kernel_optimize_test/arch/mips/kernel/kprobes.c

567 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel Probes (KProbes)
* arch/mips/kernel/kprobes.c
*
* Copyright 2006 Sony Corp.
* Copyright 2010 Cavium Networks
*
* Some portions copied from the powerpc version.
*
* Copyright (C) IBM Corporation, 2002, 2004
*/
#include <linux/kprobes.h>
#include <linux/preempt.h>
MIPS Kprobes: Fix OOPS in arch_prepare_kprobe() This patch fixes the arch_prepare_kprobe() on MIPS when it tries to find the instruction at the previous address to the probed address. The oops happens when the probed address is the first address in a kernel module and there is no previous address. The patch uses probe_kernel_read() to safely read the previous instruction. CPU 3 Unable to handle kernel paging request at virtual address ffffffffc0211ffc, epc == ffffffff81113204, ra == ffffffff8111511c Oops[#1]: Cpu 3 $ 0 : 0000000000000000 0000000000000001 ffffffffc0212000 0000000000000000 $ 4 : ffffffffc0220030 0000000000000000 0000000000000adf ffffffff81a3f898 $ 8 : ffffffffc0220030 ffffffffffffffff 000000000000ffff 0000000000004821 $12 : 000000000000000a ffffffff81105ddc ffffffff812927d0 0000000000000000 $16 : ffffffff81a40000 ffffffffc0220030 ffffffffc0220030 ffffffffc0212660 $20 : 0000000000000000 0000000000000008 efffffffffffffff ffffffffc0220000 $24 : 0000000000000002 ffffffff8139f5b0 $28 : a800000072adc000 a800000072adfca0 ffffffffc0220000 ffffffff8111511c Hi : 0000000000000000 Lo : 0000000000000000 epc : ffffffff81113204 arch_prepare_kprobe+0x1c/0xe8 Tainted: P ra : ffffffff8111511c register_kprobe+0x33c/0x730 Status: 10008ce3 KX SX UX KERNEL EXL IE Cause : 00800008 BadVA : ffffffffc0211ffc PrId : 000d9008 (Cavium Octeon II) Modules linked in: bpa_mem crashinfo pds tun cpumem ipv6 exportfs nfsd OOBnd(P) OOBhal(P) cvmx_mdio cvmx_gpio aipcmod(P) mtsmod procfs(P) utaker_mod dplr_pci hello atomicm_foo [last unloaded: sysmgr_hb] Process stapio (pid: 5603, threadinfo=a800000072adc000, task=a8000000722e0438, tls=000000002b4bcda0) Stack : ffffffff81a40000 ffffffff81a40000 ffffffffc0220030 ffffffff8111511c ffffffffc0218008 0000000000000001 ffffffffc0218008 0000000000000001 ffffffffc0220000 ffffffffc021efe8 1000000000000000 0000000000000008 efffffffffffffff ffffffffc0220000 ffffffffc0220000 ffffffffc021d500 0000000000000022 0000000000000002 1111000072be02b8 0000000000000000 00000000000015e6 00000000000015e6 00000000007d0f00 a800000072be02b8 0000000000000000 ffffffff811d16c8 a80000000382e3b0 ffffffff811d5ba0 ffffffff81b0a270 ffffffff81b0a270 ffffffffc0212000 0000000000000013 ffffffffc0220030 ffffffffc021ed00 a800000089114c80 000000007f90d590 a800000072adfe38 a800000089114c80 0000000010020000 0000000010020000 ... Call Trace: [<ffffffff81113204>] arch_prepare_kprobe+0x1c/0xe8 [<ffffffff8111511c>] register_kprobe+0x33c/0x730 [<ffffffffc021d500>] _stp_ctl_write_cmd+0x8e8/0xa88 [atomicm_foo] [<ffffffff812925cc>] vfs_write+0xb4/0x178 [<ffffffff81292828>] SyS_write+0x58/0x148 [<ffffffff81103844>] handle_sysn32+0x44/0x84 Code: ffb20010 ffb00000 dc820028 <8c44fffc> 8c500000 0c4449e0 0004203c 14400029 3c048199 Signed-off-by: Maneesh Soni <manesoni@cisco.com> Signed-off-by: Victor Kamensky <kamensky@cisco.com> Cc: David Daney <david.daney@cavium.com> Cc: ananth@in.ibm.com Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/2915/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2011-11-08 19:34:54 +08:00
#include <linux/uaccess.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
#include <asm/ptrace.h>
#include <asm/branch.h>
#include <asm/break.h>
#include "probes-common.h"
