1
0
Fork 0
alistair23-linux/arch/arm/probes/kprobes/core.c

558 lines
15 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* arch/arm/kernel/kprobes.c
*
* Kprobes on ARM
*
* Abhishek Sagar <sagar.abhishek@gmail.com>
* Copyright (C) 2006, 2007 Motorola Inc.
*
* Nicolas Pitre <nico@marvell.com>
* Copyright (C) 2007 Marvell Ltd.
*/
#include <linux/kernel.h>
#include <linux/kprobes.h>
#include <linux/module.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 02:04:11 -06:00
#include <linux/slab.h>
#include <linux/stop_machine.h>
#include <linux/sched/debug.h>
#include <linux/stringify.h>
#include <asm/traps.h>
#include <asm/opcodes.h>
#include <asm/cacheflush.h>
#include <linux/percpu.h>
#include <linux/bug.h>
#include <asm/patch.h>
#include <asm/sections.h>
#include "../decode-arm.h"
#include "../decode-thumb.h"
#include "core.h"
#define MIN_STACK_SIZE(addr) \
min((unsigned long)MAX_STACK_SIZE, \
(unsigned long)current_thread_info() + THREAD_START_SP - (addr))
#define flush_insns(addr, size) \
flush_icache_range((unsigned long)(addr), \
(unsigned long)(addr) + \
(size))
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
kprobe_opcode_t insn;
kprobe_opcode_t tmp_insn[MAX_INSN_SIZE];
unsigned long addr = (unsigned long)p->addr;
bool thumb;
kprobe_decode_insn_t *decode_insn;
const union decode_action *actions;
int is;
const struct decode_checker **checkers;
#ifdef CONFIG_THUMB2_KERNEL
thumb = true;
addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]);
if (is_wide_instruction(insn)) {
u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]);
insn = __opcode_thumb32_compose(insn, inst2);
decode_insn = thumb32_probes_decode_insn;
actions = kprobes_t32_actions;
checkers = kprobes_t32_checkers;
} else {
decode_insn = thumb16_probes_decode_insn;
actions = kprobes_t16_actions;
checkers = kprobes_t16_checkers;
}
#else /* !CONFIG_THUMB2_KERNEL */
thumb = false;
if (addr & 0x3)
return -EINVAL;
insn = __mem_to_opcode_arm(*p->addr);
decode_insn = arm_probes_decode_insn;
actions = kprobes_arm_actions;
checkers = kprobes_arm_checkers;
#endif
p->opcode = insn;
p->ainsn.insn = tmp_insn;
switch ((*decode_insn)(insn, &p->ainsn, true, actions, checkers)) {
case INSN_REJECTED: /* not supported */
return -EINVAL;
case INSN_GOOD: /* instruction uses slot */
p->ainsn.insn = get_insn_slot();
if (!p->ainsn.insn)
return -ENOMEM;
for (is = 0; is < MAX_INSN_SIZE; ++is)
p->ainsn.insn[is] = tmp_insn[is];
flush_insns(p->ainsn.insn,
sizeof(p->ainsn.insn[0]) * MAX_INSN_SIZE);
p->ainsn.insn_fn = (probes_insn_fn_t *)
((uintptr_t)p->ainsn.insn | thumb);
break;
case INSN_GOOD_NO_SLOT: /* instruction doesn't need insn slot */
p->ainsn.insn = NULL;
break;
}
/*
* Never instrument insn like 'str r0, [sp, +/-r1]'. Also, insn likes
* 'str r0, [sp, #-68]' should also be prohibited.
* See __und_svc.
*/
if ((p->ainsn.stack_space < 0) ||
(p->ainsn.stack_space > MAX_STACK_SIZE))
return -EINVAL;
return 0;
}
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
unsigned int brkp;
void *addr;
if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
/* Remove any Thumb flag */
addr = (void *)((uintptr_t)p->addr & ~1);
if (is_wide_instruction(p->opcode))
brkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION;
else
brkp = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION;
} else {
kprobe_opcode_t insn = p->opcode;
addr = p->addr;
brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION;
if (insn >= 0xe0000000)
brkp |= 0xe0000000; /* Unconditional instruction */
else
brkp |= insn & 0xf0000000; /* Copy condition from insn */
}
patch_text(addr, brkp);
}
/*
* The actual disarming is done here on each CPU and synchronized using
* stop_machine. This synchronization is necessary on SMP to avoid removing
* a probe between the moment the 'Undefined Instruction' exception is raised
* and the moment the exception handler reads the faulting instruction from
* memory. It is also needed to atomically set the two half-words of a 32-bit
* Thumb breakpoint.
