2008-09-05 16:15:39 +08:00
|
|
|
/*
|
|
|
|
* Kernel probes (kprobes) for SuperH
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Chris Smith <chris.smith@st.com>
|
|
|
|
* Copyright (C) 2006 Lineo Solutions, Inc.
|
|
|
|
*
|
|
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
|
|
* for more details.
|
|
|
|
*/
|
|
|
|
#include <linux/kprobes.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/preempt.h>
|
|
|
|
#include <linux/kdebug.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2008-09-05 16:15:39 +08:00
|
|
|
#include <asm/cacheflush.h>
|
2016-12-25 03:46:01 +08:00
|
|
|
#include <linux/uaccess.h>
|
2008-09-05 16:15:39 +08:00
|
|
|
|
|
|
|
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
|
|
|
|
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
|
|
|
|
|
2010-06-14 16:06:10 +08:00
|
|
|
static DEFINE_PER_CPU(struct kprobe, saved_current_opcode);
|
|
|
|
static DEFINE_PER_CPU(struct kprobe, saved_next_opcode);
|
|
|
|
static DEFINE_PER_CPU(struct kprobe, saved_next_opcode2);
|
2008-09-05 16:15:39 +08:00
|
|
|
|
|
|
|
#define OPCODE_JMP(x) (((x) & 0xF0FF) == 0x402b)
|
|
|
|
#define OPCODE_JSR(x) (((x) & 0xF0FF) == 0x400b)
|
|
|
|
#define OPCODE_BRA(x) (((x) & 0xF000) == 0xa000)
|
|
|
|
#define OPCODE_BRAF(x) (((x) & 0xF0FF) == 0x0023)
|
|
|
|
#define OPCODE_BSR(x) (((x) & 0xF000) == 0xb000)
|
|
|
|
#define OPCODE_BSRF(x) (((x) & 0xF0FF) == 0x0003)
|
|
|
|
|
|
|
|
#define OPCODE_BF_S(x) (((x) & 0xFF00) == 0x8f00)
|
|
|
|
#define OPCODE_BT_S(x) (((x) & 0xFF00) == 0x8d00)
|
|
|
|
|
|
|
|
#define OPCODE_BF(x) (((x) & 0xFF00) == 0x8b00)
|
|
|
|
#define OPCODE_BT(x) (((x) & 0xFF00) == 0x8900)
|
|
|
|
|
|
|
|
#define OPCODE_RTS(x) (((x) & 0x000F) == 0x000b)
|
|
|
|
#define OPCODE_RTE(x) (((x) & 0xFFFF) == 0x002b)
|
|
|
|
|
|
|
|
int __kprobes arch_prepare_kprobe(struct kprobe *p)
|
|
|
|
{
|
|
|
|
kprobe_opcode_t opcode = *(kprobe_opcode_t *) (p->addr);
|
|
|
|
|
|
|
|
if (OPCODE_RTE(opcode))
|
|
|
|
return -EFAULT; /* Bad breakpoint */
|
|
|
|
|
|
|
|
p->opcode = opcode;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void __kprobes arch_copy_kprobe(struct kprobe *p)
|
|
|
|
{
|
|
|
|
memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
|
|
|
|
p->opcode = *p->addr;
|
|
|
|
}
|
|
|
|
|
|
|
|
void __kprobes arch_arm_kprobe(struct kprobe *p)
|
|
|
|
{
|
|
|
|
*p->addr = BREAKPOINT_INSTRUCTION;
|
|
|
|
flush_icache_range((unsigned long)p->addr,
|
|
|
|
(unsigned long)p->addr + sizeof(kprobe_opcode_t));
|
|
|
|
}
|
|
|
|
|
|
|
|
void __kprobes arch_disarm_kprobe(struct kprobe *p)
|
|
|
|
{
|
|
|
|
*p->addr = p->opcode;
|
|
|
|
flush_icache_range((unsigned long)p->addr,
|
|
|
|
(unsigned long)p->addr + sizeof(kprobe_opcode_t));
|
|
|
|
}
|
|
|
|
|
|
|
|
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
|
|
|
|
{
|
|
|
|
if (*p->addr == BREAKPOINT_INSTRUCTION)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* If an illegal slot instruction exception occurs for an address
|
|
|
|
* containing a kprobe, remove the probe.
|
|
|
|
*
|
|
|
|
* Returns 0 if the exception was handled successfully, 1 otherwise.
