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
  ...

6 files changed, 398 insertions, 5 deletions

diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index f4241339edd2..87f1f0252299 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -10,6 +10,7 @@
  */
 
 #define _GNU_SOURCE
+#include <errno.h>
 #include <sched.h>
 #include <string.h>
 #include <stdio.h>
@@ -75,6 +76,7 @@ static void touch(void)
 
 static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 {
+	int rc;
 	pthread_t tid;
 	cpu_set_t cpuset;
 	pthread_attr_t attr;
@@ -82,14 +84,23 @@ static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 	CPU_ZERO(&cpuset);
 	CPU_SET(cpu, &cpuset);
 
-	pthread_attr_init(&attr);
+	rc = pthread_attr_init(&attr);
+	if (rc) {
+		errno = rc;
+		perror("pthread_attr_init");
+		exit(1);
+	}
 
-	if (pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset)) {
+	rc = pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+	if (rc)	{
+		errno = rc;
 		perror("pthread_attr_setaffinity_np");
 		exit(1);
 	}
 
-	if (pthread_create(&tid, &attr, fn, arg)) {
+	rc = pthread_create(&tid, &attr, fn, arg);
+	if (rc) {
+		errno = rc;
 		perror("pthread_create");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
index 17fb1b43c320..1899bd85121f 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c
@@ -53,6 +53,8 @@ static int check_all_cpu_dscr_defaults(unsigned long val)
 	}
 
 	while ((dp = readdir(sysfs))) {
+		int len;
+
 		if (!(dp->d_type & DT_DIR))
 			continue;
 		if (!strcmp(dp->d_name, "cpuidle"))
@@ -60,7 +62,9 @@ static int check_all_cpu_dscr_defaults(unsigned long val)
 		if (!strstr(dp->d_name, "cpu"))
 			continue;
 
-		sprintf(file, "%s%s/dscr", CPU_PATH, dp->d_name);
+		len = snprintf(file, LEN_MAX, "%s%s/dscr", CPU_PATH, dp->d_name);
+		if (len >= LEN_MAX)
+			continue;
 		if (access(file, F_OK))
 			continue;
 
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 2f1f7b013293..241a4a4ee0e4 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -12,3 +12,4 @@ tm-signal-context-chk-gpr
 tm-signal-context-chk-vmx
 tm-signal-context-chk-vsx
 tm-vmx-unavail
+tm-unavailable
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index fca7c7f5e640..8ed6f8c57230 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -3,7 +3,7 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu
 	tm-signal-context-chk-vmx tm-signal-context-chk-vsx
 
 TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
-	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail \
+	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable \
 	$(SIGNAL_CONTEXT_CHK_TESTS)
 
