Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
- a bit more MM
- procfs updates
- dynamic-debug fixes
- lib/ updates
- checkpatch
- epoll
- nilfs2
- signals
- rapidio
- PID management cleanup and optimization
- kcov updates
- sysvipc updates
- quite a few misc things all over the place
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (94 commits)
EXPERT Kconfig menu: fix broken EXPERT menu
include/asm-generic/topology.h: remove unused parent_node() macro
arch/tile/include/asm/topology.h: remove unused parent_node() macro
arch/sparc/include/asm/topology_64.h: remove unused parent_node() macro
arch/sh/include/asm/topology.h: remove unused parent_node() macro
arch/ia64/include/asm/topology.h: remove unused parent_node() macro
drivers/pcmcia/sa1111_badge4.c: avoid unused function warning
mm: add infrastructure for get_user_pages_fast() benchmarking
sysvipc: make get_maxid O(1) again
sysvipc: properly name ipc_addid() limit parameter
sysvipc: duplicate lock comments wrt ipc_addid()
sysvipc: unteach ids->next_id for !CHECKPOINT_RESTORE
initramfs: use time64_t timestamps
drivers/watchdog: make use of devm_register_reboot_notifier()
kernel/reboot.c: add devm_register_reboot_notifier()
kcov: update documentation
Makefile: support flag -fsanitizer-coverage=trace-cmp
kcov: support comparison operands collection
kcov: remove pointless current != NULL check
kernel/panic.c: add TAINT_AUX
...
diff --git a/Documentation/admin-guide/dynamic-debug-howto.rst b/Documentation/admin-guide/dynamic-debug-howto.rst
index 12278a9..fdf7242 100644
--- a/Documentation/admin-guide/dynamic-debug-howto.rst
+++ b/Documentation/admin-guide/dynamic-debug-howto.rst
@@ -18,7 +18,7 @@
For ``print_hex_dump_debug()``/``print_hex_dump_bytes()``, format string is
its ``prefix_str`` argument, if it is constant string; or ``hexdump``
-in case ``prefix_str`` is build dynamically.
+in case ``prefix_str`` is built dynamically.
Dynamic debug has even more useful features:
@@ -197,8 +197,8 @@
line number matches the callsite line number exactly. A
range of line numbers matches any callsite between the first
and last line number inclusive. An empty first number means
- the first line in the file, an empty line number means the
- last number in the file. Examples::
+ the first line in the file, an empty last line number means the
+ last line number in the file. Examples::
line 1603 // exactly line 1603
line 1600-1605 // the six lines from line 1600 to line 1605
diff --git a/Documentation/clearing-warn-once.txt b/Documentation/clearing-warn-once.txt
new file mode 100644
index 0000000..5b1f5d5
--- /dev/null
+++ b/Documentation/clearing-warn-once.txt
@@ -0,0 +1,7 @@
+
+WARN_ONCE / WARN_ON_ONCE only print a warning once.
+
+echo 1 > /sys/kernel/debug/clear_warn_once
+
+clears the state and allows the warnings to print once again.
+This can be useful after test suite runs to reproduce problems.
diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst
index 44886c9..c2f6452 100644
--- a/Documentation/dev-tools/kcov.rst
+++ b/Documentation/dev-tools/kcov.rst
@@ -12,19 +12,30 @@
and instrumentation of some inherently non-deterministic parts of kernel is
disabled (e.g. scheduler, locking).
-Usage
------
+kcov is also able to collect comparison operands from the instrumented code
+(this feature currently requires that the kernel is compiled with clang).
+
+Prerequisites
+-------------
Configure the kernel with::
CONFIG_KCOV=y
CONFIG_KCOV requires gcc built on revision 231296 or later.
+
+If the comparison operands need to be collected, set::
+
+ CONFIG_KCOV_ENABLE_COMPARISONS=y
+
Profiling data will only become accessible once debugfs has been mounted::
mount -t debugfs none /sys/kernel/debug
-The following program demonstrates kcov usage from within a test program:
+Coverage collection
+-------------------
+The following program demonstrates coverage collection from within a test
+program using kcov:
.. code-block:: c
@@ -44,6 +55,9 @@
#define KCOV_DISABLE _IO('c', 101)
#define COVER_SIZE (64<<10)
+ #define KCOV_TRACE_PC 0
+ #define KCOV_TRACE_CMP 1
+
int main(int argc, char **argv)
{
int fd;
@@ -64,7 +78,7 @@
if ((void*)cover == MAP_FAILED)
perror("mmap"), exit(1);
/* Enable coverage collection on the current thread. */
- if (ioctl(fd, KCOV_ENABLE, 0))
+ if (ioctl(fd, KCOV_ENABLE, KCOV_TRACE_PC))
perror("ioctl"), exit(1);
/* Reset coverage from the tail of the ioctl() call. */
__atomic_store_n(&cover[0], 0, __ATOMIC_RELAXED);
@@ -111,3 +125,80 @@
That is, a parent process opens /sys/kernel/debug/kcov, enables trace mode,
mmaps coverage buffer and then forks child processes in a loop. Child processes
only need to enable coverage (disable happens automatically on thread end).
+
+Comparison operands collection
+------------------------------
+Comparison operands collection is similar to coverage collection:
+
+.. code-block:: c
+
+ /* Same includes and defines as above. */
+
+ /* Number of 64-bit words per record. */
+ #define KCOV_WORDS_PER_CMP 4
+
+ /*
+ * The format for the types of collected comparisons.
+ *
+ * Bit 0 shows whether one of the arguments is a compile-time constant.
+ * Bits 1 & 2 contain log2 of the argument size, up to 8 bytes.
+ */
+
+ #define KCOV_CMP_CONST (1 << 0)
+ #define KCOV_CMP_SIZE(n) ((n) << 1)
+ #define KCOV_CMP_MASK KCOV_CMP_SIZE(3)
+
+ int main(int argc, char **argv)
+ {
+ int fd;
+ uint64_t *cover, type, arg1, arg2, is_const, size;
+ unsigned long n, i;
+
+ fd = open("/sys/kernel/debug/kcov", O_RDWR);
+ if (fd == -1)
+ perror("open"), exit(1);
+ if (ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE))
+ perror("ioctl"), exit(1);
+ /*
+ * Note that the buffer pointer is of type uint64_t*, because all
+ * the comparison operands are promoted to uint64_t.
+ */
+ cover = (uint64_t *)mmap(NULL, COVER_SIZE * sizeof(unsigned long),
+ PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ if ((void*)cover == MAP_FAILED)
+ perror("mmap"), exit(1);
+ /* Note KCOV_TRACE_CMP instead of KCOV_TRACE_PC. */
+ if (ioctl(fd, KCOV_ENABLE, KCOV_TRACE_CMP))
+ perror("ioctl"), exit(1);
+ __atomic_store_n(&cover[0], 0, __ATOMIC_RELAXED);
+ read(-1, NULL, 0);
+ /* Read number of comparisons collected. */
+ n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED);
+ for (i = 0; i < n; i++) {
+ type = cover[i * KCOV_WORDS_PER_CMP + 1];
+ /* arg1 and arg2 - operands of the comparison. */
+ arg1 = cover[i * KCOV_WORDS_PER_CMP + 2];
+ arg2 = cover[i * KCOV_WORDS_PER_CMP + 3];
+ /* ip - caller address. */
+ ip = cover[i * KCOV_WORDS_PER_CMP + 4];
+ /* size of the operands. */
+ size = 1 << ((type & KCOV_CMP_MASK) >> 1);
+ /* is_const - true if either operand is a compile-time constant.*/
+ is_const = type & KCOV_CMP_CONST;
+ printf("ip: 0x%lx type: 0x%lx, arg1: 0x%lx, arg2: 0x%lx, "
+ "size: %lu, %s\n",
+ ip, type, arg1, arg2, size,
+ is_const ? "const" : "non-const");
+ }
+ if (ioctl(fd, KCOV_DISABLE, 0))
+ perror("ioctl"), exit(1);
+ /* Free resources. */
+ if (munmap(cover, COVER_SIZE * sizeof(unsigned long)))
+ perror("munmap"), exit(1);
+ if (close(fd))
+ perror("close"), exit(1);
+ return 0;
+ }
+
+Note that the kcov modes (coverage collection or comparison operands) are
+mutually exclusive.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index ec571b9..2a84bb3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -181,6 +181,7 @@
VmPTE: 20 kb
VmSwap: 0 kB
HugetlbPages: 0 kB
+ CoreDumping: 0
Threads: 1
SigQ: 0/28578
SigPnd: 0000000000000000
@@ -253,6 +254,8 @@
VmSwap amount of swap used by anonymous private data
(shmem swap usage is not included)
HugetlbPages size of hugetlb memory portions
+ CoreDumping process's memory is currently being dumped
+ (killing the process may lead to a corrupted core)
Threads number of threads
SigQ number of signals queued/max. number for queue
SigPnd bitmap of pending signals for the thread
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 055c8b3..b920423 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -818,7 +818,7 @@
swappiness
This control is used to define how aggressive the kernel will swap
-memory pages. Higher values will increase agressiveness, lower values
+memory pages. Higher values will increase aggressiveness, lower values
decrease the amount of swap. A value of 0 instructs the kernel not to
initiate swap until the amount of free and file-backed pages is less
than the high water mark in a zone.
diff --git a/Makefile b/Makefile
index 763ab35..ccb7d5b 100644
--- a/Makefile
+++ b/Makefile
@@ -375,8 +375,6 @@
AFLAGS_KERNEL =
LDFLAGS_vmlinux =
CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,)
-CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,)
-
# Use USERINCLUDE when you must reference the UAPI directories only.
USERINCLUDE := \
@@ -659,6 +657,7 @@
KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
endif
+include scripts/Makefile.kcov
include scripts/Makefile.gcc-plugins
ifdef CONFIG_READABLE_ASM
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 3ad8f69..82f9bf7 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -34,13 +34,6 @@
&node_to_cpu_mask[node])
/*
- * Returns the number of the node containing Node 'nid'.
- * Not implemented here. Multi-level hierarchies detected with
- * the help of node_distance().
- */
-#define parent_node(nid) (nid)
-
-/*
* Determines the node for a given pci bus
*/
#define pcibus_to_node(bus) PCI_CONTROLLER(bus)->node
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index f7693f4..f4db216 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -31,8 +31,8 @@ void foo(void)
DEFINE(SIGFRAME_SIZE, sizeof (struct sigframe));
DEFINE(UNW_FRAME_INFO_SIZE, sizeof (struct unw_frame_info));
- BUILD_BUG_ON(sizeof(struct upid) != 32);
- DEFINE(IA64_UPID_SHIFT, 5);
+ BUILD_BUG_ON(sizeof(struct upid) != 16);
+ DEFINE(IA64_UPID_SHIFT, 4);
BLANK();
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index f23781d6..f0bfa14 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -60,7 +60,7 @@ void bust_spinlocks(int yes)
void do_BUG(const char *file, int line)
{
bust_spinlocks(1);
- printk(KERN_EMERG "------------[ cut here ]------------\n");
+ printk(KERN_EMERG CUT_HERE);
printk(KERN_EMERG "kernel BUG at %s:%d!\n", file, line);
}
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 1fbb5da..e47761c 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1093,7 +1093,7 @@ static int show_spu_loadavg(struct seq_file *s, void *private)
LOAD_INT(c), LOAD_FRAC(c),
count_active_contexts(),
atomic_read(&nr_spu_contexts),
- task_active_pid_ns(current)->last_pid);
+ idr_get_cursor(&task_active_pid_ns(current)->idr));
return 0;
}
diff --git a/arch/sh/boot/compressed/misc.c b/arch/sh/boot/compressed/misc.c
index f2d9d30..627ce8e 100644
--- a/arch/sh/boot/compressed/misc.c
+++ b/arch/sh/boot/compressed/misc.c
@@ -104,6 +104,18 @@ static void error(char *x)
while(1); /* Halt */
}
+unsigned long __stack_chk_guard;
+
+void __stack_chk_guard_setup(void)
+{
+ __stack_chk_guard = 0x000a0dff;
+}
+
+void __stack_chk_fail(void)
+{
+ error("stack-protector: Kernel stack is corrupted\n");
+}
+
#ifdef CONFIG_SUPERH64
#define stackalign 8
#else
@@ -118,6 +130,8 @@ void decompress_kernel(void)
{
unsigned long output_addr;
+ __stack_chk_guard_setup();
+
#ifdef CONFIG_SUPERH64
output_addr = (CONFIG_MEMORY_START + 0x2000);
#else
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
index 9a32eb4..1db470e 100644
--- a/arch/sh/include/asm/topology.h
+++ b/arch/sh/include/asm/topology.h
@@ -5,7 +5,6 @@
#ifdef CONFIG_NUMA
#define cpu_to_node(cpu) ((void)(cpu),0)
-#define parent_node(node) ((void)(node),0)
#define cpumask_of_node(node) ((void)node, cpu_online_mask)
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index 3831b19..34c628a 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -11,8 +11,6 @@ static inline int cpu_to_node(int cpu)
return numa_cpu_lookup_table[cpu];
}
-#define parent_node(node) (node)
-
#define cpumask_of_node(node) ((node) == -1 ? \
cpu_all_mask : \
&numa_cpumask_lookup_table[node])
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index b11d5fc..635a0a4 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -29,12 +29,6 @@ static inline int cpu_to_node(int cpu)
return cpu_2_node[cpu];
}
-/*
- * Returns the number of the node containing Node 'node'.
- * This architecture is flat, so it is a pretty simple function!
- */
-#define parent_node(node) (node)
-
/* Returns a bitmask of CPUs on Node 'node'. */
static inline const struct cpumask *cpumask_of_node(int node)
{
diff --git a/drivers/misc/lkdtm_bugs.c b/drivers/misc/lkdtm_bugs.c
index b0f7af8..7eebbdf 100644
--- a/drivers/misc/lkdtm_bugs.c
+++ b/drivers/misc/lkdtm_bugs.c
@@ -63,9 +63,11 @@ void lkdtm_BUG(void)
BUG();
}
+static int warn_counter;
+
void lkdtm_WARNING(void)
{
- WARN_ON(1);
+ WARN(1, "Warning message trigger count: %d\n", warn_counter++);
}
void lkdtm_EXCEPTION(void)
diff --git a/drivers/pcmcia/sa1111_badge4.c b/drivers/pcmcia/sa1111_badge4.c
index 2f49093..93a5c74 100644
--- a/drivers/pcmcia/sa1111_badge4.c
+++ b/drivers/pcmcia/sa1111_badge4.c
@@ -144,6 +144,7 @@ int pcmcia_badge4_init(struct sa1111_dev *dev)
sa11xx_drv_pcmcia_add_one);
}
+#ifndef MODULE
static int __init pcmv_setup(char *s)
{
int v[4];
@@ -158,3 +159,4 @@ static int __init pcmv_setup(char *s)
}
__setup("pcmv=", pcmv_setup);
+#endif
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 665d9e9..ec4bc15 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -959,9 +959,10 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
nents = dma_map_sg(chan->device->dev,
req->sgt.sgl, req->sgt.nents, dir);
- if (nents == -EFAULT) {
+ if (nents == 0) {
rmcd_error("Failed to map SG list");
- return -EFAULT;
+ ret = -EFAULT;
+ goto err_pg;
}
ret = do_dma_request(req, xfer, sync, nents);
diff --git a/drivers/rapidio/switches/idt_gen2.c b/drivers/rapidio/switches/idt_gen2.c
index e67b923..4931ed7 100644
--- a/drivers/rapidio/switches/idt_gen2.c
+++ b/drivers/rapidio/switches/idt_gen2.c
@@ -458,7 +458,7 @@ static void idtg2_remove(struct rio_dev *rdev)
idtg2_sysfs(rdev, false);
}
-static struct rio_device_id idtg2_id_table[] = {
+static const struct rio_device_id idtg2_id_table[] = {
{RIO_DEVICE(RIO_DID_IDTCPS1848, RIO_VID_IDT)},
{RIO_DEVICE(RIO_DID_IDTCPS1616, RIO_VID_IDT)},
{RIO_DEVICE(RIO_DID_IDTVPS1616, RIO_VID_IDT)},
diff --git a/drivers/rapidio/switches/idt_gen3.c b/drivers/rapidio/switches/idt_gen3.c
index c5923a5..85a3908 100644
--- a/drivers/rapidio/switches/idt_gen3.c
+++ b/drivers/rapidio/switches/idt_gen3.c
@@ -348,7 +348,7 @@ static void idtg3_shutdown(struct rio_dev *rdev)
}
}
-static struct rio_device_id idtg3_id_table[] = {
+static const struct rio_device_id idtg3_id_table[] = {
{RIO_DEVICE(RIO_DID_IDTRXS1632, RIO_VID_IDT)},
{RIO_DEVICE(RIO_DID_IDTRXS2448, RIO_VID_IDT)},
{ 0, } /* terminate list */
diff --git a/drivers/rapidio/switches/idtcps.c b/drivers/rapidio/switches/idtcps.c
index 7fbb60d..4058ce2 100644
--- a/drivers/rapidio/switches/idtcps.c
+++ b/drivers/rapidio/switches/idtcps.c
@@ -168,7 +168,7 @@ static void idtcps_remove(struct rio_dev *rdev)
spin_unlock(&rdev->rswitch->lock);
}
-static struct rio_device_id idtcps_id_table[] = {
+static const struct rio_device_id idtcps_id_table[] = {
{RIO_DEVICE(RIO_DID_IDTCPS6Q, RIO_VID_IDT)},
{RIO_DEVICE(RIO_DID_IDTCPS8, RIO_VID_IDT)},
{RIO_DEVICE(RIO_DID_IDTCPS10Q, RIO_VID_IDT)},
diff --git a/drivers/rapidio/switches/tsi568.c b/drivers/rapidio/switches/tsi568.c
index 8a43561..1214628b 100644
--- a/drivers/rapidio/switches/tsi568.c
+++ b/drivers/rapidio/switches/tsi568.c
@@ -169,7 +169,7 @@ static void tsi568_remove(struct rio_dev *rdev)
spin_unlock(&rdev->rswitch->lock);
}
-static struct rio_device_id tsi568_id_table[] = {
+static const struct rio_device_id tsi568_id_table[] = {
{RIO_DEVICE(RIO_DID_TSI568, RIO_VID_TUNDRA)},
{ 0, } /* terminate list */
};
diff --git a/drivers/rapidio/switches/tsi57x.c b/drivers/rapidio/switches/tsi57x.c
index 2700d15..9f063e21 100644
--- a/drivers/rapidio/switches/tsi57x.c
+++ b/drivers/rapidio/switches/tsi57x.c
@@ -336,7 +336,7 @@ static void tsi57x_remove(struct rio_dev *rdev)
spin_unlock(&rdev->rswitch->lock);
}
-static struct rio_device_id tsi57x_id_table[] = {
+static const struct rio_device_id tsi57x_id_table[] = {
{RIO_DEVICE(RIO_DID_TSI572, RIO_VID_TUNDRA)},
{RIO_DEVICE(RIO_DID_TSI574, RIO_VID_TUNDRA)},
{RIO_DEVICE(RIO_DID_TSI577, RIO_VID_TUNDRA)},
diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index 74265b2..8a8d952 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -137,25 +137,6 @@ int watchdog_init_timeout(struct watchdog_device *wdd,
}
EXPORT_SYMBOL_GPL(watchdog_init_timeout);
-static int watchdog_reboot_notifier(struct notifier_block *nb,
- unsigned long code, void *data)
-{
- struct watchdog_device *wdd = container_of(nb, struct watchdog_device,
- reboot_nb);
-
- if (code == SYS_DOWN || code == SYS_HALT) {
- if (watchdog_active(wdd)) {
- int ret;
-
- ret = wdd->ops->stop(wdd);
- if (ret)
- return NOTIFY_BAD;
- }
- }
-
- return NOTIFY_DONE;
-}
-
static int watchdog_restart_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
@@ -244,19 +225,6 @@ static int __watchdog_register_device(struct watchdog_device *wdd)
}
}
- if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) {
- wdd->reboot_nb.notifier_call = watchdog_reboot_notifier;
-
- ret = register_reboot_notifier(&wdd->reboot_nb);
- if (ret) {
- pr_err("watchdog%d: Cannot register reboot notifier (%d)\n",
- wdd->id, ret);
- watchdog_dev_unregister(wdd);
- ida_simple_remove(&watchdog_ida, wdd->id);
- return ret;
- }
- }
-
if (wdd->ops->restart) {
wdd->restart_nb.notifier_call = watchdog_restart_notifier;
@@ -302,9 +270,6 @@ static void __watchdog_unregister_device(struct watchdog_device *wdd)
if (wdd->ops->restart)
unregister_restart_handler(&wdd->restart_nb);
- if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status))
- unregister_reboot_notifier(&wdd->reboot_nb);
-
watchdog_dev_unregister(wdd);
ida_simple_remove(&watchdog_ida, wdd->id);
}
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 0826e66..1e971a5 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -42,6 +42,7 @@
#include <linux/miscdevice.h> /* For handling misc devices */
#include <linux/module.h> /* For module stuff/... */
#include <linux/mutex.h> /* For mutexes */
+#include <linux/reboot.h> /* For reboot notifier */
#include <linux/slab.h> /* For memory functions */
#include <linux/types.h> /* For standard types (like size_t) */
#include <linux/watchdog.h> /* For watchdog specific items */
@@ -1016,6 +1017,25 @@ static struct class watchdog_class = {
.dev_groups = wdt_groups,
};
+static int watchdog_reboot_notifier(struct notifier_block *nb,
+ unsigned long code, void *data)
+{
+ struct watchdog_device *wdd;
+
+ wdd = container_of(nb, struct watchdog_device, reboot_nb);
+ if (code == SYS_DOWN || code == SYS_HALT) {
+ if (watchdog_active(wdd)) {
+ int ret;
+
+ ret = wdd->ops->stop(wdd);
+ if (ret)
+ return NOTIFY_BAD;
+ }
+ }
+
+ return NOTIFY_DONE;
+}
+
/*
* watchdog_dev_register: register a watchdog device
* @wdd: watchdog device
@@ -1049,6 +1069,18 @@ int watchdog_dev_register(struct watchdog_device *wdd)
if (ret) {
device_destroy(&watchdog_class, devno);
watchdog_cdev_unregister(wdd);
+ return ret;
+ }
+
+ if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) {
+ wdd->reboot_nb.notifier_call = watchdog_reboot_notifier;
+
+ ret = devm_register_reboot_notifier(dev, &wdd->reboot_nb);
+ if (ret) {
+ pr_err("watchdog%d: Cannot register reboot notifier (%d)\n",
+ wdd->id, ret);
+ watchdog_dev_unregister(wdd);
+ }
}
return ret;
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 4ac49d0..8fc4170 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -81,7 +81,8 @@ static int autofs4_write(struct autofs_sb_info *sbi,
spin_unlock_irqrestore(¤t->sighand->siglock, flags);
}
- return (bytes > 0);
+ /* if 'wr' returned 0 (impossible) we assume -EIO (safe) */
+ return bytes == 0 ? 0 : wr < 0 ? wr : -EIO;
}
static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
@@ -95,6 +96,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
} pkt;
struct file *pipe = NULL;
size_t pktsz;
+ int ret;
pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n",
(unsigned long) wq->wait_queue_token,
@@ -169,7 +171,18 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
mutex_unlock(&sbi->wq_mutex);
if (autofs4_write(sbi, pipe, &pkt, pktsz))
+ switch (ret = autofs4_write(sbi, pipe, &pkt, pktsz)) {
+ case 0:
+ break;
+ case -ENOMEM:
+ case -ERESTARTSYS:
+ /* Just fail this one */
+ autofs4_wait_release(sbi, wq->wait_queue_token, ret);
+ break;
+ default:
autofs4_catatonic_mode(sbi);
+ break;
+ }
fput(pipe);
}
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 396a3c07..afd548e 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -276,12 +276,6 @@ static DEFINE_MUTEX(epmutex);
/* Used to check for epoll file descriptor inclusion loops */
static struct nested_calls poll_loop_ncalls;
-/* Used for safe wake up implementation */
-static struct nested_calls poll_safewake_ncalls;
-
-/* Used to call file's f_op->poll() under the nested calls boundaries */
-static struct nested_calls poll_readywalk_ncalls;
-
/* Slab cache used to allocate "struct epitem" */
static struct kmem_cache *epi_cache __read_mostly;
@@ -551,40 +545,21 @@ static int ep_call_nested(struct nested_calls *ncalls, int max_nests,
* this special case of epoll.