|
|
|
|
*/
|
|
|
|
int __kprobes kprobe_handle_illslot(unsigned long pc)
|
|
|
|
{
|
|
|
|
struct kprobe *p = get_kprobe((kprobe_opcode_t *) pc + 1);
|
|
|
|
|
|
|
|
if (p != NULL) {
|
|
|
|
printk("Warning: removing kprobe from delay slot: 0x%.8x\n",
|
|
|
|
(unsigned int)pc + 2);
|
|
|
|
unregister_kprobe(p);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
void __kprobes arch_remove_kprobe(struct kprobe *p)
|
|
|
|
{
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
struct kprobe *saved = this_cpu_ptr(&saved_next_opcode);
|
2010-06-14 16:06:10 +08:00
|
|
|
|
|
|
|
if (saved->addr) {
|
2008-09-05 16:15:39 +08:00
|
|
|
arch_disarm_kprobe(p);
|
2010-06-14 16:06:10 +08:00
|
|
|
arch_disarm_kprobe(saved);
|
|
|
|
|
|
|
|
saved->addr = NULL;
|
|
|
|
saved->opcode = 0;
|
|
|
|
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
saved = this_cpu_ptr(&saved_next_opcode2);
|
2010-06-14 16:06:10 +08:00
|
|
|
if (saved->addr) {
|
|
|
|
arch_disarm_kprobe(saved);
|
|
|
|
|
|
|
|
saved->addr = NULL;
|
|
|
|
saved->opcode = 0;
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
|
2008-09-05 16:15:39 +08:00
|
|
|
{
|
|
|
|
kcb->prev_kprobe.kp = kprobe_running();
|
|
|
|
kcb->prev_kprobe.status = kcb->kprobe_status;
|
|
|
|
}
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
|
2008-09-05 16:15:39 +08:00
|
|
|
{
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
|
2008-09-05 16:15:39 +08:00
|
|
|
kcb->kprobe_status = kcb->prev_kprobe.status;
|
|
|
|
}
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
|
|
|
|
struct kprobe_ctlblk *kcb)
|
2008-09-05 16:15:39 +08:00
|
|
|
{
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
__this_cpu_write(current_kprobe, p);
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Singlestep is implemented by disabling the current kprobe and setting one
|
|
|
|
* on the next instruction, following branches. Two probes are set if the
|
|
|
|
* branch is conditional.
|
|
|
|
*/
|
2008-09-08 17:22:47 +08:00
|
|
|
static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
|
2008-09-05 16:15:39 +08:00
|
|
|
{
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
__this_cpu_write(saved_current_opcode.addr, (kprobe_opcode_t *)regs->pc);
|
2008-09-05 16:15:39 +08:00
|
|
|
|
|
|
|
if (p != NULL) {
|
2010-06-14 16:06:10 +08:00
|
|
|
struct kprobe *op1, *op2;
|
|
|
|
|
2008-09-05 16:15:39 +08:00
|
|
|
arch_disarm_kprobe(p);
|
|
|
|
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
op1 = this_cpu_ptr(&saved_next_opcode);
|
|
|
|
op2 = this_cpu_ptr(&saved_next_opcode2);
|
2010-06-14 16:06:10 +08:00
|
|
|
|
2008-09-05 16:15:39 +08:00
|
|
|
if (OPCODE_JSR(p->opcode) || OPCODE_JMP(p->opcode)) {
|
|
|
|
unsigned int reg_nr = ((p->opcode >> 8) & 0x000F);
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->addr = (kprobe_opcode_t *) regs->regs[reg_nr];
|
2008-09-05 16:15:39 +08:00
|
|
|
} else if (OPCODE_BRA(p->opcode) || OPCODE_BSR(p->opcode)) {
|
|
|
|
unsigned long disp = (p->opcode & 0x0FFF);
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->addr =
|
2008-09-05 16:15:39 +08:00
|
|
|
(kprobe_opcode_t *) (regs->pc + 4 + disp * 2);
|
|
|
|
|
|
|
|
} else if (OPCODE_BRAF(p->opcode) || OPCODE_BSRF(p->opcode)) {
|
|
|
|
unsigned int reg_nr = ((p->opcode >> 8) & 0x000F);
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->addr =
|
2008-09-05 16:15:39 +08:00
|
|
|
(kprobe_opcode_t *) (regs->pc + 4 +
|
|
|
|
regs->regs[reg_nr]);
|
|
|
|
|
|
|
|
} else if (OPCODE_RTS(p->opcode)) {
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->addr = (kprobe_opcode_t *) regs->pr;
|
2008-09-05 16:15:39 +08:00
|
|
|
|
|
|
|
} else if (OPCODE_BF(p->opcode) || OPCODE_BT(p->opcode)) {
