[RFC PATCH -tip v5 05/27] ARM: kprobes: Remove jprobe arm implementation

[RFC PATCH -tip v5 05/27] ARM: kprobes: Remove jprobe arm implementation

[Masami Hiramatsu]

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/arm.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: linux-arm-kernel at lists.infradead.org
---
 arch/arm/include/asm/kprobes.h |    2 -
 arch/arm/include/asm/probes.h  |    1 
 arch/arm/probes/kprobes/core.c |  114 ----------------------------------------
 3 files changed, 117 deletions(-)

diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 59655459da59..82290f212d8e 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -44,8 +44,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h
index 1e5b9bb92270..991c9127c650 100644
--- a/arch/arm/include/asm/probes.h
+++ b/arch/arm/include/asm/probes.h
@@ -51,7 +51,6 @@ struct arch_probes_insn {
  * We assume one instruction can consume at most 64 bytes stack, which is
  * 'push {r0-r15}'. Instructions consume more or unknown stack space like
  * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe.
- * Both kprobe and jprobe use this macro.
  */
 #define MAX_STACK_SIZE			64
 
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index e90cc8a08186..23562111c511 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -47,9 +47,6 @@
 			   (unsigned long)(addr) +	\
 			   (size))
 
-/* Used as a marker in ARM_pc to note when we're in a jprobe. */
-#define JPROBE_MAGIC_ADDR		0xffffffff
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -521,117 +518,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
 }
 
-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 sp_addr = regs->ARM_sp;
-	long cpsr;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ARM_pc = (long)jp->entry;
-
-	cpsr = regs->ARM_cpsr | PSR_I_BIT;
-#ifdef CONFIG_THUMB2_KERNEL
-	/* Set correct Thumb state in cpsr */
-	if (regs->ARM_pc & 1)
-		cpsr |= PSR_T_BIT;
-	else
-		cpsr &= ~PSR_T_BIT;
-#endif
-	regs->ARM_cpsr = cpsr;
-
-	preempt_disable();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	__asm__ __volatile__ (
-		/*
-		 * Setup an empty pt_regs. Fill SP and PC fields as
-		 * they're needed by longjmp_break_handler.
-		 *
-		 * We allocate some slack between the original SP and start of
-		 * our fabricated regs. To be precise we want to have worst case
-		 * covered which is STMFD with all 16 regs so we allocate 2 *
-		 * sizeof(struct_pt_regs)).
-		 *
-		 * This is to prevent any simulated instruction from writing
-		 * over the regs when they are accessing the stack.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"sub    r0, %0, %1		\n\t"
-		"mov    sp, r0			\n\t"
-#else
-		"sub    sp, %0, %1		\n\t"
-#endif
-		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
-		"str    %0, [sp, %2]		\n\t"
-		"str    r0, [sp, %3]		\n\t"
-		"mov    r0, sp			\n\t"
-		"bl     kprobe_handler		\n\t"
-
-		/*
-		 * Return to the context saved by setjmp_pre_handler
-		 * and restored by longjmp_break_handler.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"ldr	lr, [sp, %2]		\n\t" /* lr = saved sp */
-		"ldrd	r0, r1, [sp, %5]	\n\t" /* r0,r1 = saved lr,pc */
-		"ldr	r2, [sp, %4]		\n\t" /* r2 = saved psr */
-		"stmdb	lr!, {r0, r1, r2}	\n\t" /* push saved lr and */
-						      /* rfe context */
-		"ldmia	sp, {r0 - r12}		\n\t"
-		"mov	sp, lr			\n\t"
-		"ldr	lr, [sp], #4		\n\t"
-		"rfeia	sp!			\n\t"
-#else
-		"ldr	r0, [sp, %4]		\n\t"
-		"msr	cpsr_cxsf, r0		\n\t"
-		"ldmia	sp, {r0 - pc}		\n\t"
-#endif
-		:
-		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs) * 2),
-		  "J" (offsetof(struct pt_regs, ARM_sp)),
-		  "J" (offsetof(struct pt_regs, ARM_pc)),
-		  "J" (offsetof(struct pt_regs, ARM_cpsr)),
-		  "J" (offsetof(struct pt_regs, ARM_lr))
-		: "memory", "cc");
-}
-
-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.ARM_sp;
-	long orig_sp = regs->ARM_sp;
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-
-	if (regs->ARM_pc == JPROBE_MAGIC_ADDR) {
-		if (orig_sp != stack_addr) {
-			struct pt_regs *saved_regs =
-				(struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp;
-			printk("current sp %lx does not match saved sp %lx\n",
-			       orig_sp, stack_addr);
-			printk("Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk("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 __kprobes arch_trampoline_kprobe(struct kprobe *p)
 {
 	return 0;

