Merge tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Enable KFENCE for 32-bit.

 - Implement EBPF for 32-bit.

 - Convert 32-bit to do interrupt entry/exit in C.

 - Convert 64-bit BookE to do interrupt entry/exit in C.

 - Changes to our signal handling code to use user_access_begin/end()
   more extensively.

 - Add support for time namespaces (CONFIG_TIME_NS)

 - A series of fixes that allow us to reenable STRICT_KERNEL_RWX.

 - Other smaller features, fixes & cleanups.

Thanks to Alexey Kardashevskiy, Andreas Schwab, Andrew Donnellan, Aneesh
Kumar K.V, Athira Rajeev, Bhaskar Chowdhury, Bixuan Cui, Cédric Le
Goater, Chen Huang, Chris Packham, Christophe Leroy, Christopher M.
Riedl, Colin Ian King, Dan Carpenter, Daniel Axtens, Daniel Henrique
Barboza, David Gibson, Davidlohr Bueso, Denis Efremov, dingsenjie,
Dmitry Safonov, Dominic DeMarco, Fabiano Rosas, Ganesh Goudar, Geert
Uytterhoeven, Geetika Moolchandani, Greg Kurz, Guenter Roeck, Haren
Myneni, He Ying, Jiapeng Chong, Jordan Niethe, Laurent Dufour, Lee
Jones, Leonardo Bras, Li Huafei, Madhavan Srinivasan, Mahesh Salgaonkar,
Masahiro Yamada, Nathan Chancellor, Nathan Lynch, Nicholas Piggin,
Oliver O'Halloran, Paul Menzel, Pu Lehui, Randy Dunlap, Ravi Bangoria,
Rosen Penev, Russell Currey, Santosh Sivaraj, Sebastian Andrzej Siewior,
Segher Boessenkool, Shivaprasad G Bhat, Srikar Dronamraju, Stephen
Rothwell, Thadeu Lima de Souza Cascardo, Thomas Gleixner, Tony Ambardar,
Tyrel Datwyler, Vaibhav Jain, Vincenzo Frascino, Xiongwei Song, Yang Li,
Yu Kuai, and Zhang Yunkai.

* tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (302 commits)
  powerpc/signal32: Fix erroneous SIGSEGV on RT signal return
  powerpc: Avoid clang uninitialized warning in __get_user_size_allowed
  powerpc/papr_scm: Mark nvdimm as unarmed if needed during probe
  powerpc/kvm: Fix build error when PPC_MEM_KEYS/PPC_PSERIES=n
  powerpc/kasan: Fix shadow start address with modules
  powerpc/kernel/iommu: Use largepool as a last resort when !largealloc
  powerpc/kernel/iommu: Align size for IOMMU_PAGE_SIZE() to save TCEs
  powerpc/44x: fix spelling mistake in Kconfig "varients" -> "variants"
  powerpc/iommu: Annotate nested lock for lockdep
  powerpc/iommu: Do not immediately panic when failed IOMMU table allocation
  powerpc/iommu: Allocate it_map by vmalloc
  selftests/powerpc: remove unneeded semicolon
  powerpc/64s: remove unneeded semicolon
  powerpc/eeh: remove unneeded semicolon
  powerpc/selftests: Add selftest to test concurrent perf/ptrace events
  powerpc/selftests/perf-hwbreak: Add testcases for 2nd DAWR
  powerpc/selftests/perf-hwbreak: Coalesce event creation code
  powerpc/selftests/ptrace-hwbreak: Add testcases for 2nd DAWR
  powerpc/configs: Add IBMVNIC to some 64-bit configs
  selftests/powerpc: Add uaccess flush test
  ...

