Re: [PATCH v7 3/7] arm64: Kprobes with single stepping support

From: David Long
Date: Thu Jul 02 2015 - 18:36:31 EST

On 06/29/15 13:24, Steve Capper wrote:
On 15 June 2015 at 20:07, David Long <dave.long@xxxxxxxxxx> wrote:
From: Sandeepa Prabhu <sandeepa.prabhu@xxxxxxxxxx>

Add support for basic kernel probes(kprobes) and jump probes
(jprobes) for ARM64.

Kprobes utilizes software breakpoint and single step debug
exceptions supported on ARM v8.

A software breakpoint is placed at the probe address to trap the
kernel execution into the kprobe handler.

ARM v8 supports enabling single stepping before the break exception
return (ERET), with next PC in exception return address (ELR_EL1). The
kprobe handler prepares an executable memory slot for out-of-line
execution with a copy of the original instruction being probed, and
enables single stepping. The PC is set to the out-of-line slot address
before the ERET. With this scheme, the instruction is executed with the
exact same register context except for the PC (and DAIF) registers.

Debug mask (PSTATE.D) is enabled only when single stepping a recursive
kprobe, e.g.: during kprobes reenter so that probed instruction can be
single stepped within the kprobe handler -exception- context.
The recursion depth of kprobe is always 2, i.e. upon probe re-entry,
any further re-entry is prevented by not calling handlers and the case
counted as a missed kprobe).

Single stepping from the x-o-l slot has a drawback for PC-relative accesses
like branching and symbolic literals access as the offset from the new PC
(slot address) may not be ensured to fit in the immediate value of
the opcode. Such instructions need simulation, so reject
probing them.

Instructions generating exceptions or cpu mode change are rejected
for probing.

Instructions using Exclusive Monitor are rejected too.

System instructions are mostly enabled for stepping, except MSR/MRS
accesses to "DAIF" flags in PSTATE, which are not safe for
probing.

Thanks to Steve Capper and Pratyush Anand for several suggested
Changes.

Signed-off-by: Sandeepa Prabhu <sandeepa.prabhu@xxxxxxxxxx>
Signed-off-by: Steve Capper <steve.capper@xxxxxxxxxx>
Signed-off-by: David A. Long <dave.long@xxxxxxxxxx>
---
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/debug-monitors.h | 5 +
arch/arm64/include/asm/kprobes.h | 62 ++++
arch/arm64/include/asm/probes.h | 50 +++
arch/arm64/include/asm/ptrace.h | 3 +-
arch/arm64/kernel/Makefile | 1 +
arch/arm64/kernel/debug-monitors.c | 35 ++-
arch/arm64/kernel/kprobes-arm64.c | 68 ++++
arch/arm64/kernel/kprobes-arm64.h | 28 ++
arch/arm64/kernel/kprobes.c | 537 ++++++++++++++++++++++++++++++++
arch/arm64/kernel/kprobes.h | 24 ++
arch/arm64/kernel/vmlinux.lds.S | 1 +
arch/arm64/mm/fault.c | 25 ++
13 files changed, 829 insertions(+), 11 deletions(-)
create mode 100644 arch/arm64/include/asm/kprobes.h
create mode 100644 arch/arm64/include/asm/probes.h
create mode 100644 arch/arm64/kernel/kprobes-arm64.c
create mode 100644 arch/arm64/kernel/kprobes-arm64.h
create mode 100644 arch/arm64/kernel/kprobes.c
create mode 100644 arch/arm64/kernel/kprobes.h

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 966091f..45a9bd81 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -71,6 +71,7 @@ config ARM64
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RCU_TABLE_FREE
select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_KPROBES
select IRQ_DOMAIN
select MODULES_USE_ELF_RELA
select NO_BOOTMEM
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 40ec68a..92d7cea 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -90,6 +90,11 @@

