2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* Kernel Probes (KProbes)
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
|
|
* (at your option) any later version.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
* along with this program; if not, write to the Free Software
|
|
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
|
|
*
|
|
|
|
* Copyright (C) IBM Corporation, 2002, 2004
|
|
|
|
*
|
|
|
|
* 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
|
|
|
|
* Probes initial implementation ( includes contributions from
|
|
|
|
* Rusty Russell).
|
|
|
|
* 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
|
|
|
|
* interface to access function arguments.
|
|
|
|
* 2004-Nov Ananth N Mavinakayanahalli <ananth@in.ibm.com> kprobes port
|
|
|
|
* for PPC64
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kprobes.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/preempt.h>
|
2016-08-16 17:57:34 +03:00
|
|
|
#include <linux/extable.h>
|
2007-05-08 11:27:03 +04:00
|
|
|
#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 11:04:11 +03:00
|
|
|
#include <linux/slab.h>
|
2014-06-23 07:23:31 +04:00
|
|
|
#include <asm/code-patching.h>
|
2005-06-23 11:09:25 +04:00
|
|
|
#include <asm/cacheflush.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include <asm/sstep.h>
|
2017-04-19 18:29:51 +03:00
|
|
|
#include <asm/sections.h>
|
2016-12-24 22:46:01 +03:00
|
|
|
#include <linux/uaccess.h>
|
2008-06-26 11:01:37 +04:00
|
|
|
|
2005-11-07 12:00:10 +03:00
|
|
|
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
|
|
|
|
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2007-10-16 12:27:49 +04:00
|
|
|
struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
|
|
|
|
|
2017-06-01 13:48:17 +03:00
|
|
|
int is_current_kprobe_addr(unsigned long addr)
|
|
|
|
{
|
|
|
|
struct kprobe *p = kprobe_running();
|
|
|
|
return (p && (unsigned long)p->addr == addr) ? 1 : 0;
|
|
|
|
}
|
|
|
|
|
2017-04-19 18:29:51 +03:00
|
|
|
bool arch_within_kprobe_blacklist(unsigned long addr)
|
|
|
|
{
|
|
|
|
return (addr >= (unsigned long)__kprobes_text_start &&
|
|
|
|
addr < (unsigned long)__kprobes_text_end) ||
|
|
|
|
(addr >= (unsigned long)_stext &&
|
|
|
|
addr < (unsigned long)__head_end);
|
|
|
|
}
|
|
|
|
|
2017-04-19 15:51:01 +03:00
|
|
|
kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
|
2017-04-19 15:51:00 +03:00
|
|
|
{
|
|
|
|
kprobe_opcode_t *addr;
|
|
|
|
|
|
|
|
#ifdef PPC64_ELF_ABI_v2
|
|
|
|
/* PPC64 ABIv2 needs local entry point */
|
|
|
|
addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
|
2017-04-19 15:52:28 +03:00
|
|
|
if (addr && !offset) {
|
|
|
|
#ifdef CONFIG_KPROBES_ON_FTRACE
|
|
|
|
unsigned long faddr;
|
|
|
|
/*
|
|
|
|
* Per livepatch.h, ftrace location is always within the first
|
|
|
|
* 16 bytes of a function on powerpc with -mprofile-kernel.
|
|
|
|
*/
|
|
|
|
faddr = ftrace_location_range((unsigned long)addr,
|
|
|
|
(unsigned long)addr + 16);
|
|
|
|
if (faddr)
|
|
|
|
addr = (kprobe_opcode_t *)faddr;
|
|
|
|
else
|
|
|
|
#endif
|
|
|
|
addr = (kprobe_opcode_t *)ppc_function_entry(addr);
|
|
|
|
}
|
2017-04-19 15:51:00 +03:00
|
|
|
#elif defined(PPC64_ELF_ABI_v1)
|
|
|
|
/*
|
|
|
|
* 64bit powerpc ABIv1 uses function descriptors:
|
|
|
|
* - Check for the dot variant of the symbol first.
|
|
|
|
* - If that fails, try looking up the symbol provided.
|
|
|
|
*
|
|
|
|
* This ensures we always get to the actual symbol and not
|
|
|
|
* the descriptor.
|
|
|
|
*
|
|
|
|
* Also handle <module:symbol> format.