17 files changed, 1578 insertions, 58 deletions

diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
index c25cf7cd45e9..33ee34fc0828 100644
--- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c
+++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
@@ -10,16 +10,7 @@
  *
  * We create two sets of source and destination buffers, one in regular memory,
  * the other cache-inhibited (by default we use /dev/fb0 for this, but an
- * alterative path for cache-inhibited memory may be provided).
- *
- * One way to get cache-inhibited memory is to use the "mem" kernel parameter
- * to limit the kernel to less memory than actually exists.  Addresses above
- * the limit may still be accessed but will be treated as cache-inhibited. For
- * example, if there is actually 4GB of memory and the parameter "mem=3GB" is
- * used, memory from address 0xC0000000 onwards is treated as cache-inhibited.
- * To access this region /dev/mem is used. The kernel should be configured
- * without CONFIG_STRICT_DEVMEM. In this case use:
- *         ./alignment_handler /dev/mem 0xc0000000
+ * alterative path for cache-inhibited memory may be provided, e.g. memtrace).
  *
  * We initialise the source buffers, then use whichever set of load/store
  * instructions is under test to copy bytes from the source buffers to the
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index defe488d6bf1..40253abc6208 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -5,6 +5,7 @@ noarg:
 TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
 		  large_vm_fork_separation bad_accesses pkey_exec_prot \
 		  pkey_siginfo stack_expansion_signal stack_expansion_ldst
+TEST_PROGS := stress_code_patching.sh
 
 TEST_GEN_PROGS_EXTENDED := tlbie_test
 TEST_GEN_FILES := tempfile
diff --git a/tools/testing/selftests/powerpc/mm/stress_code_patching.sh b/tools/testing/selftests/powerpc/mm/stress_code_patching.sh
new file mode 100755
index 000000000000..e454509659f6
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/stress_code_patching.sh
@@ -0,0 +1,49 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+TIMEOUT=30
+
+DEBUFS_DIR=`cat /proc/mounts | grep debugfs | awk '{print $2}'`
+if [ ! -e "$DEBUFS_DIR" ]
+then
+	echo "debugfs not found, skipping" 1>&2
+	exit 4
+fi
+
+if [ ! -e "$DEBUFS_DIR/tracing/current_tracer" ]
+then
+	echo "Tracing files not found, skipping" 1>&2
+	exit 4
+fi
+
+
+echo "Testing for spurious faults when mapping kernel memory..."
+
+if grep -q "FUNCTION TRACING IS CORRUPTED" "$DEBUFS_DIR/tracing/trace"
+then
+	echo "FAILED: Ftrace already dead. Probably due to a spurious fault" 1>&2
+	exit 1
+fi
+
+dmesg -C
+START_TIME=`date +%s`
+END_TIME=`expr $START_TIME + $TIMEOUT`
+while [ `date +%s` -lt $END_TIME ]
+do
+	echo function > $DEBUFS_DIR/tracing/current_tracer
+	echo nop > $DEBUFS_DIR/tracing/current_tracer
+	if dmesg | grep -q 'ftrace bug'
+	then
+		break
+	fi
+done
+
+echo nop > $DEBUFS_DIR/tracing/current_tracer
+if dmesg | grep -q 'ftrace bug'
+then
+	echo "FAILED: Mapping kernel memory causes spurious faults" 1>&2
+	exit 1
+else
+	echo "OK: Mapping kernel memory does not cause spurious faults"
+	exit 0
+fi
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
index 02dffb65de48..b099753b50e4 100644
--- a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
+++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
@@ -324,7 +324,7 @@ int compress_file(int argc, char **argv, void *handle)
 				fprintf(stderr, "error: cannot progress; ");
 				fprintf(stderr, "too many faults\n");
 				exit(-1);
-			};
+			}
 		}
 
 		fault_tries = NX_MAX_FAULTS; /* Reset for the next chunk */
diff --git a/tools/testing/selftests/powerpc/ptrace/.gitignore b/tools/testing/selftests/powerpc/ptrace/.gitignore
index 0e96150b7c7e..eb75e5360e31 100644
--- a/tools/testing/selftests/powerpc/ptrace/.gitignore
+++ b/tools/testing/selftests/powerpc/ptrace/.gitignore
@@ -14,3 +14,4 @@ perf-hwbreak
 core-pkey
 ptrace-pkey
 ptrace-syscall
+ptrace-perf-hwbreak
diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 8d3f006c98cc..a500639da97a 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -2,7 +2,7 @@
 TEST_GEN_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
               ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \
               ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \
-              perf-hwbreak ptrace-syscall
+              perf-hwbreak ptrace-syscall ptrace-perf-hwbreak
 