*/
struct patch {
void *addr;
unsigned int insn;
};
static int __kprobes_remove_breakpoint(void *data)
{
struct patch *p = data;
__patch_text(p->addr, p->insn);
return 0;
}
void __kprobes kprobes_remove_breakpoint(void *addr, unsigned int insn)
{
struct patch p = {
.addr = addr,
.insn = insn,
};
stop_machine_cpuslocked(__kprobes_remove_breakpoint, &p,
cpu_online_mask);
}
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
kprobes_remove_breakpoint((void *)((uintptr_t)p->addr & ~1),
p->opcode);
}
void __kprobes arch_remove_kprobe(struct kprobe *p)
{
if (p->ainsn.insn) {
free_insn_slot(p->ainsn.insn, 0);
p->ainsn.insn = NULL;
}
}
static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
kcb->prev_kprobe.kp = kprobe_running();
kcb->prev_kprobe.status = kcb->kprobe_status;
}
static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
kcb->kprobe_status = kcb->prev_kprobe.status;
}
static void __kprobes set_current_kprobe(struct kprobe *p)
{
__this_cpu_write(current_kprobe, p);
}
static void __kprobes
singlestep_skip(struct kprobe *p, struct pt_regs *regs)
{
#ifdef CONFIG_THUMB2_KERNEL
regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
if (is_wide_instruction(p->opcode))
regs->ARM_pc += 4;
else
regs->ARM_pc += 2;
#else
regs->ARM_pc += 4;
#endif
}
static inline void __kprobes
singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
p->ainsn.insn_singlestep(p->opcode, &p->ainsn, regs);
}
/*
* Called with IRQs disabled. IRQs must remain disabled from that point
* all the way until processing this kprobe is complete. The current
* kprobes implementation cannot process more than one nested level of
* kprobe, and that level is reserved for user kprobe handlers, so we can't
* risk encountering a new kprobe in an interrupt handler.
*/
void __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p, *cur;
struct kprobe_ctlblk *kcb;
kcb = get_kprobe_ctlblk();
cur = kprobe_running();
#ifdef CONFIG_THUMB2_KERNEL
/*
* First look for a probe which was registered using an address with
* bit 0 set, this is the usual situation for pointers to Thumb code.
* If not found, fallback to looking for one with bit 0 clear.
*/
p = get_kprobe((kprobe_opcode_t *)(regs->ARM_pc | 1));
if (!p)
p = get_kprobe((kprobe_opcode_t *)regs->ARM_pc);
#else /* ! CONFIG_THUMB2_KERNEL */
p = get_kprobe((kprobe_opcode_t *)regs->ARM_pc);
#endif
if (p) {
if (!p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
/*
* Probe hit but conditional execution check failed,
* so just skip the instruction and continue as if
* nothing had happened.
* In this case, we can skip recursing check too.
*/
singlestep_skip(p, regs);
} else if (cur) {
/* Kprobe is pending, so we're recursing. */
switch (kcb->kprobe_status) {
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
case KPROBE_HIT_SS:
/* A pre- or post-handler probe got us here. */
kprobes_inc_nmissed_count(p);
save_previous_kprobe(kcb);
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_REENTER;
singlestep(p, regs, kcb);
restore_previous_kprobe(kcb);
break;
case KPROBE_REENTER:
/* A nested probe was hit in FIQ, it is a BUG */
pr_warn("Unrecoverable kprobe detected.\n");
dump_kprobe(p);
/* fall through */
default:
/* impossible cases */
BUG();
}
} else {
/* Probe hit and conditional execution check ok. */
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
/*
* If we have no pre-handler or it returned 0, we
bpf/error-inject/kprobes: Clear current_kprobe and enable preempt in kprobe Clear current_kprobe and enable preemption in kprobe even if pre_handler returns !0. This simplifies function override using kprobes. Jprobe used to require to keep the preemption disabled and keep current_kprobe until it returned to original function entry. For this reason kprobe_int3_handler() and similar arch dependent kprobe handers checks pre_handler result and exit without enabling preemption if the result is !0. After removing the jprobe, Kprobes does not need to keep preempt disabled even if user handler returns !0 anymore. But since the function override handler in error-inject and bpf is also returns !0 if it overrides a function, to balancing the preempt count, it enables preemption and reset current kprobe by itself. That is a bad design that is very buggy. This fixes such unbalanced preempt-count and current_kprobes setting in kprobes, bpf and error-inject. Note: for powerpc and x86, this removes all preempt_disable from kprobe_ftrace_handler because ftrace callbacks are called under preempt disabled. Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David S. Miller <davem@davemloft.net> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: James Hogan <jhogan@kernel.org> Cc: Josef Bacik <jbacik@fb.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: linux-arch@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Link: https://lore.kernel.org/lkml/152942494574.15209.12323837825873032258.stgit@devbox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-06-19 10:15:45 -06:00
* continue with normal processing. If we have a
* pre-handler and it returned non-zero, it will
* modify the execution path and no need to single
* stepping. Let's just reset current kprobe and exit.