|
|
|
|
*/
|
|
|
|
char dot_name[MODULE_NAME_LEN + 1 + KSYM_NAME_LEN];
|
|
|
|
const char *modsym;
|
|
|
|
bool dot_appended = false;
|
|
|
|
if ((modsym = strchr(name, ':')) != NULL) {
|
|
|
|
modsym++;
|
|
|
|
if (*modsym != '\0' && *modsym != '.') {
|
|
|
|
/* Convert to <module:.symbol> */
|
|
|
|
strncpy(dot_name, name, modsym - name);
|
|
|
|
dot_name[modsym - name] = '.';
|
|
|
|
dot_name[modsym - name + 1] = '\0';
|
|
|
|
strncat(dot_name, modsym,
|
|
|
|
sizeof(dot_name) - (modsym - name) - 2);
|
|
|
|
dot_appended = true;
|
|
|
|
} else {
|
|
|
|
dot_name[0] = '\0';
|
|
|
|
strncat(dot_name, name, sizeof(dot_name) - 1);
|
|
|
|
}
|
|
|
|
} else if (name[0] != '.') {
|
|
|
|
dot_name[0] = '.';
|
|
|
|
dot_name[1] = '\0';
|
|
|
|
strncat(dot_name, name, KSYM_NAME_LEN - 2);
|
|
|
|
dot_appended = true;
|
|
|
|
} else {
|
|
|
|
dot_name[0] = '\0';
|
|
|
|
strncat(dot_name, name, KSYM_NAME_LEN - 1);
|
|
|
|
}
|
|
|
|
addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name);
|
|
|
|
if (!addr && dot_appended) {
|
|
|
|
/* Let's try the original non-dot symbol lookup */
|
|
|
|
addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
return addr;
|
|
|
|
}
|
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
int arch_prepare_kprobe(struct kprobe *p)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2005-06-09 02:49:41 +04:00
|
|
|
int ret = 0;
|
2005-04-17 02:20:36 +04:00
|
|
|
kprobe_opcode_t insn = *p->addr;
|
|
|
|
|
2005-06-09 02:49:41 +04:00
|
|
|
if ((unsigned long)p->addr & 0x03) {
|
|
|
|
printk("Attempt to register kprobe at an unaligned address\n");
|
|
|
|
ret = -EINVAL;
|
2007-02-07 07:55:19 +03:00
|
|
|
} else if (IS_MTMSRD(insn) || IS_RFID(insn) || IS_RFI(insn)) {
|
|
|
|
printk("Cannot register a kprobe on rfi/rfid or mtmsr[d]\n");
|
2005-06-09 02:49:41 +04:00
|
|
|
ret = -EINVAL;
|
|
|
|
}
|
2005-06-28 02:17:01 +04:00
|
|
|
|
2008-06-26 11:01:37 +04:00
|
|
|
/* insn must be on a special executable page on ppc64. This is
|
|
|
|
* not explicitly required on ppc32 (right now), but it doesn't hurt */
|
2005-06-28 02:17:01 +04:00
|
|
|
if (!ret) {
|
2005-10-01 21:14:17 +04:00
|
|
|
p->ainsn.insn = get_insn_slot();
|
2005-06-28 02:17:01 +04:00
|
|
|
if (!p->ainsn.insn)
|
|
|
|
ret = -ENOMEM;
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2006-01-10 07:52:43 +03:00
|
|
|
if (!ret) {
|
2007-04-18 09:57:51 +04:00
|
|
|
memcpy(p->ainsn.insn, p->addr,
|
|
|
|
MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
|
2006-01-10 07:52:43 +03:00
|
|
|
p->opcode = *p->addr;
|
[POWERPC] kprobes: Fix possible system crash during out-of-line single-stepping
- On archs that have no-exec support, we vmalloc() a executable scratch
area of PAGE_SIZE and divide it up into an array of slots of maximum
instruction size for that arch
- On a kprobe registration, the original instruction is copied to the
first available free slot, so if multiple kprobes are registered, chances
are, they get contiguous slots
- On POWER4, due to not having coherent icaches, we could hit a situation
where a probe that is registered on one processor, is hit immediately on
another. This second processor could have fetched the stream of text from
the out-of-line single-stepping area *before* the probe registration
completed, possibly due to an earlier (and a different) kprobe hit and
hence would see stale data at the slot.
Executing such an arbitrary instruction lead to a problem as reported
in LTC bugzilla 23555.
The correct solution is to call flush_icache_range() as soon as the
instruction is copied for out-of-line single-stepping, so the correct
instruction is seen on all processors.
Thanks to Will Schmidt who tracked this down.
