[PATCH] powerpc/32e: Ignore ESR in instruction storage interrupt handler

[Nicholas Piggin <npiggin@gmail.com>]

A e5500 machine running a 32-bit kernel sometimes hangs at boot,
seemingly going into an infinite loop of instruction storage interrupts.
The ESR SPR has a value of 0x800000 (store) when this happens, which is
likely set by a previous store. An instruction TLB miss interrupt would
then leave ESR unchanged, and if no PTE exists it calls directly to the
instruction storage interrupt handler without changing ESR.

access_error() does not cause a segfault due to a store to a read-only
vma because is_exec is true. Most subsequent fault handling does not
check for a write fault on a read-only vma, and might do strange things
like create a writeable PTE or call page_mkwrite on a read only vma or
file. It's not clear what happens here to cause the infinite faulting in
this case, a fault handler failure or low level PTE or TLB handling.

In any case this can be fixed by having the instruction storage
interrupt zero regs->dsisr rather than storing the ESR value to it.

Link: https://lore.kernel.org/linuxppc-dev/1635306738.0z8wt7619v.astroid@bobo.none/
Fixes: a01a3f2ddbcd ("powerpc: remove arguments from fault handler functions")
Reported-by: Jacques de Laval <jacques.delaval@protonmail.com>
Tested-by: Jacques de Laval <jacques.delaval@protonmail.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/head_booke.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index e5503420b6c6..ef8d1b1c234e 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -465,12 +465,21 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	bl	do_page_fault;						      \
 	b	interrupt_return
 
+/*
+ * Instruction TLB Error interrupt handlers may call InstructionStorage
+ * directly without clearing ESR, so the ESR at this point may be left over
+ * from a prior interrupt.
+ *
+ * In any case, do_page_fault for BOOK3E does not use ESR and always expects
+ * dsisr to be 0. ESR_DST from a prior store in particular would confuse fault
+ * handling.
+ */
 #define INSTRUCTION_STORAGE_EXCEPTION					      \
 	START_EXCEPTION(InstructionStorage)				      \
-	NORMAL_EXCEPTION_PROLOG(0x400, INST_STORAGE);		      \
-	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
+	NORMAL_EXCEPTION_PROLOG(0x400, INST_STORAGE);			      \
+	li	r5,0;			/* Store 0 in regs->esr (dsisr) */    \
 	stw	r5,_ESR(r11);						      \
-	stw	r12, _DEAR(r11);	/* Pass SRR0 as arg2 */		      \
+	stw	r12, _DEAR(r11);	/* Set regs->dear (dar) to SRR0 */    \
 	prepare_transfer_to_handler;					      \
 	bl	do_page_fault;						      \
 	b	interrupt_return
-- 
2.23.0