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
- unsigned long events, int subclass)
-{
- unsigned long flags;
- spin_lock_irqsave_nested(&wqueue->lock, flags, subclass);
- wake_up_locked_poll(wqueue, events);
- spin_unlock_irqrestore(&wqueue->lock, flags);
-}
-#else
-static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
- unsigned long events, int subclass)
-{
- wake_up_poll(wqueue, events);
-}
-#endif
+static struct nested_calls poll_safewake_ncalls;
static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
{
- ep_wake_up_nested((wait_queue_head_t *) cookie, POLLIN,
- 1 + call_nests);
+ unsigned long flags;
+ wait_queue_head_t *wqueue = (wait_queue_head_t *)cookie;
+
+ spin_lock_irqsave_nested(&wqueue->lock, flags, call_nests + 1);
+ wake_up_locked_poll(wqueue, POLLIN);
+ spin_unlock_irqrestore(&wqueue->lock, flags);
+
return 0;
}
-/*
- * Perform a safe wake up of the poll wait list. The problem is that
- * with the new callback'd wake up system, it is possible that the
- * poll callback is reentered from inside the call to wake_up() done
- * on the poll wait queue head. The rule is that we cannot reenter the
- * wake up code from the same task more than EP_MAX_NESTS times,
- * and we cannot reenter the same wait queue head at all. This will
- * enable to have a hierarchy of epoll file descriptor of no more than
- * EP_MAX_NESTS deep.
- */
static void ep_poll_safewake(wait_queue_head_t *wq)
{
int this_cpu = get_cpu();
@@ -595,6 +570,15 @@ static void ep_poll_safewake(wait_queue_head_t *wq)
put_cpu();
}
+#else
+
+static void ep_poll_safewake(wait_queue_head_t *wq)
+{
+ wake_up_poll(wq, POLLIN);
+}
+
+#endif
+
static void ep_remove_wait_queue(struct eppoll_entry *pwq)
{
wait_queue_head_t *whead;
@@ -880,11 +864,33 @@ static int ep_eventpoll_release(struct inode *inode, struct file *file)
return 0;
}
-static inline unsigned int ep_item_poll(struct epitem *epi, poll_table *pt)
-{
- pt->_key = epi->event.events;
+static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
+ void *priv);
+static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
+ poll_table *pt);
- return epi->ffd.file->f_op->poll(epi->ffd.file, pt) & epi->event.events;
+/*
+ * Differs from ep_eventpoll_poll() in that internal callers already have
+ * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
+ * is correctly annotated.
+ */
+static unsigned int ep_item_poll(struct epitem *epi, poll_table *pt, int depth)
+{
+ struct eventpoll *ep;
+ bool locked;
+
+ pt->_key = epi->event.events;
+ if (!is_file_epoll(epi->ffd.file))
+ return epi->ffd.file->f_op->poll(epi->ffd.file, pt) &
+ epi->event.events;
+
+ ep = epi->ffd.file->private_data;
+ poll_wait(epi->ffd.file, &ep->poll_wait, pt);
+ locked = pt && (pt->_qproc == ep_ptable_queue_proc);
+
+ return ep_scan_ready_list(epi->ffd.file->private_data,
+ ep_read_events_proc, &depth, depth,
+ locked) & epi->event.events;
}
static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
@@ -892,13 +898,15 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
{
struct epitem *epi, *tmp;
poll_table pt;
+ int depth = *(int *)priv;
init_poll_funcptr(&pt, NULL);
+ depth++;
list_for_each_entry_safe(epi, tmp, head, rdllink) {
- if (ep_item_poll(epi, &pt))
+ if (ep_item_poll(epi, &pt, depth)) {
return POLLIN | POLLRDNORM;
- else {
+ } else {
/*
* Item has been dropped into the ready list by the poll
* callback, but it's not actually ready, as far as
@@ -912,48 +920,20 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
return 0;
}
-static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
- poll_table *pt);
-
-struct readyevents_arg {
- struct eventpoll *ep;
- bool locked;
-};
-
-static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
-{
- struct readyevents_arg *arg = priv;
-
- return ep_scan_ready_list(arg->ep, ep_read_events_proc, NULL,
- call_nests + 1, arg->locked);
-}
-
static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
{
- int pollflags;
struct eventpoll *ep = file->private_data;
- struct readyevents_arg arg;
-
- /*
- * During ep_insert() we already hold the ep->mtx for the tfile.
- * Prevent re-aquisition.
- */
- arg.locked = wait && (wait->_qproc == ep_ptable_queue_proc);
- arg.ep = ep;
+ int depth = 0;
/* Insert inside our poll wait queue */
poll_wait(file, &ep->poll_wait, wait);
/*
* Proceed to find out if wanted events are really available inside
- * the ready list. This need to be done under ep_call_nested()
- * supervision, since the call to f_op->poll() done on listed files
- * could re-enter here.
+ * the ready list.
*/
- pollflags = ep_call_nested(&poll_readywalk_ncalls, EP_MAX_NESTS,
- ep_poll_readyevents_proc, &arg, ep, current);
-
- return pollflags != -1 ? pollflags : 0;
+ return ep_scan_ready_list(ep, ep_read_events_proc,
+ &depth, depth, false);
}
#ifdef CONFIG_PROC_FS
@@ -1472,7 +1452,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
* this operation completes, the poll callback can start hitting
* the new item.
*/
- revents = ep_item_poll(epi, &epq.pt);
+ revents = ep_item_poll(epi, &epq.pt, 1);
/*
* We have to check if something went wrong during the poll wait queue
@@ -1606,7 +1586,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
* Get current event bits. We can safely use the file* here because
* its usage count has been increased by the caller of this function.
*/
- revents = ep_item_poll(epi, &pt);
+ revents = ep_item_poll(epi, &pt, 1);
/*
* If the item is "hot" and it is not registered inside the ready
@@ -1674,7 +1654,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
list_del_init(&epi->rdllink);
- revents = ep_item_poll(epi, &pt);
+ revents = ep_item_poll(epi, &pt, 1);
/*
* If the event mask intersect the caller-requested one,
@@ -2313,11 +2293,10 @@ static int __init eventpoll_init(void)
*/
ep_nested_calls_init(&poll_loop_ncalls);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
/* Initialize the structure used to perform safe poll wait head wake ups */
ep_nested_calls_init(&poll_safewake_ncalls);
-
- /* Initialize the structure used to perform file's f_op->poll() calls */
- ep_nested_calls_init(&poll_readywalk_ncalls);
+#endif
/*
* We can have many thousands of epitems, so prevent this from
@@ -2327,11 +2306,11 @@ static int __init eventpoll_init(void)
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
- 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
/* Allocates slab cache used to allocate "struct eppoll_entry" */
pwq_cache = kmem_cache_create("eventpoll_pwq",
- sizeof(struct eppoll_entry), 0, SLAB_PANIC, NULL);
+ sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
return 0;
}
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 81cecbe..b833ffe 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -291,7 +291,6 @@ static int fat_parse_long(struct inode *dir, loff_t *pos,
}
}
parse_long:
- slots = 0;
ds = (struct msdos_dir_slot *)*de;
id = ds->id;
if (!(id & 0x40))
diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c
index 8aec5e7..b63a4df 100644
--- a/fs/hfs/bnode.c
+++ b/fs/hfs/bnode.c
@@ -98,13 +98,11 @@ void hfs_bnode_clear(struct hfs_bnode *node, int off, int len)
void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
struct hfs_bnode *src_node, int src, int len)
{
- struct hfs_btree *tree;
struct page *src_page, *dst_page;
hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len);
if (!len)
return;
- tree = src_node->tree;
src += src_node->page_offset;
dst += dst_node->page_offset;
src_page = src_node->page[0];
@@ -237,7 +235,6 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid)
static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
{
- struct super_block *sb;
struct hfs_bnode *node, *node2;
struct address_space *mapping;
struct page *page;
@@ -249,7 +246,6 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
return NULL;
}
- sb = tree->inode->i_sb;
size = sizeof(struct hfs_bnode) + tree->pages_per_bnode *
sizeof(struct page *);
node = kzalloc(size, GFP_KERNEL);
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index d77015c..177fae4e 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -127,14 +127,12 @@ void hfs_bnode_clear(struct hfs_bnode *node, int off, int len)
void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
struct hfs_bnode *src_node, int src, int len)
{
- struct hfs_btree *tree;
struct page **src_page, **dst_page;
int l;
hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len);
if (!len)
return;
- tree = src_node->tree;
src += src_node->page_offset;
dst += dst_node->page_offset;
src_page = src_node->page + (src >> PAGE_SHIFT);
@@ -401,7 +399,6 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid)
static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
{
- struct super_block *sb;
struct hfs_bnode *node, *node2;
struct address_space *mapping;
struct page *page;
@@ -414,7 +411,6 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
return NULL;
}
- sb = tree->inode->i_sb;
size = sizeof(struct hfs_bnode) + tree->pages_per_bnode *
sizeof(struct page *);
node = kzalloc(size, GFP_KERNEL);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 515d13c..1a2894a 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -150,7 +150,7 @@ static int nilfs_symlink(struct inode *dir, struct dentry *dentry,
if (err)
return err;
- inode = nilfs_new_inode(dir, S_IFLNK | S_IRWXUGO);
+ inode = nilfs_new_inode(dir, S_IFLNK | 0777);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index f65392f..f572538 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1954,8 +1954,6 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
err, ii->vfs_inode.i_ino);
return err;
}
- mark_buffer_dirty(ibh);
- nilfs_mdt_mark_dirty(ifile);
spin_lock(&nilfs->ns_inode_lock);
if (likely(!ii->i_bh))
ii->i_bh = ibh;
@@ -1964,6 +1962,10 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
goto retry;
}
+ // Always redirty the buffer to avoid race condition
+ mark_buffer_dirty(ii->i_bh);
+ nilfs_mdt_mark_dirty(ifile);
+
clear_bit(NILFS_I_QUEUED, &ii->i_state);
set_bit(NILFS_I_BUSY, &ii->i_state);
list_move_tail(&ii->i_dirty, &sci->sc_dirty_files);
@@ -2400,11 +2402,11 @@ static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode)
return err;
}
-static void nilfs_construction_timeout(unsigned long data)
+static void nilfs_construction_timeout(struct timer_list *t)
{
- struct task_struct *p = (struct task_struct *)data;
+ struct nilfs_sc_info *sci = from_timer(sci, t, sc_timer);
- wake_up_process(p);
+ wake_up_process(sci->sc_timer_task);
}
static void
@@ -2542,8 +2544,7 @@ static int nilfs_segctor_thread(void *arg)
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
int timeout = 0;
- sci->sc_timer.data = (unsigned long)current;
- sci->sc_timer.function = nilfs_construction_timeout;
+ sci->sc_timer_task = current;
/* start sync. */
sci->sc_task = current;
@@ -2674,7 +2675,7 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
INIT_LIST_HEAD(&sci->sc_gc_inodes);
INIT_LIST_HEAD(&sci->sc_iput_queue);
INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
- init_timer(&sci->sc_timer);
+ timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ;
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 1060949..84084a4 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -180,6 +180,7 @@ struct nilfs_sc_info {
unsigned long sc_watermark;
struct timer_list sc_timer;
+ struct task_struct *sc_timer_task;
struct task_struct *sc_task;
};
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 1541a1e..1341a41 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -630,22 +630,22 @@ void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum,
}
/**
- * nilfs_sufile_truncate_range - truncate range of segment array
- * @sufile: inode of segment usage file
- * @start: start segment number (inclusive)
- * @end: end segment number (inclusive)
- *
- * Return Value: On success, 0 is returned. On error, one of the
- * following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EINVAL - Invalid number of segments specified
- *
- * %-EBUSY - Dirty or active segments are present in the range
- */
+ * nilfs_sufile_truncate_range - truncate range of segment array
+ * @sufile: inode of segment usage file
+ * @start: start segment number (inclusive)
+ * @end: end segment number (inclusive)
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid number of segments specified
+ *
+ * %-EBUSY - Dirty or active segments are present in the range
+ */
static int nilfs_sufile_truncate_range(struct inode *sufile,
__u64 start, __u64 end)
{
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 4fc018d..3ce20cd 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -160,7 +160,6 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
ii->i_bh = NULL;
ii->i_state = 0;
ii->i_cno = 0;
- ii->vfs_inode.i_version = 1;
nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode);
return &ii->vfs_inode;
}
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 2dd75bf..afebb50 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -737,7 +737,7 @@ struct nilfs_root *nilfs_lookup_root(struct the_nilfs *nilfs, __u64 cno)
} else if (cno > root->cno) {
n = n->rb_right;
} else {
- atomic_inc(&root->count);
+ refcount_inc(&root->count);
spin_unlock(&nilfs->ns_cptree_lock);
return root;
}
@@ -776,7 +776,7 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno)
} else if (cno > root->cno) {
p = &(*p)->rb_right;
} else {
- atomic_inc(&root->count);
+ refcount_inc(&root->count);
spin_unlock(&nilfs->ns_cptree_lock);
kfree(new);
return root;
@@ -786,7 +786,7 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno)
new->cno = cno;
new->ifile = NULL;
new->nilfs = nilfs;
- atomic_set(&new->count, 1);
+ refcount_set(&new->count, 1);
atomic64_set(&new->inodes_count, 0);
atomic64_set(&new->blocks_count, 0);
@@ -806,7 +806,7 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno)
void nilfs_put_root(struct nilfs_root *root)
{
- if (atomic_dec_and_test(&root->count)) {
+ if (refcount_dec_and_test(&root->count)) {
struct the_nilfs *nilfs = root->nilfs;
nilfs_sysfs_delete_snapshot_group(root);
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index b305c6f..883d732 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -27,6 +27,7 @@
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/slab.h>
+#include <linux/refcount.h>
struct nilfs_sc_info;
struct nilfs_sysfs_dev_subgroups;
@@ -246,7 +247,7 @@ struct nilfs_root {
__u64 cno;
struct rb_node rb_node;
- atomic_t count;
+ refcount_t count;
struct the_nilfs *nilfs;
struct inode *ifile;
@@ -299,7 +300,7 @@ void nilfs_swap_super_block(struct the_nilfs *);
static inline void nilfs_get_root(struct nilfs_root *root)
{
- atomic_inc(&root->count);
+ refcount_inc(&root->count);
}
static inline int nilfs_valid_fs(struct the_nilfs *nilfs)
diff --git a/fs/pipe.c b/fs/pipe.c
index 349c9d5..6d98566 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1018,13 +1018,19 @@ const struct file_operations pipefifo_fops = {
/*
* Currently we rely on the pipe array holding a power-of-2 number
- * of pages.
+ * of pages. Returns 0 on error.
*/
-static inline unsigned int round_pipe_size(unsigned int size)
+unsigned int round_pipe_size(unsigned int size)
{
unsigned long nr_pages;
+ if (size < pipe_min_size)
+ size = pipe_min_size;
+
nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (nr_pages == 0)
+ return 0;
+
return roundup_pow_of_two(nr_pages) << PAGE_SHIFT;
}
@@ -1040,6 +1046,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
long ret = 0;
size = round_pipe_size(arg);
+ if (size == 0)
+ return -EINVAL;
nr_pages = size >> PAGE_SHIFT;
if (!nr_pages)
@@ -1117,20 +1125,13 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
}
/*
- * This should work even if CONFIG_PROC_FS isn't set, as proc_dointvec_minmax
+ * This should work even if CONFIG_PROC_FS isn't set, as proc_dopipe_max_size
* will return an error.