Signed-off-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Acked-by: Will Schmidt <will_schmidt@vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-08-11 15:31:34 +04:00
|
|
|
flush_icache_range((unsigned long)p->ainsn.insn,
|
|
|
|
(unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t));
|
2006-01-10 07:52:43 +03:00
|
|
|
}
|
|
|
|
|
2007-04-18 09:57:51 +04:00
|
|
|
p->ainsn.boostable = 0;
|
2006-01-10 07:52:43 +03:00
|
|
|
return ret;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(arch_prepare_kprobe);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
void arch_arm_kprobe(struct kprobe *p)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2005-06-23 11:09:25 +04:00
|
|
|
*p->addr = BREAKPOINT_INSTRUCTION;
|
|
|
|
flush_icache_range((unsigned long) p->addr,
|
|
|
|
(unsigned long) p->addr + sizeof(kprobe_opcode_t));
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(arch_arm_kprobe);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
void arch_disarm_kprobe(struct kprobe *p)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
*p->addr = p->opcode;
|
2005-06-23 11:09:25 +04:00
|
|
|
flush_icache_range((unsigned long) p->addr,
|
|
|
|
(unsigned long) p->addr + sizeof(kprobe_opcode_t));
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(arch_disarm_kprobe);
|
2005-06-23 11:09:25 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
void arch_remove_kprobe(struct kprobe *p)
|
2005-06-23 11:09:25 +04:00
|
|
|
{
|
2009-01-07 01:41:50 +03:00
|
|
|
if (p->ainsn.insn) {
|
|
|
|
free_insn_slot(p->ainsn.insn, 0);
|
|
|
|
p->ainsn.insn = NULL;
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(arch_remove_kprobe);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
static nokprobe_inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2012-12-03 19:08:37 +04:00
|
|
|
enable_single_step(regs);
|
2005-06-28 02:17:01 +04:00
|
|
|
|
2006-04-28 16:08:42 +04:00
|
|
|
/*
|
|
|
|
* On powerpc we should single step on the original
|
|
|
|
* instruction even if the probed insn is a trap
|
|
|
|
* variant as values in regs could play a part in
|
|
|
|
* if the trap is taken or not
|
|
|
|
*/
|
|
|
|
regs->nip = (unsigned long)p->ainsn.insn;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
static nokprobe_inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
|
2005-11-07 12:00:10 +03:00
|
|
|
{
|
|
|
|
kcb->prev_kprobe.kp = kprobe_running();
|
|
|
|
kcb->prev_kprobe.status = kcb->kprobe_status;
|
|
|
|
kcb->prev_kprobe.saved_msr = kcb->kprobe_saved_msr;
|
|
|
|
}
|
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
static nokprobe_inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
|
2005-06-23 11:09:38 +04:00
|
|
|
{
|
powerpc: Replace __get_cpu_var uses
This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.
V2->V2
- Fix up to work against 3.18-rc1
__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 :
__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)
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-22 00:23:25 +04:00
|
|
|
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
|
2005-11-07 12:00:10 +03:00
|
|
|
kcb->kprobe_status = kcb->prev_kprobe.status;
|
|
|
|
kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
|
2005-06-23 11:09:38 +04:00
|
|
|
}
|
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
|
2005-11-07 12:00:10 +03:00
|
|
|
struct kprobe_ctlblk *kcb)
|
2005-06-23 11:09:38 +04:00
|
|
|
{
|
powerpc: Replace __get_cpu_var uses
This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.
