traps.c

linux-2.6.15.6

/* $Id: traps.c,v 1.85 2002/02/09 19:49:31 davem Exp $
 * arch/sparc64/kernel/traps.c
 *
 * Copyright (C) 1995,1997 David S. Miller ([e-mail])
 * Copyright (C) 1997,1999,2000 Jakub Jelinek ([e-mail])
 */

/*
 * I like traps on v9, :))))
 */

#include <linux/config.h>
#include <linux/module.h>
#include <linux/sched.h>  /* for jiffies */
#include <linux/kernel.h>
#include <linux/kallsyms.h>
#include <linux/signal.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/mm.h>
#include <linux/init.h>

#include <asm/delay.h>
#include <asm/system.h>
#include <asm/ptrace.h>
#include <asm/oplib.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/unistd.h>
#include <asm/uaccess.h>
#include <asm/fpumacro.h>
#include <asm/lsu.h>
#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>
#include <asm/kdebug.h>
#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif

struct notifier_block *sparc64die_chain;
static DEFINE_SPINLOCK(die_notifier_lock);

int register_die_notifier(struct notifier_block *nb)
{
	int err = 0;
	unsigned long flags;
	spin_lock_irqsave(&die_notifier_lock, flags);
	err = notifier_chain_register(&sparc64die_chain, nb);
	spin_unlock_irqrestore(&die_notifier_lock, flags);
	return err;
}

/* When an irrecoverable trap occurs at tl > 0, the trap entry
 * code logs the trap state registers at every level in the trap
 * stack.  It is found at (pt_regs + sizeof(pt_regs)) and the layout
 * is as follows:
 */
struct tl1_traplog {
	struct {
		unsigned long tstate;
		unsigned long tpc;
		unsigned long tnpc;
		unsigned long tt;
	} trapstack[4];
	unsigned long tl;
};

static void dump_tl1_traplog(struct tl1_traplog *p)
{
	int i;

	printk("TRAPLOG: Error at trap level 0x%lx, dumping track stack.\n",
	       p->tl);
	for (i = 0; i < 4; i++) {
		printk(KERN_CRIT
		       "TRAPLOG: Trap level %d TSTATE[%016lx] TPC[%016lx] "
		       "TNPC[%016lx] TT[%lx]\n",
		       i + 1,
		       p->trapstack[i].tstate, p->trapstack[i].tpc,
		       p->trapstack[i].tnpc, p->trapstack[i].tt);
	}
}

void do_call_debug(struct pt_regs *regs) 
{ 
	notify_die(DIE_CALL, "debug call", regs, 0, 255, SIGINT); 
}

void bad_trap(struct pt_regs *regs, long lvl)
{
	char buffer[32];
	siginfo_t info;

	if (notify_die(DIE_TRAP, "bad trap", regs,
		       0, lvl, SIGTRAP) == NOTIFY_STOP)
		return;

	if (lvl < 0x100) {
		sprintf(buffer, "Bad hw trap %lx at tl0\n", lvl);
		die_if_kernel(buffer, regs);
	}

	lvl -= 0x100;
	if (regs->tstate & TSTATE_PRIV) {
		sprintf(buffer, "Kernel bad sw trap %lx", lvl);
		die_if_kernel(buffer, regs);
	}
	if (test_thread_flag(TIF_32BIT)) {
		regs->tpc &= 0xffffffff;
		regs->tnpc &= 0xffffffff;
	}
	info.si_signo = SIGILL;
	info.si_errno = 0;
	info.si_code = ILL_ILLTRP;
	info.si_addr = (void __user *)regs->tpc;
	info.si_trapno = lvl;
	force_sig_info(SIGILL, &info, current);
}

void bad_trap_tl1(struct pt_regs *regs, long lvl)
{
	char buffer[32];
	
	if (notify_die(DIE_TRAP_TL1, "bad trap tl1", regs,
		       0, lvl, SIGTRAP) == NOTIFY_STOP)
		return;