*/
int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
size_t *lenp, loff_t *ppos)
{
- int ret;
-
- ret = proc_dointvec_minmax(table, write, buf, lenp, ppos);
- if (ret < 0 || !write)
- return ret;
-
- pipe_max_size = round_pipe_size(pipe_max_size);
- return ret;
+ return proc_dopipe_max_size(table, write, buf, lenp, ppos);
}
/*
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index f7456c4..ead487e 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -21,6 +21,7 @@
proc-y += meminfo.o
proc-y += stat.o
proc-y += uptime.o
+proc-y += util.o
proc-y += version.o
proc-y += softirqs.o
proc-y += namespaces.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 6f6fc16..79375fc 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -366,6 +366,11 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
cpumask_pr_args(&task->cpus_allowed));
}
+static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)
+{
+ seq_printf(m, "CoreDumping:\t%d\n", !!mm->core_state);
+}
+
int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
@@ -376,6 +381,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
if (mm) {
task_mem(m, mm);
+ task_core_dumping(m, mm);
mmput(mm);
}
task_sig(m, task);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index a34195e..9aad373 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -103,28 +103,7 @@ static inline struct task_struct *get_proc_task(struct inode *inode)
void task_dump_owner(struct task_struct *task, mode_t mode,
kuid_t *ruid, kgid_t *rgid);
-static inline unsigned name_to_int(const struct qstr *qstr)
-{
- const char *name = qstr->name;
- int len = qstr->len;
- unsigned n = 0;
-
- if (len > 1 && *name == '0')
- goto out;
- while (len-- > 0) {
- unsigned c = *name++ - '0';
- if (c > 9)
- goto out;
- if (n >= (~0U-9)/10)
- goto out;
- n *= 10;
- n += c;
- }
- return n;
-out:
- return ~0U;
-}
-
+unsigned name_to_int(const struct qstr *qstr);
/*
* Offset of the first process in the /proc root directory..
*/
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index 9bc5c58..a000d75 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -24,7 +24,7 @@ static int loadavg_proc_show(struct seq_file *m, void *v)
LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
nr_running(), nr_threads,
- task_active_pid_ns(current)->last_pid);
+ idr_get_cursor(&task_active_pid_ns(current)->idr));
return 0;
}
diff --git a/fs/proc/util.c b/fs/proc/util.c
new file mode 100644
index 0000000..b161cfa
--- /dev/null
+++ b/fs/proc/util.c
@@ -0,0 +1,23 @@
+#include <linux/dcache.h>
+
+unsigned name_to_int(const struct qstr *qstr)
+{
+ const char *name = qstr->name;
+ int len = qstr->len;
+ unsigned n = 0;
+
+ if (len > 1 && *name == '0')
+ goto out;
+ do {
+ unsigned c = *name++ - '0';
+ if (c > 9)
+ goto out;
+ if (n >= (~0U-9)/10)
+ goto out;
+ n *= 10;
+ n += c;
+ } while (--len > 0);
+ return n;
+out:
+ return ~0U;
+}
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index af2cc94..963b755 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -4,6 +4,8 @@
#include <linux/compiler.h>
+#define CUT_HERE "------------[ cut here ]------------\n"
+
#ifdef CONFIG_GENERIC_BUG
#define BUGFLAG_WARNING (1 << 0)
#define BUGFLAG_ONCE (1 << 1)
@@ -90,10 +92,11 @@ extern void warn_slowpath_null(const char *file, const int line);
#define __WARN_printf_taint(taint, arg...) \
warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)
#else
+extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
#define __WARN() __WARN_TAINT(TAINT_WARN)
-#define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0)
+#define __WARN_printf(arg...) do { __warn_printk(arg); __WARN(); } while (0)
#define __WARN_printf_taint(taint, arg...) \
- do { printk(arg); __WARN_TAINT(taint); } while (0)
+ do { __warn_printk(arg); __WARN_TAINT(taint); } while (0)
#endif
/* used internally by panic.c */
@@ -130,7 +133,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
#ifndef WARN_ON_ONCE
#define WARN_ON_ONCE(condition) ({ \
- static bool __section(.data.unlikely) __warned; \
+ static bool __section(.data.once) __warned; \
int __ret_warn_once = !!(condition); \
\
if (unlikely(__ret_warn_once && !__warned)) { \
@@ -142,7 +145,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
#endif
#define WARN_ONCE(condition, format...) ({ \
- static bool __section(.data.unlikely) __warned; \
+ static bool __section(.data.once) __warned; \
int __ret_warn_once = !!(condition); \
\
if (unlikely(__ret_warn_once && !__warned)) { \
@@ -153,7 +156,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
})
#define WARN_TAINT_ONCE(condition, taint, format...) ({ \
- static bool __section(.data.unlikely) __warned; \
+ static bool __section(.data.once) __warned; \
int __ret_warn_once = !!(condition); \
\
if (unlikely(__ret_warn_once && !__warned)) { \
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 6d95769..03cc5f9 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -44,6 +44,7 @@ extern char __entry_text_start[], __entry_text_end[];
extern char __start_rodata[], __end_rodata[];
extern char __irqentry_text_start[], __irqentry_text_end[];
extern char __softirqentry_text_start[], __softirqentry_text_end[];
+extern char __start_once[], __end_once[];
/* Start and end of .ctors section - used for constructor calls. */
extern char __ctors_start[], __ctors_end[];
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 5d2add1..2388737 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -44,9 +44,6 @@
#define cpu_to_mem(cpu) ((void)(cpu),0)
#endif
-#ifndef parent_node
-#define parent_node(node) ((void)(node),0)
-#endif
#ifndef cpumask_of_node
#ifdef CONFIG_NEED_MULTIPLE_NODES
#define cpumask_of_node(node) ((node) == 0 ? cpu_online_mask : cpu_none_mask)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index bdcd1ca..ee8b707 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -223,6 +223,9 @@
MEM_KEEP(init.data) \
MEM_KEEP(exit.data) \
*(.data.unlikely) \
+ VMLINUX_SYMBOL(__start_once) = .; \
+ *(.data.once) \
+ VMLINUX_SYMBOL(__end_once) = .; \
STRUCT_ALIGN(); \
*(__tracepoints) \
/* implement dynamic printk debug */ \
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index f2deb71..1030651 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -15,7 +15,7 @@
#ifndef _LINUX_BITFIELD_H
#define _LINUX_BITFIELD_H
-#include <linux/bug.h>
+#include <linux/build_bug.h>
/*
* Bitfield access macros
diff --git a/include/linux/bug.h b/include/linux/bug.h
index da4231c..fe59165 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -43,6 +43,8 @@ enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs);
/* These are defined by the architecture */
int is_valid_bugaddr(unsigned long addr);
+void generic_bug_clear_once(void);
+
#else /* !CONFIG_GENERIC_BUG */
static inline enum bug_trap_type report_bug(unsigned long bug_addr,
@@ -51,6 +53,9 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr,
return BUG_TRAP_TYPE_BUG;
}
+
+static inline void generic_bug_clear_once(void) {}
+
#endif /* CONFIG_GENERIC_BUG */
/*
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index a06583e..3b609ed 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -16,3 +16,6 @@
* with any version that can compile the kernel
*/
#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#define randomized_struct_fields_start struct {
+#define randomized_struct_fields_end };
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 6dfec4d..872f930 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -32,6 +32,7 @@
#include <linux/types.h>
#include <linux/spinlock_types.h>
+#include <linux/atomic.h>
struct device;
struct device_node;
@@ -71,7 +72,7 @@ struct gen_pool {
*/
struct gen_pool_chunk {
struct list_head next_chunk; /* next chunk in pool */
- atomic_t avail;
+ atomic_long_t avail;
phys_addr_t phys_addr; /* physical starting address of memory chunk */
unsigned long start_addr; /* start address of memory chunk */
unsigned long end_addr; /* end address of memory chunk (inclusive) */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 8062e6c..6a53262 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -105,7 +105,6 @@ extern struct group_info init_groups;
.numbers = { { \
.nr = 0, \
.ns = &init_pid_ns, \
- .pid_chain = { .next = NULL, .pprev = NULL }, \
}, } \
}
diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index d29e1e2..b1d861c 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -42,18 +42,21 @@
*/
#define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \
({ \
- ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
- might_sleep_if(sleep_us); \
+ u64 __timeout_us = (timeout_us); \
+ unsigned long __sleep_us = (sleep_us); \
+ ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
+ might_sleep_if((__sleep_us) != 0); \
for (;;) { \
(val) = op(addr); \
if (cond) \
break; \
- if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+ if (__timeout_us && \
+ ktime_compare(ktime_get(), __timeout) > 0) { \
(val) = op(addr); \
break; \
} \
- if (sleep_us) \
- usleep_range((sleep_us >> 2) + 1, sleep_us); \
+ if (__sleep_us) \
+ usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
} \
(cond) ? 0 : -ETIMEDOUT; \
})
@@ -77,17 +80,20 @@
*/
#define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \
({ \
- ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+ u64 __timeout_us = (timeout_us); \
+ unsigned long __delay_us = (delay_us); \
+ ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
for (;;) { \
(val) = op(addr); \
if (cond) \
break; \
- if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+ if (__timeout_us && \
+ ktime_compare(ktime_get(), __timeout) > 0) { \
(val) = op(addr); \
break; \
} \
- if (delay_us) \
- udelay(delay_us); \
+ if (__delay_us) \
+ udelay(__delay_us); \
} \
(cond) ? 0 : -ETIMEDOUT; \
})
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 474812a..b5630c8 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -19,7 +19,10 @@ struct ipc_ids {
bool tables_initialized;
struct rw_semaphore rwsem;
struct idr ipcs_idr;
+ int max_id;
+#ifdef CONFIG_CHECKPOINT_RESTORE
int next_id;
+#endif
struct rhashtable key_ht;
};
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index f5d8ce4..3ecf6f5 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -8,19 +8,23 @@ struct task_struct;
#ifdef CONFIG_KCOV
-void kcov_task_init(struct task_struct *t);
-void kcov_task_exit(struct task_struct *t);
-
enum kcov_mode {
/* Coverage collection is not enabled yet. */
KCOV_MODE_DISABLED = 0,
+ /* KCOV was initialized, but tracing mode hasn't been chosen yet. */
+ KCOV_MODE_INIT = 1,
/*
* Tracing coverage collection mode.
* Covered PCs are collected in a per-task buffer.
*/
- KCOV_MODE_TRACE = 1,
+ KCOV_MODE_TRACE_PC = 2,
+ /* Collecting comparison operands mode. */
+ KCOV_MODE_TRACE_CMP = 3,
};
+void kcov_task_init(struct task_struct *t);
+void kcov_task_exit(struct task_struct *t);
+
#else
static inline void kcov_task_init(struct task_struct *t) {}
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4b484ab..ce51455 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -549,7 +549,8 @@ extern enum system_states {
#define TAINT_UNSIGNED_MODULE 13
#define TAINT_SOFTLOCKUP 14
#define TAINT_LIVEPATCH 15
-#define TAINT_FLAGS_COUNT 16
+#define TAINT_AUX 16
+#define TAINT_FLAGS_COUNT 17
struct taint_flag {
char c_true; /* character printed when tainted */
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 15cab39..1fbde8a 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -104,9 +104,16 @@ extern nodemask_t _unused_nodemask_arg_;
*
* Can be used to provide arguments for '%*pb[l]' when printing a nodemask.
*/
-#define nodemask_pr_args(maskp) \
- ((maskp) != NULL) ? MAX_NUMNODES : 0, \
- ((maskp) != NULL) ? (maskp)->bits : NULL
+#define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \
+ __nodemask_pr_bits(maskp)
+static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
+{
+ return m ? MAX_NUMNODES : 0;
+}
+static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
+{
+ return m ? m->bits : NULL;
+}
/*
* The inline keyword gives the compiler room to decide to inline, or
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index e942558..9132c5c 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -96,6 +96,17 @@ void set_pfnblock_flags_mask(struct page *page,
#define set_pageblock_skip(page) \
set_pageblock_flags_group(page, 1, PB_migrate_skip, \
PB_migrate_skip)
+#else
+static inline bool get_pageblock_skip(struct page *page)
+{
+ return false;
+}
+static inline void clear_pageblock_skip(struct page *page)
+{
+}
+static inline void set_pageblock_skip(struct page *page)
+{
+}
#endif /* CONFIG_COMPACTION */
#endif /* PAGEBLOCK_FLAGS_H */
diff --git a/include/linux/pid.h b/include/linux/pid.h
index dfd684c..7633d55 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -51,10 +51,8 @@ enum pid_type
*/
struct upid {
- /* Try to keep pid_chain in the same cacheline as nr for find_vpid */
int nr;
struct pid_namespace *ns;
- struct hlist_node pid_chain;
};
struct pid
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index c78af60..49538b1 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -10,15 +10,8 @@
#include <linux/nsproxy.h>
#include <linux/kref.h>
#include <linux/ns_common.h>
+#include <linux/idr.h>
-struct pidmap {
- atomic_t nr_free;
- void *page;
-};
-
-#define BITS_PER_PAGE (PAGE_SIZE * 8)
-#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1)
-#define PIDMAP_ENTRIES ((PID_MAX_LIMIT+BITS_PER_PAGE-1)/BITS_PER_PAGE)
struct fs_pin;
@@ -30,10 +23,9 @@ enum { /* definitions for pid_namespace's hide_pid field */
struct pid_namespace {
struct kref kref;
- struct pidmap pidmap[PIDMAP_ENTRIES];
+ struct idr idr;
struct rcu_head rcu;
- int last_pid;
- unsigned int nr_hashed;
+ unsigned int pid_allocated;
struct task_struct *child_reaper;
struct kmem_cache *pid_cachep;
unsigned int level;
@@ -57,7 +49,7 @@ struct pid_namespace {
extern struct pid_namespace init_pid_ns;
-#define PIDNS_HASH_ADDING (1U << 31)
+#define PIDNS_ADDING (1U << 31)
#ifdef CONFIG_PID_NS
static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
@@ -106,6 +98,6 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
void pidhash_init(void);
-void pidmap_init(void);
+void pid_idr_init(void);
#endif /* _LINUX_PID_NS_H */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 6a80cfc..2dc5e98 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -191,5 +191,6 @@ long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
struct pipe_inode_info *get_pipe_info(struct file *file);
int create_pipe_files(struct file **, int);
+unsigned int round_pipe_size(unsigned int size);
#endif
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 0ca448c..23a9c89 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -22,7 +22,6 @@
#define _LINUX_RADIX_TREE_H
#include <linux/bitops.h>
-#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/preempt.h>
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index d03da0e..e63799a 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -6,6 +6,8 @@
#include <linux/notifier.h>
#include <uapi/linux/reboot.h>
+struct device;
+
#define SYS_DOWN 0x0001 /* Notify of system down */
#define SYS_RESTART SYS_DOWN
#define SYS_HALT 0x0002 /* Notify of system halt */
@@ -39,6 +41,8 @@ extern int reboot_force;
extern int register_reboot_notifier(struct notifier_block *);
extern int unregister_reboot_notifier(struct notifier_block *);
+extern int devm_register_reboot_notifier(struct device *, struct notifier_block *);
+
extern int register_restart_handler(struct notifier_block *);
extern int unregister_restart_handler(struct notifier_block *);
extern void do_kernel_restart(char *cmd);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index b769ecf..992bc99 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -51,6 +51,9 @@ extern int proc_dointvec_minmax(struct ctl_table *, int,
extern int proc_douintvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
+extern int proc_dopipe_max_size(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
extern int proc_dointvec_jiffies(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int,
diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h
index 33eabbb..9529867 100644
--- a/include/uapi/linux/kcov.h
+++ b/include/uapi/linux/kcov.h
@@ -8,4 +8,28 @@
#define KCOV_ENABLE _IO('c', 100)
#define KCOV_DISABLE _IO('c', 101)
+enum {
+ /*
+ * Tracing coverage collection mode.
+ * Covered PCs are collected in a per-task buffer.
+ * In new KCOV version the mode is chosen by calling
+ * ioctl(fd, KCOV_ENABLE, mode). In older versions the mode argument
+ * was supposed to be 0 in such a call. So, for reasons of backward
+ * compatibility, we have chosen the value KCOV_TRACE_PC to be 0.
+ */
+ KCOV_TRACE_PC = 0,
+ /* Collecting comparison operands mode. */
+ KCOV_TRACE_CMP = 1,
+};
+
+/*
+ * The format for the types of collected comparisons.
+ *
+ * Bit 0 shows whether one of the arguments is a compile-time constant.
+ * Bits 1 & 2 contain log2 of the argument size, up to 8 bytes.
+ */
+#define KCOV_CMP_CONST (1 << 0)
+#define KCOV_CMP_SIZE(n) ((n) << 1)
+#define KCOV_CMP_MASK KCOV_CMP_SIZE(3)
+
#endif /* _LINUX_KCOV_IOCTLS_H */
diff --git a/init/Kconfig b/init/Kconfig
index 7d5a6fb..2934249 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -283,19 +283,6 @@
to directly read from or write to another process' address space.
See the man page for more details.
-config FHANDLE
- bool "open by fhandle syscalls" if EXPERT
- select EXPORTFS
- default y
- help
- If you say Y here, a user level program will be able to map
- file names to handle and then later use the handle for
- different file system operations. This is useful in implementing
- userspace file servers, which now track files using handles instead
- of names. The handle would remain the same even if file names
- get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
- syscalls.
-
config USELIB
bool "uselib syscall"
def_bool ALPHA || M68K || SPARC || X86_32 || IA32_EMULATION
@@ -883,18 +870,6 @@
endif # CGROUPS
-config CHECKPOINT_RESTORE
- bool "Checkpoint/restore support" if EXPERT
- select PROC_CHILDREN
- default n
- help
- Enables additional kernel features in a sake of checkpoint/restore.
- In particular it adds auxiliary prctl codes to setup process text,
- data and heap segment sizes, and a few additional /proc filesystem
- entries.
-
- If unsure, say N here.
-
menuconfig NAMESPACES
bool "Namespaces support" if EXPERT
depends on MULTIUSER
@@ -1163,6 +1138,19 @@
If unsure say N here.
+config FHANDLE
+ bool "open by fhandle syscalls" if EXPERT
+ select EXPORTFS
+ default y
+ help
+ If you say Y here, a user level program will be able to map
+ file names to handle and then later use the handle for
+ different file system operations. This is useful in implementing
+ userspace file servers, which now track files using handles instead
+ of names. The handle would remain the same even if file names
+ get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
+ syscalls.
+
config POSIX_TIMERS
bool "Posix Clocks & timers" if EXPERT
default y
@@ -1180,54 +1168,6 @@
If unsure say y.
-config KALLSYMS
- bool "Load all symbols for debugging/ksymoops" if EXPERT
- default y
- help
- Say Y here to let the kernel print out symbolic crash information and
- symbolic stack backtraces. This increases the size of the kernel
- somewhat, as all symbols have to be loaded into the kernel image.
-
-config KALLSYMS_ALL
- bool "Include all symbols in kallsyms"
- depends on DEBUG_KERNEL && KALLSYMS
- help
- Normally kallsyms only contains the symbols of functions for nicer
- OOPS messages and backtraces (i.e., symbols from the text and inittext
- sections). This is sufficient for most cases. And only in very rare
- cases (e.g., when a debugger is used) all symbols are required (e.g.,
- names of variables from the data sections, etc).
-
- This option makes sure that all symbols are loaded into the kernel
- image (i.e., symbols from all sections) in cost of increased kernel
- size (depending on the kernel configuration, it may be 300KiB or
- something like this).
-
- Say N unless you really need all symbols.
-
-config KALLSYMS_ABSOLUTE_PERCPU
- bool
- depends on KALLSYMS
- default X86_64 && SMP
-
-config KALLSYMS_BASE_RELATIVE
- bool
- depends on KALLSYMS
- default !IA64 && !(TILE && 64BIT)
- help
- Instead of emitting them as absolute values in the native word size,
- emit the symbol references in the kallsyms table as 32-bit entries,
- each containing a relative value in the range [base, base + U32_MAX]
- or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either
- an absolute value in the range [0, S32_MAX] or a relative value in the
- range [base, base + S32_MAX], where base is the lowest relative symbol
- address encountered in the image.
-
- On 64-bit builds, this reduces the size of the address table by 50%,
- but more importantly, it results in entries whose values are build
- time constants, and no relocation pass is required at runtime to fix
- up the entries based on the runtime load address of the kernel.
-
config PRINTK
default y
bool "Enable support for printk" if EXPERT
@@ -1339,16 +1279,6 @@
If unsure, say Y.