V2->V2
- Fix up to work against 3.18-rc1
__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 :
__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)
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-22 00:23:25 +04:00
|
|
|
__this_cpu_write(current_kprobe, p);
|
2005-11-07 12:00:10 +03:00
|
|
|
kcb->kprobe_saved_msr = regs->msr;
|
2005-06-23 11:09:38 +04:00
|
|
|
}
|
|
|
|
|
2017-03-08 11:26:07 +03:00
|
|
|
bool arch_function_offset_within_entry(unsigned long offset)
|
|
|
|
{
|
|
|
|
#ifdef PPC64_ELF_ABI_v2
|
2017-04-19 15:52:26 +03:00
|
|
|
#ifdef CONFIG_KPROBES_ON_FTRACE
|
|
|
|
return offset <= 16;
|
|
|
|
#else
|
2017-03-08 11:26:07 +03:00
|
|
|
return offset <= 8;
|
2017-04-19 15:52:26 +03:00
|
|
|
#endif
|
2017-03-08 11:26:07 +03:00
|
|
|
#else
|
|
|
|
return !offset;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
|
2005-06-28 02:17:15 +04:00
|
|
|
{
|
2007-05-08 11:34:14 +04:00
|
|
|
ri->ret_addr = (kprobe_opcode_t *)regs->link;
|
|
|
|
|
|
|
|
/* Replace the return addr with trampoline addr */
|
|
|
|
regs->link = (unsigned long)kretprobe_trampoline;
|
2005-06-28 02:17:15 +04:00
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(arch_prepare_kretprobe);
|
2005-06-28 02:17:15 +04:00
|
|
|
|
2017-04-24 17:24:04 +03:00
|
|
|
int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
|
2017-04-19 15:51:04 +03:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
unsigned int insn = *p->ainsn.insn;
|
|
|
|
|
|
|
|
/* regs->nip is also adjusted if emulate_step returns 1 */
|
|
|
|
ret = emulate_step(regs, insn);
|
|
|
|
if (ret > 0) {
|
|
|
|
/*
|
|
|
|
* Once this instruction has been boosted
|
|
|
|
* successfully, set the boostable flag
|
|
|
|
*/
|
|
|
|
if (unlikely(p->ainsn.boostable == 0))
|
|
|
|
p->ainsn.boostable = 1;
|
|
|
|
} else if (ret < 0) {
|
|
|
|
/*
|
|
|
|
* We don't allow kprobes on mtmsr(d)/rfi(d), etc.
|
|
|
|
* So, we should never get here... but, its still
|
|
|
|
* good to catch them, just in case...
|
|
|
|
*/
|
|
|
|
printk("Can't step on instruction %x\n", insn);
|
|
|
|
BUG();
|
|
|
|
} else if (ret == 0)
|
|
|
|
/* This instruction can't be boosted */
|
|
|
|
p->ainsn.boostable = -1;
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
2017-04-24 17:24:04 +03:00
|
|
|
NOKPROBE_SYMBOL(try_to_emulate);
|
2017-04-19 15:51:04 +03:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
int kprobe_handler(struct pt_regs *regs)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
struct kprobe *p;
|
|
|
|
int ret = 0;
|
|
|
|
unsigned int *addr = (unsigned int *)regs->nip;
|
2005-11-07 12:00:14 +03:00
|
|
|
struct kprobe_ctlblk *kcb;
|
|
|
|
|
2016-11-21 20:06:41 +03:00
|
|
|
if (user_mode(regs))
|
|
|
|
return 0;
|
|
|
|
|
2005-11-07 12:00:14 +03:00
|
|
|
/*
|
|
|
|
* We don't want to be preempted for the entire
|
|
|
|
* duration of kprobe processing
|
|
|
|
*/
|
|
|
|
preempt_disable();
|
|
|
|
kcb = get_kprobe_ctlblk();
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
/* Check we're not actually recursing */
|
|
|
|
if (kprobe_running()) {
|
|
|
|
p = get_kprobe(addr);
|
|
|
|
if (p) {
|
2005-09-07 02:19:35 +04:00
|
|
|
kprobe_opcode_t insn = *p->ainsn.insn;
|
2005-11-07 12:00:10 +03:00
|
|
|
if (kcb->kprobe_status == KPROBE_HIT_SS &&
|
2005-09-07 02:19:35 +04:00
|
|
|
is_trap(insn)) {
|
2008-06-26 11:01:37 +04:00
|
|
|
/* Turn off 'trace' bits */
|
|
|
|
regs->msr &= ~MSR_SINGLESTEP;
|
2005-11-07 12:00:10 +03:00
|
|
|
regs->msr |= kcb->kprobe_saved_msr;
|
2005-04-17 02:20:36 +04:00
|
|
|
goto no_kprobe;
|
|
|
|
}
|
2005-06-23 11:09:38 +04:00
|
|
|
/* 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.