	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));

	sprintf (buffer, "Bad trap %lx at tl>0", lvl);
	die_if_kernel (buffer, regs);
}

#ifdef CONFIG_DEBUG_BUGVERBOSE
void do_BUG(const char *file, int line)
{
	bust_spinlocks(1);
	printk("kernel BUG at %s:%d!\n", file, line);
}
#endif

void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
{
	siginfo_t info;

	if (notify_die(DIE_TRAP, "instruction access exception", regs,
		       0, 0x8, SIGTRAP) == NOTIFY_STOP)
		return;

	if (regs->tstate & TSTATE_PRIV) {
		printk("spitfire_insn_access_exception: SFSR[%016lx] "
		       "SFAR[%016lx], going.\n", sfsr, sfar);
		die_if_kernel("Iax", regs);
	}
	if (test_thread_flag(TIF_32BIT)) {
		regs->tpc &= 0xffffffff;
		regs->tnpc &= 0xffffffff;
	}
	info.si_signo = SIGSEGV;
	info.si_errno = 0;
	info.si_code = SEGV_MAPERR;
	info.si_addr = (void __user *)regs->tpc;
	info.si_trapno = 0;
	force_sig_info(SIGSEGV, &info, current);
}

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));
	spitfire_insn_access_exception(regs, sfsr, sfar);
}

void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
{
	siginfo_t info;

	if (notify_die(DIE_TRAP, "data access exception", regs,
		       0, 0x30, SIGTRAP) == NOTIFY_STOP)
		return;

	if (regs->tstate & TSTATE_PRIV) {
		/* Test if this comes from uaccess places. */
		const struct exception_table_entry *entry;

		entry = search_exception_tables(regs->tpc);
		if (entry) {
			/* Ouch, somebody is trying VM hole tricks on us... */
#ifdef DEBUG_EXCEPTIONS
			printk("Exception: PC<%016lx> faddr<UNKNOWN>\n", regs->tpc);
			printk("EX_TABLE: insn<%016lx> fixup<%016lx>\n",
			       regs->tpc, entry->fixup);
#endif
			regs->tpc = entry->fixup;
			regs->tnpc = regs->tpc + 4;
			return;
		}
		/* Shit... */
		printk("spitfire_data_access_exception: SFSR[%016lx] "
		       "SFAR[%016lx], going.\n", sfsr, sfar);
		die_if_kernel("Dax", regs);
	}

	info.si_signo = SIGSEGV;
	info.si_errno = 0;
	info.si_code = SEGV_MAPERR;
	info.si_addr = (void __user *)sfar;
	info.si_trapno = 0;
	force_sig_info(SIGSEGV, &info, current);
}

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));
	spitfire_data_access_exception(regs, sfsr, sfar);
}

#ifdef CONFIG_PCI
/* This is really pathetic... */
extern volatile int pci_poke_in_progress;
extern volatile int pci_poke_cpu;
extern volatile int pci_poke_faulted;
#endif

/* When access exceptions happen, we must do this. */
static void spitfire_clean_and_reenable_l1_caches(void)
{
	unsigned long va;

	if (tlb_type != spitfire)
		BUG();

	/* Clean 'em. */
	for (va =  0; va < (PAGE_SIZE << 1); va += 32) {
		spitfire_put_icache_tag(va, 0x0);
		spitfire_put_dcache_tag(va, 0x0);
	}

	/* Re-enable in LSU. */
	__asm__ __volatile__("flush %%g6\n\t"
			     "membar #Sync\n\t"
			     "stxa %0, [%%g0] %1\n\t"
			     "membar #Sync"
			     : /* no outputs */
			     : "r" (LSU_CONTROL_IC | LSU_CONTROL_DC |
				    LSU_CONTROL_IM | LSU_CONTROL_DM),
			     "i" (ASI_LSU_CONTROL)
			     : "memory");
}