-# syscall, maps, verifier
-config BPF_SYSCALL
- bool "Enable bpf() system call"
- select ANON_INODES
- select BPF
- default n
- help
- Enable the bpf() system call that allows to manipulate eBPF
- programs and maps via file descriptors.
-
config SHMEM
bool "Use full shmem filesystem" if EXPERT
default y
@@ -1378,14 +1308,6 @@
applications use these syscalls, you can disable this option to save
space.
-config USERFAULTFD
- bool "Enable userfaultfd() system call"
- select ANON_INODES
- depends on MMU
- help
- Enable the userfaultfd() system call that allows to intercept and
- handle page faults in userland.
-
config MEMBARRIER
bool "Enable membarrier() system call" if EXPERT
default y
@@ -1398,6 +1320,86 @@
If unsure, say Y.
+config CHECKPOINT_RESTORE
+ bool "Checkpoint/restore support" if EXPERT
+ select PROC_CHILDREN
+ default n
+ help
+ Enables additional kernel features in a sake of checkpoint/restore.
+ In particular it adds auxiliary prctl codes to setup process text,
+ data and heap segment sizes, and a few additional /proc filesystem
+ entries.
+
+ If unsure, say N here.
+
+config KALLSYMS
+ bool "Load all symbols for debugging/ksymoops" if EXPERT
+ default y
+ help
+ Say Y here to let the kernel print out symbolic crash information and
+ symbolic stack backtraces. This increases the size of the kernel
+ somewhat, as all symbols have to be loaded into the kernel image.
+
+config KALLSYMS_ALL
+ bool "Include all symbols in kallsyms"
+ depends on DEBUG_KERNEL && KALLSYMS
+ help
+ Normally kallsyms only contains the symbols of functions for nicer
+ OOPS messages and backtraces (i.e., symbols from the text and inittext
+ sections). This is sufficient for most cases. And only in very rare
+ cases (e.g., when a debugger is used) all symbols are required (e.g.,
+ names of variables from the data sections, etc).
+
+ This option makes sure that all symbols are loaded into the kernel
+ image (i.e., symbols from all sections) in cost of increased kernel
+ size (depending on the kernel configuration, it may be 300KiB or
+ something like this).
+
+ Say N unless you really need all symbols.
+
+config KALLSYMS_ABSOLUTE_PERCPU
+ bool
+ depends on KALLSYMS
+ default X86_64 && SMP
+
+config KALLSYMS_BASE_RELATIVE
+ bool
+ depends on KALLSYMS
+ default !IA64 && !(TILE && 64BIT)
+ help
+ Instead of emitting them as absolute values in the native word size,
+ emit the symbol references in the kallsyms table as 32-bit entries,
+ each containing a relative value in the range [base, base + U32_MAX]
+ or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either
+ an absolute value in the range [0, S32_MAX] or a relative value in the
+ range [base, base + S32_MAX], where base is the lowest relative symbol
+ address encountered in the image.
+
+ On 64-bit builds, this reduces the size of the address table by 50%,
+ but more importantly, it results in entries whose values are build
+ time constants, and no relocation pass is required at runtime to fix
+ up the entries based on the runtime load address of the kernel.
+
+# end of the "standard kernel features (expert users)" menu
+
+# syscall, maps, verifier
+config BPF_SYSCALL
+ bool "Enable bpf() system call"
+ select ANON_INODES
+ select BPF
+ default n
+ help
+ Enable the bpf() system call that allows to manipulate eBPF
+ programs and maps via file descriptors.
+
+config USERFAULTFD
+ bool "Enable userfaultfd() system call"
+ select ANON_INODES
+ depends on MMU
+ help
+ Enable the userfaultfd() system call that allows to intercept and
+ handle page faults in userland.
+
config EMBEDDED
bool "Embedded system"
option allnoconfig_y
diff --git a/init/initramfs.c b/init/initramfs.c
index 7046fef..7e99a00 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -109,7 +109,7 @@ static void __init free_hash(void)
}
}
-static long __init do_utime(char *filename, time_t mtime)
+static long __init do_utime(char *filename, time64_t mtime)
{
struct timespec64 t[2];
@@ -125,10 +125,10 @@ static __initdata LIST_HEAD(dir_list);
struct dir_entry {
struct list_head list;
char *name;
- time_t mtime;
+ time64_t mtime;
};
-static void __init dir_add(const char *name, time_t mtime)
+static void __init dir_add(const char *name, time64_t mtime)
{
struct dir_entry *de = kmalloc(sizeof(struct dir_entry), GFP_KERNEL);
if (!de)
@@ -150,7 +150,7 @@ static void __init dir_utime(void)
}
}
-static __initdata time_t mtime;
+static __initdata time64_t mtime;
/* cpio header parsing */
@@ -177,7 +177,7 @@ static void __init parse_header(char *s)
uid = parsed[2];
gid = parsed[3];
nlink = parsed[4];
- mtime = parsed[5];
+ mtime = parsed[5]; /* breaks in y2106 */
body_len = parsed[6];
major = parsed[7];
minor = parsed[8];
diff --git a/init/main.c b/init/main.c
index 859a786..dfec380 100644
--- a/init/main.c
+++ b/init/main.c
@@ -562,7 +562,6 @@ asmlinkage __visible void __init start_kernel(void)
* kmem_cache_init()
*/
setup_log_buf(0);
- pidhash_init();
vfs_caches_init_early();
sort_main_extable();
trap_init();
@@ -669,7 +668,7 @@ asmlinkage __visible void __init start_kernel(void)
if (late_time_init)
late_time_init();
calibrate_delay();
- pidmap_init();
+ pid_idr_init();
anon_vma_init();
#ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES))
diff --git a/init/version.c b/init/version.c
index 5606341..bfb4e3f 100644
--- a/init/version.c
+++ b/init/version.c
@@ -7,7 +7,7 @@
*/
#include <generated/compile.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/uts.h>
#include <linux/utsname.h>
#include <generated/utsrelease.h>
diff --git a/ipc/sem.c b/ipc/sem.c
index a5cff0e..87bd38f 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -515,6 +515,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
sma->sem_nsems = nsems;
sma->sem_ctime = ktime_get_real_seconds();
+ /* ipc_addid() locks sma upon success. */
retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
if (retval < 0) {
call_rcu(&sma->sem_perm.rcu, sem_rcu_free);
diff --git a/ipc/shm.c b/ipc/shm.c
index 7733d76..7acda23 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -601,6 +601,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
shp->shm_file = file;
shp->shm_creator = current;
+ /* ipc_addid() locks shp upon success. */
error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
if (error < 0)
goto no_id;
diff --git a/ipc/util.c b/ipc/util.c
index 79b30ee..ff045fe 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -116,13 +116,16 @@ int ipc_init_ids(struct ipc_ids *ids)
int err;
ids->in_use = 0;
ids->seq = 0;
- ids->next_id = -1;
init_rwsem(&ids->rwsem);
err = rhashtable_init(&ids->key_ht, &ipc_kht_params);
if (err)
return err;
idr_init(&ids->ipcs_idr);
ids->tables_initialized = true;
+ ids->max_id = -1;
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ ids->next_id = -1;
+#endif
return 0;
}
@@ -186,41 +189,51 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
return NULL;
}
-/**
- * ipc_get_maxid - get the last assigned id
- * @ids: ipc identifier set
- *
- * Called with ipc_ids.rwsem held.
+#ifdef CONFIG_CHECKPOINT_RESTORE
+/*
+ * Specify desired id for next allocated IPC object.
*/
-int ipc_get_maxid(struct ipc_ids *ids)
+#define ipc_idr_alloc(ids, new) \
+ idr_alloc(&(ids)->ipcs_idr, (new), \
+ (ids)->next_id < 0 ? 0 : ipcid_to_idx((ids)->next_id),\
+ 0, GFP_NOWAIT)
+
+static inline int ipc_buildid(int id, struct ipc_ids *ids,
+ struct kern_ipc_perm *new)
{
- struct kern_ipc_perm *ipc;
- int max_id = -1;
- int total, id;
-
- if (ids->in_use == 0)
- return -1;
-
- if (ids->in_use == IPCMNI)
- return IPCMNI - 1;
-
- /* Look for the last assigned id */
- total = 0;
- for (id = 0; id < IPCMNI && total < ids->in_use; id++) {
- ipc = idr_find(&ids->ipcs_idr, id);
- if (ipc != NULL) {
- max_id = id;
- total++;
- }
+ if (ids->next_id < 0) { /* default, behave as !CHECKPOINT_RESTORE */
+ new->seq = ids->seq++;
+ if (ids->seq > IPCID_SEQ_MAX)
+ ids->seq = 0;
+ } else {
+ new->seq = ipcid_to_seqx(ids->next_id);
+ ids->next_id = -1;
}
- return max_id;
+
+ return SEQ_MULTIPLIER * new->seq + id;
}
+#else
+#define ipc_idr_alloc(ids, new) \
+ idr_alloc(&(ids)->ipcs_idr, (new), 0, 0, GFP_NOWAIT)
+
+static inline int ipc_buildid(int id, struct ipc_ids *ids,
+ struct kern_ipc_perm *new)
+{
+ new->seq = ids->seq++;
+ if (ids->seq > IPCID_SEQ_MAX)
+ ids->seq = 0;
+
+ return SEQ_MULTIPLIER * new->seq + id;
+}
+
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
/**
* ipc_addid - add an ipc identifier
* @ids: ipc identifier set
* @new: new ipc permission set
- * @size: limit for the number of used ids
+ * @limit: limit for the number of used ids
*
* Add an entry 'new' to the ipc ids idr. The permissions object is
* initialised and the first free entry is set up and the id assigned
@@ -229,17 +242,16 @@ int ipc_get_maxid(struct ipc_ids *ids)
*
* Called with writer ipc_ids.rwsem held.
*/
-int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
+int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit)
{
kuid_t euid;
kgid_t egid;
int id, err;
- int next_id = ids->next_id;
- if (size > IPCMNI)
- size = IPCMNI;
+ if (limit > IPCMNI)
+ limit = IPCMNI;
- if (!ids->tables_initialized || ids->in_use >= size)
+ if (!ids->tables_initialized || ids->in_use >= limit)
return -ENOSPC;
idr_preload(GFP_KERNEL);
@@ -254,9 +266,7 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
new->cuid = new->uid = euid;
new->gid = new->cgid = egid;
- id = idr_alloc(&ids->ipcs_idr, new,
- (next_id < 0) ? 0 : ipcid_to_idx(next_id), 0,
- GFP_NOWAIT);
+ id = ipc_idr_alloc(ids, new);
idr_preload_end();
if (id >= 0 && new->key != IPC_PRIVATE) {
@@ -274,17 +284,11 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
}
ids->in_use++;
+ if (id > ids->max_id)
+ ids->max_id = id;
- if (next_id < 0) {
- new->seq = ids->seq++;
- if (ids->seq > IPCID_SEQ_MAX)
- ids->seq = 0;
- } else {
- new->seq = ipcid_to_seqx(next_id);
- ids->next_id = -1;
- }
+ new->id = ipc_buildid(id, ids, new);
- new->id = ipc_buildid(id, new->seq);
return id;
}
@@ -429,6 +433,15 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
ipc_kht_remove(ids, ipcp);
ids->in_use--;
ipcp->deleted = true;
+
+ if (unlikely(lid == ids->max_id)) {
+ do {
+ lid--;
+ if (lid == -1)
+ break;
+ } while (!idr_find(&ids->ipcs_idr, lid));
+ ids->max_id = lid;
+ }
}
/**
diff --git a/ipc/util.h b/ipc/util.h
index 579112d..89b8ec1 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -13,6 +13,7 @@
#include <linux/unistd.h>
#include <linux/err.h>
+#include <linux/ipc_namespace.h>
#define SEQ_MULTIPLIER (IPCMNI)
@@ -99,9 +100,6 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
/* must be called with ids->rwsem acquired for writing */
int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
-/* must be called with ids->rwsem acquired for reading */
-int ipc_get_maxid(struct ipc_ids *);
-
/* must be called with both locks acquired. */
void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *);
@@ -111,6 +109,23 @@ void ipc_set_key_private(struct ipc_ids *, struct kern_ipc_perm *);
/* must be called with ipcp locked */
int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg);
+/**
+ * ipc_get_maxid - get the last assigned id
+ * @ids: ipc identifier set
+ *
+ * Called with ipc_ids.rwsem held for reading.
+ */
+static inline int ipc_get_maxid(struct ipc_ids *ids)
+{
+ if (ids->in_use == 0)
+ return -1;
+
+ if (ids->in_use == IPCMNI)
+ return IPCMNI - 1;
+
+ return ids->max_id;
+}
+
/*
* For allocation that need to be freed by RCU.
* Objects are reference counted, they start with reference count 1.
@@ -146,11 +161,6 @@ extern struct msg_msg *load_msg(const void __user *src, size_t len);
extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len);
-static inline int ipc_buildid(int id, int seq)
-{
- return SEQ_MULTIPLIER * seq + id;
-}
-
static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid)
{
return uid / SEQ_MULTIPLIER != ipcp->seq;
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 6db80fc..b366389 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -108,7 +108,8 @@ static int __init parse_crashkernel_mem(char *cmdline,
return -EINVAL;
}
}
- }
+ } else
+ pr_info("crashkernel size resulted in zero bytes\n");
return 0;
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 4e55eed..432eadf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1871,7 +1871,7 @@ static __latent_entropy struct task_struct *copy_process(
retval = -ERESTARTNOINTR;
goto bad_fork_cancel_cgroup;
}
- if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
retval = -ENOMEM;
goto bad_fork_cancel_cgroup;
}
diff --git a/kernel/kcov.c b/kernel/kcov.c
index fc6af9e..15f33fa 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -22,13 +22,21 @@
#include <linux/kcov.h>
#include <asm/setup.h>
+/* Number of 64-bit words written per one comparison: */
+#define KCOV_WORDS_PER_CMP 4
+
/*
* kcov descriptor (one per opened debugfs file).
* State transitions of the descriptor:
* - initial state after open()
* - then there must be a single ioctl(KCOV_INIT_TRACE) call
* - then, mmap() call (several calls are allowed but not useful)
- * - then, repeated enable/disable for a task (only one task a time allowed)
+ * - then, ioctl(KCOV_ENABLE, arg), where arg is
+ * KCOV_TRACE_PC - to trace only the PCs
+ * or
+ * KCOV_TRACE_CMP - to trace only the comparison operands
+ * - then, ioctl(KCOV_DISABLE) to disable the task.
+ * Enabling/disabling ioctls can be repeated (only one task a time allowed).
*/
struct kcov {
/*
@@ -48,6 +56,36 @@ struct kcov {
struct task_struct *t;
};
+static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
+{
+ enum kcov_mode mode;
+
+ /*
+ * We are interested in code coverage as a function of a syscall inputs,
+ * so we ignore code executed in interrupts.
+ */
+ if (!in_task())
+ return false;
+ mode = READ_ONCE(t->kcov_mode);
+ /*
+ * There is some code that runs in interrupts but for which
+ * in_interrupt() returns false (e.g. preempt_schedule_irq()).
+ * READ_ONCE()/barrier() effectively provides load-acquire wrt
+ * interrupts, there are paired barrier()/WRITE_ONCE() in
+ * kcov_ioctl_locked().
+ */
+ barrier();
+ return mode == needed_mode;
+}
+
+static unsigned long canonicalize_ip(unsigned long ip)
+{
+#ifdef CONFIG_RANDOMIZE_BASE
+ ip -= kaslr_offset();
+#endif
+ return ip;
+}
+
/*
* Entry point from instrumented code.
* This is called once per basic-block/edge.
@@ -55,44 +93,139 @@ struct kcov {
void notrace __sanitizer_cov_trace_pc(void)
{
struct task_struct *t;
- enum kcov_mode mode;
+ unsigned long *area;
+ unsigned long ip = canonicalize_ip(_RET_IP_);
+ unsigned long pos;
t = current;
- /*
- * We are interested in code coverage as a function of a syscall inputs,
- * so we ignore code executed in interrupts.
- */
- if (!t || !in_task())
+ if (!check_kcov_mode(KCOV_MODE_TRACE_PC, t))
return;
- mode = READ_ONCE(t->kcov_mode);
- if (mode == KCOV_MODE_TRACE) {
- unsigned long *area;
- unsigned long pos;
- unsigned long ip = _RET_IP_;
-#ifdef CONFIG_RANDOMIZE_BASE
- ip -= kaslr_offset();
-#endif
-
- /*
- * There is some code that runs in interrupts but for which
- * in_interrupt() returns false (e.g. preempt_schedule_irq()).
- * READ_ONCE()/barrier() effectively provides load-acquire wrt
- * interrupts, there are paired barrier()/WRITE_ONCE() in
- * kcov_ioctl_locked().
- */
- barrier();
- area = t->kcov_area;
- /* The first word is number of subsequent PCs. */
- pos = READ_ONCE(area[0]) + 1;
- if (likely(pos < t->kcov_size)) {
- area[pos] = ip;
- WRITE_ONCE(area[0], pos);
- }
+ area = t->kcov_area;
+ /* The first 64-bit word is the number of subsequent PCs. */
+ pos = READ_ONCE(area[0]) + 1;
+ if (likely(pos < t->kcov_size)) {
+ area[pos] = ip;
+ WRITE_ONCE(area[0], pos);
}
}
EXPORT_SYMBOL(__sanitizer_cov_trace_pc);
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+static void write_comp_data(u64 type, u64 arg1, u64 arg2, u64 ip)
+{
+ struct task_struct *t;
+ u64 *area;
+ u64 count, start_index, end_pos, max_pos;
+
+ t = current;
+ if (!check_kcov_mode(KCOV_MODE_TRACE_CMP, t))
+ return;
+
+ ip = canonicalize_ip(ip);
+
+ /*
+ * We write all comparison arguments and types as u64.
+ * The buffer was allocated for t->kcov_size unsigned longs.
+ */
+ area = (u64 *)t->kcov_area;
+ max_pos = t->kcov_size * sizeof(unsigned long);
+
+ count = READ_ONCE(area[0]);
+
+ /* Every record is KCOV_WORDS_PER_CMP 64-bit words. */
+ start_index = 1 + count * KCOV_WORDS_PER_CMP;
+ end_pos = (start_index + KCOV_WORDS_PER_CMP) * sizeof(u64);
+ if (likely(end_pos <= max_pos)) {
+ area[start_index] = type;
+ area[start_index + 1] = arg1;
+ area[start_index + 2] = arg2;
+ area[start_index + 3] = ip;
+ WRITE_ONCE(area[0], count + 1);
+ }
+}
+
+void notrace __sanitizer_cov_trace_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp1);
+
+void notrace __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp2);
+
+void notrace __sanitizer_cov_trace_cmp4(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp4);
+
+void notrace __sanitizer_cov_trace_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp8);
+
+void notrace __sanitizer_cov_trace_const_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp1);
+
+void notrace __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp2);
+
+void notrace __sanitizer_cov_trace_const_cmp4(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp4);
+
+void notrace __sanitizer_cov_trace_const_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp8);
+
+void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases)
+{
+ u64 i;
+ u64 count = cases[0];
+ u64 size = cases[1];
+ u64 type = KCOV_CMP_CONST;
+
+ switch (size) {
+ case 8:
+ type |= KCOV_CMP_SIZE(0);
+ break;
+ case 16:
+ type |= KCOV_CMP_SIZE(1);
+ break;
+ case 32:
+ type |= KCOV_CMP_SIZE(2);
+ break;
+ case 64:
+ type |= KCOV_CMP_SIZE(3);
+ break;
+ default:
+ return;
+ }
+ for (i = 0; i < count; i++)
+ write_comp_data(type, cases[i + 2], val, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_switch);
+#endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */
+
static void kcov_get(struct kcov *kcov)
{
atomic_inc(&kcov->refcount);
@@ -129,6 +262,7 @@ void kcov_task_exit(struct task_struct *t)
/* Just to not leave dangling references behind. */
kcov_task_init(t);
kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
spin_unlock(&kcov->lock);
kcov_put(kcov);
}
@@ -147,7 +281,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
spin_lock(&kcov->lock);
size = kcov->size * sizeof(unsigned long);
- if (kcov->mode == KCOV_MODE_DISABLED || vma->vm_pgoff != 0 ||
+ if (kcov->mode != KCOV_MODE_INIT || vma->vm_pgoff != 0 ||
vma->vm_end - vma->vm_start != size) {
res = -EINVAL;
goto exit;
@@ -176,6 +310,7 @@ static int kcov_open(struct inode *inode, struct file *filep)
kcov = kzalloc(sizeof(*kcov), GFP_KERNEL);
if (!kcov)
return -ENOMEM;
+ kcov->mode = KCOV_MODE_DISABLED;
atomic_set(&kcov->refcount, 1);
spin_lock_init(&kcov->lock);
filep->private_data = kcov;
@@ -211,7 +346,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
if (size < 2 || size > INT_MAX / sizeof(unsigned long))
return -EINVAL;
kcov->size = size;
- kcov->mode = KCOV_MODE_TRACE;
+ kcov->mode = KCOV_MODE_INIT;
return 0;
case KCOV_ENABLE:
/*
@@ -221,17 +356,25 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
* at task exit or voluntary by KCOV_DISABLE. After that it can
* be enabled for another task.
