summaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig2
-rw-r--r--lib/Kconfig.debug122
-rw-r--r--lib/Kconfig.kgdb3
-rw-r--r--lib/Makefile2
-rw-r--r--lib/bug.c3
-rw-r--r--lib/debugobjects.c21
-rw-r--r--lib/devres.c60
-rw-r--r--lib/digsig.c41
-rw-r--r--lib/dynamic_debug.c165
-rw-r--r--lib/hexdump.c4
-rw-r--r--lib/idr.c446
-rw-r--r--lib/kfifo.c607
-rw-r--r--lib/locking-selftest.c34
-rw-r--r--lib/lru_cache.c3
-rw-r--r--lib/mpi/mpi-internal.h4
-rw-r--r--lib/mpi/mpicoder.c8
-rw-r--r--lib/parser.c6
-rw-r--r--lib/rwsem-spinlock.c69
-rw-r--r--lib/rwsem.c75
-rw-r--r--lib/scatterlist.c86
-rw-r--r--lib/swiotlb.c47
-rw-r--r--lib/vsprintf.c7
-rw-r--r--lib/xz/Kconfig34
23 files changed, 1354 insertions, 495 deletions
diff --git a/lib/Kconfig b/lib/Kconfig
index 75cdb77..3958dc4 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -322,7 +322,7 @@ config CPUMASK_OFFSTACK
config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS
- depends on EXPERIMENTAL && BROKEN
+ depends on BROKEN
config CPU_RMAP
bool
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 67604e5..e4a7f80 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -243,8 +243,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
config PANIC_ON_OOPS
- bool "Panic on Oops" if EXPERT
- default n
+ bool "Panic on Oops"
help
Say Y here to enable the kernel to panic when it oopses. This
has the same effect as setting oops=panic on the kernel command
@@ -455,7 +454,7 @@ config HAVE_DEBUG_KMEMLEAK
config DEBUG_KMEMLEAK
bool "Kernel memory leak detector"
- depends on DEBUG_KERNEL && EXPERIMENTAL && HAVE_DEBUG_KMEMLEAK
+ depends on DEBUG_KERNEL && HAVE_DEBUG_KMEMLEAK
select DEBUG_FS
select STACKTRACE if STACKTRACE_SUPPORT
select KALLSYMS
@@ -605,61 +604,6 @@ config PROVE_LOCKING
For more details, see Documentation/lockdep-design.txt.
-config PROVE_RCU
- bool "RCU debugging: prove RCU correctness"
- depends on PROVE_LOCKING
- default n
- help
- This feature enables lockdep extensions that check for correct
- use of RCU APIs. This is currently under development. Say Y
- if you want to debug RCU usage or help work on the PROVE_RCU
- feature.
-
- Say N if you are unsure.
-
-config PROVE_RCU_REPEATEDLY
- bool "RCU debugging: don't disable PROVE_RCU on first splat"
- depends on PROVE_RCU
- default n
- help
- By itself, PROVE_RCU will disable checking upon issuing the
- first warning (or "splat"). This feature prevents such
- disabling, allowing multiple RCU-lockdep warnings to be printed
- on a single reboot.
-
- Say Y to allow multiple RCU-lockdep warnings per boot.
-
- Say N if you are unsure.
-
-config PROVE_RCU_DELAY
- bool "RCU debugging: preemptible RCU race provocation"
- depends on DEBUG_KERNEL && PREEMPT_RCU
- default n
- help
- There is a class of races that involve an unlikely preemption
- of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
- been set to INT_MIN. This feature inserts a delay at that
- point to increase the probability of these races.
-
- Say Y to increase probability of preemption of __rcu_read_unlock().
-
- Say N if you are unsure.
-
-config SPARSE_RCU_POINTER
- bool "RCU debugging: sparse-based checks for pointer usage"
- default n
- help
- This feature enables the __rcu sparse annotation for
- RCU-protected pointers. This annotation will cause sparse
- to flag any non-RCU used of annotated pointers. This can be
- helpful when debugging RCU usage. Please note that this feature
- is not intended to enforce code cleanliness; it is instead merely
- a debugging aid.
-
- Say Y to make sparse flag questionable use of RCU-protected pointers
-
- Say N if you are unsure.
-
config LOCKDEP
bool
depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
@@ -937,6 +881,63 @@ config BOOT_PRINTK_DELAY
BOOT_PRINTK_DELAY also may cause LOCKUP_DETECTOR to detect
what it believes to be lockup conditions.
+menu "RCU Debugging"
+
+config PROVE_RCU
+ bool "RCU debugging: prove RCU correctness"
+ depends on PROVE_LOCKING
+ default n
+ help
+ This feature enables lockdep extensions that check for correct
+ use of RCU APIs. This is currently under development. Say Y
+ if you want to debug RCU usage or help work on the PROVE_RCU
+ feature.
+
+ Say N if you are unsure.
+
+config PROVE_RCU_REPEATEDLY
+ bool "RCU debugging: don't disable PROVE_RCU on first splat"
+ depends on PROVE_RCU
+ default n
+ help
+ By itself, PROVE_RCU will disable checking upon issuing the
+ first warning (or "splat"). This feature prevents such
+ disabling, allowing multiple RCU-lockdep warnings to be printed
+ on a single reboot.
+
+ Say Y to allow multiple RCU-lockdep warnings per boot.
+
+ Say N if you are unsure.
+
+config PROVE_RCU_DELAY
+ bool "RCU debugging: preemptible RCU race provocation"
+ depends on DEBUG_KERNEL && PREEMPT_RCU
+ default n
+ help
+ There is a class of races that involve an unlikely preemption
+ of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
+ been set to INT_MIN. This feature inserts a delay at that
+ point to increase the probability of these races.
+
+ Say Y to increase probability of preemption of __rcu_read_unlock().
+
+ Say N if you are unsure.
+
+config SPARSE_RCU_POINTER
+ bool "RCU debugging: sparse-based checks for pointer usage"
+ default n
+ help
+ This feature enables the __rcu sparse annotation for
+ RCU-protected pointers. This annotation will cause sparse
+ to flag any non-RCU used of annotated pointers. This can be
+ helpful when debugging RCU usage. Please note that this feature
+ is not intended to enforce code cleanliness; it is instead merely
+ a debugging aid.
+
+ Say Y to make sparse flag questionable use of RCU-protected pointers
+
+ Say N if you are unsure.
+
config RCU_TORTURE_TEST
tristate "torture tests for RCU"
depends on DEBUG_KERNEL
@@ -970,7 +971,7 @@ config RCU_TORTURE_TEST_RUNNABLE
config RCU_CPU_STALL_TIMEOUT
int "RCU CPU stall timeout in seconds"
- depends on TREE_RCU || TREE_PREEMPT_RCU
+ depends on RCU_STALL_COMMON
range 3 300
default 21
help
@@ -1008,6 +1009,7 @@ config RCU_CPU_STALL_INFO
config RCU_TRACE
bool "Enable tracing for RCU"
depends on DEBUG_KERNEL
+ select TRACE_CLOCK
help
This option provides tracing in RCU which presents stats
in debugfs for debugging RCU implementation.
@@ -1015,6 +1017,8 @@ config RCU_TRACE
Say Y here if you want to enable RCU tracing
Say N if you are unsure.
+endmenu # "RCU Debugging"
+
config KPROBES_SANITY_TEST
bool "Kprobes sanity tests"
depends on DEBUG_KERNEL
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index 43cb93f..dbb58ae 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -5,7 +5,7 @@ config HAVE_ARCH_KGDB
menuconfig KGDB
bool "KGDB: kernel debugger"
depends on HAVE_ARCH_KGDB
- depends on DEBUG_KERNEL && EXPERIMENTAL
+ depends on DEBUG_KERNEL
help
If you say Y here, it will be possible to remotely debug the
kernel using gdb. It is recommended but not required, that
@@ -22,6 +22,7 @@ config KGDB_SERIAL_CONSOLE
tristate "KGDB: use kgdb over the serial console"
select CONSOLE_POLL
select MAGIC_SYSRQ
+ depends on TTY
default y
help
Share a serial console with kgdb. Sysrq-g must be used
diff --git a/lib/Makefile b/lib/Makefile
index 02ed6c0..d7946ff 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -23,7 +23,7 @@ lib-y += kobject.o klist.o
obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \
- bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o
+ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o
obj-y += kstrtox.o
obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
diff --git a/lib/bug.c b/lib/bug.c
index d0cdf14..1686034 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -166,7 +166,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
print_modules();
show_regs(regs);
print_oops_end_marker();
- add_taint(BUG_GET_TAINT(bug));
+ /* Just a warning, don't kill lockdep. */
+ add_taint(BUG_GET_TAINT(bug), LOCKDEP_STILL_OK);
return BUG_TRAP_TYPE_WARN;
}
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index d11808c..37061ed 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -109,11 +109,10 @@ static void fill_pool(void)
*/
static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b)
{
- struct hlist_node *node;
struct debug_obj *obj;
int cnt = 0;
- hlist_for_each_entry(obj, node, &b->list, node) {
+ hlist_for_each_entry(obj, &b->list, node) {
cnt++;
if (obj->object == addr)
return obj;
@@ -213,7 +212,7 @@ static void free_object(struct debug_obj *obj)
static void debug_objects_oom(void)
{
struct debug_bucket *db = obj_hash;
- struct hlist_node *node, *tmp;
+ struct hlist_node *tmp;
HLIST_HEAD(freelist);
struct debug_obj *obj;
unsigned long flags;
@@ -227,7 +226,7 @@ static void debug_objects_oom(void)
raw_spin_unlock_irqrestore(&db->lock, flags);
/* Now free them */
- hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) {
+ hlist_for_each_entry_safe(obj, tmp, &freelist, node) {
hlist_del(&obj->node);
free_object(obj);
}
@@ -658,7 +657,7 @@ debug_object_active_state(void *addr, struct debug_obj_descr *descr,
static void __debug_check_no_obj_freed(const void *address, unsigned long size)
{
unsigned long flags, oaddr, saddr, eaddr, paddr, chunks;
- struct hlist_node *node, *tmp;
+ struct hlist_node *tmp;
HLIST_HEAD(freelist);
struct debug_obj_descr *descr;
enum debug_obj_state state;
@@ -678,7 +677,7 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size)
repeat:
cnt = 0;
raw_spin_lock_irqsave(&db->lock, flags);
- hlist_for_each_entry_safe(obj, node, tmp, &db->list, node) {
+ hlist_for_each_entry_safe(obj, tmp, &db->list, node) {
cnt++;
oaddr = (unsigned long) obj->object;
if (oaddr < saddr || oaddr >= eaddr)
@@ -702,7 +701,7 @@ repeat:
raw_spin_unlock_irqrestore(&db->lock, flags);
/* Now free them */
- hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) {
+ hlist_for_each_entry_safe(obj, tmp, &freelist, node) {
hlist_del(&obj->node);
free_object(obj);
}
@@ -1013,7 +1012,7 @@ void __init debug_objects_early_init(void)
static int __init debug_objects_replace_static_objects(void)
{
struct debug_bucket *db = obj_hash;
- struct hlist_node *node, *tmp;
+ struct hlist_node *tmp;
struct debug_obj *obj, *new;
HLIST_HEAD(objects);
int i, cnt = 0;
@@ -1033,7 +1032,7 @@ static int __init debug_objects_replace_static_objects(void)
local_irq_disable();
/* Remove the statically allocated objects from the pool */
- hlist_for_each_entry_safe(obj, node, tmp, &obj_pool, node)
+ hlist_for_each_entry_safe(obj, tmp, &obj_pool, node)
hlist_del(&obj->node);
/* Move the allocated objects to the pool */
hlist_move_list(&objects, &obj_pool);
@@ -1042,7 +1041,7 @@ static int __init debug_objects_replace_static_objects(void)
for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) {
hlist_move_list(&db->list, &objects);
- hlist_for_each_entry(obj, node, &objects, node) {
+ hlist_for_each_entry(obj, &objects, node) {
new = hlist_entry(obj_pool.first, typeof(*obj), node);
hlist_del(&new->node);
/* copy object data */
@@ -1057,7 +1056,7 @@ static int __init debug_objects_replace_static_objects(void)
obj_pool_used);
return 0;
free:
- hlist_for_each_entry_safe(obj, node, tmp, &objects, node) {
+ hlist_for_each_entry_safe(obj, tmp, &objects, node) {
hlist_del(&obj->node);
kmem_cache_free(obj_cache, obj);
}
diff --git a/lib/devres.c b/lib/devres.c
index 80b9c76..8235331 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -1,3 +1,4 @@
+#include <linux/err.h>
#include <linux/pci.h>
#include <linux/io.h>
#include <linux/gfp.h>
@@ -86,22 +87,24 @@ void devm_iounmap(struct device *dev, void __iomem *addr)
EXPORT_SYMBOL(devm_iounmap);
/**
- * devm_request_and_ioremap() - Check, request region, and ioremap resource
- * @dev: Generic device to handle the resource for
+ * devm_ioremap_resource() - check, request region, and ioremap resource
+ * @dev: generic device to handle the resource for
* @res: resource to be handled
*
- * Takes all necessary steps to ioremap a mem resource. Uses managed device, so
- * everything is undone on driver detach. Checks arguments, so you can feed
- * it the result from e.g. platform_get_resource() directly. Returns the
- * remapped pointer or NULL on error. Usage example:
+ * Checks that a resource is a valid memory region, requests the memory region
+ * and ioremaps it either as cacheable or as non-cacheable memory depending on
+ * the resource's flags. All operations are managed and will be undone on
+ * driver detach.
