traps.c

linux-2.4.29操作系统的源码

	printk("%s" "ERROR(%d): D-cache idx[%x] tag[%016lx] utag[%016lx] stag[%016lx]\n",
	       (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(),
	       (int) info->dcache_index,
	       info->dcache_tag,
	       info->dcache_utag,
	       info->dcache_stag);
	printk("%s" "ERROR(%d): D-cache data0[%016lx] data1[%016lx] data2[%016lx] data3[%016lx]\n",
	       (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(),
	       info->dcache_data[0],
	       info->dcache_data[1],
	       info->dcache_data[2],
	       info->dcache_data[3]);
	printk("%s" "ERROR(%d): I-cache idx[%x] tag[%016lx] utag[%016lx] stag[%016lx] "
	       "u[%016lx] l[%016lx]\n",
	       (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(),
	       (int) info->icache_index,
	       info->icache_tag,
	       info->icache_utag,
	       info->icache_stag,
	       info->icache_upper,
	       info->icache_lower);
	printk("%s" "ERROR(%d): I-cache INSN0[%016lx] INSN1[%016lx] INSN2[%016lx] INSN3[%016lx]\n",
	       (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(),
	       info->icache_data[0],
	       info->icache_data[1],
	       info->icache_data[2],
	       info->icache_data[3]);
	printk("%s" "ERROR(%d): I-cache INSN4[%016lx] INSN5[%016lx] INSN6[%016lx] INSN7[%016lx]\n",
	       (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(),
	       info->icache_data[4],
	       info->icache_data[5],
	       info->icache_data[6],
	       info->icache_data[7]);
	printk("%s" "ERROR(%d): E-cache idx[%x] tag[%016lx]\n",
	       (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(),
	       (int) info->ecache_index, info->ecache_tag);
	printk("%s" "ERROR(%d): E-cache data0[%016lx] data1[%016lx] data2[%016lx] data3[%016lx]\n",
	       (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(),
	       info->ecache_data[0],
	       info->ecache_data[1],
	       info->ecache_data[2],
	       info->ecache_data[3]);

	afsr = (afsr & ~hipri) & cheetah_afsr_errors;
	while (afsr != 0UL) {
		unsigned long bit = cheetah_get_hipri(afsr);

		printk("%s" "ERROR: Multiple-error (%016lx) \"%s\"\n",
		       (recoverable ? KERN_WARNING : KERN_CRIT),
		       bit, cheetah_get_string(bit));

		afsr &= ~bit;
	}

	if (!recoverable)
		printk(KERN_CRIT "ERROR: This condition is not recoverable.\n");
}

static int cheetah_recheck_errors(struct cheetah_err_info *logp)
{
	unsigned long afsr, afar;
	int ret = 0;

	__asm__ __volatile__("ldxa [%%g0] %1, %0\n\t"
			     : "=r" (afsr)
			     : "i" (ASI_AFSR));
	if ((afsr & cheetah_afsr_errors) != 0) {
		if (logp != NULL) {
			__asm__ __volatile__("ldxa [%%g0] %1, %0\n\t"
					     : "=r" (afar)
					     : "i" (ASI_AFAR));
			logp->afsr = afsr;
			logp->afar = afar;
		}
		ret = 1;
	}
	__asm__ __volatile__("stxa %0, [%%g0] %1\n\t"
			     "membar #Sync\n\t"
			     : : "r" (afsr), "i" (ASI_AFSR));

	return ret;
}

void cheetah_fecc_handler(struct pt_regs *regs, unsigned long afsr, unsigned long afar)
{
	struct cheetah_err_info local_snapshot, *p;
	int recoverable;

	/* Flush E-cache */
	cheetah_flush_ecache();

	p = cheetah_get_error_log(afsr);
	if (!p) {
		prom_printf("ERROR: Early Fast-ECC error afsr[%016lx] afar[%016lx]\n",
			    afsr, afar);
		prom_printf("ERROR: CPU(%d) TPC[%016lx] TNPC[%016lx] TSTATE[%016lx]\n",
			    smp_processor_id(), regs->tpc, regs->tnpc, regs->tstate);
		prom_halt();
	}

	/* Grab snapshot of logged error. */
	memcpy(&local_snapshot, p, sizeof(local_snapshot));

	/* If the current trap snapshot does not match what the
	 * trap handler passed along into our args, big trouble.
	 * In such a case, mark the local copy as invalid.
	 *
	 * Else, it matches and we mark the afsr in the non-local
	 * copy as invalid so we may log new error traps there.
	 */
	if (p->afsr != afsr || p->afar != afar)
		local_snapshot.afsr = CHAFSR_INVALID;
	else
		p->afsr = CHAFSR_INVALID;

	cheetah_flush_icache();
	cheetah_flush_dcache();