*/
- unused = arg;
- if (unused != 0 || kcov->mode == KCOV_MODE_DISABLED ||
- kcov->area == NULL)
+ if (kcov->mode != KCOV_MODE_INIT || !kcov->area)
return -EINVAL;
if (kcov->t != NULL)
return -EBUSY;
+ if (arg == KCOV_TRACE_PC)
+ kcov->mode = KCOV_MODE_TRACE_PC;
+ else if (arg == KCOV_TRACE_CMP)
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+ kcov->mode = KCOV_MODE_TRACE_CMP;
+#else
+ return -ENOTSUPP;
+#endif
+ else
+ return -EINVAL;
t = current;
/* Cache in task struct for performance. */
t->kcov_size = kcov->size;
t->kcov_area = kcov->area;
- /* See comment in __sanitizer_cov_trace_pc(). */
+ /* See comment in check_kcov_mode(). */
barrier();
WRITE_ONCE(t->kcov_mode, kcov->mode);
t->kcov = kcov;
@@ -249,6 +392,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
return -EINVAL;
kcov_task_init(t);
kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
kcov_put(kcov);
return 0;
default:
diff --git a/kernel/panic.c b/kernel/panic.c
index bdd18af..2cfef40 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -27,6 +27,8 @@
#include <linux/console.h>
#include <linux/bug.h>
#include <linux/ratelimit.h>
+#include <linux/debugfs.h>
+#include <asm/sections.h>
#define PANIC_TIMER_STEP 100
#define PANIC_BLINK_SPD 18
@@ -322,6 +324,7 @@ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = {
{ 'E', ' ', true }, /* TAINT_UNSIGNED_MODULE */
{ 'L', ' ', false }, /* TAINT_SOFTLOCKUP */
{ 'K', ' ', true }, /* TAINT_LIVEPATCH */
+ { 'X', ' ', true }, /* TAINT_AUX */
};
/**
@@ -343,6 +346,7 @@ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = {
* 'E' - Unsigned module has been loaded.
* 'L' - A soft lockup has previously occurred.
* 'K' - Kernel has been live patched.
+ * 'X' - Auxiliary taint, for distros' use.
*
* The string is overwritten by the next call to print_tainted().
*/
@@ -518,7 +522,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
{
disable_trace_on_warning();
- pr_warn("------------[ cut here ]------------\n");
+ if (args)
+ pr_warn(CUT_HERE);
if (file)
pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
@@ -582,9 +587,49 @@ EXPORT_SYMBOL(warn_slowpath_fmt_taint);
void warn_slowpath_null(const char *file, int line)
{
+ pr_warn(CUT_HERE);
__warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, NULL);
}
EXPORT_SYMBOL(warn_slowpath_null);
+#else
+void __warn_printk(const char *fmt, ...)
+{
+ va_list args;
+
+ pr_warn(CUT_HERE);
+
+ va_start(args, fmt);
+ vprintk(fmt, args);
+ va_end(args);
+}
+EXPORT_SYMBOL(__warn_printk);
+#endif
+
+#ifdef CONFIG_BUG
+
+/* Support resetting WARN*_ONCE state */
+
+static int clear_warn_once_set(void *data, u64 val)
+{
+ generic_bug_clear_once();
+ memset(__start_once, 0, __end_once - __start_once);
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(clear_warn_once_fops,
+ NULL,
+ clear_warn_once_set,
+ "%lld\n");
+
+static __init int register_warn_debugfs(void)
+{
+ /* Don't care about failure */
+ debugfs_create_file("clear_warn_once", 0200, NULL,
+ NULL, &clear_warn_once_fops);
+ return 0;
+}
+
+device_initcall(register_warn_debugfs);
#endif
#ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/kernel/pid.c b/kernel/pid.c
index 020dedb..b13b624 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -39,11 +39,8 @@
#include <linux/proc_ns.h>
#include <linux/proc_fs.h>
#include <linux/sched/task.h>
+#include <linux/idr.h>
-#define pid_hashfn(nr, ns) \
- hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
-static struct hlist_head *pid_hash;
-static unsigned int pidhash_shift = 4;
struct pid init_struct_pid = INIT_STRUCT_PID;
int pid_max = PID_MAX_DEFAULT;
@@ -53,15 +50,6 @@ int pid_max = PID_MAX_DEFAULT;
int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;
-static inline int mk_pid(struct pid_namespace *pid_ns,
- struct pidmap *map, int off)
-{
- return (map - pid_ns->pidmap)*BITS_PER_PAGE + off;
-}
-
-#define find_next_offset(map, off) \
- find_next_zero_bit((map)->page, BITS_PER_PAGE, off)
-
/*
* PID-map pages start out as NULL, they get allocated upon
* first use and are never deallocated. This way a low pid_max
@@ -70,11 +58,8 @@ static inline int mk_pid(struct pid_namespace *pid_ns,
*/
struct pid_namespace init_pid_ns = {
.kref = KREF_INIT(2),
- .pidmap = {
- [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
- },
- .last_pid = 0,
- .nr_hashed = PIDNS_HASH_ADDING,
+ .idr = IDR_INIT,
+ .pid_allocated = PIDNS_ADDING,
.level = 0,
.child_reaper = &init_task,
.user_ns = &init_user_ns,
@@ -101,138 +86,6 @@ EXPORT_SYMBOL_GPL(init_pid_ns);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
-static void free_pidmap(struct upid *upid)
-{
- int nr = upid->nr;
- struct pidmap *map = upid->ns->pidmap + nr / BITS_PER_PAGE;
- int offset = nr & BITS_PER_PAGE_MASK;
-
- clear_bit(offset, map->page);
- atomic_inc(&map->nr_free);
-}
-
-/*
- * If we started walking pids at 'base', is 'a' seen before 'b'?
- */
-static int pid_before(int base, int a, int b)
-{
- /*
- * This is the same as saying
- *
- * (a - base + MAXUINT) % MAXUINT < (b - base + MAXUINT) % MAXUINT
- * and that mapping orders 'a' and 'b' with respect to 'base'.
- */
- return (unsigned)(a - base) < (unsigned)(b - base);
-}
-
-/*
- * We might be racing with someone else trying to set pid_ns->last_pid
- * at the pid allocation time (there's also a sysctl for this, but racing
- * with this one is OK, see comment in kernel/pid_namespace.c about it).
- * We want the winner to have the "later" value, because if the
- * "earlier" value prevails, then a pid may get reused immediately.
- *
- * Since pids rollover, it is not sufficient to just pick the bigger
- * value. We have to consider where we started counting from.
- *
- * 'base' is the value of pid_ns->last_pid that we observed when
- * we started looking for a pid.
- *
- * 'pid' is the pid that we eventually found.
- */
-static void set_last_pid(struct pid_namespace *pid_ns, int base, int pid)
-{
- int prev;
- int last_write = base;
- do {
- prev = last_write;
- last_write = cmpxchg(&pid_ns->last_pid, prev, pid);
- } while ((prev != last_write) && (pid_before(base, last_write, pid)));
-}
-
-static int alloc_pidmap(struct pid_namespace *pid_ns)
-{
- int i, offset, max_scan, pid, last = pid_ns->last_pid;
- struct pidmap *map;
-
- pid = last + 1;
- if (pid >= pid_max)
- pid = RESERVED_PIDS;
- offset = pid & BITS_PER_PAGE_MASK;
- map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
- /*
- * If last_pid points into the middle of the map->page we
- * want to scan this bitmap block twice, the second time
- * we start with offset == 0 (or RESERVED_PIDS).
- */
- max_scan = DIV_ROUND_UP(pid_max, BITS_PER_PAGE) - !offset;
- for (i = 0; i <= max_scan; ++i) {
- if (unlikely(!map->page)) {
- void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
- /*
- * Free the page if someone raced with us
- * installing it:
- */
- spin_lock_irq(&pidmap_lock);
- if (!map->page) {
- map->page = page;
- page = NULL;
- }
- spin_unlock_irq(&pidmap_lock);
- kfree(page);
- if (unlikely(!map->page))
- return -ENOMEM;
- }
- if (likely(atomic_read(&map->nr_free))) {
- for ( ; ; ) {
- if (!test_and_set_bit(offset, map->page)) {
- atomic_dec(&map->nr_free);
- set_last_pid(pid_ns, last, pid);
- return pid;
- }
- offset = find_next_offset(map, offset);
- if (offset >= BITS_PER_PAGE)
- break;
- pid = mk_pid(pid_ns, map, offset);
- if (pid >= pid_max)
- break;
- }
- }
- if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
- ++map;
- offset = 0;
- } else {
- map = &pid_ns->pidmap[0];
- offset = RESERVED_PIDS;
- if (unlikely(last == offset))
- break;
- }
- pid = mk_pid(pid_ns, map, offset);
- }
- return -EAGAIN;
-}
-
-int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
-{
- int offset;
- struct pidmap *map, *end;
-
- if (last >= PID_MAX_LIMIT)
- return -1;
-
- offset = (last + 1) & BITS_PER_PAGE_MASK;
- map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE];
- end = &pid_ns->pidmap[PIDMAP_ENTRIES];
- for (; map < end; map++, offset = 0) {
- if (unlikely(!map->page))
- continue;
- offset = find_next_bit((map)->page, BITS_PER_PAGE, offset);
- if (offset < BITS_PER_PAGE)
- return mk_pid(pid_ns, map, offset);
- }
- return -1;
-}
-
void put_pid(struct pid *pid)
{
struct pid_namespace *ns;
@@ -265,8 +118,7 @@ void free_pid(struct pid *pid)
for (i = 0; i <= pid->level; i++) {
struct upid *upid = pid->numbers + i;
struct pid_namespace *ns = upid->ns;
- hlist_del_rcu(&upid->pid_chain);
- switch(--ns->nr_hashed) {
+ switch (--ns->pid_allocated) {
case 2:
case 1:
/* When all that is left in the pid namespace
@@ -275,21 +127,20 @@ void free_pid(struct pid *pid)
*/
wake_up_process(ns->child_reaper);
break;
- case PIDNS_HASH_ADDING:
+ case PIDNS_ADDING:
/* Handle a fork failure of the first process */
WARN_ON(ns->child_reaper);
- ns->nr_hashed = 0;
+ ns->pid_allocated = 0;
/* fall through */
case 0:
schedule_work(&ns->proc_work);
break;
}
+
+ idr_remove(&ns->idr, upid->nr);
}
spin_unlock_irqrestore(&pidmap_lock, flags);
- for (i = 0; i <= pid->level; i++)
- free_pidmap(pid->numbers + i);
-
call_rcu(&pid->rcu, delayed_put_pid);
}
@@ -308,8 +159,29 @@ struct pid *alloc_pid(struct pid_namespace *ns)
tmp = ns;
pid->level = ns->level;
+
for (i = ns->level; i >= 0; i--) {
- nr = alloc_pidmap(tmp);
+ int pid_min = 1;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock_irq(&pidmap_lock);
+
+ /*
+ * init really needs pid 1, but after reaching the maximum
+ * wrap back to RESERVED_PIDS
+ */
+ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
+ pid_min = RESERVED_PIDS;
+
+ /*
+ * Store a null pointer so find_pid_ns does not find
+ * a partially initialized PID (see below).
+ */
+ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
+ pid_max, GFP_ATOMIC);
+ spin_unlock_irq(&pidmap_lock);
+ idr_preload_end();
+
if (nr < 0) {
retval = nr;
goto out_free;
@@ -334,12 +206,12 @@ struct pid *alloc_pid(struct pid_namespace *ns)
upid = pid->numbers + ns->level;
spin_lock_irq(&pidmap_lock);
- if (!(ns->nr_hashed & PIDNS_HASH_ADDING))
+ if (!(ns->pid_allocated & PIDNS_ADDING))
goto out_unlock;
for ( ; upid >= pid->numbers; --upid) {
- hlist_add_head_rcu(&upid->pid_chain,
- &pid_hash[pid_hashfn(upid->nr, upid->ns)]);
- upid->ns->nr_hashed++;
+ /* Make the PID visible to find_pid_ns. */
+ idr_replace(&upid->ns->idr, pid, upid->nr);
+ upid->ns->pid_allocated++;
}
spin_unlock_irq(&pidmap_lock);
@@ -350,8 +222,11 @@ struct pid *alloc_pid(struct pid_namespace *ns)
put_pid_ns(ns);
out_free:
+ spin_lock_irq(&pidmap_lock);
while (++i <= ns->level)
- free_pidmap(pid->numbers + i);
+ idr_remove(&ns->idr, (pid->numbers + i)->nr);
+
+ spin_unlock_irq(&pidmap_lock);
kmem_cache_free(ns->pid_cachep, pid);
return ERR_PTR(retval);
@@ -360,21 +235,13 @@ struct pid *alloc_pid(struct pid_namespace *ns)
void disable_pid_allocation(struct pid_namespace *ns)
{
spin_lock_irq(&pidmap_lock);
- ns->nr_hashed &= ~PIDNS_HASH_ADDING;
+ ns->pid_allocated &= ~PIDNS_ADDING;
spin_unlock_irq(&pidmap_lock);
}
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
- struct upid *pnr;
-
- hlist_for_each_entry_rcu(pnr,
- &pid_hash[pid_hashfn(nr, ns)], pid_chain)
- if (pnr->nr == nr && pnr->ns == ns)
- return container_of(pnr, struct pid,
- numbers[ns->level]);
-
- return NULL;
+ return idr_find(&ns->idr, nr);
}
EXPORT_SYMBOL_GPL(find_pid_ns);
@@ -530,6 +397,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
if (type != PIDTYPE_PID) {
if (type == __PIDTYPE_TGID)
type = PIDTYPE_PID;
+
task = task->group_leader;
}
nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
@@ -553,35 +421,13 @@ EXPORT_SYMBOL_GPL(task_active_pid_ns);
*/
struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
- struct pid *pid;
-
- do {
- pid = find_pid_ns(nr, ns);
- if (pid)
- break;
- nr = next_pidmap(ns, nr);
- } while (nr > 0);
-
- return pid;
+ return idr_get_next(&ns->idr, &nr);
}
-/*
- * The pid hash table is scaled according to the amount of memory in the
- * machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or
- * more.
- */
-void __init pidhash_init(void)
-{
- pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
- HASH_EARLY | HASH_SMALL | HASH_ZERO,
- &pidhash_shift, NULL,
- 0, 4096);
-}
-
-void __init pidmap_init(void)
+void __init pid_idr_init(void)
{
/* Verify no one has done anything silly: */
- BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
+ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING);
/* bump default and minimum pid_max based on number of cpus */
pid_max = min(pid_max_max, max_t(int, pid_max,
@@ -590,10 +436,7 @@ void __init pidmap_init(void)
PIDS_PER_CPU_MIN * num_possible_cpus());
pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);
- init_pid_ns.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
- /* Reserve PID 0. We never call free_pidmap(0) */
- set_bit(0, init_pid_ns.pidmap[0].page);
- atomic_dec(&init_pid_ns.pidmap[0].nr_free);
+ idr_init(&init_pid_ns.idr);
init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 4918314..0b53eef 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -21,6 +21,7 @@
#include <linux/export.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
+#include <linux/idr.h>
struct pid_cache {
int nr_ids;
@@ -98,7 +99,6 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
struct pid_namespace *ns;
unsigned int level = parent_pid_ns->level + 1;
struct ucounts *ucounts;
- int i;
int err;
err = -EINVAL;
@@ -117,17 +117,15 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
if (ns == NULL)
goto out_dec;
- ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
- if (!ns->pidmap[0].page)
- goto out_free;
+ idr_init(&ns->idr);
ns->pid_cachep = create_pid_cachep(level + 1);
if (ns->pid_cachep == NULL)
- goto out_free_map;
+ goto out_free_idr;
err = ns_alloc_inum(&ns->ns);
if (err)
- goto out_free_map;
+ goto out_free_idr;
ns->ns.ops = &pidns_operations;
kref_init(&ns->kref);
@@ -135,20 +133,13 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
ns->parent = get_pid_ns(parent_pid_ns);
ns->user_ns = get_user_ns(user_ns);
ns->ucounts = ucounts;
- ns->nr_hashed = PIDNS_HASH_ADDING;
+ ns->pid_allocated = PIDNS_ADDING;
INIT_WORK(&ns->proc_work, proc_cleanup_work);
- set_bit(0, ns->pidmap[0].page);
- atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
-
- for (i = 1; i < PIDMAP_ENTRIES; i++)
- atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
-
return ns;
-out_free_map:
- kfree(ns->pidmap[0].page);
-out_free:
+out_free_idr:
+ idr_destroy(&ns->idr);
kmem_cache_free(pid_ns_cachep, ns);
out_dec:
dec_pid_namespaces(ucounts);
@@ -168,11 +159,9 @@ static void delayed_free_pidns(struct rcu_head *p)
static void destroy_pid_namespace(struct pid_namespace *ns)
{
- int i;
-
ns_free_inum(&ns->ns);
- for (i = 0; i < PIDMAP_ENTRIES; i++)
- kfree(ns->pidmap[i].page);
+
+ idr_destroy(&ns->idr);
call_rcu(&ns->rcu, delayed_free_pidns);
}
@@ -213,6 +202,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
int rc;
struct task_struct *task, *me = current;
int init_pids = thread_group_leader(me) ? 1 : 2;
+ struct pid *pid;
/* Don't allow any more processes into the pid namespace */
disable_pid_allocation(pid_ns);
@@ -239,20 +229,16 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
* maintain a tasklist for each pid namespace.
*
*/
+ rcu_read_lock();
read_lock(&tasklist_lock);
- nr = next_pidmap(pid_ns, 1);
- while (nr > 0) {
- rcu_read_lock();
-
- task = pid_task(find_vpid(nr), PIDTYPE_PID);
+ nr = 2;
+ idr_for_each_entry_continue(&pid_ns->idr, pid, nr) {
+ task = pid_task(pid, PIDTYPE_PID);
if (task && !__fatal_signal_pending(task))
send_sig_info(SIGKILL, SEND_SIG_FORCED, task);
-
- rcu_read_unlock();
-
- nr = next_pidmap(pid_ns, nr);
}
read_unlock(&tasklist_lock);
+ rcu_read_unlock();
/*
* Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
@@ -268,7 +254,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
* sys_wait4() above can't reap the EXIT_DEAD children but we do not
* really care, we could reparent them to the global init. We could
* exit and reap ->child_reaper even if it is not the last thread in
- * this pid_ns, free_pid(nr_hashed == 0) calls proc_cleanup_work(),
+ * this pid_ns, free_pid(pid_allocated == 0) calls proc_cleanup_work(),
* pid_ns can not go away until proc_kill_sb() drops the reference.
*
* But this ns can also have other tasks injected by setns()+fork().
@@ -282,7 +268,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
*/
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
- if (pid_ns->nr_hashed == init_pids)
+ if (pid_ns->pid_allocated == init_pids)
break;
schedule();
}
@@ -301,6 +287,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
{
struct pid_namespace *pid_ns = task_active_pid_ns(current);
struct ctl_table tmp = *table;
+ int ret, next;
if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
@@ -311,8 +298,14 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
* it should synchronize its usage with external means.
