[SPARC64]: Revamp Spitfire error trap handling.

Current uncorrectable error handling was poor enough
that the processor could just loop taking the same
trap over and over again.  Fix things up so that we
at least get a log message and perhaps even some register
state.

In the process, much consolidation became possible,
particularly with the correctable error handler.

Prefix assembler and C function names with "spitfire"
to indicate that these are for Ultra-I/II/IIi/IIe only.

More work is needed to make these routines robust and
featureful to the level of the Ultra-III error handlers.

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 145 insertions, 119 deletions

diff --git a/arch/sparc64/kernel/traps.c b/arch/sparc64/kernel/traps.c
index 210b3e321c29..b280b2ef674f 100644
--- a/arch/sparc64/kernel/traps.c
+++ b/arch/sparc64/kernel/traps.c
@@ -33,6 +33,7 @@
 #include <asm/dcu.h>
 #include <asm/estate.h>
 #include <asm/chafsr.h>
+#include <asm/sfafsr.h>
 #include <asm/psrcompat.h>
 #include <asm/processor.h>
 #include <asm/timer.h>
@@ -143,8 +144,7 @@ void do_BUG(const char *file, int line)
 }
 #endif
 
-void instruction_access_exception(struct pt_regs *regs,
-				  unsigned long sfsr, unsigned long sfar)
+void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
 {
 	siginfo_t info;
 
@@ -153,8 +153,8 @@ void instruction_access_exception(struct pt_regs *regs,
 		return;
 
 	if (regs->tstate & TSTATE_PRIV) {
-		printk("instruction_access_exception: SFSR[%016lx] SFAR[%016lx], going.\n",
-		       sfsr, sfar);
+		printk("spitfire_insn_access_exception: SFSR[%016lx] "
+		       "SFAR[%016lx], going.\n", sfsr, sfar);
 		die_if_kernel("Iax", regs);
 	}
 	if (test_thread_flag(TIF_32BIT)) {
@@ -169,19 +169,17 @@ void instruction_access_exception(struct pt_regs *regs,
 	force_sig_info(SIGSEGV, &info, current);
 }
 
-void instruction_access_exception_tl1(struct pt_regs *regs,
-				      unsigned long sfsr, unsigned long sfar)
+void spitfire_insn_access_exception_tl1(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
 {
 	if (notify_die(DIE_TRAP_TL1, "instruction access exception tl1", regs,
 		       0, 0x8, SIGTRAP) == NOTIFY_STOP)
 		return;
 
 	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	instruction_access_exception(regs, sfsr, sfar);
+	spitfire_insn_access_exception(regs, sfsr, sfar);
 }
 
-void data_access_exception(struct pt_regs *regs,
-			   unsigned long sfsr, unsigned long sfar)
+void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
 {
 	siginfo_t info;
 
@@ -207,8 +205,8 @@ void data_access_exception(struct pt_regs *regs,
 			return;
 		}
 		/* Shit... */
-		printk("data_access_exception: SFSR[%016lx] SFAR[%016lx], going.\n",
-		       sfsr, sfar);
+		printk("spitfire_data_access_exception: SFSR[%016lx] "
+		       "SFAR[%016lx], going.\n", sfsr, sfar);
 		die_if_kernel("Dax", regs);
 	}
 
@@ -220,15 +218,14 @@ void data_access_exception(struct pt_regs *regs,
 	force_sig_info(SIGSEGV, &info, current);
 }
 
-void data_access_exception_tl1(struct pt_regs *regs,
-			       unsigned long sfsr, unsigned long sfar)
+void spitfire_data_access_exception_tl1(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
 {
 	if (notify_die(DIE_TRAP_TL1, "data access exception tl1", regs,
 		       0, 0x30, SIGTRAP) == NOTIFY_STOP)
 		return;
 
 	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	data_access_exception(regs, sfsr, sfar);
+	spitfire_data_access_exception(regs, sfsr, sfar);
 }
 
 #ifdef CONFIG_PCI
@@ -264,54 +261,13 @@ static void spitfire_clean_and_reenable_l1_caches(void)
 			     : "memory");
 }
 