|
|
|
|
unsigned long disp = (p->opcode & 0x00FF);
|
|
|
|
/* case 1 */
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->addr = p->addr + 1;
|
2008-09-05 16:15:39 +08:00
|
|
|
/* case 2 */
|
2010-06-14 16:06:10 +08:00
|
|
|
op2->addr =
|
2008-09-05 16:15:39 +08:00
|
|
|
(kprobe_opcode_t *) (regs->pc + 4 + disp * 2);
|
2010-06-14 16:06:10 +08:00
|
|
|
op2->opcode = *(op2->addr);
|
|
|
|
arch_arm_kprobe(op2);
|
2008-09-05 16:15:39 +08:00
|
|
|
|
|
|
|
} else if (OPCODE_BF_S(p->opcode) || OPCODE_BT_S(p->opcode)) {
|
|
|
|
unsigned long disp = (p->opcode & 0x00FF);
|
|
|
|
/* case 1 */
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->addr = p->addr + 2;
|
2008-09-05 16:15:39 +08:00
|
|
|
/* case 2 */
|
2010-06-14 16:06:10 +08:00
|
|
|
op2->addr =
|
2008-09-05 16:15:39 +08:00
|
|
|
(kprobe_opcode_t *) (regs->pc + 4 + disp * 2);
|
2010-06-14 16:06:10 +08:00
|
|
|
op2->opcode = *(op2->addr);
|
|
|
|
arch_arm_kprobe(op2);
|
2008-09-05 16:15:39 +08:00
|
|
|
|
|
|
|
} else {
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->addr = p->addr + 1;
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
|
2010-06-14 16:06:10 +08:00
|
|
|
op1->opcode = *(op1->addr);
|
|
|
|
arch_arm_kprobe(op1);
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Called with kretprobe_lock held */
|
|
|
|
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
|
|
|
|
struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
ri->ret_addr = (kprobe_opcode_t *) regs->pr;
|
|
|
|
|
|
|
|
/* Replace the return addr with trampoline addr */
|
|
|
|
regs->pr = (unsigned long)kretprobe_trampoline;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __kprobes kprobe_handler(struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
struct kprobe *p;
|
|
|
|
int ret = 0;
|
|
|
|
kprobe_opcode_t *addr = NULL;
|
|
|
|
struct kprobe_ctlblk *kcb;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We don't want to be preempted for the entire
|
|
|
|
* duration of kprobe processing
|
|
|
|
*/
|
|
|
|
preempt_disable();
|
|
|
|
kcb = get_kprobe_ctlblk();
|
|
|
|
|
|
|
|
addr = (kprobe_opcode_t *) (regs->pc);
|
|
|
|
|
|
|
|
/* Check we're not actually recursing */
|
|
|
|
if (kprobe_running()) {
|
|
|
|
p = get_kprobe(addr);
|
|
|
|
if (p) {
|
|
|
|
if (kcb->kprobe_status == KPROBE_HIT_SS &&
|
|
|
|
*p->ainsn.insn == BREAKPOINT_INSTRUCTION) {
|
|
|
|
goto no_kprobe;
|
|
|
|
}
|
|
|
|
/* We have reentered the kprobe_handler(), since
|
|
|
|
* another probe was hit while within the handler.
|
|
|
|
* We here save the original kprobes variables and
|
|
|
|
* just single step on the instruction of the new probe
|
|
|
|
* without calling any user handlers.
|
|
|
|
*/
|
|
|
|
save_previous_kprobe(kcb);
|
|
|
|
set_current_kprobe(p, regs, kcb);
|
|
|
|
kprobes_inc_nmissed_count(p);
|
|
|
|
prepare_singlestep(p, regs);
|
|
|
|
kcb->kprobe_status = KPROBE_REENTER;
|
|
|
|
return 1;
|
|
|
|
} else {
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
p = __this_cpu_read(current_kprobe);
|
2008-09-05 16:15:39 +08:00
|
|
|
if (p->break_handler && p->break_handler(p, regs)) {
|
|
|
|
goto ss_probe;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
goto no_kprobe;
|
|
|
|
}
|
|
|
|
|
|
|
|
p = get_kprobe(addr);
|
|
|
|
if (!p) {
|
|
|
|
/* Not one of ours: let kernel handle it */
|
2008-09-08 17:15:55 +08:00
|
|
|
if (*(kprobe_opcode_t *)addr != BREAKPOINT_INSTRUCTION) {
|
|
|
|
/*
|
|
|
|
* The breakpoint instruction was removed right
|
|
|
|
* after we hit it. Another cpu has removed
|
|
|
|
* either a probepoint or a debugger breakpoint
|
|
|
|
* at this address. In either case, no further
|
|
|
|
* handling of this interrupt is appropriate.