static const union mips_instruction breakpoint_insn = {
.b_format = {
.opcode = spec_op,
.code = BRK_KPROBE_BP,
.func = break_op
}
};
static const union mips_instruction breakpoint2_insn = {
.b_format = {
.opcode = spec_op,
.code = BRK_KPROBE_SSTEPBP,
.func = break_op
}
};
DEFINE_PER_CPU(struct kprobe *, current_kprobe);
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
static int __kprobes insn_has_delayslot(union mips_instruction insn)
{
return __insn_has_delay_slot(insn);
}
/*
* insn_has_ll_or_sc function checks whether instruction is ll or sc
* one; putting breakpoint on top of atomic ll/sc pair is bad idea;
* so we need to prevent it and refuse kprobes insertion for such
* instructions; cannot do much about breakpoint in the middle of
* ll/sc pair; it is upto user to avoid those places
*/
static int __kprobes insn_has_ll_or_sc(union mips_instruction insn)
{
int ret = 0;
switch (insn.i_format.opcode) {
case ll_op:
case lld_op:
case sc_op:
case scd_op:
ret = 1;
break;
default:
break;
}
return ret;
}
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
union mips_instruction insn;
union mips_instruction prev_insn;
int ret = 0;
insn = p->addr[0];
if (insn_has_ll_or_sc(insn)) {
pr_notice("Kprobes for ll and sc instructions are not"
"supported\n");
ret = -EINVAL;
goto out;
}
MIPS Kprobes: Fix OOPS in arch_prepare_kprobe() This patch fixes the arch_prepare_kprobe() on MIPS when it tries to find the instruction at the previous address to the probed address. The oops happens when the probed address is the first address in a kernel module and there is no previous address. The patch uses probe_kernel_read() to safely read the previous instruction. CPU 3 Unable to handle kernel paging request at virtual address ffffffffc0211ffc, epc == ffffffff81113204, ra == ffffffff8111511c Oops[#1]: Cpu 3 $ 0 : 0000000000000000 0000000000000001 ffffffffc0212000 0000000000000000 $ 4 : ffffffffc0220030 0000000000000000 0000000000000adf ffffffff81a3f898 $ 8 : ffffffffc0220030 ffffffffffffffff 000000000000ffff 0000000000004821 $12 : 000000000000000a ffffffff81105ddc ffffffff812927d0 0000000000000000 $16 : ffffffff81a40000 ffffffffc0220030 ffffffffc0220030 ffffffffc0212660 $20 : 0000000000000000 0000000000000008 efffffffffffffff ffffffffc0220000 $24 : 0000000000000002 ffffffff8139f5b0 $28 : a800000072adc000 a800000072adfca0 ffffffffc0220000 ffffffff8111511c Hi : 0000000000000000 Lo : 0000000000000000 epc : ffffffff81113204 arch_prepare_kprobe+0x1c/0xe8 Tainted: P ra : ffffffff8111511c register_kprobe+0x33c/0x730 Status: 10008ce3 KX SX UX KERNEL EXL IE Cause : 00800008 BadVA : ffffffffc0211ffc PrId : 000d9008 (Cavium Octeon II) Modules linked in: bpa_mem crashinfo pds tun cpumem ipv6 exportfs nfsd OOBnd(P) OOBhal(P) cvmx_mdio cvmx_gpio aipcmod(P) mtsmod procfs(P) utaker_mod dplr_pci hello atomicm_foo [last unloaded: sysmgr_hb] Process stapio (pid: 5603, threadinfo=a800000072adc000, task=a8000000722e0438, tls=000000002b4bcda0) Stack : ffffffff81a40000 ffffffff81a40000 ffffffffc0220030 ffffffff8111511c ffffffffc0218008 0000000000000001 ffffffffc0218008 0000000000000001 ffffffffc0220000 ffffffffc021efe8 1000000000000000 0000000000000008 efffffffffffffff ffffffffc0220000 ffffffffc0220000 ffffffffc021d500 0000000000000022 0000000000000002 1111000072be02b8 0000000000000000 00000000000015e6 00000000000015e6 00000000007d0f00 a800000072be02b8 0000000000000000 ffffffff811d16c8 a80000000382e3b0 ffffffff811d5ba0 ffffffff81b0a270 ffffffff81b0a270 ffffffffc0212000 0000000000000013 ffffffffc0220030 ffffffffc021ed00 a800000089114c80 000000007f90d590 