 include ../../lib.mk
@@ -17,6 +17,7 @@ $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
 $(OUTPUT)/tm-tmspr: CFLAGS += -pthread
 $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
 $(OUTPUT)/tm-resched-dscr: ../pmu/lib.o
+$(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 
 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
 $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S
diff --git a/tools/testing/selftests/powerpc/tm/tm-unavailable.c b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
new file mode 100644
index 000000000000..96c37f84ce54
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
@@ -0,0 +1,371 @@
+/*
+ * Copyright 2017, Gustavo Romero, Breno Leitao, Cyril Bur, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Force FP, VEC and VSX unavailable exception during transaction in all
+ * possible scenarios regarding the MSR.FP and MSR.VEC state, e.g. when FP
+ * is enable and VEC is disable, when FP is disable and VEC is enable, and
+ * so on. Then we check if the restored state is correctly set for the
+ * FP and VEC registers to the previous state we set just before we entered
+ * in TM, i.e. we check if it corrupts somehow the recheckpointed FP and
+ * VEC/Altivec registers on abortion due to an unavailable exception in TM.
+ * N.B. In this test we do not test all the FP/Altivec/VSX registers for
+ * corruption, but only for registers vs0 and vs32, which are respectively
+ * representatives of FP and VEC/Altivec reg sets.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <sched.h>
+
+#include "tm.h"
+
+#define DEBUG 0
+
+/* Unavailable exceptions to test in HTM */
+#define FP_UNA_EXCEPTION	0
+#define VEC_UNA_EXCEPTION	1
+#define VSX_UNA_EXCEPTION	2
+
+#define NUM_EXCEPTIONS		3
+
+struct Flags {
+	int touch_fp;
+	int touch_vec;
+	int result;
+	int exception;
+} flags;
+
+bool expecting_failure(void)
+{
+	if (flags.touch_fp && flags.exception == FP_UNA_EXCEPTION)
+		return false;
+
+	if (flags.touch_vec && flags.exception == VEC_UNA_EXCEPTION)
+		return false;
+
+	/*
+	 * If both FP and VEC are touched it does not mean that touching VSX
+	 * won't raise an exception. However since FP and VEC state are already
+	 * correctly loaded, the transaction is not aborted (i.e.
+	 * treclaimed/trecheckpointed) and MSR.VSX is just set as 1, so a TM
+	 * failure is not expected also in this case.
+	 */
+	if ((flags.touch_fp && flags.touch_vec) &&
+	     flags.exception == VSX_UNA_EXCEPTION)
+		return false;
+
+	return true;
+}
+
+/* Check if failure occurred whilst in transaction. */
+bool is_failure(uint64_t condition_reg)
+{
+	/*
+	 * When failure handling occurs, CR0 is set to 0b1010 (0xa). Otherwise
+	 * transaction completes without failure and hence reaches out 'tend.'
+	 * that sets CR0 to 0b0100 (0x4).
+	 */
+	return ((condition_reg >> 28) & 0xa) == 0xa;
+}
+
+void *ping(void *input)
+{
+
+	/*
+	 * Expected values for vs0 and vs32 after a TM failure. They must never
+	 * change, otherwise they got corrupted.
+	 */
+	uint64_t high_vs0 = 0x5555555555555555;
+	uint64_t low_vs0 = 0xffffffffffffffff;
+	uint64_t high_vs32 = 0x5555555555555555;
+	uint64_t low_vs32 = 0xffffffffffffffff;
+
+	/* Counter for busy wait */
+	uint64_t counter = 0x1ff000000;
+
+	/*
+	 * Variable to keep a copy of CR register content taken just after we
+	 * leave the transactional state.
+	 */
+	uint64_t cr_ = 0;
+
+	/*
+	 * Wait a bit so thread can get its name "ping". This is not important
+	 * to reproduce the issue but it's nice to have for systemtap debugging.
+	 */
+	if (DEBUG)
+		sleep(1);
+
+	printf("If MSR.FP=%d MSR.VEC=%d: ", flags.touch_fp, flags.touch_vec);
+
+	if (flags.exception != FP_UNA_EXCEPTION &&
+	    flags.exception != VEC_UNA_EXCEPTION &&