 top_srcdir = ../../../../..
 include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c
index c1f324afdbf3..ecde2c199f3b 100644
--- a/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c
+++ b/tools/testing/selftests/powerpc/ptrace/perf-hwbreak.c
@@ -21,8 +21,13 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <signal.h>
 #include <string.h>
 #include <sys/ioctl.h>
+#include <sys/wait.h>
+#include <sys/ptrace.h>
+#include <sys/sysinfo.h>
+#include <asm/ptrace.h>
 #include <elf.h>
 #include <pthread.h>
 #include <sys/syscall.h>
@@ -30,32 +35,130 @@
 #include <linux/hw_breakpoint.h>
 #include "utils.h"
 
+#ifndef PPC_DEBUG_FEATURE_DATA_BP_ARCH_31
+#define PPC_DEBUG_FEATURE_DATA_BP_ARCH_31	0x20
+#endif
+
 #define MAX_LOOPS 10000
 
 #define DAWR_LENGTH_MAX ((0x3f + 1) * 8)
 
-static inline int sys_perf_event_open(struct perf_event_attr *attr, pid_t pid,
-				      int cpu, int group_fd,
-				      unsigned long flags)
+int nprocs;
+
+static volatile int a = 10;
+static volatile int b = 10;
+static volatile char c[512 + 8] __attribute__((aligned(512)));
+
+static void perf_event_attr_set(struct perf_event_attr *attr,
+				__u32 type, __u64 addr, __u64 len,
+				bool exclude_user)
 {
-	attr->size = sizeof(*attr);
-	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+	memset(attr, 0, sizeof(struct perf_event_attr));
+	attr->type           = PERF_TYPE_BREAKPOINT;
+	attr->size           = sizeof(struct perf_event_attr);
+	attr->bp_type        = type;
+	attr->bp_addr        = addr;
+	attr->bp_len         = len;
+	attr->exclude_kernel = 1;
+	attr->exclude_hv     = 1;
+	attr->exclude_guest  = 1;
+	attr->exclude_user   = exclude_user;
+	attr->disabled       = 1;
 }
 
-static inline bool breakpoint_test(int len)
+static int
+perf_process_event_open_exclude_user(__u32 type, __u64 addr, __u64 len, bool exclude_user)
+{
+	struct perf_event_attr attr;
+
+	perf_event_attr_set(&attr, type, addr, len, exclude_user);
+	return syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
+}
+
+static int perf_process_event_open(__u32 type, __u64 addr, __u64 len)
+{
+	struct perf_event_attr attr;
+
+	perf_event_attr_set(&attr, type, addr, len, 0);
+	return syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
+}
+
+static int perf_cpu_event_open(long cpu, __u32 type, __u64 addr, __u64 len)
 {
 	struct perf_event_attr attr;
+
+	perf_event_attr_set(&attr, type, addr, len, 0);
+	return syscall(__NR_perf_event_open, &attr, -1, cpu, -1, 0);
+}
+
+static void close_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		close(fd[i]);
+}
+
+static unsigned long read_fds(int *fd, int n)
+{
+	int i;
+	unsigned long c = 0;
+	unsigned long count = 0;
+	size_t res;
+
+	for (i = 0; i < n; i++) {
+		res = read(fd[i], &c, sizeof(c));
+		assert(res == sizeof(unsigned long long));
+		count += c;
+	}
+	return count;
+}
+
+static void reset_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		ioctl(fd[i], PERF_EVENT_IOC_RESET);
+}
+
+static void enable_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		ioctl(fd[i], PERF_EVENT_IOC_ENABLE);
+}
+
+static void disable_fds(int *fd, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		ioctl(fd[i], PERF_EVENT_IOC_DISABLE);
+}
+
+static int perf_systemwide_event_open(int *fd, __u32 type, __u64 addr, __u64 len)
+{
+	int i = 0;
+
+	/* Assume online processors are 0 to nprocs for simplisity */
+	for (i = 0; i < nprocs; i++) {
+		fd[i] = perf_cpu_event_open(i, type, addr, len);
+		if (fd[i] < 0) {
+			close_fds(fd, i);
+			return fd[i];
+		}
+	}
+	return 0;
+}
+
+static inline bool breakpoint_test(int len)
+{
 	int fd;
 