a800000072adfe38 a800000089114c80 0000000010020000 0000000010020000 ... Call Trace: [<ffffffff81113204>] arch_prepare_kprobe+0x1c/0xe8 [<ffffffff8111511c>] register_kprobe+0x33c/0x730 [<ffffffffc021d500>] _stp_ctl_write_cmd+0x8e8/0xa88 [atomicm_foo] [<ffffffff812925cc>] vfs_write+0xb4/0x178 [<ffffffff81292828>] SyS_write+0x58/0x148 [<ffffffff81103844>] handle_sysn32+0x44/0x84 Code: ffb20010 ffb00000 dc820028 <8c44fffc> 8c500000 0c4449e0 0004203c 14400029 3c048199 Signed-off-by: Maneesh Soni <manesoni@cisco.com> Signed-off-by: Victor Kamensky <kamensky@cisco.com> Cc: David Daney <david.daney@cavium.com> Cc: ananth@in.ibm.com Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/2915/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2011-11-08 19:34:54 +08:00
if ((probe_kernel_read(&prev_insn, p->addr - 1,
sizeof(mips_instruction)) == 0) &&
insn_has_delayslot(prev_insn)) {
pr_notice("Kprobes for branch delayslot are not supported\n");
ret = -EINVAL;
goto out;
}
if (__insn_is_compact_branch(insn)) {
pr_notice("Kprobes for compact branches are not supported\n");
ret = -EINVAL;
goto out;
}
/* insn: must be on special executable page on mips. */
p->ainsn.insn = get_insn_slot();
if (!p->ainsn.insn) {
ret = -ENOMEM;
goto out;
}
/*
* In the kprobe->ainsn.insn[] array we store the original
* instruction at index zero and a break trap instruction at
* index one.
*
* On MIPS arch if the instruction at probed address is a
* branch instruction, we need to execute the instruction at
* Branch Delayslot (BD) at the time of probe hit. As MIPS also
* doesn't have single stepping support, the BD instruction can
* not be executed in-line and it would be executed on SSOL slot
* using a normal breakpoint instruction in the next slot.
* So, read the instruction and save it for later execution.
*/
if (insn_has_delayslot(insn))
memcpy(&p->ainsn.insn[0], p->addr + 1, sizeof(kprobe_opcode_t));
else
memcpy(&p->ainsn.insn[0], p->addr, sizeof(kprobe_opcode_t));
p->ainsn.insn[1] = breakpoint2_insn;
p->opcode = *p->addr;
out:
return ret;
}
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
*p->addr = breakpoint_insn;
flush_insn_slot(p);
}
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
*p->addr = p->opcode;
flush_insn_slot(p);
}
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 save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
kcb->prev_kprobe.kp = kprobe_running();
kcb->prev_kprobe.status = kcb->kprobe_status;
kcb->prev_kprobe.old_SR = kcb->kprobe_old_SR;
kcb->prev_kprobe.saved_SR = kcb->kprobe_saved_SR;
kcb->prev_kprobe.saved_epc = kcb->kprobe_saved_epc;
}
static void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
mips: Replace __get_cpu_var uses __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:44 +08:00
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
kcb->kprobe_status = kcb->prev_kprobe.status;
kcb->kprobe_old_SR = kcb->prev_kprobe.old_SR;
kcb->kprobe_saved_SR = kcb->prev_kprobe.saved_SR;
kcb->kprobe_saved_epc = kcb->prev_kprobe.saved_epc;
}
static void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
mips: Replace __get_cpu_var uses __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:44 +08:00
__this_cpu_write(current_kprobe, p);
kcb->kprobe_saved_SR = kcb->kprobe_old_SR = (regs->cp0_status & ST0_IE);
kcb->kprobe_saved_epc = regs->cp0_epc;
}
/**
* evaluate_branch_instrucion -
*
* Evaluate the branch instruction at probed address during probe hit. The
* result of evaluation would be the updated epc. The insturction in delayslot
* would actually be single stepped using a normal breakpoint) on SSOL slot.
