->bio);
bio_endio(io->bio, io->bio->bi_size, io->error);
}
@@ -582,10 +582,10 @@
r = ti->type->map(ti, clone, &tio->info);
if (r == DM_MAPIO_REMAPPED) {
/* the bio has been remapped so dispatch it */
-
- blk_add_trace_remap(bdev_get_queue(clone->bi_bdev), clone,
- tio->io->bio->bi_bdev->bd_dev, sector,
- clone->bi_sector);
+ trace_mark(blk_remap, "%p %p %u %llu %llu",
+ bdev_get_queue(clone->bi_bdev), clone,
+ (u64)tio->io->bio->bi_bdev->bd_dev, (u64)sector,
+ (u64)clone->bi_sector);
generic_make_request(clone);
} else if (r < 0 || r == DM_MAPIO_REQUEUE) {
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
^ permalink raw reply [flat|nested] 8+ messages in thread