+ *
+ * Returns a pointer to the remapped memory or an ERR_PTR() encoded error code
+ * on failure. Usage example:
*
* res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- * base = devm_request_and_ioremap(&pdev->dev, res);
- * if (!base)
- * return -EADDRNOTAVAIL;
+ * base = devm_ioremap_resource(&pdev->dev, res);
+ * if (IS_ERR(base))
+ * return PTR_ERR(base);
*/
-void __iomem *devm_request_and_ioremap(struct device *dev,
- struct resource *res)
+void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res)
{
resource_size_t size;
const char *name;
@@ -111,7 +114,7 @@ void __iomem *devm_request_and_ioremap(struct device *dev,
if (!res || resource_type(res) != IORESOURCE_MEM) {
dev_err(dev, "invalid resource\n");
- return NULL;
+ return ERR_PTR(-EINVAL);
}
size = resource_size(res);
@@ -119,7 +122,7 @@ void __iomem *devm_request_and_ioremap(struct device *dev,
if (!devm_request_mem_region(dev, res->start, size, name)) {
dev_err(dev, "can't request region for resource %pR\n", res);
- return NULL;
+ return ERR_PTR(-EBUSY);
}
if (res->flags & IORESOURCE_CACHEABLE)
@@ -130,10 +133,39 @@ void __iomem *devm_request_and_ioremap(struct device *dev,
if (!dest_ptr) {
dev_err(dev, "ioremap failed for resource %pR\n", res);
devm_release_mem_region(dev, res->start, size);
+ dest_ptr = ERR_PTR(-ENOMEM);
}
return dest_ptr;
}
+EXPORT_SYMBOL(devm_ioremap_resource);
+
+/**
+ * devm_request_and_ioremap() - Check, request region, and ioremap resource
+ * @dev: Generic device to handle the resource for
+ * @res: resource to be handled
+ *
+ * Takes all necessary steps to ioremap a mem resource. Uses managed device, so
+ * everything is undone on driver detach. Checks arguments, so you can feed
+ * it the result from e.g. platform_get_resource() directly. Returns the
+ * remapped pointer or NULL on error. Usage example:
+ *
+ * res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ * base = devm_request_and_ioremap(&pdev->dev, res);
+ * if (!base)
+ * return -EADDRNOTAVAIL;
+ */
+void __iomem *devm_request_and_ioremap(struct device *device,
+ struct resource *res)
+{
+ void __iomem *dest_ptr;
+
+ dest_ptr = devm_ioremap_resource(device, res);
+ if (IS_ERR(dest_ptr))
+ return NULL;
+
+ return dest_ptr;
+}
EXPORT_SYMBOL(devm_request_and_ioremap);
#ifdef CONFIG_HAS_IOPORT
@@ -195,6 +227,7 @@ void devm_ioport_unmap(struct device *dev, void __iomem *addr)
devm_ioport_map_match, (void *)addr));
}
EXPORT_SYMBOL(devm_ioport_unmap);
+#endif /* CONFIG_HAS_IOPORT */
#ifdef CONFIG_PCI
/*
@@ -400,4 +433,3 @@ void pcim_iounmap_regions(struct pci_dev *pdev, int mask)
}
EXPORT_SYMBOL(pcim_iounmap_regions);
#endif /* CONFIG_PCI */
-#endif /* CONFIG_HAS_IOPORT */
diff --git a/lib/digsig.c b/lib/digsig.c
index dc2be7e..2f31e6a 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -30,11 +30,10 @@
static struct crypto_shash *shash;
-static int pkcs_1_v1_5_decode_emsa(const unsigned char *msg,
- unsigned long msglen,
- unsigned long modulus_bitlen,
- unsigned char *out,
- unsigned long *outlen)
+static const char *pkcs_1_v1_5_decode_emsa(const unsigned char *msg,
+ unsigned long msglen,
+ unsigned long modulus_bitlen,
+ unsigned long *outlen)
{
unsigned long modulus_len, ps_len, i;
@@ -42,11 +41,11 @@ static int pkcs_1_v1_5_decode_emsa(const unsigned char *msg,
/* test message size */
if ((msglen > modulus_len) || (modulus_len < 11))
- return -EINVAL;
+ return NULL;
/* separate encoded message */
- if ((msg[0] != 0x00) || (msg[1] != (unsigned char)1))
- return -EINVAL;
+ if (msg[0] != 0x00 || msg[1] != 0x01)
+ return NULL;
for (i = 2; i < modulus_len - 1; i++)
if (msg[i] != 0xFF)
@@ -56,19 +55,13 @@ static int pkcs_1_v1_5_decode_emsa(const unsigned char *msg,
if (msg[i] != 0)
/* There was no octet with hexadecimal value 0x00
to separate ps from m. */
- return -EINVAL;
+ return NULL;
ps_len = i - 2;
- if (*outlen < (msglen - (2 + ps_len + 1))) {
- *outlen = msglen - (2 + ps_len + 1);
- return -EOVERFLOW;
- }
-
*outlen = (msglen - (2 + ps_len + 1));
- memcpy(out, &msg[2 + ps_len + 1], *outlen);
- return 0;
+ return msg + 2 + ps_len + 1;
}
/*
@@ -83,7 +76,8 @@ static int digsig_verify_rsa(struct key *key,
unsigned long mlen, mblen;
unsigned nret, l;
int head, i;
- unsigned char *out1 = NULL, *out2 = NULL;
+ unsigned char *out1 = NULL;
+ const char *m;
MPI in = NULL, res = NULL, pkey[2];
uint8_t *p, *datap, *endp;
struct user_key_payload *ukp;
@@ -120,7 +114,7 @@ static int digsig_verify_rsa(struct key *key,
}
mblen = mpi_get_nbits(pkey[0]);
- mlen = (mblen + 7)/8;
+ mlen = DIV_ROUND_UP(mblen, 8);
if (mlen == 0)
goto err;
@@ -129,10 +123,6 @@ static int digsig_verify_rsa(struct key *key,
if (!out1)
goto err;
- out2 = kzalloc(mlen, GFP_KERNEL);
- if (!out2)
- goto err;
-
nret = siglen;
in = mpi_read_from_buffer(sig, &nret);
if (!in)
@@ -164,18 +154,15 @@ static int digsig_verify_rsa(struct key *key,
kfree(p);
- err = pkcs_1_v1_5_decode_emsa(out1, len, mblen, out2, &len);
- if (err)
- goto err;
+ m = pkcs_1_v1_5_decode_emsa(out1, len, mblen, &len);
- if (len != hlen || memcmp(out2, h, hlen))
+ if (!m || len != hlen || memcmp(m, h, hlen))
err = -EINVAL;
err:
mpi_free(in);
mpi_free(res);
kfree(out1);
- kfree(out2);
while (--i >= 0)
mpi_free(pkey[i]);
err1:
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 1db1fc6..5276b99 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -59,7 +59,7 @@ struct ddebug_iter {
static DEFINE_MUTEX(ddebug_lock);
static LIST_HEAD(ddebug_tables);
-static int verbose = 0;
+static int verbose;
module_param(verbose, int, 0644);
/* Return the path relative to source root */
@@ -100,24 +100,32 @@ static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
return buf;
}
-#define vpr_info(fmt, ...) \
- if (verbose) do { pr_info(fmt, ##__VA_ARGS__); } while (0)
-
-#define vpr_info_dq(q, msg) \
+#define vpr_info(fmt, ...) \
do { \
- /* trim last char off format print */ \
- vpr_info("%s: func=\"%s\" file=\"%s\" " \
- "module=\"%s\" format=\"%.*s\" " \
- "lineno=%u-%u", \
- msg, \
- q->function ? q->function : "", \
- q->filename ? q->filename : "", \
- q->module ? q->module : "", \
- (int)(q->format ? strlen(q->format) - 1 : 0), \
- q->format ? q->format : "", \
- q->first_lineno, q->last_lineno); \
+ if (verbose) \
+ pr_info(fmt, ##__VA_ARGS__); \
} while (0)
+static void vpr_info_dq(const struct ddebug_query *query, const char *msg)
+{
+ /* trim any trailing newlines */
+ int fmtlen = 0;
+
+ if (query->format) {
+ fmtlen = strlen(query->format);
+ while (fmtlen && query->format[fmtlen - 1] == '\n')
+ fmtlen--;
+ }
+
+ vpr_info("%s: func=\"%s\" file=\"%s\" module=\"%s\" format=\"%.*s\" lineno=%u-%u\n",
+ msg,
+ query->function ? query->function : "",
+ query->filename ? query->filename : "",
+ query->module ? query->module : "",
+ fmtlen, query->format ? query->format : "",
+ query->first_lineno, query->last_lineno);
+}
+
/*
* Search the tables for _ddebug's which match the given `query' and
* apply the `flags' and `mask' to them. Returns number of matching
@@ -141,7 +149,7 @@ static int ddebug_change(const struct ddebug_query *query,
if (query->module && strcmp(query->module, dt->mod_name))
continue;
- for (i = 0 ; i < dt->num_ddebugs ; i++) {
+ for (i = 0; i < dt->num_ddebugs; i++) {
struct _ddebug *dp = &dt->ddebugs[i];
/* match against the source filename */
@@ -176,10 +184,10 @@ static int ddebug_change(const struct ddebug_query *query,
continue;
dp->flags = newflags;
vpr_info("changed %s:%d [%s]%s =%s\n",
- trim_prefix(dp->filename), dp->lineno,
- dt->mod_name, dp->function,
- ddebug_describe_flags(dp, flagbuf,
- sizeof(flagbuf)));
+ trim_prefix(dp->filename), dp->lineno,
+ dt->mod_name, dp->function,
+ ddebug_describe_flags(dp, flagbuf,
+ sizeof(flagbuf)));
}
}
mutex_unlock(&ddebug_lock);
@@ -213,19 +221,23 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords)
/* find `end' of word, whitespace separated or quoted */
if (*buf == '"' || *buf == '\'') {
int quote = *buf++;
- for (end = buf ; *end && *end != quote ; end++)
+ for (end = buf; *end && *end != quote; end++)
;
- if (!*end)
+ if (!*end) {
+ pr_err("unclosed quote: %s\n", buf);
return -EINVAL; /* unclosed quote */
+ }
} else {
- for (end = buf ; *end && !isspace(*end) ; end++)
+ for (end = buf; *end && !isspace(*end); end++)
;
BUG_ON(end == buf);
}
/* `buf' is start of word, `end' is one past its end */
- if (nwords == maxwords)
+ if (nwords == maxwords) {
+ pr_err("too many words, legal max <=%d\n", maxwords);
return -EINVAL; /* ran out of words[] before bytes */
+ }
if (*end)
*end++ = '\0'; /* terminate the word */
words[nwords++] = buf;
@@ -235,7 +247,7 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords)
if (verbose) {
int i;
pr_info("split into words:");
- for (i = 0 ; i < nwords ; i++)
+ for (i = 0; i < nwords; i++)
pr_cont(" \"%s\"", words[i]);
pr_cont("\n");
}
@@ -257,7 +269,11 @@ static inline int parse_lineno(const char *str, unsigned int *val)
return 0;
}
*val = simple_strtoul(str, &end, 10);
- return end == NULL || end == str || *end != '\0' ? -EINVAL : 0;
+ if (end == NULL || end == str || *end != '\0') {
+ pr_err("bad line-number: %s\n", str);
+ return -EINVAL;
+ }
+ return 0;
}
/*
@@ -286,11 +302,11 @@ static char *unescape(char *str)
in += 2;
continue;
} else if (isodigit(in[1]) &&
- isodigit(in[2]) &&
- isodigit(in[3])) {
- *out++ = ((in[1] - '0')<<6) |
- ((in[2] - '0')<<3) |
- (in[3] - '0');
+ isodigit(in[2]) &&
+ isodigit(in[3])) {
+ *out++ = (((in[1] - '0') << 6) |
+ ((in[2] - '0') << 3) |
+ (in[3] - '0'));
in += 4;
continue;
}
@@ -308,8 +324,8 @@ static int check_set(const char **dest, char *src, char *name)
if (*dest) {
rc = -EINVAL;
- pr_err("match-spec:%s val:%s overridden by %s",
- name, *dest, src);
+ pr_err("match-spec:%s val:%s overridden by %s\n",
+ name, *dest, src);
}
*dest = src;
return rc;
@@ -337,40 +353,46 @@ static int ddebug_parse_query(char *words[], int nwords,
int rc;
/* check we have an even number of words */
- if (nwords % 2 != 0)
+ if (nwords % 2 != 0) {
+ pr_err("expecting pairs of match-spec <value>\n");
return -EINVAL;
+ }
memset(query, 0, sizeof(*query));
if (modname)
/* support $modname.dyndbg=<multiple queries> */
query->module = modname;
- for (i = 0 ; i < nwords ; i += 2) {
- if (!strcmp(words[i], "func"))
+ for (i = 0; i < nwords; i += 2) {
+ if (!strcmp(words[i], "func")) {
rc = check_set(&query->function, words[i+1], "func");
- else if (!strcmp(words[i], "file"))
+ } else if (!strcmp(words[i], "file")) {
