summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig3
-rw-r--r--lib/Kconfig.debug53
-rw-r--r--lib/Kconfig.kmemcheck3
-rw-r--r--lib/Makefile2
-rw-r--r--lib/debugobjects.c1
-rw-r--r--lib/decompress_inflate.c8
-rw-r--r--lib/decompress_unlzma.c10
-rw-r--r--lib/dma-debug.c6
-rw-r--r--lib/fault-inject.c1
-rw-r--r--lib/flex_array.c121
-rw-r--r--lib/inflate.c2
-rw-r--r--lib/is_single_threaded.c61
-rw-r--r--lib/kernel_lock.c20
-rw-r--r--lib/lru_cache.c560
-rw-r--r--lib/radix-tree.c5
-rw-r--r--lib/ratelimit.c45
-rw-r--r--lib/string.c20
-rw-r--r--lib/swiotlb.c162
-rw-r--r--lib/vsprintf.c236
-rw-r--r--lib/zlib_deflate/deflate.c4
20 files changed, 1070 insertions, 253 deletions
diff --git a/lib/Kconfig b/lib/Kconfig
index bb1326d3839c..1cfe51628e1b 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -200,4 +200,7 @@ config NLATTR
config GENERIC_ATOMIC64
bool
+config LRU_CACHE
+ tristate
+
endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 12327b2bb785..0b8f35918a36 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -50,6 +50,14 @@ config MAGIC_SYSRQ
keys are documented in <file:Documentation/sysrq.txt>. Don't say Y
unless you really know what this hack does.
+config STRIP_ASM_SYMS
+ bool "Strip assembler-generated symbols during link"
+ default n
+ help
+ Strip internal assembler-generated symbols during a link (symbols
+ that look like '.Lxxx') so they don't pollute the output of
+ get_wchan() and suchlike.
+
config UNUSED_SYMBOLS
bool "Enable unused/obsolete exported symbols"
default y if X86
@@ -338,8 +346,9 @@ config SLUB_STATS
config DEBUG_KMEMLEAK
bool "Kernel memory leak detector"
- depends on DEBUG_KERNEL && EXPERIMENTAL && (X86 || ARM) && \
- !MEMORY_HOTPLUG
+ depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \
+ (X86 || ARM || PPC || S390)
+
select DEBUG_FS if SYSFS
select STACKTRACE if STACKTRACE_SUPPORT
select KALLSYMS
@@ -362,7 +371,7 @@ config DEBUG_KMEMLEAK
config DEBUG_KMEMLEAK_EARLY_LOG_SIZE
int "Maximum kmemleak early log entries"
depends on DEBUG_KMEMLEAK
- range 200 2000
+ range 200 40000
default 400
help
Kmemleak must track all the memory allocations to avoid
@@ -383,7 +392,7 @@ config DEBUG_KMEMLEAK_TEST
config DEBUG_PREEMPT
bool "Debug preemptible kernel"
- depends on DEBUG_KERNEL && PREEMPT && (TRACE_IRQFLAGS_SUPPORT || PPC64)
+ depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
default y
help
If you say Y here then the kernel will use a debug variant of the
@@ -653,6 +662,21 @@ config DEBUG_NOTIFIERS
This is a relatively cheap check but if you care about maximum
performance, say N.
+config DEBUG_CREDENTIALS
+ bool "Debug credential management"
+ depends on DEBUG_KERNEL
+ help
+ Enable this to turn on some debug checking for credential
+ management. The additional code keeps track of the number of
+ pointers from task_structs to any given cred struct, and checks to
+ see that this number never exceeds the usage count of the cred
+ struct.
+
+ Furthermore, if SELinux is enabled, this also checks that the
+ security pointer in the cred struct is never seen to be invalid.
+
+ If unsure, say N.
+
#
# Select this config option from the architecture Kconfig, if it
# it is preferred to always offer frame pointers as a config
@@ -725,8 +749,8 @@ config RCU_TORTURE_TEST_RUNNABLE
config RCU_CPU_STALL_DETECTOR
bool "Check for stalled CPUs delaying RCU grace periods"
- depends on CLASSIC_RCU || TREE_RCU
- default n
+ depends on TREE_RCU || TREE_PREEMPT_RCU
+ default y
help
This option causes RCU to printk information on which
CPUs are delaying the current grace period, but only when
@@ -790,6 +814,21 @@ config DEBUG_BLOCK_EXT_DEVT
Say N if you are unsure.
+config DEBUG_FORCE_WEAK_PER_CPU
+ bool "Force weak per-cpu definitions"
+ depends on DEBUG_KERNEL
+ help
+ s390 and alpha require percpu variables in modules to be
+ defined weak to work around addressing range issue which
+ puts the following two restrictions on percpu variable
+ definitions.
+
+ 1. percpu symbols must be unique whether static or not
+ 2. percpu variables can't be defined inside a function
+
+ To ensure that generic code follows the above rules, this
+ option forces all percpu variables to be defined as weak.
+
config LKDTM
tristate "Linux Kernel Dump Test Tool Module"
depends on DEBUG_KERNEL
@@ -873,7 +912,7 @@ config LATENCYTOP
config SYSCTL_SYSCALL_CHECK
bool "Sysctl checks"
- depends on SYSCTL_SYSCALL
+ depends on SYSCTL
---help---
sys_sysctl uses binary paths that have been found challenging
to properly maintain and use. This enables checks that help
diff --git a/lib/Kconfig.kmemcheck b/lib/Kconfig.kmemcheck
index 603c81b66549..846e039a86b4 100644
--- a/lib/Kconfig.kmemcheck
+++ b/lib/Kconfig.kmemcheck
@@ -1,6 +1,8 @@
config HAVE_ARCH_KMEMCHECK
bool
+if HAVE_ARCH_KMEMCHECK
+
menuconfig KMEMCHECK
bool "kmemcheck: trap use of uninitialized memory"
depends on DEBUG_KERNEL
@@ -89,3 +91,4 @@ config KMEMCHECK_BITOPS_OK
accesses where not all the bits are initialized at the same time.
This may also hide some real bugs.