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
kcb->kprobe_status = KPROBE_HIT_SS;
singlestep(p, regs, kcb);
if (p->post_handler) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
p->post_handler(p, regs, 0);
}
}
bpf/error-inject/kprobes: Clear current_kprobe and enable preempt in kprobe Clear current_kprobe and enable preemption in kprobe even if pre_handler returns !0. This simplifies function override using kprobes. Jprobe used to require to keep the preemption disabled and keep current_kprobe until it returned to original function entry. For this reason kprobe_int3_handler() and similar arch dependent kprobe handers checks pre_handler result and exit without enabling preemption if the result is !0. After removing the jprobe, Kprobes does not need to keep preempt disabled even if user handler returns !0 anymore. But since the function override handler in error-inject and bpf is also returns !0 if it overrides a function, to balancing the preempt count, it enables preemption and reset current kprobe by itself. That is a bad design that is very buggy. This fixes such unbalanced preempt-count and current_kprobes setting in kprobes, bpf and error-inject. Note: for powerpc and x86, this removes all preempt_disable from kprobe_ftrace_handler because ftrace callbacks are called under preempt disabled. Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David S. Miller <davem@davemloft.net> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: James Hogan <jhogan@kernel.org> Cc: Josef Bacik <jbacik@fb.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: linux-arch@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Link: https://lore.kernel.org/lkml/152942494574.15209.12323837825873032258.stgit@devbox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-06-19 10:15:45 -06:00
reset_current_kprobe();
}
} else {
/*
* The probe was removed and a race is in progress.
* There is nothing we can do about it. Let's restart
* the instruction. By the time we can restart, the
* real instruction will be there.
*/
}
}
static int __kprobes kprobe_trap_handler(struct pt_regs *regs, unsigned int instr)
{
unsigned long flags;
local_irq_save(flags);
kprobe_handler(regs);
local_irq_restore(flags);
return 0;
}
int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
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 PC to point back to the probe address
* and allow the page fault handler to continue as a
* normal page fault.
*/
regs->ARM_pc = (long)cur->addr;
if (kcb->kprobe_status == KPROBE_REENTER) {
restore_previous_kprobe(kcb);
} else {
reset_current_kprobe();
}
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.
*/
if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
return 1;
break;
default:
break;
}
return 0;
}
int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
/*
* notify_die() is currently never called on ARM,
* so this callback is currently empty.
*/
return NOTIFY_DONE;
}
/*
* When a retprobed function returns, trampoline_handler() is called,
* calling the kretprobe's handler. We construct a struct pt_regs to
* give a view of registers r0-r11 to the user return-handler. This is
* not a complete pt_regs structure, but that should be plenty sufficient
* for kretprobe handlers which should normally be interested in r0 only
* anyway.
*/
void __naked __kprobes kretprobe_trampoline(void)
{
__asm__ __volatile__ (
"stmdb sp!, {r0 - r11} \n\t"
"mov r0, sp \n\t"
"bl trampoline_handler \n\t"
"mov lr, r0 \n\t"
"ldmia sp!, {r0 - r11} \n\t"
#ifdef CONFIG_THUMB2_KERNEL
"bx lr \n\t"
#else
"mov pc, lr \n\t"
#endif
: : : "memory");
}
/* Called from kretprobe_trampoline */
static __used __kprobes void *trampoline_handler(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>
2013-02-27 18:06:00 -07:00
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
kprobe_opcode_t *correct_ret_addr = NULL;
INIT_HLIST_HEAD(&empty_rp);
kprobes: improve kretprobe scalability with hashed locking Currently list of kretprobe instances are stored in kretprobe object (as used_instances,free_instances) and in kretprobe hash table. We have one global kretprobe lock to serialise the access to these lists. This causes only one kretprobe handler to execute at a time. Hence affects system performance, particularly on SMP systems and when return probe is set on lot of functions (like on all systemcalls). Solution proposed here gives fine-grain locks that performs better on SMP system compared to present kretprobe implementation. Solution: 1) Instead of having one global lock to protect kretprobe instances present in kretprobe object and kretprobe hash table. We will have two locks, one lock for protecting kretprobe hash table and another lock for kretporbe object. 