#define CACHE_FLUSH_IS_SAFE 1

+/* kprobes BRK opcodes with ESR encoding */
+#define BRK64_ESR_MASK 0xFFFF
+#define BRK64_ESR_KPROBES 0x0004
+#define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+
/* AArch32 */
#define DBG_ESR_EVT_BKPT 0x4
#define DBG_ESR_EVT_VECC 0x5
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
new file mode 100644
index 0000000..af31c4d
--- /dev/null
+++ b/arch/arm64/include/asm/kprobes.h
@@ -0,0 +1,62 @@
+/*
+ * arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KPROBES_H
+#define _ARM_KPROBES_H
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE 1
+#define MAX_STACK_SIZE 128
+
+#define flush_insn_slot(p) do { } while (0)
+#define kretprobe_blacklist_size 0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+ struct kprobe *kp;
+ unsigned int status;
+};
+
+/* Single step context for kprobe */
+struct kprobe_step_ctx {
+#define KPROBES_STEP_NONE 0x0
+#define KPROBES_STEP_PENDING 0x1
+ unsigned long ss_status;
+ unsigned long match_addr;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+ unsigned int kprobe_status;
+ unsigned long saved_irqflag;
+ struct prev_kprobe prev_kprobe;
+ struct kprobe_step_ctx ss_ctx;
+ struct pt_regs jprobe_saved_regs;
+ char jprobes_stack[MAX_STACK_SIZE];
+};
+
+void arch_remove_kprobe(struct kprobe *);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
+int kprobe_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data);
+int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
+int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
+
+#endif /* _ARM_KPROBES_H */
diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h
new file mode 100644
index 0000000..7f5a27f
--- /dev/null
+++ b/arch/arm64/include/asm/probes.h
@@ -0,0 +1,50 @@
+/*
+ * arch/arm64/include/asm/probes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef _ARM_PROBES_H
+#define _ARM_PROBES_H
+
+struct kprobe;
+struct arch_specific_insn;
+
+typedef u32 kprobe_opcode_t;
+typedef unsigned long (kprobes_pstate_check_t)(unsigned long);
+typedef unsigned long
+(probes_condition_check_t)(struct kprobe *p, struct pt_regs *);
+typedef void
+(probes_prepare_t)(struct kprobe *, struct arch_specific_insn *);
+typedef void (kprobes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+
+enum pc_restore_type {
+ NO_RESTORE,
+ RESTORE_PC,
+};
+
+struct kprobe_pc_restore {
+ enum pc_restore_type type;
+ unsigned long addr;
+};
+
+/* architecture specific copy of original instruction */
+struct arch_specific_insn {
+ kprobe_opcode_t *insn;
+ kprobes_pstate_check_t *pstate_cc;
+ probes_condition_check_t *check_condn;
+ probes_prepare_t *prepare;
+ kprobes_handler_t *handler;
+ /* restore address after step xol */
+ struct kprobe_pc_restore restore;
+};
+
+#endif
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 8f440e9..aadf61a 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -206,7 +206,8 @@ static inline int valid_user_regs(struct user_pt_regs *regs)
return 0;
}

-#define instruction_pointer(regs) ((unsigned long)(regs)->pc)
+#define instruction_pointer(regs) ((regs)->pc)
+#define stack_pointer(regs) ((regs)->sp)

#ifdef CONFIG_SMP
extern unsigned long profile_pc(struct pt_regs *regs);
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 426d076..1319872 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -32,6 +32,7 @@ arm64-obj-$(CONFIG_CPU_PM) += sleep.o suspend.o
arm64-obj-$(CONFIG_CPU_IDLE) += cpuidle.o
arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o
arm64-obj-$(CONFIG_KGDB) += kgdb.o
+arm64-obj-$(CONFIG_KPROBES) += kprobes.o kprobes-arm64.o
arm64-obj-$(CONFIG_EFI) += efi.o efi-stub.o efi-entry.o
arm64-obj-$(CONFIG_PCI) += pci.o
arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index b056369..486ee94 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -23,6 +23,7 @@
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/ptrace.h>
+#include <linux/kprobes.h>
#include <linux/stat.h>
#include <linux/uaccess.h>

@@ -228,6 +229,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
siginfo_t info;
+ bool handler_found = false;

