[RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call (v2)

[RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call (v2)

[Mathieu Desnoyers]

Hi,

Here is an updated patchset submitted as RFC for 4.21 (next merge
window).

This series contain:

- rseq selftests:
  - Added reference counter within user-space __rseq_abi structure, for
    integration of rseq application/libraries with future use by glibc,
  - Adapt number of threads to the number of online cpus.

- cpu_opv:
  - Introduce vm_map_user_ram()/vm_unmap_user_ram() (mm),
  - Provide is_vma_noncached() (mm),
  - Introduce cpu_opv system call, with vmap space limiting,
    - Wire up cpu_opv on x86, powerpc, arm,
  - Provide cpu_opv selftests.

The cpu_opv system call covers the use-cases that rseq does not handle,
namely single-stepping with debuggers, moving data between per-cpu data
structures without interfering with cpu affinity masks, and using rseq
from signal handlers nested between thread creation and rseq
registration by glibc, or between rseq unregistration by glibc and
thread teardown.

The cpu_opv system call has been greatly simplified since the last round
based on feedback from Peter Zijlstra and Will Deacon at OSS Europe.
Major simplifications are:

- Remove unnecessary operations. Only keep compare, memcpy,
  memcpy_release, add, add_release,
- Remove the "mb" instruction in favor of a release semantic,
- Use IPI to execute operations on remote CPUs rather than try to
  migrate the current thread,
- Reduce the maximum operation vector size from 16 to 4 elements,
  thus removing the need to perform memory allocation in the cpu_opv
  system call (there is enough space on the stack). Add a new flag
  allowing user-space to query the maximum vector size supported by
  the kernel for future extensibility.

Feedback is welcome!

Thanks,

Mathieu

Mathieu Desnoyers (16):
  rseq/selftests: Expose reference counter to coexist with glibc (v2)
  rseq/selftests: Adapt number of threads to the number of detected cpus
  mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram()
  mm: Introduce vm_map_user_ram, vm_unmap_user_ram (v2)
  mm: Provide is_vma_noncached
  cpu_opv: Provide cpu_opv system call (v9)
  cpu_opv: limit amount of virtual address space used by cpu_opv
  x86: Wire up cpu_opv system call
  powerpc: Wire up cpu_opv system call
  arm: Wire up cpu_opv system call
  cpu-opv/selftests: Provide cpu-op library
  cpu-opv/selftests: Provide basic test
  cpu-opv/selftests: Provide percpu_op API
  cpu-opv/selftests: Provide basic percpu ops test
  cpu-opv/selftests: Provide parametrized tests
  cpu-opv/selftests: Provide Makefile, scripts, gitignore

 MAINTAINERS                                        |    8 +
 arch/arm/tools/syscall.tbl                         |    1 +
 arch/powerpc/include/asm/systbl.h                  |    1 +
 arch/powerpc/include/uapi/asm/unistd.h             |    1 +
 arch/x86/entry/syscalls/syscall_32.tbl             |    1 +
 arch/x86/entry/syscalls/syscall_64.tbl             |    1 +
 include/linux/mm.h                                 |   24 +
 include/linux/syscalls.h                           |    3 +
 include/linux/vmalloc.h                            |    4 +
 include/uapi/linux/cpu_opv.h                       |   69 ++
 init/Kconfig                                       |   17 +
 kernel/Makefile                                    |    1 +
 kernel/cpu_opv.c                                   | 1027 +++++++++++++++++
 kernel/sys_ni.c                                    |    1 +
 kernel/sysctl.c                                    |   15 +
 mm/vmalloc.c                                       |   78 +-
 tools/testing/selftests/Makefile                   |    1 +
 tools/testing/selftests/cpu-opv/.gitignore         |    6 +
 tools/testing/selftests/cpu-opv/Makefile           |   39 +
 .../testing/selftests/cpu-opv/basic_cpu_opv_test.c | 1207 ++++++++++++++++++++
 .../selftests/cpu-opv/basic_percpu_ops_test.c      |  295 +++++
 tools/testing/selftests/cpu-opv/cpu-op.c           |  362 ++++++
 tools/testing/selftests/cpu-opv/cpu-op.h           |   43 +
 tools/testing/selftests/cpu-opv/param_test.c       | 1187 +++++++++++++++++++
 tools/testing/selftests/cpu-opv/percpu-op.h        |  151 +++
 tools/testing/selftests/cpu-opv/run_param_test.sh  |  134 +++
 tools/testing/selftests/rseq/rseq.c                |   23 +-
 tools/testing/selftests/rseq/rseq.h                |    1 +
 tools/testing/selftests/rseq/run_param_test.sh     |    7 +-
 29 files changed, 4694 insertions(+), 14 deletions(-)
 create mode 100644 include/uapi/linux/cpu_opv.h
 create mode 100644 kernel/cpu_opv.c
 create mode 100644 tools/testing/selftests/cpu-opv/.gitignore
 create mode 100644 tools/testing/selftests/cpu-opv/Makefile
 create mode 100644 tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c
 create mode 100644 tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c
 create mode 100644 tools/testing/selftests/cpu-opv/cpu-op.c
 create mode 100644 tools/testing/selftests/cpu-opv/cpu-op.h
 create mode 100644 tools/testing/selftests/cpu-opv/param_test.c
 create mode 100644 tools/testing/selftests/cpu-opv/percpu-op.h
 create mode 100755 tools/testing/selftests/cpu-opv/run_param_test.sh

-- 
2.11.0

[RFC PATCH for 4.21 01/16] rseq/selftests: Expose reference counter to coexist with glibc (v2)

[Mathieu Desnoyers]

In order to integrate rseq into user-space applications, expose a
reference counter TLS as a __rseq_refcount weak symbol so many rseq
users can be linked into the same application (e.g. librseq and glibc).
The reference count ensures that rseq syscall
registration/unregistration happens only for the most early/late user
for each thread, thus ensuring that rseq is registered across the
lifetime of all rseq users for a given thread.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Shuah Khan <shuah@kernel.org>
CC: Carlos O'Donell <carlos@redhat.com>
CC: Florian Weimer <fweimer@redhat.com>
CC: Joseph Myers <joseph@codesourcery.com>
CC: Szabolcs Nagy <szabolcs.nagy@arm.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Ben Maurer <bmaurer@fb.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Dave Watson <davejwatson@fb.com>
CC: Paul Turner <pjt@google.com>
CC: linux-api@vger.kernel.org
---
Changes since v1:
- Error out on refcount overflow/underflow.
- Expose __rseq_refcount weak symbol.
---
 tools/testing/selftests/rseq/rseq.c | 23 ++++++++++++++++-------
 tools/testing/selftests/rseq/rseq.h |  1 +
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index 4847e97ed049..835e3917d220 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -25,18 +25,19 @@
 #include <syscall.h>
 #include <assert.h>
 #include <signal.h>
+#include <limits.h>
 
 #include "rseq.h"
 
 #define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
 
-__attribute__((tls_model("initial-exec"))) __thread
+__attribute__((weak)) __thread
 volatile struct rseq __rseq_abi = {
 	.cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
 };
 
-static __attribute__((tls_model("initial-exec"))) __thread
-volatile int refcount;
+__attribute__((weak)) __thread
+volatile uint32_t __rseq_refcount;
 
 static void signal_off_save(sigset_t *oldset)
 {
@@ -70,7 +71,11 @@ int rseq_register_current_thread(void)
 	sigset_t oldset;
 
 	signal_off_save(&oldset);
-	if (refcount++)
+	if (__rseq_refcount == UINT_MAX) {
+		ret = -1;
+		goto end;
+	}
+	if (__rseq_refcount++)
 		goto end;
 	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
 	if (!rc) {
@@ -78,9 +83,9 @@ int rseq_register_current_thread(void)
 		goto end;
 	}
 	if (errno != EBUSY)
-		__rseq_abi.cpu_id = -2;
+		__rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED;
 	ret = -1;
-	refcount--;
+	__rseq_refcount--;
 end:
 	signal_restore(oldset);
 	return ret;
@@ -92,7 +97,11 @@ int rseq_unregister_current_thread(void)
 	sigset_t oldset;
 
 	signal_off_save(&oldset);
-	if (--refcount)
+	if (!__rseq_refcount) {
+		ret = -1;
+		goto end;
+	}
+	if (--__rseq_refcount)
 		goto end;
 	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq),
 		      RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index c72eb70f9b52..47f815c19cef 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -45,6 +45,7 @@
 #endif
 
 extern __thread volatile struct rseq __rseq_abi;
+extern __thread volatile uint32_t __rseq_refcount;
 
 #define rseq_likely(x)		__builtin_expect(!!(x), 1)
 #define rseq_unlikely(x)	__builtin_expect(!!(x), 0)
-- 
2.11.0

[RFC PATCH for 4.21 02/16] rseq/selftests: Adapt number of threads to the number of detected cpus

[Mathieu Desnoyers]

On smaller systems, running a test with 200 threads can take a long
time on machines with smaller number of CPUs.

Detect the number of online cpus at test runtime, and multiply that
by 6 to have 6 rseq threads per cpu preempting each other.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/rseq/run_param_test.sh | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh
index 3acd6d75ff9f..e426304fd4a0 100755
--- a/tools/testing/selftests/rseq/run_param_test.sh
+++ b/tools/testing/selftests/rseq/run_param_test.sh
@@ -1,6 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0+ or MIT
 
+NR_CPUS=`grep '^processor' /proc/cpuinfo | wc -l`
+
 EXTRA_ARGS=${@}
 
 OLDIFS="$IFS"
@@ -28,15 +30,16 @@ IFS="$OLDIFS"
 
 REPS=1000
 SLOW_REPS=100
+NR_THREADS=$((6*${NR_CPUS}))
 
 function do_tests()
 {
 	local i=0
 	while [ "$i" -lt "${#TEST_LIST[@]}" ]; do
 		echo "Running test ${TEST_NAME[$i]}"
-		./param_test ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1
+		./param_test ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
 		echo "Running compare-twice test ${TEST_NAME[$i]}"
-		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1
+		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
 		let "i++"
 	done
 }
-- 
2.11.0

[RFC PATCH for 4.21 03/16] mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram()

[Mathieu Desnoyers]

It is encouraged to warn and return rather than use BUG_ON() when
the condition can be recovered from in ways that are more graceful than
halting the whole system.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
CC: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
CC: Matthew Wilcox <mawilcox@microsoft.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
---
 mm/vmalloc.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a728fc492557..a236bac872f0 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1123,10 +1123,11 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 	struct vmap_area *va;
 
 	might_sleep();
-	BUG_ON(!addr);
-	BUG_ON(addr < VMALLOC_START);
-	BUG_ON(addr > VMALLOC_END);
-	BUG_ON(!PAGE_ALIGNED(addr));
+	if (WARN_ON(!addr) ||
+	    WARN_ON(addr < VMALLOC_START) ||
+	    WARN_ON(addr > VMALLOC_END) ||
+	    WARN_ON(!PAGE_ALIGNED(addr)))
+		return;
 
 	if (likely(count <= VMAP_MAX_ALLOC)) {
 		debug_check_no_locks_freed(mem, size);
@@ -1135,7 +1136,8 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 	}
 
 	va = find_vmap_area(addr);
-	BUG_ON(!va);
+	if (WARN_ON(!va))
+		return;
 	debug_check_no_locks_freed((void *)va->va_start,
 				    (va->va_end - va->va_start));
 	free_unmap_vmap_area(va);
-- 
2.11.0

[RFC PATCH for 4.21 04/16] mm: Introduce vm_map_user_ram, vm_unmap_user_ram (v2)

[Mathieu Desnoyers]

Create and destroy mappings aliased to a user-space mapping with the same
cache coloring as the userspace mapping. Allow the kernel to load from
and store to pages shared with user-space through its own mapping in
kernel virtual addresses while ensuring cache conherency between kernel
and userspace mappings for virtually aliased architectures.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
---
Changes since v1:
- Use WARN_ON() rather than BUG_ON().
---
 include/linux/vmalloc.h |  4 +++
 mm/vmalloc.c            | 66 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 398e9c95cd61..899657b3d469 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -59,6 +59,10 @@ struct vmap_area {
 extern void vm_unmap_ram(const void *mem, unsigned int count);
 extern void *vm_map_ram(struct page **pages, unsigned int count,
 				int node, pgprot_t prot);
+extern void vm_unmap_user_ram(const void *mem, unsigned int count);
+extern void *vm_map_user_ram(struct page **pages, unsigned int count,
+				unsigned long uaddr, int node, pgprot_t prot);
+
 extern void vm_unmap_aliases(void);
 
 #ifdef CONFIG_MMU
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a236bac872f0..8df3c572036c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1188,6 +1188,72 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro
 }
 EXPORT_SYMBOL(vm_map_ram);
 
+/**
+ * vm_unmap_user_ram - unmap linear kernel address space set up by vm_map_user_ram
+ * @mem: the pointer returned by vm_map_user_ram
+ * @count: the count passed to that vm_map_user_ram call (cannot unmap partial)
+ */
+void vm_unmap_user_ram(const void *mem, unsigned int count)
+{
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
+	unsigned long addr = (unsigned long)mem;
+	struct vmap_area *va;
+
+	might_sleep();
+	if (WARN_ON(!addr) ||
+	    WARN_ON(addr < VMALLOC_START) ||
+	    WARN_ON(addr > VMALLOC_END) ||
+	    WARN_ON(!PAGE_ALIGNED(addr)))
+		return;
+
+	debug_check_no_locks_freed(mem, size);
+	va = find_vmap_area(addr);
+	if (WARN_ON(!va))
+		return;
+	free_unmap_vmap_area(va);
+}
+EXPORT_SYMBOL(vm_unmap_user_ram);
+
+/**
+ * vm_map_user_ram - map user space pages linearly into kernel virtual address
+ * @pages: an array of pointers to the virtually contiguous pages to be mapped
+ * @count: number of pages
+ * @uaddr: address within the first page in the userspace mapping
+ * @node: prefer to allocate data structures on this node
+ * @prot: memory protection to use. PAGE_KERNEL for regular RAM
+ *
+ * Create a mapping aliased to a user-space mapping with the same cache
+ * coloring as the userspace mapping. Allow the kernel to load from and
+ * store to pages shared with user-space through its own mapping in kernel
+ * virtual addresses while ensuring cache conherency between kernel and
+ * userspace mappings for virtually aliased architectures.
+ *
+ * Returns: a pointer to the address that has been mapped, or %NULL on failure
+ */
+void *vm_map_user_ram(struct page **pages, unsigned int count,
+		unsigned long uaddr, int node, pgprot_t prot)
+{
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
+	unsigned long va_offset = ALIGN_DOWN(uaddr, PAGE_SIZE) & (SHMLBA - 1);
+	unsigned long alloc_size = ALIGN(va_offset + size, SHMLBA);
+	struct vmap_area *va;
+	unsigned long addr;
+	void *mem;
+
+	va = alloc_vmap_area(alloc_size, SHMLBA, VMALLOC_START, VMALLOC_END,
+			node, GFP_KERNEL);
+	if (IS_ERR(va))
+		return NULL;
+	addr = va->va_start + va_offset;
+	mem = (void *)addr;
+	if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
+		vm_unmap_user_ram(mem, count);
+		return NULL;
+	}
+	return mem;
+}
+EXPORT_SYMBOL(vm_map_user_ram);
+
 static struct vm_struct *vmlist __initdata;
 /**
  * vm_area_add_early - add vmap area early during boot
-- 
2.11.0

[RFC PATCH for 4.21 05/16] mm: Provide is_vma_noncached

[Mathieu Desnoyers]

Provide is_vma_noncached() static inline to allow generic code to
check whether the given vma consists of noncached memory.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-mm@kvack.org
---
 include/linux/mm.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0416a7204be3..18acf4f339f8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2551,6 +2551,30 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 	return follow_page_mask(vma, address, foll_flags, &unused_page_mask);
 }
 
+static inline bool pgprot_same(pgprot_t a, pgprot_t b)
+{
+	return pgprot_val(a) == pgprot_val(b);
+}
+
+#ifdef pgprot_noncached
+static inline bool is_vma_noncached(struct vm_area_struct *vma)
+{
+	pgprot_t pgprot = vma->vm_page_prot;
+
+	/* Check whether architecture implements noncached pages. */
+	if (pgprot_same(pgprot_noncached(PAGE_KERNEL), PAGE_KERNEL))
+		return false;
+	if (!pgprot_same(pgprot, pgprot_noncached(pgprot)))
+		return false;
+	return true;
+}
+#else
+static inline bool is_vma_noncached(struct vm_area_struct *vma)
+{
+	return false;
+}
+#endif
+
 #define FOLL_WRITE	0x01	/* check pte is writable */
 #define FOLL_TOUCH	0x02	/* mark page accessed */
 #define FOLL_GET	0x04	/* do get_page on page */
-- 
2.11.0

[RFC PATCH for 4.21 06/16] cpu_opv: Provide cpu_opv system call (v9)

[Mathieu Desnoyers]

The cpu_opv system call executes a vector of operations on behalf of
user-space on a specific CPU with interrupts disabled or within an
IPI handler. It is similar to readv() and writev() system calls which
take a "struct iovec" array as argument.

The operations available are: comparison, memcpy, memcpy_release, add,
and add_release. The system call receives a CPU number from user-space
as argument, which is the CPU on which those operations need to be
performed. All pointers in the ops must have been set up to point to
the per CPU memory of the CPU on which the operations should be
executed. The "comparison" operation can be used to check that the data
used in the preparation step did not change between preparation of
system call inputs and operation execution within the irq-off critical
section.

The reason why for requiring all pointer offsets to be calculated by
user-space beforehand is because get_user_pages() first needs to be
used to pin all pages touched by each operation. This takes care of
faulting-in the pages. Those pages are then vmap'd into the kernel
virtual address range. Then the operations are performed atomically with
respect to other thread's execution on that CPU, without generating any
page fault, by means of a IPI handler (or disabling interrupts).

An overall maximum of 4120 bytes in enforced on the sum of operation
length within an operation vector, so user-space cannot generate a
too long irq-off critical section. The maximum number of operations
supported in a vector is 4. User-space can query the maximum vector
size and the number of operation "instructions" supported with by
passing the appropriate flags as system call parameter. The cache cold
critical section duration has been measured as 4.7µs on x86-64 for 16
operations, therefore a more restrictive limit of 4 operations should
cause an even shorter irq-off latency. Each operation is also limited to
a length of 4096 bytes, meaning that an operation can touch a maximum of
4 pages (memcpy: 2 pages for source, 2 pages for destination if
addresses are not aligned on page boundaries).

**** Justification for cpu_opv ****

Here are a few reasons justifying why the cpu_opv system call is
needed in addition to rseq:

1) Allow algorithms to perform per-cpu data migration without relying on
   sched_setaffinity()

The use-cases are migration of memory between per-cpu memory free-lists,
and stealing tasks from other per-cpu work queues: each require that
accesses to remote per-cpu data structures are performed.

Just rseq is not enough to cover those use-cases without additionally
relying on sched_setaffinity, which is unfortunately not
CPU-hotplug-safe.

The cpu_opv system call receives a CPU number as argument, and
performs the operation sequence in a IPI handler on the right CPU. The
IPI handler ensures any restartable sequence critical section it
interrupts will be aborted. If the requested CPU is offline, it performs
the operations from the current CPU while preventing CPU hotplug, and
with a mutex held.

2) Handling single-stepping from tools

Tools like debuggers and simulators use single-stepping to run through
existing programs. If core libraries start to use restartable sequences
for e.g. memory allocation, this means pre-existing programs cannot be
single-stepped, simply because the underlying glibc or jemalloc has
changed.

The rseq user-space does expose a __rseq_table section for the sake of
debuggers, so they can skip over the rseq critical sections if they
want. However, this requires upgrading tools, and still breaks
single-stepping in case where glibc or jemalloc is updated, but not the
tooling.

Having a performance-related library improvement break tooling is likely
to cause a big push-back against wide adoption of rseq.

3) Forward-progress guarantee

Having a piece of user-space code that stops progressing due to external
conditions is pretty bad. Developers are used to think of fast-path and
slow-path (e.g. for locking), where the contended vs uncontended cases
have different performance characteristics, but each need to provide
some level of progress guarantees.

There are concerns about using just "rseq" without the associated
slow-path (cpu_opv) that guarantees progress. It's just asking for
trouble when real-life happen: page faults, uprobes, and other
unforeseen conditions that would seldom cause a rseq fast-path to never
progress.

4) Handling page faults

It's pretty easy to come up with corner-case scenarios where rseq does
not progress without the help from cpu_opv. For instance, a system with
swap enabled which is under high memory pressure could trigger page
faults at pretty much every rseq attempt. Although this scenario
is extremely unlikely, rseq becomes the weak link of the chain.

5) Comparison with LL/SC handling of debugger single-stepping

The layman versed in the load-link/store-conditional instructions in
RISC architectures will notice the similarity between rseq and LL/SC
critical sections. The comparison can even be pushed further: since
debuggers can handle those LL/SC critical sections, they should be
able to handle rseq c.s. in the same way.

First, the way gdb recognises LL/SC c.s. patterns is very fragile:
it's limited to specific common patterns, and will miss the pattern
in all other cases. But fear not, having the rseq c.s. expose a
__rseq_table to debuggers removes that guessing part.