+endif
diff --git a/lib/Makefile b/lib/Makefile
index 2e78277eff9d..347ad8db29d3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -91,6 +91,8 @@ obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
obj-$(CONFIG_NLATTR) += nlattr.o
+obj-$(CONFIG_LRU_CACHE) += lru_cache.o
+
obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
obj-$(CONFIG_GENERIC_CSUM) += checksum.o
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 2755a3bd16a1..eae56fddfa3b 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -9,6 +9,7 @@
*/
#include <linux/debugobjects.h>
#include <linux/interrupt.h>
+#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/hash.h>
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index 68dfce59c1b8..fc686c7a0a0d 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -27,6 +27,11 @@
#define GZIP_IOBUF_SIZE (16*1024)
+static int nofill(void *buffer, unsigned int len)
+{
+ return -1;
+}
+
/* Included from initramfs et al code */
STATIC int INIT gunzip(unsigned char *buf, int len,
int(*fill)(void*, unsigned int),
@@ -76,6 +81,9 @@ STATIC int INIT gunzip(unsigned char *buf, int len,
goto gunzip_nomem4;
}
+ if (!fill)
+ fill = nofill;
+
if (len == 0)
len = fill(zbuf, GZIP_IOBUF_SIZE);
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index 0b954e04bd30..ca82fde81c8f 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -82,6 +82,11 @@ struct rc {
#define RC_MODEL_TOTAL_BITS 11
+static int nofill(void *buffer, unsigned int len)
+{
+ return -1;
+}
+
/* Called twice: once at startup and once in rc_normalize() */
static void INIT rc_read(struct rc *rc)
{
@@ -97,7 +102,10 @@ static inline void INIT rc_init(struct rc *rc,
int (*fill)(void*, unsigned int),
char *buffer, int buffer_size)
{
- rc->fill = fill;
+ if (fill)
+ rc->fill = fill;
+ else
+ rc->fill = nofill;
rc->buffer = (uint8_t *)buffer;
rc->buffer_size = buffer_size;
rc->buffer_end = rc->buffer + rc->buffer_size;
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 58a9f9fc609a..ce6b7eabf674 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -819,9 +819,11 @@ static void check_unmap(struct dma_debug_entry *ref)
err_printk(ref->dev, entry, "DMA-API: device driver frees "
"DMA memory with different CPU address "
"[device address=0x%016llx] [size=%llu bytes] "
- "[cpu alloc address=%p] [cpu free address=%p]",
+ "[cpu alloc address=0x%016llx] "
+ "[cpu free address=0x%016llx]",
ref->dev_addr, ref->size,
- (void *)entry->paddr, (void *)ref->paddr);
+ (unsigned long long)entry->paddr,
+ (unsigned long long)ref->paddr);
}
if (ref->sg_call_ents && ref->type == dma_debug_sg &&
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index f97af55bdd96..7e65af70635e 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -1,6 +1,7 @@
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/random.h>
+#include <linux/sched.h>
#include <linux/stat.h>
#include <linux/types.h>
#include <linux/fs.h>
diff --git a/lib/flex_array.c b/lib/flex_array.c
index 7baed2fc3bc8..66eef2e4483e 100644
--- a/lib/flex_array.c
+++ b/lib/flex_array.c
@@ -28,23 +28,6 @@ struct flex_array_part {
char elements[FLEX_ARRAY_PART_SIZE];
};
-static inline int __elements_per_part(int element_size)
-{
- return FLEX_ARRAY_PART_SIZE / element_size;
-}
-
-static inline int bytes_left_in_base(void)
-{
- int element_offset = offsetof(struct flex_array, parts);
- int bytes_left = FLEX_ARRAY_BASE_SIZE - element_offset;
- return bytes_left;
-}
-
-static inline int nr_base_part_ptrs(void)
-{
- return bytes_left_in_base() / sizeof(struct flex_array_part *);
-}
-
/*
* If a user requests an allocation which is small
* enough, we may simply use the space in the
@@ -54,7 +37,7 @@ static inline int nr_base_part_ptrs(void)
static inline int elements_fit_in_base(struct flex_array *fa)
{
int data_size = fa->element_size * fa->total_nr_elements;
- if (data_size <= bytes_left_in_base())
+ if (data_size <= FLEX_ARRAY_BASE_BYTES_LEFT)
return 1;
return 0;
}
@@ -63,6 +46,7 @@ static inline int elements_fit_in_base(struct flex_array *fa)
* flex_array_alloc - allocate a new flexible array
* @element_size: the size of individual elements in the array
* @total: total number of elements that this should hold
+ * @flags: page allocation flags to use for base array
*
* Note: all locking must be provided by the caller.
*
@@ -103,7 +87,8 @@ struct flex_array *flex_array_alloc(int element_size, unsigned int total,
gfp_t flags)
{
struct flex_array *ret;
- int max_size = nr_base_part_ptrs() * __elements_per_part(element_size);
+ int max_size = FLEX_ARRAY_NR_BASE_PTRS *
+ FLEX_ARRAY_ELEMENTS_PER_PART(element_size);
/* max_size will end up 0 if element_size > PAGE_SIZE */
if (total > max_size)
@@ -113,17 +98,21 @@ struct flex_array *flex_array_alloc(int element_size, unsigned int total,
return NULL;
ret->element_size = element_size;
ret->total_nr_elements = total;
+ if (elements_fit_in_base(ret) && !(flags & __GFP_ZERO))
+ memset(ret->parts[0], FLEX_ARRAY_FREE,
+ FLEX_ARRAY_BASE_BYTES_LEFT);
return ret;
}
static int fa_element_to_part_nr(struct flex_array *fa,
unsigned int element_nr)
{
- return element_nr / __elements_per_part(fa->element_size);
+ return element_nr / FLEX_ARRAY_ELEMENTS_PER_PART(fa->element_size);
}
/**
* flex_array_free_parts - just free the second-level pages
+ * @fa: the flex array from which to free parts
*
* This is to be used in cases where the base 'struct flex_array'
* has been statically allocated and should not be free.
@@ -131,11 +120,10 @@ static int fa_element_to_part_nr(struct flex_array *fa,
void flex_array_free_parts(struct flex_array *fa)
{
int part_nr;
- int max_part = nr_base_part_ptrs();
if (elements_fit_in_base(fa))
return;
- for (part_nr = 0; part_nr < max_part; part_nr++)
+ for (part_nr = 0; part_nr < FLEX_ARRAY_NR_BASE_PTRS; part_nr++)
kfree(fa->parts[part_nr]);
}
@@ -150,7 +138,8 @@ static unsigned int index_inside_part(struct flex_array *fa,
{
unsigned int part_offset;
- part_offset = element_nr % __elements_per_part(fa->element_size);
+ part_offset = element_nr %
+ FLEX_ARRAY_ELEMENTS_PER_PART(fa->element_size);
return part_offset * fa->element_size;
}
@@ -159,15 +148,12 @@ __fa_get_part(struct flex_array *fa, int part_nr, gfp_t flags)
{
struct flex_array_part *part = fa->parts[part_nr];
if (!part) {
- /*
- * This leaves the part pages uninitialized
- * and with potentially random data, just
- * as if the user had kmalloc()'d the whole.
- * __GFP_ZERO can be used to zero it.
- */
- part = kmalloc(FLEX_ARRAY_PART_SIZE, flags);
+ part = kmalloc(sizeof(struct flex_array_part), flags);
if (!part)
return NULL;
+ if (!(flags & __GFP_ZERO))
+ memset(part, FLEX_ARRAY_FREE,
+ sizeof(struct flex_array_part));
fa->parts[part_nr] = part;
}
return part;
@@ -175,9 +161,12 @@ __fa_get_part(struct flex_array *fa, int part_nr, gfp_t flags)
/**
* flex_array_put - copy data into the array at @element_nr
- * @src: address of data to copy into the array
+ * @fa: the flex array to copy data into
* @element_nr: index of the position in which to insert
* the new element.
+ * @src: address of data to copy into the array
+ * @flags: page allocation flags to use for array expansion
+ *
*
* Note that this *copies* the contents of @src into
* the array. If you are trying to store an array of
@@ -207,9 +196,38 @@ int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src,
}
/**
+ * flex_array_clear - clear element in array at @element_nr
+ * @fa: the flex array of the element.
+ * @element_nr: index of the position to clear.
+ *
+ * Locking must be provided by the caller.
+ */
+int flex_array_clear(struct flex_array *fa, unsigned int element_nr)
+{
+ int part_nr = fa_element_to_part_nr(fa, element_nr);
+ struct flex_array_part *part;
+ void *dst;
+
+ if (element_nr >= fa->total_nr_elements)
+ return -ENOSPC;
+ if (elements_fit_in_base(fa))
+ part = (struct flex_array_part *)&fa->parts[0];
+ else {
+ part = fa->parts[part_nr];
+ if (!part)
+ return -EINVAL;
+ }
+ dst = &part->elements[index_inside_part(fa, element_nr)];
+ memset(dst, FLEX_ARRAY_FREE, fa->element_size);
+ return 0;
+}
+
+/**
* flex_array_prealloc - guarantee that array space exists
+ * @fa: the flex array for which to preallocate parts
* @start: index of first array element for which space is allocated
* @end: index of last (inclusive) element for which space is allocated
+ * @flags: page allocation flags
*
* This will guarantee that no future calls to flex_array_put()
* will allocate memory. It can be used if you are expecting to
@@ -242,6 +260,7 @@ int flex_array_prealloc(struct flex_array *fa, unsigned int start,
/**
* flex_array_get - pull data back out of the array
+ * @fa: the flex array from which to extract data
* @element_nr: index of the element to fetch from the array
*
* Returns a pointer to the data at index @element_nr. Note
@@ -266,3 +285,43 @@ void *flex_array_get(struct flex_array *fa, unsigned int element_nr)
}
return &part->elements[index_inside_part(fa, element_nr)];
}
+
+static int part_is_free(struct flex_array_part *part)
+{
+ int i;
+
+ for (i = 0; i < sizeof(struct flex_array_part); i++)
+ if (part->elements[i] != FLEX_ARRAY_FREE)
+ return 0;
+ return 1;
+}
+
+/**
+ * flex_array_shrink - free unused second-level pages
+ * @fa: the flex array to shrink
+ *
+ * Frees all second-level pages that consist solely of unused
+ * elements. Returns the number of pages freed.