+	    flags.exception != VSX_UNA_EXCEPTION) {
+		printf("No valid exception specified to test.\n");
+		return NULL;
+	}
+
+	asm (
+		/* Prepare to merge low and high. */
+		"	mtvsrd		33, %[high_vs0]		;"
+		"	mtvsrd		34, %[low_vs0]		;"
+
+		/*
+		 * Adjust VS0 expected value after an TM failure,
+		 * i.e. vs0 = 0x5555555555555555555FFFFFFFFFFFFFFFF
+		 */
+		"	xxmrghd		0, 33, 34		;"
+
+		/*
+		 * Adjust VS32 expected value after an TM failure,
+		 * i.e. vs32 = 0x5555555555555555555FFFFFFFFFFFFFFFF
+		 */
+		"	xxmrghd		32, 33, 34		;"
+
+		/*
+		 * Wait an amount of context switches so load_fp and load_vec
+		 * overflow and MSR.FP, MSR.VEC, and MSR.VSX become zero (off).
+		 */
+		"	mtctr		%[counter]		;"
+
+		/* Decrement CTR branch if CTR non zero. */
+		"1:	bdnz 1b					;"
+
+		/*
+		 * Check if we want to touch FP prior to the test in order
+		 * to set MSR.FP = 1 before provoking an unavailable
+		 * exception in TM.
+		 */
+		"	cmpldi		%[touch_fp], 0		;"
+		"	beq		no_fp			;"
+		"	fadd		10, 10, 10		;"
+		"no_fp:						;"
+
+		/*
+		 * Check if we want to touch VEC prior to the test in order
+		 * to set MSR.VEC = 1 before provoking an unavailable
+		 * exception in TM.
+		 */
+		"	cmpldi		%[touch_vec], 0		;"
+		"	beq		no_vec			;"
+		"	vaddcuw		10, 10, 10		;"
+		"no_vec:					;"
+
+		/*
+		 * Perhaps it would be a better idea to do the
+		 * compares outside transactional context and simply
+		 * duplicate code.
+		 */
+		"	tbegin.					;"
+		"	beq		trans_fail		;"
+
+		/* Do we do FP Unavailable? */
+		"	cmpldi		%[exception], %[ex_fp]	;"
+		"	bne		1f			;"
+		"	fadd		10, 10, 10		;"
+		"	b		done			;"
+
+		/* Do we do VEC Unavailable? */
+		"1:	cmpldi		%[exception], %[ex_vec]	;"
+		"	bne		2f			;"
+		"	vaddcuw		10, 10, 10		;"
+		"	b		done			;"
+
+		/*
+		 * Not FP or VEC, therefore VSX. Ensure this
+		 * instruction always generates a VSX Unavailable.
+		 * ISA 3.0 is tricky here.
+		 * (xxmrghd will on ISA 2.07 and ISA 3.0)
+		 */
+		"2:	xxmrghd		10, 10, 10		;"
+
+		"done:	tend. ;"
+
+		"trans_fail: ;"
+
+		/* Give values back to C. */
+		"	mfvsrd		%[high_vs0], 0		;"
+		"	xxsldwi		3, 0, 0, 2		;"
+		"	mfvsrd		%[low_vs0], 3		;"
+		"	mfvsrd		%[high_vs32], 32	;"
+		"	xxsldwi		3, 32, 32, 2		;"
+		"	mfvsrd		%[low_vs32], 3		;"
+
+		/* Give CR back to C so that it can check what happened. */
+		"	mfcr		%[cr_]		;"
+
+		: [high_vs0]  "+r" (high_vs0),
+		  [low_vs0]   "+r" (low_vs0),
+		  [high_vs32] "=r" (high_vs32),
+		  [low_vs32]  "=r" (low_vs32),
+		  [cr_]       "+r" (cr_)
+		: [touch_fp]  "r"  (flags.touch_fp),
+		  [touch_vec] "r"  (flags.touch_vec),
+		  [exception] "r"  (flags.exception),
+		  [ex_fp]     "i"  (FP_UNA_EXCEPTION),
+		  [ex_vec]    "i"  (VEC_UNA_EXCEPTION),
+		  [ex_vsx]    "i"  (VSX_UNA_EXCEPTION),
+		  [counter]   "r"  (counter)
+
+		: "cr0", "ctr", "v10", "vs0", "vs10", "vs3", "vs32", "vs33",
+		  "vs34", "fr10"
+
+		);
+
+	/*
+	 * Check if we were expecting a failure and it did not occur by checking
+	 * CR0 state just after we leave the transaction. Either way we check if
+	 * vs0 or vs32 got corrupted.
+	 */
+	if (expecting_failure() && !is_failure(cr_)) {
+		printf("\n\tExpecting the transaction to fail, %s",
+			"but it didn't\n\t");
+		flags.result++;
+	}
+
+	/* Check if we were not expecting a failure and a it occurred. */
+	if (!expecting_failure() && is_failure(cr_)) {
+		printf("\n\tUnexpected transaction failure 0x%02lx\n\t",
+			failure_code());
+		return (void *) -1;
+	}
+
+	/*
+	 * Check if TM failed due to the cause we were expecting. 0xda is a
+	 * TM_CAUSE_FAC_UNAV cause, otherwise it's an unexpected cause.
+	 */
+	if (is_failure(cr_) && !failure_is_unavailable()) {
+		printf("\n\tUnexpected failure cause 0x%02lx\n\t",
+			failure_code());