[RFC PATCH -tip v5 06/27] arm64: kprobes: Remove jprobe implementation

[Masami Hiramatsu]

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/arm64.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel at lists.infradead.org
---
 arch/arm64/include/asm/kprobes.h   |    1 -
 arch/arm64/kernel/probes/kprobes.c |   68 ------------------------------------
 2 files changed, 69 deletions(-)

diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 6deb8d726041..d5a44cf859e9 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -48,7 +48,6 @@ struct kprobe_ctlblk {
 	unsigned long saved_irqflag;
 	struct prev_kprobe prev_kprobe;
 	struct kprobe_step_ctx ss_ctx;
-	struct pt_regs jprobe_saved_regs;
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d849d9804011..3ca2351109a6 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -465,74 +465,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 	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();
-
-	kcb->jprobe_saved_regs = *regs;
-	/*
-	 * Since we can't be sure where in the stack frame "stacked"
-	 * pass-by-value arguments are stored we just don't try to
-	 * duplicate any of the stack. Do not use jprobes on functions that
-	 * use more than 64 bytes (after padding each to an 8 byte boundary)
-	 * of arguments, or pass individual arguments larger than 16 bytes.
-	 */
-
-	instruction_pointer_set(regs, (unsigned long) jp->entry);
-	preempt_disable();
-	pause_graph_tracing();
-	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 special PC to identify it from the other kprobes.
-	 * -restore stack addr to original saved pt_regs
-	 */
-	asm volatile("				mov sp, %0	\n"
-		     "jprobe_return_break:	brk %1		\n"
-		     :
-		     : "r" (kcb->jprobe_saved_regs.sp),
-		       "I" (BRK64_ESR_KPROBES)
-		     : "memory");
-
-	unreachable();
-}
-
-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 = kernel_stack_pointer(regs);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	extern const char jprobe_return_break[];
-
-	if (instruction_pointer(regs) != (u64) jprobe_return_break)
-		return 0;
-
-	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();
-	}
-	unpause_graph_tracing();
-	*regs = kcb->jprobe_saved_regs;
-	preempt_enable_no_resched();
-	return 1;
-}
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	if ((addr >= (unsigned long)__kprobes_text_start &&

[RFC PATCH -tip v5 06/27] arm64: kprobes: Remove jprobe implementation

[Will Deacon]

On Tue, Jun 05, 2018 at 12:51:24AM +0900, Masami Hiramatsu wrote:
> Remove arch dependent setjump/longjump functions
> and unused fields in kprobe_ctlblk for jprobes
> from arch/arm64.
> 
> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: linux-arm-kernel at lists.infradead.org
> ---
>  arch/arm64/include/asm/kprobes.h   |    1 -
>  arch/arm64/kernel/probes/kprobes.c |   68 ------------------------------------
>  2 files changed, 69 deletions(-)

Acked-by: Will Deacon <will.deacon@arm.com>

Will

[RFC PATCH -tip v5 06/27] arm64: kprobes: Remove jprobe implementation

[Masami Hiramatsu]

On Tue, 5 Jun 2018 16:34:21 +0100
Will Deacon <will.deacon@arm.com> wrote:

> On Tue, Jun 05, 2018 at 12:51:24AM +0900, Masami Hiramatsu wrote:
> > Remove arch dependent setjump/longjump functions
> > and unused fields in kprobe_ctlblk for jprobes
> > from arch/arm64.
> > 
> > Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
> > Cc: Catalin Marinas <catalin.marinas@arm.com>
> > Cc: Will Deacon <will.deacon@arm.com>
> > Cc: linux-arm-kernel at lists.infradead.org
> > ---
> >  arch/arm64/include/asm/kprobes.h   |    1 -
> >  arch/arm64/kernel/probes/kprobes.c |   68 ------------------------------------
> >  2 files changed, 69 deletions(-)
> 
> Acked-by: Will Deacon <will.deacon@arm.com>

Thank you Will!