-	/* setup counters */
-	memset(&attr, 0, sizeof(attr));
-	attr.disabled = 1;
-	attr.type = PERF_TYPE_BREAKPOINT;
-	attr.bp_type = HW_BREAKPOINT_R;
 	/* bp_addr can point anywhere but needs to be aligned */
-	attr.bp_addr = (__u64)(&attr) & 0xfffffffffffff800;
-	attr.bp_len = len;
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	fd = perf_process_event_open(HW_BREAKPOINT_R, (__u64)(&fd) & 0xfffffffffffff800, len);
 	if (fd < 0)
 		return false;
 	close(fd);
@@ -75,7 +178,6 @@ static inline bool dawr_supported(void)
 static int runtestsingle(int readwriteflag, int exclude_user, int arraytest)
 {
 	int i,j;
-	struct perf_event_attr attr;
 	size_t res;
 	unsigned long long breaks, needed;
 	int readint;
@@ -85,6 +187,7 @@ static int runtestsingle(int readwriteflag, int exclude_user, int arraytest)
 	int break_fd;
 	int loop_num = MAX_LOOPS - (rand() % 100); /* provide some variability */
 	volatile int *k;
+	__u64 len;
 
 	/* align to 0x400 boundary as required by DAWR */
 	readintalign = (int *)(((unsigned long)readintarraybig + 0x7ff) &
@@ -94,19 +197,11 @@ static int runtestsingle(int readwriteflag, int exclude_user, int arraytest)
 	if (arraytest)
 		ptr = &readintalign[0];
 
-	/* setup counters */
-	memset(&attr, 0, sizeof(attr));
-	attr.disabled = 1;
-	attr.type = PERF_TYPE_BREAKPOINT;
-	attr.bp_type = readwriteflag;
-	attr.bp_addr = (__u64)ptr;
-	attr.bp_len = sizeof(int);
-	if (arraytest)
-		attr.bp_len = DAWR_LENGTH_MAX;
-	attr.exclude_user = exclude_user;
-	break_fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	len = arraytest ? DAWR_LENGTH_MAX : sizeof(int);
+	break_fd = perf_process_event_open_exclude_user(readwriteflag, (__u64)ptr,
+							len, exclude_user);
 	if (break_fd < 0) {
-		perror("sys_perf_event_open");
+		perror("perf_process_event_open_exclude_user");
 		exit(1);
 	}
 
@@ -153,7 +248,6 @@ static int runtest_dar_outside(void)
 	void *target;
 	volatile __u16 temp16;
 	volatile __u64 temp64;
-	struct perf_event_attr attr;
 	int break_fd;
 	unsigned long long breaks;
 	int fail = 0;
@@ -165,21 +259,11 @@ static int runtest_dar_outside(void)
 		exit(EXIT_FAILURE);
 	}
 
-	/* setup counters */
-	memset(&attr, 0, sizeof(attr));
-	attr.disabled = 1;
-	attr.type = PERF_TYPE_BREAKPOINT;
-	attr.exclude_kernel = 1;
-	attr.exclude_hv = 1;
-	attr.exclude_guest = 1;
-	attr.bp_type = HW_BREAKPOINT_RW;
 	/* watch middle half of target array */
-	attr.bp_addr = (__u64)(target + 2);
-	attr.bp_len = 4;
-	break_fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	break_fd = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)(target + 2), 4);
 	if (break_fd < 0) {
 		free(target);
-		perror("sys_perf_event_open");
+		perror("perf_process_event_open");
 		exit(EXIT_FAILURE);
 	}
 