/*
* If we are stepping a pending breakpoint, call the hw_breakpoint
@@ -251,15 +253,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
*/
user_rewind_single_step(current);
} else {
+#ifdef CONFIG_KPROBES
+ if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
+ handler_found = true;
+#endif
if (call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
- return 0;
-
- pr_warning("Unexpected kernel single-step exception at EL1\n");
- /*
- * Re-enable stepping since we know that we will be
- * returning to regs.
- */
- set_regs_spsr_ss(regs);
+ handler_found = true;
+
+ if (!handler_found) {
+ pr_warn("Unexpected kernel single-step exception at EL1\n");
+ /*
+ * Re-enable stepping since we know that we will be
+ * returning to regs.
+ */
+ set_regs_spsr_ss(regs);
+ }
}

return 0;
@@ -315,8 +323,15 @@ static int brk_handler(unsigned long addr, unsigned int esr,
};

force_sig_info(SIGTRAP, &info, current);
- } else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
- pr_warning("Unexpected kernel BRK exception at EL1\n");
+ }
+#ifdef CONFIG_KPROBES
+ else if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
+ if (kprobe_breakpoint_handler(regs, esr) != DBG_HOOK_HANDLED)
+ return -EFAULT;
+ }
+#endif
+ else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+ pr_warn("Unexpected kernel BRK exception at EL1\n");
return -EFAULT;
}

