linux_dsm_epyc7002/arch/arc/kernel/kprobes.c

481 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*/
#include <linux/types.h>
#include <linux/kprobes.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/kdebug.h>
#include <linux/sched.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/current.h>
#include <asm/disasm.h>
#define MIN_STACK_SIZE(addr) min((unsigned long)MAX_STACK_SIZE, \
(unsigned long)current_thread_info() + THREAD_SIZE - (addr))
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
/* Attempt to probe at unaligned address */
if ((unsigned long)p->addr & 0x01)
return -EINVAL;
/* Address should not be in exception handling code */
p->ainsn.is_short = is_short_instr((unsigned long)p->addr);
p->opcode = *p->addr;
return 0;
}
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
*p->addr = UNIMP_S_INSTRUCTION;
flush_icache_range((unsigned long)p->addr,
(unsigned long)p->addr + sizeof(kprobe_opcode_t));
}
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
*p->addr = p->opcode;
flush_icache_range((unsigned long)p->addr,
(unsigned long)p->addr + sizeof(kprobe_opcode_t));
}
void __kprobes arch_remove_kprobe(struct kprobe *p)
{
arch_disarm_kprobe(p);
/* Can we remove the kprobe in the middle of kprobe handling? */
if (p->ainsn.t1_addr) {
*(p->ainsn.t1_addr) = p->ainsn.t1_opcode;
flush_icache_range((unsigned long)p->ainsn.t1_addr,
(unsigned long)p->ainsn.t1_addr +
sizeof(kprobe_opcode_t));
p->ainsn.t1_addr = NULL;
}
if (p->ainsn.t2_addr) {
*(p->ainsn.t2_addr) = p->ainsn.t2_opcode;
flush_icache_range((unsigned long)p->ainsn.t2_addr,
(unsigned long)p->ainsn.t2_addr +
sizeof(kprobe_opcode_t));
p->ainsn.t2_addr = 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)
{
arc: 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 calcualtions are avoided and less registers are used when code is generated. At the end of the patchset all uses of __get_cpu_var have been removed so the macro is removed too. The patchset 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, u); 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(this_cpu_ptr(&x), 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) Acked-by: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Christoph Lameter <cl@linux.com>
2013-08-29 02:48:15 +07:00
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
kcb->kprobe_status = kcb->prev_kprobe.status;
}
static inline void __kprobes set_current_kprobe(struct kprobe *p)
{
arc: 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 calcualtions are avoided and less registers are used when code is generated. At the end of the patchset all uses of __get_cpu_var have been removed so the macro is removed too. The patchset 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, u); 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(this_cpu_ptr(&x), 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) Acked-by: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Christoph Lameter <cl@linux.com>
2013-08-29 02:48:15 +07:00
__this_cpu_write(current_kprobe, p);
}
static void __kprobes resume_execution(struct kprobe *p, unsigned long addr,
struct pt_regs *regs)
{
/* Remove the trap instructions inserted for single step and
* restore the original instructions
*/
if (p->ainsn.t1_addr) {
*(p->ainsn.t1_addr) = p->ainsn.t1_opcode;
flush_icache_range((unsigned long)p->ainsn.t1_addr,
(unsigned long)p->ainsn.t1_addr +
sizeof(kprobe_opcode_t));
p->ainsn.t1_addr = NULL;
}
if (p->ainsn.t2_addr) {
*(p->ainsn.t2_addr) = p->ainsn.t2_opcode;
flush_icache_range((unsigned long)p->ainsn.t2_addr,
(unsigned long)p->ainsn.t2_addr +
sizeof(kprobe_opcode_t));
p->ainsn.t2_addr = NULL;
}
return;
}
static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs)
{
unsigned long next_pc;
unsigned long tgt_if_br = 0;
int is_branch;
unsigned long bta;
/* Copy the opcode back to the kprobe location and execute the
* instruction. Because of this we will not be able to get into the
* same kprobe until this kprobe is done
*/
*(p->addr) = p->opcode;
flush_icache_range((unsigned long)p->addr,
(unsigned long)p->addr + sizeof(kprobe_opcode_t));
/* Now we insert the trap at the next location after this instruction to
* single step. If it is a branch we insert the trap at possible branch
* targets
*/
bta = regs->bta;
if (regs->status32 & 0x40) {
/* We are in a delay slot with the branch taken */
next_pc = bta & ~0x01;
if (!p->ainsn.is_short) {
if (bta & 0x01)
regs->blink += 2;
else {
/* Branch not taken */
next_pc += 2;
/* next pc is taken from bta after executing the
* delay slot instruction
*/
regs->bta += 2;
}
}
is_branch = 0;
} else
is_branch =
disasm_next_pc((unsigned long)p->addr, regs,
(struct callee_regs *) current->thread.callee_reg,
&next_pc, &tgt_if_br);
p->ainsn.t1_addr = (kprobe_opcode_t *) next_pc;
p->ainsn.t1_opcode = *(p->ainsn.t1_addr);
*(p->ainsn.t1_addr) = TRAP_S_2_INSTRUCTION;
flush_icache_range((unsigned long)p->ainsn.t1_addr,
(unsigned long)p->ainsn.t1_addr +
sizeof(kprobe_opcode_t));
if (is_branch) {
p->ainsn.t2_addr = (kprobe_opcode_t *) tgt_if_br;
p->ainsn.t2_opcode = *(p->ainsn.t2_addr);
*(p->ainsn.t2_addr) = TRAP_S_2_INSTRUCTION;
flush_icache_range((unsigned long)p->ainsn.t2_addr,
(unsigned long)p->ainsn.t2_addr +
sizeof(kprobe_opcode_t));
}
}
int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
{
struct kprobe *p;
struct kprobe_ctlblk *kcb;
preempt_disable();
kcb = get_kprobe_ctlblk();
p = get_kprobe((unsigned long *)addr);
if (p) {
/*
* We have reentered the kprobe_handler, since another kprobe
* was hit while within the handler, we save the original
* kprobes and single step on the instruction of the new probe
* without calling any user handlers to avoid recursive
* kprobes.