@@ -263,11 +347,467 @@ static int runtest_dar_outside(void)
 	return fail;
 }
 
+static void multi_dawr_workload(void)
+{
+	a += 10;
+	b += 10;
+	c[512 + 1] += 'a';
+}
+
+static int test_process_multi_diff_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, diff addr";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&b, (__u64)sizeof(b));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_process_multi_same_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, same addr";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_process_multi_diff_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, diff addr, one is RO, other is WO";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_R, (__u64)&b, (__u64)sizeof(b));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_process_multi_same_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int fd1, fd2;
+	char *desc = "Process specific, Two events, same addr, one is RO, other is WO";
+	size_t res;
+
+	fd1 = perf_process_event_open(HW_BREAKPOINT_R, (__u64)&a, (__u64)sizeof(a));
+	if (fd1 < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	fd2 = perf_process_event_open(HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (fd2 < 0) {
+		close(fd1);
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd1, PERF_EVENT_IOC_RESET);
+	ioctl(fd2, PERF_EVENT_IOC_RESET);
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd1, &breaks1, sizeof(breaks1));
+	assert(res == sizeof(unsigned long long));
+	res = read(fd2, &breaks2, sizeof(breaks2));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd1);
+	close(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_diff_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, diff addr";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_RW, (__u64)&b, (__u64)sizeof(b));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_same_addr(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, same addr";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_RW, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 2 || breaks2 != 2) {
+		printf("FAILED: %s: %lld != 2 || %lld != 2\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_diff_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, diff addr, one is RO, other is WO";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_R, (__u64)&b, (__u64)sizeof(b));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int test_syswide_multi_same_addr_ro_wo(void)
+{
+	unsigned long long breaks1 = 0, breaks2 = 0;
+	int *fd1 = malloc(nprocs * sizeof(int));
+	int *fd2 = malloc(nprocs * sizeof(int));
+	char *desc = "Systemwide, Two events, same addr, one is RO, other is WO";
+	int ret;
+
+	ret = perf_systemwide_event_open(fd1, HW_BREAKPOINT_W, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ret = perf_systemwide_event_open(fd2, HW_BREAKPOINT_R, (__u64)&a, (__u64)sizeof(a));
+	if (ret) {
+		close_fds(fd1, nprocs);
+		perror("perf_systemwide_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	reset_fds(fd1, nprocs);
+	reset_fds(fd2, nprocs);
+	enable_fds(fd1, nprocs);
+	enable_fds(fd2, nprocs);
+	multi_dawr_workload();
+	disable_fds(fd1, nprocs);
+	disable_fds(fd2, nprocs);
+
+	breaks1 = read_fds(fd1, nprocs);
+	breaks2 = read_fds(fd2, nprocs);
+
+	close_fds(fd1, nprocs);
+	close_fds(fd2, nprocs);
+
+	free(fd1);
+	free(fd2);
+
+	if (breaks1 != 1 || breaks2 != 1) {
+		printf("FAILED: %s: %lld != 1 || %lld != 1\n", desc, breaks1, breaks2);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+static int runtest_multi_dawr(void)
+{
+	int ret = 0;
+
+	ret |= test_process_multi_diff_addr();
+	ret |= test_process_multi_same_addr();
+	ret |= test_process_multi_diff_addr_ro_wo();
+	ret |= test_process_multi_same_addr_ro_wo();
+	ret |= test_syswide_multi_diff_addr();
+	ret |= test_syswide_multi_same_addr();
+	ret |= test_syswide_multi_diff_addr_ro_wo();
+	ret |= test_syswide_multi_same_addr_ro_wo();
+
+	return ret;
+}
+
+static int runtest_unaligned_512bytes(void)
+{
+	unsigned long long breaks = 0;
+	int fd;
+	char *desc = "Process specific, 512 bytes, unaligned";
+	__u64 addr = (__u64)&c + 8;
+	size_t res;
+
+	fd = perf_process_event_open(HW_BREAKPOINT_RW, addr, 512);
+	if (fd < 0) {
+		perror("perf_process_event_open");
+		exit(EXIT_FAILURE);
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE);
+	multi_dawr_workload();
+	ioctl(fd, PERF_EVENT_IOC_DISABLE);
+
+	res = read(fd, &breaks, sizeof(breaks));
+	assert(res == sizeof(unsigned long long));
+
+	close(fd);
+
+	if (breaks != 2) {
+		printf("FAILED: %s: %lld != 2\n", desc, breaks);
+		return 1;
+	}
+
+	printf("TESTED: %s\n", desc);
+	return 0;
+}
+
+/* There is no perf api to find number of available watchpoints. Use ptrace. */
+static int get_nr_wps(bool *arch_31)
+{
+	struct ppc_debug_info dbginfo;
+	int child_pid;
+
+	child_pid = fork();
+	if (!child_pid) {
+		int ret = ptrace(PTRACE_TRACEME, 0, NULL, 0);
+		if (ret) {
+			perror("PTRACE_TRACEME failed\n");
+			exit(EXIT_FAILURE);
+		}
+		kill(getpid(), SIGUSR1);
+
+		sleep(1);
+		exit(EXIT_SUCCESS);
+	}
+
+	wait(NULL);
+	if (ptrace(PPC_PTRACE_GETHWDBGINFO, child_pid, NULL, &dbginfo)) {
+		perror("Can't get breakpoint info");
+		exit(EXIT_FAILURE);
+	}
+
+	*arch_31 = !!(dbginfo.features & PPC_DEBUG_FEATURE_DATA_BP_ARCH_31);
+	return dbginfo.num_data_bps;
+}
+
 static int runtest(void)
 {
 	int rwflag;
 	int exclude_user;
 	int ret;
+	bool dawr = dawr_supported();
+	bool arch_31 = false;
+	int nr_wps = get_nr_wps(&arch_31);
 