|
|
|
|
*/
|
2005-11-07 12:00:10 +03:00
|
|
|
save_previous_kprobe(kcb);
|
|
|
|
set_current_kprobe(p, regs, kcb);
|
2005-12-12 11:37:34 +03:00
|
|
|
kprobes_inc_nmissed_count(p);
|
2005-11-07 12:00:10 +03:00
|
|
|
kcb->kprobe_status = KPROBE_REENTER;
|
2017-04-19 15:51:05 +03:00
|
|
|
if (p->ainsn.boostable >= 0) {
|
|
|
|
ret = try_to_emulate(p, regs);
|
|
|
|
|
|
|
|
if (ret > 0) {
|
|
|
|
restore_previous_kprobe(kcb);
|
2017-05-15 21:10:05 +03:00
|
|
|
preempt_enable_no_resched();
|
2017-04-19 15:51:05 +03:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|
2017-05-15 21:10:05 +03:00
|
|
|
prepare_singlestep(p, regs);
|
2005-06-23 11:09:38 +04:00
|
|
|
return 1;
|
2005-04-17 02:20:36 +04:00
|
|
|
} else {
|
2006-01-11 23:17:42 +03:00
|
|
|
if (*addr != BREAKPOINT_INSTRUCTION) {
|
|
|
|
/* If trap variant, then it belongs not to us */
|
|
|
|
kprobe_opcode_t cur_insn = *addr;
|
|
|
|
if (is_trap(cur_insn))
|
|
|
|
goto no_kprobe;
|
|
|
|
/* The breakpoint instruction was removed by
|
|
|
|
* another cpu right after we hit, no further
|
|
|
|
* handling of this interrupt is appropriate
|
|
|
|
*/
|
|
|
|
ret = 1;
|
|
|
|
goto no_kprobe;
|
|
|
|
}
|
powerpc: Replace __get_cpu_var uses
This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.
V2->V2
- Fix up to work against 3.18-rc1
__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 :
__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)
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-22 00:23:25 +04:00
|
|
|
p = __this_cpu_read(current_kprobe);
|
2005-04-17 02:20:36 +04:00
|
|
|
if (p->break_handler && p->break_handler(p, regs)) {
|
2017-04-19 15:52:26 +03:00
|
|
|
if (!skip_singlestep(p, regs, kcb))
|
|
|
|
goto ss_probe;
|
|
|
|
ret = 1;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
goto no_kprobe;
|
|
|
|
}
|
|
|
|
|
|
|
|
p = get_kprobe(addr);
|
|
|
|
if (!p) {
|
|
|
|
if (*addr != BREAKPOINT_INSTRUCTION) {
|
|
|
|
/*
|
|
|
|
* PowerPC has multiple variants of the "trap"
|
|
|
|
* instruction. If the current instruction is a
|
|
|
|
* trap variant, it could belong to someone else
|
|
|
|
*/
|
|
|
|
kprobe_opcode_t cur_insn = *addr;
|
2005-09-07 02:19:35 +04:00
|
|
|
if (is_trap(cur_insn))
|
2005-04-17 02:20:36 +04:00
|
|
|
goto no_kprobe;
|
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
/* Not one of ours: let kernel handle it */
|
|
|
|
goto no_kprobe;
|
|
|
|
}
|
|
|
|
|
2005-11-07 12:00:10 +03:00
|
|
|
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
|
|
|
|
set_current_kprobe(p, regs, kcb);
|
2005-04-17 02:20:36 +04:00
|
|
|
if (p->pre_handler && p->pre_handler(p, regs))
|
|
|
|
/* handler has already set things up, so skip ss setup */
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
ss_probe:
|
2007-04-18 09:57:51 +04:00
|
|
|
if (p->ainsn.boostable >= 0) {
|
2017-04-19 15:51:04 +03:00
|
|
|
ret = try_to_emulate(p, regs);
|
2007-04-18 09:57:51 +04:00
|
|
|
|
|
|
|
if (ret > 0) {
|
|
|
|
if (p->post_handler)
|
|
|
|
p->post_handler(p, regs, 0);
|
|
|
|
|
|
|
|
kcb->kprobe_status = KPROBE_HIT_SSDONE;
|
|
|
|
reset_current_kprobe();
|
|
|
|
preempt_enable_no_resched();
|
|
|
|
return 1;
|
2017-04-19 15:51:04 +03:00
|
|
|
}
|
2007-04-18 09:57:51 +04:00
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
prepare_singlestep(p, regs);
|
2005-11-07 12:00:10 +03:00
|
|
|
kcb->kprobe_status = KPROBE_HIT_SS;
|
2005-04-17 02:20:36 +04:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
no_kprobe:
|
2005-11-07 12:00:14 +03:00
|
|
|
preempt_enable_no_resched();
|
2005-04-17 02:20:36 +04:00
|
|
|
return ret;
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(kprobe_handler);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2005-06-28 02:17:15 +04:00
|
|
|
/*
|
|
|
|
* Function return probe trampoline:
|
|
|
|
* - init_kprobes() establishes a probepoint here
|
|
|
|
* - When the probed function returns, this probe
|
|
|
|
* causes the handlers to fire
|
|
|
|
*/
|
2016-03-31 23:10:40 +03:00
|
|
|