|
|
|
|
*/
|
|
|
|
ret = 1;
|
|
|
|
}
|
|
|
|
|
2008-09-05 16:15:39 +08:00
|
|
|
goto no_kprobe;
|
|
|
|
}
|
|
|
|
|
|
|
|
set_current_kprobe(p, regs, kcb);
|
|
|
|
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
|
|
|
|
|
|
|
|
if (p->pre_handler && p->pre_handler(p, regs))
|
|
|
|
/* handler has already set things up, so skip ss setup */
|
|
|
|
return 1;
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
ss_probe:
|
2008-09-05 16:15:39 +08:00
|
|
|
prepare_singlestep(p, regs);
|
|
|
|
kcb->kprobe_status = KPROBE_HIT_SS;
|
|
|
|
return 1;
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
no_kprobe:
|
2008-09-05 16:15:39 +08:00
|
|
|
preempt_enable_no_resched();
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For function-return probes, init_kprobes() establishes a probepoint
|
|
|
|
* here. When a retprobed function returns, this probe is hit and
|
|
|
|
* trampoline_probe_handler() runs, calling the kretprobe's handler.
|
|
|
|
*/
|
2008-09-08 11:02:17 +08:00
|
|
|
static void __used kretprobe_trampoline_holder(void)
|
2008-09-05 16:15:39 +08:00
|
|
|
{
|
2008-09-09 07:13:28 +08:00
|
|
|
asm volatile (".globl kretprobe_trampoline\n"
|
|
|
|
"kretprobe_trampoline:\n\t"
|
|
|
|
"nop\n");
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Called when we hit the probe point at kretprobe_trampoline
|
|
|
|
*/
|
|
|
|
int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
struct kretprobe_instance *ri = NULL;
|
|
|
|
struct hlist_head *head, empty_rp;
|
hlist: drop the node parameter from iterators
I'm not sure why, but the hlist for each entry iterators were conceived
list_for_each_entry(pos, head, member)
The hlist ones were greedy and wanted an extra parameter:
hlist_for_each_entry(tpos, pos, head, member)
Why did they need an extra pos parameter? I'm not quite sure. Not only
they don't really need it, it also prevents the iterator from looking
exactly like the list iterator, which is unfortunate.
Besides the semantic patch, there was some manual work required:
- Fix up the actual hlist iterators in linux/list.h
- Fix up the declaration of other iterators based on the hlist ones.
- A very small amount of places were using the 'node' parameter, this
was modified to use 'obj->member' instead.
- Coccinelle didn't handle the hlist_for_each_entry_safe iterator
properly, so those had to be fixed up manually.
The semantic patch which is mostly the work of Peter Senna Tschudin is here:
@@
iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host;
type T;
expression a,c,d,e;
identifier b;
statement S;
@@
-T b;
<+... when != b
(
hlist_for_each_entry(a,
- b,
c, d) S
|
hlist_for_each_entry_continue(a,
- b,
c) S
|
hlist_for_each_entry_from(a,
- b,
c) S
|
hlist_for_each_entry_rcu(a,
- b,
c, d) S
|
hlist_for_each_entry_rcu_bh(a,
- b,
c, d) S
|
hlist_for_each_entry_continue_rcu_bh(a,
- b,
c) S
|
for_each_busy_worker(a, c,
- b,
d) S
|
ax25_uid_for_each(a,
- b,
c) S
|
ax25_for_each(a,
- b,
c) S
|
inet_bind_bucket_for_each(a,
- b,
c) S
|
sctp_for_each_hentry(a,
- b,
c) S
|
sk_for_each(a,
- b,
c) S
|
sk_for_each_rcu(a,
- b,
c) S
|
sk_for_each_from
-(a, b)
+(a)
S
+ sk_for_each_from(a) S
|
sk_for_each_safe(a,
- b,
c, d) S
|
sk_for_each_bound(a,
- b,
c) S
|
hlist_for_each_entry_safe(a,
- b,
c, d, e) S
|
hlist_for_each_entry_continue_rcu(a,
- b,
c) S
|
nr_neigh_for_each(a,
- b,
c) S
|
nr_neigh_for_each_safe(a,
- b,
c, d) S
|
nr_node_for_each(a,
- b,
c) S
|
nr_node_for_each_safe(a,
- b,
c, d) S
|
- for_each_gfn_sp(a, c, d, b) S
+ for_each_gfn_sp(a, c, d) S
|
- for_each_gfn_indirect_valid_sp(a, c, d, b) S
+ for_each_gfn_indirect_valid_sp(a, c, d) S
|
for_each_host(a,
- b,
c) S
|
for_each_host_safe(a,
- b,
c, d) S
|
for_each_mesh_entry(a,
- b,
c, d) S
)
...+>
[akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c]
[akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c]
[akpm@linux-foundation.org: checkpatch fixes]
[akpm@linux-foundation.org: fix warnings]
[akpm@linux-foudnation.org: redo intrusive kvm changes]
Tested-by: Peter Senna Tschudin <peter.senna@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
|
|
|
struct hlist_node *tmp;
|
2008-09-05 16:15:39 +08:00
|
|
|
unsigned long flags, orig_ret_address = 0;
|
|
|
|
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
|
|
|
|
|
|
|
|
INIT_HLIST_HEAD(&empty_rp);
|
|
|
|
kretprobe_hash_lock(current, &head, &flags);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* It is possible to have multiple instances associated with a given
|
|
|
|
* task either because an multiple functions in the call path
|
|
|
|
* have a return probe installed on them, and/or more then one return
|
|
|
|
* return probe was registered for a target function.