diff --git a/arch/arm64/kernel/kprobes-arm64.c b/arch/arm64/kernel/kprobes-arm64.c
new file mode 100644
index 0000000..f958c52
--- /dev/null
+++ b/arch/arm64/kernel/kprobes-arm64.c
@@ -0,0 +1,68 @@
+/*
+ * arch/arm64/kernel/kprobes-arm64.c
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <asm/kprobes.h>
+#include <asm/insn.h>
+
+#include "kprobes-arm64.h"
+
+static bool __kprobes aarch64_insn_is_steppable(u32 insn)
+{
+ if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) {
+ if (aarch64_insn_is_branch(insn))
+ return false;
+
+ /* modification of daif creates issues */
+ if (aarch64_insn_is_daif_access(insn))
+ return false;
+
+ if (aarch64_insn_is_exception(insn))
+ return false;
+
+ if (aarch64_insn_is_hint(insn))
+ return aarch64_insn_is_nop(insn);
+
+ return true;
+ }
+
+ if (aarch64_insn_uses_literal(insn))
+ return false;
+
+ if (aarch64_insn_is_exclusive(insn))
+ return false;
+
+ return true;
+}
+
+/* Return:
+ * INSN_REJECTED If instruction is one not allowed to kprobe,
+ * INSN_GOOD If instruction is supported and uses instruction slot,
+ * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
+ */
+enum kprobe_insn __kprobes
+arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+{
+ /*
+ * Instructions reading or modifying the PC won't work from the XOL
+ * slot.
+ */
+ if (aarch64_insn_is_steppable(insn))
+ return INSN_GOOD;
+ else
+ return INSN_REJECTED;
+}
diff --git a/arch/arm64/kernel/kprobes-arm64.h b/arch/arm64/kernel/kprobes-arm64.h
new file mode 100644
index 0000000..87e7891
--- /dev/null
+++ b/arch/arm64/kernel/kprobes-arm64.h
@@ -0,0 +1,28 @@
+/*
+ * arch/arm64/kernel/kprobes-arm64.h
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KERNEL_KPROBES_ARM64_H
+#define _ARM_KERNEL_KPROBES_ARM64_H
+
+enum kprobe_insn {
+ INSN_REJECTED,
+ INSN_GOOD_NO_SLOT,
+ INSN_GOOD,
+};
+
+enum kprobe_insn __kprobes
+arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi);
+
+#endif /* _ARM_KERNEL_KPROBES_ARM64_H */
diff --git a/arch/arm64/kernel/kprobes.c b/arch/arm64/kernel/kprobes.c
new file mode 100644
index 0000000..601d2c6
--- /dev/null
+++ b/arch/arm64/kernel/kprobes.c
@@ -0,0 +1,537 @@
+/*
+ * arch/arm64/kernel/kprobes.c
+ *
+ * Kprobes support for ARM64
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ * Author: Sandeepa Prabhu <sandeepa.prabhu@xxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <linux/stringify.h>
+#include <asm/traps.h>
+#include <asm/ptrace.h>
+#include <asm/cacheflush.h>
+#include <asm/debug-monitors.h>
+#include <asm/system_misc.h>
+#include <asm/insn.h>
+
+#include "kprobes.h"
+#include "kprobes-arm64.h"
+
+#define MIN_STACK_SIZE(addr) min((unsigned long)MAX_STACK_SIZE, \
+ (unsigned long)current_thread_info() + THREAD_START_SP - (addr))
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+{
+ /* prepare insn slot */
+ p->ainsn.insn[0] = p->opcode;
+
+ flush_icache_range((uintptr_t) (p->ainsn.insn),
+ (uintptr_t) (p->ainsn.insn) + MAX_INSN_SIZE);
+
+ /*
+ * Needs restoring of return address after stepping xol.
+ */
+ p->ainsn.restore.addr = (unsigned long) p->addr +
+ sizeof(kprobe_opcode_t);
+ p->ainsn.restore.type = RESTORE_PC;
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+ kprobe_opcode_t insn;
+ unsigned long probe_addr = (unsigned long)p->addr;
+
+ /* copy instruction */
+ insn = *p->addr;
+ p->opcode = insn;
+
+ if (in_exception_text(probe_addr))
+ return -EINVAL;
+
+ /* decode instruction */
+ switch (arm_kprobe_decode_insn(insn, &p->ainsn)) {
+ case INSN_REJECTED: /* insn not supported */
+ return -EINVAL;
+
+ case INSN_GOOD_NO_SLOT: /* insn need simulation */
+ return -EINVAL;
+
+ case INSN_GOOD: /* instruction uses slot */
+ p->ainsn.insn = get_insn_slot();
+ if (!p->ainsn.insn)
+ return -ENOMEM;
+ break;
+ };
+
+ /* prepare the instruction */
+ arch_prepare_ss_slot(p);
+
+ return 0;
+}
+
+static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
+{
+ void *addrs[1];
+ u32 insns[1];
+
+ addrs[0] = (void *)addr;
+ insns[0] = (u32)opcode;
+
+ return aarch64_insn_patch_text_sync(addrs, insns, 1);
+}
+
+/* arm kprobe: install breakpoint in text */
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+ patch_text(p->addr, BRK64_OPCODE_KPROBES);
+}
+
+/* disarm kprobe: remove breakpoint from text */
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+ patch_text(p->addr, 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);
+}
+
+/*
+ * The D-flag (Debug mask) is set (masked) upon exception entry.
+ * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive
+ * probe i.e. when probe hit from kprobe handler context upon
+ * executing the pre/post handlers. In this case we return with
+ * D-flag clear so that single-stepping can be carried-out.
+ *
+ * Leave D-flag set in all other cases.
+ */
+static void __kprobes
+spsr_set_debug_flag(struct pt_regs *regs, int mask)
+{
+ unsigned long spsr = regs->pstate;
+
+ if (mask)
+ spsr |= PSR_D_BIT;
+ else
+ spsr &= ~PSR_D_BIT;
+
+ regs->pstate = spsr;
+}
+
+/*
+ * Interrupts need to be disabled before single-step mode is set, and not
+ * reenabled until after single-step mode ends.
+ * Without disabling interrupt on local CPU, there is a chance of
+ * interrupt occurrence in the period of exception return and start of
+ * out-of-line single-step, that result in wrongly single stepping
+ * the interrupt handler.
+ */
+static void __kprobes kprobes_save_local_irqflag(struct pt_regs *regs)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ kcb->saved_irqflag = regs->pstate;
+ regs->pstate |= PSR_I_BIT;
+}
+
+static void __kprobes kprobes_restore_local_irqflag(struct pt_regs *regs)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ if (kcb->saved_irqflag & PSR_I_BIT)
+ regs->pstate |= PSR_I_BIT;
+ else
+ regs->pstate &= ~PSR_I_BIT;
+}
+
+static void __kprobes
+set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr)
+{
+ kcb->ss_ctx.ss_status = KPROBES_STEP_PENDING;
+ kcb->ss_ctx.match_addr = addr + sizeof(kprobe_opcode_t);
+}
+
+static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb)
+{
+ kcb->ss_ctx.ss_status = KPROBES_STEP_NONE;
+ kcb->ss_ctx.match_addr = 0;
+}
+
+static void __kprobes
+skip_singlestep_missed(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+{
+ /* set return addr to next pc to continue */
+ instruction_pointer(regs) += sizeof(kprobe_opcode_t);
+}

I'm not sure if this is the best approach for skip_singlestep_missed?
If the condition check fails, we have very little to simulate :-), but
I think the user will expect the kprobe to fire?

