powerpc/xics: Harden xics hypervisor backend

commit 3ce21cdfe93efffa4ffba9cf3ca2576d3d60d6dc upstream.

During kdump stress testing I sometimes see the kdump kernel panic
with:

  Interrupt 0x306 (real) is invalid, disabling it.
  Kernel panic - not syncing: bad return code EOI - rc = -4, value=ff000306

Instead of panicing print the error message, dump the stack the first
time it happens and continue on. Add some more information to the
debug messages as well.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 9518d36..784b3fc 100644 (file)
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -27,33 +27,49 @@ static inline unsigned int icp_hv_get_xirr(unsigned char cppr)
 {
        unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
        long rc;
+       unsigned int ret = XICS_IRQ_SPURIOUS;
 
        rc = plpar_hcall(H_XIRR, retbuf, cppr);
-       if (rc != H_SUCCESS)
-               panic(" bad return code xirr - rc = %lx\n", rc);
-       return (unsigned int)retbuf[0];
+       if (rc == H_SUCCESS) {
+               ret = (unsigned int)retbuf[0];
+       } else {
+               pr_err("%s: bad return code xirr cppr=0x%x returned %ld\n",
+                       __func__, cppr, rc);
+               WARN_ON_ONCE(1);
+       }
+
+       return ret;
 }
 
 static inline void icp_hv_set_xirr(unsigned int value)
 {
        long rc = plpar_hcall_norets(H_EOI, value);
-       if (rc != H_SUCCESS)
-               panic("bad return code EOI - rc = %ld, value=%x\n", rc, value);
+       if (rc != H_SUCCESS) {
+               pr_err("%s: bad return code eoi xirr=0x%x returned %ld\n",
+                       __func__, value, rc);
+               WARN_ON_ONCE(1);
+       }
 }
 
 static inline void icp_hv_set_cppr(u8 value)
 {
        long rc = plpar_hcall_norets(H_CPPR, value);
-       if (rc != H_SUCCESS)
-               panic("bad return code cppr - rc = %lx\n", rc);
+       if (rc != H_SUCCESS) {
+               pr_err("%s: bad return code cppr cppr=0x%x returned %ld\n",
+                       __func__, value, rc);
+               WARN_ON_ONCE(1);
+       }
 }
 
 static inline void icp_hv_set_qirr(int n_cpu , u8 value)
 {
-       long rc = plpar_hcall_norets(H_IPI, get_hard_smp_processor_id(n_cpu),
-                                    value);
-       if (rc != H_SUCCESS)
-               panic("bad return code qirr - rc = %lx\n", rc);
+       int hw_cpu = get_hard_smp_processor_id(n_cpu);
+       long rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
+       if (rc != H_SUCCESS) {
+               pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x "
+                       "returned %ld\n", __func__, n_cpu, hw_cpu, value, rc);
+               WARN_ON_ONCE(1);
+       }
 }
 
 static void icp_hv_eoi(struct irq_data *d)