|
|
|
|
*
|
|
|
|
* We can handle this because:
|
|
|
|
* - instances are always inserted at the head of the list
|
|
|
|
* - when multiple return probes are registered for the same
|
|
|
|
* function, the first instance's ret_addr will point to the
|
|
|
|
* real return address, and all the rest will point to
|
|
|
|
* kretprobe_trampoline
|
|
|
|
*/
|
hlist: drop the node parameter from iterators
I'm not sure why, but the hlist for each entry iterators were conceived
list_for_each_entry(pos, head, member)
The hlist ones were greedy and wanted an extra parameter:
hlist_for_each_entry(tpos, pos, head, member)
Why did they need an extra pos parameter? I'm not quite sure. Not only
they don't really need it, it also prevents the iterator from looking
exactly like the list iterator, which is unfortunate.
Besides the semantic patch, there was some manual work required:
- Fix up the actual hlist iterators in linux/list.h
- Fix up the declaration of other iterators based on the hlist ones.
- A very small amount of places were using the 'node' parameter, this
was modified to use 'obj->member' instead.
- Coccinelle didn't handle the hlist_for_each_entry_safe iterator
properly, so those had to be fixed up manually.
The semantic patch which is mostly the work of Peter Senna Tschudin is here:
@@
iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host;
type T;
expression a,c,d,e;
identifier b;
statement S;
@@
-T b;
<+... when != b
(
hlist_for_each_entry(a,
- b,
c, d) S
|
hlist_for_each_entry_continue(a,
- b,
c) S
|
hlist_for_each_entry_from(a,
- b,
c) S
|
hlist_for_each_entry_rcu(a,
- b,
c, d) S
|
hlist_for_each_entry_rcu_bh(a,
- b,
c, d) S
|
hlist_for_each_entry_continue_rcu_bh(a,
- b,
c) S
|
for_each_busy_worker(a, c,
- b,
d) S
|
ax25_uid_for_each(a,
- b,
c) S
|
ax25_for_each(a,
- b,
c) S
|
inet_bind_bucket_for_each(a,
- b,
c) S
|
sctp_for_each_hentry(a,
- b,
c) S
|
sk_for_each(a,
- b,
c) S
|
sk_for_each_rcu(a,
- b,
c) S
|
sk_for_each_from
-(a, b)
+(a)
S
+ sk_for_each_from(a) S
|
sk_for_each_safe(a,
- b,
c, d) S
|
sk_for_each_bound(a,
- b,
c) S
|
hlist_for_each_entry_safe(a,
- b,
c, d, e) S
|
hlist_for_each_entry_continue_rcu(a,
- b,
c) S
|
nr_neigh_for_each(a,
- b,
c) S
|
nr_neigh_for_each_safe(a,
- b,
c, d) S
|
nr_node_for_each(a,
- b,
c) S
|
nr_node_for_each_safe(a,
- b,
c, d) S
|
- for_each_gfn_sp(a, c, d, b) S
+ for_each_gfn_sp(a, c, d) S
|
- for_each_gfn_indirect_valid_sp(a, c, d, b) S
+ for_each_gfn_indirect_valid_sp(a, c, d) S
|
for_each_host(a,
- b,
c) S
|
for_each_host_safe(a,
- b,
c, d) S
|
for_each_mesh_entry(a,
- b,
c, d) S
)
...+>
[akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c]
[akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c]
[akpm@linux-foundation.org: checkpatch fixes]
[akpm@linux-foundation.org: fix warnings]
[akpm@linux-foudnation.org: redo intrusive kvm changes]
Tested-by: Peter Senna Tschudin <peter.senna@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
|
|
|
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
|
2008-09-05 16:15:39 +08:00
|
|
|
if (ri->task != current)
|
|
|
|
/* another task is sharing our hash bucket */
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (ri->rp && ri->rp->handler) {
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
__this_cpu_write(current_kprobe, &ri->rp->kp);
|
2008-09-05 16:15:39 +08:00
|
|
|
ri->rp->handler(ri, regs);
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
__this_cpu_write(current_kprobe, NULL);
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