The main difference between LL/SC and rseq is that debuggers had
to support single-stepping through LL/SC critical sections from the
get go in order to support a given architecture. For rseq, we're
adding critical sections into pre-existing applications/libraries,
so the user expectation is that tools don't break due to a library
optimization.

6) Perform maintenance operations on per-cpu data

rseq c.s. are quite limited feature-wise: they need to end with a
*single* commit instruction that updates a memory location. On the other
hand, the cpu_opv system call can combine a sequence of operations that
need to be executed atomically with respect to concurrent execution on
a given CPU. While slower than rseq, this allows for more complex
maintenance operations to be performed on per-cpu data concurrently with
rseq fast-paths, in cases where it's not possible to map those sequences
of ops to a rseq.

7) Use cpu_opv as generic implementation for architectures not
   implementing rseq assembly code

rseq critical sections require architecture-specific user-space code to
be crafted in order to port an algorithm to a given architecture. In
addition, it requires that the kernel architecture implementation adds
hooks into signal delivery and resume to user-space.

In order to facilitate integration of rseq into user-space, cpu_opv can
provide a (relatively slower) architecture-agnostic implementation of
rseq. This means that user-space code can be ported to all architectures
through use of cpu_opv initially, and have the fast-path use rseq
whenever the asm code is implemented.

8) Allow libraries with multi-part algorithms to work on same per-cpu
   data without affecting the allowed cpu mask

The lttng-ust tracer presents an interesting use-case for per-cpu
buffers: the algorithm needs to update a "reserve" counter, serialize
data into the buffer, and then update a "commit" counter _on the same
per-cpu buffer_. Using rseq for both reserve and commit can bring
significant performance benefits.

Clearly, if rseq reserve fails, the algorithm can retry on a different
per-cpu buffer. However, it's not that easy for the commit. It needs to
be performed on the same per-cpu buffer as the reserve.

The cpu_opv system call solves that problem by receiving the cpu number
on which the operation needs to be performed as argument. It uses an
IPI to perform the operations on the requested CPU.

Changing the allowed cpu mask for the current thread is not an
acceptable alternative for a tracing library, because the application
being traced does not expect that mask to be changed by libraries.

9) Ensure that data structures don't need store-release/load-acquire
   semantic to handle fall-back

cpu_opv performs the fall-back on the requested CPU with an IPI to that
CPU. Executing the slow-path on the right CPU ensures that
store-release/load-acquire semantic is not required neither on the
fast-path nor slow-path.

10) Allow use of rseq critical sections from signal handlers

Considering that rseq needs to be registered/unregistered from the
current thread, it means there is a window at thread creation/exit where
a signal handler can nest over the thread before rseq is registered by
glibc, or after it has been unregistered by glibc. One possibility to
handle this would be to extend clone() to have rseq registered
immediately when the thread is created, and unregistered implicitly when
the thread vanishes. Adding complexity to clone() has not been an idea
received well so far. So an alternative solution is to ensure that
signal handlers using rseq critical sections have a fallback mechanism
(cpu_opv) to work on per-cpu data structures when they are nested over
threads for which rseq is not currently registered.

11) Inability to mix rseq and non-rseq atomic operations on percpu data

A typical approach when dealing with locking fast-path and slow-path is
to fall-back on a slower/less efficient mechanism to perform what the
fast-path cannot do.

One approach that naturally comes to mind when considering rseq
fast-path abort would be to rather issue the same side-effect by
means of an atomic instruction. Arguably, before rseq, updates to
per-cpu data structures used to be done by reading the current CPU
number and by then using an atomic instruction to update the data in a
way that is safe against concurrent updates. This atomic instruction was
indeed needed to deal with migration between reading the current CPU
number and doing the update.

Unfortunately, it is a _bug_ to mix concurrent access to a per-cpu data
with both rseq (guaranteed to be on the right CPU, never migrated before
the commit) and non-rseq atomic instructions (which can be issued from
the wrong CPU), because the rseq critical section (on the right CPU)
executing concurrently with the atomic instruction (on another CPU due
to migration) on can cause data corruption of the per-cpu data.

**** rseq and cpu_opv use-cases ****

1) per-cpu spinlock

A per-cpu spinlock can be implemented as a rseq consisting of a
comparison operation (== 0) on a word, and a word store (1), followed
by an acquire barrier after control dependency. The unlock path can be
performed with a simple store-release of 0 to the word, which does
not require rseq.

The cpu_opv fallback requires a single-word comparison (== 0) and a
single-word store (1).

2) per-cpu statistics counters

A per-cpu statistics counters can be implemented as a rseq consisting
of a final "add" instruction on a word as commit.

The cpu_opv fallback can be implemented as a "ADD" operation.

Besides statistics tracking, these counters can be used to implement
user-space RCU per-cpu grace period tracking for both single and
multi-process user-space RCU.

3) per-cpu LIFO linked-list (unlimited size stack)

A per-cpu LIFO linked-list has a "push" and "pop" operation,
which respectively adds an item to the list, and removes an
item from the list.

The "push" operation can be implemented as a rseq consisting of
a word comparison instruction against head followed by a word store
(commit) to head. Its cpu_opv fallback can be implemented as a
word-compare followed by word-store as well.

The "pop" operation can be implemented as a rseq consisting of
loading head, comparing it against NULL, loading the next pointer
at the right offset within the head item, and the next pointer as
a new head, returning the old head on success.

The cpu_opv fallback for "pop" differs from its rseq algorithm:
considering that cpu_opv requires to know all pointers at system
call entry so it can pin all pages, so cpu_opv cannot simply load
head and then load the head->next address within the irq-off
critical section. User-space needs to pass the head and head->next
addresses to the kernel, and the kernel needs to check that the
head address is unchanged since it has been loaded by user-space.
However, when accessing head->next in a ABA situation, it's
possible that head is unchanged, but loading head->next can
result in a page fault due to a concurrently freed head object.
This is why the "expect_fault" operation field is introduced: if a
fault is triggered by this access, "-EAGAIN" will be returned by
cpu_opv rather than -EFAULT, thus indicating the the operation
vector should be attempted again. The "pop" operation can thus be
implemented as a word comparison of head against the head loaded
by user-space, followed by a load of the head->next pointer (which
may fault), and a store of that pointer as a new head.

4) per-cpu LIFO ring buffer with pointers to objects (fixed-sized stack)

This structure is useful for passing around allocated objects
by passing pointers through per-cpu fixed-sized stack.

The "push" side can be implemented with a check of the current
offset against the maximum buffer length, followed by a rseq
consisting of a comparison of the previously loaded offset
against the current offset, a word "try store" operation into the
next ring buffer array index (it's OK to abort after a try-store,
since it's not the commit, and its side-effect can be overwritten),
then followed by a word-store to increment the current offset (commit).

The "push" cpu_opv fallback can be done with the comparison, and
two consecutive word stores, all within the irq-off section.

The "pop" side can be implemented with a check that offset is not
0 (whether the buffer is empty), a load of the "head" pointer before the
offset array index, followed by a rseq consisting of a word
comparison checking that the offset is unchanged since previously
loaded, another check ensuring that the "head" pointer is unchanged,
followed by a store decrementing the current offset.

The cpu_opv "pop" can be implemented with the same algorithm
as the rseq fast-path (compare, compare, store).

5) per-cpu LIFO ring buffer with pointers to objects (fixed-sized stack)
   supporting "peek" from remote CPU

In order to implement work queues with work-stealing between CPUs, it is
useful to ensure the offset "commit" in scenario 4) "push" have a
store-release semantic, thus allowing remote CPU to load the offset
with acquire semantic, and load the top pointer, in order to check if
work-stealing should be performed. The task (work queue item) existence
should be protected by other means, e.g. RCU.

If the peek operation notices that work-stealing should indeed be
performed, a thread can use cpu_opv to move the task between per-cpu
workqueues, by first invoking cpu_opv passing the remote work queue
cpu number as argument to pop the task, and then again as "push" with
the target work queue CPU number.

6) per-cpu LIFO ring buffer with data copy (fixed-sized stack)
   (with and without acquire-release)

This structure is useful for passing around data without requiring
memory allocation by copying the data content into per-cpu fixed-sized
stack.

The "push" operation is performed with an offset comparison against
the buffer size (figuring out if the buffer is full), followed by
a rseq consisting of a comparison of the offset, a try-memcpy attempting
to copy the data content into the buffer (which can be aborted and
overwritten), and a final store incrementing the offset.

The cpu_opv fallback needs to same operations, except that the memcpy
is guaranteed to complete, given that it is performed with irqs
disabled or from IPI handler. This requires a memcpy operation
supporting length up to 4kB.

The "pop" operation is similar to the "push, except that the offset
is first compared to 0 to ensure the buffer is not empty. The
copy source is the ring buffer, and the destination is an output
buffer.

7) per-cpu FIFO ring buffer (fixed-sized queue)

This structure is useful wherever a FIFO behavior (queue) is needed.
One major use-case is tracer ring buffer.

An implementation of this ring buffer has a "reserve", followed by
serialization of multiple bytes into the buffer, ended by a "commit".
The "reserve" can be implemented as a rseq consisting of a word
comparison followed by a word store. The reserve operation moves the
producer "head". The multi-byte serialization can be performed
non-atomically. Finally, the "commit" update can be performed with
a rseq "add" commit instruction with store-release semantic. The
ring buffer consumer reads the commit value with load-acquire
semantic to know whenever it is safe to read from the ring buffer.

This use-case requires that both "reserve" and "commit" operations
be performed on the same per-cpu ring buffer, even if a migration
happens between those operations. In the typical case, both operations
will happens on the same CPU and use rseq. In the unlikely event of a
migration, the cpu_opv system call will ensure the commit can be
performed on the right CPU by migrating the task to that CPU.

On the consumer side, an alternative to using store-release and
load-acquire on the commit counter would be to use cpu_opv to
ensure the commit counter load is performed on the right CPU through an
IPI.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-api@vger.kernel.org
---
Changes since v1:
- handle CPU hotplug,
- cleanup implementation using function pointers: We can use function
  pointers to implement the operations rather than duplicating all the
  user-access code.
- refuse device pages: Performing cpu_opv operations on io map'd pages
  with preemption disabled could generate long preempt-off critical
  sections, which leads to unwanted scheduler latency. Return EFAULT if
  a device page is received as parameter
- restrict op vector to 4216 bytes length sum: Restrict the operation
  vector to length sum of:
  - 4096 bytes (typical page size on most architectures, should be
    enough for a string, or structures)
  - 15 * 8 bytes (typical operations on integers or pointers).
  The goal here is to keep the duration of preempt off critical section
  short, so we don't add significant scheduler latency.
- Add INIT_ONSTACK macro: Introduce the
  CPU_OP_FIELD_u32_u64_INIT_ONSTACK() macros to ensure that users
  correctly initialize the upper bits of CPU_OP_FIELD_u32_u64() on their
  stack to 0 on 32-bit architectures.
- Add CPU_MB_OP operation:
  Use-cases with:
  - two consecutive stores,
  - a mempcy followed by a store,
  require a memory barrier before the final store operation. A typical
  use-case is a store-release on the final store. Given that this is a
  slow path, just providing an explicit full barrier instruction should
  be sufficient.
- Add expect fault field:
  The use-case of list_pop brings interesting challenges. With rseq, we
  can use rseq_cmpnev_storeoffp_load(), and therefore load a pointer,
  compare it against NULL, add an offset, and load the target "next"
  pointer from the object, all within a single req critical section.

  Life is not so easy for cpu_opv in this use-case, mainly because we
  need to pin all pages we are going to touch in the preempt-off
  critical section beforehand. So we need to know the target object (in
  which we apply an offset to fetch the next pointer) when we pin pages
  before disabling preemption.

  So the approach is to load the head pointer and compare it against
  NULL in user-space, before doing the cpu_opv syscall. User-space can
  then compute the address of the head->next field, *without loading it*.

  The cpu_opv system call will first need to pin all pages associated
  with input data. This includes the page backing the head->next object,
  which may have been concurrently deallocated and unmapped. Therefore,
  in this case, getting -EFAULT when trying to pin those pages may
  happen: it just means they have been concurrently unmapped. This is
  an expected situation, and should just return -EAGAIN to user-space,
  to user-space can distinguish between "should retry" type of
  situations and actual errors that should be handled with extreme
  prejudice to the program (e.g. abort()).

  Therefore, add "expect_fault" fields along with op input address
  pointers, so user-space can identify whether a fault when getting a
  field should return EAGAIN rather than EFAULT.
- Add compiler barrier between operations: Adding a compiler barrier
  between store operations in a cpu_opv sequence can be useful when
  paired with membarrier system call.

  An algorithm with a paired slow path and fast path can use
  sys_membarrier on the slow path to replace fast-path memory barriers
  by compiler barrier.

  Adding an explicit compiler barrier between operations allows
  cpu_opv to be used as fallback for operations meant to match
  the membarrier system call.

Changes since v2:

- Fix memory leak by introducing struct cpu_opv_pinned_pages.
  Suggested by Boqun Feng.
- Cast argument 1 passed to access_ok from integer to void __user *,
  fixing sparse warning.

Changes since v3:

- Fix !SMP by adding push_task_to_cpu() empty static inline.
- Add missing sys_cpu_opv() asmlinkage declaration to
  include/linux/syscalls.h.

Changes since v4:

- Cleanup based on Thomas Gleixner's feedback.
- Handle retry in case where the scheduler migrates the thread away
  from the target CPU after migration within the syscall rather than
  returning EAGAIN to user-space.
- Move push_task_to_cpu() to its own patch.
- New scheme for touching user-space memory:
   1) get_user_pages_fast() to pin/get all pages (which can sleep),
   2) vm_map_ram() those pages
   3) grab mmap_sem (read lock)
   4) __get_user_pages_fast() (or get_user_pages() on failure)
      -> Confirm that the same page pointers are returned. This
         catches cases where COW mappings are changed concurrently.
      -> If page pointers differ, or on gup failure, release mmap_sem,
         vm_unmap_ram/put_page and retry from step (1).
      -> perform put_page on the extra reference immediately for each
         page.
   5) preempt disable
   6) Perform operations on vmap. Those operations are normal
      loads/stores/memcpy.
   7) preempt enable
   8) release mmap_sem
   9) vm_unmap_ram() all virtual addresses
  10) put_page() all pages
- Handle architectures with VIVT caches along with vmap(): call
  flush_kernel_vmap_range() after each "write" operation. This
  ensures that the user-space mapping and vmap reach a consistent
  state between each operation.
- Depend on MMU for is_zero_pfn(). e.g. Blackfin and SH architectures
  don't provide the zero_pfn symbol.

Changes since v5:

- Fix handling of push_task_to_cpu() when argument is a cpu which is
  not part of the task's allowed cpu mask.
- Add CPU_OP_NR_FLAG flag, which returns the number of operations
  supported by the system call.

Changes since v6:

- Use __u* in public uapi header rather than uint*_t.
- Disallow cpu_opv targeting noncached vma, which requires using
  get_user_pages() rather than get_user_pages_fast() to get the
  vma.
- Fix handling of vm_map_ram() errors by increasing nr_vaddr only after
  success.
- Issue vm_unmap_aliases() after each cpu_opv system call, thus ensuring
  lazy unmapping does not exhaust vmalloc address space in stress-tests on
  32-bit systems.
- Use vm_map_user_ram() and vm_unmap_user_ram() to ensure cache coherency
  on virtually aliased architectures.

Changes since v7:

- Adapt to removal of types_32_64.h.

Changes since v8:

- Use IPI to interpret operation vector (or interrupt off critical
  section). This is possible now that the interpreter touches a shadow
  mapping (vmap) of the user-space pages, and it is simpler than trying
  to migrate the current thread.
- Update documentation to reflect the change from preempt-off critical
  section to IPI.
- Introduce SPDX license comments.
- Remove unused bitwise and shift operations (reduce instruction-set),
- Remove "mb" instruction,
- Introduce memcpy_release and add_release instructions,
- Allow user-space to query operation vector size supported by the kernel,
- Reduce operation vector size supported from 16 to 4.

---
Man page associated:

CPU_OPV(2)              Linux Programmer's Manual             CPU_OPV(2)

NAME
       cpu_opv - Per-CPU-atomic operation vector system call

SYNOPSIS
       #include <linux/cpu_opv.h>

       int cpu_opv(struct cpu_op * cpu_opv, int cpuopcnt, int cpu, int flags);

DESCRIPTION
       The cpu_opv system call executes a vector of operations on behalf
       of user-space on a specific CPU atomically with respect  to  con‐
       current execution on that CPU.

       The term CPU used in this documentation refers to a hardware exe‐
       cution context.

       The operations available are: comparison, memcpy, add. Both  mem‐
       cpy  and add operations have a counterpart with release semantic.
       The system call receives a CPU number from  user-space  as  argu‐
       ment,  which is the CPU on which those operations need to be per‐
       formed.  All pointers in the ops must have been set up  to  point
       to  the  per CPU memory of the CPU on which the operations should
       be executed. The "comparison" operation can be used to check that
       the  data  used  in  the  preparation step did not change between
       preparation of system call inputs and operation execution by  the
       kernel.

       An overall maximum of 4216 bytes in enforced on the sum of opera‐
       tion length within an operation vector, so user-space cannot gen‐
       erate  a too long interrupt-off critical section or inter-proces‐
       sor interrupt handler. Each operation is also limited a length of
       4096  bytes.  A maximum limit of 4 operations per cpu_opv syscall
       invocation is enforced.

       The layout of struct cpu_opv is as follows:

       Fields

           op Operation of type enum cpu_op_type to perform. This opera‐
              tion type selects the associated "u" union field.

           len
              Length (in bytes) of data to consider for this operation.

           u.compare_op
              For  a CPU_COMPARE_EQ_OP , and CPU_COMPARE_NE_OP , a and b
              are  pointers  to  data  meant   to   be   compared.   The
              expect_fault_a  and expect_fault_b fields indicate whether
              a page fault should be expected when accessing the  memory
              holding  this  data. If expect_fault_a , or expect_fault_b
              is set, EAGAIN  is  returned  on  fault,  else  EFAULT  is
              returned.  The  len field is allowed to take values from 0
              to 4096 for comparison operations.

           u.memcpy_op
              For a CPU_MEMCPY_OP , or CPU_MEMCPY_RELEASE_OP ,  contains
              the  dst  and  src pointers, expressing a copy of src into
              dst.  The  expect_fault_dst  and  expect_fault_src  fields
              indicate  whether  a  page  fault  should be expected when
              accessing the memory holding both source and  destination,
              which  starts  at the pointer address, of length len .  If
              expect_fault_dst , or expect_fault_src is set,  EAGAIN  is
              returned  on fault, else EFAULT is returned. The len field
              is allowed to take values from 0 to 4096 for memcpy opera‐
              tions.

           u.arithmetic_op
              For  a CPU_ADD_OP , or CPU_ADD_RELEASE_OP , contains the p
              , count , and expect_fault_p  fields,  which  are  respec‐
              tively  a pointer to the memory location to increment, the
              64-bit signed integer value to add,  and  whether  a  page
              fault  should  be  expected  for p .  If expect_fault_p is
              set, EAGAIN is returned on fault, else EFAULT is returned.
              The  len  field  is  allowed  to take values of 1, 2, 4, 8
              bytes for arithmetic operations.

       The enum cpu_op_types contains the following operations:

       · CPU_COMPARE_EQ_OP: Compare whether  two  memory  locations  are
         equal,

       · CPU_COMPARE_NE_OP: Compare whether two memory locations differ,

       · CPU_MEMCPY_OP:  Copy  a  source memory location into a destina‐
         tion,

       · CPU_MEMCPY_RELEASE_OP: Copy a source  memory  location  into  a
         destination, with release semantic,

       · CPU_ADD_OP:  Increment  a  target  memory  location  of a given
         count,

       · CPU_ADD_RELEASE_OP: Increment a target  memory  location  of  a
         given count, with release semantic,

         All of the operations above provide single-copy atomicity guar‐
         antees for word-sized, word-aligned target pointers,  for  both
         loads and stores.

       The  cpuopcnt  argument  is the number of elements in the cpu_opv
       array. It can take values from 0 to an upper  limit  returned  by
       invoking cpu_opv() with the CPU_OP_VEC_LEN_MAX_FLAG flag set.

       The  cpu  argument  is  the  CPU  number  on  which the operation
       sequence needs to be executed.

       The flags argument is a bitmask. When CPU_OP_NR_FLAG is set,  the
       cpu_opv() system call returns the number of operations available.
        When  CPU_OP_VEC_LEN_MAX_FLAG  is set, the cpu_opv() system call
       returns the maximum length of the sequence of operations that  is
       accepted  as  input argument by the system call. When flags is 0,
       the sequence of operations received as parameter is performed.

RETURN VALUE
       When invoked with flags set at 0, a return value of  0  indicates
       success.  On  error, -1 is returned, and errno is set.  If a com‐
       parison operation fails, execution of  the  operation  vector  is
       stopped,  and  the return value is the index after the comparison
       operation (values between 1 and 4).

       When flags is non-zero, on error,  -1 is returned, and  errno  is
       set.  On  success,  the  behavior is described in the DESCRIPTION
       section for each flag.

ERRORS
       EAGAIN cpu_opv() system call should be attempted again.