	/* Re-enable I-cache/D-cache */
	__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
			     "or %%g1, %1, %%g1\n\t"
			     "stxa %%g1, [%%g0] %0\n\t"
			     "membar #Sync"
			     : /* no outputs */
			     : "i" (ASI_DCU_CONTROL_REG),
			       "i" (DCU_DC | DCU_IC)
			     : "g1");

	/* Re-enable error reporting */
	__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
			     "or %%g1, %1, %%g1\n\t"
			     "stxa %%g1, [%%g0] %0\n\t"
			     "membar #Sync"
			     : /* no outputs */
			     : "i" (ASI_ESTATE_ERROR_EN),
			       "i" (ESTATE_ERROR_NCEEN | ESTATE_ERROR_CEEN)
			     : "g1");

	/* Decide if we can continue after handling this trap and
	 * logging the error.
	 */
	recoverable = 1;
	if (afsr & (CHAFSR_PERR | CHAFSR_IERR | CHAFSR_ISAP))
		recoverable = 0;

	/* Re-check AFSR/AFAR.  What we are looking for here is whether a new
	 * error was logged while we had error reporting traps disabled.
	 */
	if (cheetah_recheck_errors(&local_snapshot)) {
		unsigned long new_afsr = local_snapshot.afsr;

		/* If we got a new asynchronous error, die... */
		if (new_afsr & (CHAFSR_EMU | CHAFSR_EDU |
				CHAFSR_WDU | CHAFSR_CPU |
				CHAFSR_IVU | CHAFSR_UE |
				CHAFSR_BERR | CHAFSR_TO))
			recoverable = 0;
	}

	/* Log errors. */
	cheetah_log_errors(regs, &local_snapshot, afsr, afar, recoverable);

	if (!recoverable)
		panic("Irrecoverable Fast-ECC error trap.\n");

	/* Flush E-cache to kick the error trap handlers out. */
	cheetah_flush_ecache();
}

/* Try to fix a correctable error by pushing the line out from
 * the E-cache.  Recheck error reporting registers to see if the
 * problem is intermittent.
 */
static int cheetah_fix_ce(unsigned long physaddr)
{
	unsigned long orig_estate;
	unsigned long alias1, alias2;
	int ret;

	/* Make sure correctable error traps are disabled. */
	__asm__ __volatile__("ldxa	[%%g0] %2, %0\n\t"
			     "andn	%0, %1, %%g1\n\t"
			     "stxa	%%g1, [%%g0] %2\n\t"
			     "membar	#Sync"
			     : "=&r" (orig_estate)
			     : "i" (ESTATE_ERROR_CEEN),
			       "i" (ASI_ESTATE_ERROR_EN)
			     : "g1");

	/* We calculate alias addresses that will force the
	 * cache line in question out of the E-cache.  Then
	 * we bring it back in with an atomic instruction so
	 * that we get it in some modified/exclusive state,
	 * then we displace it again to try and get proper ECC
	 * pushed back into the system.
	 */
	physaddr &= ~(8UL - 1UL);
	alias1 = (ecache_flush_physbase +
		  (physaddr & ((ecache_flush_size >> 1) - 1)));
	alias2 = alias1 + (ecache_flush_size >> 1);
	__asm__ __volatile__("ldxa	[%0] %3, %%g0\n\t"
			     "ldxa	[%1] %3, %%g0\n\t"
			     "casxa	[%2] %3, %%g0, %%g0\n\t"
			     "membar	#StoreLoad | #StoreStore\n\t"
			     "ldxa	[%0] %3, %%g0\n\t"
			     "ldxa	[%1] %3, %%g0\n\t"
			     "membar	#Sync"
			     : /* no outputs */
			     : "r" (alias1), "r" (alias2),
			       "r" (physaddr), "i" (ASI_PHYS_USE_EC));

	/* Did that trigger another error? */
	if (cheetah_recheck_errors(NULL)) {
		/* Try one more time. */
		__asm__ __volatile__("ldxa [%0] %1, %%g0\n\t"
				     "membar #Sync"
				     : : "r" (physaddr), "i" (ASI_PHYS_USE_EC));
		if (cheetah_recheck_errors(NULL))
			ret = 2;
		else
			ret = 1;
	} else {
		/* No new error, intermittent problem. */
		ret = 0;
	}