+ *
+ * Locking must be provided by the caller.
+ */
+int flex_array_shrink(struct flex_array *fa)
+{
+ struct flex_array_part *part;
+ int part_nr;
+ int ret = 0;
+
+ if (elements_fit_in_base(fa))
+ return ret;
+ for (part_nr = 0; part_nr < FLEX_ARRAY_NR_BASE_PTRS; part_nr++) {
+ part = fa->parts[part_nr];
+ if (!part)
+ continue;
+ if (part_is_free(part)) {
+ fa->parts[part_nr] = NULL;
+ kfree(part);
+ ret++;
+ }
+ }
+ return ret;
+}
diff --git a/lib/inflate.c b/lib/inflate.c
index 1a8e8a978128..d10255973a9f 100644
--- a/lib/inflate.c
+++ b/lib/inflate.c
@@ -7,7 +7,7 @@
* Adapted for booting Linux by Hannu Savolainen 1993
* based on gzip-1.0.3
*
- * Nicolas Pitre <nico@cam.org>, 1999/04/14 :
+ * Nicolas Pitre <nico@fluxnic.net>, 1999/04/14 :
* Little mods for all variable to reside either into rodata or bss segments
* by marking constant variables with 'const' and initializing all the others
* at run-time only. This allows for the kernel uncompressor to run
diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c
index f1ed2fe76c65..bd2bea963364 100644
--- a/lib/is_single_threaded.c
+++ b/lib/is_single_threaded.c
@@ -12,34 +12,47 @@
#include <linux/sched.h>
-/**
- * is_single_threaded - Determine if a thread group is single-threaded or not
- * @p: A task in the thread group in question
- *
- * This returns true if the thread group to which a task belongs is single
- * threaded, false if it is not.
+/*
+ * Returns true if the task does not share ->mm with another thread/process.
*/
-bool is_single_threaded(struct task_struct *p)
+bool current_is_single_threaded(void)
{
- struct task_struct *g, *t;
- struct mm_struct *mm = p->mm;
+ struct task_struct *task = current;
+ struct mm_struct *mm = task->mm;
+ struct task_struct *p, *t;
+ bool ret;
- if (atomic_read(&p->signal->count) != 1)
- goto no;
+ if (atomic_read(&task->signal->live) != 1)
+ return false;
- if (atomic_read(&p->mm->mm_users) != 1) {
- read_lock(&tasklist_lock);
- do_each_thread(g, t) {
- if (t->mm == mm && t != p)
- goto no_unlock;
- } while_each_thread(g, t);
- read_unlock(&tasklist_lock);
- }
+ if (atomic_read(&mm->mm_users) == 1)
+ return true;
- return true;
+ ret = false;
+ rcu_read_lock();
+ for_each_process(p) {
+ if (unlikely(p->flags & PF_KTHREAD))
+ continue;
+ if (unlikely(p == task->group_leader))
+ continue;
+
+ t = p;
+ do {
+ if (unlikely(t->mm == mm))
+ goto found;
+ if (likely(t->mm))
+ break;
+ /*
+ * t->mm == NULL. Make sure next_thread/next_task
+ * will see other CLONE_VM tasks which might be
+ * forked before exiting.
+ */
+ smp_rmb();
+ } while_each_thread(p, t);
+ }
+ ret = true;
+found:
+ rcu_read_unlock();
-no_unlock:
- read_unlock(&tasklist_lock);
-no:
- return false;
+ return ret;
}
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index 39f1029e3525..4ebfa5a164d7 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -5,10 +5,13 @@
* relegated to obsolescence, but used by various less
* important (or lazy) subsystems.
*/
-#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/semaphore.h>
+#include <linux/smp_lock.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/bkl.h>
/*
* The 'big kernel lock'
@@ -113,21 +116,26 @@ static inline void __unlock_kernel(void)
* This cannot happen asynchronously, so we only need to
* worry about other CPU's.
*/
-void __lockfunc lock_kernel(void)
+void __lockfunc _lock_kernel(const char *func, const char *file, int line)
{
- int depth = current->lock_depth+1;
+ int depth = current->lock_depth + 1;
+
+ trace_lock_kernel(func, file, line);
+
if (likely(!depth))
__lock_kernel();
current->lock_depth = depth;
}
-void __lockfunc unlock_kernel(void)
+void __lockfunc _unlock_kernel(const char *func, const char *file, int line)
{
BUG_ON(current->lock_depth < 0);
if (likely(--current->lock_depth < 0))
__unlock_kernel();
+
+ trace_unlock_kernel(func, file, line);
}
-EXPORT_SYMBOL(lock_kernel);
-EXPORT_SYMBOL(unlock_kernel);
+EXPORT_SYMBOL(_lock_kernel);
+EXPORT_SYMBOL(_unlock_kernel);
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
new file mode 100644
index 000000000000..270de9d31b8c
--- /dev/null
+++ b/lib/lru_cache.c
@@ -0,0 +1,560 @@
+/*
+ lru_cache.c
+
+ This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+ Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
+ Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
+ Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
+
+ drbd 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, or (at your option)
+ any later version.
+
+ drbd 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 drbd; see the file COPYING. If not, write to
+ the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ */
+
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/string.h> /* for memset */
+#include <linux/seq_file.h> /* for seq_printf */
+#include <linux/lru_cache.h>
+
+MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
+ "Lars Ellenberg <lars@linbit.com>");
+MODULE_DESCRIPTION("lru_cache - Track sets of hot objects");
+MODULE_LICENSE("GPL");
+
+/* this is developers aid only.
+ * it catches concurrent access (lack of locking on the users part) */
+#define PARANOIA_ENTRY() do { \
+ BUG_ON(!lc); \
+ BUG_ON(!lc->nr_elements); \
+ BUG_ON(test_and_set_bit(__LC_PARANOIA, &lc->flags)); \
+} while (0)
+
+#define RETURN(x...) do { \
+ clear_bit(__LC_PARANOIA, &lc->flags); \
+ smp_mb__after_clear_bit(); return x ; } while (0)
+
+/* BUG() if e is not one of the elements tracked by lc */
+#define PARANOIA_LC_ELEMENT(lc, e) do { \
+ struct lru_cache *lc_ = (lc); \
+ struct lc_element *e_ = (e); \
+ unsigned i = e_->lc_index; \
+ BUG_ON(i >= lc_->nr_elements); \
+ BUG_ON(lc_->lc_element[i] != e_); } while (0)
+
+/**
+ * lc_create - prepares to track objects in an active set
+ * @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details
+ * @e_count: number of elements allowed to be active simultaneously
+ * @e_size: size of the tracked objects
+ * @e_off: offset to the &struct lc_element member in a tracked object
+ *
+ * Returns a pointer to a newly initialized struct lru_cache on success,
+ * or NULL on (allocation) failure.
+ */
+struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
+ unsigned e_count, size_t e_size, size_t e_off)
+{
+ struct hlist_head *slot = NULL;
+ struct lc_element **element = NULL;
+ struct lru_cache *lc;
+ struct lc_element *e;
+ unsigned cache_obj_size = kmem_cache_size(cache);
+ unsigned i;
+
+ WARN_ON(cache_obj_size < e_size);
+ if (cache_obj_size < e_size)
+ return NULL;
+
+ /* e_count too big; would probably fail the allocation below anyways.