*/
- tmp.data = &pid_ns->last_pid;
- return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ next = idr_get_cursor(&pid_ns->idr) - 1;
+
+ tmp.data = &next;
+ ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ if (!ret && write)
+ idr_set_cursor(&pid_ns->idr, next + 1);
+
+ return ret;
}
extern int pid_max;
diff --git a/kernel/reboot.c b/kernel/reboot.c
index bd30a97..e4ced88 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,6 +104,33 @@ int unregister_reboot_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_reboot_notifier);
+static void devm_unregister_reboot_notifier(struct device *dev, void *res)
+{
+ WARN_ON(unregister_reboot_notifier(*(struct notifier_block **)res));
+}
+
+int devm_register_reboot_notifier(struct device *dev, struct notifier_block *nb)
+{
+ struct notifier_block **rcnb;
+ int ret;
+
+ rcnb = devres_alloc(devm_unregister_reboot_notifier,
+ sizeof(*rcnb), GFP_KERNEL);
+ if (!rcnb)
+ return -ENOMEM;
+
+ ret = register_reboot_notifier(nb);
+ if (!ret) {
+ *rcnb = nb;
+ devres_add(dev, rcnb);
+ } else {
+ devres_free(rcnb);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(devm_register_reboot_notifier);
+
/*
* Notifier list for kernel code which wants to be called
* to restart the system.
diff --git a/kernel/signal.c b/kernel/signal.c
index babb36d..9558664 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -78,7 +78,7 @@ static int sig_task_ignored(struct task_struct *t, int sig, bool force)
handler = sig_handler(t, sig);
if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) &&
- handler == SIG_DFL && !force)
+ handler == SIG_DFL && !(force && sig_kernel_only(sig)))
return 1;
return sig_handler_ignored(handler, sig);
@@ -94,13 +94,15 @@ static int sig_ignored(struct task_struct *t, int sig, bool force)
if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
return 0;
- if (!sig_task_ignored(t, sig, force))
+ /*
+ * Tracers may want to know about even ignored signal unless it
+ * is SIGKILL which can't be reported anyway but can be ignored
+ * by SIGNAL_UNKILLABLE task.
+ */
+ if (t->ptrace && sig != SIGKILL)
return 0;
- /*
- * Tracers may want to know about even ignored signals.
- */
- return !t->ptrace;
+ return sig_task_ignored(t, sig, force);
}
/*
@@ -929,9 +931,9 @@ static void complete_signal(int sig, struct task_struct *p, int group)
* then start taking the whole group down immediately.
*/
if (sig_fatal(p, sig) &&
- !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
+ !(signal->flags & SIGNAL_GROUP_EXIT) &&
!sigismember(&t->real_blocked, sig) &&
- (sig == SIGKILL || !t->ptrace)) {
+ (sig == SIGKILL || !p->ptrace)) {
/*
* This signal will be fatal to the whole group.
*/
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4a13a38..557d467 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -66,6 +66,7 @@
#include <linux/kexec.h>
#include <linux/bpf.h>
#include <linux/mount.h>
+#include <linux/pipe_fs_i.h>
#include <linux/uaccess.h>
#include <asm/processor.h>
@@ -1816,7 +1817,7 @@ static struct ctl_table fs_table[] = {
{
.procname = "pipe-max-size",
.data = &pipe_max_size,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(pipe_max_size),
.mode = 0644,
.proc_handler = &pipe_proc_fn,
.extra1 = &pipe_min_size,
@@ -2575,12 +2576,13 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
if (write) {
unsigned int val = *lvalp;
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
+
if ((param->min && *param->min > val) ||
(param->max && *param->max < val))
return -ERANGE;
- if (*lvalp > UINT_MAX)
- return -EINVAL;
*valp = val;
} else {
unsigned int val = *valp;
@@ -2620,6 +2622,48 @@ int proc_douintvec_minmax(struct ctl_table *table, int write,
do_proc_douintvec_minmax_conv, ¶m);
}
+struct do_proc_dopipe_max_size_conv_param {
+ unsigned int *min;
+};
+
+static int do_proc_dopipe_max_size_conv(unsigned long *lvalp,
+ unsigned int *valp,
+ int write, void *data)
+{
+ struct do_proc_dopipe_max_size_conv_param *param = data;
+
+ if (write) {
+ unsigned int val;
+
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
+
+ val = round_pipe_size(*lvalp);
+ if (val == 0)
+ return -EINVAL;
+
+ if (param->min && *param->min > val)
+ return -ERANGE;
+
+ *valp = val;
+ } else {
+ unsigned int val = *valp;
+ *lvalp = (unsigned long) val;
+ }
+
+ return 0;
+}
+
+int proc_dopipe_max_size(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct do_proc_dopipe_max_size_conv_param param = {
+ .min = (unsigned int *) table->extra1,
+ };
+ return do_proc_douintvec(table, write, buffer, lenp, ppos,
+ do_proc_dopipe_max_size_conv, ¶m);
+}
+
static void validate_coredump_safety(void)
{
#ifdef CONFIG_COREDUMP
@@ -3083,14 +3127,12 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
else
bitmap_copy(bitmap, tmp_bitmap, bitmap_len);
}
- kfree(tmp_bitmap);
*lenp -= left;
*ppos += *lenp;
- return 0;
- } else {
- kfree(tmp_bitmap);
- return err;
}
+
+ kfree(tmp_bitmap);
+ return err;
}
#else /* CONFIG_PROC_SYSCTL */
@@ -3125,6 +3167,12 @@ int proc_douintvec_minmax(struct ctl_table *table, int write,
return -ENOSYS;
}
+int proc_dopipe_max_size(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+
int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -3168,6 +3216,7 @@ EXPORT_SYMBOL(proc_douintvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
EXPORT_SYMBOL(proc_dointvec_minmax);
EXPORT_SYMBOL_GPL(proc_douintvec_minmax);
+EXPORT_SYMBOL_GPL(proc_dopipe_max_size);
EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
EXPORT_SYMBOL(proc_dostring);
diff --git a/kernel/umh.c b/kernel/umh.c
index 6ff9905..18e5fa4 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -537,14 +537,14 @@ static int proc_cap_handler(struct ctl_table *table, int write,
/*
* Drop everything not in the new_cap (but don't add things)
*/
- spin_lock(&umh_sysctl_lock);
if (write) {
+ spin_lock(&umh_sysctl_lock);
if (table->data == CAP_BSET)
usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap);
if (table->data == CAP_PI)
usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap);
+ spin_unlock(&umh_sysctl_lock);
}
- spin_unlock(&umh_sysctl_lock);
return 0;
}
diff --git a/lib/Kconfig b/lib/Kconfig
index a2b6745..368972f 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -584,7 +584,7 @@
tristate
config STRING_SELFTEST
- bool "Test string functions"
+ tristate "Test string functions"
endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8ffd891..947d3e2 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -756,6 +756,16 @@
For more details, see Documentation/dev-tools/kcov.rst.
+config KCOV_ENABLE_COMPARISONS
+ bool "Enable comparison operands collection by KCOV"
+ depends on KCOV
+ default n
+ help
+ KCOV also exposes operands of every comparison in the instrumented
+ code along with operand sizes and PCs of the comparison instructions.
+ These operands can be used by fuzzing engines to improve the quality
+ of fuzzing coverage.
+
config KCOV_INSTRUMENT_ALL
bool "Instrument all code by default"
depends on KCOV
@@ -1850,6 +1860,15 @@
If unsure, say N.
+config TEST_FIND_BIT
+ tristate "Test find_bit functions"
+ default n
+ help
+ This builds the "test_find_bit" module that measure find_*_bit()
+ functions performance.
+
+ If unsure, say N.
+
config TEST_FIRMWARE
tristate "Test firmware loading via userspace interface"
default n
diff --git a/lib/Makefile b/lib/Makefile
index 136a0b2..d11c48e 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -40,12 +40,14 @@
bsearch.o find_bit.o llist.o memweight.o kfifo.o \
percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \
once.o refcount.o usercopy.o errseq.o
+obj-$(CONFIG_STRING_SELFTEST) += test_string.o
obj-y += string_helpers.o
obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
obj-y += hexdump.o
obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
obj-y += kstrtox.o
obj-$(CONFIG_TEST_BPF) += test_bpf.o
+obj-$(CONFIG_TEST_FIND_BIT) += test_find_bit.o
obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o
diff --git a/lib/bug.c b/lib/bug.c
index 1e09440..c1b0fad 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -186,7 +186,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
return BUG_TRAP_TYPE_WARN;
}
- printk(KERN_DEFAULT "------------[ cut here ]------------\n");
+ printk(KERN_DEFAULT CUT_HERE);
if (file)
pr_crit("kernel BUG at %s:%u!\n", file, line);
@@ -196,3 +196,26 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
return BUG_TRAP_TYPE_BUG;
}
+
+static void clear_once_table(struct bug_entry *start, struct bug_entry *end)
+{
+ struct bug_entry *bug;
+
+ for (bug = start; bug < end; bug++)
+ bug->flags &= ~BUGFLAG_DONE;
+}
+
+void generic_bug_clear_once(void)
+{
+#ifdef CONFIG_MODULES
+ struct module *mod;
+
+ rcu_read_lock_sched();
+ list_for_each_entry_rcu(mod, &module_bug_list, bug_list)
+ clear_once_table(mod->bug_table,
+ mod->bug_table + mod->num_bugs);
+ rcu_read_unlock_sched();
+#endif
+
+ clear_once_table(__start___bug_table, __stop___bug_table);
+}
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index ea4cc3d..1b34d21 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -1495,14 +1495,22 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size,
if (!entry)
return;
+ /* handle vmalloc and linear addresses */
+ if (!is_vmalloc_addr(virt) && !virt_to_page(virt))
+ return;
+
entry->type = dma_debug_coherent;
entry->dev = dev;
- entry->pfn = page_to_pfn(virt_to_page(virt));
entry->offset = offset_in_page(virt);
entry->size = size;
entry->dev_addr = dma_addr;
entry->direction = DMA_BIDIRECTIONAL;
+ if (is_vmalloc_addr(virt))
+ entry->pfn = vmalloc_to_pfn(virt);
+ else
+ entry->pfn = page_to_pfn(virt_to_page(virt));
+
add_dma_entry(entry);
}
EXPORT_SYMBOL(debug_dma_alloc_coherent);
@@ -1513,13 +1521,21 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
struct dma_debug_entry ref = {
.type = dma_debug_coherent,
.dev = dev,
- .pfn = page_to_pfn(virt_to_page(virt)),
.offset = offset_in_page(virt),
.dev_addr = addr,
.size = size,
.direction = DMA_BIDIRECTIONAL,
};
+ /* handle vmalloc and linear addresses */
+ if (!is_vmalloc_addr(virt) && !virt_to_page(virt))
+ return;
+
+ if (is_vmalloc_addr(virt))
+ ref.pfn = vmalloc_to_pfn(virt);
+ else
+ ref.pfn = page_to_pfn(virt_to_page(virt));
+
if (unlikely(dma_debug_disabled()))
return;
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index da796e2..c7c96bc7 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -360,6 +360,10 @@ static int ddebug_parse_query(char *words[], int nwords,
if (parse_lineno(last, &query->last_lineno) < 0)
return -EINVAL;
+ /* special case for last lineno not specified */
+ if (query->last_lineno == 0)
+ query->last_lineno = UINT_MAX;
+
if (query->last_lineno < query->first_lineno) {
pr_err("last-line:%d < 1st-line:%d\n",
query->last_lineno,
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 144fe6b..ca06adc 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -194,7 +194,7 @@ int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phy
chunk->phys_addr = phys;
chunk->start_addr = virt;
chunk->end_addr = virt + size - 1;
- atomic_set(&chunk->avail, size);
+ atomic_long_set(&chunk->avail, size);
spin_lock(&pool->lock);
list_add_rcu(&chunk->next_chunk, &pool->chunks);
@@ -304,7 +304,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size,
nbits = (size + (1UL << order) - 1) >> order;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
- if (size > atomic_read(&chunk->avail))
+ if (size > atomic_long_read(&chunk->avail))
continue;
start_bit = 0;
@@ -324,7 +324,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size,
addr = chunk->start_addr + ((unsigned long)start_bit << order);
size = nbits << order;
- atomic_sub(size, &chunk->avail);
+ atomic_long_sub(size, &chunk->avail);
break;
}
rcu_read_unlock();
@@ -390,7 +390,7 @@ void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
BUG_ON(remain);
size = nbits << order;
- atomic_add(size, &chunk->avail);
+ atomic_long_add(size, &chunk->avail);
rcu_read_unlock();
return;
}
@@ -464,7 +464,7 @@ size_t gen_pool_avail(struct gen_pool *pool)
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
- avail += atomic_read(&chunk->avail);
+ avail += atomic_long_read(&chunk->avail);
rcu_read_unlock();
return avail;
}
diff --git a/lib/int_sqrt.c b/lib/int_sqrt.c
index db0b5aa..e2d3290 100644
--- a/lib/int_sqrt.c
+++ b/lib/int_sqrt.c
@@ -8,12 +8,13 @@
#include <linux/kernel.h>
#include <linux/export.h>
+#include <linux/bitops.h>
/**
- * int_sqrt - rough approximation to sqrt
+ * int_sqrt - computes the integer square root
* @x: integer of which to calculate the sqrt
*
- * A very rough approximation to the sqrt() function.
+ * Computes: floor(sqrt(x))
*/
unsigned long int_sqrt(unsigned long x)
{
@@ -22,7 +23,7 @@ unsigned long int_sqrt(unsigned long x)
if (x <= 1)
return x;
- m = 1UL << (BITS_PER_LONG - 2);
+ m = 1UL << (__fls(x) & ~1UL);
while (m != 0) {
b = y + m;
y >>= 1;
diff --git a/lib/interval_tree_test.c b/lib/interval_tree_test.c
index 0e343fd..835242e 100644
--- a/lib/interval_tree_test.c
+++ b/lib/interval_tree_test.c
@@ -11,10 +11,10 @@
MODULE_PARM_DESC(name, msg);
__param(int, nnodes, 100, "Number of nodes in the interval tree");
-__param(int, perf_loops, 100000, "Number of iterations modifying the tree");
+__param(int, perf_loops, 1000, "Number of iterations modifying the tree");
__param(int, nsearches, 100, "Number of searches to the interval tree");
-__param(int, search_loops, 10000, "Number of iterations searching the tree");
+__param(int, search_loops, 1000, "Number of iterations searching the tree");
__param(bool, search_all, false, "Searches will iterate all nodes in the tree");
__param(uint, max_endpoint, ~0, "Largest value for the interval's endpoint");
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 46e4c749..61a6b5a 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -93,8 +93,8 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
arch_spin_lock(&lock);
if (regs && cpu_in_idle(instruction_pointer(regs))) {
- pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n",
- cpu, instruction_pointer(regs));
+ pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
+ cpu, (void *)instruction_pointer(regs));
} else {
pr_warn("NMI backtrace for cpu %d\n", cpu);
if (regs)
diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c
index 191a238..7d36c1e 100644
--- a/lib/rbtree_test.c
+++ b/lib/rbtree_test.c
@@ -11,7 +11,7 @@
MODULE_PARM_DESC(name, msg);
__param(int, nnodes, 100, "Number of nodes in the rb-tree");
-__param(int, perf_loops, 100000, "Number of iterations modifying the rb-tree");
+__param(int, perf_loops, 1000, "Number of iterations modifying the rb-tree");
__param(int, check_loops, 100, "Number of iterations modifying and verifying the rb-tree");
struct test_node {
diff --git a/lib/string.c b/lib/string.c
index 5e8d410..64a9e33 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -1052,144 +1052,3 @@ void fortify_panic(const char *name)
BUG();
}
EXPORT_SYMBOL(fortify_panic);
-
-#ifdef CONFIG_STRING_SELFTEST
-#include <linux/slab.h>
-#include <linux/module.h>
-
-static __init int memset16_selftest(void)
-{
- unsigned i, j, k;
- u16 v, *p;
-
- p = kmalloc(256 * 2 * 2, GFP_KERNEL);
- if (!p)
- return -1;
-
- for (i = 0; i < 256; i++) {
- for (j = 0; j < 256; j++) {
- memset(p, 0xa1, 256 * 2 * sizeof(v));
- memset16(p + i, 0xb1b2, j);
- for (k = 0; k < 512; k++) {
- v = p[k];
- if (k < i) {
- if (v != 0xa1a1)
- goto fail;
- } else if (k < i + j) {
- if (v != 0xb1b2)
- goto fail;
- } else {
- if (v != 0xa1a1)
- goto fail;
- }
- }
- }
- }
-
-fail:
- kfree(p);
- if (i < 256)
- return (i << 24) | (j << 16) | k;
- return 0;
-}
-
-static __init int memset32_selftest(void)
-{
- unsigned i, j, k;
- u32 v, *p;
-
- p = kmalloc(256 * 2 * 4, GFP_KERNEL);
- if (!p)
- return -1;
-
- for (i = 0; i < 256; i++) {
- for (j = 0; j < 256; j++) {
- memset(p, 0xa1, 256 * 2 * sizeof(v));
- memset32(p + i, 0xb1b2b3b4, j);
- for (k = 0; k < 512; k++) {
- v = p[k];
- if (k < i) {
- if (v != 0xa1a1a1a1)
- goto fail;
- } else if (k < i + j) {
- if (v != 0xb1b2b3b4)
- goto fail;
- } else {
- if (v != 0xa1a1a1a1)
- goto fail;
- }
- }
- }
- }
-
-fail:
- kfree(p);
- if (i < 256)
- return (i << 24) | (j << 16) | k;
- return 0;
-}
-
-static __init int memset64_selftest(void)
-{
- unsigned i, j, k;
- u64 v, *p;
-
- p = kmalloc(256 * 2 * 8, GFP_KERNEL);
- if (!p)
- return -1;
-
- for (i = 0; i < 256; i++) {
- for (j = 0; j < 256; j++) {
- memset(p, 0xa1, 256 * 2 * sizeof(v));
- memset64(p + i, 0xb1b2b3b4b5b6b7b8ULL, j);
- for (k = 0; k < 512; k++) {
- v = p[k];
- if (k < i) {
- if (v != 0xa1a1a1a1a1a1a1a1ULL)
- goto fail;
- } else if (k < i + j) {
- if (v != 0xb1b2b3b4b5b6b7b8ULL)
- goto fail;
- } else {
- if (v != 0xa1a1a1a1a1a1a1a1ULL)
- goto fail;
- }
- }
- }
- }
-
-fail:
- kfree(p);
- if (i < 256)
- return (i << 24) | (j << 16) | k;
- return 0;
-}
-
-static __init int string_selftest_init(void)
-{
- int test, subtest;
-
- test = 1;
- subtest = memset16_selftest();
- if (subtest)
- goto fail;
-
- test = 2;
- subtest = memset32_selftest();
- if (subtest)
- goto fail;
-
- test = 3;
- subtest = memset64_selftest();
- if (subtest)
- goto fail;
-
- pr_info("String selftests succeeded\n");
- return 0;
-fail:
- pr_crit("String selftest failure %d.%08x\n", test, subtest);
- return 0;
-}
-
-module_init(string_selftest_init);
-#endif /* CONFIG_STRING_SELFTEST */
diff --git a/lib/test_find_bit.c b/lib/test_find_bit.c
new file mode 100644
index 0000000..f4394a3
--- /dev/null
+++ b/lib/test_find_bit.c
@@ -0,0 +1,144 @@
+/*
+ * Test for find_*_bit functions.
+ *
+ * Copyright (c) 2017 Cavium.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program 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
+ * General Public License for more details.
+ */
+
+/*
+ * find_bit functions are widely used in kernel, so the successful boot
+ * is good enough test for correctness.
+ *
+ * This test is focused on performance of traversing bitmaps. Two typical
+ * scenarios are reproduced:
+ * - randomly filled bitmap with approximately equal number of set and
+ * cleared bits;
+ * - sparse bitmap with few set bits at random positions.
+ */
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+
+#define BITMAP_LEN (4096UL * 8 * 10)
+#define SPARSE 500
+
+static DECLARE_BITMAP(bitmap, BITMAP_LEN) __initdata;
+
+/*
+ * This is Schlemiel the Painter's algorithm. It should be called after
+ * all other tests for the same bitmap because it sets all bits of bitmap to 1.