For instance I have the following memcpy in my kernel:

ffffffc0003b6500 <memcpy>:
ffffffc0003b6500: aa0003e6 mov x6, x0
ffffffc0003b6504: f100405f cmp x2, #0x10
ffffffc0003b6508: 540003c3 b.cc ffffffc0003b6580 <memcpy+0x80>
ffffffc0003b650c: cb0103e4 neg x4, x1
ffffffc0003b6510: f2400c84 ands x4, x4, #0xf
ffffffc0003b6514: 540001c0 b.eq ffffffc0003b654c <memcpy+0x4c>

If I set the following kprobes:
p:kprobes/memcpy1 0xffffffc0003b6500
p:kprobes/memcpy2 0xffffffc0003b6508

So the second kprobe is placed on a conditional instruction.

I get the following statistics from perf:
perf stat -e kprobes:memcpy1 -e kprobes:memcpy2 -a sleep 10

Performance counter stats for 'system wide':

2,001 kprobes:memcpy1
(100.00%)
1,563 kprobes:memcpy2

10.001287601 seconds time elapsed

I (maybe naively) would expect the event counts to be the same? (as
both pc values are "hit").
For a case where the condition check fails, I think we should do something like:

set_current_probe(p);
instruction_pointer(regs) += sizeof(kprobe_opcode_t);
post_kprobe_handler(kcb, regs);


Well maybe it's debatable but the implementations of both the 32bit and 64bit ARM kprobes feature assumes a conditional instruction that is not executed (condition is false) is not to be considered as having been a kprobe hit. Maybe the problem is how one defines "executed", but the existing code assumes it means the condition must be true. I really think this is reasonable, but if we change it we really should be changing it for both ARM architectures and for any other architecture with conditional instruction execution that implements it the way arm does now. Right now users presumably look at the trace log and hit counts on conditional instructions as an indication of how often a condition has been met. Changing that is likely to be confusing and I think removes useful information from the log. In your specific example the existing behavior can be used for calculating a percentage of times the condition was true or false. I personally think this is more useful than the alternative behavior.