asm(".global kretprobe_trampoline\n"
|
|
|
|
".type kretprobe_trampoline, @function\n"
|
|
|
|
"kretprobe_trampoline:\n"
|
|
|
|
"nop\n"
|
2017-02-08 12:50:52 +03:00
|
|
|
"blr\n"
|
2016-03-31 23:10:40 +03:00
|
|
|
".size kretprobe_trampoline, .-kretprobe_trampoline\n");
|
2005-06-28 02:17:15 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Called when the probe at kretprobe trampoline is hit
|
|
|
|
*/
|
2017-04-12 14:18:51 +03:00
|
|
|
static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
|
2005-06-28 02:17:15 +04:00
|
|
|
{
|
2006-10-02 13:17:33 +04:00
|
|
|
struct kretprobe_instance *ri = NULL;
|
2006-10-02 13:17:35 +04:00
|
|
|
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 05:06:00 +04:00
|
|
|
struct hlist_node *tmp;
|
2005-11-07 12:00:14 +03:00
|
|
|
unsigned long flags, orig_ret_address = 0;
|
2005-06-28 02:17:15 +04:00
|
|
|
unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
|
|
|
|
|
2006-10-02 13:17:35 +04:00
|
|
|
INIT_HLIST_HEAD(&empty_rp);
|
2008-07-25 12:46:04 +04:00
|
|
|
kretprobe_hash_lock(current, &head, &flags);
|
2005-06-28 02:17:15 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* It is possible to have multiple instances associated with a given
|
|
|
|
* task either because an multiple functions in the call path
|
2008-10-16 21:02:37 +04:00
|
|
|
* have a return probe installed on them, and/or more than one return
|
2005-06-28 02:17:15 +04:00
|
|
|
* 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
|
2006-10-02 13:17:33 +04:00
|
|
|
* function, the first instance's ret_addr will point to the
|
2005-06-28 02:17:15 +04:00
|
|
|
* 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 05:06:00 +04:00
|
|
|
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
|
2006-10-02 13:17:33 +04:00
|
|
|
if (ri->task != current)
|
2005-06-28 02:17:15 +04:00
|
|
|
/* another task is sharing our hash bucket */
|
2006-10-02 13:17:33 +04:00
|
|
|
continue;
|
2005-06-28 02:17:15 +04:00
|
|
|
|
|
|
|
if (ri->rp && ri->rp->handler)
|
|
|
|
ri->rp->handler(ri, regs);
|
|
|
|
|
|
|
|
orig_ret_address = (unsigned long)ri->ret_addr;
|
2006-10-02 13:17:35 +04:00
|
|
|
recycle_rp_inst(ri, &empty_rp);
|
2005-06-28 02:17:15 +04:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2007-05-08 11:28:27 +04:00
|
|
|
kretprobe_assert(ri, orig_ret_address, trampoline_address);
|
2005-06-28 02:17:15 +04:00
|
|
|
regs->nip = orig_ret_address;
|
2017-02-08 12:50:52 +03:00
|
|
|
/*
|
|
|
|
* Make LR point to the orig_ret_address.
|
|
|
|
* When the 'nop' inside the kretprobe_trampoline
|
|
|
|
* is optimized, we can do a 'blr' after executing the
|
|
|
|
* detour buffer code.
|
|
|
|
*/
|
|
|
|
regs->link = orig_ret_address;
|
2005-06-28 02:17:15 +04:00
|
|
|
|
2005-11-07 12:00:10 +03:00
|
|
|
reset_current_kprobe();
|
2008-07-25 12:46:04 +04:00
|
|
|
kretprobe_hash_unlock(current, &flags);
|
2005-11-07 12:00:07 +03:00
|
|
|
preempt_enable_no_resched();
|
2005-06-28 02:17:15 +04:00
|
|
|
|
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 05:06:00 +04:00
|
|
|
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
|
2006-10-02 13:17:35 +04:00
|
|
|
hlist_del(&ri->hlist);
|
|
|
|
kfree(ri);
|
|
|
|
}
|
2006-10-02 13:17:33 +04:00
|
|
|
/*
|
|
|
|
* By returning a non-zero value, we are telling
|
|
|
|
* kprobe_handler() that we don't want the post_handler
|
|
|
|
* to run (and have re-enabled preemption)
|
|
|
|
*/
|
|
|
|
return 1;
|
2005-06-28 02:17:15 +04:00
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(trampoline_probe_handler);
|
2005-06-28 02:17:15 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* Called after single-stepping. p->addr is the address of the
|
|
|
|
* instruction whose first byte has been replaced by the "breakpoint"
|
|
|
|
* instruction. To avoid the SMP problems that can occur when we
|
|
|
|
* temporarily put back the original opcode to single-step, we
|
|
|
|
* single-stepped a copy of the instruction. The address of this
|
|
|
|
* copy is p->ainsn.insn.