+ */
+static int __init test_find_first_bit(void *bitmap, unsigned long len)
+{
+ unsigned long i, cnt;
+ cycles_t cycles;
+
+ cycles = get_cycles();
+ for (cnt = i = 0; i < len; cnt++) {
+ i = find_first_bit(bitmap, len);
+ __clear_bit(i, bitmap);
+ }
+ cycles = get_cycles() - cycles;
+ pr_err("find_first_bit:\t\t%llu cycles,\t%ld iterations\n",
+ (u64)cycles, cnt);
+
+ return 0;
+}
+
+static int __init test_find_next_bit(const void *bitmap, unsigned long len)
+{
+ unsigned long i, cnt;
+ cycles_t cycles;
+
+ cycles = get_cycles();
+ for (cnt = i = 0; i < BITMAP_LEN; cnt++)
+ i = find_next_bit(bitmap, BITMAP_LEN, i) + 1;
+ cycles = get_cycles() - cycles;
+ pr_err("find_next_bit:\t\t%llu cycles,\t%ld iterations\n",
+ (u64)cycles, cnt);
+
+ return 0;
+}
+
+static int __init test_find_next_zero_bit(const void *bitmap, unsigned long len)
+{
+ unsigned long i, cnt;
+ cycles_t cycles;
+
+ cycles = get_cycles();
+ for (cnt = i = 0; i < BITMAP_LEN; cnt++)
+ i = find_next_zero_bit(bitmap, len, i) + 1;
+ cycles = get_cycles() - cycles;
+ pr_err("find_next_zero_bit:\t%llu cycles,\t%ld iterations\n",
+ (u64)cycles, cnt);
+
+ return 0;
+}
+
+static int __init test_find_last_bit(const void *bitmap, unsigned long len)
+{
+ unsigned long l, cnt = 0;
+ cycles_t cycles;
+
+ cycles = get_cycles();
+ do {
+ cnt++;
+ l = find_last_bit(bitmap, len);
+ if (l >= len)
+ break;
+ len = l;
+ } while (len);
+ cycles = get_cycles() - cycles;
+ pr_err("find_last_bit:\t\t%llu cycles,\t%ld iterations\n",
+ (u64)cycles, cnt);
+
+ return 0;
+}
+
+static int __init find_bit_test(void)
+{
+ unsigned long nbits = BITMAP_LEN / SPARSE;
+
+ pr_err("\nStart testing find_bit() with random-filled bitmap\n");
+
+ get_random_bytes(bitmap, sizeof(bitmap));
+
+ test_find_next_bit(bitmap, BITMAP_LEN);
+ test_find_next_zero_bit(bitmap, BITMAP_LEN);
+ test_find_last_bit(bitmap, BITMAP_LEN);
+ test_find_first_bit(bitmap, BITMAP_LEN);
+
+ pr_err("\nStart testing find_bit() with sparse bitmap\n");
+
+ bitmap_zero(bitmap, BITMAP_LEN);
+
+ while (nbits--)
+ __set_bit(prandom_u32() % BITMAP_LEN, bitmap);
+
+ test_find_next_bit(bitmap, BITMAP_LEN);
+ test_find_next_zero_bit(bitmap, BITMAP_LEN);
+ test_find_last_bit(bitmap, BITMAP_LEN);
+ test_find_first_bit(bitmap, BITMAP_LEN);
+
+ return 0;
+}
+module_init(find_bit_test);
+
+static void __exit test_find_bit_cleanup(void)
+{
+}
+module_exit(test_find_bit_cleanup);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index a25c976..ef1a3ac 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -353,10 +353,9 @@ static noinline void __init memcg_accounted_kmem_cache(void)
*/
for (i = 0; i < 5; i++) {
p = kmem_cache_alloc(cache, GFP_KERNEL);
- if (!p) {
- pr_err("Allocation failed\n");
+ if (!p)
goto free_cache;
- }
+
kmem_cache_free(cache, p);
msleep(100);
}
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index fba78d25..337f408 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -783,10 +783,8 @@ static int kmod_config_sync_info(struct kmod_test_device *test_dev)
free_test_dev_info(test_dev);
test_dev->info = vzalloc(config->num_threads *
sizeof(struct kmod_test_device_info));
- if (!test_dev->info) {
- dev_err(test_dev->dev, "Cannot alloc test_dev info\n");
+ if (!test_dev->info)
return -ENOMEM;
- }
return 0;
}
@@ -1089,10 +1087,8 @@ static struct kmod_test_device *alloc_test_dev_kmod(int idx)
struct miscdevice *misc_dev;
test_dev = vzalloc(sizeof(struct kmod_test_device));
- if (!test_dev) {
- pr_err("Cannot alloc test_dev\n");
+ if (!test_dev)
goto err_out;
- }
mutex_init(&test_dev->config_mutex);
mutex_init(&test_dev->trigger_mutex);
diff --git a/lib/test_list_sort.c b/lib/test_list_sort.c
index 28e8173..5474f3f 100644
--- a/lib/test_list_sort.c
+++ b/lib/test_list_sort.c
@@ -76,17 +76,14 @@ static int __init list_sort_test(void)
pr_debug("start testing list_sort()\n");
elts = kcalloc(TEST_LIST_LEN, sizeof(*elts), GFP_KERNEL);
- if (!elts) {
- pr_err("error: cannot allocate memory\n");
+ if (!elts)
return err;
- }
for (i = 0; i < TEST_LIST_LEN; i++) {
el = kmalloc(sizeof(*el), GFP_KERNEL);
- if (!el) {
- pr_err("error: cannot allocate memory\n");
+ if (!el)
goto exit;
- }
+
/* force some equivalencies */
el->value = prandom_u32() % (TEST_LIST_LEN / 3);
el->serial = i;
diff --git a/lib/test_string.c b/lib/test_string.c
new file mode 100644
index 0000000..0fcdb82d
--- /dev/null
+++ b/lib/test_string.c
@@ -0,0 +1,141 @@
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+static __init int memset16_selftest(void)
+{
+ unsigned i, j, k;
+ u16 v, *p;
+
+ p = kmalloc(256 * 2 * 2, GFP_KERNEL);
+ if (!p)
+ return -1;
+
+ for (i = 0; i < 256; i++) {
+ for (j = 0; j < 256; j++) {
+ memset(p, 0xa1, 256 * 2 * sizeof(v));
+ memset16(p + i, 0xb1b2, j);
+ for (k = 0; k < 512; k++) {
+ v = p[k];
+ if (k < i) {
+ if (v != 0xa1a1)
+ goto fail;
+ } else if (k < i + j) {
+ if (v != 0xb1b2)
+ goto fail;
+ } else {
+ if (v != 0xa1a1)
+ goto fail;
+ }
+ }
+ }
+ }
+
+fail:
+ kfree(p);
+ if (i < 256)
+ return (i << 24) | (j << 16) | k;
+ return 0;
+}
+
+static __init int memset32_selftest(void)
+{
+ unsigned i, j, k;
+ u32 v, *p;
+
+ p = kmalloc(256 * 2 * 4, GFP_KERNEL);
+ if (!p)
+ return -1;
+
+ for (i = 0; i < 256; i++) {
+ for (j = 0; j < 256; j++) {
+ memset(p, 0xa1, 256 * 2 * sizeof(v));
+ memset32(p + i, 0xb1b2b3b4, j);
+ for (k = 0; k < 512; k++) {
+ v = p[k];
+ if (k < i) {
+ if (v != 0xa1a1a1a1)
+ goto fail;
+ } else if (k < i + j) {
+ if (v != 0xb1b2b3b4)
+ goto fail;
+ } else {
+ if (v != 0xa1a1a1a1)
+ goto fail;
+ }
+ }
+ }
+ }
+
+fail:
+ kfree(p);
+ if (i < 256)
+ return (i << 24) | (j << 16) | k;
+ return 0;
+}
+
+static __init int memset64_selftest(void)
+{
+ unsigned i, j, k;
+ u64 v, *p;
+
+ p = kmalloc(256 * 2 * 8, GFP_KERNEL);
+ if (!p)
+ return -1;
+
+ for (i = 0; i < 256; i++) {
+ for (j = 0; j < 256; j++) {
+ memset(p, 0xa1, 256 * 2 * sizeof(v));
+ memset64(p + i, 0xb1b2b3b4b5b6b7b8ULL, j);
+ for (k = 0; k < 512; k++) {
+ v = p[k];
+ if (k < i) {
+ if (v != 0xa1a1a1a1a1a1a1a1ULL)
+ goto fail;
+ } else if (k < i + j) {
+ if (v != 0xb1b2b3b4b5b6b7b8ULL)
+ goto fail;
+ } else {
+ if (v != 0xa1a1a1a1a1a1a1a1ULL)
+ goto fail;
+ }
+ }
+ }
+ }
+
+fail:
+ kfree(p);
+ if (i < 256)
+ return (i << 24) | (j << 16) | k;
+ return 0;
+}
+
+static __init int string_selftest_init(void)
+{
+ int test, subtest;
+
+ test = 1;
+ subtest = memset16_selftest();
+ if (subtest)
+ goto fail;
+
+ test = 2;
+ subtest = memset32_selftest();
+ if (subtest)
+ goto fail;
+
+ test = 3;
+ subtest = memset64_selftest();
+ if (subtest)
+ goto fail;
+
+ pr_info("String selftests succeeded\n");
+ return 0;
+fail:
+ pr_crit("String selftest failure %d.%08x\n", test, subtest);
+ return 0;
+}
+
+module_init(string_selftest_init);
+MODULE_LICENSE("GPL v2");
diff --git a/mm/Kconfig b/mm/Kconfig
index 9c4bddd..03ff770 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -756,3 +756,12 @@
This feature collects and exposes statistics via debugfs. The
information includes global and per chunk statistics, which can
be used to help understand percpu memory usage.
+
+config GUP_BENCHMARK
+ bool "Enable infrastructure for get_user_pages_fast() benchmarking"
+ default n
+ help
+ Provides /sys/kernel/debug/gup_benchmark that helps with testing
+ performance of get_user_pages_fast().
+
+ See tools/testing/selftests/vm/gup_benchmark.c
diff --git a/mm/Makefile b/mm/Makefile
index e7ebd17..e669f02 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -80,6 +80,7 @@
obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o
obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
+obj-$(CONFIG_GUP_BENCHMARK) += gup_benchmark.o
obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
diff --git a/mm/compaction.c b/mm/compaction.c
index 85395dc..10cd757 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -219,6 +219,24 @@ static void reset_cached_positions(struct zone *zone)
}
/*
+ * Compound pages of >= pageblock_order should consistenly be skipped until
+ * released. It is always pointless to compact pages of such order (if they are
+ * migratable), and the pageblocks they occupy cannot contain any free pages.
+ */
+static bool pageblock_skip_persistent(struct page *page)
+{
+ if (!PageCompound(page))
+ return false;
+
+ page = compound_head(page);
+
+ if (compound_order(page) >= pageblock_order)
+ return true;
+
+ return false;
+}
+
+/*
* This function is called to clear all cached information on pageblocks that
* should be skipped for page isolation when the migrate and free page scanner
* meet.
@@ -242,6 +260,8 @@ static void __reset_isolation_suitable(struct zone *zone)
continue;
if (zone != page_zone(page))
continue;
+ if (pageblock_skip_persistent(page))
+ continue;
clear_pageblock_skip(page);
}
@@ -275,7 +295,7 @@ static void update_pageblock_skip(struct compact_control *cc,
struct zone *zone = cc->zone;
unsigned long pfn;
- if (cc->ignore_skip_hint)
+ if (cc->no_set_skip_hint)
return;
if (!page)
@@ -307,7 +327,12 @@ static inline bool isolation_suitable(struct compact_control *cc,
return true;
}
-static void update_pageblock_skip(struct compact_control *cc,
+static inline bool pageblock_skip_persistent(struct page *page)
+{
+ return false;
+}
+
+static inline void update_pageblock_skip(struct compact_control *cc,
struct page *page, unsigned long nr_isolated,
bool migrate_scanner)
{
@@ -449,13 +474,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
* and the only danger is skipping too much.
*/
if (PageCompound(page)) {
- unsigned int comp_order = compound_order(page);
+ const unsigned int order = compound_order(page);
- if (likely(comp_order < MAX_ORDER)) {
- blockpfn += (1UL << comp_order) - 1;
- cursor += (1UL << comp_order) - 1;
+ if (likely(order < MAX_ORDER)) {
+ blockpfn += (1UL << order) - 1;
+ cursor += (1UL << order) - 1;
}
-
goto isolate_fail;
}
@@ -772,11 +796,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
* danger is skipping too much.
*/
if (PageCompound(page)) {
- unsigned int comp_order = compound_order(page);
+ const unsigned int order = compound_order(page);
- if (likely(comp_order < MAX_ORDER))
- low_pfn += (1UL << comp_order) - 1;
-
+ if (likely(order < MAX_ORDER))
+ low_pfn += (1UL << order) - 1;
goto isolate_fail;
}
@@ -1928,9 +1951,8 @@ static void kcompactd_do_work(pg_data_t *pgdat)
.total_free_scanned = 0,
.classzone_idx = pgdat->kcompactd_classzone_idx,
.mode = MIGRATE_SYNC_LIGHT,
- .ignore_skip_hint = true,
+ .ignore_skip_hint = false,
.gfp_mask = GFP_KERNEL,
-
};
trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
cc.classzone_idx);
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
new file mode 100644
index 0000000..5c8e2ab
--- /dev/null
+++ b/mm/gup_benchmark.c
@@ -0,0 +1,100 @@
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/ktime.h>
+#include <linux/debugfs.h>
+
+#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark)
+
+struct gup_benchmark {
+ __u64 delta_usec;
+ __u64 addr;
+ __u64 size;
+ __u32 nr_pages_per_call;
+ __u32 flags;
+};
+
+static int __gup_benchmark_ioctl(unsigned int cmd,
+ struct gup_benchmark *gup)
+{
+ ktime_t start_time, end_time;
+ unsigned long i, nr, nr_pages, addr, next;
+ struct page **pages;
+
+ nr_pages = gup->size / PAGE_SIZE;
+ pages = kvmalloc(sizeof(void *) * nr_pages, GFP_KERNEL);
+ if (!pages)
+ return -ENOMEM;
+
+ i = 0;
+ nr = gup->nr_pages_per_call;
+ start_time = ktime_get();
+ for (addr = gup->addr; addr < gup->addr + gup->size; addr = next) {
+ if (nr != gup->nr_pages_per_call)
+ break;
+
+ next = addr + nr * PAGE_SIZE;
+ if (next > gup->addr + gup->size) {
+ next = gup->addr + gup->size;
+ nr = (next - addr) / PAGE_SIZE;
+ }
+
+ nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i);
+ i += nr;
+ }
+ end_time = ktime_get();
+
+ gup->delta_usec = ktime_us_delta(end_time, start_time);
+ gup->size = addr - gup->addr;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (!pages[i])
+ break;
+ put_page(pages[i]);
+ }
+
+ kvfree(pages);
+ return 0;
+}
+
+static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
+ unsigned long arg)
+{
+ struct gup_benchmark gup;
+ int ret;
+
+ if (cmd != GUP_FAST_BENCHMARK)
+ return -EINVAL;
+
+ if (copy_from_user(&gup, (void __user *)arg, sizeof(gup)))
+ return -EFAULT;
+
+ ret = __gup_benchmark_ioctl(cmd, &gup);
+ if (ret)
+ return ret;
+
+ if (copy_to_user((void __user *)arg, &gup, sizeof(gup)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static const struct file_operations gup_benchmark_fops = {
+ .open = nonseekable_open,
+ .unlocked_ioctl = gup_benchmark_ioctl,
+};
+
+static int gup_benchmark_init(void)
+{
+ void *ret;
+
+ ret = debugfs_create_file_unsafe("gup_benchmark", 0600, NULL, NULL,
+ &gup_benchmark_fops);
+ if (!ret)
+ pr_warn("Failed to create gup_benchmark in debugfs");
+
+ return 0;
+}
+
+late_initcall(gup_benchmark_init);
diff --git a/mm/internal.h b/mm/internal.h
index 1df011f..e6bd351 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -198,6 +198,7 @@ struct compact_control {
const int classzone_idx; /* zone index of a direct compactor */
enum migrate_mode mode; /* Async or sync migration mode */
bool ignore_skip_hint; /* Scan blocks even if marked skip */
+ bool no_set_skip_hint; /* Don't mark blocks for skipping */
bool ignore_block_suitable; /* Scan blocks considered unsuitable */
bool direct_compaction; /* False from kcompactd or /proc/... */
bool whole_zone; /* Whole zone should/has been scanned */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 55ded92..d4096f4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7619,6 +7619,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
.zone = page_zone(pfn_to_page(start)),
.mode = MIGRATE_SYNC,
.ignore_skip_hint = true,
+ .no_set_skip_hint = true,
.gfp_mask = current_gfp_context(gfp_mask),
};
INIT_LIST_HEAD(&cc.migratepages);
diff --git a/mm/shmem.c b/mm/shmem.c
index 1f97d77..4aa9307 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3202,7 +3202,6 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
int len;
struct inode *inode;
struct page *page;
- struct shmem_inode_info *info;
len = strlen(symname) + 1;
if (len > PAGE_SIZE)
@@ -3222,7 +3221,6 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
error = 0;
}
- info = SHMEM_I(inode);
inode->i_size = len-1;
if (len <= SHORT_SYMLINK_LEN) {
inode->i_link = kmemdup(symname, len, GFP_KERNEL);
diff --git a/mm/z3fold.c b/mm/z3fold.c
index b2ba2ba..39e1912 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -404,8 +404,7 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked)
WARN_ON(z3fold_page_trylock(zhdr));
else
z3fold_page_lock(zhdr);
- if (test_bit(PAGE_STALE, &page->private) ||
- !test_and_clear_bit(NEEDS_COMPACTING, &page->private)) {
+ if (WARN_ON(!test_and_clear_bit(NEEDS_COMPACTING, &page->private))) {
z3fold_page_unlock(zhdr);
return;
}
@@ -413,6 +412,11 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked)
list_del_init(&zhdr->buddy);
spin_unlock(&pool->lock);
+ if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) {
+ atomic64_dec(&pool->pages_nr);
+ return;
+ }
+
z3fold_compact_page(zhdr);
unbuddied = get_cpu_ptr(pool->unbuddied);
fchunks = num_free_chunks(zhdr);
@@ -753,9 +757,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
list_del_init(&zhdr->buddy);
spin_unlock(&pool->lock);
zhdr->cpu = -1;
+ kref_get(&zhdr->refcount);
do_compact_page(zhdr, true);
return;
}
+ kref_get(&zhdr->refcount);
queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work);
z3fold_page_unlock(zhdr);
}
diff --git a/scripts/Makefile.kcov b/scripts/Makefile.kcov
new file mode 100644
index 0000000..5cc7203
--- /dev/null
+++ b/scripts/Makefile.kcov
@@ -0,0 +1,7 @@
+ifdef CONFIG_KCOV
+CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,)
+ifeq ($(CONFIG_KCOV_ENABLE_COMPARISONS),y)
+CFLAGS_KCOV += $(call cc-option,-fsanitize-coverage=trace-cmp,)
+endif
+
+endif
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 8b80bac..95cda3e 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -454,6 +454,7 @@
our $logFunctions = qr{(?x:
printk(?:_ratelimited|_once|_deferred_once|_deferred|)|
(?:[a-z0-9]+_){1,2}(?:printk|emerg|alert|crit|err|warning|warn|notice|info|debug|dbg|vdbg|devel|cont|WARN)(?:_ratelimited|_once|)|
+ TP_printk|
WARN(?:_RATELIMIT|_ONCE|)|
panic|
MODULE_[A-Z_]+|
@@ -2900,8 +2901,9 @@
$line =~ /^\+\s*#\s*define\s+\w+\s+$String$/) {
$msg_type = "";
- # EFI_GUID is another special case
- } elsif ($line =~ /^\+.*\bEFI_GUID\s*\(/) {
+ # More special cases
+ } elsif ($line =~ /^\+.*\bEFI_GUID\s*\(/ ||
+ $line =~ /^\+\s*(?:\w+)?\s*DEFINE_PER_CPU/) {
$msg_type = "";
# Otherwise set the alternate message types
@@ -3103,6 +3105,7 @@
$line =~ /^\+[a-z_]*init/ ||
$line =~ /^\+\s*(?:static\s+)?[A-Z_]*ATTR/ ||
$line =~ /^\+\s*DECLARE/ ||
+ $line =~ /^\+\s*builtin_[\w_]*driver/ ||
$line =~ /^\+\s*__setup/)) {
if (CHK("LINE_SPACING",
"Please use a blank line after function/struct/union/enum declarations\n" . $hereprev) &&
@@ -3182,6 +3185,12 @@
# check we are in a valid C source file if not then ignore this hunk
next if ($realfile !~ /\.(h|c)$/);
+# check for unusual line ending [ or (
+ if ($line =~ /^\+.*([\[\(])\s*$/) {
+ CHK("OPEN_ENDED_LINE",
+ "Lines should not end with a '$1'\n" . $herecurr);
+ }
+
# check if this appears to be the start function declaration, save the name
if ($sline =~ /^\+\{\s*$/ &&
$prevline =~ /^\+(?:(?:(?:$Storage|$Inline)\s*)*\s*$Type\s*)?($Ident)\(/) {
@@ -3829,28 +3838,10 @@
"Prefer printk_ratelimited or pr_<level>_ratelimited to printk_ratelimit\n" . $herecurr);
}
-# printk should use KERN_* levels. Note that follow on printk's on the
-# same line do not need a level, so we use the current block context
-# to try and find and validate the current printk. In summary the current
-# printk includes all preceding printk's which have no newline on the end.