orig_ret_address = (unsigned long)ri->ret_addr;
|
|
|
|
recycle_rp_inst(ri, &empty_rp);
|
|
|
|
|
|
|
|
if (orig_ret_address != trampoline_address)
|
|
|
|
/*
|
|
|
|
* This is the real return address. Any other
|
|
|
|
* instances associated with this task are for
|
|
|
|
* other calls deeper on the call stack
|
|
|
|
*/
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
kretprobe_assert(ri, orig_ret_address, trampoline_address);
|
|
|
|
|
|
|
|
regs->pc = orig_ret_address;
|
|
|
|
kretprobe_hash_unlock(current, &flags);
|
|
|
|
|
|
|
|
preempt_enable_no_resched();
|
|
|
|
|
hlist: drop the node parameter from iterators
I'm not sure why, but the hlist for each entry iterators were conceived
list_for_each_entry(pos, head, member)
The hlist ones were greedy and wanted an extra parameter:
hlist_for_each_entry(tpos, pos, head, member)
Why did they need an extra pos parameter? I'm not quite sure. Not only
they don't really need it, it also prevents the iterator from looking
exactly like the list iterator, which is unfortunate.
Besides the semantic patch, there was some manual work required:
- Fix up the actual hlist iterators in linux/list.h
- Fix up the declaration of other iterators based on the hlist ones.
- A very small amount of places were using the 'node' parameter, this
was modified to use 'obj->member' instead.
- Coccinelle didn't handle the hlist_for_each_entry_safe iterator
properly, so those had to be fixed up manually.
The semantic patch which is mostly the work of Peter Senna Tschudin is here:
@@
iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host;
type T;
expression a,c,d,e;
identifier b;
statement S;
@@
-T b;
<+... when != b
(
hlist_for_each_entry(a,
- b,
c, d) S
|
hlist_for_each_entry_continue(a,
- b,
c) S
|
hlist_for_each_entry_from(a,
- b,
c) S
|
hlist_for_each_entry_rcu(a,
- b,
c, d) S
|
hlist_for_each_entry_rcu_bh(a,
- b,
c, d) S
|
hlist_for_each_entry_continue_rcu_bh(a,
- b,
c) S
|
for_each_busy_worker(a, c,
- b,
d) S
|
ax25_uid_for_each(a,
- b,
c) S
|
ax25_for_each(a,
- b,
c) S
|
inet_bind_bucket_for_each(a,
- b,
c) S
|
sctp_for_each_hentry(a,
- b,
c) S
|
sk_for_each(a,
- b,
c) S
|
sk_for_each_rcu(a,
- b,
c) S
|
sk_for_each_from
-(a, b)
+(a)
S
+ sk_for_each_from(a) S
|
sk_for_each_safe(a,
- b,
c, d) S
|
sk_for_each_bound(a,
- b,
c) S
|
hlist_for_each_entry_safe(a,
- b,
c, d, e) S
|
hlist_for_each_entry_continue_rcu(a,
- b,
c) S
|
nr_neigh_for_each(a,
- b,
c) S
|
nr_neigh_for_each_safe(a,
- b,
c, d) S
|
nr_node_for_each(a,
- b,
c) S
|
nr_node_for_each_safe(a,
- b,
c, d) S
|
- for_each_gfn_sp(a, c, d, b) S
+ for_each_gfn_sp(a, c, d) S
|
- for_each_gfn_indirect_valid_sp(a, c, d, b) S
+ for_each_gfn_indirect_valid_sp(a, c, d) S
|
for_each_host(a,
- b,
c) S
|
for_each_host_safe(a,
- b,
c, d) S
|
for_each_mesh_entry(a,
- b,
c, d) S
)
...+>
[akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c]
[akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c]
[akpm@linux-foundation.org: checkpatch fixes]
[akpm@linux-foundation.org: fix warnings]
[akpm@linux-foudnation.org: redo intrusive kvm changes]
Tested-by: Peter Senna Tschudin <peter.senna@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
|
|
|
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
|
2008-09-05 16:15:39 +08:00
|
|
|
hlist_del(&ri->hlist);
|
|
|
|
kfree(ri);
|
|
|
|
}
|
|
|
|
|
|
|
|
return orig_ret_address;
|
|
|
|
}
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
static int __kprobes post_kprobe_handler(struct pt_regs *regs)
|
2008-09-05 16:15:39 +08:00
|
|
|
{
|
|
|
|