       EINVAL Either flags contains an invalid value, or cpu contains an
              invalid  value  or  a  value  not  allowed  by the current
              thread's allowed cpu mask, or cpuopcnt contains an invalid
              value, or the cpu_opv operation vector contains an invalid
              op value, or the  cpu_opv  operation  vector  contains  an
              invalid  len value, or the cpu_opv operation vector sum of
              len values is too large.

       ENOSYS The cpu_opv() system call is not implemented by this  ker‐
              nel.

       EFAULT cpu_opv  is  an  invalid  address,  or a pointer contained
              within an  operation  is  invalid  (and  a  fault  is  not
              expected  for  that  pointer). Pointers to device and non‐
              cached memory within an operation are considered invalid.

VERSIONS
       The cpu_opv() system call was added in Linux 4.X (TODO).

CONFORMING TO
       cpu_opv() is Linux-specific.

SEE ALSO
       membarrier(2), rseq(2)

Linux                          2018-10-27                     CPU_OPV(2)
---
 MAINTAINERS                  |   7 +
 include/linux/syscalls.h     |   3 +
 include/uapi/linux/cpu_opv.h |  69 ++++
 init/Kconfig                 |  18 +
 kernel/Makefile              |   1 +
 kernel/cpu_opv.c             | 955 +++++++++++++++++++++++++++++++++++++++++++
 kernel/sys_ni.c              |   1 +
 7 files changed, 1054 insertions(+)
 create mode 100644 include/uapi/linux/cpu_opv.h
 create mode 100644 kernel/cpu_opv.c

diff --git a/MAINTAINERS b/MAINTAINERS
index b2f710eee67a..de59c7c12c8f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3872,6 +3872,13 @@ B:	https://bugzilla.kernel.org
 F:	drivers/cpuidle/*
 F:	include/linux/cpuidle.h
 
+PER-CPU-ATOMIC OPERATION VECTOR SUPPORT
+M:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+F:	kernel/cpu_opv.c
+F:	include/uapi/linux/cpu_opv.h
+
 CRAMFS FILESYSTEM
 M:	Nicolas Pitre <nico@linaro.org>
 S:	Maintained
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2ff814c92f7f..c5af29eccd0e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -68,6 +68,7 @@ struct perf_event_attr;
 struct file_handle;
 struct sigaltstack;
 struct rseq;
+struct cpu_op;
 union bpf_attr;
 
 #include <linux/types.h>
@@ -906,6 +907,8 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
+asmlinkage long sys_cpu_opv(struct cpu_op __user *ucpuopv, int cpuopcnt,
+			int cpu, int flags);
 
 /*
  * Architecture-specific system calls
diff --git a/include/uapi/linux/cpu_opv.h b/include/uapi/linux/cpu_opv.h
new file mode 100644
index 000000000000..350e5a7a61f2
--- /dev/null
+++ b/include/uapi/linux/cpu_opv.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_CPU_OPV_H
+#define _UAPI_LINUX_CPU_OPV_H
+
+/*
+ * linux/cpu_opv.h
+ *
+ * Per-CPU-atomic operation vector system call API
+ *
+ * Copyright (c) 2017-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include <linux/types.h>
+
+/* Maximum size of operation structure within struct cpu_op. */
+#define CPU_OP_ARG_LEN_MAX			24
+/* Maximum data len for compare and memcpy operations. */
+#define CPU_OP_DATA_LEN_MAX			4096
+/* Maximum data len for arithmetic operations. */
+#define CPU_OP_ARITHMETIC_DATA_LEN_MAX		8
+
+enum cpu_op_flags {
+	CPU_OP_NR_FLAG =		(1U << 0),
+	CPU_OP_VEC_LEN_MAX_FLAG =	(1U << 1),
+};
+
+enum cpu_op_type {
+	/* compare */
+	CPU_COMPARE_EQ_OP,
+	CPU_COMPARE_NE_OP,
+	/* memcpy */
+	CPU_MEMCPY_OP,
+	CPU_MEMCPY_RELEASE_OP,
+	/* arithmetic */
+	CPU_ADD_OP,
+	CPU_ADD_RELEASE_OP,
+
+	NR_CPU_OPS,
+};
+
+/* Vector of operations to perform. Limited to 16. */
+struct cpu_op {
+	/* enum cpu_op_type. */
+	__s32 op;
+	/* data length, in bytes. */
+	__u32 len;
+	union {
+		struct {
+			__u64 a;
+			__u64 b;
+			__u8 expect_fault_a;
+			__u8 expect_fault_b;
+		} compare_op;
+		struct {
+			__u64 dst;
+			__u64 src;
+			__u8 expect_fault_dst;
+			__u8 expect_fault_src;
+		} memcpy_op;
+		struct {
+			__u64 p;
+			__s64 count;
+			__u8 expect_fault_p;
+		} arithmetic_op;
+		char __padding[CPU_OP_ARG_LEN_MAX];
+	} u;
+};
+
+#endif /* _UAPI_LINUX_CPU_OPV_H */
diff --git a/init/Kconfig b/init/Kconfig
index 1e234e2f1cba..e7c21a683642 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1483,6 +1483,8 @@ config RSEQ
 	bool "Enable rseq() system call" if EXPERT
 	default y
 	depends on HAVE_RSEQ
+	depends on MMU
+	select CPU_OPV
 	select MEMBARRIER
 	help
 	  Enable the restartable sequences system call. It provides a
@@ -1502,6 +1504,22 @@ config DEBUG_RSEQ
 
 	  If unsure, say N.
 
+# CPU_OPV depends on MMU for is_zero_pfn()
+config CPU_OPV
+	bool "Enable cpu_opv() system call" if EXPERT
+	default y
+	depends on MMU
+	help
+	  Enable the per-CPU-atomic operation vector system call.
+	  It allows user-space to perform a sequence of operations on
+	  per-CPU data atomically with respect to concurrent execution on that
+	  CPU. Useful as single-stepping fall-back for restartable sequences,
+	  migration of data between per-CPU data structures, and for performing
+	  more complex operations on per-CPU data that would not be otherwise
+	  possible to do with restartable sequences.
+
+	  If unsure, say Y.
+
 config EMBEDDED
 	bool "Embedded system"
 	option allnoconfig_y
diff --git a/kernel/Makefile b/kernel/Makefile
index 7a63d567fdb5..507150b93521 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -116,6 +116,7 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o
 obj-$(CONFIG_HAS_IOMEM) += iomem.o
 obj-$(CONFIG_ZONE_DEVICE) += memremap.o
 obj-$(CONFIG_RSEQ) += rseq.o
+obj-$(CONFIG_CPU_OPV) += cpu_opv.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 
diff --git a/kernel/cpu_opv.c b/kernel/cpu_opv.c
new file mode 100644
index 000000000000..6ee7ca3376be
--- /dev/null
+++ b/kernel/cpu_opv.c
@@ -0,0 +1,955 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Per-CPU-atomic operation vector system call
+ *
+ * It allows user-space to perform a sequence of operations on per-cpu
+ * data in the user-space address space atomically with respect to concurrent
+ * accesses from the same cpu. Useful as single-stepping fall-back for
+ * restartable sequences, and for performing more complex operations on per-cpu
+ * data that would not be otherwise possible to do with restartable sequences,
+ * such as migration of per-cpu data from one cpu to another.
+ *
+ * Copyright (C) 2017-2018 EfficiOS Inc.,
+ * Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/cpu_opv.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/pagemap.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/atomic.h>
+#include <linux/smp.h>
+#include <asm/ptrace.h>
+#include <asm/byteorder.h>
+#include <asm/cacheflush.h>
+
+#include "sched/sched.h"
+
+/*
+ * Maximum number of operations expected for a vector.
+ */
+#define CPU_OP_VEC_LEN_MAX		4
+
+/*
+ * Maximum data len for overall vector. Restrict the amount of user-space
+ * data touched by the kernel in interrupt-off or IPI handler context, so it
+ * does not introduce long interrupt latencies.
+ * cpu_opv allows one copy of up to 4096 bytes, and 3 operations touching 8
+ * bytes each.
+ * This limit is applied to the sum of length specified for all operations
+ * in a vector.
+ */
+#define CPU_OP_VEC_DATA_LEN_MAX	(CPU_OP_DATA_LEN_MAX +	\
+	 (CPU_OP_VEC_LEN_MAX - 1) * CPU_OP_ARITHMETIC_DATA_LEN_MAX)
+
+/*
+ * Invocation of cpu_opv requires a maximum of 8 virtual address pointers.
+ * Keep those in an array on the stack of the cpu_opv system call.
+ */
+#define NR_VADDR			8
+
+/* Maximum pages per op. */
+#define CPU_OP_MAX_PAGES		4
+
+/* Maximum number of virtual addresses per op. */
+#define CPU_OP_VEC_MAX_ADDR		(2 * CPU_OP_VEC_LEN_MAX)
+
+union op_fn_data {
+	uint8_t _u8;
+	uint16_t _u16;
+	uint32_t _u32;
+	uint64_t _u64;
+#if (BITS_PER_LONG < 64)
+	uint32_t _u64_split[2];
+#endif
+};
+
+struct vaddr {
+	unsigned long mem;
+	unsigned long uaddr;
+	struct page *pages[2];
+	unsigned int nr_pages;
+	int write;
+};
+
+struct cpu_opv_vaddr {
+	struct vaddr addr[NR_VADDR];
+	size_t nr_vaddr;
+};
+
+typedef int (*op_fn_t)(union op_fn_data *data, uint64_t v, uint32_t len);
+
+struct opv_ipi_args {
+	struct cpu_op *cpuop;
+	int cpuopcnt;
+	int ret;
+};
+
+/*
+ * Provide mutual exclution for threads executing a cpu_opv against an
+ * offline CPU.
+ */
+static DEFINE_MUTEX(cpu_opv_offline_lock);
+
+/*
+ * The cpu_opv system call executes a vector of operations on behalf of
+ * user-space on a specific CPU either with interrupts disabled or within
+ * a interrupt handler. It is inspired by readv() and writev() system
+ * calls which take a "struct iovec" array as argument.
+ *
+ * The operations available are: comparison, memcpy, memcpy_release, add,
+ * add_release. The system call receives a CPU number from user-space as
+ * argument, which is the CPU on which those operations need to be
+ * performed.  All pointers in the ops must have been set up to point to
+ * the per CPU memory of the CPU on which the operations should be
+ * executed. The "comparison" operation can be used to check that the data
+ * used in the preparation step did not change between preparation of
+ * system call inputs and interpretation of the operation vector within
+ * the kernel.
+ *
+ * The reason why we require all pointer offsets to be calculated by
+ * user-space beforehand is because we need to use get_user_pages()
+ * to first pin all pages touched by each operation. This takes care of
+ * faulting-in the pages. Then, either interrupts are disabled if the
+ * target CPU is the current CPU, or an IPI is sent to the target CPU, and
+ * the operations are performed atomically with respect to other thread
+ * execution on that CPU, without generating any page fault. If the IPI
+ * nests over a restartable sequence critical section, it will abort that
+ * critical section.
+ *
+ * An overall maximum of 4120 bytes in enforced on the sum of operation
+ * length within an operation vector, so user-space cannot generate a
+ * too long interrupt-off critical section or IPI handler. The operation
+ * vector size is limited to 4 operations. The cache cold critical section
+ * duration has been measured as 4.7µs for 16 operations on x86-64. Each
+ * operation is also limited a length of 4096 bytes, meaning that an
+ * operation can touch a maximum of 4 pages (memcpy: 2 pages for source, 2
+ * pages for destination if addresses are not aligned on page boundaries).
+ *
+ * If the current thread running on the requested CPU, interrupts are
+ * disabled around interpretation of the operation vector. If the target
+ * CPU differs from the current CPU, an IPI is sent to the remote CPU
+ * to interpret the operation vector. If the remote CPU is offline, the
+ * operation vector is executed while holding a reference count preventing
+ * concurrent CPU hotplug changes, with cpu_opv_offline_lock mutex held.
+ */
+
+static unsigned long cpu_op_range_nr_pages(unsigned long addr,
+					   unsigned long len)
+{
+	return ((addr + len - 1) >> PAGE_SHIFT) - (addr >> PAGE_SHIFT) + 1;
+}
+
+static int cpu_op_count_pages(u64 addr, unsigned long len)
+{
+	unsigned long nr_pages;
+
+	/*
+	 * Validate that the address is within the process address space.
+	 * This allows cast of those addresses to unsigned long throughout the
+	 * rest of this system call, because it would be invalid to have an
+	 * address over 4GB on a 32-bit kernel.
+	 */
+	if (addr >= TASK_SIZE)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	nr_pages = cpu_op_range_nr_pages(addr, len);
+	if (nr_pages > 2) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	return nr_pages;
+}
+
+/*
+ * Check operation types and length parameters. Count number of pages.
+ */
+static int cpu_opv_check_op(struct cpu_op *op, int *nr_vaddr, uint32_t *sum)
+{
+	int ret;
+
+	*sum += op->len;
+
+	/* Validate inputs. */
+	switch (op->op) {
+	case CPU_COMPARE_EQ_OP:
+	case CPU_COMPARE_NE_OP:
+	case CPU_MEMCPY_OP:
+	case CPU_MEMCPY_RELEASE_OP:
+		if (op->len > CPU_OP_DATA_LEN_MAX)
+			return -EINVAL;
+		break;
+	case CPU_ADD_OP:
+	case CPU_ADD_RELEASE_OP:
+		switch (op->len) {
+		case 1:
+		case 2:
+		case 4:
+		case 8:
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Validate pointers, count pages and virtual addresses. */
+	switch (op->op) {
+	case CPU_COMPARE_EQ_OP:
+	case CPU_COMPARE_NE_OP:
+		ret = cpu_op_count_pages(op->u.compare_op.a, op->len);
+		if (ret < 0)
+			return ret;
+		ret = cpu_op_count_pages(op->u.compare_op.b, op->len);
+		if (ret < 0)
+			return ret;
+		*nr_vaddr += 2;
+		break;
+	case CPU_MEMCPY_OP:
+	case CPU_MEMCPY_RELEASE_OP:
+		ret = cpu_op_count_pages(op->u.memcpy_op.dst, op->len);
+		if (ret < 0)
+			return ret;
+		ret = cpu_op_count_pages(op->u.memcpy_op.src, op->len);
+		if (ret < 0)
+			return ret;
+		*nr_vaddr += 2;
+		break;
+	case CPU_ADD_OP:
+	case CPU_ADD_RELEASE_OP:
+		ret = cpu_op_count_pages(op->u.arithmetic_op.p, op->len);
+		if (ret < 0)
+			return ret;
+		(*nr_vaddr)++;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Check operation types and length parameters. Count number of pages.
+ */
+static int cpu_opv_check(struct cpu_op *cpuopv, int cpuopcnt, int *nr_vaddr)
+{
+	uint32_t sum = 0;
+	int i, ret;
+
+	for (i = 0; i < cpuopcnt; i++) {
+		ret = cpu_opv_check_op(&cpuopv[i], nr_vaddr, &sum);
+		if (ret)
+			return ret;
+	}
+	if (sum > CPU_OP_VEC_DATA_LEN_MAX)
+		return -EINVAL;
+	return 0;
+}
+
+static int cpu_op_check_page(struct page *page, int write)
+{
+	struct address_space *mapping;
+
+	if (is_zone_device_page(page))
+		return -EFAULT;
+
+	/*
+	 * The page lock protects many things but in this context the page
+	 * lock stabilizes mapping, prevents inode freeing in the shared
+	 * file-backed region case and guards against movement to swap
+	 * cache.
+	 *
+	 * Strictly speaking the page lock is not needed in all cases being
+	 * considered here and page lock forces unnecessarily serialization
+	 * From this point on, mapping will be re-verified if necessary and
+	 * page lock will be acquired only if it is unavoidable
+	 *
+	 * Mapping checks require the head page for any compound page so the
+	 * head page and mapping is looked up now.
+	 */
+	page = compound_head(page);
+	mapping = READ_ONCE(page->mapping);
+
+	/*
+	 * If page->mapping is NULL, then it cannot be a PageAnon page;
+	 * but it might be the ZERO_PAGE (which is OK to read from), or
+	 * in the gate area or in a special mapping (for which this
+	 * check should fail); or it may have been a good file page when
+	 * get_user_pages found it, but truncated or holepunched or
+	 * subjected to invalidate_complete_page2 before the page lock
+	 * is acquired (also cases which should fail). Given that a
+	 * reference to the page is currently held, refcount care in
+	 * invalidate_complete_page's remove_mapping prevents
+	 * drop_caches from setting mapping to NULL concurrently.
+	 *
+	 * The case to guard against is when memory pressure cause
+	 * shmem_writepage to move the page from filecache to swapcache
+	 * concurrently: an unlikely race, but a retry for page->mapping
+	 * is required in that situation.
+	 */
+	if (!mapping) {
+		int shmem_swizzled;
+
+		/*
+		 * Check again with page lock held to guard against
+		 * memory pressure making shmem_writepage move the page
+		 * from filecache to swapcache.
+		 */
+		lock_page(page);
+		shmem_swizzled = PageSwapCache(page) || page->mapping;
+		unlock_page(page);
+		if (shmem_swizzled)
+			return -EAGAIN;
+		/*
+		 * It is valid to read from, but invalid to write to the
+		 * ZERO_PAGE.
+		 */
+		if (!(is_zero_pfn(page_to_pfn(page)) ||
+		      is_huge_zero_page(page)) || write)
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int cpu_op_check_pages(struct page **pages,
+			      unsigned long nr_pages,
+			      int write)
+{
+	unsigned long i;
+
+	for (i = 0; i < nr_pages; i++) {
+		int ret;
+
+		ret = cpu_op_check_page(pages[i], write);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int cpu_op_pin_pages(unsigned long addr, unsigned long len,
+			    struct cpu_opv_vaddr *vaddr_ptrs,
+			    unsigned long *vaddr, int write)
+{
+	struct page *pages[2];
+	struct vm_area_struct *vmas[2];
+	int ret, nr_pages, nr_put_pages, n;
+	unsigned long _vaddr;
+	struct vaddr *va;
+	struct mm_struct *mm = current->mm;
+
+	nr_pages = cpu_op_count_pages(addr, len);
+	if (nr_pages <= 0)
+		return nr_pages;
+again:
+	down_read(&mm->mmap_sem);
+	ret = get_user_pages(addr, nr_pages, write ? FOLL_WRITE : 0, pages,
+			     vmas);
+	if (ret < nr_pages) {
+		if (ret >= 0) {
+			nr_put_pages = ret;
+			ret = -EFAULT;
+		} else {
+			nr_put_pages = 0;
+		}
+		up_read(&mm->mmap_sem);
+		goto error;
+	}
+	/*
+	 * cpu_opv() accesses its own cached mapping of the userspace pages.
+	 * Considering that concurrent noncached and cached accesses may yield
+	 * to unexpected results in terms of memory consistency, explicitly
+	 * disallow cpu_opv on noncached memory.
+	 */
+	for (n = 0; n < nr_pages; n++) {
+		if (is_vma_noncached(vmas[n])) {
+			nr_put_pages = nr_pages;
+			ret = -EFAULT;
+			up_read(&mm->mmap_sem);
+			goto error;
+		}
+	}
+	up_read(&mm->mmap_sem);
+	ret = cpu_op_check_pages(pages, nr_pages, write);
+	if (ret) {
+		nr_put_pages = nr_pages;
+		goto error;
+	}
+	_vaddr = (unsigned long)vm_map_user_ram(pages, nr_pages, addr,
+						numa_node_id(), PAGE_KERNEL);
+	if (!_vaddr) {
+		nr_put_pages = nr_pages;
+		ret = -ENOMEM;
+		goto error;
+	}
+	va = &vaddr_ptrs->addr[vaddr_ptrs->nr_vaddr++];
+	va->mem = _vaddr;
+	va->uaddr = addr;
+	for (n = 0; n < nr_pages; n++)
+		va->pages[n] = pages[n];
+	va->nr_pages = nr_pages;
+	va->write = write;
+	*vaddr = _vaddr + (addr & ~PAGE_MASK);
+	return 0;
+
+error:
+	for (n = 0; n < nr_put_pages; n++)
+		put_page(pages[n]);
+	/*
+	 * Retry if a page has been faulted in, or is being swapped in.
+	 */
+	if (ret == -EAGAIN)
+		goto again;
+	return ret;
+}
+
+static int cpu_opv_pin_pages_op(struct cpu_op *op,
+				struct cpu_opv_vaddr *vaddr_ptrs,
+				bool *expect_fault)
+{
+	int ret;
+	unsigned long vaddr = 0;
+
+	switch (op->op) {
+	case CPU_COMPARE_EQ_OP:
+	case CPU_COMPARE_NE_OP:
+		ret = -EFAULT;
+		*expect_fault = op->u.compare_op.expect_fault_a;
+		if (!access_ok(VERIFY_READ,
+			       (void __user *)(unsigned long)op->u.compare_op.a,
+			       op->len))
+			return ret;
+		ret = cpu_op_pin_pages(op->u.compare_op.a, op->len,
+				       vaddr_ptrs, &vaddr, 0);
+		if (ret)
+			return ret;
+		op->u.compare_op.a = vaddr;
+		ret = -EFAULT;
+		*expect_fault = op->u.compare_op.expect_fault_b;
+		if (!access_ok(VERIFY_READ,
+			       (void __user *)(unsigned long)op->u.compare_op.b,
+			       op->len))
+			return ret;
+		ret = cpu_op_pin_pages(op->u.compare_op.b, op->len,
+				       vaddr_ptrs, &vaddr, 0);
+		if (ret)
+			return ret;
+		op->u.compare_op.b = vaddr;
+		break;
+	case CPU_MEMCPY_OP:
+	case CPU_MEMCPY_RELEASE_OP:
+		ret = -EFAULT;
+		*expect_fault = op->u.memcpy_op.expect_fault_dst;
+		if (!access_ok(VERIFY_WRITE,
+			       (void __user *)(unsigned long)op->u.memcpy_op.dst,
+			       op->len))
+			return ret;
+		ret = cpu_op_pin_pages(op->u.memcpy_op.dst, op->len,
+				       vaddr_ptrs, &vaddr, 1);
+		if (ret)
+			return ret;
+		op->u.memcpy_op.dst = vaddr;
+		ret = -EFAULT;
+		*expect_fault = op->u.memcpy_op.expect_fault_src;
+		if (!access_ok(VERIFY_READ,
+			       (void __user *)(unsigned long)op->u.memcpy_op.src,
+			       op->len))
+			return ret;
+		ret = cpu_op_pin_pages(op->u.memcpy_op.src, op->len,
+				       vaddr_ptrs, &vaddr, 0);
+		if (ret)
+			return ret;
+		op->u.memcpy_op.src = vaddr;
+		break;
+	case CPU_ADD_OP:
+	case CPU_ADD_RELEASE_OP:
+		ret = -EFAULT;
+		*expect_fault = op->u.arithmetic_op.expect_fault_p;
+		if (!access_ok(VERIFY_WRITE,
+			       (void __user *)(unsigned long)op->u.arithmetic_op.p,
+			       op->len))
+			return ret;
+		ret = cpu_op_pin_pages(op->u.arithmetic_op.p, op->len,
+				       vaddr_ptrs, &vaddr, 1);
+		if (ret)
+			return ret;
+		op->u.arithmetic_op.p = vaddr;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int cpu_opv_pin_pages(struct cpu_op *cpuop, int cpuopcnt,
+			     struct cpu_opv_vaddr *vaddr_ptrs)
+{
+	int ret, i;
+	bool expect_fault = false;
+
+	/* Check access, pin pages. */
+	for (i = 0; i < cpuopcnt; i++) {
+		ret = cpu_opv_pin_pages_op(&cpuop[i], vaddr_ptrs,
+					   &expect_fault);
+		if (ret)
+			goto error;
+	}
+	return 0;
+
+error:
+	/*
+	 * If faulting access is expected, return EAGAIN to user-space.
+	 * It allows user-space to distinguish between a fault caused by
+	 * an access which is expect to fault (e.g. due to concurrent
+	 * unmapping of underlying memory) from an unexpected fault from
+	 * which a retry would not recover.
+	 */
+	if (ret == -EFAULT && expect_fault)
+		return -EAGAIN;
+	return ret;
+}
+
+static int __op_get(union op_fn_data *data, void *p, size_t len)
+{
+	switch (len) {
+	case 1:
+		data->_u8 = READ_ONCE(*(uint8_t *)p);
+		break;
+	case 2:
+		data->_u16 = READ_ONCE(*(uint16_t *)p);
+		break;
+	case 4:
+		data->_u32 = READ_ONCE(*(uint32_t *)p);
+		break;
+	case 8:
+#if (BITS_PER_LONG == 64)
+		data->_u64 = READ_ONCE(*(uint64_t *)p);
+#else
+	{
+		data->_u64_split[0] = READ_ONCE(*(uint32_t *)p);
+		data->_u64_split[1] = READ_ONCE(*((uint32_t *)p + 1));
+	}
+#endif
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int __op_put(union op_fn_data *data, void *p, size_t len, bool release)
+{
+	switch (len) {
+	case 1:
+		if (release)
+			smp_store_release((uint8_t *)p, data->_u8);
+		else
+			WRITE_ONCE(*(uint8_t *)p, data->_u8);
+		break;
+	case 2:
+		if (release)
+			smp_store_release((uint16_t *)p, data->_u16);
+		else
+			WRITE_ONCE(*(uint16_t *)p, data->_u16);
+		break;
+	case 4:
+		if (release)
+			smp_store_release((uint32_t *)p, data->_u32);
+		else
+			WRITE_ONCE(*(uint32_t *)p, data->_u32);
+		break;
+	case 8:
+#if (BITS_PER_LONG == 64)
+		if (release)
+			smp_store_release((uint64_t *)p, data->_u64);
+		else
+			WRITE_ONCE(*(uint64_t *)p, data->_u64);
+#else
+	{
+		if (release)
+			smp_store_release((uint32_t *)p, data->_u64_split[0]);
+		else
+			WRITE_ONCE(*(uint32_t *)p, data->_u64_split[0]);
+		WRITE_ONCE(*((uint32_t *)p + 1), data->_u64_split[1]);
+	}
+#endif
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Return 0 if same, > 0 if different, < 0 on error. */
+static int do_cpu_op_compare(unsigned long _a, unsigned long _b, uint32_t len)
+{
+	void *a = (void *)_a;
+	void *b = (void *)_b;
+	union op_fn_data tmp[2];
+	int ret;
+
+	switch (len) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		if (!IS_ALIGNED(_a, len) || !IS_ALIGNED(_b, len))
+			goto memcmp;
+		break;
+	default:
+		goto memcmp;
+	}
+
+	ret = __op_get(&tmp[0], a, len);
+	if (ret)
+		return ret;
+	ret = __op_get(&tmp[1], b, len);
+	if (ret)
+		return ret;
+
+	switch (len) {
+	case 1:
+		ret = !!(tmp[0]._u8 != tmp[1]._u8);
+		break;
+	case 2:
+		ret = !!(tmp[0]._u16 != tmp[1]._u16);
+		break;
+	case 4:
+		ret = !!(tmp[0]._u32 != tmp[1]._u32);
+		break;
+	case 8:
+		ret = !!(tmp[0]._u64 != tmp[1]._u64);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return ret;
+
+memcmp:
+	if (memcmp(a, b, len))
+		return 1;
+	return 0;
+}
+
+/* Return 0 on success, < 0 on error. */
+static int do_cpu_op_memcpy(unsigned long _dst, unsigned long _src,
+			    uint32_t len, bool release)
+{
+	void *dst = (void *)_dst;
+	void *src = (void *)_src;
+	union op_fn_data tmp;
+	int ret;
+
+	switch (len) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		if (!IS_ALIGNED(_dst, len) || !IS_ALIGNED(_src, len))
+			goto memcpy;
+		break;
+	default:
+		goto memcpy;
+	}
+
+	ret = __op_get(&tmp, src, len);
+	if (ret)
+		return ret;
+	return __op_put(&tmp, dst, len, release);
+
+memcpy:
+	if (release)
+		smp_mb();
+	memcpy(dst, src, len);
+	return 0;
+}
+
+static int op_add_fn(union op_fn_data *data, uint64_t count, uint32_t len)
+{
+	switch (len) {
+	case 1:
+		data->_u8 += (uint8_t)count;
+		break;
+	case 2:
+		data->_u16 += (uint16_t)count;
+		break;
+	case 4:
+		data->_u32 += (uint32_t)count;
+		break;
+	case 8:
+		data->_u64 += (uint64_t)count;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Return 0 on success, < 0 on error. */
+static int do_cpu_op_fn(op_fn_t op_fn, unsigned long _p, uint64_t v,
+			uint32_t len, bool release)
+{
+	union op_fn_data tmp;
+	void *p = (void *)_p;
+	int ret;
+
+	ret = __op_get(&tmp, p, len);
+	if (ret)
+		return ret;
+	ret = op_fn(&tmp, v, len);
+	if (ret)
+		return ret;
+	ret = __op_put(&tmp, p, len, release);
+	if (ret)
+		return ret;
+	return 0;
+}
+
+/*
+ * Return negative value on error, positive value if comparison
+ * fails, 0 on success.
+ */
+static int __do_cpu_opv_op(struct cpu_op *op)
+{
+	/* Guarantee a compiler barrier between each operation. */
+	barrier();
+
+	switch (op->op) {
+	case CPU_COMPARE_EQ_OP:
+		return do_cpu_op_compare(op->u.compare_op.a,
+					 op->u.compare_op.b,
+					 op->len);
+	case CPU_COMPARE_NE_OP:
+	{
+		int ret;
+
+		ret = do_cpu_op_compare(op->u.compare_op.a,
+					op->u.compare_op.b,
+					op->len);
+		if (ret < 0)
+			return ret;
+		/*
+		 * Stop execution, return positive value if comparison
+		 * is identical.
+		 */
+		if (ret == 0)
+			return 1;
+		return 0;
+	}
+	case CPU_MEMCPY_OP:
+		return do_cpu_op_memcpy(op->u.memcpy_op.dst,
+					op->u.memcpy_op.src,
+					op->len, false);
+	case CPU_MEMCPY_RELEASE_OP:
+		return do_cpu_op_memcpy(op->u.memcpy_op.dst,
+					op->u.memcpy_op.src,
+					op->len, true);
+	case CPU_ADD_OP:
+		return do_cpu_op_fn(op_add_fn, op->u.arithmetic_op.p,
+				    op->u.arithmetic_op.count, op->len, false);
+	case CPU_ADD_RELEASE_OP:
+		return do_cpu_op_fn(op_add_fn, op->u.arithmetic_op.p,
+				    op->u.arithmetic_op.count, op->len, true);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int __do_cpu_opv(struct cpu_op *cpuop, int cpuopcnt)
+{
+	int i, ret;
+
+	for (i = 0; i < cpuopcnt; i++) {
+		ret = __do_cpu_opv_op(&cpuop[i]);
+		/* If comparison fails, stop execution and return index + 1. */
+		if (ret > 0)
+			return i + 1;
+		/* On error, stop execution. */
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+/*
+ * Check that the page pointers pinned by get_user_pages()
+ * are still in the page table. Invoked with mmap_sem held.
+ * Return 0 if pointers match, -EAGAIN if they don't.
+ */
+static int vaddr_check(struct vaddr *vaddr)
+{
+	struct page *pages[2];
+	int ret, n;
+
+	ret = __get_user_pages_fast(vaddr->uaddr, vaddr->nr_pages,
+				    vaddr->write, pages);
+	for (n = 0; n < ret; n++)
+		put_page(pages[n]);
+	if (ret < vaddr->nr_pages) {
+		ret = get_user_pages(vaddr->uaddr, vaddr->nr_pages,
+				     vaddr->write ? FOLL_WRITE : 0,
+				     pages, NULL);
+		if (ret < 0)
+			return -EAGAIN;
+		for (n = 0; n < ret; n++)
+			put_page(pages[n]);
+		if (ret < vaddr->nr_pages)
+			return -EAGAIN;
+	}
+	for (n = 0; n < vaddr->nr_pages; n++) {
+		if (pages[n] != vaddr->pages[n])
+			return -EAGAIN;
+	}
+	return 0;
+}
+
+static int vaddr_ptrs_check(struct cpu_opv_vaddr *vaddr_ptrs)
+{
+	int i;
+
+	for (i = 0; i < vaddr_ptrs->nr_vaddr; i++) {
+		int ret;
+
+		ret = vaddr_check(&vaddr_ptrs->addr[i]);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static void cpu_opv_ipi(void *info)
+{
+	struct opv_ipi_args *args = info;
+
+	rseq_preempt(current);
+	args->ret = __do_cpu_opv(args->cpuop, args->cpuopcnt);
+}
+
+static int do_cpu_opv(struct cpu_op *cpuop, int cpuopcnt,
+		      struct cpu_opv_vaddr *vaddr_ptrs, int cpu)
+{
+	struct mm_struct *mm = current->mm;
+	struct opv_ipi_args args = {
+		.cpuop = cpuop,
+		.cpuopcnt = cpuopcnt,
+	};
+	int ret;
+
+retry:
+	if (!cpumask_test_cpu(cpu, &current->cpus_allowed))
+		return -EINVAL;
+	down_read(&mm->mmap_sem);
+	ret = vaddr_ptrs_check(vaddr_ptrs);
+	if (ret)
+		goto end;
+	ret = smp_call_function_single(cpu, cpu_opv_ipi, &args, 1);
+	if (ret) {
+		up_read(&mm->mmap_sem);
+		goto check_online;
+	}
+	ret = args.ret;
+end:
+	up_read(&mm->mmap_sem);
+	return ret;
+
+check_online:
+	get_online_cpus();
+	if (cpu_online(cpu)) {
+		put_online_cpus();
+		goto retry;
+	}
+	/*
+	 * CPU is offline. Perform operation from the current CPU with
+	 * cpu_online read lock held, preventing that CPU from coming online,
+	 * and with mutex held, providing mutual exclusion against other
+	 * CPUs also finding out about an offline CPU.
+	 */
+	down_read(&mm->mmap_sem);
+	ret = vaddr_ptrs_check(vaddr_ptrs);
+	if (ret)
+		goto offline_end;
+	mutex_lock(&cpu_opv_offline_lock);
+	ret = __do_cpu_opv(cpuop, cpuopcnt);
+	mutex_unlock(&cpu_opv_offline_lock);
+offline_end:
+	up_read(&mm->mmap_sem);
+	put_online_cpus();
+	return ret;
+}
+
+/*
+ * cpu_opv - execute operation vector on a given CPU in interrupt context.
+ *
+ * Userspace should pass the CPU number on which the operation vector
+ * should be executed as parameter.
+ */
+SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
+		int, cpu, int, flags)
+{
+	struct cpu_op cpuopv[CPU_OP_VEC_LEN_MAX];
+	struct cpu_opv_vaddr vaddr_ptrs = {
+		.nr_vaddr = 0,
+	};
+	int ret, i, nr_vaddr = 0;
+	bool retry = false;
+
+	if (unlikely(flags & ~(CPU_OP_NR_FLAG | CPU_OP_VEC_LEN_MAX_FLAG)))
+		return -EINVAL;
+	if (flags & CPU_OP_NR_FLAG) {
+		if (flags & CPU_OP_VEC_LEN_MAX_FLAG)
+			return -EINVAL;
+		return NR_CPU_OPS;
+	}
+	if (flags & CPU_OP_VEC_LEN_MAX_FLAG)
+		return CPU_OP_VEC_LEN_MAX;
+	if (unlikely(cpu < 0))
+		return -EINVAL;
+	if (cpuopcnt < 0 || cpuopcnt > CPU_OP_VEC_LEN_MAX)
+		return -EINVAL;
+	if (copy_from_user(cpuopv, ucpuopv, cpuopcnt * sizeof(struct cpu_op)))
+		return -EFAULT;
+	ret = cpu_opv_check(cpuopv, cpuopcnt, &nr_vaddr);
+	if (ret)
+		return ret;
+	if (nr_vaddr > NR_VADDR)
+		return -EINVAL;
+again:
+	ret = cpu_opv_pin_pages(cpuopv, cpuopcnt, &vaddr_ptrs);
+	if (ret)
+		goto end;
+	ret = do_cpu_opv(cpuopv, cpuopcnt, &vaddr_ptrs, cpu);
+	if (ret == -EAGAIN)
+		retry = true;
+end:
+	for (i = 0; i < vaddr_ptrs.nr_vaddr; i++) {
+		struct vaddr *vaddr = &vaddr_ptrs.addr[i];
+		int j;
+
+		vm_unmap_user_ram((void *)vaddr->mem, vaddr->nr_pages);
+		for (j = 0; j < vaddr->nr_pages; j++) {
+			if (vaddr->write)
+				set_page_dirty(vaddr->pages[j]);
+			put_page(vaddr->pages[j]);
+		}
+	}
+	/*
+	 * Force vm_map flush to ensure we don't exhaust available vmalloc
+	 * address space.
+	 */
+	if (vaddr_ptrs.nr_vaddr)
+		vm_unmap_aliases();
+	if (retry) {
+		retry = false;
+		vaddr_ptrs.nr_vaddr = 0;
+		goto again;
+	}
+	return ret;
+}
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index df556175be50..0a6410d77c33 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -435,3 +435,4 @@ COND_SYSCALL(setuid16);
 
