powerpc/book3s: Recover from MC in sapphire on SCOM read via MMIO.

Detect and recover from machine check when inside opal on a special
scom load instructions. On specific SCOM read via MMIO we may get a machine
check exception with SRR0 pointing inside opal. To recover from MC
in this scenario, get a recovery instruction address and return to it from
MC.

OPAL will export the machine check recoverable ranges through
device tree node mcheck-recoverable-ranges under ibm,opal:

# hexdump /proc/device-tree/ibm,opal/mcheck-recoverable-ranges
0000000 0000 0000 3000 2804 0000 000c 0000 0000
0000010 3000 2814 0000 0000 3000 27f0 0000 000c
0000020 0000 0000 3000 2814 xxxx xxxx xxxx xxxx
0000030 llll llll yyyy yyyy yyyy yyyy
...
...
#

where:
	xxxx xxxx xxxx xxxx = Starting instruction address
	llll llll           = Length of the address range.
	yyyy yyyy yyyy yyyy = recovery address

Each recoverable address range entry is (start address, len,
recovery address), 2 cells each for start and recovery address, 1 cell for
len, totalling 5 cells per entry. During kernel boot time, build up the
recovery table with the list of recovery ranges from device-tree node which
will be used during machine check exception to recover from MMIO SCOM UE.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

3 files changed, 8 insertions, 1 deletions

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index ad3025d0880b..4da6574e9a20 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -170,6 +170,9 @@ struct machdep_calls {
 	int		(*system_reset_exception)(struct pt_regs *regs);
 	int 		(*machine_check_exception)(struct pt_regs *regs);
 
+	/* Called during machine check exception to retrive fixup address. */
+	bool		(*mce_check_early_recovery)(struct pt_regs *regs);
+
 	/* Motherboard/chipset features. This is a kind of general purpose
 	 * hook used to control some machine specific features (like reset
 	 * lines, chip power control, etc...).
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 8e99edf6d966..f97d8cb6bdf6 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -187,7 +187,8 @@ struct mce_error_info {
 #define MCE_EVENT_DONTRELEASE	false
 
 extern void save_mce_event(struct pt_regs *regs, long handled,
-			   struct mce_error_info *mce_err, uint64_t addr);
+			   struct mce_error_info *mce_err, uint64_t nip,
+			   uint64_t addr);
 extern int get_mce_event(struct machine_check_event *mce, bool release);
 extern void release_mce_event(void);
 extern void machine_check_queue_event(void);
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index ed82142a3251..ad67c40c1a21 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -833,6 +833,8 @@ int64_t opal_sync_host_reboot(void);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
+extern int early_init_dt_scan_recoverable_ranges(unsigned long node,
+				 const char *uname, int depth, void *data);
 
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
@@ -863,6 +865,7 @@ extern void opal_nvram_init(void);
 extern void opal_flash_init(void);
 
 extern int opal_machine_check(struct pt_regs *regs);
+extern bool opal_mce_check_early_recovery(struct pt_regs *regs);
 
 extern void opal_shutdown(void);