-# we assume the first bad printk is the one to report.
- if ($line =~ /\bprintk\((?!KERN_)\s*"/) {
- my $ok = 0;
- for (my $ln = $linenr - 1; $ln >= $first_line; $ln--) {
- #print "CHECK<$lines[$ln - 1]\n";
- # we have a preceding printk if it ends
- # with "\n" ignore it, else it is to blame
- if ($lines[$ln - 1] =~ m{\bprintk\(}) {
- if ($rawlines[$ln - 1] !~ m{\\n"}) {
- $ok = 1;
- }
- last;
- }
- }
- if ($ok == 0) {
- WARN("PRINTK_WITHOUT_KERN_LEVEL",
- "printk() should include KERN_ facility level\n" . $herecurr);
- }
+# printk should use KERN_* levels
+ if ($line =~ /\bprintk\s*\(\s*(?!KERN_[A-Z]+\b)/) {
+ WARN("PRINTK_WITHOUT_KERN_LEVEL",
+ "printk() should include KERN_<LEVEL> facility level\n" . $herecurr);
}
if ($line =~ /\bprintk\s*\(\s*KERN_([A-Z]+)/) {
@@ -5957,7 +5948,7 @@
# check for function declarations that have arguments without identifier names
if (defined $stat &&
- $stat =~ /^.\s*(?:extern\s+)?$Type\s*$Ident\s*\(\s*([^{]+)\s*\)\s*;/s &&
+ $stat =~ /^.\s*(?:extern\s+)?$Type\s*(?:$Ident|\(\s*\*\s*$Ident\s*\))\s*\(\s*([^{]+)\s*\)\s*;/s &&
$1 ne "void") {
my $args = trim($1);
while ($args =~ m/\s*($Type\s*(?:$Ident|\(\s*\*\s*$Ident?\s*\)\s*$balanced_parens)?)/g) {
@@ -6109,7 +6100,7 @@
next if ($fline =~ /^.[\s$;]*$/);
$has_statement = 1;
$count++;
- $has_break = 1 if ($fline =~ /\bswitch\b|\b(?:break\s*;[\s$;]*$|return\b|goto\b|continue\b)/);
+ $has_break = 1 if ($fline =~ /\bswitch\b|\b(?:break\s*;[\s$;]*$|exit\s*\(\b|return\b|goto\b|continue\b)/);
}
if (!$has_break && $has_statement) {
WARN("MISSING_BREAK",
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index bc44320..99c96e8 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -57,6 +57,7 @@
my $file_emails = 0;
my $from_filename = 0;
my $pattern_depth = 0;
+my $self_test = undef;
my $version = 0;
my $help = 0;
my $find_maintainer_files = 0;
@@ -138,6 +139,7 @@
"subject_pattern" => "^GitSubject: (.*)",
"stat_pattern" => "^(\\d+)\\t(\\d+)\\t\$file\$",
"file_exists_cmd" => "git ls-files \$file",
+ "list_files_cmd" => "git ls-files \$file",
);
my %VCS_cmds_hg = (
@@ -167,6 +169,7 @@
"subject_pattern" => "^HgSubject: (.*)",
"stat_pattern" => "^(\\d+)\t(\\d+)\t\$file\$",
"file_exists_cmd" => "hg files \$file",
+ "list_files_cmd" => "hg manifest -R \$file",
);
my $conf = which_conf(".get_maintainer.conf");
@@ -216,6 +219,14 @@
close($ignore);
}
+if ($#ARGV > 0) {
+ foreach (@ARGV) {
+ if ($_ =~ /^-{1,2}self-test(?:=|$)/) {
+ die "$P: using --self-test does not allow any other option or argument\n";
+ }
+ }
+}
+
if (!GetOptions(
'email!' => \$email,
'git!' => \$email_git,
@@ -252,6 +263,7 @@
'fe|file-emails!' => \$file_emails,
'f|file' => \$from_filename,
'find-maintainer-files' => \$find_maintainer_files,
+ 'self-test:s' => \$self_test,
'v|version' => \$version,
'h|help|usage' => \$help,
)) {
@@ -268,6 +280,12 @@
exit 0;
}
+if (defined $self_test) {
+ read_all_maintainer_files();
+ self_test();
+ exit 0;
+}
+
if (-t STDIN && !@ARGV) {
# We're talking to a terminal, but have no command line arguments.
die "$P: missing patchfile or -f file - use --help if necessary\n";
@@ -311,14 +329,17 @@
my @typevalue = ();
my %keyword_hash;
my @mfiles = ();
+my @self_test_info = ();
sub read_maintainer_file {
my ($file) = @_;
open (my $maint, '<', "$file")
or die "$P: Can't open MAINTAINERS file '$file': $!\n";
+ my $i = 1;
while (<$maint>) {
my $line = $_;
+ chomp $line;
if ($line =~ m/^([A-Z]):\s*(.*)/) {
my $type = $1;
@@ -338,9 +359,12 @@
}
push(@typevalue, "$type:$value");
} elsif (!(/^\s*$/ || /^\s*\#/)) {
- $line =~ s/\n$//g;
push(@typevalue, $line);
}
+ if (defined $self_test) {
+ push(@self_test_info, {file=>$file, linenr=>$i, line=>$line});
+ }
+ $i++;
}
close($maint);
}
@@ -357,26 +381,30 @@
return grep { $_ !~ /^\.git$/; } @_;
}
-if (-d "${lk_path}MAINTAINERS") {
- opendir(DIR, "${lk_path}MAINTAINERS") or die $!;
- my @files = readdir(DIR);
- closedir(DIR);
- foreach my $file (@files) {
- push(@mfiles, "${lk_path}MAINTAINERS/$file") if ($file !~ /^\./);
+read_all_maintainer_files();
+
+sub read_all_maintainer_files {
+ if (-d "${lk_path}MAINTAINERS") {
+ opendir(DIR, "${lk_path}MAINTAINERS") or die $!;
+ my @files = readdir(DIR);
+ closedir(DIR);
+ foreach my $file (@files) {
+ push(@mfiles, "${lk_path}MAINTAINERS/$file") if ($file !~ /^\./);
+ }
}
-}
-if ($find_maintainer_files) {
- find( { wanted => \&find_is_maintainer_file,
- preprocess => \&find_ignore_git,
- no_chdir => 1,
- }, "${lk_path}");
-} else {
- push(@mfiles, "${lk_path}MAINTAINERS") if -f "${lk_path}MAINTAINERS";
-}
+ if ($find_maintainer_files) {
+ find( { wanted => \&find_is_maintainer_file,
+ preprocess => \&find_ignore_git,
+ no_chdir => 1,
+ }, "${lk_path}");
+ } else {
+ push(@mfiles, "${lk_path}MAINTAINERS") if -f "${lk_path}MAINTAINERS";
+ }
-foreach my $file (@mfiles) {
- read_maintainer_file("$file");
+ foreach my $file (@mfiles) {
+ read_maintainer_file("$file");
+ }
}
#
@@ -586,6 +614,135 @@
exit($exit);
+sub self_test {
+ my @lsfiles = ();
+ my @good_links = ();
+ my @bad_links = ();
+ my @section_headers = ();
+ my $index = 0;
+
+ @lsfiles = vcs_list_files($lk_path);
+
+ for my $x (@self_test_info) {
+ $index++;
+
+ ## Section header duplication and missing section content
+ if (($self_test eq "" || $self_test =~ /\bsections\b/) &&
+ $x->{line} =~ /^\S[^:]/ &&
+ defined $self_test_info[$index] &&
+ $self_test_info[$index]->{line} =~ /^([A-Z]):\s*\S/) {
+ my $has_S = 0;
+ my $has_F = 0;
+ my $has_ML = 0;
+ my $status = "";
+ if (grep(m@^\Q$x->{line}\E@, @section_headers)) {
+ print("$x->{file}:$x->{linenr}: warning: duplicate section header\t$x->{line}\n");
+ } else {
+ push(@section_headers, $x->{line});
+ }
+ my $nextline = $index;
+ while (defined $self_test_info[$nextline] &&
+ $self_test_info[$nextline]->{line} =~ /^([A-Z]):\s*(\S.*)/) {
+ my $type = $1;
+ my $value = $2;
+ if ($type eq "S") {
+ $has_S = 1;
+ $status = $value;
+ } elsif ($type eq "F" || $type eq "N") {
+ $has_F = 1;
+ } elsif ($type eq "M" || $type eq "R" || $type eq "L") {
+ $has_ML = 1;
+ }
+ $nextline++;
+ }
+ if (!$has_ML && $status !~ /orphan|obsolete/i) {
+ print("$x->{file}:$x->{linenr}: warning: section without email address\t$x->{line}\n");
+ }
+ if (!$has_S) {
+ print("$x->{file}:$x->{linenr}: warning: section without status \t$x->{line}\n");
+ }
+ if (!$has_F) {
+ print("$x->{file}:$x->{linenr}: warning: section without file pattern\t$x->{line}\n");
+ }
+ }
+
+ next if ($x->{line} !~ /^([A-Z]):\s*(.*)/);
+
+ my $type = $1;
+ my $value = $2;
+
+ ## Filename pattern matching
+ if (($type eq "F" || $type eq "X") &&
+ ($self_test eq "" || $self_test =~ /\bpatterns\b/)) {
+ $value =~ s@\.@\\\.@g; ##Convert . to \.
+ $value =~ s/\*/\.\*/g; ##Convert * to .*
+ $value =~ s/\?/\./g; ##Convert ? to .
+ ##if pattern is a directory and it lacks a trailing slash, add one
+ if ((-d $value)) {
+ $value =~ s@([^/])$@$1/@;
+ }
+ if (!grep(m@^$value@, @lsfiles)) {
+ print("$x->{file}:$x->{linenr}: warning: no file matches\t$x->{line}\n");
+ }
+
+ ## Link reachability
+ } elsif (($type eq "W" || $type eq "Q" || $type eq "B") &&
+ $value =~ /^https?:/ &&
+ ($self_test eq "" || $self_test =~ /\blinks\b/)) {
+ next if (grep(m@^\Q$value\E$@, @good_links));
+ my $isbad = 0;
+ if (grep(m@^\Q$value\E$@, @bad_links)) {
+ $isbad = 1;
+ } else {
+ my $output = `wget --spider -q --no-check-certificate --timeout 10 --tries 1 $value`;
+ if ($? == 0) {
+ push(@good_links, $value);
+ } else {
+ push(@bad_links, $value);
+ $isbad = 1;
+ }
+ }
+ if ($isbad) {
+ print("$x->{file}:$x->{linenr}: warning: possible bad link\t$x->{line}\n");
+ }
+
+ ## SCM reachability
+ } elsif ($type eq "T" &&
+ ($self_test eq "" || $self_test =~ /\bscm\b/)) {
+ next if (grep(m@^\Q$value\E$@, @good_links));
+ my $isbad = 0;
+ if (grep(m@^\Q$value\E$@, @bad_links)) {
+ $isbad = 1;
+ } elsif ($value !~ /^(?:git|quilt|hg)\s+\S/) {
+ print("$x->{file}:$x->{linenr}: warning: malformed entry\t$x->{line}\n");
+ } elsif ($value =~ /^git\s+(\S+)(\s+([^\(]+\S+))?/) {
+ my $url = $1;
+ my $branch = "";
+ $branch = $3 if $3;
+ my $output = `git ls-remote --exit-code -h "$url" $branch > /dev/null 2>&1`;
+ if ($? == 0) {
+ push(@good_links, $value);
+ } else {
+ push(@bad_links, $value);
+ $isbad = 1;
+ }
+ } elsif ($value =~ /^(?:quilt|hg)\s+(https?:\S+)/) {
+ my $url = $1;
+ my $output = `wget --spider -q --no-check-certificate --timeout 10 --tries 1 $url`;
+ if ($? == 0) {
+ push(@good_links, $value);
+ } else {
+ push(@bad_links, $value);
+ $isbad = 1;
+ }
+ }
+ if ($isbad) {
+ print("$x->{file}:$x->{linenr}: warning: possible bad link\t$x->{line}\n");
+ }
+ }
+ }
+}
+
sub ignore_email_address {
my ($address) = @_;
@@ -863,6 +1020,7 @@
--sections => print all of the subsystem sections with pattern matches
--letters => print all matching 'letter' types from all matching sections
--mailmap => use .mailmap file (default: $email_use_mailmap)
+ --self-test => show potential issues with MAINTAINERS file content
--version => show version
--help => show this help information
@@ -2192,6 +2350,23 @@
return $exists;
}
+sub vcs_list_files {
+ my ($file) = @_;
+
+ my @lsfiles = ();
+
+ my $vcs_used = vcs_exists();
+ return 0 if (!$vcs_used);
+
+ my $cmd = $VCS_cmds{"list_files_cmd"};
+ $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd
+ @lsfiles = &{$VCS_cmds{"execute_cmd"}}($cmd);
+
+ return () if ($? != 0);
+
+ return @lsfiles;
+}
+
sub uniq {
my (@parms) = @_;
diff --git a/scripts/parse-maintainers.pl b/scripts/parse-maintainers.pl
index 5dbd2fa..255cef1 100644
--- a/scripts/parse-maintainers.pl
+++ b/scripts/parse-maintainers.pl
@@ -2,9 +2,44 @@
# SPDX-License-Identifier: GPL-2.0
use strict;
+use Getopt::Long qw(:config no_auto_abbrev);
+
+my $input_file = "MAINTAINERS";
+my $output_file = "MAINTAINERS.new";
+my $output_section = "SECTION.new";
+my $help = 0;
my $P = $0;
+if (!GetOptions(
+ 'input=s' => \$input_file,
+ 'output=s' => \$output_file,
+ 'section=s' => \$output_section,
+ 'h|help|usage' => \$help,
+ )) {
+ die "$P: invalid argument - use --help if necessary\n";
+}
+
+if ($help != 0) {
+ usage();
+ exit 0;
+}
+
+sub usage {
+ print <<EOT;
+usage: $P [options] <pattern matching regexes>
+
+ --input => MAINTAINERS file to read (default: MAINTAINERS)
+ --output => sorted MAINTAINERS file to write (default: MAINTAINERS.new)
+ --section => new sorted MAINTAINERS file to write to (default: SECTION.new)
+
+If <pattern match regexes> exist, then the sections that match the
+regexes are not written to the output file but are written to the
+section file.
+
+EOT
+}
+
# sort comparison functions
sub by_category($$) {
my ($a, $b) = @_;
@@ -56,13 +91,20 @@
sub alpha_output {
my ($hashref, $filename) = (@_);
+ return if ! scalar(keys %$hashref);
+
open(my $file, '>', "$filename") or die "$P: $filename: open failed - $!\n";
+ my $separator;
foreach my $key (sort by_category keys %$hashref) {
if ($key eq " ") {
- chomp $$hashref{$key};
print $file $$hashref{$key};
} else {
- print $file "\n" . $key . "\n";
+ if (! defined $separator) {
+ $separator = "\n";
+ } else {
+ print $file $separator;
+ }
+ print $file $key . "\n";
foreach my $pattern (sort by_pattern split('\n', %$hashref{$key})) {
print $file ($pattern . "\n");
}
@@ -112,7 +154,7 @@
my %hash;
my %new_hash;
-file_input(\%hash, "MAINTAINERS");
+file_input(\%hash, $input_file);
foreach my $type (@ARGV) {
foreach my $key (keys %hash) {
@@ -123,7 +165,7 @@
}
}
-alpha_output(\%hash, "MAINTAINERS.new");
-alpha_output(\%new_hash, "SECTION.new");
+alpha_output(\%hash, $output_file);
+alpha_output(\%new_hash, $output_section);
exit(0);
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index aa0cc49..9a058cf 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -1187,6 +1187,10 @@
unknow||unknown
unkown||unknown
unneded||unneeded
+unneccecary||unnecessary
+unneccesary||unnecessary
+unneccessary||unnecessary
+unnecesary||unnecessary
unneedingly||unnecessarily
unnsupported||unsupported
unmached||unmatched
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 7c214ce..315df0a 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -436,13 +436,13 @@ create_arg_exp(enum filter_exp_type etype)
return NULL;
arg->type = FILTER_ARG_EXP;
- arg->op.type = etype;
+ arg->exp.type = etype;
return arg;
}
static struct filter_arg *
-create_arg_cmp(enum filter_exp_type etype)
+create_arg_cmp(enum filter_cmp_type ctype)
{
struct filter_arg *arg;
@@ -452,7 +452,7 @@ create_arg_cmp(enum filter_exp_type etype)
/* Use NUM and change if necessary */
arg->type = FILTER_ARG_NUM;
- arg->op.type = etype;
+ arg->num.type = ctype;
return arg;
}
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index e49eca1..7f45806 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -18,6 +18,7 @@
TEST_GEN_FILES += userfaultfd
TEST_GEN_FILES += mlock-random-test
TEST_GEN_FILES += virtual_address_range
+TEST_GEN_FILES += gup_benchmark
TEST_PROGS := run_vmtests
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
new file mode 100644
index 0000000..36df551
--- /dev/null
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -0,0 +1,91 @@
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+#define MB (1UL << 20)
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark)
+
+struct gup_benchmark {
+ __u64 delta_usec;
+ __u64 addr;
+ __u64 size;
+ __u32 nr_pages_per_call;
+ __u32 flags;
+};
+
+int main(int argc, char **argv)
+{
+ struct gup_benchmark gup;
+ unsigned long size = 128 * MB;
+ int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+ char *p;
+
+ while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) {
+ switch (opt) {
+ case 'm':
+ size = atoi(optarg) * MB;
+ break;
+ case 'r':
+ repeats = atoi(optarg);
+ break;
+ case 'n':
+ nr_pages = atoi(optarg);
+ break;
+ case 't':
+ thp = 1;
+ break;
+ case 'T':
+ thp = 0;
+ break;
+ case 'w':
+ write = 1;
+ default:
+ return -1;
+ }
+ }
+
+ gup.nr_pages_per_call = nr_pages;
+ gup.flags = write;
+
+ fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
+ if (fd == -1)
+ perror("open"), exit(1);
+
+ p = mmap(NULL, size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (p == MAP_FAILED)
+ perror("mmap"), exit(1);
+ gup.addr = (unsigned long)p;
+
+ if (thp == 1)
+ madvise(p, size, MADV_HUGEPAGE);
+ else if (thp == 0)
+ madvise(p, size, MADV_NOHUGEPAGE);
+
+ for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
+ p[0] = 0;
+
+ for (i = 0; i < repeats; i++) {
+ gup.size = size;
+ if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
+ perror("ioctl"), exit(1);
+
+ printf("Time: %lld us", gup.delta_usec);
+ if (gup.size != size)
+ printf(", truncated (size: %lld)", gup.size);
+ printf("\n");
+ }
+
+ return 0;
+}