rc = check_set(&query->filename, words[i+1], "file");
- else if (!strcmp(words[i], "module"))
+ } else if (!strcmp(words[i], "module")) {
rc = check_set(&query->module, words[i+1], "module");
- else if (!strcmp(words[i], "format"))
+ } else if (!strcmp(words[i], "format")) {
rc = check_set(&query->format, unescape(words[i+1]),
- "format");
- else if (!strcmp(words[i], "line")) {
+ "format");
+ } else if (!strcmp(words[i], "line")) {
char *first = words[i+1];
char *last = strchr(first, '-');
if (query->first_lineno || query->last_lineno) {
- pr_err("match-spec:line given 2 times\n");
+ pr_err("match-spec: line used 2x\n");
return -EINVAL;
}
if (last)
*last++ = '\0';
- if (parse_lineno(first, &query->first_lineno) < 0)
+ if (parse_lineno(first, &query->first_lineno) < 0) {
+ pr_err("line-number is <0\n");
return -EINVAL;
+ }
if (last) {
/* range <first>-<last> */
if (parse_lineno(last, &query->last_lineno)
< query->first_lineno) {
- pr_err("last-line < 1st-line\n");
+ pr_err("last-line:%d < 1st-line:%d\n",
+ query->last_lineno,
+ query->first_lineno);
return -EINVAL;
}
} else {
@@ -406,19 +428,22 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
op = *str++;
break;
default:
+ pr_err("bad flag-op %c, at start of %s\n", *str, str);
return -EINVAL;
}
vpr_info("op='%c'\n", op);
- for ( ; *str ; ++str) {
+ for (; *str ; ++str) {
for (i = ARRAY_SIZE(opt_array) - 1; i >= 0; i--) {
if (*str == opt_array[i].opt_char) {
flags |= opt_array[i].flag;
break;
}
}
- if (i < 0)
+ if (i < 0) {
+ pr_err("unknown flag '%c' in \"%s\"\n", *str, str);
return -EINVAL;
+ }
}
vpr_info("flags=0x%x\n", flags);
@@ -450,16 +475,22 @@ static int ddebug_exec_query(char *query_string, const char *modname)
char *words[MAXWORDS];
nwords = ddebug_tokenize(query_string, words, MAXWORDS);
- if (nwords <= 0)
+ if (nwords <= 0) {
+ pr_err("tokenize failed\n");
return -EINVAL;
- if (ddebug_parse_query(words, nwords-1, &query, modname))
+ }
+ /* check flags 1st (last arg) so query is pairs of spec,val */
+ if (ddebug_parse_flags(words[nwords-1], &flags, &mask)) {
+ pr_err("flags parse failed\n");
return -EINVAL;
- if (ddebug_parse_flags(words[nwords-1], &flags, &mask))
+ }
+ if (ddebug_parse_query(words, nwords-1, &query, modname)) {
+ pr_err("query parse failed\n");
return -EINVAL;
-
+ }
/* actually go and implement the change */
nfound = ddebug_change(&query, flags, mask);
- vpr_info_dq((&query), (nfound) ? "applied" : "no-match");
+ vpr_info_dq(&query, nfound ? "applied" : "no-match");
return nfound;
}
@@ -488,8 +519,9 @@ static int ddebug_exec_queries(char *query, const char *modname)
if (rc < 0) {
errs++;
exitcode = rc;
- } else
+ } else {
nfound += rc;
+ }
i++;
}
vpr_info("processed %d queries, with %d matches, %d errs\n",
@@ -765,7 +797,7 @@ static void *ddebug_proc_next(struct seq_file *m, void *p, loff_t *pos)
struct _ddebug *dp;
vpr_info("called m=%p p=%p *pos=%lld\n",
- m, p, (unsigned long long)*pos);
+ m, p, (unsigned long long)*pos);
if (p == SEQ_START_TOKEN)
dp = ddebug_iter_first(iter);
@@ -791,14 +823,14 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
if (p == SEQ_START_TOKEN) {
seq_puts(m,
- "# filename:lineno [module]function flags format\n");
+ "# filename:lineno [module]function flags format\n");
return 0;
}
seq_printf(m, "%s:%u [%s]%s =%s \"",
- trim_prefix(dp->filename), dp->lineno,
- iter->table->mod_name, dp->function,
- ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf)));
+ trim_prefix(dp->filename), dp->lineno,
+ iter->table->mod_name, dp->function,
+ ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf)));
seq_escape(m, dp->format, "\t\r\n\"");
seq_puts(m, "\"\n");
@@ -845,7 +877,7 @@ static int ddebug_proc_open(struct inode *inode, struct file *file)
kfree(iter);
return err;
}
- ((struct seq_file *) file->private_data)->private = iter;
+ ((struct seq_file *)file->private_data)->private = iter;
return 0;
}
@@ -1002,8 +1034,7 @@ static int __init dynamic_debug_init(void)
int verbose_bytes = 0;
if (__start___verbose == __stop___verbose) {
- pr_warn("_ddebug table is empty in a "
- "CONFIG_DYNAMIC_DEBUG build");
+ pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
return 1;
}
iter = __start___verbose;
@@ -1030,18 +1061,16 @@ static int __init dynamic_debug_init(void)
goto out_err;
ddebug_init_success = 1;
- vpr_info("%d modules, %d entries and %d bytes in ddebug tables,"
- " %d bytes in (readonly) verbose section\n",
- modct, entries, (int)( modct * sizeof(struct ddebug_table)),
- verbose_bytes + (int)(__stop___verbose - __start___verbose));
+ vpr_info("%d modules, %d entries and %d bytes in ddebug tables, %d bytes in (readonly) verbose section\n",
+ modct, entries, (int)(modct * sizeof(struct ddebug_table)),
+ verbose_bytes + (int)(__stop___verbose - __start___verbose));
/* apply ddebug_query boot param, dont unload tables on err */
if (ddebug_setup_string[0] != '\0') {
- pr_warn("ddebug_query param name is deprecated,"
- " change it to dyndbg\n");
+ pr_warn("ddebug_query param name is deprecated, change it to dyndbg\n");
ret = ddebug_exec_queries(ddebug_setup_string, NULL);
if (ret < 0)
- pr_warn("Invalid ddebug boot param %s",
+ pr_warn("Invalid ddebug boot param %s\n",
ddebug_setup_string);
else
pr_info("%d changes by ddebug_query\n", ret);
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 6540d65..3f0494c 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -227,6 +227,7 @@ void print_hex_dump(const char *level, const char *prefix_str, int prefix_type,
}
EXPORT_SYMBOL(print_hex_dump);
+#if !defined(CONFIG_DYNAMIC_DEBUG)
/**
* print_hex_dump_bytes - shorthand form of print_hex_dump() with default params
* @prefix_str: string to prefix each line with;
@@ -246,4 +247,5 @@ void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
buf, len, true);
}
EXPORT_SYMBOL(print_hex_dump_bytes);
-#endif
+#endif /* !defined(CONFIG_DYNAMIC_DEBUG) */
+#endif /* defined(CONFIG_PRINTK) */
diff --git a/lib/idr.c b/lib/idr.c
index 6482390..73f4d53 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -35,10 +35,41 @@
#include <linux/string.h>
#include <linux/idr.h>
#include <linux/spinlock.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+
+#define MAX_IDR_SHIFT (sizeof(int) * 8 - 1)
+#define MAX_IDR_BIT (1U << MAX_IDR_SHIFT)
+
+/* Leave the possibility of an incomplete final layer */
+#define MAX_IDR_LEVEL ((MAX_IDR_SHIFT + IDR_BITS - 1) / IDR_BITS)
+
+/* Number of id_layer structs to leave in free list */
+#define MAX_IDR_FREE (MAX_IDR_LEVEL * 2)
static struct kmem_cache *idr_layer_cache;
+static DEFINE_PER_CPU(struct idr_layer *, idr_preload_head);
+static DEFINE_PER_CPU(int, idr_preload_cnt);
static DEFINE_SPINLOCK(simple_ida_lock);
+/* the maximum ID which can be allocated given idr->layers */
+static int idr_max(int layers)
+{
+ int bits = min_t(int, layers * IDR_BITS, MAX_IDR_SHIFT);
+
+ return (1 << bits) - 1;
+}
+
+/*
+ * Prefix mask for an idr_layer at @layer. For layer 0, the prefix mask is
+ * all bits except for the lower IDR_BITS. For layer 1, 2 * IDR_BITS, and
+ * so on.
+ */
+static int idr_layer_prefix_mask(int layer)
+{
+ return ~idr_max(layer + 1);
+}
+
static struct idr_layer *get_from_free_list(struct idr *idp)
{
struct idr_layer *p;
@@ -54,6 +85,50 @@ static struct idr_layer *get_from_free_list(struct idr *idp)
return(p);
}
+/**
+ * idr_layer_alloc - allocate a new idr_layer
+ * @gfp_mask: allocation mask
+ * @layer_idr: optional idr to allocate from
+ *
+ * If @layer_idr is %NULL, directly allocate one using @gfp_mask or fetch
+ * one from the per-cpu preload buffer. If @layer_idr is not %NULL, fetch
+ * an idr_layer from @idr->id_free.
+ *
+ * @layer_idr is to maintain backward compatibility with the old alloc
+ * interface - idr_pre_get() and idr_get_new*() - and will be removed
+ * together with per-pool preload buffer.
+ */
+static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr)
+{
+ struct idr_layer *new;
+
+ /* this is the old path, bypass to get_from_free_list() */
+ if (layer_idr)
+ return get_from_free_list(layer_idr);
+
+ /* try to allocate directly from kmem_cache */
+ new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
+ if (new)
+ return new;
+
+ /*
+ * Try to fetch one from the per-cpu preload buffer if in process
+ * context. See idr_preload() for details.
+ */
+ if (in_interrupt())
+ return NULL;
+
+ preempt_disable();
+ new = __this_cpu_read(idr_preload_head);
+ if (new) {
+ __this_cpu_write(idr_preload_head, new->ary[0]);
+ __this_cpu_dec(idr_preload_cnt);
+ new->ary[0] = NULL;
+ }
+ preempt_enable();
+ return new;
+}
+
static void idr_layer_rcu_free(struct rcu_head *head)
{
struct idr_layer *layer;
@@ -62,8 +137,10 @@ static void idr_layer_rcu_free(struct rcu_head *head)
kmem_cache_free(idr_layer_cache, layer);
}
-static inline void free_layer(struct idr_layer *p)
+static inline void free_layer(struct idr *idr, struct idr_layer *p)
{
+ if (idr->hint && idr->hint == p)
+ RCU_INIT_POINTER(idr->hint, NULL);
call_rcu(&p->rcu_head, idr_layer_rcu_free);
}
@@ -92,18 +169,18 @@ static void idr_mark_full(struct idr_layer **pa, int id)
struct idr_layer *p = pa[0];
int l = 0;
- __set_bit(id & IDR_MASK, &p->bitmap);
+ __set_bit(id & IDR_MASK, p->bitmap);
/*
* If this layer is full mark the bit in the layer above to
* show that this part of the radix tree is full. This may
* complete the layer above and require walking up the radix
* tree.
*/
- while (p->bitmap == IDR_FULL) {
+ while (bitmap_full(p->bitmap, IDR_SIZE)) {
if (!(p = pa[++l]))
break;
id = id >> IDR_BITS;
- __set_bit((id & IDR_MASK), &p->bitmap);
+ __set_bit((id & IDR_MASK), p->bitmap);
}
}
@@ -133,12 +210,29 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
}
EXPORT_SYMBOL(idr_pre_get);
-static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
+/**
+ * sub_alloc - try to allocate an id without growing the tree depth
+ * @idp: idr handle
+ * @starting_id: id to start search at
+ * @id: pointer to the allocated handle
+ * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer
+ * @gfp_mask: allocation mask for idr_layer_alloc()
+ * @layer_idr: optional idr passed to idr_layer_alloc()
+ *
+ * Allocate an id in range [@starting_id, INT_MAX] from @idp without
+ * growing its depth. Returns
+ *
+ * the allocated id >= 0 if successful,
+ * -EAGAIN if the tree needs to grow for allocation to succeed,
+ * -ENOSPC if the id space is exhausted,
+ * -ENOMEM if more idr_layers need to be allocated.