+
+static void __kprobes setup_singlestep(struct kprobe *p,
+ struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb, int reenter)
+{
+ unsigned long slot;
+
+ if (reenter) {
+ save_previous_kprobe(kcb);
+ set_current_kprobe(p);
+ kcb->kprobe_status = KPROBE_REENTER;
+ } else {
+ kcb->kprobe_status = KPROBE_HIT_SS;
+ }
+
+ if (p->ainsn.insn) {
+ /* prepare for single stepping */
+ slot = (unsigned long)p->ainsn.insn;
+
+ set_ss_context(kcb, slot); /* mark pending ss */
+
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ spsr_set_debug_flag(regs, 0);
+
+ /* IRQs and single stepping do not mix well. */
+ kprobes_save_local_irqflag(regs);
+ kernel_enable_single_step(regs);
+ instruction_pointer(regs) = slot;
+ } else {
+ BUG();
+ }
+}
+
+static int __kprobes reenter_kprobe(struct kprobe *p,
+ struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ switch (kcb->kprobe_status) {
+ case KPROBE_HIT_SSDONE:
+ case KPROBE_HIT_ACTIVE:
+ if (!p->ainsn.check_condn || p->ainsn.check_condn(p, regs)) {
+ kprobes_inc_nmissed_count(p);
+ setup_singlestep(p, regs, kcb, 1);
+ } else {
+ /* condition check failed, skip stepping */
+ skip_singlestep_missed(kcb, regs);
+ }
+ break;
+ case KPROBE_HIT_SS:
+ case KPROBE_REENTER:
+ pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+ dump_kprobe(p);
+ BUG();
+ break;
+ default:
+ WARN_ON(1);
+ return 0;
+ }
+
+ return 1;
+}
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+{
+ struct kprobe *cur = kprobe_running();
+
+ if (!cur)
+ return;
+
+ /* return addr restore if non-branching insn */
+ if (cur->ainsn.restore.type == RESTORE_PC) {
+ instruction_pointer(regs) = cur->ainsn.restore.addr;
+ if (!instruction_pointer(regs))
+ BUG();
+ }
+
+ /* restore back original saved kprobe variables and continue */
+ if (kcb->kprobe_status == KPROBE_REENTER) {
+ restore_previous_kprobe(kcb);
+ return;
+ }
+ /* call post handler */
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ if (cur->post_handler) {
+ /* post_handler can hit breakpoint and single step
+ * again, so we enable D-flag for recursive exception.
+ */
+ cur->post_handler(cur, regs, 0);
+ }
+
+ reset_current_kprobe();
+}
+
+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 ip points back to the probe address
+ * and allow the page fault handler to continue as a
+ * normal page fault.
+ */
+ instruction_pointer(regs) = (unsigned long)cur->addr;
+ if (!instruction_pointer(regs))
+ BUG();
+ 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 first.
+ */
+ if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
+ return 1;
+
+ /*
+ * In case the user-specified fault handler returned
+ * zero, try to fix up.
+ */
+ if (fixup_exception(regs))
+ return 1;
+
+ break;
+ }
+ return 0;
+}
+
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return NOTIFY_DONE;
+}
+
+void __kprobes kprobe_handler(struct pt_regs *regs)
+{
+ struct kprobe *p, *cur;
+ struct kprobe_ctlblk *kcb;
+ unsigned long addr = instruction_pointer(regs);
+
+ kcb = get_kprobe_ctlblk();
+ cur = kprobe_running();
+
+ p = get_kprobe((kprobe_opcode_t *) addr);
+
+ if (p) {
+ if (cur) {
+ if (reenter_kprobe(p, regs, kcb))
+ return;
+ } else if (!p->ainsn.check_condn ||
+ p->ainsn.check_condn(p, regs)) {
+ /* 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
+ * continue with normal processing. If we have a
+ * pre-handler and it returned non-zero, it prepped
+ * for calling the break_handler below on re-entry,
+ * so get out doing nothing more here.
+ *
+ * pre_handler can hit a breakpoint and can step thru
+ * before return, keep PSTATE D-flag enabled until
+ * pre_handler return back.
+ */
+ if (!p->pre_handler || !p->pre_handler(p, regs)) {
+ kcb->kprobe_status = KPROBE_HIT_SS;
+ setup_singlestep(p, regs, kcb, 0);
+ return;
+ }
+ } else {
+ /*
+ * Breakpoint hit but conditional check failed,
+ * so just skip the instruction (NOP behaviour)
+ */
+ skip_singlestep_missed(kcb, regs);
+ return;
+ }
+ } else if (*(kprobe_opcode_t *) addr != BRK64_OPCODE_KPROBES) {
+ /*
+ * 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.
+ * Return back to original instruction, and continue.
+ */
+ return;
+ } else if (cur) {
+ /* We probably hit a jprobe. Call its break handler. */
+ if (cur->break_handler && cur->break_handler(cur, regs)) {
+ kcb->kprobe_status = KPROBE_HIT_SS;
+ setup_singlestep(cur, regs, kcb, 0);
+ return;
+ }
+ } else {