|
|
|
|
*/
|
2017-04-12 14:18:51 +03:00
|
|
|
int kprobe_post_handler(struct pt_regs *regs)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2005-11-07 12:00:10 +03:00
|
|
|
struct kprobe *cur = kprobe_running();
|
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
|
|
|
|
2016-11-21 20:06:41 +03:00
|
|
|
if (!cur || user_mode(regs))
|
2005-04-17 02:20:36 +04:00
|
|
|
return 0;
|
|
|
|
|
2008-06-26 10:57:58 +04:00
|
|
|
/* make sure we got here for instruction we have a kprobe on */
|
|
|
|
if (((unsigned long)cur->ainsn.insn + 4) != regs->nip)
|
|
|
|
return 0;
|
|
|
|
|
2005-11-07 12:00:10 +03:00
|
|
|
if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
|
|
|
|
kcb->kprobe_status = KPROBE_HIT_SSDONE;
|
|
|
|
cur->post_handler(cur, regs, 0);
|
2005-06-23 11:09:38 +04:00
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2010-05-27 23:19:20 +04:00
|
|
|
/* Adjust nip to after the single-stepped instruction */
|
|
|
|
regs->nip = (unsigned long)cur->addr + 4;
|
2005-11-07 12:00:10 +03:00
|
|
|
regs->msr |= kcb->kprobe_saved_msr;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2005-06-23 11:09:38 +04:00
|
|
|
/*Restore back the original saved kprobes variables and continue. */
|
2005-11-07 12:00:10 +03:00
|
|
|
if (kcb->kprobe_status == KPROBE_REENTER) {
|
|
|
|
restore_previous_kprobe(kcb);
|
2005-06-23 11:09:38 +04:00
|
|
|
goto out;
|
|
|
|
}
|
2005-11-07 12:00:10 +03:00
|
|
|
reset_current_kprobe();
|
2005-06-23 11:09:38 +04:00
|
|
|
out:
|
2005-04-17 02:20:36 +04:00
|
|
|
preempt_enable_no_resched();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* if somebody else is singlestepping across a probe point, msr
|
2008-06-26 11:01:37 +04:00
|
|
|
* will have DE/SE set, in which case, continue the remaining processing
|
2005-04-17 02:20:36 +04:00
|
|
|
* of do_debug, as if this is not a probe hit.
|
|
|
|
*/
|
2008-06-26 11:01:37 +04:00
|
|
|
if (regs->msr & MSR_SINGLESTEP)
|
2005-04-17 02:20:36 +04:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(kprobe_post_handler);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2005-11-07 12:00:10 +03:00
|
|
|
struct kprobe *cur = kprobe_running();
|
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
2006-03-26 13:38:24 +04:00
|
|
|
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 and the nip points back to the probe address
|
|
|
|
* and allow the page fault handler to continue as a
|
|
|
|
* normal page fault.
|
|
|
|
*/
|
|
|
|
regs->nip = (unsigned long)cur->addr;
|
2008-06-26 11:01:37 +04:00
|
|
|
regs->msr &= ~MSR_SINGLESTEP; /* Turn off 'trace' bits */
|
2005-11-07 12:00:10 +03:00
|
|
|
regs->msr |= kcb->kprobe_saved_msr;
|
2006-03-26 13:38:24 +04:00
|
|
|
if (kcb->kprobe_status == KPROBE_REENTER)
|
|
|
|
restore_previous_kprobe(kcb);
|
|
|
|
else
|
|
|
|
reset_current_kprobe();
|
2005-04-17 02:20:36 +04:00
|
|
|
preempt_enable_no_resched();
|
2006-03-26 13:38:24 +04:00
|
|
|
break;
|
|
|
|
case KPROBE_HIT_ACTIVE:
|
|
|
|
case KPROBE_HIT_SSDONE:
|
|
|
|
/*
|
|
|
|
* We increment the nmissed count for accounting,
|
2013-09-20 07:55:41 +04:00
|
|
|
* we can also use npre/npostfault count for accounting
|
2006-03-26 13:38:24 +04:00
|
|
|
* 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->nip)) != NULL) {
|
2016-10-14 08:47:31 +03:00
|
|
|
regs->nip = extable_fixup(entry);
|
2006-03-26 13:38:24 +04:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* fixup_exception() could not handle it,
|
|
|
|
* Let do_page_fault() fix it.