+ */
+static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa,
+ gfp_t gfp_mask, struct idr *layer_idr)
{
int n, m, sh;
struct idr_layer *p, *new;
int l, id, oid;
- unsigned long bm;
id = *starting_id;
restart:
@@ -150,8 +244,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
* We run around this while until we reach the leaf node...
*/
n = (id >> (IDR_BITS*l)) & IDR_MASK;
- bm = ~p->bitmap;
- m = find_next_bit(&bm, IDR_SIZE, n);
+ m = find_next_zero_bit(p->bitmap, IDR_SIZE, n);
if (m == IDR_SIZE) {
/* no space available go back to previous layer. */
l++;
@@ -161,7 +254,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
/* if already at the top layer, we need to grow */
if (id >= 1 << (idp->layers * IDR_BITS)) {
*starting_id = id;
- return IDR_NEED_TO_GROW;
+ return -EAGAIN;
}
p = pa[l];
BUG_ON(!p);
@@ -180,17 +273,18 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
id = ((id >> sh) ^ n ^ m) << sh;
}
if ((id >= MAX_IDR_BIT) || (id < 0))
- return IDR_NOMORE_SPACE;
+ return -ENOSPC;
if (l == 0)
break;
/*
* Create the layer below if it is missing.
*/
if (!p->ary[m]) {
- new = get_from_free_list(idp);
+ new = idr_layer_alloc(gfp_mask, layer_idr);
if (!new)
- return -1;
+ return -ENOMEM;
new->layer = l-1;
+ new->prefix = id & idr_layer_prefix_mask(new->layer);
rcu_assign_pointer(p->ary[m], new);
p->count++;
}
@@ -203,7 +297,8 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
}
static int idr_get_empty_slot(struct idr *idp, int starting_id,
- struct idr_layer **pa)
+ struct idr_layer **pa, gfp_t gfp_mask,
+ struct idr *layer_idr)
{
struct idr_layer *p, *new;
int layers, v, id;
@@ -214,8 +309,8 @@ build_up:
p = idp->top;
layers = idp->layers;
if (unlikely(!p)) {
- if (!(p = get_from_free_list(idp)))
- return -1;
+ if (!(p = idr_layer_alloc(gfp_mask, layer_idr)))
+ return -ENOMEM;
p->layer = 0;
layers = 1;
}
@@ -223,7 +318,7 @@ build_up:
* Add a new layer to the top of the tree if the requested
* id is larger than the currently allocated space.
*/
- while ((layers < (MAX_IDR_LEVEL - 1)) && (id >= (1 << (layers*IDR_BITS)))) {
+ while (id > idr_max(layers)) {
layers++;
if (!p->count) {
/* special case: if the tree is currently empty,
@@ -231,9 +326,10 @@ build_up:
* upwards.
*/
p->layer++;
+ WARN_ON_ONCE(p->prefix);
continue;
}
- if (!(new = get_from_free_list(idp))) {
+ if (!(new = idr_layer_alloc(gfp_mask, layer_idr))) {
/*
* The allocation failed. If we built part of
* the structure tear it down.
@@ -242,45 +338,42 @@ build_up:
for (new = p; p && p != idp->top; new = p) {
p = p->ary[0];
new->ary[0] = NULL;
- new->bitmap = new->count = 0;
+ new->count = 0;
+ bitmap_clear(new->bitmap, 0, IDR_SIZE);
__move_to_free_list(idp, new);
}
spin_unlock_irqrestore(&idp->lock, flags);
- return -1;
+ return -ENOMEM;
}
new->ary[0] = p;
new->count = 1;
new->layer = layers-1;
- if (p->bitmap == IDR_FULL)
- __set_bit(0, &new->bitmap);
+ new->prefix = id & idr_layer_prefix_mask(new->layer);
+ if (bitmap_full(p->bitmap, IDR_SIZE))
+ __set_bit(0, new->bitmap);
p = new;
}
rcu_assign_pointer(idp->top, p);
idp->layers = layers;
- v = sub_alloc(idp, &id, pa);
- if (v == IDR_NEED_TO_GROW)
+ v = sub_alloc(idp, &id, pa, gfp_mask, layer_idr);
+ if (v == -EAGAIN)
goto build_up;
return(v);
}
-static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
+/*
+ * @id and @pa are from a successful allocation from idr_get_empty_slot().
+ * Install the user pointer @ptr and mark the slot full.
+ */
+static void idr_fill_slot(struct idr *idr, void *ptr, int id,
+ struct idr_layer **pa)
{
- struct idr_layer *pa[MAX_IDR_LEVEL];
- int id;
-
- id = idr_get_empty_slot(idp, starting_id, pa);
- if (id >= 0) {
- /*
- * Successfully found an empty slot. Install the user
- * pointer and mark the slot full.
- */
- rcu_assign_pointer(pa[0]->ary[id & IDR_MASK],
- (struct idr_layer *)ptr);
- pa[0]->count++;
- idr_mark_full(pa, id);
- }
+ /* update hint used for lookup, cleared from free_layer() */
+ rcu_assign_pointer(idr->hint, pa[0]);
- return id;
+ rcu_assign_pointer(pa[0]->ary[id & IDR_MASK], (struct idr_layer *)ptr);
+ pa[0]->count++;
+ idr_mark_full(pa, id);
}
/**
@@ -303,49 +396,124 @@ static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
*/
int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
{
+ struct idr_layer *pa[MAX_IDR_LEVEL + 1];
int rv;
- rv = idr_get_new_above_int(idp, ptr, starting_id);
- /*
- * This is a cheap hack until the IDR code can be fixed to
- * return proper error values.
- */
+ rv = idr_get_empty_slot(idp, starting_id, pa, 0, idp);
if (rv < 0)
- return _idr_rc_to_errno(rv);
+ return rv == -ENOMEM ? -EAGAIN : rv;
+
+ idr_fill_slot(idp, ptr, rv, pa);
*id = rv;
return 0;
}
EXPORT_SYMBOL(idr_get_new_above);
/**
- * idr_get_new - allocate new idr entry
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @id: pointer to the allocated handle
+ * idr_preload - preload for idr_alloc()
+ * @gfp_mask: allocation mask to use for preloading
*
- * If allocation from IDR's private freelist fails, idr_get_new_above() will
- * return %-EAGAIN. The caller should retry the idr_pre_get() call to refill
- * IDR's preallocation and then retry the idr_get_new_above() call.
+ * Preload per-cpu layer buffer for idr_alloc(). Can only be used from
+ * process context and each idr_preload() invocation should be matched with
+ * idr_preload_end(). Note that preemption is disabled while preloaded.
*
- * If the idr is full idr_get_new_above() will return %-ENOSPC.
+ * The first idr_alloc() in the preloaded section can be treated as if it
+ * were invoked with @gfp_mask used for preloading. This allows using more
+ * permissive allocation masks for idrs protected by spinlocks.
+ *
+ * For example, if idr_alloc() below fails, the failure can be treated as
+ * if idr_alloc() were called with GFP_KERNEL rather than GFP_NOWAIT.
+ *
+ * idr_preload(GFP_KERNEL);
+ * spin_lock(lock);
+ *
+ * id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT);
*
- * @id returns a value in the range %0 ... %0x7fffffff
+ * spin_unlock(lock);
+ * idr_preload_end();
+ * if (id < 0)
+ * error;
*/
-int idr_get_new(struct idr *idp, void *ptr, int *id)
+void idr_preload(gfp_t gfp_mask)
{
- int rv;
+ /*
+ * Consuming preload buffer from non-process context breaks preload
+ * allocation guarantee. Disallow usage from those contexts.
+ */
+ WARN_ON_ONCE(in_interrupt());
+ might_sleep_if(gfp_mask & __GFP_WAIT);
+
+ preempt_disable();
- rv = idr_get_new_above_int(idp, ptr, 0);
/*
- * This is a cheap hack until the IDR code can be fixed to
- * return proper error values.
+ * idr_alloc() is likely to succeed w/o full idr_layer buffer and
+ * return value from idr_alloc() needs to be checked for failure
+ * anyway. Silently give up if allocation fails. The caller can
+ * treat failures from idr_alloc() as if idr_alloc() were called
+ * with @gfp_mask which should be enough.
*/
- if (rv < 0)
- return _idr_rc_to_errno(rv);
- *id = rv;
- return 0;
+ while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) {
+ struct idr_layer *new;
+
+ preempt_enable();
+ new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
+ preempt_disable();
+ if (!new)
+ break;
+
+ /* link the new one to per-cpu preload list */
+ new->ary[0] = __this_cpu_read(idr_preload_head);
+ __this_cpu_write(idr_preload_head, new);
+ __this_cpu_inc(idr_preload_cnt);
+ }
}
-EXPORT_SYMBOL(idr_get_new);
+EXPORT_SYMBOL(idr_preload);
+
+/**
+ * idr_alloc - allocate new idr entry
+ * @idr: the (initialized) idr
+ * @ptr: pointer to be associated with the new id
+ * @start: the minimum id (inclusive)
+ * @end: the maximum id (exclusive, <= 0 for max)
+ * @gfp_mask: memory allocation flags
+ *
+ * Allocate an id in [start, end) and associate it with @ptr. If no ID is
+ * available in the specified range, returns -ENOSPC. On memory allocation
+ * failure, returns -ENOMEM.
+ *
+ * Note that @end is treated as max when <= 0. This is to always allow
+ * using @start + N as @end as long as N is inside integer range.
+ *
+ * The user is responsible for exclusively synchronizing all operations
+ * which may modify @idr. However, read-only accesses such as idr_find()
+ * or iteration can be performed under RCU read lock provided the user
+ * destroys @ptr in RCU-safe way after removal from idr.
+ */
+int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask)
+{
+ int max = end > 0 ? end - 1 : INT_MAX; /* inclusive upper limit */
+ struct idr_layer *pa[MAX_IDR_LEVEL + 1];
+ int id;
+
+ might_sleep_if(gfp_mask & __GFP_WAIT);
+
+ /* sanity checks */
+ if (WARN_ON_ONCE(start < 0))
+ return -EINVAL;
+ if (unlikely(max < start))
+ return -ENOSPC;
+
+ /* allocate id */
+ id = idr_get_empty_slot(idr, start, pa, gfp_mask, NULL);
+ if (unlikely(id < 0))
+ return id;
+ if (unlikely(id > max))
+ return -ENOSPC;
+
+ idr_fill_slot(idr, ptr, id, pa);
+ return id;
+}
+EXPORT_SYMBOL_GPL(idr_alloc);
static void idr_remove_warning(int id)
{
@@ -357,7 +525,7 @@ static void idr_remove_warning(int id)
static void sub_remove(struct idr *idp, int shift, int id)
{
struct idr_layer *p = idp->top;
- struct idr_layer **pa[MAX_IDR_LEVEL];
+ struct idr_layer **pa[MAX_IDR_LEVEL + 1];
struct idr_layer ***paa = &pa[0];
struct idr_layer *to_free;
int n;
@@ -367,26 +535,26 @@ static void sub_remove(struct idr *idp, int shift, int id)
while ((shift > 0) && p) {
n = (id >> shift) & IDR_MASK;
- __clear_bit(n, &p->bitmap);
+ __clear_bit(n, p->bitmap);
*++paa = &p->ary[n];
p = p->ary[n];
shift -= IDR_BITS;
}
n = id & IDR_MASK;
- if (likely(p != NULL && test_bit(n, &p->bitmap))){
- __clear_bit(n, &p->bitmap);
+ if (likely(p != NULL && test_bit(n, p->bitmap))) {
+ __clear_bit(n, p->bitmap);
rcu_assign_pointer(p->ary[n], NULL);
to_free = NULL;
while(*paa && ! --((**paa)->count)){
if (to_free)
- free_layer(to_free);
+ free_layer(idp, to_free);
to_free = **paa;
**paa-- = NULL;
}
if (!*paa)
idp->layers = 0;
if (to_free)
- free_layer(to_free);
+ free_layer(idp, to_free);
} else
idr_remove_warning(id);
}
@@ -401,8 +569,9 @@ void idr_remove(struct idr *idp, int id)
struct idr_layer *p;
struct idr_layer *to_free;
- /* Mask off upper bits we don't use for the search. */
- id &= MAX_IDR_MASK;
+ /* see comment in idr_find_slowpath() */
+ if (WARN_ON_ONCE(id < 0))
+ return;
sub_remove(idp, (idp->layers - 1) * IDR_BITS, id);
if (idp->top && idp->top->count == 1 && (idp->layers > 1) &&
@@ -417,8 +586,9 @@ void idr_remove(struct idr *idp, int id)
p = idp->top->ary[0];
rcu_assign_pointer(idp->top, p);
--idp->layers;
- to_free->bitmap = to_free->count = 0;
- free_layer(to_free);
+ to_free->count = 0;
+ bitmap_clear(to_free->bitmap, 0, IDR_SIZE);
+ free_layer(idp, to_free);
}
while (idp->id_free_cnt >= MAX_IDR_FREE) {
p = get_from_free_list(idp);
@@ -433,34 +603,21 @@ void idr_remove(struct idr *idp, int id)
}
EXPORT_SYMBOL(idr_remove);
-/**
- * idr_remove_all - remove all ids from the given idr tree
- * @idp: idr handle
- *
- * idr_destroy() only frees up unused, cached idp_layers, but this
- * function will remove all id mappings and leave all idp_layers
- * unused.