+ * for typical use cases, e_count should be few thousand at most. */
+ if (e_count > LC_MAX_ACTIVE)
+ return NULL;
+
+ slot = kzalloc(e_count * sizeof(struct hlist_head*), GFP_KERNEL);
+ if (!slot)
+ goto out_fail;
+ element = kzalloc(e_count * sizeof(struct lc_element *), GFP_KERNEL);
+ if (!element)
+ goto out_fail;
+
+ lc = kzalloc(sizeof(*lc), GFP_KERNEL);
+ if (!lc)
+ goto out_fail;
+
+ INIT_LIST_HEAD(&lc->in_use);
+ INIT_LIST_HEAD(&lc->lru);
+ INIT_LIST_HEAD(&lc->free);
+
+ lc->name = name;
+ lc->element_size = e_size;
+ lc->element_off = e_off;
+ lc->nr_elements = e_count;
+ lc->new_number = LC_FREE;
+ lc->lc_cache = cache;
+ lc->lc_element = element;
+ lc->lc_slot = slot;
+
+ /* preallocate all objects */
+ for (i = 0; i < e_count; i++) {
+ void *p = kmem_cache_alloc(cache, GFP_KERNEL);
+ if (!p)
+ break;
+ memset(p, 0, lc->element_size);
+ e = p + e_off;
+ e->lc_index = i;
+ e->lc_number = LC_FREE;
+ list_add(&e->list, &lc->free);
+ element[i] = e;
+ }
+ if (i == e_count)
+ return lc;
+
+ /* else: could not allocate all elements, give up */
+ for (i--; i; i--) {
+ void *p = element[i];
+ kmem_cache_free(cache, p - e_off);
+ }
+ kfree(lc);
+out_fail:
+ kfree(element);
+ kfree(slot);
+ return NULL;
+}
+
+void lc_free_by_index(struct lru_cache *lc, unsigned i)
+{
+ void *p = lc->lc_element[i];
+ WARN_ON(!p);
+ if (p) {
+ p -= lc->element_off;
+ kmem_cache_free(lc->lc_cache, p);
+ }
+}
+
+/**
+ * lc_destroy - frees memory allocated by lc_create()
+ * @lc: the lru cache to destroy
+ */
+void lc_destroy(struct lru_cache *lc)
+{
+ unsigned i;
+ if (!lc)
+ return;
+ for (i = 0; i < lc->nr_elements; i++)
+ lc_free_by_index(lc, i);
+ kfree(lc->lc_element);
+ kfree(lc->lc_slot);
+ kfree(lc);
+}
+
+/**
+ * lc_reset - does a full reset for @lc and the hash table slots.
+ * @lc: the lru cache to operate on
+ *
+ * It is roughly the equivalent of re-allocating a fresh lru_cache object,
+ * basically a short cut to lc_destroy(lc); lc = lc_create(...);
+ */
+void lc_reset(struct lru_cache *lc)
+{
+ unsigned i;
+
+ INIT_LIST_HEAD(&lc->in_use);
+ INIT_LIST_HEAD(&lc->lru);
+ INIT_LIST_HEAD(&lc->free);
+ lc->used = 0;
+ lc->hits = 0;
+ lc->misses = 0;
+ lc->starving = 0;
+ lc->dirty = 0;
+ lc->changed = 0;
+ lc->flags = 0;
+ lc->changing_element = NULL;
+ lc->new_number = LC_FREE;
+ memset(lc->lc_slot, 0, sizeof(struct hlist_head) * lc->nr_elements);
+
+ for (i = 0; i < lc->nr_elements; i++) {
+ struct lc_element *e = lc->lc_element[i];
+ void *p = e;
+ p -= lc->element_off;
+ memset(p, 0, lc->element_size);
+ /* re-init it */
+ e->lc_index = i;
+ e->lc_number = LC_FREE;
+ list_add(&e->list, &lc->free);
+ }
+}
+
+/**
+ * lc_seq_printf_stats - print stats about @lc into @seq
+ * @seq: the seq_file to print into
+ * @lc: the lru cache to print statistics of
+ */
+size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc)
+{
+ /* NOTE:
+ * total calls to lc_get are
+ * (starving + hits + misses)
+ * misses include "dirty" count (update from an other thread in
+ * progress) and "changed", when this in fact lead to an successful
+ * update of the cache.
+ */
+ return seq_printf(seq, "\t%s: used:%u/%u "
+ "hits:%lu misses:%lu starving:%lu dirty:%lu changed:%lu\n",
+ lc->name, lc->used, lc->nr_elements,
+ lc->hits, lc->misses, lc->starving, lc->dirty, lc->changed);
+}
+
+static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr)
+{
+ return lc->lc_slot + (enr % lc->nr_elements);
+}
+
+
+/**
+ * lc_find - find element by label, if present in the hash table
+ * @lc: The lru_cache object
+ * @enr: element number
+ *
+ * Returns the pointer to an element, if the element with the requested
+ * "label" or element number is present in the hash table,
+ * or NULL if not found. Does not change the refcnt.
+ */
+struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr)
+{
+ 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) {
+ if (e->lc_number == enr)
+ return e;
+ }
+ return NULL;
+}
+
+/* returned element will be "recycled" immediately */
+static struct lc_element *lc_evict(struct lru_cache *lc)
+{
+ struct list_head *n;
+ struct lc_element *e;
+
+ if (list_empty(&lc->lru))
+ return NULL;
+
+ n = lc->lru.prev;
+ e = list_entry(n, struct lc_element, list);
+
+ PARANOIA_LC_ELEMENT(lc, e);
+
+ list_del(&e->list);
+ hlist_del(&e->colision);
+ return e;
+}
+
+/**
+ * lc_del - removes an element from the cache
+ * @lc: The lru_cache object
+ * @e: The element to remove
+ *
+ * @e must be unused (refcnt == 0). Moves @e from "lru" to "free" list,
+ * sets @e->enr to %LC_FREE.
+ */
+void lc_del(struct lru_cache *lc, struct lc_element *e)
+{
+ PARANOIA_ENTRY();
+ PARANOIA_LC_ELEMENT(lc, e);
+ BUG_ON(e->refcnt);
+
+ e->lc_number = LC_FREE;
+ hlist_del_init(&e->colision);
+ list_move(&e->list, &lc->free);
+ RETURN();
+}
+
+static struct lc_element *lc_get_unused_element(struct lru_cache *lc)
+{
+ struct list_head *n;
+
+ if (list_empty(&lc->free))
+ return lc_evict(lc);
+
+ n = lc->free.next;
+ list_del(n);
+ return list_entry(n, struct lc_element, list);
+}
+
+static int lc_unused_element_available(struct lru_cache *lc)
+{
+ if (!list_empty(&lc->free))
+ return 1; /* something on the free list */
+ if (!list_empty(&lc->lru))
+ return 1; /* something to evict */
+
+ return 0;
+}
+
+
+/**
+ * lc_get - get element by label, maybe change the active set
+ * @lc: the lru cache to operate on
+ * @enr: the label to look up
+ *
+ * Finds an element in the cache, increases its usage count,
+ * "touches" and returns it.
+ *
+ * In case the requested number is not present, it needs to be added to the
+ * cache. Therefore it is possible that an other element becomes evicted from
+ * the cache. In either case, the user is notified so he is able to e.g. keep
+ * a persistent log of the cache changes, and therefore the objects in use.
+ *
+ * Return values:
+ * NULL
+ * The cache was marked %LC_STARVING,
+ * or the requested label was not in the active set
+ * and a changing transaction is still pending (@lc was marked %LC_DIRTY).
+ * Or no unused or free element could be recycled (@lc will be marked as
+ * %LC_STARVING, blocking further lc_get() operations).