	/* Restore error enables. */
	__asm__ __volatile__("stxa	%0, [%%g0] %1\n\t"
			     "membar	#Sync"
			     : : "r" (orig_estate), "i" (ASI_ESTATE_ERROR_EN));

	return ret;
}

/* Return non-zero if PADDR is a valid physical memory address. */
static int cheetah_check_main_memory(unsigned long paddr)
{
	int i;

	for (i = 0; ; i++) {
		if (sp_banks[i].num_bytes == 0)
			break;
		if (paddr >= sp_banks[i].base_addr &&
		    paddr < (sp_banks[i].base_addr + sp_banks[i].num_bytes))
			return 1;
	}
	return 0;
}

void cheetah_cee_handler(struct pt_regs *regs, unsigned long afsr, unsigned long afar)
{
	struct cheetah_err_info local_snapshot, *p;
	int recoverable, is_memory;

	p = cheetah_get_error_log(afsr);
	if (!p) {
		prom_printf("ERROR: Early CEE error afsr[%016lx] afar[%016lx]\n",
			    afsr, afar);
		prom_printf("ERROR: CPU(%d) TPC[%016lx] TNPC[%016lx] TSTATE[%016lx]\n",
			    smp_processor_id(), regs->tpc, regs->tnpc, regs->tstate);
		prom_halt();
	}

	/* Grab snapshot of logged error. */
	memcpy(&local_snapshot, p, sizeof(local_snapshot));

	/* If the current trap snapshot does not match what the
	 * trap handler passed along into our args, big trouble.
	 * In such a case, mark the local copy as invalid.
	 *
	 * Else, it matches and we mark the afsr in the non-local
	 * copy as invalid so we may log new error traps there.
	 */
	if (p->afsr != afsr || p->afar != afar)
		local_snapshot.afsr = CHAFSR_INVALID;
	else
		p->afsr = CHAFSR_INVALID;

	is_memory = cheetah_check_main_memory(afar);

	if (is_memory && (afsr & CHAFSR_CE) != 0UL) {
		/* XXX Might want to log the results of this operation
		 * XXX somewhere... -DaveM
		 */
		cheetah_fix_ce(afar);
	}

	{
		int flush_all, flush_line;

		flush_all = flush_line = 0;
		if ((afsr & CHAFSR_EDC) != 0UL) {
			if ((afsr & cheetah_afsr_errors) == CHAFSR_EDC)
				flush_line = 1;
			else
				flush_all = 1;
		} else if ((afsr & CHAFSR_CPC) != 0UL) {
			if ((afsr & cheetah_afsr_errors) == CHAFSR_CPC)
				flush_line = 1;
			else
				flush_all = 1;
		}

		/* Trap handler only disabled I-cache, flush it. */
		cheetah_flush_icache();

		/* Re-enable I-cache */
		__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
				     "or %%g1, %1, %%g1\n\t"
				     "stxa %%g1, [%%g0] %0\n\t"
				     "membar #Sync"
				     : /* no outputs */
				     : "i" (ASI_DCU_CONTROL_REG),
				     "i" (DCU_IC)
				     : "g1");

		if (flush_all)
			cheetah_flush_ecache();
		else if (flush_line)
			cheetah_flush_ecache_line(afar);
	}

	/* Re-enable error reporting */
	__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
			     "or %%g1, %1, %%g1\n\t"
			     "stxa %%g1, [%%g0] %0\n\t"
			     "membar #Sync"
			     : /* no outputs */
			     : "i" (ASI_ESTATE_ERROR_EN),
			       "i" (ESTATE_ERROR_CEEN)
			     : "g1");

	/* Decide if we can continue after handling this trap and
	 * logging the error.
	 */
	recoverable = 1;
	if (afsr & (CHAFSR_PERR | CHAFSR_IERR | CHAFSR_ISAP))
		recoverable = 0;

	/* Re-check AFSR/AFAR */
	(void) cheetah_recheck_errors(&local_snapshot);

	/* Log errors. */
	cheetah_log_errors(regs, &local_snapshot, afsr, afar, recoverable);

	if (!recoverable)
		panic("Irrecoverable Correctable-ECC error trap.\n");
}

void cheetah_deferred_handler(struct pt_regs *regs, unsigned long afsr, unsigned long afar)
{
	struct cheetah_err_info local_snapshot, *p;
	int recoverable, is_memory;

#ifdef CONFIG_PCI
	/* Check for the special PCI poke sequence. */
	if (pci_poke_in_progress && pci_poke_cpu == smp_processor_id()) {
		cheetah_flush_icache();
		cheetah_flush_dcache();

		/* Re-enable I-cache/D-cache */
		__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
				     "or %%g1, %1, %%g1\n\t"
				     "stxa %%g1, [%%g0] %0\n\t"
				     "membar #Sync"
				     : /* no outputs */
				     : "i" (ASI_DCU_CONTROL_REG),
				       "i" (DCU_DC | DCU_IC)
				     : "g1");