- *
- * A typical clean-up sequence for objects stored in an idr tree will
- * use idr_for_each() to free all objects, if necessay, then
- * idr_remove_all() to remove all ids, and idr_destroy() to free
- * up the cached idr_layers.
- */
-void idr_remove_all(struct idr *idp)
+void __idr_remove_all(struct idr *idp)
{
int n, id, max;
int bt_mask;
struct idr_layer *p;
- struct idr_layer *pa[MAX_IDR_LEVEL];
+ struct idr_layer *pa[MAX_IDR_LEVEL + 1];
struct idr_layer **paa = &pa[0];
n = idp->layers * IDR_BITS;
p = idp->top;
rcu_assign_pointer(idp->top, NULL);
- max = 1 << n;
+ max = idr_max(idp->layers);
id = 0;
- while (id < max) {
+ while (id >= 0 && id <= max) {
while (n > IDR_BITS && p) {
n -= IDR_BITS;
*paa++ = p;
@@ -472,21 +629,32 @@ void idr_remove_all(struct idr *idp)
/* Get the highest bit that the above add changed from 0->1. */
while (n < fls(id ^ bt_mask)) {
if (p)
- free_layer(p);
+ free_layer(idp, p);
n += IDR_BITS;
p = *--paa;
}
}
idp->layers = 0;
}
-EXPORT_SYMBOL(idr_remove_all);
+EXPORT_SYMBOL(__idr_remove_all);
/**
* idr_destroy - release all cached layers within an idr tree
* @idp: idr handle
+ *
+ * Free all id mappings and all idp_layers. After this function, @idp is
+ * completely unused and can be freed / recycled. The caller is
+ * responsible for ensuring that no one else accesses @idp during or after
+ * idr_destroy().
+ *
+ * A typical clean-up sequence for objects stored in an idr tree will use
+ * idr_for_each() to free all objects, if necessay, then idr_destroy() to
+ * free up the id mappings and cached idr_layers.
*/
void idr_destroy(struct idr *idp)
{
+ __idr_remove_all(idp);
+
while (idp->id_free_cnt) {
struct idr_layer *p = get_from_free_list(idp);
kmem_cache_free(idr_layer_cache, p);
@@ -494,32 +662,28 @@ void idr_destroy(struct idr *idp)
}
EXPORT_SYMBOL(idr_destroy);
-/**
- * idr_find - return pointer for given id
- * @idp: idr handle
- * @id: lookup key
- *
- * Return the pointer given the id it has been registered with. A %NULL
- * return indicates that @id is not valid or you passed %NULL in
- * idr_get_new().
- *
- * This function can be called under rcu_read_lock(), given that the leaf
- * pointers lifetimes are correctly managed.
- */
-void *idr_find(struct idr *idp, int id)
+void *idr_find_slowpath(struct idr *idp, int id)
{
int n;
struct idr_layer *p;
+ /*
+ * If @id is negative, idr_find() used to ignore the sign bit and
+ * performed lookup with the rest of bits, which is weird and can
+ * lead to very obscure bugs. We're now returning NULL for all
+ * negative IDs but just in case somebody was depending on the sign
+ * bit being ignored, let's trigger WARN_ON_ONCE() so that they can
+ * be detected and fixed. WARN_ON_ONCE() can later be removed.
+ */
+ if (WARN_ON_ONCE(id < 0))
+ return NULL;
+
p = rcu_dereference_raw(idp->top);
if (!p)
return NULL;
n = (p->layer+1) * IDR_BITS;
- /* Mask off upper bits we don't use for the search. */
- id &= MAX_IDR_MASK;
-
- if (id >= (1 << n))
+ if (id > idr_max(p->layer + 1))
return NULL;
BUG_ON(n == 0);
@@ -530,7 +694,7 @@ void *idr_find(struct idr *idp, int id)
}
return((void *)p);
}
-EXPORT_SYMBOL(idr_find);
+EXPORT_SYMBOL(idr_find_slowpath);
/**
* idr_for_each - iterate through all stored pointers
@@ -555,15 +719,15 @@ int idr_for_each(struct idr *idp,
{
int n, id, max, error = 0;
struct idr_layer *p;
- struct idr_layer *pa[MAX_IDR_LEVEL];
+ struct idr_layer *pa[MAX_IDR_LEVEL + 1];
struct idr_layer **paa = &pa[0];
n = idp->layers * IDR_BITS;
p = rcu_dereference_raw(idp->top);
- max = 1 << n;
+ max = idr_max(idp->layers);
id = 0;
- while (id < max) {
+ while (id >= 0 && id <= max) {
while (n > 0 && p) {
n -= IDR_BITS;
*paa++ = p;
@@ -601,7 +765,7 @@ EXPORT_SYMBOL(idr_for_each);
*/
void *idr_get_next(struct idr *idp, int *nextidp)
{
- struct idr_layer *p, *pa[MAX_IDR_LEVEL];
+ struct idr_layer *p, *pa[MAX_IDR_LEVEL + 1];
struct idr_layer **paa = &pa[0];
int id = *nextidp;
int n, max;
@@ -611,9 +775,9 @@ void *idr_get_next(struct idr *idp, int *nextidp)
if (!p)
return NULL;
n = (p->layer + 1) * IDR_BITS;
- max = 1 << n;
+ max = idr_max(p->layer + 1);
- while (id < max) {
+ while (id >= 0 && id <= max) {
while (n > 0 && p) {
n -= IDR_BITS;
*paa++ = p;
@@ -625,7 +789,14 @@ void *idr_get_next(struct idr *idp, int *nextidp)
return p;
}
- id += 1 << n;
+ /*
+ * Proceed to the next layer at the current level. Unlike
+ * idr_for_each(), @id isn't guaranteed to be aligned to
+ * layer boundary at this point and adding 1 << n may
+ * incorrectly skip IDs. Make sure we jump to the
+ * beginning of the next layer using round_up().
+ */
+ id = round_up(id + 1, 1 << n);
while (n < fls(id)) {
n += IDR_BITS;
p = *--paa;
@@ -653,14 +824,16 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
int n;
struct idr_layer *p, *old_p;
+ /* see comment in idr_find_slowpath() */
+ if (WARN_ON_ONCE(id < 0))
+ return ERR_PTR(-EINVAL);
+
p = idp->top;
if (!p)
return ERR_PTR(-EINVAL);
n = (p->layer+1) * IDR_BITS;
- id &= MAX_IDR_MASK;
-
if (id >= (1 << n))
return ERR_PTR(-EINVAL);
@@ -671,7 +844,7 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
}
n = id & IDR_MASK;
- if (unlikely(p == NULL || !test_bit(n, &p->bitmap)))
+ if (unlikely(p == NULL || !test_bit(n, p->bitmap)))
return ERR_PTR(-ENOENT);
old_p = p->ary[n];
@@ -780,7 +953,7 @@ EXPORT_SYMBOL(ida_pre_get);
*/
int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
{
- struct idr_layer *pa[MAX_IDR_LEVEL];
+ struct idr_layer *pa[MAX_IDR_LEVEL + 1];
struct ida_bitmap *bitmap;
unsigned long flags;
int idr_id = starting_id / IDA_BITMAP_BITS;
@@ -789,9 +962,9 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
restart:
/* get vacant slot */
- t = idr_get_empty_slot(&ida->idr, idr_id, pa);
+ t = idr_get_empty_slot(&ida->idr, idr_id, pa, 0, &ida->idr);
if (t < 0)
- return _idr_rc_to_errno(t);
+ return t == -ENOMEM ? -EAGAIN : t;
if (t * IDA_BITMAP_BITS >= MAX_IDR_BIT)
return -ENOSPC;
@@ -852,25 +1025,6 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
EXPORT_SYMBOL(ida_get_new_above);
/**
- * ida_get_new - allocate new ID
- * @ida: idr handle
- * @p_id: pointer to the allocated handle
- *
- * Allocate new ID. It should be called with any required locks.
- *
- * If memory is required, it will return %-EAGAIN, you should unlock
- * and go back to the idr_pre_get() call. If the idr is full, it will
- * return %-ENOSPC.
- *
- * @p_id returns a value in the range %0 ... %0x7fffffff.
- */
-int ida_get_new(struct ida *ida, int *p_id)
-{
- return ida_get_new_above(ida, 0, p_id);
-}
-EXPORT_SYMBOL(ida_get_new);
-
-/**
* ida_remove - remove the given ID
* @ida: ida handle
* @id: ID to free
@@ -887,7 +1041,7 @@ void ida_remove(struct ida *ida, int id)
/* clear full bits while looking up the leaf idr_layer */
while ((shift > 0) && p) {
n = (idr_id >> shift) & IDR_MASK;
- __clear_bit(n, &p->bitmap);
+ __clear_bit(n, p->bitmap);
p = p->ary[n];
shift -= IDR_BITS;
}
@@ -896,7 +1050,7 @@ void ida_remove(struct ida *ida, int id)
goto err;
n = idr_id & IDR_MASK;
- __clear_bit(n, &p->bitmap);
+ __clear_bit(n, p->bitmap);
bitmap = (void *)p->ary[n];
if (!test_bit(offset, bitmap->bitmap))
@@ -905,7 +1059,7 @@ void ida_remove(struct ida *ida, int id)
/* update bitmap and remove it if empty */
__clear_bit(offset, bitmap->bitmap);
if (--bitmap->nr_busy == 0) {
- __set_bit(n, &p->bitmap); /* to please idr_remove() */
+ __set_bit(n, p->bitmap); /* to please idr_remove() */
idr_remove(&ida->idr, idr_id);
free_bitmap(ida, bitmap);
}
diff --git a/lib/kfifo.c b/lib/kfifo.c
new file mode 100644
index 0000000..7b7f830
--- /dev/null
+++ b/lib/kfifo.c
@@ -0,0 +1,607 @@
+/*
+ * A generic kernel FIFO implementation
+ *
+ * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/log2.h>
+#include <linux/uaccess.h>
+#include <linux/kfifo.h>
+
+/*
+ * internal helper to calculate the unused elements in a fifo
+ */
+static inline unsigned int kfifo_unused(struct __kfifo *fifo)
+{
+ return (fifo->mask + 1) - (fifo->in - fifo->out);
+}
+
+int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
+ size_t esize, gfp_t gfp_mask)
+{
+ /*
+ * round down to the next power of 2, since our 'let the indices
+ * wrap' technique works only in this case.