 /* restartable sequence */
 COND_SYSCALL(rseq);
+COND_SYSCALL(cpu_opv);
-- 
2.11.0

[RFC PATCH for 4.21 07/16] cpu_opv: limit amount of virtual address space used by cpu_opv

[Mathieu Desnoyers]

Introduce sysctl cpu_opv_va_max_bytes, which limits the amount of
virtual address space that can be used by cpu_opv.

Its default value is the maximum amount of virtual address space which
can be used by a single cpu_opv system call (e.g. 64 kB on x86).

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-api@vger.kernel.org
---
 kernel/cpu_opv.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 kernel/sysctl.c  | 15 ++++++++++++
 2 files changed, 88 insertions(+), 1 deletion(-)

diff --git a/kernel/cpu_opv.c b/kernel/cpu_opv.c
index 6ee7ca3376be..309d20a35227 100644
--- a/kernel/cpu_opv.c
+++ b/kernel/cpu_opv.c
@@ -59,6 +59,16 @@
 /* Maximum number of virtual addresses per op. */
 #define CPU_OP_VEC_MAX_ADDR		(2 * CPU_OP_VEC_LEN_MAX)
 
+/* Maximum address range size (aligned on SHMLBA) per virtual address. */
+#define CPU_OP_RANGE_PER_ADDR_MAX	(2 * SHMLBA)
+
+/*
+ * Minimum value for sysctl_cpu_opv_va_max_bytes is the maximum virtual memory
+ * space needed by one cpu_opv system call.
+ */
+#define CPU_OPV_VA_MAX_BYTES_MIN	\
+		(CPU_OP_VEC_MAX_ADDR * CPU_OP_RANGE_PER_ADDR_MAX)
+
 union op_fn_data {
 	uint8_t _u8;
 	uint16_t _u16;
@@ -96,6 +106,15 @@ struct opv_ipi_args {
  */
 static DEFINE_MUTEX(cpu_opv_offline_lock);
 
+/* Maximum virtual address space which can be used by cpu_opv. */
+int sysctl_cpu_opv_va_max_bytes __read_mostly;
+int sysctl_cpu_opv_va_max_bytes_min;
+
+static atomic_t cpu_opv_va_allocated_bytes;
+
+/* Waitqueue for cpu_opv blocked on virtual address space reservation. */
+static DECLARE_WAIT_QUEUE_HEAD(cpu_opv_va_wait);
+
 /*
  * The cpu_opv system call executes a vector of operations on behalf of
  * user-space on a specific CPU either with interrupts disabled or within
@@ -489,6 +508,43 @@ static int cpu_opv_pin_pages_op(struct cpu_op *op,
 	return 0;
 }
 
+/*
+ * Approximate the amount of virtual address space required per
+ * vaddr to a worse-case of CPU_OP_RANGE_PER_ADDR_MAX.
+ */
+static int cpu_opv_reserve_va(int nr_vaddr, int *reserved_va)
+{
+	int nr_bytes = nr_vaddr * CPU_OP_RANGE_PER_ADDR_MAX;
+	int old_bytes, new_bytes;
+
+	WARN_ON_ONCE(*reserved_va != 0);
+	if (nr_bytes > sysctl_cpu_opv_va_max_bytes) {
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+	do {
+		wait_event(cpu_opv_va_wait,
+			(old_bytes = atomic_read(&cpu_opv_va_allocated_bytes)) +
+			nr_bytes <= sysctl_cpu_opv_va_max_bytes);
+		new_bytes = old_bytes + nr_bytes;
+	} while (atomic_cmpxchg(&cpu_opv_va_allocated_bytes,
+		 old_bytes, new_bytes) != old_bytes);
+
+	*reserved_va = nr_bytes;
+	return 0;
+}
+
+static void cpu_opv_unreserve_va(int *reserved_va)
+{
+	int nr_bytes = *reserved_va;
+
+	if (!nr_bytes)
+		return;
+	atomic_sub(nr_bytes, &cpu_opv_va_allocated_bytes);
+	wake_up(&cpu_opv_va_wait);
+	*reserved_va = 0;
+}
+
 static int cpu_opv_pin_pages(struct cpu_op *cpuop, int cpuopcnt,
 			     struct cpu_opv_vaddr *vaddr_ptrs)
 {
@@ -898,7 +954,7 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
 	struct cpu_opv_vaddr vaddr_ptrs = {
 		.nr_vaddr = 0,
 	};
-	int ret, i, nr_vaddr = 0;
+	int ret, i, nr_vaddr = 0, reserved_va = 0;
 	bool retry = false;
 
 	if (unlikely(flags & ~(CPU_OP_NR_FLAG | CPU_OP_VEC_LEN_MAX_FLAG)))
@@ -922,6 +978,9 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
 	if (nr_vaddr > NR_VADDR)
 		return -EINVAL;
 again:
+	ret = cpu_opv_reserve_va(nr_vaddr, &reserved_va);
+	if (ret)
+		goto end;
 	ret = cpu_opv_pin_pages(cpuopv, cpuopcnt, &vaddr_ptrs);
 	if (ret)
 		goto end;
@@ -946,6 +1005,7 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
 	 */
 	if (vaddr_ptrs.nr_vaddr)
 		vm_unmap_aliases();
+	cpu_opv_unreserve_va(&reserved_va);
 	if (retry) {
 		retry = false;
 		vaddr_ptrs.nr_vaddr = 0;
@@ -953,3 +1013,15 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt,
 	}
 	return ret;
 }
+
+/*
+ * Dynamic initialization is required on sparc because SHMLBA is not a
+ * constant.
+ */
+static int __init cpu_opv_init(void)
+{
+	sysctl_cpu_opv_va_max_bytes = CPU_OPV_VA_MAX_BYTES_MIN;
+	sysctl_cpu_opv_va_max_bytes_min = CPU_OPV_VA_MAX_BYTES_MIN;
+	return 0;
+}
+core_initcall(cpu_opv_init);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index cc02050fd0c4..eb34c6be2aa4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -175,6 +175,11 @@ extern int unaligned_dump_stack;
 extern int no_unaligned_warning;
 #endif
 