+ *
+ * pointer to the element with the REQUESTED element number.
+ * In this case, it can be used right away
+ *
+ * pointer to an UNUSED element with some different element number,
+ * where that different number may also be %LC_FREE.
+ *
+ * In this case, the cache is marked %LC_DIRTY (blocking further changes),
+ * and the returned element pointer is removed from the lru list and
+ * hash collision chains. The user now should do whatever housekeeping
+ * is necessary.
+ * Then he must call lc_changed(lc,element_pointer), to finish
+ * the change.
+ *
+ * NOTE: The user needs to check the lc_number on EACH use, so he recognizes
+ * any cache set change.
+ */
+struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr)
+{
+ struct lc_element *e;
+
+ PARANOIA_ENTRY();
+ if (lc->flags & LC_STARVING) {
+ ++lc->starving;
+ RETURN(NULL);
+ }
+
+ e = lc_find(lc, enr);
+ if (e) {
+ ++lc->hits;
+ if (e->refcnt++ == 0)
+ lc->used++;
+ list_move(&e->list, &lc->in_use); /* Not evictable... */
+ RETURN(e);
+ }
+
+ ++lc->misses;
+
+ /* In case there is nothing available and we can not kick out
+ * the LRU element, we have to wait ...
+ */
+ if (!lc_unused_element_available(lc)) {
+ __set_bit(__LC_STARVING, &lc->flags);
+ RETURN(NULL);
+ }
+
+ /* it was not present in the active set.
+ * we are going to recycle an unused (or even "free") element.
+ * user may need to commit a transaction to record that change.
+ * we serialize on flags & TF_DIRTY */
+ if (test_and_set_bit(__LC_DIRTY, &lc->flags)) {
+ ++lc->dirty;
+ RETURN(NULL);
+ }
+
+ e = lc_get_unused_element(lc);
+ BUG_ON(!e);
+
+ clear_bit(__LC_STARVING, &lc->flags);
+ BUG_ON(++e->refcnt != 1);
+ lc->used++;
+
+ lc->changing_element = e;
+ lc->new_number = enr;
+
+ RETURN(e);
+}
+
+/* similar to lc_get,
+ * but only gets a new reference on an existing element.
+ * you either get the requested element, or NULL.
+ * will be consolidated into one function.
+ */
+struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr)
+{
+ struct lc_element *e;
+
+ PARANOIA_ENTRY();
+ if (lc->flags & LC_STARVING) {
+ ++lc->starving;
+ RETURN(NULL);
+ }
+
+ e = lc_find(lc, enr);
+ if (e) {
+ ++lc->hits;
+ if (e->refcnt++ == 0)
+ lc->used++;
+ list_move(&e->list, &lc->in_use); /* Not evictable... */
+ }
+ RETURN(e);
+}
+
+/**
+ * lc_changed - tell @lc that the change has been recorded
+ * @lc: the lru cache to operate on
+ * @e: the element pending label change
+ */
+void lc_changed(struct lru_cache *lc, struct lc_element *e)
+{
+ PARANOIA_ENTRY();
+ BUG_ON(e != lc->changing_element);
+ PARANOIA_LC_ELEMENT(lc, e);
+ ++lc->changed;
+ e->lc_number = lc->new_number;
+ list_add(&e->list, &lc->in_use);
+ hlist_add_head(&e->colision, lc_hash_slot(lc, lc->new_number));
+ lc->changing_element = NULL;
+ lc->new_number = LC_FREE;
+ clear_bit(__LC_DIRTY, &lc->flags);
+ smp_mb__after_clear_bit();
+ RETURN();
+}
+
+
+/**
+ * lc_put - give up refcnt of @e
+ * @lc: the lru cache to operate on
+ * @e: the element to put
+ *
+ * If refcnt reaches zero, the element is moved to the lru list,
+ * and a %LC_STARVING (if set) is cleared.
+ * Returns the new (post-decrement) refcnt.
+ */
+unsigned int lc_put(struct lru_cache *lc, struct lc_element *e)
+{
+ PARANOIA_ENTRY();
+ PARANOIA_LC_ELEMENT(lc, e);
+ BUG_ON(e->refcnt == 0);
+ BUG_ON(e == lc->changing_element);
+ if (--e->refcnt == 0) {
+ /* move it to the front of LRU. */
+ list_move(&e->list, &lc->lru);
+ lc->used--;
+ clear_bit(__LC_STARVING, &lc->flags);
+ smp_mb__after_clear_bit();
+ }
+ RETURN(e->refcnt);
+}
+
+/**
+ * lc_element_by_index
+ * @lc: the lru cache to operate on
+ * @i: the index of the element to return
+ */
+struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i)
+{
+ BUG_ON(i >= lc->nr_elements);
+ BUG_ON(lc->lc_element[i] == NULL);
+ BUG_ON(lc->lc_element[i]->lc_index != i);
+ return lc->lc_element[i];
+}
+
+/**
+ * lc_index_of
+ * @lc: the lru cache to operate on
+ * @e: the element to query for its index position in lc->element
+ */
+unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e)
+{
+ PARANOIA_LC_ELEMENT(lc, e);
+ return e->lc_index;
+}
+
+/**
+ * lc_set - associate index with label
+ * @lc: the lru cache to operate on
+ * @enr: the label to set
+ * @index: the element index to associate label with.
+ *
+ * Used to initialize the active set to some previously recorded state.
+ */
+void lc_set(struct lru_cache *lc, unsigned int enr, int index)
+{
+ struct lc_element *e;
+
+ if (index < 0 || index >= lc->nr_elements)
+ return;
+
+ e = lc_element_by_index(lc, index);
+ e->lc_number = enr;
+
+ hlist_del_init(&e->colision);
+ hlist_add_head(&e->colision, lc_hash_slot(lc, enr));
+ list_move(&e->list, e->refcnt ? &lc->in_use : &lc->lru);
+}
+
+/**
+ * lc_dump - Dump a complete LRU cache to seq in textual form.
+ * @lc: the lru cache to operate on
+ * @seq: the &struct seq_file pointer to seq_printf into
+ * @utext: user supplied "heading" or other info
+ * @detail: function pointer the user may provide to dump further details
+ * of the object the lc_element is embedded in.
+ */
+void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext,
+ void (*detail) (struct seq_file *, struct lc_element *))
+{
+ unsigned int nr_elements = lc->nr_elements;
+ struct lc_element *e;
+ int i;
+
+ seq_printf(seq, "\tnn: lc_number refcnt %s\n ", utext);
+ for (i = 0; i < nr_elements; i++) {
+ e = lc_element_by_index(lc, i);
+ if (e->lc_number == LC_FREE) {
+ seq_printf(seq, "\t%2d: FREE\n", i);
+ } else {
+ seq_printf(seq, "\t%2d: %4u %4u ", i,
+ e->lc_number, e->refcnt);
+ detail(seq, e);
+ }
+ }
+}
+
+EXPORT_SYMBOL(lc_create);
+EXPORT_SYMBOL(lc_reset);
+EXPORT_SYMBOL(lc_destroy);
+EXPORT_SYMBOL(lc_set);
+EXPORT_SYMBOL(lc_del);
+EXPORT_SYMBOL(lc_try_get);
+EXPORT_SYMBOL(lc_find);
+EXPORT_SYMBOL(lc_get);
+EXPORT_SYMBOL(lc_put);
+EXPORT_SYMBOL(lc_changed);
+EXPORT_SYMBOL(lc_element_by_index);
+EXPORT_SYMBOL(lc_index_of);
+EXPORT_SYMBOL(lc_seq_printf_stats);
+EXPORT_SYMBOL(lc_seq_dump_details);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 23abbd93cae1..92cdd9936e3d 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -200,6 +200,9 @@ radix_tree_node_free(struct radix_tree_node *node)
* ensure that the addition of a single element in the tree cannot fail. On
* success, return zero, with preemption disabled. On error, return -ENOMEM
* with preemption not disabled.
