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
  ...

tools/testing/selftests/powerpc/benchmarks/null_syscall.c

@@ -25,7 +25,7 @@ unsigned long long clock_frequency;
 unsigned long long timebase_frequency;
 double timebase_multiplier;
 
-static inline unsigned long long mftb(void)
+static inline unsigned long mftb(void)
 {
 	unsigned long low;
 

tools/testing/selftests/powerpc/include/reg.h

@@ -77,6 +77,14 @@
 #define TEXASR_TE	0x0000000004000000
 #define TEXASR_ROT	0x0000000002000000
 
+/* MSR register bits */
+#define MSR_TS_S_LG     33              /* Trans Mem state: Suspended */
+
+#define __MASK(X)       (1UL<<(X))
+
+/* macro to check TM MSR bits */
+#define MSR_TS_S        __MASK(MSR_TS_S_LG)   /* Transaction Suspended */
+
 /* Vector Instructions */
 #define VSX_XX1(xs, ra, rb)	(((xs) & 0x1f) << 21 | ((ra) << 16) |  \
 				 ((rb) << 11) | (((xs) >> 5)))

tools/testing/selftests/powerpc/include/utils.h

@@ -102,8 +102,10 @@ do {								\
 
 #if defined(__powerpc64__)
 #define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.gp_regs[PT_NIP]
+#define UCONTEXT_MSR(UC)	(UC)->uc_mcontext.gp_regs[PT_MSR]
 #elif defined(__powerpc__)
 #define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.uc_regs->gregs[PT_NIP]
+#define UCONTEXT_MSR(UC)	(UC)->uc_mcontext.uc_regs->gregs[PT_MSR]
 #else
 #error implement UCONTEXT_NIA
 #endif

tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c

@@ -11,7 +11,6 @@
 #include <sys/wait.h>
 #include <unistd.h>
 #include <setjmp.h>
-#include <signal.h>
 
 #include "ebb.h"
 

tools/testing/selftests/powerpc/tm/.gitignore

@@ -11,6 +11,7 @@ tm-signal-context-chk-fpu
 tm-signal-context-chk-gpr
 tm-signal-context-chk-vmx
 tm-signal-context-chk-vsx
+tm-signal-context-force-tm
 tm-signal-sigreturn-nt
 tm-vmx-unavail
 tm-unavailable

tools/testing/selftests/powerpc/tm/Makefile

@@ -4,7 +4,8 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu
 
 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-unavailable tm-trap \
-	$(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt
+	$(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt \
+	tm-signal-context-force-tm
 
 top_srcdir = ../../../../..
 include ../../lib.mk
@@ -20,6 +21,7 @@ $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
 $(OUTPUT)/tm-resched-dscr: ../pmu/lib.c
 $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64
+$(OUTPUT)/tm-signal-context-force-tm: CFLAGS += -pthread -m64
 
 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
 $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S

tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c

@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018, Breno Leitao, Gustavo Romero, IBM Corp.
+ *
+ * This test raises a SIGUSR1 signal, and toggle the MSR[TS]
+ * fields at the signal handler. With MSR[TS] being set, the kernel will
+ * force a recheckpoint, which may cause a segfault when returning to
+ * user space. Since the test needs to re-run, the segfault needs to be
+ * caught and handled.
+ *
+ * In order to continue the test even after a segfault, the context is
+ * saved prior to the signal being raised, and it is restored when there is
+ * a segmentation fault. This happens for COUNT_MAX times.
+ *
+ * This test never fails (as returning EXIT_FAILURE). It either succeeds,
+ * or crash the kernel (on a buggy kernel).
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+#include <ucontext.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+#include "tm.h"
+#include "utils.h"
+#include "reg.h"
+
+#define COUNT_MAX       5000		/* Number of interactions */
+
+/*
+ * This test only runs on 64 bits system. Unsetting MSR_TS_S to avoid
+ * compilation issue on 32 bits system. There is no side effect, since the
+ * whole test will be skipped if it is not running on 64 bits system.
+ */
+#ifndef __powerpc64__
+#undef  MSR_TS_S
+#define MSR_TS_S	0
+#endif
+
+/* Setting contexts because the test will crash and we want to recover */
+ucontext_t init_context, main_context;
+
+static int count, first_time;
+
+void usr_signal_handler(int signo, siginfo_t *si, void *uc)
+{
+	ucontext_t *ucp = uc;
+	int ret;
+
+	/*
+	 * Allocating memory in a signal handler, and never freeing it on
+	 * purpose, forcing the heap increase, so, the memory leak is what
+	 * we want here.
+	 */
+	ucp->uc_link = mmap(NULL, sizeof(ucontext_t),
+			    PROT_READ | PROT_WRITE,
+			    MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+	if (ucp->uc_link == (void *)-1) {
+		perror("Mmap failed");
+		exit(-1);
+	}
+
+	/* Forcing the page to be allocated in a page fault */
+	ret = madvise(ucp->uc_link, sizeof(ucontext_t), MADV_DONTNEED);
+	if (ret) {
+		perror("madvise failed");
+		exit(-1);
+	}
+
+	memcpy(&ucp->uc_link->uc_mcontext, &ucp->uc_mcontext,
+		sizeof(ucp->uc_mcontext));
+
+	/* Forcing to enable MSR[TM] */
+	UCONTEXT_MSR(ucp) |= MSR_TS_S;
+
+	/*
+	 * A fork inside a signal handler seems to be more efficient than a
+	 * fork() prior to the signal being raised.
+	 */
+	if (fork() == 0) {
+		/*
+		 * Both child and parent will return, but, child returns
+		 * with count set so it will exit in the next segfault.
+		 * Parent will continue to loop.
+		 */
+		count = COUNT_MAX;
+	}
+
+	/*
+	 * If the change above does not hit the bug, it will cause a
+	 * segmentation fault, since the ck structures are NULL.
+	 */
+}
+
+void seg_signal_handler(int signo, siginfo_t *si, void *uc)
+{
+	if (count == COUNT_MAX) {
+		/* Return to tm_signal_force_msr() and exit */
+		setcontext(&main_context);
+	}
+
+	count++;
+
+	/* Reexecute the test */
+	setcontext(&init_context);
+}
+
+void tm_trap_test(void)
+{
+	struct sigaction usr_sa, seg_sa;
+	stack_t ss;
+
+	usr_sa.sa_flags = SA_SIGINFO | SA_ONSTACK;
+	usr_sa.sa_sigaction = usr_signal_handler;
+
+	seg_sa.sa_flags = SA_SIGINFO;
+	seg_sa.sa_sigaction = seg_signal_handler;
+
+	/*
+	 * Set initial context. Will get back here from
+	 * seg_signal_handler()
+	 */
+	getcontext(&init_context);
+
+	/* Allocated an alternative signal stack area */
+	ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+	ss.ss_size = SIGSTKSZ;
+	ss.ss_flags = 0;
+
+	if (ss.ss_sp == (void *)-1) {
+		perror("mmap error\n");
+		exit(-1);
+	}
+
+	/* Force the allocation through a page fault */
+	if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) {
+		perror("madvise\n");
+		exit(-1);
+	}
+
+	/* Setting an alternative stack to generate a page fault when
+	 * the signal is raised.
+	 */
+	if (sigaltstack(&ss, NULL)) {
+		perror("sigaltstack\n");
+		exit(-1);
+	}
+
+	/* The signal handler will enable MSR_TS */
+	sigaction(SIGUSR1, &usr_sa, NULL);
+	/* If it does not crash, it will segfault, avoid it to retest */
+	sigaction(SIGSEGV, &seg_sa, NULL);
+
+	raise(SIGUSR1);
+}
+
+int tm_signal_context_force_tm(void)
+{
+	SKIP_IF(!have_htm());
+	/*
+	 * Skipping if not running on 64 bits system, since I think it is
+	 * not possible to set mcontext's [MSR] with TS, due to it being 32
+	 * bits.
+	 */
+	SKIP_IF(!is_ppc64le());
+
+	/* Will get back here after COUNT_MAX interactions */
+	getcontext(&main_context);
+
+	if (!first_time++)
+		tm_trap_test();
+
+	return EXIT_SUCCESS;
+}
+
+int main(int argc, char **argv)
+{
+	test_harness(tm_signal_context_force_tm, "tm_signal_context_force_tm");
+}

tools/testing/selftests/vm/map_hugetlb.c

@@ -23,6 +23,14 @@
 #define MAP_HUGETLB 0x40000 /* arch specific */
 #endif
 
+#ifndef MAP_HUGE_SHIFT
+#define MAP_HUGE_SHIFT 26
+#endif
+
+#ifndef MAP_HUGE_MASK
+#define MAP_HUGE_MASK 0x3f
+#endif
+
 /* Only ia64 requires this */
 #ifdef __ia64__
 #define ADDR (void *)(0x8000000000000000UL)
@@ -58,12 +66,29 @@ static int read_bytes(char *addr)
 	return 0;
 }
 
-int main(void)
+int main(int argc, char **argv)
 {
 	void *addr;
 	int ret;
+	size_t length = LENGTH;
+	int flags = FLAGS;
+	int shift = 0;
 
-	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, -1, 0);
+	if (argc > 1)
+		length = atol(argv[1]) << 20;
+	if (argc > 2) {
+		shift = atoi(argv[2]);
+		if (shift)
+			flags |= (shift & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
+	}
+
+	if (shift)
+		printf("%u kB hugepages\n", 1 << shift);
+	else
+		printf("Default size hugepages\n");
+	printf("Mapping %lu Mbytes\n", (unsigned long)length >> 20);
+
+	addr = mmap(ADDR, length, PROTECTION, flags, -1, 0);
 	if (addr == MAP_FAILED) {
 		perror("mmap");
 		exit(1);