+#ifdef CONFIG_CPU_OPV
+extern int sysctl_cpu_opv_va_max_bytes;
+extern int sysctl_cpu_opv_va_max_bytes_min;
+#endif
+
 #ifdef CONFIG_PROC_SYSCTL
 
 /**
@@ -1233,6 +1238,16 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &one,
 	},
 #endif
+#ifdef CONFIG_CPU_OPV
+	{
+		.procname	= "cpu_opv_va_max_bytes",
+		.data		= &sysctl_cpu_opv_va_max_bytes,
+		.maxlen		= sizeof(sysctl_cpu_opv_va_max_bytes),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &sysctl_cpu_opv_va_max_bytes_min,
+	},
+#endif
 	{ }
 };
 
-- 
2.11.0

[RFC PATCH for 4.21 08/16] x86: Wire up cpu_opv system call

[Mathieu Desnoyers]

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul Turner <pjt@google.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Michael Kerrisk <mtk.manpages@gmail.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-api@vger.kernel.org
---
 arch/x86/entry/syscalls/syscall_32.tbl | 1 +
 arch/x86/entry/syscalls/syscall_64.tbl | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 3cf7b533b3d1..d3253547e15e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -398,3 +398,4 @@
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents		__ia32_compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
+387	i386	cpu_opv			sys_cpu_opv			__ia32_sys_cpu_opv
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..1391971b1517 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,7 @@
 332	common	statx			__x64_sys_statx
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
+335	common	cpu_opv			__x64_sys_cpu_opv
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
-- 
2.11.0

[RFC PATCH for 4.21 09/16] powerpc: Wire up cpu_opv system call

[Mathieu Desnoyers]

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: linuxppc-dev@lists.ozlabs.org
---
 arch/powerpc/include/asm/systbl.h      | 1 +
 arch/powerpc/include/uapi/asm/unistd.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 01b5171ea189..8f58710f5e8b 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -394,3 +394,4 @@ SYSCALL(pkey_free)
 SYSCALL(pkey_mprotect)
 SYSCALL(rseq)
 COMPAT_SYS(io_pgetevents)
+SYSCALL(cpu_opv)
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 985534d0b448..112e2c54750a 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -400,5 +400,6 @@
 #define __NR_pkey_mprotect	386
 #define __NR_rseq		387
 #define __NR_io_pgetevents	388
+#define __NR_cpu_opv		389
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
-- 
2.11.0

[RFC PATCH for 4.21 10/16] arm: Wire up cpu_opv system call

[Mathieu Desnoyers]

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Paul Turner <pjt@google.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-api@vger.kernel.org
---
 arch/arm/tools/syscall.tbl | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 8edf93b4490f..da2cb7a12644 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -414,3 +414,4 @@
 397	common	statx			sys_statx
 398	common	rseq			sys_rseq
 399	common	io_pgetevents		sys_io_pgetevents
+400	common	cpu_opv			sys_cpu_opv
-- 
2.11.0

[RFC PATCH for 4.21 11/16] cpu-opv/selftests: Provide cpu-op library

[Mathieu Desnoyers]

This cpu-op helper library provides a user-space API to the cpu_opv()
system call.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/cpu-opv/cpu-op.c | 362 +++++++++++++++++++++++++++++++
 tools/testing/selftests/cpu-opv/cpu-op.h |  43 ++++
 2 files changed, 405 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/cpu-op.c
 create mode 100644 tools/testing/selftests/cpu-opv/cpu-op.h

diff --git a/tools/testing/selftests/cpu-opv/cpu-op.c b/tools/testing/selftests/cpu-opv/cpu-op.c
new file mode 100644
index 000000000000..0cdc39bffbbf
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/cpu-op.c
@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * cpu-op.c
+ *
+ * Copyright (C) 2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; only
+ * version 2.1 of the License.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <syscall.h>
+#include <assert.h>
+#include <signal.h>
+
+#include "cpu-op.h"
+
+#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+
+#define ACCESS_ONCE(x)		(*(__volatile__  __typeof__(x) *)&(x))
+#define WRITE_ONCE(x, v)	__extension__ ({ ACCESS_ONCE(x) = (v); })
+#define READ_ONCE(x)		ACCESS_ONCE(x)
+
+int cpu_opv(struct cpu_op *cpu_opv, int cpuopcnt, int cpu, int flags)
+{
+	return syscall(__NR_cpu_opv, cpu_opv, cpuopcnt, cpu, flags);
+}
+
+int cpu_op_get_current_cpu(void)
+{
+	int cpu;
+
+	cpu = sched_getcpu();
+	if (cpu < 0) {
+		perror("sched_getcpu()");
+		abort();
+	}
+	return cpu;
+}
+
+int cpu_op_cmpxchg(void *v, void *expect, void *old, void *n, size_t len,
+		   int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)old,
+			.u.memcpy_op.src = (unsigned long)v,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+		[1] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = len,
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[2] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)n,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_add(void *v, int64_t count, size_t len, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_ADD_OP,
+			.len = len,
+			.u.arithmetic_op.p = (unsigned long)v,
+			.u.arithmetic_op.count = count,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_add_release(void *v, int64_t count, size_t len, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_ADD_RELEASE_OP,
+			.len = len,
+			.u.arithmetic_op.p = (unsigned long)v,
+			.u.arithmetic_op.count = count,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv,
+			 int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)&expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)&newv,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int cpu_op_cmpeqv_storep_expect_fault(intptr_t *v, intptr_t expect,
+					     intptr_t *newp, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)&expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)newp,
+			.u.memcpy_op.expect_fault_dst = 0,
+			/* Return EAGAIN on src fault. */
+			.u.memcpy_op.expect_fault_src = 1,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+				 off_t voffp, intptr_t *load, int cpu)
+{
+	int ret;
+
+	do {
+		intptr_t oldv = READ_ONCE(*v);
+		intptr_t *newp = (intptr_t *)(oldv + voffp);
+
+		if (oldv == expectnot)
+			return 1;
+		ret = cpu_op_cmpeqv_storep_expect_fault(v, oldv, newp, cpu);
+		if (!ret) {
+			*load = oldv;
+			return 0;
+		}
+	} while (ret > 0);
+
+	return -1;
+}
+
+int cpu_op_cmpeqv_storev_storev(intptr_t *v, intptr_t expect,
+				intptr_t *v2, intptr_t newv2,
+				intptr_t newv, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)&expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v2,
+			.u.memcpy_op.src = (unsigned long)&newv2,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+		[2] = {
+			.op = CPU_MEMCPY_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)&newv,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_storev_storev_release(intptr_t *v, intptr_t expect,
+				   intptr_t *v2, intptr_t newv2,
+				   intptr_t newv, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)&expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v2,
+			.u.memcpy_op.src = (unsigned long)&newv2,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+		[2] = {
+			.op = CPU_MEMCPY_RELEASE_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)&newv,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+				intptr_t *v2, intptr_t expect2,
+				intptr_t newv, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)&expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v2,
+			.u.compare_op.b = (unsigned long)&expect2,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[2] = {
+			.op = CPU_MEMCPY_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)&newv,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_memcpy_storev(intptr_t *v, intptr_t expect,
+				void *dst, void *src, size_t len,
+				intptr_t newv, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)&expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst,
+			.u.memcpy_op.src = (unsigned long)src,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+		[2] = {
+			.op = CPU_MEMCPY_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)&newv,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_cmpeqv_memcpy_storev_release(intptr_t *v, intptr_t expect,
+				   void *dst, void *src, size_t len,
+				   intptr_t newv, int cpu)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = sizeof(intptr_t),
+			.u.compare_op.a = (unsigned long)v,
+			.u.compare_op.b = (unsigned long)&expect,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst,
+			.u.memcpy_op.src = (unsigned long)src,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+		[2] = {
+			.op = CPU_MEMCPY_RELEASE_OP,
+			.len = sizeof(intptr_t),
+			.u.memcpy_op.dst = (unsigned long)v,
+			.u.memcpy_op.src = (unsigned long)&newv,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+int cpu_op_addv(intptr_t *v, int64_t count, int cpu)
+{
+	return cpu_op_add(v, count, sizeof(intptr_t), cpu);
+}
diff --git a/tools/testing/selftests/cpu-opv/cpu-op.h b/tools/testing/selftests/cpu-opv/cpu-op.h
new file mode 100644
index 000000000000..853fcb302516
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/cpu-op.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * cpu-op.h
+ *
+ * (C) Copyright 2017-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef CPU_OPV_H
+#define CPU_OPV_H
+
+#include <stdlib.h>
+#include <stdint.h>
+#include <linux/cpu_opv.h>
+
+int cpu_opv(struct cpu_op *cpuopv, int cpuopcnt, int cpu, int flags);
+int cpu_op_get_current_cpu(void);
+
+int cpu_op_cmpxchg(void *v, void *expect, void *old, void *_new, size_t len,
+		   int cpu);
+int cpu_op_add(void *v, int64_t count, size_t len, int cpu);
+int cpu_op_add_release(void *v, int64_t count, size_t len, int cpu);
+
+int cpu_op_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu);
+int cpu_op_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+				 off_t voffp, intptr_t *load, int cpu);
+int cpu_op_cmpeqv_storev_storev(intptr_t *v, intptr_t expect,
+				intptr_t *v2, intptr_t newv2,
+				intptr_t newv, int cpu);
+int cpu_op_cmpeqv_storev_storev_release(intptr_t *v, intptr_t expect,
+				   intptr_t *v2, intptr_t newv2,
+				   intptr_t newv, int cpu);
+int cpu_op_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+				intptr_t *v2, intptr_t expect2,
+				intptr_t newv, int cpu);
+int cpu_op_cmpeqv_memcpy_storev(intptr_t *v, intptr_t expect,
+				void *dst, void *src, size_t len,
+				intptr_t newv, int cpu);
+int cpu_op_cmpeqv_memcpy_storev_release(intptr_t *v, intptr_t expect,
+				   void *dst, void *src, size_t len,
+				   intptr_t newv, int cpu);
+int cpu_op_addv(intptr_t *v, int64_t count, int cpu);
+
+#endif  /* CPU_OPV_H_ */
-- 
2.11.0

[RFC PATCH for 4.21 12/16] cpu-opv/selftests: Provide basic test

[Mathieu Desnoyers]

"basic_cpu_opv_test" tests basic functionality of cpu_opv.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 .../testing/selftests/cpu-opv/basic_cpu_opv_test.c | 1207 ++++++++++++++++++++
 1 file changed, 1207 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c