-void do_iae(struct pt_regs *regs)
+static void spitfire_enable_estate_errors(void)
 {
-	siginfo_t info;
-
-	spitfire_clean_and_reenable_l1_caches();
-
-	if (notify_die(DIE_TRAP, "instruction access exception", regs,
-		       0, 0x8, SIGTRAP) == NOTIFY_STOP)
-		return;
-
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_OBJERR;
-	info.si_addr = (void *)0;
-	info.si_trapno = 0;
-	force_sig_info(SIGBUS, &info, current);
-}
-
-void do_dae(struct pt_regs *regs)
-{
-	siginfo_t info;
-
-#ifdef CONFIG_PCI
-	if (pci_poke_in_progress && pci_poke_cpu == smp_processor_id()) {
-		spitfire_clean_and_reenable_l1_caches();
-
-		pci_poke_faulted = 1;
-
-		/* Why the fuck did they have to change this? */
-		if (tlb_type == cheetah || tlb_type == cheetah_plus)
-			regs->tpc += 4;
-
-		regs->tnpc = regs->tpc + 4;
-		return;
-	}
-#endif
-	spitfire_clean_and_reenable_l1_caches();
-
-	if (notify_die(DIE_TRAP, "data access exception", regs,
-		       0, 0x30, SIGTRAP) == NOTIFY_STOP)
-		return;
-
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_OBJERR;
-	info.si_addr = (void *)0;
-	info.si_trapno = 0;
-	force_sig_info(SIGBUS, &info, current);
+	__asm__ __volatile__("stxa	%0, [%%g0] %1\n\t"
+			     "membar	#Sync"
+			     : /* no outputs */
+			     : "r" (ESTATE_ERR_ALL),
+			       "i" (ASI_ESTATE_ERROR_EN));
 }
 
 static char ecc_syndrome_table[] = {
@@ -349,65 +305,15 @@ static char ecc_syndrome_table[] = {
 	0x0b, 0x48, 0x48, 0x4b, 0x48, 0x4b, 0x4b, 0x4a
 };
 
-/* cee_trap in entry.S encodes AFSR/UDBH/UDBL error status
- * in the following format.  The AFAR is left as is, with
- * reserved bits cleared, and is a raw 40-bit physical
- * address.
- */
-#define CE_STATUS_UDBH_UE		(1UL << (43 + 9))
-#define CE_STATUS_UDBH_CE		(1UL << (43 + 8))
-#define CE_STATUS_UDBH_ESYNDR		(0xffUL << 43)
-#define CE_STATUS_UDBH_SHIFT		43
-#define CE_STATUS_UDBL_UE		(1UL << (33 + 9))
-#define CE_STATUS_UDBL_CE		(1UL << (33 + 8))
-#define CE_STATUS_UDBL_ESYNDR		(0xffUL << 33)
-#define CE_STATUS_UDBL_SHIFT		33
-#define CE_STATUS_AFSR_MASK		(0x1ffffffffUL)
-#define CE_STATUS_AFSR_ME		(1UL << 32)
-#define CE_STATUS_AFSR_PRIV		(1UL << 31)
-#define CE_STATUS_AFSR_ISAP		(1UL << 30)
-#define CE_STATUS_AFSR_ETP		(1UL << 29)
-#define CE_STATUS_AFSR_IVUE		(1UL << 28)
-#define CE_STATUS_AFSR_TO		(1UL << 27)
-#define CE_STATUS_AFSR_BERR		(1UL << 26)
-#define CE_STATUS_AFSR_LDP		(1UL << 25)
-#define CE_STATUS_AFSR_CP		(1UL << 24)
-#define CE_STATUS_AFSR_WP		(1UL << 23)
-#define CE_STATUS_AFSR_EDP		(1UL << 22)
-#define CE_STATUS_AFSR_UE		(1UL << 21)
-#define CE_STATUS_AFSR_CE		(1UL << 20)
-#define CE_STATUS_AFSR_ETS		(0xfUL << 16)
-#define CE_STATUS_AFSR_ETS_SHIFT	16
-#define CE_STATUS_AFSR_PSYND		(0xffffUL << 0)
-#define CE_STATUS_AFSR_PSYND_SHIFT	0
-
-/* Layout of Ecache TAG Parity Syndrome of AFSR */
-#define AFSR_ETSYNDROME_7_0		0x1UL /* E$-tag bus bits  <7:0> */
-#define AFSR_ETSYNDROME_15_8		0x2UL /* E$-tag bus bits <15:8> */
-#define AFSR_ETSYNDROME_21_16		0x4UL /* E$-tag bus bits <21:16> */
-#define AFSR_ETSYNDROME_24_22		0x8UL /* E$-tag bus bits <24:22> */
-
 static char *syndrome_unknown = "<Unknown>";
 
