commit e6b8fd028b584ffca7a7255b8971f254932c9fce
author Michael Neuling <mikey@neuling.org> Fri Apr 04 20:19:48 2014 +1100
committer Benjamin Herrenschmidt <benh@kernel.crashing.org> Mon Apr 07 10:33:13 2014 +1000
tree 4ac41335a6f86f5f69e3dc48d92bec280e5c2c31
parent a08a53ea4c97940fe83fea3eab27618ac0fb5ed1

powerpc/tm: Disable IRQ in tm_recheckpoint

We can't take an IRQ when we're about to do a trechkpt as our GPR state is set
to user GPR values.

We've hit this when running some IBM Java stress tests in the lab resulting in
the following dump:

  cpu 0x3f: Vector: 700 (Program Check) at [c000000007eb3d40]
      pc: c000000000050074: restore_gprs+0xc0/0x148
      lr: 00000000b52a8184
      sp: ac57d360
     msr: 8000000100201030
    current = 0xc00000002c500000
    paca    = 0xc000000007dbfc00     softe: 0     irq_happened: 0x00
      pid   = 34535, comm = Pooled Thread #
  R00 = 00000000b52a8184   R16 = 00000000b3e48fda
  R01 = 00000000ac57d360   R17 = 00000000ade79bd8
  R02 = 00000000ac586930   R18 = 000000000fac9bcc
  R03 = 00000000ade60000   R19 = 00000000ac57f930
  R04 = 00000000f6624918   R20 = 00000000ade79be8
  R05 = 00000000f663f238   R21 = 00000000ac218a54
  R06 = 0000000000000002   R22 = 000000000f956280
  R07 = 0000000000000008   R23 = 000000000000007e
  R08 = 000000000000000a   R24 = 000000000000000c
  R09 = 00000000b6e69160   R25 = 00000000b424cf00
  R10 = 0000000000000181   R26 = 00000000f66256d4
  R11 = 000000000f365ec0   R27 = 00000000b6fdcdd0
  R12 = 00000000f66400f0   R28 = 0000000000000001
  R13 = 00000000ada71900   R29 = 00000000ade5a300
  R14 = 00000000ac2185a8   R30 = 00000000f663f238
  R15 = 0000000000000004   R31 = 00000000f6624918
  pc  = c000000000050074 restore_gprs+0xc0/0x148
  cfar= c00000000004fe28 dont_restore_vec+0x1c/0x1a4
  lr  = 00000000b52a8184
  msr = 8000000100201030   cr  = 24804888
  ctr = 0000000000000000   xer = 0000000000000000   trap =  700

This moves tm_recheckpoint to a C function and moves the tm_restore_sprs into
that function.  It then adds IRQ disabling over the trechkpt critical section.
It also sets the TEXASR FS in the signals code to ensure this is never set now
that we explictly write the TM sprs in tm_recheckpoint.

Signed-off-by: Michael Neuling <mikey@neuling.org>
cc: stable@vger.kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/kernel/process.c

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index af064d2..31d0215 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -610,6 +610,31 @@
 	tm_save_sprs(thr);
 }
 
+extern void __tm_recheckpoint(struct thread_struct *thread,
+			      unsigned long orig_msr);
+
+void tm_recheckpoint(struct thread_struct *thread,
+		     unsigned long orig_msr)
+{
+	unsigned long flags;
+
+	/* We really can't be interrupted here as the TEXASR registers can't
+	 * change and later in the trecheckpoint code, we have a userspace R1.
+	 * So let's hard disable over this region.
+	 */
+	local_irq_save(flags);
+	hard_irq_disable();
+
+	/* The TM SPRs are restored here, so that TEXASR.FS can be set
+	 * before the trecheckpoint and no explosion occurs.
+	 */
+	tm_restore_sprs(thread);
+
+	__tm_recheckpoint(thread, orig_msr);
+
+	local_irq_restore(flags);
+}
+
 static inline void tm_recheckpoint_new_task(struct task_struct *new)
 {
 	unsigned long msr;
@@ -628,13 +653,10 @@
 	if (!new->thread.regs)
 		return;
 
-	/* The TM SPRs are restored here, so that TEXASR.FS can be set
-	 * before the trecheckpoint and no explosion occurs.
-	 */
-	tm_restore_sprs(&new->thread);
-
-	if (!MSR_TM_ACTIVE(new->thread.regs->msr))
+	if (!MSR_TM_ACTIVE(new->thread.regs->msr)){
+		tm_restore_sprs(&new->thread);
 		return;
+	}
 	msr = new->thread.tm_orig_msr;
 	/* Recheckpoint to restore original checkpointed register state. */
 	TM_DEBUG("*** tm_recheckpoint of pid %d "

arch/powerpc/kernel/signal_32.c

diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index a67e00a..4e47db6 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -881,6 +881,8 @@
 	 * transactional versions should be loaded.
 	 */
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 	/* Get the top half of the MSR */

arch/powerpc/kernel/signal_64.c

diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 8d253c2..d501dc4 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -527,6 +527,8 @@
 	}
 #endif
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 

arch/powerpc/kernel/tm.S

diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index ef47bcbd..03567c0 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -307,7 +307,7 @@
 	 *	Call with IRQs off, stacks get all out of sync for
 	 *	some periods in here!
 	 */
-_GLOBAL(tm_recheckpoint)
+_GLOBAL(__tm_recheckpoint)
 	mfcr	r5
 	mflr	r0
 	stw	r5, 8(r1)