diff --git a/tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c b/tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c
new file mode 100644
index 000000000000..28221b0260fa
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/basic_cpu_opv_test.c
@@ -0,0 +1,1207 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Basic test coverage for cpu_opv system call.
+ */
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <sys/mman.h>
+#include <sched.h>
+
+#include "../kselftest.h"
+
+#include "cpu-op.h"
+
+#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+
+#define TESTBUFLEN	4096
+#define TESTBUFLEN_CMP	16
+
+#define TESTBUFLEN_PAGE_MAX	65536
+
+#define NR_PF_ARRAY	16384
+#define PF_ARRAY_LEN	4096
+
+#define NR_HUGE_ARRAY	512
+#define HUGEMAPLEN	(NR_HUGE_ARRAY * PF_ARRAY_LEN)
+
+/* 64 MB arrays for page fault testing. */
+char pf_array_dst[NR_PF_ARRAY][PF_ARRAY_LEN];
+char pf_array_src[NR_PF_ARRAY][PF_ARRAY_LEN];
+
+static int test_ops_supported(void)
+{
+	const char *test_name = "test_ops_supported";
+	int ret;
+
+	ret = cpu_opv(NULL, 0, -1, CPU_OP_NR_FLAG);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret < NR_CPU_OPS) {
+		ksft_test_result_fail("%s test: only %d operations supported, expecting at least %d\n",
+				      test_name, ret, NR_CPU_OPS);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_compare_eq_op(char *a, char *b, size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = len,
+			.u.compare_op.a = (unsigned long)a,
+			.u.compare_op.b = (unsigned long)b,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_compare_eq_same(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN];
+	char buf2[TESTBUFLEN];
+	const char *test_name = "test_compare_eq same";
+
+	/* Test compare_eq */
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf1[i] = (char)i;
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf2[i] = (char)i;
+	ret = test_compare_eq_op(buf2, buf1, TESTBUFLEN);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret > 0) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 0);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_compare_eq_diff(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN];
+	char buf2[TESTBUFLEN];
+	const char *test_name = "test_compare_eq different";
+
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf1[i] = (char)i;
+	memset(buf2, 0, TESTBUFLEN);
+	ret = test_compare_eq_op(buf2, buf1, TESTBUFLEN);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret == 0) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 1);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_compare_ne_op(char *a, char *b, size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_NE_OP,
+			.len = len,
+			.u.compare_op.a = (unsigned long)a,
+			.u.compare_op.b = (unsigned long)b,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_compare_ne_same(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN];
+	char buf2[TESTBUFLEN];
+	const char *test_name = "test_compare_ne same";
+
+	/* Test compare_ne */
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf1[i] = (char)i;
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf2[i] = (char)i;
+	ret = test_compare_ne_op(buf2, buf1, TESTBUFLEN);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret == 0) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 1);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_compare_ne_diff(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN];
+	char buf2[TESTBUFLEN];
+	const char *test_name = "test_compare_ne different";
+
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf1[i] = (char)i;
+	memset(buf2, 0, TESTBUFLEN);
+	ret = test_compare_ne_op(buf2, buf1, TESTBUFLEN);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret != 0) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 0);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_2compare_eq_op(char *a, char *b, char *c, char *d,
+		size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = len,
+			.u.compare_op.a = (unsigned long)a,
+			.u.compare_op.b = (unsigned long)b,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_COMPARE_EQ_OP,
+			.len = len,
+			.u.compare_op.a = (unsigned long)c,
+			.u.compare_op.b = (unsigned long)d,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_2compare_eq_index(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN_CMP];
+	char buf2[TESTBUFLEN_CMP];
+	char buf3[TESTBUFLEN_CMP];
+	char buf4[TESTBUFLEN_CMP];
+	const char *test_name = "test_2compare_eq index";
+
+	for (i = 0; i < TESTBUFLEN_CMP; i++)
+		buf1[i] = (char)i;
+	memset(buf2, 0, TESTBUFLEN_CMP);
+	memset(buf3, 0, TESTBUFLEN_CMP);
+	memset(buf4, 0, TESTBUFLEN_CMP);
+
+	/* First compare failure is op[0], expect 1. */
+	ret = test_2compare_eq_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret != 1) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 1);
+		return -1;
+	}
+
+	/* All compares succeed. */
+	for (i = 0; i < TESTBUFLEN_CMP; i++)
+		buf2[i] = (char)i;
+	ret = test_2compare_eq_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret != 0) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 0);
+		return -1;
+	}
+
+	/* First compare failure is op[1], expect 2. */
+	for (i = 0; i < TESTBUFLEN_CMP; i++)
+		buf3[i] = (char)i;
+	ret = test_2compare_eq_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret != 2) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 2);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_2compare_ne_op(char *a, char *b, char *c, char *d,
+		size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_COMPARE_NE_OP,
+			.len = len,
+			.u.compare_op.a = (unsigned long)a,
+			.u.compare_op.b = (unsigned long)b,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+		[1] = {
+			.op = CPU_COMPARE_NE_OP,
+			.len = len,
+			.u.compare_op.a = (unsigned long)c,
+			.u.compare_op.b = (unsigned long)d,
+			.u.compare_op.expect_fault_a = 0,
+			.u.compare_op.expect_fault_b = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_2compare_ne_index(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN_CMP];
+	char buf2[TESTBUFLEN_CMP];
+	char buf3[TESTBUFLEN_CMP];
+	char buf4[TESTBUFLEN_CMP];
+	const char *test_name = "test_2compare_ne index";
+
+	memset(buf1, 0, TESTBUFLEN_CMP);
+	memset(buf2, 0, TESTBUFLEN_CMP);
+	memset(buf3, 0, TESTBUFLEN_CMP);
+	memset(buf4, 0, TESTBUFLEN_CMP);
+
+	/* First compare ne failure is op[0], expect 1. */
+	ret = test_2compare_ne_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret != 1) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 1);
+		return -1;
+	}
+
+	/* All compare ne succeed. */
+	for (i = 0; i < TESTBUFLEN_CMP; i++)
+		buf1[i] = (char)i;
+	for (i = 0; i < TESTBUFLEN_CMP; i++)
+		buf3[i] = (char)i;
+	ret = test_2compare_ne_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret != 0) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 0);
+		return -1;
+	}
+
+	/* First compare failure is op[1], expect 2. */
+	for (i = 0; i < TESTBUFLEN_CMP; i++)
+		buf4[i] = (char)i;
+	ret = test_2compare_ne_op(buf2, buf1, buf4, buf3, TESTBUFLEN_CMP);
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret != 2) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, ret, 2);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_memcpy_op(void *dst, void *src, size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst,
+			.u.memcpy_op.src = (unsigned long)src,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_memcpy(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN];
+	char buf2[TESTBUFLEN];
+	const char *test_name = "test_memcpy";
+
+	/* Test memcpy */
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf1[i] = (char)i;
+	memset(buf2, 0, TESTBUFLEN);
+	ret = test_memcpy_op(buf2, buf1, TESTBUFLEN);
+	if (ret) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	for (i = 0; i < TESTBUFLEN; i++) {
+		if (buf2[i] != (char)i) {
+			ksft_test_result_fail("%s test: unexpected value at offset %d. Found %d. Should be %d.\n",
+					      test_name, i, buf2[i], (char)i);
+			return -1;
+		}
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_memcpy_u32(void)
+{
+	int ret;
+	uint32_t v1, v2;
+	const char *test_name = "test_memcpy_u32";
+
+	/* Test memcpy_u32 */
+	v1 = 42;
+	v2 = 0;
+	ret = test_memcpy_op(&v2, &v1, sizeof(v1));
+	if (ret) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (v1 != v2) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, v2, v1);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_memcpy_memcpy_release_op(void *dst1, void *src1,
+		void *dst2, void *src2, size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst1,
+			.u.memcpy_op.src = (unsigned long)src1,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_RELEASE_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst2,
+			.u.memcpy_op.src = (unsigned long)src2,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_memcpy_memcpy_release(void)
+{
+	int ret;
+	int v1, v2, v3;
+	const char *test_name = "test_memcpy_memcpy_release";
+
+	/* Test memcpy */
+	v1 = 42;
+	v2 = v3 = 0;
+	ret = test_memcpy_memcpy_release_op(&v2, &v1, &v3, &v2, sizeof(int));
+	if (ret) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (v3 != v1) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, v3, v1);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_add_op(int *v, int64_t increment)
+{
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_op_add(v, increment, sizeof(*v), cpu);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_add(void)
+{
+	int orig_v = 42, v, ret;
+	int increment = 1;
+	const char *test_name = "test_add";
+
+	v = orig_v;
+	ret = test_add_op(&v, increment);
+	if (ret) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (v != orig_v + increment) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, v,
+				      orig_v + increment);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_add_release_op(int *v, int64_t increment)
+{
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_op_add_release(v, increment, sizeof(*v), cpu);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_add_release(void)
+{
+	int orig_v = 42, v, ret;
+	int increment = 1;
+	const char *test_name = "test_add_release";
+
+	v = orig_v;
+	ret = test_add_release_op(&v, increment);
+	if (ret) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (v != orig_v + increment) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, v,
+				      orig_v + increment);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_two_add_op(int *v, int64_t *increments)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(*v),
+			.u.arithmetic_op.p = (unsigned long)v,
+			.u.arithmetic_op.count = increments[0],
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[1] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(*v),
+			.u.arithmetic_op.p = (unsigned long)v,
+			.u.arithmetic_op.count = increments[1],
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_two_add(void)
+{
+	int orig_v = 42, v, ret;
+	int64_t increments[2] = { 99, 123 };
+	const char *test_name = "test_two_add";
+
+	v = orig_v;
+	ret = test_two_add_op(&v, increments);
+	if (ret) {
+		ksft_test_result_fail("%s test: returned with %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (v != orig_v + increments[0] + increments[1]) {
+		ksft_test_result_fail("%s test: unexpected value %d. Should be %d.\n",
+				      test_name, v,
+				      orig_v + increments[0] + increments[1]);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_cmpxchg_op(void *v, void *expect, void *old, void *n,
+		size_t len)
+{
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_op_cmpxchg(v, expect, old, n, len, cpu);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_cmpxchg_success(void)
+{
+	int ret;
+	uint64_t orig_v = 1, v, expect = 1, old = 0, n = 3;
+	const char *test_name = "test_cmpxchg success";
+
+	v = orig_v;
+	ret = test_cmpxchg_op(&v, &expect, &old, &n, sizeof(uint64_t));
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret) {
+		ksft_test_result_fail("%s returned %d, expecting %d\n",
+				      test_name, ret, 0);
+		return -1;
+	}
+	if (v != n) {
+		ksft_test_result_fail("%s v is %lld, expecting %lld\n",
+				      test_name, (long long)v, (long long)n);
+		return -1;
+	}
+	if (old != orig_v) {
+		ksft_test_result_fail("%s old is %lld, expecting %lld\n",
+				      test_name, (long long)old,
+				      (long long)orig_v);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_cmpxchg_fail(void)
+{
+	int ret;
+	uint64_t orig_v = 1, v, expect = 123, old = 0, n = 3;
+	const char *test_name = "test_cmpxchg fail";
+
+	v = orig_v;
+	ret = test_cmpxchg_op(&v, &expect, &old, &n, sizeof(uint64_t));
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (ret == 0) {
+		ksft_test_result_fail("%s returned %d, expecting %d\n",
+				      test_name, ret, 1);
+		return -1;
+	}
+	if (v == n) {
+		ksft_test_result_fail("%s returned %lld, expecting %lld\n",
+				      test_name, (long long)v,
+				      (long long)orig_v);
+		return -1;
+	}
+	if (old != orig_v) {
+		ksft_test_result_fail("%s old is %lld, expecting %lld\n",
+				      test_name, (long long)old,
+				      (long long)orig_v);
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_memcpy_expect_fault_op(void *dst, void *src, size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst,
+			.u.memcpy_op.src = (unsigned long)src,
+			.u.memcpy_op.expect_fault_dst = 0,
+			/* Return EAGAIN on fault. */
+			.u.memcpy_op.expect_fault_src = 1,
+		},
+	};
+	int cpu;
+
+	cpu = cpu_op_get_current_cpu();
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_memcpy_fault(void)
+{
+	int ret;
+	char buf1[TESTBUFLEN];
+	const char *test_name = "test_memcpy_fault";
+
+	/* Test memcpy */
+	ret = test_memcpy_op(buf1, NULL, TESTBUFLEN);
+	if (!ret || (ret < 0 && errno != EFAULT)) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	/* Test memcpy expect fault */
+	ret = test_memcpy_expect_fault_op(buf1, NULL, TESTBUFLEN);
+	if (!ret || (ret < 0 && errno != EAGAIN)) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int do_test_unknown_op(void)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = -1,	/* Unknown */
+			.len = 0,
+		},
+	};
+	int cpu;
+
+	cpu = cpu_op_get_current_cpu();
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_unknown_op(void)
+{
+	int ret;
+	const char *test_name = "test_unknown_op";
+
+	ret = do_test_unknown_op();
+	if (!ret || (ret < 0 && errno != EINVAL)) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int do_test_max_ops(void)
+{
+	int v = 0;
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[1] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[2] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[3] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+	};
+	int cpu;
+
+	cpu = cpu_op_get_current_cpu();
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_max_ops(void)
+{
+	int ret;
+	const char *test_name = "test_max_ops";
+
+	ret = do_test_max_ops();
+	if (ret < 0) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int do_test_too_many_ops(void)
+{
+	int v = 0;
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[1] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[2] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[3] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+		[4] = {
+			.op = CPU_ADD_OP,
+			.len = sizeof(v),
+			.u.arithmetic_op.p = (unsigned long)&v,
+			.u.arithmetic_op.count = 0,
+			.u.arithmetic_op.expect_fault_p = 0,
+		},
+	};
+	int cpu;
+
+	cpu = cpu_op_get_current_cpu();
+	return cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+}
+
+static int test_too_many_ops(void)
+{
+	int ret;
+	const char *test_name = "test_too_many_ops";
+
+	ret = do_test_too_many_ops();
+	if (!ret || (ret < 0 && errno != EINVAL)) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+/* Use 64kB len, largest page size known on Linux. */
+static int test_memcpy_single_too_large(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN_PAGE_MAX + 1];
+	char buf2[TESTBUFLEN_PAGE_MAX + 1];
+	const char *test_name = "test_memcpy_single_too_large";
+
+	/* Test memcpy */
+	for (i = 0; i < TESTBUFLEN_PAGE_MAX + 1; i++)
+		buf1[i] = (char)i;
+	memset(buf2, 0, TESTBUFLEN_PAGE_MAX + 1);
+	ret = test_memcpy_op(buf2, buf1, TESTBUFLEN_PAGE_MAX + 1);
+	if (!ret || (ret < 0 && errno != EINVAL)) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+static int test_memcpy_single_ok_sum_too_large_op(void *dst, void *src,
+						  size_t len)
+{
+	struct cpu_op opvec[] = {
+		[0] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst,
+			.u.memcpy_op.src = (unsigned long)src,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+		[1] = {
+			.op = CPU_MEMCPY_OP,
+			.len = len,
+			.u.memcpy_op.dst = (unsigned long)dst,
+			.u.memcpy_op.src = (unsigned long)src,
+			.u.memcpy_op.expect_fault_dst = 0,
+			.u.memcpy_op.expect_fault_src = 0,
+		},
+	};
+	int ret, cpu;
+
+	do {
+		cpu = cpu_op_get_current_cpu();
+		ret = cpu_opv(opvec, ARRAY_SIZE(opvec), cpu, 0);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_memcpy_single_ok_sum_too_large(void)
+{
+	int i, ret;
+	char buf1[TESTBUFLEN];
+	char buf2[TESTBUFLEN];
+	const char *test_name = "test_memcpy_single_ok_sum_too_large";
+
+	/* Test memcpy */
+	for (i = 0; i < TESTBUFLEN; i++)
+		buf1[i] = (char)i;
+	memset(buf2, 0, TESTBUFLEN);
+	ret = test_memcpy_single_ok_sum_too_large_op(buf2, buf1, TESTBUFLEN);
+	if (!ret || (ret < 0 && errno != EINVAL)) {
+		ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+/*
+ * Iterate over large uninitialized arrays to trigger page faults.
+ * This includes reading from zero pages.
+ */
+int test_page_fault(void)
+{
+	int ret = 0;
+	uint64_t i;
+	const char *test_name = "test_page_fault";
+
+	for (i = 0; i < NR_PF_ARRAY; i++) {
+		ret = test_memcpy_op(pf_array_dst[i],
+				     pf_array_src[i],
+				     PF_ARRAY_LEN);
+		if (ret) {
+			ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+					      test_name, ret, strerror(errno));
+			return ret;
+		}
+	}
+	ksft_test_result_pass("%s test\n", test_name);
+	return 0;
+}
+
+/*
+ * Try to use 2MB huge pages.
+ */
+int test_hugetlb(void)
+{
+	int ret = 0;
+	uint64_t i;
+	const char *test_name = "test_hugetlb";
+	int *dst, *src;
+
+	dst = mmap(NULL, HUGEMAPLEN, PROT_READ | PROT_WRITE,
+		   MAP_HUGETLB | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (dst == MAP_FAILED) {
+		switch (errno) {
+		case ENOMEM:
+		case ENOENT:
+		case EINVAL:
+			ksft_test_result_skip("%s test.\n", test_name);
+			goto end;
+		default:
+			break;
+		}
+		perror("mmap");
+		abort();
+	}
+	src = mmap(NULL, HUGEMAPLEN, PROT_READ | PROT_WRITE,
+		   MAP_HUGETLB | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (src == MAP_FAILED) {
+		if (errno == ENOMEM) {
+			ksft_test_result_skip("%s test.\n", test_name);
+			goto unmap_dst;
+		}
+		perror("mmap");
+		abort();
+	}
+
+	/* Read/write from/to huge zero pages. */
+	for (i = 0; i < NR_HUGE_ARRAY; i++) {
+		ret = test_memcpy_op(dst + (i * PF_ARRAY_LEN / sizeof(int)),
+				     src + (i * PF_ARRAY_LEN / sizeof(int)),
+				     PF_ARRAY_LEN);
+		if (ret) {
+			ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+					      test_name, ret, strerror(errno));
+			return ret;
+		}
+	}
+	for (i = 0; i < NR_HUGE_ARRAY * (PF_ARRAY_LEN / sizeof(int)); i++)
+		src[i] = i;
+
+	for (i = 0; i < NR_HUGE_ARRAY; i++) {
+		ret = test_memcpy_op(dst + (i * PF_ARRAY_LEN / sizeof(int)),
+				     src + (i * PF_ARRAY_LEN / sizeof(int)),
+				     PF_ARRAY_LEN);
+		if (ret) {
+			ksft_test_result_fail("%s test: ret = %d, errno = %s\n",
+					      test_name, ret, strerror(errno));
+			return ret;
+		}
+	}
+
+	for (i = 0; i < NR_HUGE_ARRAY * (PF_ARRAY_LEN / sizeof(int)); i++) {
+		if (dst[i] != i) {
+			ksft_test_result_fail("%s mismatch, expect %d, got %d\n",
+					      test_name, i, dst[i]);
+			return ret;
+		}
+	}
+
+	ksft_test_result_pass("%s test\n", test_name);
+
+	if (munmap(src, HUGEMAPLEN)) {
+		perror("munmap");
+		abort();
+	}
+unmap_dst:
+	if (munmap(dst, HUGEMAPLEN)) {
+		perror("munmap");
+		abort();
+	}
+end:
+	return 0;
+}
+
+static int test_cmpxchg_op_cpu(void *v, void *expect, void *old, void *n,
+		size_t len, int cpu)
+{
+	int ret;
+
+	do {
+		ret = cpu_op_cmpxchg(v, expect, old, n, len, cpu);
+	} while (ret == -1 && errno == EAGAIN);
+
+	return ret;
+}
+
+static int test_over_possible_cpu(void)
+{
+	int ret;
+	uint64_t orig_v = 1, v, expect = 1, old = 0, n = 3;
+	const char *test_name = "test_over_possible_cpu";
+
+	v = orig_v;
+	ret = test_cmpxchg_op_cpu(&v, &expect, &old, &n, sizeof(uint64_t),
+				  0xFFFFFFFF);
+	if (ret == 0) {
+		ksft_test_result_fail("%s test: ret = %d\n",
+				      test_name, ret);
+		return -1;
+	}
+	if (ret < 0 && errno == EINVAL) {
+		ksft_test_result_pass("%s test\n", test_name);
+		return 0;
+	}
+	ksft_test_result_fail("%s returned %d, errno %s, expecting %d, errno %s\n",
+			      test_name, ret, strerror(errno),
+			      0, strerror(EINVAL));
+	return -1;
+}
+
+static int test_allowed_affinity(void)
+{
+	int ret;
+	uint64_t orig_v = 1, v, expect = 1, old = 0, n = 3;
+	const char *test_name = "test_allowed_affinity";
+	cpu_set_t allowed_cpus, cpuset;
+
+	ret = sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	if (ret) {
+		ksft_test_result_fail("%s returned %d, errno %s\n",
+				      test_name, ret, strerror(errno));
+		return -1;
+	}
+	if (!(CPU_ISSET(0, &allowed_cpus) && CPU_ISSET(1, &allowed_cpus))) {
+		ksft_test_result_skip("%s test. Requiring allowed CPUs 0 and 1.\n",
+				      test_name);
+		return 0;
+	}
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) {
+		ksft_test_result_fail("%s test. Unable to set affinity. errno = %s\n",
+				      test_name, strerror(errno));
+		return -1;
+	}
+	v = orig_v;
+	ret = test_cmpxchg_op_cpu(&v, &expect, &old, &n, sizeof(uint64_t),
+				  1);
+	if (sched_setaffinity(0, sizeof(allowed_cpus), &allowed_cpus) != 0) {
+		ksft_test_result_fail("%s test. Unable to set affinity. errno = %s\n",
+				      test_name, strerror(errno));
+		return -1;
+	}
+	if (ret == 0) {
+		ksft_test_result_fail("%s test: ret = %d\n",
+				      test_name, ret);
+		return -1;
+	}
+
+	if (ret < 0 && errno == EINVAL) {
+		ksft_test_result_pass("%s test\n", test_name);
+		return 0;
+	}
+	ksft_test_result_fail("%s returned %d, errno %s, expecting %d, errno %s\n",
+			      test_name, ret, strerror(errno),
+			      0, strerror(EINVAL));
+	return -1;
+}
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+
+	test_ops_supported();
+	test_compare_eq_same();
+	test_compare_eq_diff();
+	test_compare_ne_same();
+	test_compare_ne_diff();
+	test_2compare_eq_index();
+	test_2compare_ne_index();
+	test_memcpy();
+	test_memcpy_u32();
+	test_memcpy_memcpy_release();
+	test_add();
+	test_add_release();
+	test_two_add();
+	test_cmpxchg_success();
+	test_cmpxchg_fail();
+	test_memcpy_fault();
+	test_unknown_op();
+	test_max_ops();
+	test_too_many_ops();
+	test_memcpy_single_too_large();
+	test_memcpy_single_ok_sum_too_large();
+	test_page_fault();
+	test_hugetlb();
+	test_over_possible_cpu();
+	test_allowed_affinity();
+
+	return ksft_exit_pass();
+}
-- 
2.11.0

[RFC PATCH for 4.21 13/16] cpu-opv/selftests: Provide percpu_op API

[Mathieu Desnoyers]

Introduce percpu-op.h API. It uses rseq internally as fast-path if
invoked from the right CPU, else cpu_opv as slow-path if called
from the wrong CPU or if rseq fails.

This allows acting on per-cpu data from various CPUs transparently from
user-space: cpu_opv will take care of migrating the thread to the
requested CPU. Use-cases such as rebalancing memory across per-cpu
memory pools, or migrating tasks for a user-space scheduler, are thus
facilitated. This also handles debugger single-stepping.

The use from userspace is, e.g. for a counter increment:

    int cpu, ret;

    cpu = percpu_current_cpu();
    ret = percpu_addv(&data->c[cpu].count, 1, cpu);
    if (unlikely(ret)) {
         perror("percpu_addv");
         return -1;
    }
    return 0;

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Shuah Khan <shuah@kernel.org>
CC: Russell King <linux@arm.linux.org.uk>
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Paul Turner <pjt@google.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: Dave Watson <davejwatson@fb.com>
CC: Chris Lameter <cl@linux.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ben Maurer <bmaurer@fb.com>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: linux-kselftest@vger.kernel.org
CC: linux-api@vger.kernel.org
---
 tools/testing/selftests/cpu-opv/percpu-op.h | 151 ++++++++++++++++++++++++++++
 1 file changed, 151 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/percpu-op.h

diff --git a/tools/testing/selftests/cpu-opv/percpu-op.h b/tools/testing/selftests/cpu-opv/percpu-op.h
new file mode 100644
index 000000000000..918171e585d7
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/percpu-op.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * percpu-op.h
+ *
+ * (C) Copyright 2017-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef PERCPU_OP_H
+#define PERCPU_OP_H
+
+#include <stdint.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <stdlib.h>
+#include "rseq.h"
+#include "cpu-op.h"
+
+static inline uint32_t percpu_current_cpu(void)
+{
+	return rseq_current_cpu();
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv,
+			 int cpu)
+{
+	int ret;
+
+	ret = rseq_cmpeqv_storev(v, expect, newv, cpu);
+	if (rseq_unlikely(ret)) {
+		if (ret > 0)
+			return ret;
+		return cpu_op_cmpeqv_storev(v, expect, newv, cpu);
+	}
+	return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	int ret;
+
+	ret = rseq_cmpnev_storeoffp_load(v, expectnot, voffp, load, cpu);
+	if (rseq_unlikely(ret)) {
+		if (ret > 0)
+			return ret;
+		return cpu_op_cmpnev_storeoffp_load(v, expectnot, voffp,
+						    load, cpu);
+	}
+	return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	if (rseq_unlikely(rseq_addv(v, count, cpu)))
+		return cpu_op_addv(v, count, cpu);
+	return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_storev_storev(intptr_t *v, intptr_t expect,
+				intptr_t *v2, intptr_t newv2,
+				intptr_t newv, int cpu)
+{
+	int ret;
+
+	ret = rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2,
+					   newv, cpu);
+	if (rseq_unlikely(ret)) {
+		if (ret > 0)
+			return ret;
+		return cpu_op_cmpeqv_storev_storev(v, expect, v2, newv2,
+						   newv, cpu);
+	}
+	return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_storev_storev_release(intptr_t *v, intptr_t expect,
+					intptr_t *v2, intptr_t newv2,
+					intptr_t newv, int cpu)
+{
+	int ret;
+
+	ret = rseq_cmpeqv_trystorev_storev_release(v, expect, v2, newv2,
+						   newv, cpu);
+	if (rseq_unlikely(ret)) {
+		if (ret > 0)
+			return ret;
+		return cpu_op_cmpeqv_storev_storev_release(v, expect, v2, newv2,
+							   newv, cpu);
+	}
+	return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+				intptr_t *v2, intptr_t expect2,
+				intptr_t newv, int cpu)
+{
+	int ret;
+
+	ret = rseq_cmpeqv_cmpeqv_storev(v, expect, v2, expect2, newv, cpu);
+	if (rseq_unlikely(ret)) {
+		if (ret > 0)
+			return ret;
+		return cpu_op_cmpeqv_cmpeqv_storev(v, expect, v2, expect2,
+						   newv, cpu);
+	}
+	return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_memcpy_storev(intptr_t *v, intptr_t expect,
+				void *dst, void *src, size_t len,
+				intptr_t newv, int cpu)
+{
+	int ret;
+
+	ret = rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+					   newv, cpu);
+	if (rseq_unlikely(ret)) {
+		if (ret > 0)
+			return ret;
+		return cpu_op_cmpeqv_memcpy_storev(v, expect, dst, src, len,
+						   newv, cpu);
+	}
+	return 0;
+}
+
+static inline __attribute__((always_inline))
+int percpu_cmpeqv_memcpy_storev_release(intptr_t *v, intptr_t expect,
+					void *dst, void *src, size_t len,
+					intptr_t newv, int cpu)
+{
+	int ret;
+
+	ret = rseq_cmpeqv_trymemcpy_storev_release(v, expect, dst, src, len,
+						   newv, cpu);
+	if (rseq_unlikely(ret)) {
+		if (ret > 0)
+			return ret;
+		return cpu_op_cmpeqv_memcpy_storev_release(v, expect, dst, src,
+							   len, newv, cpu);
+	}
+	return 0;
+}
+
+#endif  /* PERCPU_OP_H_ */
-- 
2.11.0

[RFC PATCH for 4.21 14/16] cpu-opv/selftests: Provide basic percpu ops test

[Mathieu Desnoyers]

"basic_percpu_ops_test" implements a few simple per-cpu operations and
testing their correctness.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 .../selftests/cpu-opv/basic_percpu_ops_test.c      | 295 +++++++++++++++++++++
 1 file changed, 295 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c

diff --git a/tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c b/tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c
new file mode 100644
index 000000000000..2ce5202f25b2
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/basic_percpu_ops_test.c
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+
+#include "percpu-op.h"
+
+#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+
+struct percpu_lock_entry {
+	intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+	struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+	intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+	struct percpu_lock lock;
+	struct test_data_entry c[CPU_SETSIZE];
+	int reps;
+};
+
+struct percpu_list_node {
+	intptr_t data;
+	struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+	struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+	struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock. */
+void rseq_percpu_lock(struct percpu_lock *lock, int cpu)
+{
+	for (;;) {
+		int ret;
+
+		ret = percpu_cmpeqv_storev(&lock->c[cpu].v,
+					   0, 1, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	/*
+	 * Acquire semantic when taking lock after control dependency.
+	 * Matches rseq_smp_store_release().
+	 */
+	rseq_smp_acquire__after_ctrl_dep();
+}
+
+void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+	assert(lock->c[cpu].v == 1);
+	/*
+	 * Release lock, with release semantic. Matches
+	 * rseq_smp_acquire__after_ctrl_dep().
+	 */
+	rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+	struct spinlock_test_data *data = arg;
+	int i;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	for (i = 0; i < data->reps; i++) {
+		int cpu = percpu_current_cpu();
+
+		rseq_percpu_lock(&data->lock, cpu);
+		data->c[cpu].count++;
+		rseq_percpu_unlock(&data->lock, cpu);
+	}
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock.  Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+	const int num_threads = 200;
+	int i;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct spinlock_test_data data;
+
+	memset(&data, 0, sizeof(data));
+	data.reps = 5000;
+
+	for (i = 0; i < num_threads; i++)
+		pthread_create(&test_threads[i], NULL,
+			       test_percpu_spinlock_thread, &data);
+
+	for (i = 0; i < num_threads; i++)
+		pthread_join(test_threads[i], NULL);
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)data.reps * num_threads);
+}
+
+int percpu_list_push(struct percpu_list *list, struct percpu_list_node *node,
+		     int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr, newval, expect;
+		int ret;
+
+		/* Load list->c[cpu].head with single-copy atomicity. */
+		expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+		newval = (intptr_t)node;
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		node->next = (struct percpu_list_node *)expect;
+		ret = percpu_cmpeqv_storev(targetptr, expect, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return cpu;
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *percpu_list_pop(struct percpu_list *list,
+					 int cpu)
+{
+	struct percpu_list_node *head;
+	intptr_t *targetptr, expectnot, *load;
+	off_t offset;
+	int ret;
+
+	targetptr = (intptr_t *)&list->c[cpu].head;
+	expectnot = (intptr_t)NULL;
+	offset = offsetof(struct percpu_list_node, next);
+	load = (intptr_t *)&head;
+	ret = percpu_cmpnev_storeoffp_load(targetptr, expectnot,
+					   offset, load, cpu);
+	if (rseq_unlikely(ret < 0)) {
+		perror("cpu_opv");
+		abort();
+	}
+	if (ret > 0)
+		return NULL;
+	return head;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+	int i;
+	struct percpu_list *list = (struct percpu_list *)arg;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	for (i = 0; i < 100000; i++) {
+		struct percpu_list_node *node;
+
+		node = percpu_list_pop(list, percpu_current_cpu());
+		sched_yield();  /* encourage shuffling */
+		if (node)
+			percpu_list_push(list, node, percpu_current_cpu());
+	}
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads.  */
+void test_percpu_list(void)
+{
+	int i, j;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_list list;
+	pthread_t test_threads[200];
+	cpu_set_t allowed_cpus;
+
+	memset(&list, 0, sizeof(list));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		for (j = 1; j <= 100; j++) {
+			struct percpu_list_node *node;
+
+			expected_sum += j;
+
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			node->next = list.c[i].head;
+			list.c[i].head = node;
+		}
+	}
+
+	for (i = 0; i < 200; i++)
+		pthread_create(&test_threads[i], NULL,
+		       test_percpu_list_thread, &list);
+
+	for (i = 0; i < 200; i++)
+		pthread_join(test_threads[i], NULL);
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = percpu_list_pop(&list, i))) {
+			sum += node->data;
+			free(node);
+		}
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+int main(int argc, char **argv)
+{
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto error;
+	}
+	printf("spinlock\n");
+	test_percpu_spinlock();
+	printf("percpu_list\n");
+	test_percpu_list();
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		goto error;
+	}
+	return 0;
+
+error:
+	return -1;
+}
+
-- 
2.11.0

[RFC PATCH for 4.21 15/16] cpu-opv/selftests: Provide parametrized tests

[Mathieu Desnoyers]

"param_test" is a parametrizable percpu operations test using
both restartable sequences and cpu_opv. See the "--help" output for
usage.

