Merge tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Enable THREAD_INFO_IN_TASK to move thread_info off the stack.

   - A big series from Christoph reworking our DMA code to use more of
     the generic infrastructure, as he said:
       "This series switches the powerpc port to use the generic swiotlb
        and noncoherent dma ops, and to use more generic code for the
        coherent direct mapping, as well as removing a lot of dead
        code."

   - Increase our vmalloc space to 512T with the Hash MMU on modern
     CPUs, allowing us to support machines with larger amounts of total
     RAM or distance between nodes.

   - Two series from Christophe, one to optimise TLB miss handlers on
     6xx, and another to optimise the way STRICT_KERNEL_RWX is
     implemented on some 32-bit CPUs.

   - Support for KCOV coverage instrumentation which means we can run
     syzkaller and discover even more bugs in our code.

  And as always many clean-ups, reworks and minor fixes etc.

  Thanks to: Alan Modra, Alexey Kardashevskiy, Alistair Popple, Andrea
  Arcangeli, Andrew Donnellan, Aneesh Kumar K.V, Aravinda Prasad, Balbir
  Singh, Brajeswar Ghosh, Breno Leitao, Christian Lamparter, Christian
  Zigotzky, Christophe Leroy, Christoph Hellwig, Corentin Labbe, Daniel
  Axtens, David Gibson, Diana Craciun, Firoz Khan, Gustavo A. R. Silva,
  Igor Stoppa, Joe Lawrence, Joel Stanley, Jonathan Neuschäfer, Jordan
  Niethe, Laurent Dufour, Madhavan Srinivasan, Mahesh Salgaonkar, Mark
  Cave-Ayland, Masahiro Yamada, Mathieu Malaterre, Matteo Croce, Meelis
  Roos, Michael W. Bringmann, Nathan Chancellor, Nathan Fontenot,
  Nicholas Piggin, Nick Desaulniers, Nicolai Stange, Oliver O'Halloran,
  Paul Mackerras, Peter Xu, PrasannaKumar Muralidharan, Qian Cai,
  Rashmica Gupta, Reza Arbab, Robert P. J. Day, Russell Currey,
  Sabyasachi Gupta, Sam Bobroff, Sandipan Das, Sergey Senozhatsky,
  Souptick Joarder, Stewart Smith, Tyrel Datwyler, Vaibhav Jain,
  YueHaibing"

* tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (200 commits)
  powerpc/32: Clear on-stack exception marker upon exception return
  powerpc: Remove export of save_stack_trace_tsk_reliable()
  powerpc/mm: fix "section_base" set but not used
  powerpc/mm: Fix "sz" set but not used warning
  powerpc/mm: Check secondary hash page table
  powerpc: remove nargs from __SYSCALL
  powerpc/64s: Fix unrelocated interrupt trampoline address test
  powerpc/powernv/ioda: Fix locked_vm counting for memory used by IOMMU tables
  powerpc/fsl: Fix the flush of branch predictor.
  powerpc/powernv: Make opal log only readable by root
  powerpc/xmon: Fix opcode being uninitialized in print_insn_powerpc
  powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C
  powerpc/64s: Fix data interrupts vs d-side MCE reentrancy
  powerpc/64s: Prepare to handle data interrupts vs d-side MCE reentrancy
  powerpc/64s: system reset interrupt preserve HSRRs
  powerpc/64s: Fix HV NMI vs HV interrupt recoverability test
  powerpc/mm/hash: Handle mmap_min_addr correctly in get_unmapped_area topdown search
  powerpc/hugetlb: Handle mmap_min_addr correctly in get_unmapped_area callback
  selftests/powerpc: Remove duplicate header
  powerpc sstep: Add support for modsd, modud instructions
  ...

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");