2) We hold lock present in kretprobe object while we modify kretprobe instance in kretprobe object and we hold per-hash-list lock while modifying kretprobe instances present in that hash list. To prevent deadlock, we never grab a per-hash-list lock while holding a kretprobe lock. 3) We can remove used_instances from struct kretprobe, as we can track used instances of kretprobe instances using kretprobe hash table. Time duration for kernel compilation ("make -j 8") on a 8-way ppc64 system with return probes set on all systemcalls looks like this. cacheline non-cacheline Un-patched kernel aligned patch aligned patch =============================================================================== real 9m46.784s 9m54.412s 10m2.450s user 40m5.715s 40m7.142s 40m4.273s sys 2m57.754s 2m58.583s 3m17.430s =========================================================== Time duration for kernel compilation ("make -j 8) on the same system, when kernel is not probed. ========================= real 9m26.389s user 40m8.775s sys 2m7.283s ========================= Signed-off-by: Srinivasa DS <srinivasa@in.ibm.com> Signed-off-by: Jim Keniston <jkenisto@us.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Masami Hiramatsu <mhiramat@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 02:46:04 -06:00
kretprobe_hash_lock(current, &head, &flags);
/*
* It is possible to have multiple instances associated with a given
* task either because multiple functions in the call path have
* a return probe installed on them, and/or more than one 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>
2013-02-27 18:06:00 -07:00
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
orig_ret_address = (unsigned long)ri->ret_addr;
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);
correct_ret_addr = ri->ret_addr;
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
__this_cpu_write(current_kprobe, NULL);
}
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;
}
kprobes: improve kretprobe scalability with hashed locking Currently list of kretprobe instances are stored in kretprobe object (as used_instances,free_instances) and in kretprobe hash table. We have one global kretprobe lock to serialise the access to these lists. This causes only one kretprobe handler to execute at a time. Hence affects system performance, particularly on SMP systems and when return probe is set on lot of functions (like on all systemcalls). Solution proposed here gives fine-grain locks that performs better on SMP system compared to present kretprobe implementation. Solution: 1) Instead of having one global lock to protect kretprobe instances present in kretprobe object and kretprobe hash table. We will have two locks, one lock for protecting kretprobe hash table and another lock for kretporbe object. 2) We hold lock present in kretprobe object while we modify kretprobe instance in kretprobe object and we hold per-hash-list lock while modifying kretprobe instances present in that hash list. To prevent deadlock, we never grab a per-hash-list lock while holding a kretprobe lock. 3) We can remove used_instances from struct kretprobe, as we can track used instances of kretprobe instances using kretprobe hash table. Time duration for kernel compilation ("make -j 8") on a 8-way ppc64 system with return probes set on all systemcalls looks like this. cacheline non-cacheline Un-patched kernel aligned patch aligned patch =============================================================================== real 9m46.784s 9m54.412s 10m2.450s user 40m5.715s 40m7.142s 40m4.273s sys 2m57.754s 2m58.583s 3m17.430s =========================================================== Time duration for kernel compilation ("make -j 8) on the same system, when kernel is not probed. ========================= real 9m26.389s user 40m8.775s sys 2m7.283s ========================= Signed-off-by: Srinivasa DS <srinivasa@in.ibm.com> Signed-off-by: Jim Keniston <jkenisto@us.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Masami Hiramatsu <mhiramat@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 02:46:04 -06:00
kretprobe_hash_unlock(current, &flags);
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>
2013-02-27 18:06:00 -07:00
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
}
return (void *)orig_ret_address;
}
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *)regs->ARM_lr;
/* Replace the return addr with trampoline addr. */
regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
return 0;
}
#ifdef CONFIG_THUMB2_KERNEL
static struct undef_hook kprobes_thumb16_break_hook = {
.instr_mask = 0xffff,
.instr_val = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION,
.cpsr_mask = MODE_MASK,
.cpsr_val = SVC_MODE,
.fn = kprobe_trap_handler,
};
static struct undef_hook kprobes_thumb32_break_hook = {
.instr_mask = 0xffffffff,
.instr_val = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION,
.cpsr_mask = MODE_MASK,
.cpsr_val = SVC_MODE,
.fn = kprobe_trap_handler,
};
#else /* !CONFIG_THUMB2_KERNEL */
static struct undef_hook kprobes_arm_break_hook = {
.instr_mask = 0x0fffffff,
.instr_val = KPROBE_ARM_BREAKPOINT_INSTRUCTION,
.cpsr_mask = MODE_MASK,
.cpsr_val = SVC_MODE,
.fn = kprobe_trap_handler,
};
#endif /* !CONFIG_THUMB2_KERNEL */
int __init arch_init_kprobes()
{
arm_probes_decode_init();
#ifdef CONFIG_THUMB2_KERNEL
register_undef_hook(&kprobes_thumb16_break_hook);
register_undef_hook(&kprobes_thumb32_break_hook);
#else
register_undef_hook(&kprobes_arm_break_hook);
#endif
return 0;
}
bool arch_within_kprobe_blacklist(unsigned long addr)
{
void *a = (void *)addr;
return __in_irqentry_text(addr) ||
in_entry_text(addr) ||
in_idmap_text(addr) ||
memory_contains(__kprobes_text_start, __kprobes_text_end, a, 1);
}