+ */
+ size = roundup_pow_of_two(size);
+
+ fifo->in = 0;
+ fifo->out = 0;
+ fifo->esize = esize;
+
+ if (size < 2) {
+ fifo->data = NULL;
+ fifo->mask = 0;
+ return -EINVAL;
+ }
+
+ fifo->data = kmalloc(size * esize, gfp_mask);
+
+ if (!fifo->data) {
+ fifo->mask = 0;
+ return -ENOMEM;
+ }
+ fifo->mask = size - 1;
+
+ return 0;
+}
+EXPORT_SYMBOL(__kfifo_alloc);
+
+void __kfifo_free(struct __kfifo *fifo)
+{
+ kfree(fifo->data);
+ fifo->in = 0;
+ fifo->out = 0;
+ fifo->esize = 0;
+ fifo->data = NULL;
+ fifo->mask = 0;
+}
+EXPORT_SYMBOL(__kfifo_free);
+
+int __kfifo_init(struct __kfifo *fifo, void *buffer,
+ unsigned int size, size_t esize)
+{
+ size /= esize;
+
+ size = roundup_pow_of_two(size);
+
+ fifo->in = 0;
+ fifo->out = 0;
+ fifo->esize = esize;
+ fifo->data = buffer;
+
+ if (size < 2) {
+ fifo->mask = 0;
+ return -EINVAL;
+ }
+ fifo->mask = size - 1;
+
+ return 0;
+}
+EXPORT_SYMBOL(__kfifo_init);
+
+static void kfifo_copy_in(struct __kfifo *fifo, const void *src,
+ unsigned int len, unsigned int off)
+{
+ unsigned int size = fifo->mask + 1;
+ unsigned int esize = fifo->esize;
+ unsigned int l;
+
+ off &= fifo->mask;
+ if (esize != 1) {
+ off *= esize;
+ size *= esize;
+ len *= esize;
+ }
+ l = min(len, size - off);
+
+ memcpy(fifo->data + off, src, l);
+ memcpy(fifo->data, src + l, len - l);
+ /*
+ * make sure that the data in the fifo is up to date before
+ * incrementing the fifo->in index counter
+ */
+ smp_wmb();
+}
+
+unsigned int __kfifo_in(struct __kfifo *fifo,
+ const void *buf, unsigned int len)
+{
+ unsigned int l;
+
+ l = kfifo_unused(fifo);
+ if (len > l)
+ len = l;
+
+ kfifo_copy_in(fifo, buf, len, fifo->in);
+ fifo->in += len;
+ return len;
+}
+EXPORT_SYMBOL(__kfifo_in);
+
+static void kfifo_copy_out(struct __kfifo *fifo, void *dst,
+ unsigned int len, unsigned int off)
+{
+ unsigned int size = fifo->mask + 1;
+ unsigned int esize = fifo->esize;
+ unsigned int l;
+
+ off &= fifo->mask;
+ if (esize != 1) {
+ off *= esize;
+ size *= esize;
+ len *= esize;
+ }
+ l = min(len, size - off);
+
+ memcpy(dst, fifo->data + off, l);
+ memcpy(dst + l, fifo->data, len - l);
+ /*
+ * make sure that the data is copied before
+ * incrementing the fifo->out index counter
+ */
+ smp_wmb();
+}
+
+unsigned int __kfifo_out_peek(struct __kfifo *fifo,
+ void *buf, unsigned int len)
+{
+ unsigned int l;
+
+ l = fifo->in - fifo->out;
+ if (len > l)
+ len = l;
+
+ kfifo_copy_out(fifo, buf, len, fifo->out);
+ return len;
+}
+EXPORT_SYMBOL(__kfifo_out_peek);
+
+unsigned int __kfifo_out(struct __kfifo *fifo,
+ void *buf, unsigned int len)
+{
+ len = __kfifo_out_peek(fifo, buf, len);
+ fifo->out += len;
+ return len;
+}
+EXPORT_SYMBOL(__kfifo_out);
+
+static unsigned long kfifo_copy_from_user(struct __kfifo *fifo,
+ const void __user *from, unsigned int len, unsigned int off,
+ unsigned int *copied)
+{
+ unsigned int size = fifo->mask + 1;
+ unsigned int esize = fifo->esize;
+ unsigned int l;
+ unsigned long ret;
+
+ off &= fifo->mask;
+ if (esize != 1) {
+ off *= esize;
+ size *= esize;
+ len *= esize;
+ }
+ l = min(len, size - off);
+
+ ret = copy_from_user(fifo->data + off, from, l);
+ if (unlikely(ret))
+ ret = DIV_ROUND_UP(ret + len - l, esize);
+ else {
+ ret = copy_from_user(fifo->data, from + l, len - l);
+ if (unlikely(ret))
+ ret = DIV_ROUND_UP(ret, esize);
+ }
+ /*
+ * make sure that the data in the fifo is up to date before
+ * incrementing the fifo->in index counter
+ */
+ smp_wmb();
+ *copied = len - ret;
+ /* return the number of elements which are not copied */
+ return ret;
+}
+
+int __kfifo_from_user(struct __kfifo *fifo, const void __user *from,
+ unsigned long len, unsigned int *copied)
+{
+ unsigned int l;
+ unsigned long ret;
+ unsigned int esize = fifo->esize;
+ int err;
+
+ if (esize != 1)
+ len /= esize;
+
+ l = kfifo_unused(fifo);
+ if (len > l)
+ len = l;
+
+ ret = kfifo_copy_from_user(fifo, from, len, fifo->in, copied);
+ if (unlikely(ret)) {
+ len -= ret;
+ err = -EFAULT;
+ } else
+ err = 0;
+ fifo->in += len;
+ return err;
+}
+EXPORT_SYMBOL(__kfifo_from_user);
+
+static unsigned long kfifo_copy_to_user(struct __kfifo *fifo, void __user *to,
+ unsigned int len, unsigned int off, unsigned int *copied)
+{
+ unsigned int l;
+ unsigned long ret;
+ unsigned int size = fifo->mask + 1;
+ unsigned int esize = fifo->esize;
+
+ off &= fifo->mask;
+ if (esize != 1) {
+ off *= esize;
+ size *= esize;
+ len *= esize;
+ }
+ l = min(len, size - off);
+
+ ret = copy_to_user(to, fifo->data + off, l);
+ if (unlikely(ret))
+ ret = DIV_ROUND_UP(ret + len - l, esize);
+ else {
+ ret = copy_to_user(to + l, fifo->data, len - l);
+ if (unlikely(ret))
+ ret = DIV_ROUND_UP(ret, esize);
+ }
+ /*
+ * make sure that the data is copied before
+ * incrementing the fifo->out index counter
+ */
+ smp_wmb();
+ *copied = len - ret;
+ /* return the number of elements which are not copied */
+ return ret;
+}
+
+int __kfifo_to_user(struct __kfifo *fifo, void __user *to,
+ unsigned long len, unsigned int *copied)
+{
+ unsigned int l;
+ unsigned long ret;
+ unsigned int esize = fifo->esize;
+ int err;
+
+ if (esize != 1)
+ len /= esize;
+
+ l = fifo->in - fifo->out;
+ if (len > l)
+ len = l;
+ ret = kfifo_copy_to_user(fifo, to, len, fifo->out, copied);
+ if (unlikely(ret)) {
+ len -= ret;
+ err = -EFAULT;
+ } else
+ err = 0;
+ fifo->out += len;
+ return err;
+}
+EXPORT_SYMBOL(__kfifo_to_user);
+
+static int setup_sgl_buf(struct scatterlist *sgl, void *buf,
+ int nents, unsigned int len)
+{
+ int n;
+ unsigned int l;
+ unsigned int off;
+ struct page *page;
+
+ if (!nents)
+ return 0;
+
+ if (!len)
+ return 0;
+
+ n = 0;
+ page = virt_to_page(buf);
+ off = offset_in_page(buf);
+ l = 0;
+
+ while (len >= l + PAGE_SIZE - off) {
+ struct page *npage;
+
+ l += PAGE_SIZE;
+ buf += PAGE_SIZE;
+ npage = virt_to_page(buf);
+ if (page_to_phys(page) != page_to_phys(npage) - l) {
+ sg_set_page(sgl, page, l - off, off);
+ sgl = sg_next(sgl);
+ if (++n == nents || sgl == NULL)
+ return n;
+ page = npage;
+ len -= l - off;
+ l = off = 0;
+ }
+ }
+ sg_set_page(sgl, page, len, off);
+ return n + 1;
+}
+
+static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl,
+ int nents, unsigned int len, unsigned int off)
+{
+ unsigned int size = fifo->mask + 1;
+ unsigned int esize = fifo->esize;
+ unsigned int l;
+ unsigned int n;
+
+ off &= fifo->mask;
+ if (esize != 1) {
+ off *= esize;
+ size *= esize;
+ len *= esize;
+ }
+ l = min(len, size - off);
+
+ n = setup_sgl_buf(sgl, fifo->data + off, nents, l);
+ n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l);
+
+ return n;
+}
+
+unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo,
+ struct scatterlist *sgl, int nents, unsigned int len)
+{
+ unsigned int l;
+
+ l = kfifo_unused(fifo);
+ if (len > l)
+ len = l;
+
+ return setup_sgl(fifo, sgl, nents, len, fifo->in);
+}
+EXPORT_SYMBOL(__kfifo_dma_in_prepare);
+
+unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo,
+ struct scatterlist *sgl, int nents, unsigned int len)
+{
+ unsigned int l;
+
+ l = fifo->in - fifo->out;
+ if (len > l)
+ len = l;
+
+ return setup_sgl(fifo, sgl, nents, len, fifo->out);
+}
+EXPORT_SYMBOL(__kfifo_dma_out_prepare);
+
+unsigned int __kfifo_max_r(unsigned int len, size_t recsize)
+{
+ unsigned int max = (1 << (recsize << 3)) - 1;
+
+ if (len > max)
+ return max;
+ return len;
+}
+EXPORT_SYMBOL(__kfifo_max_r);
+
+#define __KFIFO_PEEK(data, out, mask) \
+ ((data)[(out) & (mask)])
+/*
+ * __kfifo_peek_n internal helper function for determinate the length of
+ * the next record in the fifo
+ */
+static unsigned int __kfifo_peek_n(struct __kfifo *fifo, size_t recsize)
+{
+ unsigned int l;
+ unsigned int mask = fifo->mask;
+ unsigned char *data = fifo->data;
+
+ l = __KFIFO_PEEK(data, fifo->out, mask);
+
+ if (--recsize)
+ l |= __KFIFO_PEEK(data, fifo->out + 1, mask) << 8;
+
+ return l;
+}
+
+#define __KFIFO_POKE(data, in, mask, val) \
+ ( \
+ (data)[(in) & (mask)] = (unsigned char)(val) \
+ )
+
+/*
+ * __kfifo_poke_n internal helper function for storeing the length of
+ * the record into the fifo
+ */
+static void __kfifo_poke_n(struct __kfifo *fifo, unsigned int n, size_t recsize)
+{
+ unsigned int mask = fifo->mask;
+ unsigned char *data = fifo->data;
+
+ __KFIFO_POKE(data, fifo->in, mask, n);
+
+ if (recsize > 1)
+ __KFIFO_POKE(data, fifo->in + 1, mask, n >> 8);
+}
+
+unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize)
+{
+ return __kfifo_peek_n(fifo, recsize);
+}
+EXPORT_SYMBOL(__kfifo_len_r);
+
+unsigned int __kfifo_in_r(struct __kfifo *fifo, const void *buf,
+ unsigned int len, size_t recsize)
+{
+ if (len + recsize > kfifo_unused(fifo))
+ return 0;
+
+ __kfifo_poke_n(fifo, len, recsize);
+
+ kfifo_copy_in(fifo, buf, len, fifo->in + recsize);
+ fifo->in += len + recsize;
+ return len;
+}
+EXPORT_SYMBOL(__kfifo_in_r);
+
+static unsigned int kfifo_out_copy_r(struct __kfifo *fifo,
+ void *buf, unsigned int len, size_t recsize, unsigned int *n)
+{
+ *n = __kfifo_peek_n(fifo, recsize);
+
+ if (len > *n)
+ len = *n;
+
+ kfifo_copy_out(fifo, buf, len, fifo->out + recsize);
+ return len;
+}
+
+unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf,
+ unsigned int len, size_t recsize)
+{
+ unsigned int n;
+
+ if (fifo->in == fifo->out)
+ return 0;
+
+ return kfifo_out_copy_r(fifo, buf, len, recsize, &n);
+}
+EXPORT_SYMBOL(__kfifo_out_peek_r);
+
+unsigned int __kfifo_out_r(struct __kfifo *fifo, void *buf,
+ unsigned int len, size_t recsize)
+{
+ unsigned int n;
+
+ if (fifo->in == fifo->out)
+ return 0;
+
+ len = kfifo_out_copy_r(fifo, buf, len, recsize, &n);
+ fifo->out += n + recsize;
+ return len;
+}
+EXPORT_SYMBOL(__kfifo_out_r);
+
+void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize)
+{
+ unsigned int n;
+
+ n = __kfifo_peek_n(fifo, recsize);
+ fifo->out += n + recsize;
+}
+EXPORT_SYMBOL(__kfifo_skip_r);
+
+int __kfifo_from_user_r(struct __kfifo *fifo, const void __user *from,
+ unsigned long len, unsigned int *copied, size_t recsize)
+{
+ unsigned long ret;
+
+ len = __kfifo_max_r(len, recsize);
+
+ if (len + recsize > kfifo_unused(fifo)) {
+ *copied = 0;
+ return 0;
+ }
+
+ __kfifo_poke_n(fifo, len, recsize);
+
+ ret = kfifo_copy_from_user(fifo, from, len, fifo->in + recsize, copied);
+ if (unlikely(ret)) {
+ *copied = 0;
+ return -EFAULT;
+ }
+ fifo->in += len + recsize;
+ return 0;
+}
+EXPORT_SYMBOL(__kfifo_from_user_r);
+
+int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to,
+ unsigned long len, unsigned int *copied, size_t recsize)
+{
+ unsigned long ret;
+ unsigned int n;
+
+ if (fifo->in == fifo->out) {
+ *copied = 0;
+ return 0;
+ }
+
+ n = __kfifo_peek_n(fifo, recsize);
+ if (len > n)
+ len = n;
+
+ ret = kfifo_copy_to_user(fifo, to, len, fifo->out + recsize, copied);
+ if (unlikely(ret)) {
+ *copied = 0;
+ return -EFAULT;
+ }
+ fifo->out += n + recsize;
+ return 0;
+}
+EXPORT_SYMBOL(__kfifo_to_user_r);
+
+unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo,
+ struct scatterlist *sgl, int nents, unsigned int len, size_t recsize)
+{
+ if (!nents)
+ BUG();
+
+ len = __kfifo_max_r(len, recsize);
+
+ if (len + recsize > kfifo_unused(fifo))
+ return 0;
+
+ return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize);
+}
+EXPORT_SYMBOL(__kfifo_dma_in_prepare_r);
+
+void __kfifo_dma_in_finish_r(struct __kfifo *fifo,