|
|
|
|
*/
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
break;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(kprobe_fault_handler);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2007-07-19 12:48:11 +04:00
|
|
|
unsigned long arch_deref_entry_point(void *entry)
|
|
|
|
{
|
2014-06-23 07:23:31 +04:00
|
|
|
return ppc_global_function_entry(entry);
|
2007-07-19 12:48:11 +04:00
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(arch_deref_entry_point);
|
2007-07-19 12:48:11 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
struct jprobe *jp = container_of(p, struct jprobe, kp);
|
2005-11-07 12:00:10 +03:00
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2005-11-07 12:00:10 +03:00
|
|
|
memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
/* setup return addr to the jprobe handler routine */
|
2007-07-19 12:48:11 +04:00
|
|
|
regs->nip = arch_deref_entry_point(jp->entry);
|
2016-06-06 19:56:10 +03:00
|
|
|
#ifdef PPC64_ELF_ABI_v2
|
2014-06-23 07:23:31 +04:00
|
|
|
regs->gpr[12] = (unsigned long)jp->entry;
|
2016-06-06 19:56:10 +03:00
|
|
|
#elif defined(PPC64_ELF_ABI_v1)
|
2005-04-17 02:20:36 +04:00
|
|
|
regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
|
2007-02-07 07:55:19 +03:00
|
|
|
#endif
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-06-01 13:48:15 +03:00
|
|
|
/*
|
|
|
|
* jprobes use jprobe_return() which skips the normal return
|
|
|
|
* path of the function, and this messes up the accounting of the
|
|
|
|
* function graph tracer.
|
|
|
|
*
|
|
|
|
* Pause function graph tracing while performing the jprobe function.
|
|
|
|
*/
|
|
|
|
pause_graph_tracing();
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
return 1;
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(setjmp_pre_handler);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
void __used jprobe_return(void)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
asm volatile("trap" ::: "memory");
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(jprobe_return);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
static void __used jprobe_return_end(void)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2017-04-12 14:18:51 +03:00
|
|
|
}
|
|
|
|
NOKPROBE_SYMBOL(jprobe_return_end);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2005-11-07 12:00:10 +03:00
|
|
|
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* FIXME - we should ideally be validating that we got here 'cos
|
|
|
|
* of the "trap" in jprobe_return() above, before restoring the
|
|
|
|
* saved regs...
|
|
|
|
*/
|
2005-11-07 12:00:10 +03:00
|
|
|
memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
|
2017-06-01 13:48:15 +03:00
|
|
|
/* It's OK to start function graph tracing again */
|
|
|
|
unpause_graph_tracing();
|
2005-11-07 12:00:14 +03:00
|
|
|
preempt_enable_no_resched();
|
2005-04-17 02:20:36 +04:00
|
|
|
return 1;
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(longjmp_break_handler);
|
2005-06-28 02:17:15 +04:00
|
|
|
|
|
|
|
static struct kprobe trampoline_p = {
|
|
|
|
.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
|
|
|
|
.pre_handler = trampoline_probe_handler
|
|
|
|
};
|
|
|
|
|
2005-07-06 05:54:50 +04:00
|
|
|
int __init arch_init_kprobes(void)
|
2005-06-28 02:17:15 +04:00
|
|
|
{
|
|
|
|
return register_kprobe(&trampoline_p);
|
|
|
|
}
|
2007-05-08 11:34:16 +04:00
|
|
|
|
2017-04-12 14:18:51 +03:00
|
|
|
int arch_trampoline_kprobe(struct kprobe *p)
|
2007-05-08 11:34:16 +04:00
|
|
|
{
|
|
|
|
if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2017-04-12 14:18:51 +03:00
|
|
|
NOKPROBE_SYMBOL(arch_trampoline_kprobe);
|