*/
if (kprobe_running()) {
save_previous_kprobe(kcb);
set_current_kprobe(p);
kprobes_inc_nmissed_count(p);
setup_singlestep(p, regs);
kcb->kprobe_status = KPROBE_REENTER;
return 1;
}
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
/* If we have no pre-handler or it returned 0, we continue with
* normal processing. If we have a pre-handler and it returned
* non-zero - which means user handler setup registers to exit
* to another instruction, we must skip the single stepping.
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
setup_singlestep(p, regs);
kcb->kprobe_status = KPROBE_HIT_SS;
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 23:15:45 +07:00
} else {
reset_current_kprobe();
preempt_enable_no_resched();
}
return 1;
}
/* no_kprobe: */
preempt_enable_no_resched();
return 0;
}
static int __kprobes arc_post_kprobe_handler(unsigned long addr,
struct pt_regs *regs)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (!cur)
return 0;
resume_execution(cur, addr, regs);
/* Rearm the kprobe */
arch_arm_kprobe(cur);
/*
* When we return from trap instruction we go to the next instruction
* We restored the actual instruction in resume_exectuiont and we to
* return to the same address and execute it
*/
regs->ret = addr;
if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
cur->post_handler(cur, regs, 0);
}
if (kcb->kprobe_status == KPROBE_REENTER) {
restore_previous_kprobe(kcb);
goto out;
}
reset_current_kprobe();
out:
preempt_enable_no_resched();
return 1;
}
/*
* Fault can be for the instruction being single stepped or for the
* pre/post handlers in the module.
* This is applicable for applications like user probes, where we have the
* probe in user space and the handlers in the kernel
*/
int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned long trapnr)
{
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 the fault. We reset the current kprobe and allow the
* exception handler as if it is regular exception. In our
* case it doesn't matter because the system will be halted
*/
resume_execution(cur, (unsigned long)cur->addr, regs);
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else
reset_current_kprobe();
preempt_enable_no_resched();
break;
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
/*
* We are here because the instructions in the pre/post handler
* caused the fault.
*/
/* We increment the nmissed count for accounting,
* we can also use npre/npostfault count for accounting
* these specific fault cases.
*/
kprobes_inc_nmissed_count(cur);
/*
* We come here because instructions in the pre/post
* handler caused the page_fault, this could happen
* if handler tries to access user space by
* copy_from_user(), get_user() etc. Let the
* user-specified handler try to fix it first.
*/
if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
/*
* In case the user-specified fault handler returned zero,
* try to fix up.
*/
if (fixup_exception(regs))
return 1;
/*
* fixup_exception() could not handle it,
* Let do_page_fault() fix it.
*/
break;
default:
break;
}
return 0;
}
int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = data;
unsigned long addr = args->err;
int ret = NOTIFY_DONE;
switch (val) {
case DIE_IERR:
if (arc_kprobe_handler(addr, args->regs))
return NOTIFY_STOP;
break;
case DIE_TRAP:
if (arc_post_kprobe_handler(addr, args->regs))
return NOTIFY_STOP;
break;
default:
break;
}
return ret;
}
static void __used kretprobe_trampoline_holder(void)
{
__asm__ __volatile__(".global kretprobe_trampoline\n"
"kretprobe_trampoline:\n" "nop\n");
}
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *) regs->blink;
/* Replace the return addr with trampoline addr */
regs->blink = (unsigned long)&kretprobe_trampoline;
}
static int __kprobes trampoline_probe_handler(struct kprobe *p,
struct pt_regs *regs)
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
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_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);
regs->ret = orig_ret_address;
kretprobe_hash_unlock(current, &flags);
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 the kprobe handler
* that we don't want the post_handler to run
*/
return 1;
}
static struct kprobe trampoline_p = {
.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
.pre_handler = trampoline_probe_handler
};
int __init arch_init_kprobes(void)
{
/* Registering the trampoline code for the kret probe */
return register_kprobe(&trampoline_p);
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
if (p->addr == (kprobe_opcode_t *) &kretprobe_trampoline)
return 1;
return 0;
}
void trap_is_kprobe(unsigned long address, struct pt_regs *regs)
{
notify_die(DIE_TRAP, "kprobe_trap", regs, address, 0, SIGTRAP);
}