Merge tag 'powerpc-4.12-3' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "The headliner is a fix for FP/VMX register corruption when using
  transactional memory, and a new selftest to go with it.

  Then there's the virt_addr_valid() fix, currently HARDENDED_USERCOPY
  is tripping on that causing some machines to crash.

  A few other fairly minor fixes for long tail things, and a couple of
  fixes for code we just merged.

  Thanks to: Breno Leitao, Gautham Shenoy, Michael Neuling, Naveen Rao.
  Nicholas Piggin, Paul Mackerras"

* tag 'powerpc-4.12-3' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/mm: Fix virt_addr_valid() etc. on 64-bit hash
  powerpc/mm: Fix crash in page table dump with huge pages
  powerpc/kprobes: Fix handling of instruction emulation on probe re-entry
  powerpc/powernv: Set NAPSTATELOST after recovering paca on P9 DD1
  selftests/powerpc: Test TM and VMX register state
  powerpc/tm: Fix FP and VMX register corruption
  powerpc/modules: If mprofile-kernel is enabled add it to vermagic

9 files changed, 164 insertions, 6 deletions

diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 53885512b8d3..6c0132c7212f 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -14,6 +14,10 @@
 #include <asm-generic/module.h>
 
 
+#ifdef CC_USING_MPROFILE_KERNEL
+#define MODULE_ARCH_VERMAGIC	"mprofile-kernel"
+#endif
+
 #ifndef __powerpc64__
 /*
  * Thanks to Paul M for explaining this.
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 2a32483c7b6c..8da5d4c1cab2 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -132,7 +132,19 @@ extern long long virt_phys_offset;
 #define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
 #define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * On hash the vmalloc and other regions alias to the kernel region when passed
+ * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can
+ * return true for some vmalloc addresses, which is incorrect. So explicitly
+ * check that the address is in the kernel region.
+ */
+#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \
+				pfn_valid(virt_to_pfn(kaddr)))
+#else
 #define virt_addr_valid(kaddr)	pfn_valid(virt_to_pfn(kaddr))
+#endif
 
 /*
  * On Book-E parts we need __va to parse the device tree and we can't
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 07d4e0ad60db..4898d676dcae 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -416,7 +416,7 @@ power9_dd1_recover_paca:
 	 * which needs to be restored from the stack.
 	 */
 	li	r3, 1
-	stb	r0,PACA_NAPSTATELOST(r13)
+	stb	r3,PACA_NAPSTATELOST(r13)
 	blr
 
 /*
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 160ae0fa7d0d..fc4343514bed 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -305,16 +305,17 @@ int kprobe_handler(struct pt_regs *regs)
 			save_previous_kprobe(kcb);
 			set_current_kprobe(p, regs, kcb);
 			kprobes_inc_nmissed_count(p);
-			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			if (p->ainsn.boostable >= 0) {
 				ret = try_to_emulate(p, regs);
 
 				if (ret > 0) {
 					restore_previous_kprobe(kcb);
+					preempt_enable_no_resched();
 					return 1;
 				}
 			}
+			prepare_singlestep(p, regs);
 			return 1;
 		} else {
 			if (*addr != BREAKPOINT_INSTRUCTION) {
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d645da302bf2..baae104b16c7 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -864,6 +864,25 @@ static void tm_reclaim_thread(struct thread_struct *thr,
 	if (!MSR_TM_SUSPENDED(mfmsr()))
 		return;
 
+	/*
+	 * If we are in a transaction and FP is off then we can't have
+	 * used FP inside that transaction. Hence the checkpointed
+	 * state is the same as the live state. We need to copy the
+	 * live state to the checkpointed state so that when the
+	 * transaction is restored, the checkpointed state is correct
+	 * and the aborted transaction sees the correct state. We use
+	 * ckpt_regs.msr here as that's what tm_reclaim will use to
+	 * determine if it's going to write the checkpointed state or
+	 * not. So either this will write the checkpointed registers,
+	 * or reclaim will. Similarly for VMX.
+	 */
+	if ((thr->ckpt_regs.msr & MSR_FP) == 0)
+		memcpy(&thr->ckfp_state, &thr->fp_state,
+		       sizeof(struct thread_fp_state));
+	if ((thr->ckpt_regs.msr & MSR_VEC) == 0)
+		memcpy(&thr->ckvr_state, &thr->vr_state,
+		       sizeof(struct thread_vr_state));
+
 	giveup_all(container_of(thr, struct task_struct, thread));
 