-- 
Masami Hiramatsu <mhiramat@kernel.org>

[RFC PATCH -tip v5 16/27] ARM: kprobes: Don't call the ->break_handler() in arm kprobes code

[Masami Hiramatsu]

Don't call the ->break_handler() from the arm kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: linux-arm-kernel at lists.infradead.org
---
 arch/arm/probes/kprobes/core.c |   11 -----------
 1 file changed, 11 deletions(-)

diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 23562111c511..3192350f389d 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -315,17 +315,6 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				reset_current_kprobe();
 			}
 		}
-	} 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;
-			singlestep(cur, regs, kcb);
-			if (cur->post_handler) {
-				kcb->kprobe_status = KPROBE_HIT_SSDONE;
-				cur->post_handler(cur, regs, 0);
-			}
-		}
-		reset_current_kprobe();
 	} else {
 		/*
 		 * The probe was removed and a race is in progress.

[RFC PATCH -tip v5 17/27] arm64: kprobes: Don't call the ->break_handler() in arm kprobes code

[Masami Hiramatsu]

Don't call the ->break_handler() from the arm kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel at lists.infradead.org
---
 arch/arm64/kernel/probes/kprobes.c |    8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 3ca2351109a6..076c3c0775a6 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -408,14 +408,6 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 				return;
 			}
 		}
-	} else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
-	    BRK64_OPCODE_KPROBES) && cur_kprobe) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur_kprobe->break_handler  &&
-		     cur_kprobe->break_handler(cur_kprobe, regs)) {
-			setup_singlestep(cur_kprobe, regs, kcb, 0);
-			return;
-		}
 	}
 	/*
 	 * The breakpoint instruction was removed right

[RFC PATCH -tip v5 17/27] arm64: kprobes: Don't call the ->break_handler() in arm kprobes code

[Will Deacon]

On Tue, Jun 05, 2018 at 12:56:44AM +0900, Masami Hiramatsu wrote:
> Don't call the ->break_handler() from the arm kprobes code,
> because it was only used by jprobes which got removed.
> 
> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
> 
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: linux-arm-kernel at lists.infradead.org
> ---
>  arch/arm64/kernel/probes/kprobes.c |    8 --------
>  1 file changed, 8 deletions(-)

Acked-by: Will Deacon <will.deacon@arm.com>

Will

[RFC PATCH -tip v5 24/27] bpf: error-inject: kprobes: Clear current_kprobe and enable preempt in kprobe

[Masami Hiramatsu]

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>
Cc: Vineet Gupta <vgupta@synopsys.com>
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: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: x86 at kernel.org
Cc: linux-snps-arc at lists.infradead.org
Cc: linux-kernel at vger.kernel.org
Cc: linux-arm-kernel at lists.infradead.org
Cc: linux-ia64 at vger.kernel.org
Cc: linux-mips at linux-mips.org
Cc: linuxppc-dev at lists.ozlabs.org
Cc: linux-s390 at vger.kernel.org
Cc: linux-sh at vger.kernel.org
Cc: sparclinux at vger.kernel.org
---
 Changes in v5:
  - Fix kprobe_ftrace_handler in arch/powerpc too.
---
 arch/arc/kernel/kprobes.c            |    5 +++--
 arch/arm/probes/kprobes/core.c       |   10 +++++-----
 arch/arm64/kernel/probes/kprobes.c   |   10 +++++-----
 arch/ia64/kernel/kprobes.c           |   13 ++++---------
 arch/mips/kernel/kprobes.c           |    4 ++--
 arch/powerpc/kernel/kprobes-ftrace.c |   15 ++++++---------
 arch/powerpc/kernel/kprobes.c        |    7 +++++--
 arch/s390/kernel/kprobes.c           |    7 ++++---
 arch/sh/kernel/kprobes.c             |    7 ++++---
 arch/sparc/kernel/kprobes.c          |    7 ++++---
 arch/x86/kernel/kprobes/core.c       |    4 ++++
 arch/x86/kernel/kprobes/ftrace.c     |   15 ++++++++-------
 kernel/fail_function.c               |    3 ---
 kernel/trace/trace_kprobe.c          |   11 +++--------
 14 files changed, 57 insertions(+), 61 deletions(-)

diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 465365696c91..df35d4c0b0b8 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -231,6 +231,9 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			setup_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_HIT_SS;
+		} else {
+			reset_current_kprobe();
+			preempt_enable_no_resched();
 		}
 
 		return 1;
@@ -442,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	regs->ret = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 3192350f389d..8d37601fdb20 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -300,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 
 			/*
 			 * 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.
+			 * continue with normal processing. If we have a
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				kcb->kprobe_status = KPROBE_HIT_SS;
@@ -312,8 +312,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 					kcb->kprobe_status = KPROBE_HIT_SSDONE;
 					p->post_handler(p, regs, 0);
 				}
-				reset_current_kprobe();
 			}
+			reset_current_kprobe();
 		}
 	} else {
 		/*
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 076c3c0775a6..5daf3d721cb7 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -395,9 +395,9 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			/*
 			 * 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 and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 *
 			 * pre_handler can hit a breakpoint and can step thru
 			 * before return, keep PSTATE D-flag enabled until
@@ -405,8 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				setup_singlestep(p, regs, kcb, 0);
-				return;
-			}
+			} else
+				reset_current_kprobe();
 		}
 	}
 	/*
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 74c8524e6309..aa41bd5cf9b7 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -478,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 			 */
 			break;
 	}
-
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -851,13 +848,11 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 	set_current_kprobe(p, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/*
-		 * Our pre-handler is specifically requesting that we just
-		 * do a return.  This is used for both the jprobe pre-handler
-		 * and the kretprobe trampoline
-		 */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 #if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 7fd277bc59b9..54cd675c5d1d 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -358,6 +358,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
 	}
 
@@ -543,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	instruction_pointer(regs) = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 3869b0e5d5c7..c80c35d1e26e 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -51,11 +51,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
-	preempt_disable();
-
 	p = get_kprobe((kprobe_opcode_t *)nip);
 	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
+		return;
 
 	kcb = get_kprobe_ctlblk();
 	if (kprobe_running()) {
@@ -75,15 +73,14 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 			skip_singlestep(p, regs, kcb, orig_nip);
 		else {
 			/*
-			 * If pre_handler returns !0, it sets regs->nip and
-			 * resets current kprobe. In this case, we should not
-			 * re-enable preemption.
+			 * If pre_handler returns !0, this handler
+			 * modifies regs->ip and goes back to there
+			 * directly without single stepping.
+			 * So let's just clear current kprobe.
 			 */
-			return;
+			__this_cpu_write(current_kprobe, NULL);
 		}
 	}
-end:
-	preempt_enable_no_resched();
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index f06747e2e70d..5c60bb0f927f 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -358,9 +358,12 @@ int kprobe_handler(struct pt_regs *regs)
 
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 	set_current_kprobe(p, regs, kcb);
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/* handler has already set things up, so skip ss setup */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		/* handler changed execution path, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 	if (p->ainsn.boostable >= 0) {
 		ret = try_to_emulate(p, regs);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3e34018960b5..7c0a095e9c5f 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -326,8 +326,11 @@ static int kprobe_handler(struct pt_regs *regs)
 			 */
 			push_kprobe(kcb, p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-			if (p->pre_handler && p->pre_handler(p, regs))
+			if (p->pre_handler && p->pre_handler(p, regs)) {
+				pop_kprobe(kcb);
+				preempt_enable_no_resched();
 				return 1;
+			}
 			kcb->kprobe_status = KPROBE_HIT_SS;
 		}
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
@@ -431,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 
 	regs->psw.addr = orig_ret_address;
 
-	pop_kprobe(get_kprobe_ctlblk());
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 4fafe0cd12c6..241e903dd3ee 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -272,9 +272,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
@@ -352,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->pc = orig_ret_address;
 	kretprobe_hash_unlock(current, &flags);
 
