Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "A bit of a small release, I suspect in part due to me travelling for
  KS. But my backlog of patches to review is smaller than usual, so I
  think in part folks just didn't send as much this cycle.

  Non-highlights:

   - Five fixes for the >128T address space handling, both to fix bugs
     in our implementation and to bring the semantics exactly into line
     with x86.

  Highlights:

   - Support for a new OPAL call on bare metal machines which gives us a
     true NMI (ie. is not masked by MSR[EE]=0) for debugging etc.

   - Support for Power9 DD2 in the CXL driver.

   - Improvements to machine check handling so that uncorrectable errors
     can be reported into the generic memory_failure() machinery.

   - Some fixes and improvements for VPHN, which is used under PowerVM
     to notify the Linux partition of topology changes.

   - Plumbing to enable TM (transactional memory) without suspend on
     some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND).

   - Support for emulating vector loads form cache-inhibited memory, on
     some Power9 revisions.

   - Disable the fast-endian switch "syscall" by default (behind a
     CONFIG), we believe it has never had any users.

   - A major rework of the API drivers use when initiating and waiting
     for long running operations performed by OPAL firmware, and changes
     to the powernv_flash driver to use the new API.

   - Several fixes for the handling of FP/VMX/VSX while processes are
     using transactional memory.

   - Optimisations of TLB range flushes when using the radix MMU on
     Power9.

   - Improvements to the VAS facility used to access coprocessors on
     Power9, and related improvements to the way the NX crypto driver
     handles requests.

   - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew
  Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin
  Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard,
  Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven,
  Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley,
  Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu,
  Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao,
  Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia
  Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee,
  Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel
  Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A.
  Kennington III"

* tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits)
  powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature
  powerpc/64s: Fix masking of SRR1 bits on instruction fault
  powerpc/64s: mm_context.addr_limit is only used on hash
  powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary
  powerpc/64s/hash: Fix fork() with 512TB process address space
  powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Fix 512T hint detection to use >= 128T
  powerpc: Fix DABR match on hash based systems
  powerpc/signal: Properly handle return value from uprobe_deny_signal()
  powerpc/fadump: use kstrtoint to handle sysfs store
  powerpc/lib: Implement UACCESS_FLUSHCACHE API
  powerpc/lib: Implement PMEM API
  powerpc/powernv/npu: Don't explicitly flush nmmu tlb
  powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm()
  powerpc/powernv/idle: Round up latency and residency values
  powerpc/kprobes: refactor kprobe_lookup_name for safer string operations
  powerpc/kprobes: Blacklist emulate_update_regs() from kprobes
  powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace
  powerpc/kprobes: Disable preemption before invoking probe handler for optprobes
  ...

1 files changed, 102 insertions, 45 deletions

diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 9b2ea7e71c06..742e4658c5dc 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -39,11 +39,21 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
 static DEFINE_PER_CPU(int, mce_queue_count);
 static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue);
 
+/* Queue for delayed MCE UE events. */
+static DEFINE_PER_CPU(int, mce_ue_count);
+static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],
+					mce_ue_event_queue);
+
 static void machine_check_process_queued_event(struct irq_work *work);
+void machine_check_ue_event(struct machine_check_event *evt);
+static void machine_process_ue_event(struct work_struct *work);
+
 static struct irq_work mce_event_process_work = {
         .func = machine_check_process_queued_event,
 };
 
+DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
+
 static void mce_set_error_info(struct machine_check_event *mce,
 			       struct mce_error_info *mce_err)
 {
@@ -82,7 +92,7 @@ static void mce_set_error_info(struct machine_check_event *mce,
  */
 void save_mce_event(struct pt_regs *regs, long handled,
 		    struct mce_error_info *mce_err,
-		    uint64_t nip, uint64_t addr)
+		    uint64_t nip, uint64_t addr, uint64_t phys_addr)
 {
 	int index = __this_cpu_inc_return(mce_nest_count) - 1;
 	struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
@@ -140,6 +150,11 @@ void save_mce_event(struct pt_regs *regs, long handled,
 	} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
 		mce->u.ue_error.effective_address_provided = true;
 		mce->u.ue_error.effective_address = addr;
+		if (phys_addr != ULONG_MAX) {
+			mce->u.ue_error.physical_address_provided = true;
+			mce->u.ue_error.physical_address = phys_addr;
+			machine_check_ue_event(mce);
+		}
 	}
 	return;
 }
@@ -193,6 +208,26 @@ void release_mce_event(void)
 	get_mce_event(NULL, true);
 }
 