*
* The result is also saved in the kprobe control block for later use,
* in case we need to execute the delayslot instruction. The latter will be
* false for NOP instruction in dealyslot and the branch-likely instructions
* when the branch is taken. And for those cases we set a flag as
* SKIP_DELAYSLOT in the kprobe control block
*/
static int evaluate_branch_instruction(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
union mips_instruction insn = p->opcode;
long epc;
int ret = 0;
epc = regs->cp0_epc;
if (epc & 3)
goto unaligned;
if (p->ainsn.insn->word == 0)
kcb->flags |= SKIP_DELAYSLOT;
else
kcb->flags &= ~SKIP_DELAYSLOT;
ret = __compute_return_epc_for_insn(regs, insn);
if (ret < 0)
return ret;
if (ret == BRANCH_LIKELY_TAKEN)
kcb->flags |= SKIP_DELAYSLOT;
kcb->target_epc = regs->cp0_epc;
return 0;
unaligned:
pr_notice("%s: unaligned epc - sending SIGBUS.\n", current->comm);
force_sig(SIGBUS);
return -EFAULT;
}
static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
int ret = 0;
regs->cp0_status &= ~ST0_IE;
/* single step inline if the instruction is a break */
if (p->opcode.word == breakpoint_insn.word ||
p->opcode.word == breakpoint2_insn.word)
regs->cp0_epc = (unsigned long)p->addr;
else if (insn_has_delayslot(p->opcode)) {
ret = evaluate_branch_instruction(p, regs, kcb);
if (ret < 0) {
pr_notice("Kprobes: Error in evaluating branch\n");
return;
}
}
regs->cp0_epc = (unsigned long)&p->ainsn.insn[0];
}
/*
* Called after single-stepping. p->addr is the address of the
* instruction whose first byte has been replaced by the "break 0"
* 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.
*
* This function prepares to return from the post-single-step
* breakpoint trap. In case of branch instructions, the target
* epc to be restored.
*/
static void __kprobes resume_execution(struct kprobe *p,
struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
if (insn_has_delayslot(p->opcode))
regs->cp0_epc = kcb->target_epc;
else {
unsigned long orig_epc = kcb->kprobe_saved_epc;
regs->cp0_epc = orig_epc + 4;
}
}
static int __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p;
int ret = 0;
kprobe_opcode_t *addr;
struct kprobe_ctlblk *kcb;
addr = (kprobe_opcode_t *) regs->cp0_epc;
/*
* We don't want to be preempted for the entire
* duration of kprobe processing
*/
preempt_disable();
kcb = get_kprobe_ctlblk();
/* Check we're not actually recursing */
if (kprobe_running()) {
p = get_kprobe(addr);
if (p) {
if (kcb->kprobe_status == KPROBE_HIT_SS &&
p->ainsn.insn->word == breakpoint_insn.word) {
regs->cp0_status &= ~ST0_IE;
regs->cp0_status |= kcb->kprobe_saved_SR;
goto no_kprobe;
}
/*
* We have reentered the kprobe_handler(), since
* another probe was hit while within the handler.
* We here save the original kprobes variables and
* just single step on the instruction of the new probe
* without calling any user handlers.
*/
save_previous_kprobe(kcb);
set_current_kprobe(p, regs, kcb);
kprobes_inc_nmissed_count(p);
prepare_singlestep(p, regs, kcb);
kcb->kprobe_status = KPROBE_REENTER;
if (kcb->flags & SKIP_DELAYSLOT) {
resume_execution(p, regs, kcb);
restore_previous_kprobe(kcb);
preempt_enable_no_resched();
}
return 1;
} else if (addr->word != breakpoint_insn.word) {
/*
* 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;
}
p = get_kprobe(addr);
if (!p) {
if (addr->word != breakpoint_insn.word) {
/*
* 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;
}
set_current_kprobe(p, regs, kcb);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (p->pre_handler && p->pre_handler(p, regs)) {
/* handler has already set things up, so skip ss setup */
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>
2018-06-20 00:15:45 +08:00
reset_current_kprobe();
preempt_enable_no_resched();
return 1;
}
prepare_singlestep(p, regs, kcb);
if (kcb->flags & SKIP_DELAYSLOT) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
if (p->post_handler)
p->post_handler(p, regs, 0);
resume_execution(p, regs, kcb);
preempt_enable_no_resched();
} else
kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
no_kprobe:
preempt_enable_no_resched();
return ret;
}
static inline int post_kprobe_handler(struct pt_regs *regs)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (!cur)
return 0;
if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
cur->post_handler(cur, regs, 0);
}
resume_execution(cur, regs, kcb);
regs->cp0_status |= kcb->kprobe_saved_SR;
/* Restore back the original saved kprobes variables and continue. */
if (kcb->kprobe_status == KPROBE_REENTER) {