-	preempt_enable_no_resched();
-
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index c684c96ef2e9..dfbca2470536 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -175,8 +175,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 	prepare_singlestep(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_SS;
@@ -508,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	regs->tpc = orig_ret_address;
 	regs->tnpc = orig_ret_address + 4;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0ac16a0d93e5..814e26b7c8a2 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -694,6 +694,10 @@ int kprobe_int3_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
 				setup_singlestep(p, regs, kcb, 0);
+			else {
+				reset_current_kprobe();
+				preempt_enable_no_resched();
+			}
 			return 1;
 		}
 	} else if (*addr != BREAKPOINT_INSTRUCTION) {
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index c8696f2a583f..310ef737b9d4 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -63,18 +63,19 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
 		regs->ip = ip + sizeof(kprobe_opcode_t);
 
-		/* To emulate trap based kprobes, preempt_disable here */
-		preempt_disable();
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			skip_singlestep(p, regs, kcb, orig_ip);
-			preempt_enable_no_resched();
+		} else {
+			/*
+			 * If pre_handler returns !0, this handler
+			 * modifies regs->ip and goes back to there
+			 * directly without single stepping.
+			 * So let's just clear current kprobe.
+			 */
+			__this_cpu_write(current_kprobe, NULL);
 		}
-		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe, and keep preempt count +1.
-		 */
 	}
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 1d5632d8bbcc..b090688df94f 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
 	if (should_fail(&fei_fault_attr, 1)) {
 		regs_set_return_value(regs, attr->retval);
 		override_function_with_return(regs);
-		/* Kprobe specific fixup */
-		reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 02aed76e0978..b65cd6834450 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1217,16 +1217,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 		/*
 		 * We need to check and see if we modified the pc of the
-		 * pt_regs, and if so clear the kprobe and return 1 so that we
-		 * don't do the single stepping.
-		 * The ftrace kprobe handler leaves it up to us to re-enable
-		 * preemption here before returning if we've modified the ip.
+		 * pt_regs, and if so return 1 so that we don't do the
+		 * single stepping.
 		 */
-		if (orig_ip != instruction_pointer(regs)) {
-			reset_current_kprobe();
-			preempt_enable_no_resched();
+		if (orig_ip != instruction_pointer(regs))
 			return 1;
-		}
 		if (!ret)
 			return 0;
 	}

[RFC PATCH -tip v5 24/27] bpf: error-inject: kprobes: Clear current_kprobe and enable preempt in kprobe

[Naveen N. Rao]

Masami Hiramatsu wrote:
> 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>
> Cc: Vineet Gupta <vgupta@synopsys.com>
> 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: Ralf Baechle <ralf@linux-mips.org>
> Cc: James Hogan <jhogan@kernel.org>
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
> Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
> Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
> Cc: Rich Felker <dalias@libc.org>
> Cc: "David S. Miller" <davem@davemloft.net>
> Cc: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
> Cc: Josef Bacik <jbacik@fb.com>
> Cc: Alexei Starovoitov <ast@kernel.org>
> Cc: x86 at kernel.org
> Cc: linux-snps-arc at lists.infradead.org
> Cc: linux-kernel at vger.kernel.org
> Cc: linux-arm-kernel at lists.infradead.org
> Cc: linux-ia64 at vger.kernel.org
> Cc: linux-mips at linux-mips.org
> Cc: linuxppc-dev at lists.ozlabs.org
> Cc: linux-s390 at vger.kernel.org
> Cc: linux-sh at vger.kernel.org
> Cc: sparclinux at vger.kernel.org
> ---
>  Changes in v5:
>   - Fix kprobe_ftrace_handler in arch/powerpc too.
> ---
>  arch/arc/kernel/kprobes.c            |    5 +++--
>  arch/arm/probes/kprobes/core.c       |   10 +++++-----
>  arch/arm64/kernel/probes/kprobes.c   |   10 +++++-----
>  arch/ia64/kernel/kprobes.c           |   13 ++++---------
>  arch/mips/kernel/kprobes.c           |    4 ++--
>  arch/powerpc/kernel/kprobes-ftrace.c |   15 ++++++---------
>  arch/powerpc/kernel/kprobes.c        |    7 +++++--

For the powerpc bits:
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>

Thanks,
Naveen