		/* Re-enable error reporting */
		__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
				     "or %%g1, %1, %%g1\n\t"
				     "stxa %%g1, [%%g0] %0\n\t"
				     "membar #Sync"
				     : /* no outputs */
				     : "i" (ASI_ESTATE_ERROR_EN),
				       "i" (ESTATE_ERROR_NCEEN | ESTATE_ERROR_CEEN)
				     : "g1");

		(void) cheetah_recheck_errors(NULL);

		pci_poke_faulted = 1;
		regs->tpc += 4;
		regs->tnpc = regs->tpc + 4;
		return;
	}
#endif

	p = cheetah_get_error_log(afsr);
	if (!p) {
		prom_printf("ERROR: Early deferred error afsr[%016lx] afar[%016lx]\n",
			    afsr, afar);
		prom_printf("ERROR: CPU(%d) TPC[%016lx] TNPC[%016lx] TSTATE[%016lx]\n",
			    smp_processor_id(), regs->tpc, regs->tnpc, regs->tstate);
		prom_halt();
	}

	/* Grab snapshot of logged error. */
	memcpy(&local_snapshot, p, sizeof(local_snapshot));

	/* If the current trap snapshot does not match what the
	 * trap handler passed along into our args, big trouble.
	 * In such a case, mark the local copy as invalid.
	 *
	 * Else, it matches and we mark the afsr in the non-local
	 * copy as invalid so we may log new error traps there.
	 */
	if (p->afsr != afsr || p->afar != afar)
		local_snapshot.afsr = CHAFSR_INVALID;
	else
		p->afsr = CHAFSR_INVALID;

	is_memory = cheetah_check_main_memory(afar);

	{
		int flush_all, flush_line;

		flush_all = flush_line = 0;
		if ((afsr & CHAFSR_EDU) != 0UL) {
			if ((afsr & cheetah_afsr_errors) == CHAFSR_EDU)
				flush_line = 1;
			else
				flush_all = 1;
		} else if ((afsr & CHAFSR_BERR) != 0UL) {
			if ((afsr & cheetah_afsr_errors) == CHAFSR_BERR)
				flush_line = 1;
			else
				flush_all = 1;
		}

		cheetah_flush_icache();
		cheetah_flush_dcache();

		/* Re-enable I/D caches */
		__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
				     "or %%g1, %1, %%g1\n\t"
				     "stxa %%g1, [%%g0] %0\n\t"
				     "membar #Sync"
				     : /* no outputs */
				     : "i" (ASI_DCU_CONTROL_REG),
				     "i" (DCU_IC | DCU_DC)
				     : "g1");

		if (flush_all)
			cheetah_flush_ecache();
		else if (flush_line)
			cheetah_flush_ecache_line(afar);
	}

	/* Re-enable error reporting */
	__asm__ __volatile__("ldxa [%%g0] %0, %%g1\n\t"
			     "or %%g1, %1, %%g1\n\t"
			     "stxa %%g1, [%%g0] %0\n\t"
			     "membar #Sync"
			     : /* no outputs */
			     : "i" (ASI_ESTATE_ERROR_EN),
			     "i" (ESTATE_ERROR_NCEEN | ESTATE_ERROR_CEEN)
			     : "g1");

	/* Decide if we can continue after handling this trap and
	 * logging the error.
	 */
	recoverable = 1;
	if (afsr & (CHAFSR_PERR | CHAFSR_IERR | CHAFSR_ISAP))
		recoverable = 0;

	/* Re-check AFSR/AFAR.  What we are looking for here is whether a new
	 * error was logged while we had error reporting traps disabled.
	 */
	if (cheetah_recheck_errors(&local_snapshot)) {
		unsigned long new_afsr = local_snapshot.afsr;

		/* If we got a new asynchronous error, die... */
		if (new_afsr & (CHAFSR_EMU | CHAFSR_EDU |
				CHAFSR_WDU | CHAFSR_CPU |
				CHAFSR_IVU | CHAFSR_UE |
				CHAFSR_BERR | CHAFSR_TO))
			recoverable = 0;
	}

	/* Log errors. */
	cheetah_log_errors(regs, &local_snapshot, afsr, afar, recoverable);

	/* "Recoverable" here means we try to yank the page from ever
	 * being newly used again.  This depends upon a few things:
	 * 1) Must be main memory, and AFAR must be valid.
	 * 2) If we trapped from use, OK.
	 * 3) Else, if we trapped from kernel we must find exception
	 *    table entry (ie. we have to have been accessing user
	 *    space).
	 *
	 * If AFAR is not in main memory, or we trapped from kernel
	 * and cannot find an exception table entry, it is unacceptable
	 * to try and continue.