+		return (void *) -1;
+	}
+
+	/* 0x4 is a success and 0xa is a fail. See comment in is_failure(). */
+	if (DEBUG)
+		printf("CR0: 0x%1lx ", cr_ >> 28);
+
+	/* Check FP (vs0) for the expected value. */
+	if (high_vs0 != 0x5555555555555555 || low_vs0 != 0xFFFFFFFFFFFFFFFF) {
+		printf("FP corrupted!");
+			printf("  high = %#16" PRIx64 "  low = %#16" PRIx64 " ",
+				high_vs0, low_vs0);
+		flags.result++;
+	} else
+		printf("FP ok ");
+
+	/* Check VEC (vs32) for the expected value. */
+	if (high_vs32 != 0x5555555555555555 || low_vs32 != 0xFFFFFFFFFFFFFFFF) {
+		printf("VEC corrupted!");
+			printf("  high = %#16" PRIx64 "  low = %#16" PRIx64,
+				high_vs32, low_vs32);
+		flags.result++;
+	} else
+		printf("VEC ok");
+
+	putchar('\n');
+
+	return NULL;
+}
+
+/* Thread to force context switch */
+void *pong(void *not_used)
+{
+	/* Wait thread get its name "pong". */
+	if (DEBUG)
+		sleep(1);
+
+	/* Classed as an interactive-like thread. */
+	while (1)
+		sched_yield();
+}
+
+/* Function that creates a thread and launches the "ping" task. */
+void test_fp_vec(int fp, int vec, pthread_attr_t *attr)
+{
+	int retries = 2;
+	void *ret_value;
+	pthread_t t0;
+
+	flags.touch_fp = fp;
+	flags.touch_vec = vec;
+
+	/*
+	 * Without luck it's possible that the transaction is aborted not due to
+	 * the unavailable exception caught in the middle as we expect but also,
+	 * for instance, due to a context switch or due to a KVM reschedule (if
+	 * it's running on a VM). Thus we try a few times before giving up,
+	 * checking if the failure cause is the one we expect.
+	 */
+	do {
+		/* Bind 'ping' to CPU 0, as specified in 'attr'. */
+		pthread_create(&t0, attr, ping, (void *) &flags);
+		pthread_setname_np(t0, "ping");
+		pthread_join(t0, &ret_value);
+		retries--;
+	} while (ret_value != NULL && retries);
+
+	if (!retries) {
+		flags.result = 1;
+		if (DEBUG)
+			printf("All transactions failed unexpectedly\n");
+
+	}
+}
+
+int main(int argc, char **argv)
+{
+	int exception; /* FP = 0, VEC = 1, VSX = 2 */
+	pthread_t t1;
+	pthread_attr_t attr;
+	cpu_set_t cpuset;
+
+	/* Set only CPU 0 in the mask. Both threads will be bound to CPU 0. */
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+
+	/* Init pthread attribute. */
+	pthread_attr_init(&attr);
+
+	/* Set CPU 0 mask into the pthread attribute. */
+	pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+
+	pthread_create(&t1, &attr /* Bind 'pong' to CPU 0 */, pong, NULL);
+	pthread_setname_np(t1, "pong"); /* Name it for systemtap convenience */
+
+	flags.result = 0;
+
+	for (exception = 0; exception < NUM_EXCEPTIONS; exception++) {
+		printf("Checking if FP/VEC registers are sane after");
+
+		if (exception == FP_UNA_EXCEPTION)
+			printf(" a FP unavailable exception...\n");
+
+		else if (exception == VEC_UNA_EXCEPTION)
+			printf(" a VEC unavailable exception...\n");
+
+		else
+			printf(" a VSX unavailable exception...\n");
+
+		flags.exception = exception;
+
+		test_fp_vec(0, 0, &attr);
+		test_fp_vec(1, 0, &attr);
+		test_fp_vec(0, 1, &attr);
+		test_fp_vec(1, 1, &attr);
+
+	}
+
+	if (flags.result > 0) {
+		printf("result: failed!\n");
+		exit(1);
+	} else {
+		printf("result: success\n");
+		exit(0);
+	}
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
index 0ffff04433c5..df4204247d45 100644
--- a/tools/testing/selftests/powerpc/tm/tm.h
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -47,6 +47,11 @@ static inline bool failure_is_syscall(void)
 	return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL;
 }
 
+static inline bool failure_is_unavailable(void)
+{
+	return (failure_code() & TM_CAUSE_FAC_UNAV) == TM_CAUSE_FAC_UNAV;
+}
+
 static inline bool failure_is_nesting(void)
 {
 	return (__builtin_get_texasru() & 0x400000);