+ *
+ * To make use of this facility, the radix tree must be initialised without
+ * __GFP_WAIT being passed to INIT_RADIX_TREE().
*/
int radix_tree_preload(gfp_t gfp_mask)
{
@@ -543,7 +546,6 @@ out:
}
EXPORT_SYMBOL(radix_tree_tag_clear);
-#ifndef __KERNEL__ /* Only the test harness uses this at present */
/**
* radix_tree_tag_get - get a tag on a radix tree node
* @root: radix tree root
@@ -606,7 +608,6 @@ int radix_tree_tag_get(struct radix_tree_root *root,
}
}
EXPORT_SYMBOL(radix_tree_tag_get);
-#endif
/**
* radix_tree_next_hole - find the next hole (not-present entry)
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 26187edcc7ea..09f5ce1810dc 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -7,15 +7,12 @@
* parameter. Now every user can use their own standalone ratelimit_state.
*
* This file is released under the GPLv2.
- *
*/
-#include <linux/kernel.h>
+#include <linux/ratelimit.h>
#include <linux/jiffies.h>
#include <linux/module.h>
-static DEFINE_SPINLOCK(ratelimit_lock);
-
/*
* __ratelimit - rate limiting
* @rs: ratelimit_state data
@@ -23,35 +20,43 @@ static DEFINE_SPINLOCK(ratelimit_lock);
* This enforces a rate limit: not more than @rs->ratelimit_burst callbacks
* in every @rs->ratelimit_jiffies
*/
-int __ratelimit(struct ratelimit_state *rs)
+int ___ratelimit(struct ratelimit_state *rs, const char *func)
{
unsigned long flags;
+ int ret;
if (!rs->interval)
return 1;
- spin_lock_irqsave(&ratelimit_lock, flags);
+ /*
+ * If we contend on this state's lock then almost
+ * by definition we are too busy to print a message,
+ * in addition to the one that will be printed by
+ * the entity that is holding the lock already:
+ */
+ if (!spin_trylock_irqsave(&rs->lock, flags))
+ return 1;
+
if (!rs->begin)
rs->begin = jiffies;
if (time_is_before_jiffies(rs->begin + rs->interval)) {
if (rs->missed)
printk(KERN_WARNING "%s: %d callbacks suppressed\n",
- __func__, rs->missed);
- rs->begin = 0;
+ func, rs->missed);
+ rs->begin = 0;
rs->printed = 0;
- rs->missed = 0;
+ rs->missed = 0;
}
- if (rs->burst && rs->burst > rs->printed)
- goto print;
-
- rs->missed++;
- spin_unlock_irqrestore(&ratelimit_lock, flags);
- return 0;
+ if (rs->burst && rs->burst > rs->printed) {
+ rs->printed++;
+ ret = 1;
+ } else {
+ rs->missed++;
+ ret = 0;
+ }
+ spin_unlock_irqrestore(&rs->lock, flags);
-print:
- rs->printed++;
- spin_unlock_irqrestore(&ratelimit_lock, flags);
- return 1;
+ return ret;
}
-EXPORT_SYMBOL(__ratelimit);
+EXPORT_SYMBOL(___ratelimit);
diff --git a/lib/string.c b/lib/string.c
index b19b87af65a3..e96421ab9a9a 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -246,13 +246,17 @@ EXPORT_SYMBOL(strlcat);
#undef strcmp
int strcmp(const char *cs, const char *ct)
{
- signed char __res;
+ unsigned char c1, c2;
while (1) {
- if ((__res = *cs - *ct++) != 0 || !*cs++)
+ c1 = *cs++;
+ c2 = *ct++;
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (!c1)
break;
}
- return __res;
+ return 0;
}
EXPORT_SYMBOL(strcmp);
#endif
@@ -266,14 +270,18 @@ EXPORT_SYMBOL(strcmp);
*/
int strncmp(const char *cs, const char *ct, size_t count)
{
- signed char __res = 0;
+ unsigned char c1, c2;
while (count) {
- if ((__res = *cs - *ct++) != 0 || !*cs++)
+ c1 = *cs++;
+ c2 = *ct++;
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (!c1)
break;
count--;
}
- return __res;
+ return 0;
}
EXPORT_SYMBOL(strncmp);
#endif
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index bffe6d7ef9d9..795472d8ae24 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -97,6 +97,8 @@ static phys_addr_t *io_tlb_orig_addr;
*/
static DEFINE_SPINLOCK(io_tlb_lock);
+static int late_alloc;
+
static int __init
setup_io_tlb_npages(char *str)
{
@@ -109,55 +111,22 @@ setup_io_tlb_npages(char *str)
++str;
if (!strcmp(str, "force"))
swiotlb_force = 1;
+
return 1;
}
__setup("swiotlb=", setup_io_tlb_npages);
/* make io_tlb_overflow tunable too? */
-void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
-{
- return alloc_bootmem_low_pages(size);
-}
-
-void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
-{
- return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
-}
-
-dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
- return paddr;
-}
-
-phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-{
- return baddr;
-}
-
+/* Note that this doesn't work with highmem page */
static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
volatile void *address)
{
- return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
-}
-
-void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
-{
- return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
-}
-
-int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
- dma_addr_t addr, size_t size)
-{
- return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
-}
-
-int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
-{
- return 0;
+ return phys_to_dma(hwdev, virt_to_phys(address));
}
-static void swiotlb_print_info(unsigned long bytes)
+void swiotlb_print_info(void)
{
+ unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
phys_addr_t pstart, pend;
pstart = virt_to_phys(io_tlb_start);
@@ -175,7 +144,7 @@ static void swiotlb_print_info(unsigned long bytes)
* structures for the software IO TLB used to implement the DMA API.
*/
void __init
-swiotlb_init_with_default_size(size_t default_size)
+swiotlb_init_with_default_size(size_t default_size, int verbose)
{
unsigned long i, bytes;
@@ -189,7 +158,7 @@ swiotlb_init_with_default_size(size_t default_size)
/*
* Get IO TLB memory from the low pages
*/
- io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
+ io_tlb_start = alloc_bootmem_low_pages(bytes);
if (!io_tlb_start)
panic("Cannot allocate SWIOTLB buffer");
io_tlb_end = io_tlb_start + bytes;
@@ -211,14 +180,14 @@ swiotlb_init_with_default_size(size_t default_size)
io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
if (!io_tlb_overflow_buffer)
panic("Cannot allocate SWIOTLB overflow buffer!\n");
-
- swiotlb_print_info(bytes);
+ if (verbose)
+ swiotlb_print_info();
}
void __init
-swiotlb_init(void)
+swiotlb_init(int verbose)
{
- swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */
+ swiotlb_init_with_default_size(64 * (1<<20), verbose); /* default to 64MB */
}
/*
@@ -245,7 +214,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
bytes = io_tlb_nslabs << IO_TLB_SHIFT;
while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
- io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs);
+ io_tlb_start = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+ order);
if (io_tlb_start)
break;
order--;
@@ -294,7 +264,9 @@ swiotlb_late_init_with_default_size(size_t default_size)
if (!io_tlb_overflow_buffer)
goto cleanup4;
- swiotlb_print_info(bytes);
+ swiotlb_print_info();
+
+ late_alloc = 1;
return 0;
@@ -315,20 +287,36 @@ cleanup1:
return -ENOMEM;
}
-static inline int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
+void __init swiotlb_free(void)
{
- return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
-}
+ if (!io_tlb_overflow_buffer)
+ return;
-static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
-{
- return swiotlb_force || swiotlb_arch_range_needs_mapping(paddr, size);
+ if (late_alloc) {
+ free_pages((unsigned long)io_tlb_overflow_buffer,
+ get_order(io_tlb_overflow));
+ free_pages((unsigned long)io_tlb_orig_addr,
+ get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
+ free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+ sizeof(int)));
+ free_pages((unsigned long)io_tlb_start,
+ get_order(io_tlb_nslabs << IO_TLB_SHIFT));
+ } else {
+ free_bootmem_late(__pa(io_tlb_overflow_buffer),
+ io_tlb_overflow);
+ free_bootmem_late(__pa(io_tlb_orig_addr),
+ io_tlb_nslabs * sizeof(phys_addr_t));
+ free_bootmem_late(__pa(io_tlb_list),
+ io_tlb_nslabs * sizeof(int));
+ free_bootmem_late(__pa(io_tlb_start),
+ io_tlb_nslabs << IO_TLB_SHIFT);
+ }
}
-static int is_swiotlb_buffer(char *addr)
+static int is_swiotlb_buffer(phys_addr_t paddr)
{
- return addr >= io_tlb_start && addr < io_tlb_end;
+ return paddr >= virt_to_phys(io_tlb_start) &&
+ paddr < virt_to_phys(io_tlb_end);
}
/*
@@ -561,9 +549,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_mask = hwdev->coherent_dma_mask;
ret = (void *)__get_free_pages(flags, order);
- if (ret &&
- !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(hwdev, ret),
- size)) {
+ if (ret && swiotlb_virt_to_bus(hwdev, ret) + size > dma_mask) {
/*
* The allocated memory isn't reachable by the device.
