1 files changed, 108 insertions, 25 deletions

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 64936b60d521..a21200c6aaea 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -257,24 +257,17 @@ static int __die(const char *str, struct pt_regs *regs, long err)
 {
 	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
 
-	if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
-		printk("LE ");
-	else
-		printk("BE ");
-
-	if (IS_ENABLED(CONFIG_PREEMPT))
-		pr_cont("PREEMPT ");
-
-	if (IS_ENABLED(CONFIG_SMP))
-		pr_cont("SMP NR_CPUS=%d ", NR_CPUS);
-
-	if (debug_pagealloc_enabled())
-		pr_cont("DEBUG_PAGEALLOC ");
-
-	if (IS_ENABLED(CONFIG_NUMA))
-		pr_cont("NUMA ");
-
-	pr_cont("%s\n", ppc_md.name ? ppc_md.name : "");
+	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n",
+	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
+	       PAGE_SIZE / 1024,
+	       early_radix_enabled() ? " MMU=Radix" : "",
+	       early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "",
+	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
+	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
+	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
+	       debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
+	       IS_ENABLED(CONFIG_NUMA) ? " NUMA" : "",
+	       ppc_md.name ? ppc_md.name : "");
 
 	if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP)
 		return 1;
@@ -376,16 +369,101 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 	force_sig_fault(signr, code, (void __user *)addr, current);
 }
 
+/*
+ * The interrupt architecture has a quirk in that the HV interrupts excluding
+ * the NMIs (0x100 and 0x200) do not clear MSR[RI] at entry. The first thing
+ * that an interrupt handler must do is save off a GPR into a scratch register,
+ * and all interrupts on POWERNV (HV=1) use the HSPRG1 register as scratch.
+ * Therefore an NMI can clobber an HV interrupt's live HSPRG1 without noticing
+ * that it is non-reentrant, which leads to random data corruption.
+ *
+ * The solution is for NMI interrupts in HV mode to check if they originated
+ * from these critical HV interrupt regions. If so, then mark them not
+ * recoverable.
+ *
+ * An alternative would be for HV NMIs to use SPRG for scratch to avoid the
+ * HSPRG1 clobber, however this would cause guest SPRG to be clobbered. Linux
+ * guests should always have MSR[RI]=0 when its scratch SPRG is in use, so
+ * that would work. However any other guest OS that may have the SPRG live
+ * and MSR[RI]=1 could encounter silent corruption.
+ *
+ * Builds that do not support KVM could take this second option to increase
+ * the recoverability of NMIs.
+ */
+void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_POWERNV
+	unsigned long kbase = (unsigned long)_stext;
+	unsigned long nip = regs->nip;
+
+	if (!(regs->msr & MSR_RI))
+		return;
+	if (!(regs->msr & MSR_HV))
+		return;
+	if (regs->msr & MSR_PR)
+		return;
+
+	/*
+	 * Now test if the interrupt has hit a range that may be using
+	 * HSPRG1 without having RI=0 (i.e., an HSRR interrupt). The
+	 * problem ranges all run un-relocated. Test real and virt modes
+	 * at the same time by droping the high bit of the nip (virt mode
+	 * entry points still have the +0x4000 offset).
+	 */
+	nip &= ~0xc000000000000000ULL;
+	if ((nip >= 0x500 && nip < 0x600) || (nip >= 0x4500 && nip < 0x4600))
+		goto nonrecoverable;
+	if ((nip >= 0x980 && nip < 0xa00) || (nip >= 0x4980 && nip < 0x4a00))
+		goto nonrecoverable;
+	if ((nip >= 0xe00 && nip < 0xec0) || (nip >= 0x4e00 && nip < 0x4ec0))
+		goto nonrecoverable;
+	if ((nip >= 0xf80 && nip < 0xfa0) || (nip >= 0x4f80 && nip < 0x4fa0))
+		goto nonrecoverable;
+
+	/* Trampoline code runs un-relocated so subtract kbase. */
+	if (nip >= (unsigned long)(start_real_trampolines - kbase) &&
+			nip < (unsigned long)(end_real_trampolines - kbase))
+		goto nonrecoverable;
+	if (nip >= (unsigned long)(start_virt_trampolines - kbase) &&
+			nip < (unsigned long)(end_virt_trampolines - kbase))
+		goto nonrecoverable;
+	return;
+
+nonrecoverable:
+	regs->msr &= ~MSR_RI;
+#endif
+}
+
 void system_reset_exception(struct pt_regs *regs)
 {
+	unsigned long hsrr0, hsrr1;
+	bool nested = in_nmi();
+	bool saved_hsrrs = false;
+
 	/*
 	 * Avoid crashes in case of nested NMI exceptions. Recoverability
 	 * is determined by RI and in_nmi
 	 */
-	bool nested = in_nmi();
 	if (!nested)
 		nmi_enter();
 
+	/*
+	 * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
+	 * The system reset interrupt itself may clobber HSRRs (e.g., to call
+	 * OPAL), so save them here and restore them before returning.
+	 *
+	 * Machine checks don't need to save HSRRs, as the real mode handler
+	 * is careful to avoid them, and the regular handler is not delivered
+	 * as an NMI.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		hsrr0 = mfspr(SPRN_HSRR0);
+		hsrr1 = mfspr(SPRN_HSRR1);
+		saved_hsrrs = true;
+	}
+
+	hv_nmi_check_nonrecoverable(regs);
+
 	__this_cpu_inc(irq_stat.sreset_irqs);
 
 	/* See if any machine dependent calls */
@@ -433,6 +511,11 @@ out:
 	if (!(regs->msr & MSR_RI))
 		nmi_panic(regs, "Unrecoverable System Reset");
 
+	if (saved_hsrrs) {
+		mtspr(SPRN_HSRR0, hsrr0);
+		mtspr(SPRN_HSRR1, hsrr1);
+	}
+
 	if (!nested)
 		nmi_exit();
 
@@ -763,15 +846,15 @@ void machine_check_exception(struct pt_regs *regs)
 	if (check_io_access(regs))
 		goto bail;
 
-	/* Must die if the interrupt is not recoverable */
-	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable Machine check");
-
 	if (!nested)
 		nmi_exit();
 
 	die("Machine check", regs, SIGBUS);
 
+	/* Must die if the interrupt is not recoverable */
+	if (!(regs->msr & MSR_RI))
+		nmi_panic(regs, "Unrecoverable Machine check");
+
 	return;
 
 bail:
@@ -1542,8 +1625,8 @@ bail:
 
 void StackOverflow(struct pt_regs *regs)
 {
-	printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n",
-	       current, regs->gpr[1]);
+	pr_crit("Kernel stack overflow in process %s[%d], r1=%lx\n",
+		current->comm, task_pid_nr(current), regs->gpr[1]);
 	debugger(regs);
 	show_regs(regs);
 	panic("kernel stack overflow");