+
+/*
+ * Queue up the MCE event which then can be handled later.
+ */
+void machine_check_ue_event(struct machine_check_event *evt)
+{
+	int index;
+
+	index = __this_cpu_inc_return(mce_ue_count) - 1;
+	/* If queue is full, just return for now. */
+	if (index >= MAX_MC_EVT) {
+		__this_cpu_dec(mce_ue_count);
+		return;
+	}
+	memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt));
+
+	/* Queue work to process this event later. */
+	schedule_work(&mce_ue_event_work);
+}
+
 /*
  * Queue up the MCE event which then can be handled later.
  */
@@ -215,7 +250,39 @@ void machine_check_queue_event(void)
 	/* Queue irq work to process this event later. */
 	irq_work_queue(&mce_event_process_work);
 }
-
+/*
+ * process pending MCE event from the mce event queue. This function will be
+ * called during syscall exit.
+ */
+static void machine_process_ue_event(struct work_struct *work)
+{
+	int index;
+	struct machine_check_event *evt;
+
+	while (__this_cpu_read(mce_ue_count) > 0) {
+		index = __this_cpu_read(mce_ue_count) - 1;
+		evt = this_cpu_ptr(&mce_ue_event_queue[index]);
+#ifdef CONFIG_MEMORY_FAILURE
+		/*
+		 * This should probably queued elsewhere, but
+		 * oh! well
+		 */
+		if (evt->error_type == MCE_ERROR_TYPE_UE) {
+			if (evt->u.ue_error.physical_address_provided) {
+				unsigned long pfn;
+
+				pfn = evt->u.ue_error.physical_address >>
+					PAGE_SHIFT;
+				memory_failure(pfn, SIGBUS, 0);
+			} else
+				pr_warn("Failed to identify bad address from "
+					"where the uncorrectable error (UE) "
+					"was generated\n");
+		}
+#endif
+		__this_cpu_dec(mce_ue_count);
+	}
+}
 /*
  * process pending MCE event from the mce event queue. This function will be
  * called during syscall exit.
@@ -223,6 +290,7 @@ void machine_check_queue_event(void)
 static void machine_check_process_queued_event(struct irq_work *work)
 {
 	int index;
+	struct machine_check_event *evt;
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
@@ -232,8 +300,8 @@ static void machine_check_process_queued_event(struct irq_work *work)
 	 */
 	while (__this_cpu_read(mce_queue_count) > 0) {
 		index = __this_cpu_read(mce_queue_count) - 1;
-		machine_check_print_event_info(
-				this_cpu_ptr(&mce_event_queue[index]), false);
+		evt = this_cpu_ptr(&mce_event_queue[index]);
+		machine_check_print_event_info(evt, false);
 		__this_cpu_dec(mce_queue_count);
 	}
 }
@@ -340,7 +408,7 @@ void machine_check_print_event_info(struct machine_check_event *evt,
 			printk("%s    Effective address: %016llx\n",
 			       level, evt->u.ue_error.effective_address);
 		if (evt->u.ue_error.physical_address_provided)
-			printk("%s      Physical address: %016llx\n",
+			printk("%s    Physical address:  %016llx\n",
 			       level, evt->u.ue_error.physical_address);
 		break;
 	case MCE_ERROR_TYPE_SLB:
@@ -411,45 +479,6 @@ void machine_check_print_event_info(struct machine_check_event *evt,
 }
 EXPORT_SYMBOL_GPL(machine_check_print_event_info);
 
-uint64_t get_mce_fault_addr(struct machine_check_event *evt)
-{
-	switch (evt->error_type) {
-	case MCE_ERROR_TYPE_UE:
-		if (evt->u.ue_error.effective_address_provided)
-			return evt->u.ue_error.effective_address;
-		break;
-	case MCE_ERROR_TYPE_SLB:
-		if (evt->u.slb_error.effective_address_provided)
-			return evt->u.slb_error.effective_address;
-		break;
-	case MCE_ERROR_TYPE_ERAT:
-		if (evt->u.erat_error.effective_address_provided)
-			return evt->u.erat_error.effective_address;
-		break;
-	case MCE_ERROR_TYPE_TLB:
-		if (evt->u.tlb_error.effective_address_provided)
-			return evt->u.tlb_error.effective_address;
-		break;
-	case MCE_ERROR_TYPE_USER:
-		if (evt->u.user_error.effective_address_provided)
-			return evt->u.user_error.effective_address;
-		break;
-	case MCE_ERROR_TYPE_RA:
-		if (evt->u.ra_error.effective_address_provided)
-			return evt->u.ra_error.effective_address;
-		break;
-	case MCE_ERROR_TYPE_LINK:
-		if (evt->u.link_error.effective_address_provided)
-			return evt->u.link_error.effective_address;
-		break;
-	default:
-	case MCE_ERROR_TYPE_UNKNOWN:
-		break;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(get_mce_fault_addr);
-
 /*
  * This function is called in real mode. Strictly no printk's please.
  *
@@ -470,6 +499,34 @@ long hmi_exception_realmode(struct pt_regs *regs)
 {
 	__this_cpu_inc(irq_stat.hmi_exceptions);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Workaround for P9 vector CI loads (see p9_hmi_special_emu) */
+	if (pvr_version_is(PVR_POWER9)) {
+		unsigned long hmer = mfspr(SPRN_HMER);
+
+		/* Do we have the debug bit set */
+		if (hmer & PPC_BIT(17)) {
+			hmer &= ~PPC_BIT(17);
+			mtspr(SPRN_HMER, hmer);
+
+			/*
+			 * Now to avoid problems with soft-disable we
+			 * only do the emulation if we are coming from
+			 * user space
+			 */
+			if (user_mode(regs))
+				local_paca->hmi_p9_special_emu = 1;
+
+			/*
+			 * Don't bother going to OPAL if that's the
+			 * only relevant bit.
+			 */
+			if (!(hmer & mfspr(SPRN_HMEER)))
+				return local_paca->hmi_p9_special_emu;
+		}
+	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 	wait_for_subcore_guest_exit();
 
 	if (ppc_md.hmi_exception_early)
@@ -477,5 +534,5 @@ long hmi_exception_realmode(struct pt_regs *regs)
 
 	wait_for_tb_resync();
 
-	return 0;
+	return 1;
 }