restore_previous_kprobe(kcb);
goto out;
}
reset_current_kprobe();
out:
preempt_enable_no_resched();
return 1;
}
mm, kprobes: generalize and rename notify_page_fault() as kprobe_page_fault() Architectures which support kprobes have very similar boilerplate around calling kprobe_fault_handler(). Use a helper function in kprobes.h to unify them, based on the x86 code. This changes the behaviour for other architectures when preemption is enabled. Previously, they would have disabled preemption while calling the kprobe handler. However, preemption would be disabled if this fault was due to a kprobe, so we know the fault was not due to a kprobe handler and can simply return failure. This behaviour was introduced in commit a980c0ef9f6d ("x86/kprobes: Refactor kprobes_fault() like kprobe_exceptions_notify()") [anshuman.khandual@arm.com: export kprobe_fault_handler()] Link: http://lkml.kernel.org/r/1561133358-8876-1-git-send-email-anshuman.khandual@arm.com Link: http://lkml.kernel.org/r/1560420444-25737-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: James Hogan <jhogan@kernel.org> Cc: Paul Burton <paul.burton@mips.com> Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-17 07:28:00 +08:00
int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
if (kcb->kprobe_status & KPROBE_HIT_SS) {
resume_execution(cur, regs, kcb);
regs->cp0_status |= kcb->kprobe_old_SR;
reset_current_kprobe();
preempt_enable_no_resched();
}
return 0;
}
/*
* Wrapper routine for handling exceptions.
*/
int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = (struct die_args *)data;
int ret = NOTIFY_DONE;
switch (val) {
case DIE_BREAK:
if (kprobe_handler(args->regs))
ret = NOTIFY_STOP;
break;
case DIE_SSTEPBP:
if (post_kprobe_handler(args->regs))
ret = NOTIFY_STOP;
break;
case DIE_PAGE_FAULT:
/* kprobe_running() needs smp_processor_id() */
preempt_disable();
if (kprobe_running()
&& kprobe_fault_handler(args->regs, args->trapnr))
ret = NOTIFY_STOP;
preempt_enable();
break;
default:
break;
}
return ret;
}
/*
* Function return probe trampoline:
* - init_kprobes() establishes a probepoint here
* - When the probed function returns, this probe causes the
* handlers to fire
*/
static void __used kretprobe_trampoline_holder(void)
{
asm volatile(
".set push\n\t"
/* Keep the assembler from reordering and placing JR here. */
".set noreorder\n\t"
"nop\n\t"
".global kretprobe_trampoline\n"
"kretprobe_trampoline:\n\t"
"nop\n\t"
".set pop"
: : : "memory");
}
void kretprobe_trampoline(void);
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *) regs->regs[31];
/* Replace the return addr with trampoline addr */
regs->regs[31] = (unsigned long)kretprobe_trampoline;
}
/*
* Called when the probe at kretprobe trampoline is hit
*/
static int __kprobes trampoline_probe_handler(struct kprobe *p,
struct pt_regs *regs)
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)kretprobe_trampoline;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/*
* It is possible to have multiple instances associated with a given
* task either because an multiple functions in the call path
* have a return probe installed on them, and/or more than one return
* return probe was registered for a target function.
*
* We can handle this because:
* - instances are always inserted at the head of the list
* - when multiple return probes are registered for the same
* function, the first instance's ret_addr will point to the
* real return address, and all the rest will point to
* kretprobe_trampoline
*/
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
if (ri->rp && ri->rp->handler)
ri->rp->handler(ri, regs);
orig_ret_address = (unsigned long)ri->ret_addr;
recycle_rp_inst(ri, &empty_rp);
if (orig_ret_address != trampoline_address)
/*
* This is the real return address. Any other
* instances associated with this task are for
* other calls deeper on the call stack
*/
break;
}
kretprobe_assert(ri, orig_ret_address, trampoline_address);
instruction_pointer(regs) = orig_ret_address;
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>
2013-02-28 09:06:00 +08:00
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
}
/*
* 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;
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
if (p->addr == (kprobe_opcode_t *)kretprobe_trampoline)
return 1;
return 0;
}
static struct kprobe trampoline_p = {
.addr = (kprobe_opcode_t *)kretprobe_trampoline,
.pre_handler = trampoline_probe_handler
};
int __init arch_init_kprobes(void)
{
return register_kprobe(&trampoline_p);
}