"param_test_benchmark" is the same as "param_test", but it removes
testing book-keeping code to allow accurate benchmarks.

"param_test_compare_twice" is the same as "param_test", but it performs
each comparison within rseq critical section twice, thus validating
invariants. If any of the second comparisons fails, an error message
is printed and the test aborts.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/cpu-opv/param_test.c | 1187 ++++++++++++++++++++++++++
 1 file changed, 1187 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/param_test.c

diff --git a/tools/testing/selftests/cpu-opv/param_test.c b/tools/testing/selftests/cpu-opv/param_test.c
new file mode 100644
index 000000000000..c62e75f07385
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/param_test.c
@@ -0,0 +1,1187 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <poll.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
+#include <stddef.h>
+
+static inline pid_t gettid(void)
+{
+	return syscall(__NR_gettid);
+}
+
+#define NR_INJECT	9
+static int loop_cnt[NR_INJECT + 1];
+
+static int loop_cnt_1 asm("asm_loop_cnt_1") __attribute__((used));
+static int loop_cnt_2 asm("asm_loop_cnt_2") __attribute__((used));
+static int loop_cnt_3 asm("asm_loop_cnt_3") __attribute__((used));
+static int loop_cnt_4 asm("asm_loop_cnt_4") __attribute__((used));
+static int loop_cnt_5 asm("asm_loop_cnt_5") __attribute__((used));
+static int loop_cnt_6 asm("asm_loop_cnt_6") __attribute__((used));
+
+static int opt_modulo, verbose;
+
+static int opt_yield, opt_signal, opt_sleep,
+		opt_disable_rseq, opt_threads = 200,
+		opt_disable_mod = 0, opt_test = 's', opt_mb = 0;
+
+#ifndef RSEQ_SKIP_FASTPATH
+static long long opt_reps = 5000;
+#else
+static long long opt_reps = 100;
+#endif
+
+static __thread __attribute__((tls_model("initial-exec")))
+unsigned int signals_delivered;
+
+#ifndef BENCHMARK
+
+static __thread __attribute__((tls_model("initial-exec"), unused))
+unsigned int yield_mod_cnt, nr_abort;
+
+#define printf_verbose(fmt, ...)			\
+	do {						\
+		if (verbose)				\
+			printf(fmt, ## __VA_ARGS__);	\
+	} while (0)
+
+#ifdef __i386__
+
+#define INJECT_ASM_REG	"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \
+	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+	"jz 333f\n\t" \
+	"222:\n\t" \
+	"dec %%" INJECT_ASM_REG "\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__x86_64__)
+
+#define INJECT_ASM_REG_P	"rax"
+#define INJECT_ASM_REG		"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG_P \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \
+	"mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \
+	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+	"jz 333f\n\t" \
+	"222:\n\t" \
+	"dec %%" INJECT_ASM_REG "\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__ARMEL__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"r4"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"ldr " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"cmp " INJECT_ASM_REG ", #0\n\t" \
+	"beq 333f\n\t" \
+	"222:\n\t" \
+	"subs " INJECT_ASM_REG ", #1\n\t" \
+	"bne 222b\n\t" \
+	"333:\n\t"
+
+#elif __PPC__
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"r18"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lwz %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"cmpwi %%" INJECT_ASM_REG ", 0\n\t" \
+	"beq 333f\n\t" \
+	"222:\n\t" \
+	"subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \
+	"bne 222b\n\t" \
+	"333:\n\t"
+#else
+#error unsupported target
+#endif
+
+#define RSEQ_INJECT_FAILED \
+	nr_abort++;
+
+#define RSEQ_INJECT_C(n) \
+{ \
+	int loc_i, loc_nr_loops = loop_cnt[n]; \
+	\
+	for (loc_i = 0; loc_i < loc_nr_loops; loc_i++) { \
+		rseq_barrier(); \
+	} \
+	if (loc_nr_loops == -1 && opt_modulo) { \
+		if (yield_mod_cnt == opt_modulo - 1) { \
+			if (opt_sleep > 0) \
+				poll(NULL, 0, opt_sleep); \
+			if (opt_yield) \
+				sched_yield(); \
+			if (opt_signal) \
+				raise(SIGUSR1); \
+			yield_mod_cnt = 0; \
+		} else { \
+			yield_mod_cnt++; \
+		} \
+	} \
+}
+
+#else
+
+#define printf_verbose(fmt, ...)
+
+#endif /* BENCHMARK */
+
+#include "percpu-op.h"
+
+struct percpu_lock_entry {
+	intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+	struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+	intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+	struct percpu_lock lock;
+	struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct spinlock_thread_test_data {
+	struct spinlock_test_data *data;
+	long long reps;
+	int reg;
+};
+
+struct inc_test_data {
+	struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct inc_thread_test_data {
+	struct inc_test_data *data;
+	long long reps;
+	int reg;
+};
+
+struct percpu_list_node {
+	intptr_t data;
+	struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+	struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+	struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+#define BUFFER_ITEM_PER_CPU	100
+
+struct percpu_buffer_node {
+	intptr_t data;
+};
+
+struct percpu_buffer_entry {
+	intptr_t offset;
+	intptr_t buflen;
+	struct percpu_buffer_node **array;
+} __attribute__((aligned(128)));
+
+struct percpu_buffer {
+	struct percpu_buffer_entry c[CPU_SETSIZE];
+};
+
+#define MEMCPY_BUFFER_ITEM_PER_CPU	100
+
+struct percpu_memcpy_buffer_node {
+	intptr_t data1;
+	uint64_t data2;
+};
+
+struct percpu_memcpy_buffer_entry {
+	intptr_t offset;
+	intptr_t buflen;
+	struct percpu_memcpy_buffer_node *array;
+} __attribute__((aligned(128)));
+
+struct percpu_memcpy_buffer {
+	struct percpu_memcpy_buffer_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock. */
+static void rseq_percpu_lock(struct percpu_lock *lock, int cpu)
+{
+	for (;;) {
+		int ret;
+
+		ret = percpu_cmpeqv_storev(&lock->c[cpu].v,
+					   0, 1, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	/*
+	 * Acquire semantic when taking lock after control dependency.
+	 * Matches rseq_smp_store_release().
+	 */
+	rseq_smp_acquire__after_ctrl_dep();
+}
+
+static void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+	assert(lock->c[cpu].v == 1);
+	/*
+	 * Release lock, with release semantic. Matches
+	 * rseq_smp_acquire__after_ctrl_dep().
+	 */
+	rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+	struct spinlock_thread_test_data *thread_data = arg;
+	struct spinlock_test_data *data = thread_data->data;
+	long long i, reps;
+
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_register_current_thread())
+		abort();
+	reps = thread_data->reps;
+	for (i = 0; i < reps; i++) {
+		int cpu = rseq_cpu_start();
+
+		rseq_percpu_lock(&data->lock, cpu);
+		data->c[cpu].count++;
+		rseq_percpu_unlock(&data->lock, cpu);
+#ifndef BENCHMARK
+		if (i != 0 && !(i % (reps / 10)))
+			printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+#endif
+	}
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_unregister_current_thread())
+		abort();
+	return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock.  Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+	const int num_threads = opt_threads;
+	int i, ret;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct spinlock_test_data data;
+	struct spinlock_thread_test_data thread_data[num_threads];
+
+	memset(&data, 0, sizeof(data));
+	for (i = 0; i < num_threads; i++) {
+		thread_data[i].reps = opt_reps;
+		if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+			thread_data[i].reg = 1;
+		else
+			thread_data[i].reg = 0;
+		thread_data[i].data = &data;
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_spinlock_thread,
+				     &thread_data[i]);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void *test_percpu_inc_thread(void *arg)
+{
+	struct inc_thread_test_data *thread_data = arg;
+	struct inc_test_data *data = thread_data->data;
+	long long i, reps;
+
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_register_current_thread())
+		abort();
+	reps = thread_data->reps;
+	for (i = 0; i < reps; i++) {
+		int cpu, ret;
+
+		cpu = rseq_cpu_start();
+		ret = percpu_addv(&data->c[cpu].count, 1, cpu);
+		if (rseq_unlikely(ret)) {
+			perror("cpu_opv");
+			abort();
+		}
+#ifndef BENCHMARK
+		if (i != 0 && !(i % (reps / 10)))
+			printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+#endif
+	}
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_unregister_current_thread())
+		abort();
+	return NULL;
+}
+
+void test_percpu_inc(void)
+{
+	const int num_threads = opt_threads;
+	int i, ret;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct inc_test_data data;
+	struct inc_thread_test_data thread_data[num_threads];
+
+	memset(&data, 0, sizeof(data));
+	for (i = 0; i < num_threads; i++) {
+		thread_data[i].reps = opt_reps;
+		if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+			thread_data[i].reg = 1;
+		else
+			thread_data[i].reg = 0;
+		thread_data[i].data = &data;
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_inc_thread,
+				     &thread_data[i]);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void percpu_list_push(struct percpu_list *list,
+		      struct percpu_list_node *node,
+		      int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr, newval, expect;
+		int ret;
+
+		/* Load list->c[cpu].head with single-copy atomicity. */
+		expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+		newval = (intptr_t)node;
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		node->next = (struct percpu_list_node *)expect;
+		ret = percpu_cmpeqv_storev(targetptr, expect, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *percpu_list_pop(struct percpu_list *list,
+					 int cpu)
+{
+	struct percpu_list_node *head;
+	intptr_t *targetptr, expectnot, *load;
+	off_t offset;
+	int ret;
+
+	targetptr = (intptr_t *)&list->c[cpu].head;
+	expectnot = (intptr_t)NULL;
+	offset = offsetof(struct percpu_list_node, next);
+	load = (intptr_t *)&head;
+	ret = percpu_cmpnev_storeoffp_load(targetptr, expectnot,
+					   offset, load, cpu);
+	if (rseq_unlikely(ret < 0)) {
+		perror("cpu_opv");
+		abort();
+	}
+	if (ret > 0)
+		return NULL;
+	return head;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_list *list = (struct percpu_list *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_list_node *node;
+
+		node = percpu_list_pop(list, rseq_cpu_start());
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (node)
+			percpu_list_push(list, node, rseq_cpu_start());
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads.  */
+void test_percpu_list(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_list list;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&list, 0, sizeof(list));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		for (j = 1; j <= 100; j++) {
+			struct percpu_list_node *node;
+
+			expected_sum += j;
+
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			node->next = list.c[i].head;
+			list.c[i].head = node;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_list_thread, &list);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = percpu_list_pop(&list, i))) {
+			sum += node->data;
+			free(node);
+		}
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+bool percpu_buffer_push(struct percpu_buffer *buffer,
+			struct percpu_buffer_node *node,
+			int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr_spec, newval_spec;
+		intptr_t *targetptr_final, newval_final;
+		intptr_t offset;
+		int ret;
+
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == buffer->c[cpu].buflen)
+			return false;
+		newval_spec = (intptr_t)node;
+		targetptr_spec = (intptr_t *)&buffer->c[cpu].array[offset];
+		newval_final = offset + 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		if (opt_mb)
+			ret = percpu_cmpeqv_storev_storev_release(
+				targetptr_final, offset, targetptr_spec,
+				newval_spec, newval_final, cpu);
+		else
+			ret = percpu_cmpeqv_storev_storev(targetptr_final,
+				offset, targetptr_spec, newval_spec,
+				newval_final, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return true;
+}
+
+struct percpu_buffer_node *percpu_buffer_pop(struct percpu_buffer *buffer,
+					     int cpu)
+{
+	struct percpu_buffer_node *head;
+
+	for (;;) {
+		intptr_t *targetptr, newval;
+		intptr_t offset;
+		int ret;
+
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == 0)
+			return NULL;
+		head = RSEQ_READ_ONCE(buffer->c[cpu].array[offset - 1]);
+		newval = offset - 1;
+		targetptr = (intptr_t *)&buffer->c[cpu].offset;
+		ret = percpu_cmpeqv_cmpeqv_storev(targetptr, offset,
+			(intptr_t *)&buffer->c[cpu].array[offset - 1],
+			(intptr_t)head, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return head;
+}
+
+void *test_percpu_buffer_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_buffer *buffer = (struct percpu_buffer *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_buffer_node *node;
+
+		node = percpu_buffer_pop(buffer, rseq_cpu_start());
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (node) {
+			if (!percpu_buffer_push(buffer, node,
+						rseq_cpu_start())) {
+				/* Should increase buffer size. */
+				abort();
+			}
+		}
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads.  */
+void test_percpu_buffer(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_buffer buffer;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&buffer, 0, sizeof(buffer));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		/* Worse-case is every item in same CPU. */
+		buffer.c[i].array =
+			malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+			       BUFFER_ITEM_PER_CPU);
+		assert(buffer.c[i].array);
+		buffer.c[i].buflen = CPU_SETSIZE * BUFFER_ITEM_PER_CPU;
+		for (j = 1; j <= BUFFER_ITEM_PER_CPU; j++) {
+			struct percpu_buffer_node *node;
+
+			expected_sum += j;
+
+			/*
+			 * We could theoretically put the word-sized
+			 * "data" directly in the buffer. However, we
+			 * want to model objects that would not fit
+			 * within a single word, so allocate an object
+			 * for each node.
+			 */
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			buffer.c[i].array[j - 1] = node;
+			buffer.c[i].offset++;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_buffer_thread, &buffer);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_buffer_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = percpu_buffer_pop(&buffer, i))) {
+			sum += node->data;
+			free(node);
+		}
+		free(buffer.c[i].array);
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+bool percpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer,
+			       struct percpu_memcpy_buffer_node item, int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr_final, newval_final, offset;
+		char *destptr, *srcptr;
+		size_t copylen;
+		int ret;
+
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == buffer->c[cpu].buflen)
+			return false;
+		destptr = (char *)&buffer->c[cpu].array[offset];
+		srcptr = (char *)&item;
+		/* copylen must be <= 4kB. */
+		copylen = sizeof(item);
+		newval_final = offset + 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		if (opt_mb)
+			ret = percpu_cmpeqv_memcpy_storev_release(
+				targetptr_final, offset,
+				destptr, srcptr, copylen,
+				newval_final, cpu);
+		else
+			ret = percpu_cmpeqv_memcpy_storev(targetptr_final,
+				offset, destptr, srcptr, copylen,
+				newval_final, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return true;
+}
+
+bool percpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer,
+		struct percpu_memcpy_buffer_node *item, int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr_final, newval_final, offset;
+		char *destptr, *srcptr;
+		size_t copylen;
+		int ret;
+
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == 0)
+			return false;
+		destptr = (char *)item;
+		srcptr = (char *)&buffer->c[cpu].array[offset - 1];
+		/* copylen must be <= 4kB. */
+		copylen = sizeof(*item);
+		newval_final = offset - 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		ret = percpu_cmpeqv_memcpy_storev(targetptr_final,
+			offset, destptr, srcptr, copylen,
+			newval_final, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return true;
+}
+
+void *test_percpu_memcpy_buffer_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_memcpy_buffer_node item;
+		bool result;
+
+		result = percpu_memcpy_buffer_pop(buffer, &item,
+						  rseq_cpu_start());
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (result) {
+			if (!percpu_memcpy_buffer_push(buffer, item,
+						       rseq_cpu_start())) {
+				/* Should increase buffer size. */
+				abort();
+			}
+		}
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads.  */
+void test_percpu_memcpy_buffer(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_memcpy_buffer buffer;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&buffer, 0, sizeof(buffer));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		/* Worse-case is every item in same CPU. */
+		buffer.c[i].array =
+			malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+			       MEMCPY_BUFFER_ITEM_PER_CPU);
+		assert(buffer.c[i].array);
+		buffer.c[i].buflen = CPU_SETSIZE * MEMCPY_BUFFER_ITEM_PER_CPU;
+		for (j = 1; j <= MEMCPY_BUFFER_ITEM_PER_CPU; j++) {
+			expected_sum += 2 * j + 1;
+
+			/*
+			 * We could theoretically put the word-sized
+			 * "data" directly in the buffer. However, we
+			 * want to model objects that would not fit
+			 * within a single word, so allocate an object
+			 * for each node.
+			 */
+			buffer.c[i].array[j - 1].data1 = j;
+			buffer.c[i].array[j - 1].data2 = j + 1;
+			buffer.c[i].offset++;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_memcpy_buffer_thread,
+				     &buffer);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_memcpy_buffer_node item;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while (percpu_memcpy_buffer_pop(&buffer, &item, i)) {
+			sum += item.data1;
+			sum += item.data2;
+		}
+		free(buffer.c[i].array);
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+static void test_signal_interrupt_handler(int signo)
+{
+	signals_delivered++;
+}
+
+static int set_signal_handler(void)
+{
+	int ret = 0;
+	struct sigaction sa;
+	sigset_t sigset;
+
+	ret = sigemptyset(&sigset);
+	if (ret < 0) {
+		perror("sigemptyset");
+		return ret;
+	}
+
+	sa.sa_handler = test_signal_interrupt_handler;
+	sa.sa_mask = sigset;
+	sa.sa_flags = 0;
+	ret = sigaction(SIGUSR1, &sa, NULL);
+	if (ret < 0) {
+		perror("sigaction");
+		return ret;
+	}
+
+	printf_verbose("Signal handler set for SIGUSR1\n");
+
+	return ret;
+}
+
+static void show_usage(int argc, char **argv)
+{
+	printf("Usage : %s <OPTIONS>\n",
+		argv[0]);
+	printf("OPTIONS:\n");
+	printf("	[-1 loops] Number of loops for delay injection 1\n");
+	printf("	[-2 loops] Number of loops for delay injection 2\n");
+	printf("	[-3 loops] Number of loops for delay injection 3\n");
+	printf("	[-4 loops] Number of loops for delay injection 4\n");
+	printf("	[-5 loops] Number of loops for delay injection 5\n");
+	printf("	[-6 loops] Number of loops for delay injection 6\n");
+	printf("	[-7 loops] Number of loops for delay injection 7 (-1 to enable -m)\n");
+	printf("	[-8 loops] Number of loops for delay injection 8 (-1 to enable -m)\n");
+	printf("	[-9 loops] Number of loops for delay injection 9 (-1 to enable -m)\n");
+	printf("	[-m N] Yield/sleep/kill every modulo N (default 0: disabled) (>= 0)\n");
+	printf("	[-y] Yield\n");
+	printf("	[-k] Kill thread with signal\n");
+	printf("	[-s S] S: =0: disabled (default), >0: sleep time (ms)\n");
+	printf("	[-t N] Number of threads (default 200)\n");
+	printf("	[-r N] Number of repetitions per thread (default 5000)\n");
+	printf("	[-d] Disable rseq system call (no initialization)\n");
+	printf("	[-D M] Disable rseq for each M threads\n");
+	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement\n");
+	printf("	[-M] Push into buffer and memcpy buffer with memory barriers.\n");
+	printf("	[-v] Verbose output.\n");
+	printf("	[-h] Show this help.\n");
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		if (argv[i][0] != '-')
+			continue;
+		switch (argv[i][1]) {
+		case '1':
+		case '2':
+		case '3':
+		case '4':
+		case '5':
+		case '6':
+		case '7':
+		case '8':
+		case '9':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			loop_cnt[argv[i][1] - '0'] = atol(argv[i + 1]);
+			i++;
+			break;
+		case 'm':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_modulo = atol(argv[i + 1]);
+			if (opt_modulo < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 's':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_sleep = atol(argv[i + 1]);
+			if (opt_sleep < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'y':
+			opt_yield = 1;
+			break;
+		case 'k':
+			opt_signal = 1;
+			break;
+		case 'd':
+			opt_disable_rseq = 1;
+			break;
+		case 'D':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_disable_mod = atol(argv[i + 1]);
+			if (opt_disable_mod < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 't':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_threads = atol(argv[i + 1]);
+			if (opt_threads < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'r':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_reps = atoll(argv[i + 1]);
+			if (opt_reps < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'h':
+			show_usage(argc, argv);
+			goto end;
+		case 'T':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_test = *argv[i + 1];
+			switch (opt_test) {
+			case 's':
+			case 'l':
+			case 'i':
+			case 'b':
+			case 'm':
+				break;
+			default:
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'v':
+			verbose = 1;
+			break;
+		case 'M':
+			opt_mb = 1;
+			break;
+		default:
+			show_usage(argc, argv);
+			goto error;
+		}
+	}
+
+	loop_cnt_1 = loop_cnt[1];
+	loop_cnt_2 = loop_cnt[2];
+	loop_cnt_3 = loop_cnt[3];
+	loop_cnt_4 = loop_cnt[4];
+	loop_cnt_5 = loop_cnt[5];
+	loop_cnt_6 = loop_cnt[6];
+
+	if (set_signal_handler())
+		goto error;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		goto error;
+	switch (opt_test) {
+	case 's':
+		printf_verbose("spinlock\n");
+		test_percpu_spinlock();
+		break;
+	case 'l':
+		printf_verbose("linked list\n");
+		test_percpu_list();
+		break;
+	case 'b':
+		printf_verbose("buffer\n");
+		test_percpu_buffer();
+		break;
+	case 'm':
+		printf_verbose("memcpy buffer\n");
+		test_percpu_memcpy_buffer();
+		break;
+	case 'i':
+		printf_verbose("counter increment\n");
+		test_percpu_inc();
+		break;
+	}
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+end:
+	return 0;
+
+error:
+	return -1;
+}
-- 
2.11.0

[RFC PATCH for 4.21 16/16] cpu-opv/selftests: Provide Makefile, scripts, gitignore

[Mathieu Desnoyers]

A run_param_test.sh script runs many variants of the parametrizable
tests.