static void spitfire_enable_estate_errors(void)
{
	__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[] = {
	0x4c, 0x40, 0x41, 0x48, 0x42, 0x48, 0x48, 0x49,
	0x43, 0x48, 0x48, 0x49, 0x48, 0x49, 0x49, 0x4a,
	0x44, 0x48, 0x48, 0x20, 0x48, 0x39, 0x4b, 0x48,
	0x48, 0x25, 0x31, 0x48, 0x28, 0x48, 0x48, 0x2c,
	0x45, 0x48, 0x48, 0x21, 0x48, 0x3d, 0x04, 0x48,
	0x48, 0x4b, 0x35, 0x48, 0x2d, 0x48, 0x48, 0x29,
	0x48, 0x00, 0x01, 0x48, 0x0a, 0x48, 0x48, 0x4b,
	0x0f, 0x48, 0x48, 0x4b, 0x48, 0x49, 0x49, 0x48,
	0x46, 0x48, 0x48, 0x2a, 0x48, 0x3b, 0x27, 0x48,
	0x48, 0x4b, 0x33, 0x48, 0x22, 0x48, 0x48, 0x2e,
	0x48, 0x19, 0x1d, 0x48, 0x1b, 0x4a, 0x48, 0x4b,
	0x1f, 0x48, 0x4a, 0x4b, 0x48, 0x4b, 0x4b, 0x48,
	0x48, 0x4b, 0x24, 0x48, 0x07, 0x48, 0x48, 0x36,
	0x4b, 0x48, 0x48, 0x3e, 0x48, 0x30, 0x38, 0x48,
	0x49, 0x48, 0x48, 0x4b, 0x48, 0x4b, 0x16, 0x48,
	0x48, 0x12, 0x4b, 0x48, 0x49, 0x48, 0x48, 0x4b,
	0x47, 0x48, 0x48, 0x2f, 0x48, 0x3f, 0x4b, 0x48,
	0x48, 0x06, 0x37, 0x48, 0x23, 0x48, 0x48, 0x2b,
	0x48, 0x05, 0x4b, 0x48, 0x4b, 0x48, 0x48, 0x32,
	0x26, 0x48, 0x48, 0x3a, 0x48, 0x34, 0x3c, 0x48,
	0x48, 0x11, 0x15, 0x48, 0x13, 0x4a, 0x48, 0x4b,
	0x17, 0x48, 0x4a, 0x4b, 0x48, 0x4b, 0x4b, 0x48,
	0x49, 0x48, 0x48, 0x4b, 0x48, 0x4b, 0x1e, 0x48,
	0x48, 0x1a, 0x4b, 0x48, 0x49, 0x48, 0x48, 0x4b,
	0x48, 0x08, 0x0d, 0x48, 0x02, 0x48, 0x48, 0x49,
	0x03, 0x48, 0x48, 0x49, 0x48, 0x4b, 0x4b, 0x48,
	0x49, 0x48, 0x48, 0x49, 0x48, 0x4b, 0x10, 0x48,
	0x48, 0x14, 0x4b, 0x48, 0x4b, 0x48, 0x48, 0x4b,
	0x49, 0x48, 0x48, 0x49, 0x48, 0x4b, 0x18, 0x48,
	0x48, 0x1c, 0x4b, 0x48, 0x4b, 0x48, 0x48, 0x4b,
	0x4a, 0x0c, 0x09, 0x48, 0x0e, 0x48, 0x48, 0x4b,
	0x0b, 0x48, 0x48, 0x4b, 0x48, 0x4b, 0x4b, 0x4a
};

static char *syndrome_unknown = "<Unknown>";

static void spitfire_log_udb_syndrome(unsigned long afar, unsigned long udbh, unsigned long udbl, unsigned long bit)
{
	unsigned short scode;
	char memmod_str[64], *p;

	if (udbl & bit) {
		scode = ecc_syndrome_table[udbl & 0xff];
		if (prom_getunumber(scode, afar,
				    memmod_str, sizeof(memmod_str)) == -1)
			p = syndrome_unknown;
		else
			p = memmod_str;
		printk(KERN_WARNING "CPU[%d]: UDBL Syndrome[%x] "
		       "Memory Module \"%s\"\n",
		       smp_processor_id(), scode, p);
	}

	if (udbh & bit) {
		scode = ecc_syndrome_table[udbh & 0xff];
		if (prom_getunumber(scode, afar,
				    memmod_str, sizeof(memmod_str)) == -1)
			p = syndrome_unknown;
		else
			p = memmod_str;
		printk(KERN_WARNING "CPU[%d]: UDBH Syndrome[%x] "
		       "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.