+ unsigned int len, size_t recsize)
+{
+ len = __kfifo_max_r(len, recsize);
+ __kfifo_poke_n(fifo, len, recsize);
+ fifo->in += len + recsize;
+}
+EXPORT_SYMBOL(__kfifo_dma_in_finish_r);
+
+unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo,
+ struct scatterlist *sgl, int nents, unsigned int len, size_t recsize)
+{
+ if (!nents)
+ BUG();
+
+ len = __kfifo_max_r(len, recsize);
+
+ if (len + recsize > fifo->in - fifo->out)
+ return 0;
+
+ return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize);
+}
+EXPORT_SYMBOL(__kfifo_dma_out_prepare_r);
+
+void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize)
+{
+ unsigned int len;
+
+ len = __kfifo_peek_n(fifo, recsize);
+ fifo->out += len + recsize;
+}
+EXPORT_SYMBOL(__kfifo_dma_out_finish_r);
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 7aae0f2..c3eb261 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -47,10 +47,10 @@ __setup("debug_locks_verbose=", setup_debug_locks_verbose);
* Normal standalone locks, for the circular and irq-context
* dependency tests:
*/
-static DEFINE_SPINLOCK(lock_A);
-static DEFINE_SPINLOCK(lock_B);
-static DEFINE_SPINLOCK(lock_C);
-static DEFINE_SPINLOCK(lock_D);
+static DEFINE_RAW_SPINLOCK(lock_A);
+static DEFINE_RAW_SPINLOCK(lock_B);
+static DEFINE_RAW_SPINLOCK(lock_C);
+static DEFINE_RAW_SPINLOCK(lock_D);
static DEFINE_RWLOCK(rwlock_A);
static DEFINE_RWLOCK(rwlock_B);
@@ -73,12 +73,12 @@ static DECLARE_RWSEM(rwsem_D);
* but X* and Y* are different classes. We do this so that
* we do not trigger a real lockup:
*/
-static DEFINE_SPINLOCK(lock_X1);
-static DEFINE_SPINLOCK(lock_X2);
-static DEFINE_SPINLOCK(lock_Y1);
-static DEFINE_SPINLOCK(lock_Y2);
-static DEFINE_SPINLOCK(lock_Z1);
-static DEFINE_SPINLOCK(lock_Z2);
+static DEFINE_RAW_SPINLOCK(lock_X1);
+static DEFINE_RAW_SPINLOCK(lock_X2);
+static DEFINE_RAW_SPINLOCK(lock_Y1);
+static DEFINE_RAW_SPINLOCK(lock_Y2);
+static DEFINE_RAW_SPINLOCK(lock_Z1);
+static DEFINE_RAW_SPINLOCK(lock_Z2);
static DEFINE_RWLOCK(rwlock_X1);
static DEFINE_RWLOCK(rwlock_X2);
@@ -107,10 +107,10 @@ static DECLARE_RWSEM(rwsem_Z2);
*/
#define INIT_CLASS_FUNC(class) \
static noinline void \
-init_class_##class(spinlock_t *lock, rwlock_t *rwlock, struct mutex *mutex, \
- struct rw_semaphore *rwsem) \
+init_class_##class(raw_spinlock_t *lock, rwlock_t *rwlock, \
+ struct mutex *mutex, struct rw_semaphore *rwsem)\
{ \
- spin_lock_init(lock); \
+ raw_spin_lock_init(lock); \
rwlock_init(rwlock); \
mutex_init(mutex); \
init_rwsem(rwsem); \
@@ -168,10 +168,10 @@ static void init_shared_classes(void)
* Shortcuts for lock/unlock API variants, to keep
* the testcases compact:
*/
-#define L(x) spin_lock(&lock_##x)
-#define U(x) spin_unlock(&lock_##x)
+#define L(x) raw_spin_lock(&lock_##x)
+#define U(x) raw_spin_unlock(&lock_##x)
#define LU(x) L(x); U(x)
-#define SI(x) spin_lock_init(&lock_##x)
+#define SI(x) raw_spin_lock_init(&lock_##x)
#define WL(x) write_lock(&rwlock_##x)
#define WU(x) write_unlock(&rwlock_##x)
@@ -911,7 +911,7 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft)
#define I2(x) \
do { \
- spin_lock_init(&lock_##x); \
+ raw_spin_lock_init(&lock_##x); \
rwlock_init(&rwlock_##x); \
mutex_init(&mutex_##x); \
init_rwsem(&rwsem_##x); \
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
index d71d894..8335d39 100644
--- a/lib/lru_cache.c
+++ b/lib/lru_cache.c
@@ -262,12 +262,11 @@ static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr)
static struct lc_element *__lc_find(struct lru_cache *lc, unsigned int enr,
bool include_changing)
{
- struct hlist_node *n;
struct lc_element *e;
BUG_ON(!lc);
BUG_ON(!lc->nr_elements);
- hlist_for_each_entry(e, n, lc_hash_slot(lc, enr), colision) {
+ hlist_for_each_entry(e, lc_hash_slot(lc, enr), colision) {
/* "about to be changed" elements, pending transaction commit,
* are hashed by their "new number". "Normal" elements have
* lc_number == lc_new_number. */
diff --git a/lib/mpi/mpi-internal.h b/lib/mpi/mpi-internal.h
index 77adcf6..60cf765 100644
--- a/lib/mpi/mpi-internal.h
+++ b/lib/mpi/mpi-internal.h
@@ -65,10 +65,6 @@
typedef mpi_limb_t *mpi_ptr_t; /* pointer to a limb */
typedef int mpi_size_t; /* (must be a signed type) */
-#define ABS(x) (x >= 0 ? x : -x)
-#define MIN(l, o) ((l) < (o) ? (l) : (o))
-#define MAX(h, i) ((h) > (i) ? (h) : (i))
-
static inline int RESIZE_IF_NEEDED(MPI a, unsigned b)
{
if (a->alloced < b)
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 3962b7f..5f9c44c 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -52,7 +52,7 @@ MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes)
else
nbits = 0;
- nlimbs = (nbytes + BYTES_PER_MPI_LIMB - 1) / BYTES_PER_MPI_LIMB;
+ nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
val = mpi_alloc(nlimbs);
if (!val)
return NULL;
@@ -96,8 +96,8 @@ MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread)
buffer += 2;
nread = 2;
- nbytes = (nbits + 7) / 8;
- nlimbs = (nbytes + BYTES_PER_MPI_LIMB - 1) / BYTES_PER_MPI_LIMB;
+ nbytes = DIV_ROUND_UP(nbits, 8);
+ nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
val = mpi_alloc(nlimbs);
if (!val)
return NULL;
@@ -193,7 +193,7 @@ int mpi_set_buffer(MPI a, const void *xbuffer, unsigned nbytes, int sign)
int nlimbs;
int i;
- nlimbs = (nbytes + BYTES_PER_MPI_LIMB - 1) / BYTES_PER_MPI_LIMB;
+ nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
if (RESIZE_IF_NEEDED(a, nlimbs) < 0)
return -ENOMEM;
a->sign = sign;
diff --git a/lib/parser.c b/lib/parser.c
index 52cfa69..807b2aa 100644
--- a/lib/parser.c
+++ b/lib/parser.c
@@ -157,7 +157,7 @@ static int match_number(substring_t *s, int *result, int base)
*
* Description: Attempts to parse the &substring_t @s as a decimal integer. On
* success, sets @result to the integer represented by the string and returns 0.
- * Returns either -ENOMEM or -EINVAL on failure.
+ * Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
*/
int match_int(substring_t *s, int *result)
{
@@ -171,7 +171,7 @@ int match_int(substring_t *s, int *result)
*
* Description: Attempts to parse the &substring_t @s as an octal integer. On
* success, sets @result to the integer represented by the string and returns
- * 0. Returns either -ENOMEM or -EINVAL on failure.
+ * 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
*/
int match_octal(substring_t *s, int *result)
{
@@ -185,7 +185,7 @@ int match_octal(substring_t *s, int *result)
*
* Description: Attempts to parse the &substring_t @s as a hexadecimal integer.
* On success, sets @result to the integer represented by the string and
- * returns 0. Returns either -ENOMEM or -EINVAL on failure.
+ * returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
*/
int match_hex(substring_t *s, int *result)
{
diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c
index 7e0d6a5..7542afb 100644
--- a/lib/rwsem-spinlock.c
+++ b/lib/rwsem-spinlock.c
@@ -73,20 +73,13 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
goto dont_wake_writers;
}
- /* if we are allowed to wake writers try to grant a single write lock
- * if there's a writer at the front of the queue
- * - we leave the 'waiting count' incremented to signify potential
- * contention
+ /*
+ * as we support write lock stealing, we can't set sem->activity
+ * to -1 here to indicate we get the lock. Instead, we wake it up
+ * to let it go get it again.
*/
if (waiter->flags & RWSEM_WAITING_FOR_WRITE) {
- sem->activity = -1;
- list_del(&waiter->list);
- tsk = waiter->task;
- /* Don't touch waiter after ->task has been NULLed */
- smp_mb();
- waiter->task = NULL;
- wake_up_process(tsk);
- put_task_struct(tsk);
+ wake_up_process(waiter->task);
goto out;
}
@@ -121,18 +114,10 @@ static inline struct rw_semaphore *
__rwsem_wake_one_writer(struct rw_semaphore *sem)
{
struct rwsem_waiter *waiter;
- struct task_struct *tsk;
-
- sem->activity = -1;
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
- list_del(&waiter->list);
+ wake_up_process(waiter->task);
- tsk = waiter->task;
- smp_mb();
- waiter->task = NULL;
- wake_up_process(tsk);
- put_task_struct(tsk);
return sem;
}
@@ -204,7 +189,6 @@ int __down_read_trylock(struct rw_semaphore *sem)
/*
* get a write lock on the semaphore
- * - we increment the waiting count anyway to indicate an exclusive lock
*/
void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
{
@@ -214,37 +198,32 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
raw_spin_lock_irqsave(&sem->wait_lock, flags);
- if (sem->activity == 0 && list_empty(&sem->wait_list)) {
- /* granted */
- sem->activity = -1;
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- goto out;
- }
-
- tsk = current;
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
-
/* set up my own style of waitqueue */
+ tsk = current;
waiter.task = tsk;
waiter.flags = RWSEM_WAITING_FOR_WRITE;
- get_task_struct(tsk);
-
list_add_tail(&waiter.list, &sem->wait_list);
- /* we don't need to touch the semaphore struct anymore */
- raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
- /* wait to be given the lock */
+ /* wait for someone to release the lock */
for (;;) {
- if (!waiter.task)
+ /*
+ * That is the key to support write lock stealing: allows the
+ * task already on CPU to get the lock soon rather than put
+ * itself into sleep and waiting for system woke it or someone
+ * else in the head of the wait list up.
+ */
+ if (sem->activity == 0)
break;
- schedule();
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ schedule();
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
}
+ /* got the lock */
+ sem->activity = -1;
+ list_del(&waiter.list);
- tsk->state = TASK_RUNNING;
- out:
- ;
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
}
void __sched __down_write(struct rw_semaphore *sem)
@@ -262,8 +241,8 @@ int __down_write_trylock(struct rw_semaphore *sem)
raw_spin_lock_irqsave(&sem->wait_lock, flags);
- if (sem->activity == 0 && list_empty(&sem->wait_list)) {
- /* granted */
+ if (sem->activity == 0) {
+ /* got the lock */
sem->activity = -1;
ret = 1;
}
diff --git a/lib/rwsem.c b/lib/rwsem.c
index 8337e1b9b..ad5e0df 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -2,6 +2,8 @@
*
* Written by David Howells (dhowells@redhat.com).
* Derived from arch/i386/kernel/semaphore.c
+ *
+ * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
*/
#include <linux/rwsem.h>
#include <linux/sched.h>
@@ -60,7 +62,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type)
struct rwsem_waiter *waiter;
struct task_struct *tsk;
struct list_head *next;
- signed long oldcount, woken, loop, adjustment;
+ signed long woken, loop, adjustment;
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE))
@@ -72,30 +74,8 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type)
*/
goto out;
- /* There's a writer at the front of the queue - try to grant it the
- * write lock. However, we only wake this writer if we can transition
- * the active part of the count from 0 -> 1
- */
- adjustment = RWSEM_ACTIVE_WRITE_BIAS;
- if (waiter->list.next == &sem->wait_list)
- adjustment -= RWSEM_WAITING_BIAS;
-
- try_again_write:
- oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
- if (oldcount & RWSEM_ACTIVE_MASK)
- /* Someone grabbed the sem already */
- goto undo_write;
-
- /* We must be careful not to touch 'waiter' after we set ->task = NULL.