+ /* breakpoint is removed, now in a race
+ * Return back to original instruction & continue.
+ */
+ }
+}
+
+static int __kprobes
+kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr)
+{
+ if ((kcb->ss_ctx.ss_status == KPROBES_STEP_PENDING)
+ && (kcb->ss_ctx.match_addr == addr)) {
+ clear_ss_context(kcb); /* clear pending ss */
+ return DBG_HOOK_HANDLED;
+ }
+ /* not ours, kprobes should ignore it */
+ return DBG_HOOK_ERROR;
+}
+
+int __kprobes
+kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ int retval;
+
+ /* return error if this is not our step */
+ retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
+
+ if (retval == DBG_HOOK_HANDLED) {
+ kprobes_restore_local_irqflag(regs);
+ kernel_disable_single_step();
+
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ spsr_set_debug_flag(regs, 1);
+
+ post_kprobe_handler(kcb, regs);
+ }
+
+ return retval;
+}
+
+int __kprobes
+kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
+{
+ kprobe_handler(regs);
+ return DBG_HOOK_HANDLED;
+}
+
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct jprobe *jp = container_of(p, struct jprobe, kp);
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ long stack_ptr = stack_pointer(regs);
+
+ kcb->jprobe_saved_regs = *regs;
+ memcpy(kcb->jprobes_stack, (void *)stack_ptr,
+ MIN_STACK_SIZE(stack_ptr));
+
+ instruction_pointer(regs) = (long)jp->entry;
+ preempt_disable();
+ return 1;
+}
+
+void __kprobes jprobe_return(void)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ /*
+ * Jprobe handler return by entering break exception,
+ * encoded same as kprobe, but with following conditions
+ * -a magic number in x0 to identify from rest of other kprobes.
+ * -restore stack addr to original saved pt_regs
+ */
+ asm volatile ("ldr x0, [%0]\n\t"
+ "mov sp, x0\n\t"
+ "ldr x0, =" __stringify(JPROBES_MAGIC_NUM) "\n\t"
+ "BRK %1\n\t"
+ "NOP\n\t"
+ :
+ : "r"(&kcb->jprobe_saved_regs.sp),
+ "I"(BRK64_ESR_KPROBES)
+ : "memory");
+}
+
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ long stack_addr = kcb->jprobe_saved_regs.sp;
+ long orig_sp = stack_pointer(regs);
+ struct jprobe *jp = container_of(p, struct jprobe, kp);
+
+ if (regs->regs[0] == JPROBES_MAGIC_NUM) {
+ if (orig_sp != stack_addr) {
+ struct pt_regs *saved_regs =
+ (struct pt_regs *)kcb->jprobe_saved_regs.sp;
+ pr_err("current sp %lx does not match saved sp %lx\n",
+ orig_sp, stack_addr);
+ pr_err("Saved registers for jprobe %p\n", jp);
+ show_regs(saved_regs);
+ pr_err("Current registers\n");
+ show_regs(regs);
+ BUG();
+ }
+ *regs = kcb->jprobe_saved_regs;
+ memcpy((void *)stack_addr, kcb->jprobes_stack,
+ MIN_STACK_SIZE(stack_addr));
+ preempt_enable_no_resched();
+ return 1;
+ }
+ return 0;
+}
+
+int __init arch_init_kprobes(void)
+{
+ return 0;
+}
diff --git a/arch/arm64/kernel/kprobes.h b/arch/arm64/kernel/kprobes.h
new file mode 100644
index 0000000..e98ad60
--- /dev/null
+++ b/arch/arm64/kernel/kprobes.h
@@ -0,0 +1,24 @@
+/*
+ * arch/arm64/kernel/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KERNEL_KPROBES_H
+#define _ARM_KERNEL_KPROBES_H
+
+#define JPROBES_MAGIC_NUM 0xa5a5a5a5a5a5a5a5
+
+/* Move this out to appropriate header file */
+int fixup_exception(struct pt_regs *regs);
+
+#endif /* _ARM_KERNEL_KPROBES_H */
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index a2c2986..2da5f4e 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -94,6 +94,7 @@ SECTIONS
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
+ KPROBES_TEXT
HYPERVISOR_TEXT
*(.fixup)
*(.gnu.warning)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 96da131..4c13dfb 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -39,6 +39,28 @@

static const char *fault_name(unsigned int esr);

+#ifdef CONFIG_KPROBES
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+ int ret = 0;
+
+ /* kprobe_running() needs smp_processor_id() */
+ if (!user_mode(regs)) {
+ preempt_disable();
+ if (kprobe_running() && kprobe_fault_handler(regs, esr))
+ ret = 1;
+ preempt_enable();
+ }
+
+ return ret;
+}
+#else
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+ return 0;
+}
+#endif
+
/*
* Dump out the page tables associated with 'addr' in mm 'mm'.
*/
@@ -200,6 +222,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

+ if (notify_page_fault(regs, esr))
+ return 0;
+
tsk = current;
mm = tsk->mm;

--
1.8.1.2



Thanks,
-dl

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/