-asmlinkage void cee_log(unsigned long ce_status,
-			unsigned long afar,
-			struct pt_regs *regs)
+static void spitfire_log_udb_syndrome(unsigned long afar, unsigned long udbh, unsigned long udbl, unsigned long bit)
 {
-	char memmod_str[64];
-	char *p;
-	unsigned short scode, udb_reg;
+	unsigned short scode;
+	char memmod_str[64], *p;
 
-	printk(KERN_WARNING "CPU[%d]: Correctable ECC Error "
-	       "AFSR[%lx] AFAR[%016lx] UDBL[%lx] UDBH[%lx]\n",
-	       smp_processor_id(),
-	       (ce_status & CE_STATUS_AFSR_MASK),
-	       afar,
-	       ((ce_status >> CE_STATUS_UDBL_SHIFT) & 0x3ffUL),
-	       ((ce_status >> CE_STATUS_UDBH_SHIFT) & 0x3ffUL));
-
-	udb_reg = ((ce_status >> CE_STATUS_UDBL_SHIFT) & 0x3ffUL);
-	if (udb_reg & (1 << 8)) {
-		scode = ecc_syndrome_table[udb_reg & 0xff];
+	if (udbl & bit) {
+		scode = ecc_syndrome_table[udbl & 0xff];
 		if (prom_getunumber(scode, afar,
 				    memmod_str, sizeof(memmod_str)) == -1)
 			p = syndrome_unknown;
@@ -418,9 +324,8 @@ asmlinkage void cee_log(unsigned long ce_status,
 		       smp_processor_id(), scode, p);
 	}
 
