powerpc/booke64: Fix kernel hangs at kernel_dbg_exc

MSR_DE is not cleared on entry to the kernel, and we don't clear it
explicitly outside of debug code.  If we have MSR_DE set in
prime_debug_regs(), and the new thread has events enabled in DBCR0
(e.g.  ICMP is set in thread->dbsr0, even though it was cleared in the
real DBCR0 when the thread got scheduled out), we'll end up taking a
debug exception in the kernel when DBCR0 is loaded.  DSRR0 will not
point to an exception vector, and the kernel ends up hanging at
kernel_dbg_exc.  Fix this by always clearing MSR_DE when we load new
debug state.

Another observed source of kernel_dbg_exc hangs is with the branch
taken event.  If this event is active, but we take a non-debug trap
(e.g. a TLB miss or an asynchronous interrupt) before the next branch.
We end up taking a branch-taken debug exception on the initial branch
instruction of the exception vector, but because the debug exception is
DBSR_BT rather than DBSR_IC we branch to kernel_dbg_exc before even
checking the DSRR0 address.  Fix this by checking for DBSR_BT as well
as DBSR_IC, which is what 32-bit does and what the comments suggest was
intended in the 64-bit code as well.

Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 42a756e..645170a 100644 (file)
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -489,7 +489,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
         */
 
        mfspr   r14,SPRN_DBSR           /* check single-step/branch taken */
-       andis.  r15,r14,DBSR_IC@h
+       andis.  r15,r14,(DBSR_IC|DBSR_BT)@h
        beq+    1f
 
        LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -500,7 +500,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
        bge+    cr1,1f
 
        /* here it looks like we got an inappropriate debug exception. */
-       lis     r14,DBSR_IC@h           /* clear the IC event */
+       lis     r14,(DBSR_IC|DBSR_BT)@h         /* clear the event */
        rlwinm  r11,r11,0,~MSR_DE       /* clear DE in the CSRR1 value */
        mtspr   SPRN_DBSR,r14
        mtspr   SPRN_CSRR1,r11
@@ -555,7 +555,7 @@ kernel_dbg_exc:
         */
 
        mfspr   r14,SPRN_DBSR           /* check single-step/branch taken */
-       andis.  r15,r14,DBSR_IC@h
+       andis.  r15,r14,(DBSR_IC|DBSR_BT)@h
        beq+    1f
 
        LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -566,7 +566,7 @@ kernel_dbg_exc:
        bge+    cr1,1f
 
        /* here it looks like we got an inappropriate debug exception. */
-       lis     r14,DBSR_IC@h           /* clear the IC event */
+       lis     r14,(DBSR_IC|DBSR_BT)@h         /* clear the event */
        rlwinm  r11,r11,0,~MSR_DE       /* clear DE in the DSRR1 value */
        mtspr   SPRN_DBSR,r14
        mtspr   SPRN_DSRR1,r11

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 21981a8..a902723 100644 (file)
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -339,6 +339,13 @@ static void set_debug_reg_defaults(struct thread_struct *thread)
 
 static void prime_debug_regs(struct thread_struct *thread)
 {
+       /*
+        * We could have inherited MSR_DE from userspace, since
+        * it doesn't get cleared on exception entry.  Make sure
+        * MSR_DE is clear before we enable any debug events.
+        */
+       mtmsr(mfmsr() & ~MSR_DE);
+
        mtspr(SPRN_IAC1, thread->iac1);
        mtspr(SPRN_IAC2, thread->iac2);
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2