Wire up the cpu-opv Makefile, add directory entry into MAINTAINERS file.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS                                       |   1 +
 tools/testing/selftests/Makefile                  |   1 +
 tools/testing/selftests/cpu-opv/.gitignore        |   6 +
 tools/testing/selftests/cpu-opv/Makefile          |  39 +++++++
 tools/testing/selftests/cpu-opv/run_param_test.sh | 134 ++++++++++++++++++++++
 5 files changed, 181 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/.gitignore
 create mode 100644 tools/testing/selftests/cpu-opv/Makefile
 create mode 100755 tools/testing/selftests/cpu-opv/run_param_test.sh

diff --git a/MAINTAINERS b/MAINTAINERS
index de59c7c12c8f..ad9addbc5510 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3878,6 +3878,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	kernel/cpu_opv.c
 F:	include/uapi/linux/cpu_opv.h
+F:	tools/testing/selftests/cpu-opv/
 
 CRAMFS FILESYSTEM
 M:	Nicolas Pitre <nico@linaro.org>
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f1fe492c8e17..42bcc6e5fc5d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -6,6 +6,7 @@ TARGETS += capabilities
 TARGETS += cgroup
 TARGETS += cpufreq
 TARGETS += cpu-hotplug
+TARGETS += cpu-opv
 TARGETS += efivarfs
 TARGETS += exec
 TARGETS += filesystems
diff --git a/tools/testing/selftests/cpu-opv/.gitignore b/tools/testing/selftests/cpu-opv/.gitignore
new file mode 100644
index 000000000000..8c7bb1f8be79
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/.gitignore
@@ -0,0 +1,6 @@
+basic_cpu_opv_test
+basic_percpu_ops_test
+param_test
+param_test_benchmark
+param_test_compare_twice
+param_test_skip_fastpath
diff --git a/tools/testing/selftests/cpu-opv/Makefile b/tools/testing/selftests/cpu-opv/Makefile
new file mode 100644
index 000000000000..46f49bf30bae
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/Makefile
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+CFLAGS += -O2 -Wall -g -I./ -I../rseq/ -I../../../../usr/include/ -L./ -Wl,-rpath=./
+LDLIBS += -lpthread
+
+# Own dependencies because we only want to build against 1st prerequisite, but
+# still track changes to header files and depend on shared object.
+OVERRIDE_TARGETS = 1
+
+TEST_GEN_PROGS = basic_cpu_opv_test basic_percpu_ops_test \
+		param_test param_test_skip_fastpath \
+		param_test_benchmark param_test_compare_twice
+
+TEST_GEN_PROGS_EXTENDED = librseq.so libcpu-op.so
+
+TEST_PROGS = run_param_test.sh
+
+include ../lib.mk
+
+$(OUTPUT)/libcpu-op.so: cpu-op.c cpu-op.h
+	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/librseq.so: ../rseq/rseq.c ../rseq/rseq.h ../rseq/rseq-*.h
+	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_skip_fastpath: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) -DRSEQ_SKIP_FASTPATH $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
diff --git a/tools/testing/selftests/cpu-opv/run_param_test.sh b/tools/testing/selftests/cpu-opv/run_param_test.sh
new file mode 100755
index 000000000000..066d2479893c
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/run_param_test.sh
@@ -0,0 +1,134 @@
+#!/bin/bash
+
+NR_CPUS=`grep '^processor' /proc/cpuinfo | wc -l`
+
+EXTRA_ARGS=${@}
+
+OLDIFS="$IFS"
+IFS=$'\n'
+TEST_LIST=(
+	"-T s"
+	"-T l"
+	"-T b"
+	"-T b -M"
+	"-T m"
+	"-T m -M"
+	"-T i"
+)
+
+TEST_NAME=(
+	"spinlock"
+	"list"
+	"buffer"
+	"buffer with barrier"
+	"memcpy"
+	"memcpy with barrier"
+	"increment"
+)
+IFS="$OLDIFS"
+
+REPS=1000
+SLOW_REPS=100
+NR_THREADS=$((6*${NR_CPUS}))
+
+function do_tests()
+{
+	local i=0
+	while [ "$i" -lt "${#TEST_LIST[@]}" ]; do
+		echo "Running test ${TEST_NAME[$i]}"
+		./param_test ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		echo "Running skip fast-path test ${TEST_NAME[$i]}"
+		./param_test_skip_fastpath ${TEST_LIST[$i]} -r ${SLOW_REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		echo "Running compare-twice test ${TEST_NAME[$i]}"
+		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		let "i++"
+	done
+}
+
+echo "Default parameters"
+do_tests
+
+echo "Loop injection: 10000 loops"
+
+OLDIFS="$IFS"
+IFS=$'\n'
+INJECT_LIST=(
+	"1"
+	"2"
+	"3"
+	"4"
+	"5"
+	"6"
+	"7"
+	"8"
+	"9"
+)
+IFS="$OLDIFS"
+
+NR_LOOPS=10000
+
+i=0
+while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+	echo "Injecting at <${INJECT_LIST[$i]}>"
+	do_tests -${INJECT_LIST[i]} ${NR_LOOPS}
+	let "i++"
+done
+NR_LOOPS=
+
+function inject_blocking()
+{
+	OLDIFS="$IFS"
+	IFS=$'\n'
+	INJECT_LIST=(
+		"7"
+		"8"
+		"9"
+	)
+	IFS="$OLDIFS"
+
+	NR_LOOPS=-1
+
+	i=0
+	while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+		echo "Injecting at <${INJECT_LIST[$i]}>"
+		do_tests -${INJECT_LIST[i]} -1 ${@}
+		let "i++"
+	done
+	NR_LOOPS=
+}
+
+echo "Yield injection (25%)"
+inject_blocking -m 4 -y
+
+echo "Yield injection (50%)"
+inject_blocking -m 2 -y
+
+echo "Yield injection (100%)"
+inject_blocking -m 1 -y
+
+echo "Kill injection (25%)"
+inject_blocking -m 4 -k
+
+echo "Kill injection (50%)"
+inject_blocking -m 2 -k
+
+echo "Kill injection (100%)"
+inject_blocking -m 1 -k
+
+echo "Sleep injection (1ms, 25%)"
+inject_blocking -m 4 -s 1
+
+echo "Sleep injection (1ms, 50%)"
+inject_blocking -m 2 -s 1
+
+echo "Sleep injection (1ms, 100%)"
+inject_blocking -m 1 -s 1
+
+echo "Disable rseq for 25% threads"
+do_tests -D 4
+
+echo "Disable rseq for 50% threads"
+do_tests -D 2
+
+echo "Disable rseq"
+do_tests -d
-- 
2.11.0

Re: [RFC PATCH for 4.21 03/16] mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram()

[Thomas Gleixner]

Mathieu,

On Thu, 1 Nov 2018, Mathieu Desnoyers wrote:

> It is encouraged to warn and return rather than use BUG_ON() when
> the condition can be recovered from in ways that are more graceful than
> halting the whole system.

You're failing to desribe how that graceful recovery works.

Thanks,

	tglx

Re: [RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call (v2)

[Linus Torvalds]

On Thu, Nov 1, 2018 at 2:59 AM Mathieu Desnoyers
<mathieu.desnoyers@efficios.com> wrote:
>
> Here is an updated patchset submitted as RFC for 4.21 (next merge
> window).

So I'm not willing to take the cpu_opv system call until I see the the
regular rseq code getting more real-life use.

Maybe people are using it. Maybe they aren't. I want to hold off and
wait until we _know_ it's getting used, and not just in test
libraries.

                   Linus

Re: [RFC PATCH for 4.21 03/16] mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram()

[Steven Rostedt]

On Thu, 1 Nov 2018 13:21:12 +0100 (CET)
Thomas Gleixner <tglx@linutronix.de> wrote:

> Mathieu,
> 
> On Thu, 1 Nov 2018, Mathieu Desnoyers wrote:
> 
> > It is encouraged to warn and return rather than use BUG_ON() when
> > the condition can be recovered from in ways that are more graceful than
> > halting the whole system.  
> 
> You're failing to desribe how that graceful recovery works.
> 

I think the graceful recovery is to simply return:

	if (WARN_ON(cond))
		return;

is better than just

	BUG_ON(cond);

As that's what Linus made pretty clear at the Maintainer's Summit.

-- Steve

Re: [RFC PATCH for 4.21 03/16] mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram()

[Mathieu Desnoyers]

----- On Nov 1, 2018, at 7:46 PM, rostedt rostedt@goodmis.org wrote:

> On Thu, 1 Nov 2018 13:21:12 +0100 (CET)
> Thomas Gleixner <tglx@linutronix.de> wrote:
> 
>> Mathieu,
>> 
>> On Thu, 1 Nov 2018, Mathieu Desnoyers wrote:
>> 
>> > It is encouraged to warn and return rather than use BUG_ON() when
>> > the condition can be recovered from in ways that are more graceful than
>> > halting the whole system.
>> 
>> You're failing to desribe how that graceful recovery works.
>> 
> 
> I think the graceful recovery is to simply return:
> 
>	if (WARN_ON(cond))
>		return;
> 
> is better than just
> 
>	BUG_ON(cond);
> 
> As that's what Linus made pretty clear at the Maintainer's Summit.

That's it. For an unmap function, this basically boils down to
print a warning and leak the memory on internal unmap error.

I will update the commit message describing this behavior.

Thanks,

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com

Re: [RFC PATCH for 4.21 03/16] mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram()

[Linus Torvalds]

On Thu, Nov 1, 2018 at 12:57 PM Mathieu Desnoyers
<mathieu.desnoyers@efficios.com> wrote:
>
> > I think the graceful recovery is to simply return:
> >
> >       if (WARN_ON(cond))
> >               return;
> >
> > is better than just
> >
> >       BUG_ON(cond);
> >
> > As that's what Linus made pretty clear at the Maintainer's Summit.
>
> That's it. For an unmap function, this basically boils down to
> print a warning and leak the memory on internal unmap error.
>
> I will update the commit message describing this behavior.

It might be even better to use WARN_ON_ONCE().

If it's a "this shouldn't happen" situation, the advantage of
WARN_ON_ONCE() is that it will still show the backtrace of the "how
the heck did it happen after all" situation, but if it turns ouit to
be user-triggerable (or simply triggerable by some odd hw situation),
it won't spam your logs forever.

Obviously, things like rate limiting etc can also be good ideas, but
that's just overkill for "this really should never happen" cases.

(Side note: WARN_ON_ONCE() will _warn_ just once, but will always
return the condition that it warns for, so the return value is _not_
"I have warned", but "I have seen the condition that I should warn
about". Just in case people are worried about it).

                  Linus

Re: [RFC PATCH for 4.21 03/16] mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram()

[Mathieu Desnoyers]

----- On Nov 1, 2018, at 11:00 PM, Linus Torvalds torvalds@linux-foundation.org wrote:

> On Thu, Nov 1, 2018 at 12:57 PM Mathieu Desnoyers
> <mathieu.desnoyers@efficios.com> wrote:
>>
>> > I think the graceful recovery is to simply return:
>> >
>> >       if (WARN_ON(cond))
>> >               return;
>> >
>> > is better than just
>> >
>> >       BUG_ON(cond);
>> >
>> > As that's what Linus made pretty clear at the Maintainer's Summit.
>>
>> That's it. For an unmap function, this basically boils down to
>> print a warning and leak the memory on internal unmap error.
>>
>> I will update the commit message describing this behavior.
> 
> It might be even better to use WARN_ON_ONCE().
> 
> If it's a "this shouldn't happen" situation, the advantage of
> WARN_ON_ONCE() is that it will still show the backtrace of the "how
> the heck did it happen after all" situation, but if it turns ouit to
> be user-triggerable (or simply triggerable by some odd hw situation),
> it won't spam your logs forever.
> 
> Obviously, things like rate limiting etc can also be good ideas, but
> that's just overkill for "this really should never happen" cases.
> 
> (Side note: WARN_ON_ONCE() will _warn_ just once, but will always
> return the condition that it warns for, so the return value is _not_
> "I have warned", but "I have seen the condition that I should warn
> about". Just in case people are worried about it).

Allright, I'll update this patch (and the following one implementing
vm_{map,unmap}_user_ram) to use WARN_ON_ONCE().

Thanks!

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com

[RFC PATCH for 4.21 16/16] cpu-opv/selftests: Provide Makefile, scripts, gitignore

[Mathieu Desnoyers]

A run_param_test.sh script runs many variants of the parametrizable
tests.

Wire up the cpu-opv Makefile, add directory entry into MAINTAINERS file.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS                                       |   1 +
 tools/testing/selftests/Makefile                  |   1 +
 tools/testing/selftests/cpu-opv/.gitignore        |   6 +
 tools/testing/selftests/cpu-opv/Makefile          |  39 +++++++
 tools/testing/selftests/cpu-opv/run_param_test.sh | 134 ++++++++++++++++++++++
 5 files changed, 181 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/.gitignore
 create mode 100644 tools/testing/selftests/cpu-opv/Makefile
 create mode 100755 tools/testing/selftests/cpu-opv/run_param_test.sh

diff --git a/MAINTAINERS b/MAINTAINERS
index 3b50578fc5d9..206fe4597697 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3864,6 +3864,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	kernel/cpu_opv.c
 F:	include/uapi/linux/cpu_opv.h
+F:	tools/testing/selftests/cpu-opv/
 
 CRAMFS FILESYSTEM
 M:	Nicolas Pitre <nico@linaro.org>
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f1fe492c8e17..42bcc6e5fc5d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -6,6 +6,7 @@ TARGETS += capabilities
 TARGETS += cgroup
 TARGETS += cpufreq
 TARGETS += cpu-hotplug
+TARGETS += cpu-opv
 TARGETS += efivarfs
 TARGETS += exec
 TARGETS += filesystems
diff --git a/tools/testing/selftests/cpu-opv/.gitignore b/tools/testing/selftests/cpu-opv/.gitignore
new file mode 100644
index 000000000000..8c7bb1f8be79
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/.gitignore
@@ -0,0 +1,6 @@
+basic_cpu_opv_test
+basic_percpu_ops_test
+param_test
+param_test_benchmark
+param_test_compare_twice
+param_test_skip_fastpath
diff --git a/tools/testing/selftests/cpu-opv/Makefile b/tools/testing/selftests/cpu-opv/Makefile
new file mode 100644
index 000000000000..46f49bf30bae
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/Makefile
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+CFLAGS += -O2 -Wall -g -I./ -I../rseq/ -I../../../../usr/include/ -L./ -Wl,-rpath=./
+LDLIBS += -lpthread
+
+# Own dependencies because we only want to build against 1st prerequisite, but
+# still track changes to header files and depend on shared object.
+OVERRIDE_TARGETS = 1
+
+TEST_GEN_PROGS = basic_cpu_opv_test basic_percpu_ops_test \
+		param_test param_test_skip_fastpath \
+		param_test_benchmark param_test_compare_twice
+
+TEST_GEN_PROGS_EXTENDED = librseq.so libcpu-op.so
+
+TEST_PROGS = run_param_test.sh
+
+include ../lib.mk
+
+$(OUTPUT)/libcpu-op.so: cpu-op.c cpu-op.h
+	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/librseq.so: ../rseq/rseq.c ../rseq/rseq.h ../rseq/rseq-*.h
+	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
+
+$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_skip_fastpath: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) -DRSEQ_SKIP_FASTPATH $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
+$(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \
+					../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h
+	$(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -lcpu-op -o $@
+
diff --git a/tools/testing/selftests/cpu-opv/run_param_test.sh b/tools/testing/selftests/cpu-opv/run_param_test.sh
new file mode 100755
index 000000000000..066d2479893c
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/run_param_test.sh
@@ -0,0 +1,134 @@
+#!/bin/bash
+
+NR_CPUS=`grep '^processor' /proc/cpuinfo | wc -l`
+
+EXTRA_ARGS=${@}
+
+OLDIFS="$IFS"
+IFS=$'\n'
+TEST_LIST=(
+	"-T s"
+	"-T l"
+	"-T b"
+	"-T b -M"
+	"-T m"
+	"-T m -M"
+	"-T i"
+)
+
+TEST_NAME=(
+	"spinlock"
+	"list"
+	"buffer"
+	"buffer with barrier"
+	"memcpy"
+	"memcpy with barrier"
+	"increment"
+)
+IFS="$OLDIFS"
+
+REPS=1000
+SLOW_REPS=100
+NR_THREADS=$((6*${NR_CPUS}))
+
+function do_tests()
+{
+	local i=0
+	while [ "$i" -lt "${#TEST_LIST[@]}" ]; do
+		echo "Running test ${TEST_NAME[$i]}"
+		./param_test ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		echo "Running skip fast-path test ${TEST_NAME[$i]}"
+		./param_test_skip_fastpath ${TEST_LIST[$i]} -r ${SLOW_REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		echo "Running compare-twice test ${TEST_NAME[$i]}"
+		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
+		let "i++"
+	done
+}
+
+echo "Default parameters"
+do_tests
+
+echo "Loop injection: 10000 loops"
+
+OLDIFS="$IFS"
+IFS=$'\n'
+INJECT_LIST=(
+	"1"
+	"2"
+	"3"
+	"4"
+	"5"
+	"6"
+	"7"
+	"8"
+	"9"
+)
+IFS="$OLDIFS"
+
+NR_LOOPS=10000
+
+i=0
+while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+	echo "Injecting at <${INJECT_LIST[$i]}>"
+	do_tests -${INJECT_LIST[i]} ${NR_LOOPS}
+	let "i++"
+done
+NR_LOOPS=
+
+function inject_blocking()
+{
+	OLDIFS="$IFS"
+	IFS=$'\n'
+	INJECT_LIST=(
+		"7"
+		"8"
+		"9"
+	)
+	IFS="$OLDIFS"
+
+	NR_LOOPS=-1
+
+	i=0
+	while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do
+		echo "Injecting at <${INJECT_LIST[$i]}>"
+		do_tests -${INJECT_LIST[i]} -1 ${@}
+		let "i++"
+	done
+	NR_LOOPS=
+}
+
+echo "Yield injection (25%)"
+inject_blocking -m 4 -y
+
+echo "Yield injection (50%)"
+inject_blocking -m 2 -y
+
+echo "Yield injection (100%)"
+inject_blocking -m 1 -y
+
+echo "Kill injection (25%)"
+inject_blocking -m 4 -k
+
+echo "Kill injection (50%)"
+inject_blocking -m 2 -k
+
+echo "Kill injection (100%)"
+inject_blocking -m 1 -k
+
+echo "Sleep injection (1ms, 25%)"
+inject_blocking -m 4 -s 1
+
+echo "Sleep injection (1ms, 50%)"
+inject_blocking -m 2 -s 1
+
+echo "Sleep injection (1ms, 100%)"
+inject_blocking -m 1 -s 1
+
+echo "Disable rseq for 25% threads"
+do_tests -D 4
+
+echo "Disable rseq for 50% threads"
+do_tests -D 2
+
+echo "Disable rseq"
+do_tests -d
-- 
2.11.0