-	udb_reg = ((ce_status >> CE_STATUS_UDBH_SHIFT) & 0x3ffUL);
-	if (udb_reg & (1 << 8)) {
-		scode = ecc_syndrome_table[udb_reg & 0xff];
+	if (udbh & bit) {
+		scode = ecc_syndrome_table[udbh & 0xff];
 		if (prom_getunumber(scode, afar,
 				    memmod_str, sizeof(memmod_str)) == -1)
 			p = syndrome_unknown;
@@ -430,6 +335,127 @@ asmlinkage void cee_log(unsigned long ce_status,
 		       "Memory Module \"%s\"\n",
 		       smp_processor_id(), scode, p);
 	}
+
+}
+
+static void spitfire_cee_log(unsigned long afsr, unsigned long afar, unsigned long udbh, unsigned long udbl, int tl1, struct pt_regs *regs)
+{
+
+	printk(KERN_WARNING "CPU[%d]: Correctable ECC Error "
+	       "AFSR[%lx] AFAR[%016lx] UDBL[%lx] UDBH[%lx] TL>1[%d]\n",
+	       smp_processor_id(), afsr, afar, udbl, udbh, tl1);
+
+	spitfire_log_udb_syndrome(afar, udbh, udbl, UDBE_CE);
+
+	/* We always log it, even if someone is listening for this
+	 * trap.
+	 */
+	notify_die(DIE_TRAP, "Correctable ECC Error", regs,
+		   0, TRAP_TYPE_CEE, SIGTRAP);
+
+	/* The Correctable ECC Error trap does not disable I/D caches.  So
+	 * we only have to restore the ESTATE Error Enable register.
+	 */
+	spitfire_enable_estate_errors();
+}
+
+static void spitfire_ue_log(unsigned long afsr, unsigned long afar, unsigned long udbh, unsigned long udbl, unsigned long tt, int tl1, struct pt_regs *regs)
+{
+	siginfo_t info;
+
+	printk(KERN_WARNING "CPU[%d]: Uncorrectable Error AFSR[%lx] "
+	       "AFAR[%lx] UDBL[%lx] UDBH[%ld] TT[%lx] TL>1[%d]\n",
+	       smp_processor_id(), afsr, afar, udbl, udbh, tt, tl1);
+
+	/* XXX add more human friendly logging of the error status
+	 * XXX as is implemented for cheetah
+	 */
+
+	spitfire_log_udb_syndrome(afar, udbh, udbl, UDBE_UE);
+
+	/* We always log it, even if someone is listening for this
+	 * trap.
+	 */
+	notify_die(DIE_TRAP, "Uncorrectable Error", regs,
+		   0, tt, SIGTRAP);
+
+	if (regs->tstate & TSTATE_PRIV) {
+		if (tl1)
+			dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+		die_if_kernel("UE", regs);
+	}
+
+	/* XXX need more intelligent processing here, such as is implemented
+	 * XXX for cheetah errors, in fact if the E-cache still holds the
+	 * XXX line with bad parity this will loop
+	 */
+
+	spitfire_clean_and_reenable_l1_caches();
+	spitfire_enable_estate_errors();
+
+	if (test_thread_flag(TIF_32BIT)) {
+		regs->tpc &= 0xffffffff;
+		regs->tnpc &= 0xffffffff;
+	}
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code = BUS_OBJERR;
+	info.si_addr = (void *)0;
+	info.si_trapno = 0;
+	force_sig_info(SIGBUS, &info, current);
+}
+
+void spitfire_access_error(struct pt_regs *regs, unsigned long status_encoded, unsigned long afar)
+{
+	unsigned long afsr, tt, udbh, udbl;
+	int tl1;
+
+	afsr = (status_encoded & SFSTAT_AFSR_MASK) >> SFSTAT_AFSR_SHIFT;
+	tt = (status_encoded & SFSTAT_TRAP_TYPE) >> SFSTAT_TRAP_TYPE_SHIFT;
+	tl1 = (status_encoded & SFSTAT_TL_GT_ONE) ? 1 : 0;
+	udbl = (status_encoded & SFSTAT_UDBL_MASK) >> SFSTAT_UDBL_SHIFT;
+	udbh = (status_encoded & SFSTAT_UDBH_MASK) >> SFSTAT_UDBH_SHIFT;
+
+#ifdef CONFIG_PCI
+	if (tt == TRAP_TYPE_DAE &&
+	    pci_poke_in_progress && pci_poke_cpu == smp_processor_id()) {
+		spitfire_clean_and_reenable_l1_caches();
+		spitfire_enable_estate_errors();
+
+		pci_poke_faulted = 1;
+		regs->tnpc = regs->tpc + 4;
+		return;
+	}
+#endif
+
+	if (afsr & SFAFSR_UE)
+		spitfire_ue_log(afsr, afar, udbh, udbl, tt, tl1, regs);
+
+	if (tt == TRAP_TYPE_CEE) {
+		/* Handle the case where we took a CEE trap, but ACK'd
+		 * only the UE state in the UDB error registers.
+		 */
+		if (afsr & SFAFSR_UE) {
+			if (udbh & UDBE_CE) {
+				__asm__ __volatile__(
+					"stxa	%0, [%1] %2\n\t"
+					"membar	#Sync"
+					: /* no outputs */
+					: "r" (udbh & UDBE_CE),
+					  "r" (0x0), "i" (ASI_UDB_ERROR_W));
+			}
+			if (udbl & UDBE_CE) {
+				__asm__ __volatile__(
+					"stxa	%0, [%1] %2\n\t"
+					"membar	#Sync"
+					: /* no outputs */
+					: "r" (udbl & UDBE_CE),
+					  "r" (0x18), "i" (ASI_UDB_ERROR_W));
+			}
+		}
+
+		spitfire_cee_log(afsr, afar, udbh, udbl, tl1, regs);
+	}
 }
 
 int cheetah_pcache_forced_on;