 	tm_reclaim(thr, thr->ckpt_regs.msr, cause);
diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c
index d659345a98d6..44fe4833910f 100644
--- a/arch/powerpc/mm/dump_linuxpagetables.c
+++ b/arch/powerpc/mm/dump_linuxpagetables.c
@@ -16,6 +16,7 @@
  */
 #include <linux/debugfs.h>
 #include <linux/fs.h>
+#include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
@@ -391,7 +392,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 
 	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
 		addr = start + i * PMD_SIZE;
-		if (!pmd_none(*pmd))
+		if (!pmd_none(*pmd) && !pmd_huge(*pmd))
 			/* pmd exists */
 			walk_pte(st, pmd, addr);
 		else
@@ -407,7 +408,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 
 	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
 		addr = start + i * PUD_SIZE;
-		if (!pud_none(*pud))
+		if (!pud_none(*pud) && !pud_huge(*pud))
 			/* pud exists */
 			walk_pmd(st, pud, addr);
 		else
@@ -427,7 +428,7 @@ static void walk_pagetables(struct pg_state *st)
 	 */
 	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
 		addr = KERN_VIRT_START + i * PGDIR_SIZE;
-		if (!pgd_none(*pgd))
+		if (!pgd_none(*pgd) && !pgd_huge(*pgd))
 			/* pgd exists */
 			walk_pud(st, pgd, addr);
 		else
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 427621792229..2f1f7b013293 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -11,3 +11,4 @@ tm-signal-context-chk-fpu
 tm-signal-context-chk-gpr
 tm-signal-context-chk-vmx
 tm-signal-context-chk-vsx
+tm-vmx-unavail
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 5576ee6a51f2..958c11c14acd 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -2,7 +2,8 @@ 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 $(SIGNAL_CONTEXT_CHK_TESTS)
+	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail \
+	$(SIGNAL_CONTEXT_CHK_TESTS)
 
 include ../../lib.mk
 
@@ -13,6 +14,7 @@ CFLAGS += -mhtm
 $(OUTPUT)/tm-syscall: tm-syscall-asm.S
 $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
 $(OUTPUT)/tm-tmspr: CFLAGS += -pthread
+$(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
 
 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-vmx-unavail.c b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
new file mode 100644
index 000000000000..137185ba4937
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright 2017, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ * Original: Breno Leitao <brenohl@br.ibm.com> &
+ *           Gustavo Bueno Romero <gromero@br.ibm.com>
+ * Edited: Michael Neuling
+ *
+ * Force VMX unavailable during a transaction and see if it corrupts
+ * the checkpointed VMX register state after the abort.
+ */
+
+#include <inttypes.h>
+#include <htmintrin.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <pthread.h>
+
+#include "tm.h"
+#include "utils.h"
+
+int passed;
+
+void *worker(void *unused)
+{
+	__int128 vmx0;
+	uint64_t texasr;
+
+	asm goto (
+		"li       3, 1;"  /* Stick non-zero value in VMX0 */
+		"std      3, 0(%[vmx0_ptr]);"
+		"lvx      0, 0, %[vmx0_ptr];"
+
+		/* Wait here a bit so we get scheduled out 255 times */
+		"lis      3, 0x3fff;"
+		"1: ;"
+		"addi     3, 3, -1;"
+		"cmpdi    3, 0;"
+		"bne      1b;"
+
+		/* Kernel will hopefully turn VMX off now */
+
+		"tbegin. ;"
+		"beq      failure;"
+
+		/* Cause VMX unavail. Any VMX instruction */
+		"vaddcuw  0,0,0;"
+
+		"tend. ;"
+		"b        %l[success];"
+
+		/* Check VMX0 sanity after abort */
+		"failure: ;"
+		"lvx       1,  0, %[vmx0_ptr];"
+		"vcmpequb. 2,  0, 1;"
+		"bc        4, 24, %l[value_mismatch];"
+		"b        %l[value_match];"
+		:
+		: [vmx0_ptr] "r"(&vmx0)
+		: "r3"
+		: success, value_match, value_mismatch
+		);
+
+	/* HTM aborted and VMX0 is corrupted */
+value_mismatch:
+	texasr = __builtin_get_texasr();
+
+	printf("\n\n==============\n\n");
+	printf("Failure with error: %lx\n",   _TEXASR_FAILURE_CODE(texasr));
+	printf("Summary error     : %lx\n",   _TEXASR_FAILURE_SUMMARY(texasr));
+	printf("TFIAR exact       : %lx\n\n", _TEXASR_TFIAR_EXACT(texasr));
+
+	passed = 0;
+	return NULL;
+
+	/* HTM aborted but VMX0 is correct */
+value_match:
+//	printf("!");
+	return NULL;
+
+success:
+//	printf(".");
+	return NULL;
+}
+
+int tm_vmx_unavail_test()
+{
+	int threads;
+	pthread_t *thread;
+
+	SKIP_IF(!have_htm());
+
+	passed = 1;
+
+	threads = sysconf(_SC_NPROCESSORS_ONLN) * 4;
+	thread = malloc(sizeof(pthread_t)*threads);
+	if (!thread)
+		return EXIT_FAILURE;
+
+	for (uint64_t i = 0; i < threads; i++)
+		pthread_create(&thread[i], NULL, &worker, NULL);
+
+	for (uint64_t i = 0; i < threads; i++)
+		pthread_join(thread[i], NULL);
+
+	free(thread);
+
+	return passed ? EXIT_SUCCESS : EXIT_FAILURE;
+}
+
+
+int main(int argc, char **argv)
+{
+	return test_harness(tm_vmx_unavail_test, "tm_vmx_unavail_test");
+}