Patchwork [2/2,v2] powerpc: restore dbcr0 on user space exit

login
register
mail settings
Submitter Bharat Bhushan
Date May 16, 2013, 5:34 a.m.
Message ID <1368682472-4268-3-git-send-email-Bharat.Bhushan@freescale.com>
Download mbox | patch
Permalink /patch/244222/
State Superseded
Headers show

Comments

Bharat Bhushan - May 16, 2013, 5:34 a.m.
On BookE (Branch taken + Single Step) is as same as Branch Taken
on BookS and in Linux we simulate BookS behavior for BookE as well.
When doing so, in Branch taken handling we want to set DBCR0_IC but
we update the current->thread->dbcr0 and not DBCR0.

Now on 64bit the current->thread.dbcr0 (and other debug registers)
is synchronized ONLY on context switch flow. But after handling
Branch taken in debug exception if we return back to user space
without context switch then single stepping change (DBCR0_ICMP)
does not get written in h/w DBCR0 and Instruction Complete exception
does not happen.

This fixes using ptrace reliably on BookE-PowerPC

Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
---
v1->v2
 - Subject line was not having 2/2

 arch/powerpc/kernel/asm-offsets.c |    1 +
 arch/powerpc/kernel/entry_64.S    |   24 ++++++++++++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)
Bharat Bhushan - May 16, 2013, 5:03 p.m.
> -----Original Message-----
> From: Wood Scott-B07421
> Sent: Thursday, May 16, 2013 10:24 PM
> To: Bhushan Bharat-R65777
> Cc: galak@kernel.crashing.org; benh@kernel.crashing.org; linuxppc-
> dev@lists.ozlabs.org; Yoder Stuart-B08248; Yang James-RA8135; Bhushan Bharat-
> R65777
> Subject: Re: [PATCH 2/2 v2] powerpc: restore dbcr0 on user space exit
> 
> On 05/16/2013 12:34:32 AM, Bharat Bhushan wrote:
> > On BookE (Branch taken + Single Step) is as same as Branch Taken on
> > BookS and in Linux we simulate BookS behavior for BookE as well.
> > When doing so, in Branch taken handling we want to set DBCR0_IC but we
> > update the current->thread->dbcr0 and not DBCR0.
> >
> > Now on 64bit the current->thread.dbcr0 (and other debug registers) is
> > synchronized ONLY on context switch flow. But after handling Branch
> > taken in debug exception if we return back to user space without
> > context switch then single stepping change (DBCR0_ICMP) does not get
> > written in h/w DBCR0 and Instruction Complete exception does not
> > happen.
> >
> > This fixes using ptrace reliably on BookE-PowerPC
> >
> > Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
> > ---
> > v1->v2
> >  - Subject line was not having 2/2
> >
> >  arch/powerpc/kernel/asm-offsets.c |    1 +
> >  arch/powerpc/kernel/entry_64.S    |   24 ++++++++++++++++++++----
> >  2 files changed, 21 insertions(+), 4 deletions(-)
> >
> > diff --git a/arch/powerpc/kernel/asm-offsets.c
> > b/arch/powerpc/kernel/asm-offsets.c
> > index b51a97c..1e2f450 100644
> > --- a/arch/powerpc/kernel/asm-offsets.c
> > +++ b/arch/powerpc/kernel/asm-offsets.c
> > @@ -103,6 +103,7 @@ int main(void)
> >  #endif /* CONFIG_VSX */
> >  #ifdef CONFIG_PPC64
> >  	DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid));
> > +	DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
> >  #else /* CONFIG_PPC64 */
> >  	DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));  #if
> > defined(CONFIG_4xx) || defined(CONFIG_BOOKE) diff --git
> > a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
> > index 794889b..561630d 100644
> > --- a/arch/powerpc/kernel/entry_64.S
> > +++ b/arch/powerpc/kernel/entry_64.S
> > @@ -614,7 +614,9 @@ _GLOBAL(ret_from_except_lite)
> >  	 * from the interrupt.
> >  	 */
> >  #ifdef CONFIG_PPC_BOOK3E
> > +	ld	r3,PACACURRENT(r13)
> >  	wrteei	0
> > +	lwz	r10,(THREAD+THREAD_DBCR0)(r3)
> 
> I know I asked you to move these earlier, but this is probably too early...
> wrteei has synchronization, so it will probably have to wait until the ld
> completes, defeating the purpose of moving it earlier.
> 
> Ideal would probably be to load PACACURRENT immediately after _MSR(r1), and load
> DBCR0 just after "beq resume_kernel".

ok

> 
> Or, move DBCR0 to therad_info as I suggested internally.

If no one have objection on moving dbcr0 to thread_info then I am happy to do that.

> 
> Regardless of what you do, could you run a basic syscall benchmark (e.g. from
> lmbench) before and after the patch?

Sure.

-Bharat
> 
> -Scott

Patch

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b51a97c..1e2f450 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -103,6 +103,7 @@  int main(void)
 #endif /* CONFIG_VSX */
 #ifdef CONFIG_PPC64
 	DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid));
+	DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
 #else /* CONFIG_PPC64 */
 	DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 794889b..561630d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -614,7 +614,9 @@  _GLOBAL(ret_from_except_lite)
 	 * from the interrupt.
 	 */
 #ifdef CONFIG_PPC_BOOK3E
+	ld	r3,PACACURRENT(r13)
 	wrteei	0
+	lwz	r10,(THREAD+THREAD_DBCR0)(r3)
 #else
 	ld	r10,PACAKMSR(r13) /* Get kernel MSR without EE */
 	mtmsrd	r10,1		  /* Update machine state */
@@ -628,15 +630,29 @@  _GLOBAL(ret_from_except_lite)
 
 	/* Check current_thread_info()->flags */
 	andi.	r0,r4,_TIF_USER_WORK_MASK
+	bne	1f
+#ifdef CONFIG_PPC_BOOK3E
+	/*
+	 * Check to see if the dbcr0 register is set up to debug.
+	 * Use the internal debug mode bit to do this.
+	 */
+	andis.	r0,r10,DBCR0_IDM@h
 	beq	restore
-
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq	1f
+	mfmsr	r0
+	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
+	mtmsr	r0
+	mtspr	SPRN_DBCR0,r10
+	li	r10, -1
+	mtspr	SPRN_DBSR,r10
+	b	restore
+#endif
+1:	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq	2f
 	bl	.restore_interrupts
 	SCHEDULE_USER
 	b	.ret_from_except_lite
 
-1:	bl	.save_nvgprs
+2:	bl	.save_nvgprs
 	bl	.restore_interrupts
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_notify_resume