struct kprobe *cur = kprobe_running();
|
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
|
|
|
kprobe_opcode_t *addr = NULL;
|
|
|
|
struct kprobe *p = NULL;
|
|
|
|
|
|
|
|
if (!cur)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
|
|
|
|
kcb->kprobe_status = KPROBE_HIT_SSDONE;
|
|
|
|
cur->post_handler(cur, regs, 0);
|
|
|
|
}
|
|
|
|
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
p = this_cpu_ptr(&saved_next_opcode);
|
2010-06-14 16:06:10 +08:00
|
|
|
if (p->addr) {
|
|
|
|
arch_disarm_kprobe(p);
|
|
|
|
p->addr = NULL;
|
|
|
|
p->opcode = 0;
|
2008-09-05 16:15:39 +08:00
|
|
|
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
addr = __this_cpu_read(saved_current_opcode.addr);
|
|
|
|
__this_cpu_write(saved_current_opcode.addr, NULL);
|
2008-09-05 16:15:39 +08:00
|
|
|
|
|
|
|
p = get_kprobe(addr);
|
|
|
|
arch_arm_kprobe(p);
|
|
|
|
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
p = this_cpu_ptr(&saved_next_opcode2);
|
2010-06-14 16:06:10 +08:00
|
|
|
if (p->addr) {
|
|
|
|
arch_disarm_kprobe(p);
|
|
|
|
p->addr = NULL;
|
|
|
|
p->opcode = 0;
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
/* Restore back the original saved kprobes variables and continue. */
|
2008-09-05 16:15:39 +08:00
|
|
|
if (kcb->kprobe_status == KPROBE_REENTER) {
|
|
|
|
restore_previous_kprobe(kcb);
|
|
|
|
goto out;
|
|
|
|
}
|
2008-09-08 17:22:47 +08:00
|
|
|
|
2008-09-05 16:15:39 +08:00
|
|
|
reset_current_kprobe();
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
out:
|
2008-09-05 16:15:39 +08:00
|
|
|
preempt_enable_no_resched();
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2008-09-08 11:22:47 +08:00
|
|
|
int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
|
2008-09-05 16:15:39 +08:00
|
|
|
{
|
|
|
|
struct kprobe *cur = kprobe_running();
|
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
|
|
|
const struct exception_table_entry *entry;
|
|
|
|
|
|
|
|
switch (kcb->kprobe_status) {
|
|
|
|
case KPROBE_HIT_SS:
|
|
|
|
case KPROBE_REENTER:
|
|
|
|
/*
|
|
|
|
* We are here because the instruction being single
|
|
|
|
* stepped caused a page fault. We reset the current
|
|
|
|
* kprobe, point the pc back to the probe address
|
|
|
|
* and allow the page fault handler to continue as a
|
|
|
|
* normal page fault.
|
|
|
|
*/
|
|
|
|
regs->pc = (unsigned long)cur->addr;
|
|
|
|
if (kcb->kprobe_status == KPROBE_REENTER)
|
|
|
|
restore_previous_kprobe(kcb);
|
|
|
|
else
|
|
|
|
reset_current_kprobe();
|
|
|
|
preempt_enable_no_resched();
|
|
|
|
break;
|
|
|
|
case KPROBE_HIT_ACTIVE:
|
|
|
|
case KPROBE_HIT_SSDONE:
|
|
|
|
/*
|
|
|
|
* We increment the nmissed count for accounting,
|
|
|
|
* we can also use npre/npostfault count for accounting
|
|
|
|
* these specific fault cases.
|
|
|
|
*/
|
|
|
|
kprobes_inc_nmissed_count(cur);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We come here because instructions in the pre/post
|
|
|
|
* handler caused the page_fault, this could happen
|
|
|
|
* if handler tries to access user space by
|
|
|
|
* copy_from_user(), get_user() etc. Let the
|
|
|
|
* user-specified handler try to fix it first.
|
|
|
|
*/
|
|
|
|
if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* In case the user-specified fault handler returned
|
|
|
|
* zero, try to fix up.
|
|
|
|
*/
|
|
|
|
if ((entry = search_exception_tables(regs->pc)) != NULL) {
|
|
|
|
regs->pc = entry->fixup;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* fixup_exception() could not handle it,
|
|
|
|
* Let do_page_fault() fix it.