- * It is an allocated on the waiter's stack and may become invalid at
- * any time after that point (due to a wakeup from another source).
- */
- list_del(&waiter->list);
- tsk = waiter->task;
- smp_mb();
- waiter->task = NULL;
- wake_up_process(tsk);
- put_task_struct(tsk);
+ /* Wake up the writing waiter and let the task grab the sem: */
+ wake_up_process(waiter->task);
goto out;
readers_only:
@@ -157,12 +137,40 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type)
out:
return sem;
+}
+
+/* Try to get write sem, caller holds sem->wait_lock: */
+static int try_get_writer_sem(struct rw_semaphore *sem,
+ struct rwsem_waiter *waiter)
+{
+ struct rwsem_waiter *fwaiter;
+ long oldcount, adjustment;
- /* undo the change to the active count, but check for a transition
- * 1->0 */
- undo_write:
+ /* only steal when first waiter is writing */
+ fwaiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+ if (!(fwaiter->flags & RWSEM_WAITING_FOR_WRITE))
+ return 0;
+
+ adjustment = RWSEM_ACTIVE_WRITE_BIAS;
+ /* Only one waiter in the queue: */
+ if (fwaiter == waiter && waiter->list.next == &sem->wait_list)
+ adjustment -= RWSEM_WAITING_BIAS;
+
+try_again_write:
+ oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+ if (!(oldcount & RWSEM_ACTIVE_MASK)) {
+ /* No active lock: */
+ struct task_struct *tsk = waiter->task;
+
+ list_del(&waiter->list);
+ smp_mb();
+ put_task_struct(tsk);
+ tsk->state = TASK_RUNNING;
+ return 1;
+ }
+ /* some one grabbed the sem already */
if (rwsem_atomic_update(-adjustment, sem) & RWSEM_ACTIVE_MASK)
- goto out;
+ return 0;
goto try_again_write;
}
@@ -210,6 +218,15 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
for (;;) {
if (!waiter.task)
break;
+
+ raw_spin_lock_irq(&sem->wait_lock);
+ /* Try to get the writer sem, may steal from the head writer: */
+ if (flags == RWSEM_WAITING_FOR_WRITE)
+ if (try_get_writer_sem(sem, &waiter)) {
+ raw_spin_unlock_irq(&sem->wait_lock);
+ return sem;
+ }
+ raw_spin_unlock_irq(&sem->wait_lock);
schedule();
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
}
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 7874b01..b83c144 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -394,6 +394,44 @@ int sg_alloc_table_from_pages(struct sg_table *sgt,
}
EXPORT_SYMBOL(sg_alloc_table_from_pages);
+void __sg_page_iter_start(struct sg_page_iter *piter,
+ struct scatterlist *sglist, unsigned int nents,
+ unsigned long pgoffset)
+{
+ piter->__pg_advance = 0;
+ piter->__nents = nents;
+
+ piter->page = NULL;
+ piter->sg = sglist;
+ piter->sg_pgoffset = pgoffset;
+}
+EXPORT_SYMBOL(__sg_page_iter_start);
+
+static int sg_page_count(struct scatterlist *sg)
+{
+ return PAGE_ALIGN(sg->offset + sg->length) >> PAGE_SHIFT;
+}
+
+bool __sg_page_iter_next(struct sg_page_iter *piter)
+{
+ if (!piter->__nents || !piter->sg)
+ return false;
+
+ piter->sg_pgoffset += piter->__pg_advance;
+ piter->__pg_advance = 1;
+
+ while (piter->sg_pgoffset >= sg_page_count(piter->sg)) {
+ piter->sg_pgoffset -= sg_page_count(piter->sg);
+ piter->sg = sg_next(piter->sg);
+ if (!--piter->__nents || !piter->sg)
+ return false;
+ }
+ piter->page = nth_page(sg_page(piter->sg), piter->sg_pgoffset);
+
+ return true;
+}
+EXPORT_SYMBOL(__sg_page_iter_next);
+
/**
* sg_miter_start - start mapping iteration over a sg list
* @miter: sg mapping iter to be started
@@ -411,9 +449,7 @@ void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl,
{
memset(miter, 0, sizeof(struct sg_mapping_iter));
- miter->__sg = sgl;
- miter->__nents = nents;
- miter->__offset = 0;
+ __sg_page_iter_start(&miter->piter, sgl, nents, 0);
WARN_ON(!(flags & (SG_MITER_TO_SG | SG_MITER_FROM_SG)));
miter->__flags = flags;
}
@@ -438,36 +474,35 @@ EXPORT_SYMBOL(sg_miter_start);
*/
bool sg_miter_next(struct sg_mapping_iter *miter)
{
- unsigned int off, len;
-
- /* check for end and drop resources from the last iteration */
- if (!miter->__nents)
- return false;
-
sg_miter_stop(miter);
- /* get to the next sg if necessary. __offset is adjusted by stop */
- while (miter->__offset == miter->__sg->length) {
- if (--miter->__nents) {
- miter->__sg = sg_next(miter->__sg);
- miter->__offset = 0;
- } else
+ /*
+ * Get to the next page if necessary.
+ * __remaining, __offset is adjusted by sg_miter_stop
+ */
+ if (!miter->__remaining) {
+ struct scatterlist *sg;
+ unsigned long pgoffset;
+
+ if (!__sg_page_iter_next(&miter->piter))
return false;
- }
- /* map the next page */
- off = miter->__sg->offset + miter->__offset;
- len = miter->__sg->length - miter->__offset;
+ sg = miter->piter.sg;
+ pgoffset = miter->piter.sg_pgoffset;
- miter->page = nth_page(sg_page(miter->__sg), off >> PAGE_SHIFT);
- off &= ~PAGE_MASK;
- miter->length = min_t(unsigned int, len, PAGE_SIZE - off);
- miter->consumed = miter->length;
+ miter->__offset = pgoffset ? 0 : sg->offset;
+ miter->__remaining = sg->offset + sg->length -
+ (pgoffset << PAGE_SHIFT) - miter->__offset;
+ miter->__remaining = min_t(unsigned long, miter->__remaining,
+ PAGE_SIZE - miter->__offset);
+ }
+ miter->page = miter->piter.page;
+ miter->consumed = miter->length = miter->__remaining;
if (miter->__flags & SG_MITER_ATOMIC)
- miter->addr = kmap_atomic(miter->page) + off;
+ miter->addr = kmap_atomic(miter->page) + miter->__offset;
else
- miter->addr = kmap(miter->page) + off;
+ miter->addr = kmap(miter->page) + miter->__offset;
return true;
}
@@ -494,6 +529,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
/* drop resources from the last iteration */
if (miter->addr) {
miter->__offset += miter->consumed;
+ miter->__remaining -= miter->consumed;
if (miter->__flags & SG_MITER_TO_SG)
flush_kernel_dcache_page(miter->page);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 196b069..bfe02b8 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -122,11 +122,18 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
return phys_to_dma(hwdev, virt_to_phys(address));
}
+static bool no_iotlb_memory;
+
void swiotlb_print_info(void)
{
unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
unsigned char *vstart, *vend;
+ if (no_iotlb_memory) {
+ pr_warn("software IO TLB: No low mem\n");
+ return;
+ }
+
vstart = phys_to_virt(io_tlb_start);
vend = phys_to_virt(io_tlb_end);
@@ -136,7 +143,7 @@ void swiotlb_print_info(void)
bytes >> 20, vstart, vend - 1);
}
-void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
{
void *v_overflow_buffer;
unsigned long i, bytes;
@@ -150,9 +157,10 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
/*
* Get the overflow emergency buffer
*/
- v_overflow_buffer = alloc_bootmem_low_pages(PAGE_ALIGN(io_tlb_overflow));
+ v_overflow_buffer = alloc_bootmem_low_pages_nopanic(
+ PAGE_ALIGN(io_tlb_overflow));
if (!v_overflow_buffer)
- panic("Cannot allocate SWIOTLB overflow buffer!\n");
+ return -ENOMEM;
io_tlb_overflow_buffer = __pa(v_overflow_buffer);
@@ -169,15 +177,19 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
if (verbose)
swiotlb_print_info();
+
+ return 0;
}
/*
* Statically reserve bounce buffer space and initialize bounce buffer data
* structures for the software IO TLB used to implement the DMA API.
*/
-static void __init
-swiotlb_init_with_default_size(size_t default_size, int verbose)
+void __init
+swiotlb_init(int verbose)
{
+ /* default to 64MB */
+ size_t default_size = 64UL<<20;
unsigned char *vstart;
unsigned long bytes;
@@ -188,20 +200,16 @@ swiotlb_init_with_default_size(size_t default_size, int verbose)
bytes = io_tlb_nslabs << IO_TLB_SHIFT;
- /*
- * Get IO TLB memory from the low pages
- */
- vstart = alloc_bootmem_low_pages(PAGE_ALIGN(bytes));
- if (!vstart)
- panic("Cannot allocate SWIOTLB buffer");
-
- swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose);
-}
+ /* Get IO TLB memory from the low pages */
+ vstart = alloc_bootmem_low_pages_nopanic(PAGE_ALIGN(bytes));
+ if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
+ return;
-void __init
-swiotlb_init(int verbose)
-{
- swiotlb_init_with_default_size(64 * (1<<20), verbose); /* default to 64MB */
+ if (io_tlb_start)
+ free_bootmem(io_tlb_start,
+ PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ pr_warn("Cannot allocate SWIOTLB buffer");
+ no_iotlb_memory = true;
}
/*
@@ -405,6 +413,9 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
unsigned long offset_slots;
unsigned long max_slots;
+ if (no_iotlb_memory)
+ panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+
mask = dma_get_seg_boundary(hwdev);
tbl_dma_addr &= mask;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index fab33a9..0d62fd7 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1030,6 +1030,7 @@ int kptr_restrict __read_mostly;
* N no separator
* The maximum supported length is 64 bytes of the input. Consider
* to use print_hex_dump() for the larger input.
+ * - 'a' For a phys_addr_t type and its derivative types (passed by reference)
*
* Note: The difference between 'S' and 'F' is that on ia64 and ppc64
* function pointers are really function descriptors, which contain a
@@ -1120,6 +1121,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
return netdev_feature_string(buf, end, ptr, spec);
}
break;
+ case 'a':
+ spec.flags |= SPECIAL | SMALL | ZEROPAD;
+ spec.field_width = sizeof(phys_addr_t) * 2 + 2;
+ spec.base = 16;
+ return number(buf, end,
+ (unsigned long long) *((phys_addr_t *)ptr), spec);
}
spec.flags |= SMALL;
if (spec.field_width == -1) {
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index 60a6088..82a04d7 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -6,42 +6,40 @@ config XZ_DEC
the .xz file format as the container. For integrity checking,
CRC32 is supported. See Documentation/xz.txt for more information.
+if XZ_DEC
+
config XZ_DEC_X86
- bool "x86 BCJ filter decoder" if EXPERT
- default y
- depends on XZ_DEC
+ bool "x86 BCJ filter decoder"
+ default y if X86
select XZ_DEC_BCJ
config XZ_DEC_POWERPC
- bool "PowerPC BCJ filter decoder" if EXPERT
- default y
- depends on XZ_DEC
+ bool "PowerPC BCJ filter decoder"
+ default y if POWERPC
select XZ_DEC_BCJ
config XZ_DEC_IA64
- bool "IA-64 BCJ filter decoder" if EXPERT
- default y
- depends on XZ_DEC
+ bool "IA-64 BCJ filter decoder"
+ default y if IA64
select XZ_DEC_BCJ
config XZ_DEC_ARM
- bool "ARM BCJ filter decoder" if EXPERT
- default y
- depends on XZ_DEC
+ bool "ARM BCJ filter decoder"
+ default y if ARM
select XZ_DEC_BCJ
config XZ_DEC_ARMTHUMB
- bool "ARM-Thumb BCJ filter decoder" if EXPERT
- default y
- depends on XZ_DEC
+ bool "ARM-Thumb BCJ filter decoder"
+ default y if (ARM && ARM_THUMB)
select XZ_DEC_BCJ
config XZ_DEC_SPARC
- bool "SPARC BCJ filter decoder" if EXPERT
- default y
- depends on XZ_DEC
+ bool "SPARC BCJ filter decoder"
+ default y if SPARC
select XZ_DEC_BCJ
+endif
+
config XZ_DEC_BCJ
bool
default n
OpenPOWER on IntegriCloud