 	/*
 	 * perf defines rwflag as two bits read and write and at least
@@ -280,7 +820,7 @@ static int runtest(void)
 				return ret;
 
 			/* if we have the dawr, we can do an array test */
-			if (!dawr_supported())
+			if (!dawr)
 				continue;
 			ret = runtestsingle(rwflag, exclude_user, 1);
 			if (ret)
@@ -289,6 +829,19 @@ static int runtest(void)
 	}
 
 	ret = runtest_dar_outside();
+	if (ret)
+		return ret;
+
+	if (dawr && nr_wps > 1) {
+		nprocs = get_nprocs();
+		ret = runtest_multi_dawr();
+		if (ret)
+			return ret;
+	}
+
+	if (dawr && arch_31)
+		ret = runtest_unaligned_512bytes();
+
 	return ret;
 }
 
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
index 2e0d86e0687e..a0635a3819aa 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
@@ -194,6 +194,18 @@ static void test_workload(void)
 		big_var[rand() % DAWR_MAX_LEN] = 'a';
 	else
 		cvar = big_var[rand() % DAWR_MAX_LEN];
+
+	/* PPC_PTRACE_SETHWDEBUG 2, MODE_RANGE, DW ALIGNED, WO test */
+	gstruct.a[rand() % A_LEN] = 'a';
+
+	/* PPC_PTRACE_SETHWDEBUG 2, MODE_RANGE, DW UNALIGNED, RO test */
+	cvar = gstruct.b[rand() % B_LEN];
+
+	/* PPC_PTRACE_SETHWDEBUG 2, MODE_RANGE, DAWR Overlap, WO test */
+	gstruct.a[rand() % A_LEN] = 'a';
+
+	/* PPC_PTRACE_SETHWDEBUG 2, MODE_RANGE, DAWR Overlap, RO test */
+	cvar = gstruct.a[rand() % A_LEN];
 }
 
 static void check_success(pid_t child_pid, const char *name, const char *type,
@@ -417,6 +429,69 @@ static void test_sethwdebug_range_aligned(pid_t child_pid)
 	ptrace_delhwdebug(child_pid, wh);
 }
 
+static void test_multi_sethwdebug_range(pid_t child_pid)
+{
+	struct ppc_hw_breakpoint info1, info2;
+	unsigned long wp_addr1, wp_addr2;
+	char *name1 = "PPC_PTRACE_SETHWDEBUG 2, MODE_RANGE, DW ALIGNED";
+	char *name2 = "PPC_PTRACE_SETHWDEBUG 2, MODE_RANGE, DW UNALIGNED";
+	int len1, len2;
+	int wh1, wh2;
+
+	wp_addr1 = (unsigned long)&gstruct.a;
+	wp_addr2 = (unsigned long)&gstruct.b;