|
|
|
|
*/
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
2008-09-08 17:22:47 +08:00
|
|
|
|
2008-09-05 16:15:39 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wrapper routine to for handling exceptions.
|
|
|
|
*/
|
|
|
|
int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
|
|
|
|
unsigned long val, void *data)
|
|
|
|
{
|
|
|
|
struct kprobe *p = NULL;
|
|
|
|
struct die_args *args = (struct die_args *)data;
|
|
|
|
int ret = NOTIFY_DONE;
|
|
|
|
kprobe_opcode_t *addr = NULL;
|
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
|
|
|
|
|
|
|
addr = (kprobe_opcode_t *) (args->regs->pc);
|
|
|
|
if (val == DIE_TRAP) {
|
|
|
|
if (!kprobe_running()) {
|
|
|
|
if (kprobe_handler(args->regs)) {
|
|
|
|
ret = NOTIFY_STOP;
|
|
|
|
} else {
|
|
|
|
/* Not a kprobe trap */
|
2008-09-08 17:12:33 +08:00
|
|
|
ret = NOTIFY_DONE;
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
} else {
|
|
|
|
p = get_kprobe(addr);
|
|
|
|
if ((kcb->kprobe_status == KPROBE_HIT_SS) ||
|
|
|
|
(kcb->kprobe_status == KPROBE_REENTER)) {
|
|
|
|
if (post_kprobe_handler(args->regs))
|
|
|
|
ret = NOTIFY_STOP;
|
|
|
|
} else {
|
|
|
|
if (kprobe_handler(args->regs)) {
|
|
|
|
ret = NOTIFY_STOP;
|
|
|
|
} else {
|
sh: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:51 +08:00
|
|
|
p = __this_cpu_read(current_kprobe);
|
2008-09-08 17:22:47 +08:00
|
|
|
if (p->break_handler &&
|
|
|
|
p->break_handler(p, args->regs))
|
2008-09-05 16:15:39 +08:00
|
|
|
ret = NOTIFY_STOP;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
struct jprobe *jp = container_of(p, struct jprobe, kp);
|
|
|
|
unsigned long addr;
|
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
|
|
|
|
|
|
|
kcb->jprobe_saved_regs = *regs;
|
|
|
|
kcb->jprobe_saved_r15 = regs->regs[15];
|
|
|
|
addr = kcb->jprobe_saved_r15;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* TBD: As Linus pointed out, gcc assumes that the callee
|
|
|
|
* owns the argument space and could overwrite it, e.g.
|
|
|
|
* tailcall optimization. So, to be absolutely safe
|
|
|
|
* we also save and restore enough stack bytes to cover
|
|
|
|
* the argument area.
|
|
|
|
*/
|
|
|
|
memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr,
|
|
|
|
MIN_STACK_SIZE(addr));
|
|
|
|
|
|
|
|
regs->pc = (unsigned long)(jp->entry);
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
void __kprobes jprobe_return(void)
|
|
|
|
{
|
2008-09-08 17:10:10 +08:00
|
|
|
asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t");
|
2008-09-05 16:15:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
|
|
|
unsigned long stack_addr = kcb->jprobe_saved_r15;
|
2008-09-08 17:22:47 +08:00
|
|
|
u8 *addr = (u8 *)regs->pc;
|
2008-09-05 16:15:39 +08:00
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
if ((addr >= (u8 *)jprobe_return) &&
|
|
|
|
(addr <= (u8 *)jprobe_return_end)) {
|
2008-09-05 16:15:39 +08:00
|
|
|
*regs = kcb->jprobe_saved_regs;
|
|
|
|
|
2008-09-08 17:22:47 +08:00
|
|
|
memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack,
|
2008-09-05 16:15:39 +08:00
|
|
|
MIN_STACK_SIZE(stack_addr));
|
|
|
|
|
|
|
|
kcb->kprobe_status = KPROBE_HIT_SS;
|
2008-09-08 17:14:50 +08:00
|
|
|
preempt_enable_no_resched();
|
2008-09-05 16:15:39 +08:00
|
|
|
return 1;
|
|
|
|
}
|
2008-09-08 17:22:47 +08:00
|
|
|
|
2008-09-05 16:15:39 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct kprobe trampoline_p = {
|
2008-09-08 17:22:47 +08:00
|
|
|
.addr = (kprobe_opcode_t *)&kretprobe_trampoline,
|
2008-09-05 16:15:39 +08:00
|
|
|
.pre_handler = trampoline_probe_handler
|
|
|
|
};
|
|
|
|
|
|
|
|
int __init arch_init_kprobes(void)
|
|
|
|
{
|
|
|
|
return register_kprobe(&trampoline_p);
|
|
|
|
}
|