sparc64: sun4v TLB error power off events

We've witnessed a few TLB events causing the machine to power off because
of prom_halt. In one case it was some nfs related area during rmmod. Another
was an mmapper of /dev/mem. A more recent one is an ITLB issue with
a bad pagesize which could be a hardware bug. Bugs happen but we should
attempt to not power off the machine and/or hang it when possible.

This is a DTLB error from an mmapper of /dev/mem:
[root@sparcie ~]# SUN4V-DTLB: Error at TPC[fffff80100903e6c], tl 1
SUN4V-DTLB: TPC<0xfffff80100903e6c>
SUN4V-DTLB: O7[fffff801081979d0]
SUN4V-DTLB: O7<0xfffff801081979d0>
SUN4V-DTLB: vaddr[fffff80100000000] ctx[1250] pte[98000000000f0610] error[2]
.

This is recent mainline for ITLB:
[ 3708.179864] SUN4V-ITLB: TPC<0xfffffc010071cefc>
[ 3708.188866] SUN4V-ITLB: O7[fffffc010071cee8]
[ 3708.197377] SUN4V-ITLB: O7<0xfffffc010071cee8>
[ 3708.206539] SUN4V-ITLB: vaddr[e0003] ctx[1a3c] pte[2900000dcc800eeb] error[4]
.

Normally sun4v_itlb_error_report() and sun4v_dtlb_error_report() would call
prom_halt() and drop us to OF command prompt "ok". This isn't the case for
LDOMs and the machine powers off.

For the HV reported error of HV_ENORADDR for HV HV_MMU_MAP_ADDR_TRAP we cause
a SIGBUS error by qualifying it within do_sparc64_fault() for fault code mask
of FAULT_CODE_BAD_RA. This is done when trap level (%tl) is less or equal
one("1"). Otherwise, for %tl > 1,  we proceed eventually to die_if_kernel().

The logic of this patch was partially inspired by David Miller's feedback.

Power off of large sparc64 machines is painful. Plus die_if_kernel provides
more context. A reset sequence isn't a brief period on large sparc64 but
better than power-off/power-on sequence.

Cc: sparclinux@vger.kernel.org
Signed-off-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 34 insertions, 20 deletions

diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index a5f01ac6d0f1..f85dc8512ab3 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -102,6 +102,7 @@ struct thread_info {
 #define FAULT_CODE_ITLB         0x04    /* Miss happened in I-TLB          */
 #define FAULT_CODE_WINFIXUP     0x08    /* Miss happened during spill/fill */
 #define FAULT_CODE_BLKCOMMIT    0x10    /* Use blk-commit ASI in copy_page */
+#define FAULT_CODE_BAD_RA       0x20    /* Bad RA for sun4v                */
 
 #if PAGE_SHIFT == 13
 #define THREAD_SIZE (2*PAGE_SIZE)
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index e0c09bf85610..6179e19bc9b9 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -195,6 +195,11 @@ sun4v_tsb_miss_common:
          ldx    [%g2 + TRAP_PER_CPU_PGD_PADDR], %g7
 
 sun4v_itlb_error:
+        rdpr    %tl, %g1
+        cmp     %g1, 1
+        ble,pt  %icc, sun4v_bad_ra
+         or     %g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1
+
         sethi   %hi(sun4v_err_itlb_vaddr), %g1
         stx     %g4, [%g1 + %lo(sun4v_err_itlb_vaddr)]
         sethi   %hi(sun4v_err_itlb_ctx), %g1
@@ -206,15 +211,10 @@ sun4v_itlb_error:
         sethi   %hi(sun4v_err_itlb_error), %g1
         stx     %o0, [%g1 + %lo(sun4v_err_itlb_error)]
 
+        sethi   %hi(1f), %g7
         rdpr    %tl, %g4
-        cmp     %g4, 1
-        ble,pt  %icc, 1f
-         sethi  %hi(2f), %g7
         ba,pt   %xcc, etraptl1
-         or     %g7, %lo(2f), %g7
-
-1:      ba,pt   %xcc, etrap
-2:       or     %g7, %lo(2b), %g7
+1:       or     %g7, %lo(1f), %g7
         mov     %l4, %o1
         call    sun4v_itlb_error_report
          add    %sp, PTREGS_OFF, %o0
@@ -222,6 +222,11 @@ sun4v_itlb_error:
         /* NOTREACHED */
 
 sun4v_dtlb_error:
+        rdpr    %tl, %g1
+        cmp     %g1, 1
+        ble,pt  %icc, sun4v_bad_ra
+         or     %g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1
+
         sethi   %hi(sun4v_err_dtlb_vaddr), %g1
         stx     %g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)]
         sethi   %hi(sun4v_err_dtlb_ctx), %g1
@@ -233,21 +238,23 @@ sun4v_dtlb_error:
         sethi   %hi(sun4v_err_dtlb_error), %g1
         stx     %o0, [%g1 + %lo(sun4v_err_dtlb_error)]
 
+        sethi   %hi(1f), %g7
         rdpr    %tl, %g4
-        cmp     %g4, 1
-        ble,pt  %icc, 1f
-         sethi  %hi(2f), %g7
         ba,pt   %xcc, etraptl1
-         or     %g7, %lo(2f), %g7
-
-1:      ba,pt   %xcc, etrap
-2:       or     %g7, %lo(2b), %g7
+1:       or     %g7, %lo(1f), %g7
         mov     %l4, %o1
         call    sun4v_dtlb_error_report
          add    %sp, PTREGS_OFF, %o0
 
         /* NOTREACHED */
 
+sun4v_bad_ra:
+        or      %g0, %g4, %g5
+        ba,pt   %xcc, sparc64_realfault_common
+         or     %g1, %g0, %g4
+
+        /* NOTREACHED */
+
         /* Instruction Access Exception, tl0. */
 sun4v_iacc:
         ldxa    [%g0] ASI_SCRATCHPAD, %g2
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index fb6640ec8557..981a769b9558 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2104,6 +2104,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs)
         atomic_inc(&sun4v_nonresum_oflow_cnt);
 }
 
+static void sun4v_tlb_error(struct pt_regs *regs)
+{
+        die_if_kernel("TLB/TSB error", regs);
+}
+
 unsigned long sun4v_err_itlb_vaddr;
 unsigned long sun4v_err_itlb_ctx;
 unsigned long sun4v_err_itlb_pte;
@@ -2111,8 +2116,7 @@ unsigned long sun4v_err_itlb_error;
 
 void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 {
-        if (tl > 1)
-                dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+        dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
         printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n",
                regs->tpc, tl);
@@ -2125,7 +2129,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
                sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx,
                sun4v_err_itlb_pte, sun4v_err_itlb_error);
 
-        prom_halt();
+        sun4v_tlb_error(regs);
 }
 
 unsigned long sun4v_err_dtlb_vaddr;
@@ -2135,8 +2139,7 @@ unsigned long sun4v_err_dtlb_error;
 
 void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 {
-        if (tl > 1)
-                dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+        dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
         printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n",
                regs->tpc, tl);
@@ -2149,7 +2152,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
                sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx,
                sun4v_err_dtlb_pte, sun4v_err_dtlb_error);
 
-        prom_halt();
+        sun4v_tlb_error(regs);
 }
 
 void hypervisor_tlbop_error(unsigned long err, unsigned long op)
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 587cd0565128..18fcd7167095 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -346,6 +346,9 @@ retry:
                 down_read(&mm->mmap_sem);
         }
 
+        if (fault_code & FAULT_CODE_BAD_RA)
+                goto do_sigbus;
+
         vma = find_vma(mm, address);
         if (!vma)
                 goto bad_area;