*/
@@ -585,7 +571,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dev_addr = swiotlb_virt_to_bus(hwdev, ret);
/* Confirm address can be DMA'd by device */
- if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
+ if (dev_addr + size > dma_mask) {
printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
(unsigned long long)dma_mask,
(unsigned long long)dev_addr);
@@ -601,11 +587,13 @@ EXPORT_SYMBOL(swiotlb_alloc_coherent);
void
swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
- dma_addr_t dma_handle)
+ dma_addr_t dev_addr)
{
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
WARN_ON(irqs_disabled());
- if (!is_swiotlb_buffer(vaddr))
- free_pages((unsigned long) vaddr, get_order(size));
+ if (!is_swiotlb_buffer(paddr))
+ free_pages((unsigned long)vaddr, get_order(size));
else
/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
@@ -625,12 +613,15 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
"device %s\n", size, dev ? dev_name(dev) : "?");
- if (size > io_tlb_overflow && do_panic) {
- if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
- panic("DMA: Memory would be corrupted\n");
- if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
- panic("DMA: Random memory would be DMAed\n");
- }
+ if (size <= io_tlb_overflow || !do_panic)
+ return;
+
+ if (dir == DMA_BIDIRECTIONAL)
+ panic("DMA: Random memory could be DMA accessed\n");
+ if (dir == DMA_FROM_DEVICE)
+ panic("DMA: Random memory could be DMA written\n");
+ if (dir == DMA_TO_DEVICE)
+ panic("DMA: Random memory could be DMA read\n");
}
/*
@@ -646,7 +637,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
struct dma_attrs *attrs)
{
phys_addr_t phys = page_to_phys(page) + offset;
- dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
+ dma_addr_t dev_addr = phys_to_dma(dev, phys);
void *map;
BUG_ON(dir == DMA_NONE);
@@ -655,8 +646,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
- if (!address_needs_mapping(dev, dev_addr, size) &&
- !range_needs_mapping(phys, size))
+ if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
return dev_addr;
/*
@@ -673,7 +663,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
/*
* Ensure that the address returned is DMA'ble
*/
- if (address_needs_mapping(dev, dev_addr, size))
+ if (!dma_capable(dev, dev_addr, size))
panic("map_single: bounce buffer is not DMA'ble");
return dev_addr;
@@ -691,19 +681,25 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, int dir)
{
- char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(dma_addr)) {
- do_unmap_single(hwdev, dma_addr, size, dir);
+ if (is_swiotlb_buffer(paddr)) {
+ do_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
return;
}
if (dir != DMA_FROM_DEVICE)
return;
- dma_mark_clean(dma_addr, size);
+ /*
+ * phys_to_virt doesn't work with hihgmem page but we could
+ * call dma_mark_clean() with hihgmem page here. However, we
+ * are fine since dma_mark_clean() is null on POWERPC. We can
+ * make dma_mark_clean() take a physical address if necessary.
+ */
+ dma_mark_clean(phys_to_virt(paddr), size);
}
void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
@@ -728,19 +724,19 @@ static void
swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, int dir, int target)
{
- char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(dma_addr)) {
- sync_single(hwdev, dma_addr, size, dir, target);
+ if (is_swiotlb_buffer(paddr)) {
+ sync_single(hwdev, phys_to_virt(paddr), size, dir, target);
return;
}
if (dir != DMA_FROM_DEVICE)
return;
- dma_mark_clean(dma_addr, size);
+ dma_mark_clean(phys_to_virt(paddr), size);
}
void
@@ -817,10 +813,10 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
for_each_sg(sgl, sg, nelems, i) {
phys_addr_t paddr = sg_phys(sg);
- dma_addr_t dev_addr = swiotlb_phys_to_bus(hwdev, paddr);
+ dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
- if (range_needs_mapping(paddr, sg->length) ||
- address_needs_mapping(hwdev, dev_addr, sg->length)) {
+ if (swiotlb_force ||
+ !dma_capable(hwdev, dev_addr, sg->length)) {
void *map = map_single(hwdev, sg_phys(sg),
sg->length, dir);
if (!map) {
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 756ccafa9cec..33bed5e67a21 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -25,6 +25,7 @@
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ioport.h>
+#include <net/addrconf.h>
#include <asm/page.h> /* for PAGE_SIZE */
#include <asm/div64.h>
@@ -580,7 +581,7 @@ static char *symbol_string(char *buf, char *end, void *ptr,
unsigned long value = (unsigned long) ptr;
#ifdef CONFIG_KALLSYMS
char sym[KSYM_SYMBOL_LEN];
- if (ext != 'f')
+ if (ext != 'f' && ext != 's')
sprint_symbol(sym, value);
else
kallsyms_lookup(value, NULL, NULL, NULL, sym);
@@ -630,60 +631,161 @@ static char *resource_string(char *buf, char *end, struct resource *res,
}
static char *mac_address_string(char *buf, char *end, u8 *addr,
- struct printf_spec spec)
+ struct printf_spec spec, const char *fmt)
{
- char mac_addr[6 * 3]; /* (6 * 2 hex digits), 5 colons and trailing zero */
+ char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")];
char *p = mac_addr;
int i;
for (i = 0; i < 6; i++) {
p = pack_hex_byte(p, addr[i]);
- if (!(spec.flags & SPECIAL) && i != 5)
+ if (fmt[0] == 'M' && i != 5)
*p++ = ':';
}
*p = '\0';
- spec.flags &= ~SPECIAL;
return string(buf, end, mac_addr, spec);
}
-static char *ip6_addr_string(char *buf, char *end, u8 *addr,
- struct printf_spec spec)
+static char *ip4_string(char *p, const u8 *addr, bool leading_zeros)
{
- char ip6_addr[8 * 5]; /* (8 * 4 hex digits), 7 colons and trailing zero */
- char *p = ip6_addr;
int i;
+ for (i = 0; i < 4; i++) {
+ char temp[3]; /* hold each IP quad in reverse order */
+ int digits = put_dec_trunc(temp, addr[i]) - temp;
+ if (leading_zeros) {
+ if (digits < 3)
+ *p++ = '0';
+ if (digits < 2)
+ *p++ = '0';
+ }
+ /* reverse the digits in the quad */
+ while (digits--)
+ *p++ = temp[digits];
+ if (i < 3)
+ *p++ = '.';
+ }
+
+ *p = '\0';
+ return p;
+}
+
+static char *ip6_compressed_string(char *p, const char *addr)
+{
+ int i;
+ int j;
+ int range;
+ unsigned char zerolength[8];
+ int longest = 1;
+ int colonpos = -1;
+ u16 word;
+ u8 hi;
+ u8 lo;
+ bool needcolon = false;
+ bool useIPv4;
+ struct in6_addr in6;
+
+ memcpy(&in6, addr, sizeof(struct in6_addr));
+
+ useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6);
+
+ memset(zerolength, 0, sizeof(zerolength));
+
+ if (useIPv4)
+ range = 6;
+ else
+ range = 8;
+
+ /* find position of longest 0 run */
+ for (i = 0; i < range; i++) {
+ for (j = i; j < range; j++) {
+ if (in6.s6_addr16[j] != 0)
+ break;
+ zerolength[i]++;
+ }
+ }
+ for (i = 0; i < range; i++) {
+ if (zerolength[i] > longest) {
+ longest = zerolength[i];
+ colonpos = i;
+ }
+ }
+
+ /* emit address */
+ for (i = 0; i < range; i++) {
+ if (i == colonpos) {
+ if (needcolon || i == 0)
+ *p++ = ':';
+ *p++ = ':';
+ needcolon = false;
+ i += longest - 1;
+ continue;
+ }
+ if (needcolon) {
+ *p++ = ':';
+ needcolon = false;
+ }
+ /* hex u16 without leading 0s */
+ word = ntohs(in6.s6_addr16[i]);
+ hi = word >> 8;
+ lo = word & 0xff;
+ if (hi) {
+ if (hi > 0x0f)
+ p = pack_hex_byte(p, hi);
+ else
+ *p++ = hex_asc_lo(hi);
+ }
+ if (hi || lo > 0x0f)
+ p = pack_hex_byte(p, lo);
+ else
+ *p++ = hex_asc_lo(lo);
+ needcolon = true;
+ }
+
+ if (useIPv4) {
+ if (needcolon)
+ *p++ = ':';
+ p = ip4_string(p, &in6.s6_addr[12], false);
+ }
+
+ *p = '\0';
+ return p;
+}
+
+static char *ip6_string(char *p, const char *addr, const char *fmt)
+{
+ int i;
for (i = 0; i < 8; i++) {
- p = pack_hex_byte(p, addr[2 * i]);
- p = pack_hex_byte(p, addr[2 * i + 1]);
- if (!(spec.flags & SPECIAL) && i != 7)
+ p = pack_hex_byte(p, *addr++);
+ p = pack_hex_byte(p, *addr++);
+ if (fmt[0] == 'I' && i != 7)
*p++ = ':';
}
+
*p = '\0';
- spec.flags &= ~SPECIAL;
+ return p;
+}
+
+static char *ip6_addr_string(char *buf, char *end, const u8 *addr,
+ struct printf_spec spec, const char *fmt)
+{
+ char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")];
+
+ if (fmt[0] == 'I' && fmt[2] == 'c')
+ ip6_compressed_string(ip6_addr, addr);
+ else
+ ip6_string(ip6_addr, addr, fmt);
return string(buf, end, ip6_addr, spec);
}
-static char *ip4_addr_string(char *buf, char *end, u8 *addr,
- struct printf_spec spec)
+static char *ip4_addr_string(char *buf, char *end, const u8 *addr,
+ struct printf_spec spec, const char *fmt)
{
- char ip4_addr[4 * 4]; /* (4 * 3 decimal digits), 3 dots and trailing zero */
- char temp[3]; /* hold each IP quad in reverse order */
- char *p = ip4_addr;
- int i, digits;
+ char ip4_addr[sizeof("255.255.255.255")];
- for (i = 0; i < 4; i++) {
- digits = put_dec_trunc(temp, addr[i]) - temp;
- /* reverse the digits in the quad */
- while (digits--)
- *p++ = temp[digits];
- if (i != 3)
- *p++ = '.';
- }
- *p = '\0';
- spec.flags &= ~SPECIAL;
+ ip4_string(ip4_addr, addr, fmt[0] == 'i');
return string(buf, end, ip4_addr, spec);
}
@@ -697,16 +799,21 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr,
*
* - 'F' For symbolic function descriptor pointers with offset
* - 'f' For simple symbolic function names without offset
- * - 'S' For symbolic direct pointers
+ * - 'S' For symbolic direct pointers with offset
+ * - 's' For symbolic direct pointers without offset
* - 'R' For a struct resource pointer, it prints the range of
* addresses (not the name nor the flags)
* - 'M' For a 6-byte MAC address, it prints the address in the
* usual colon-separated hex notation
- * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way (dot-separated
- * decimal for v4 and colon separated network-order 16 bit hex for v6)
- * - 'i' [46] for 'raw' IPv4/IPv6 addresses, IPv6 omits the colons, IPv4 is
- * currently the same
- *
+ * - 'm' For a 6-byte MAC address, it prints the hex address without colons
+ * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way
+ * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4)
+ * IPv6 uses colon separated network-order 16 bit hex with leading 0's
+ * - 'i' [46] for 'raw' IPv4/IPv6 addresses
+ * IPv6 omits the colons (01020304...0f)
+ * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006)
+ * - 'I6c' for IPv6 addresses printed as specified by
+ * http://www.ietf.org/id/draft-kawamura-ipv6-text-representation-03.txt
* Note: The difference between 'S' and 'F' is that on ia64 and ppc64
* function pointers are really function descriptors, which contain a
* pointer to the real address.
@@ -721,25 +828,30 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
case 'F':
case 'f':
ptr = dereference_function_descriptor(ptr);
+ case 's':
/* Fallthrough */
case 'S':
return symbol_string(buf, end, ptr, spec, *fmt);
case 'R':
return resource_string(buf, end, ptr, spec);
- case 'm':
- spec.flags |= SPECIAL;
- /* Fallthrough */
- case 'M':
- return mac_address_string(buf, end, ptr, spec);
- case 'i':
- spec.flags |= SPECIAL;
- /* Fallthrough */
- case 'I':
- if (fmt[1] == '6')
- return ip6_addr_string(buf, end, ptr, spec);
- if (fmt[1] == '4')
- return ip4_addr_string(buf, end, ptr, spec);
- spec.flags &= ~SPECIAL;
+ case 'M': /* Colon separated: 00:01:02:03:04:05 */
+ case 'm': /* Contiguous: 000102030405 */
+ return mac_address_string(buf, end, ptr, spec, fmt);
+ case 'I': /* Formatted IP supported
+ * 4: 1.2.3.4
+ * 6: 0001:0203:...:0708
+ * 6c: 1::708 or 1::1.2.3.4
+ */
+ case 'i': /* Contiguous:
+ * 4: 001.002.003.004
+ * 6: 000102...0f
+ */
+ switch (fmt[1]) {
+ case '6':
+ return ip6_addr_string(buf, end, ptr, spec, fmt);
+ case '4':
+ return ip4_addr_string(buf, end, ptr, spec, fmt);
+ }
break;
}
spec.flags |= SMALL;
@@ -958,10 +1070,12 @@ qualifier:
* @args: Arguments for the format string
*
* This function follows C99 vsnprintf, but has some extensions:
- * %pS output the name of a text symbol
+ * %pS output the name of a text symbol with offset
+ * %ps output the name of a text symbol without offset
* %pF output the name of a function pointer with its offset
* %pf output the name of a function pointer without its offset
* %pR output the address range in a struct resource
+ * %n is ignored
*
* The return value is the number of characters which would
* be generated for the given input, excluding the trailing
@@ -983,13 +1097,8 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
/* Reject out-of-range values early. Large positive sizes are
used for unknown buffer sizes. */
- if (unlikely((int) size < 0)) {
- /* There can be only one.. */
- static char warn = 1;
- WARN_ON(warn);
- warn = 0;
+ if (WARN_ON_ONCE((int) size < 0))
return 0;
- }
str = buf;
end = buf + size;
@@ -1417,11 +1526,7 @@ EXPORT_SYMBOL_GPL(vbin_printf);
* a binary buffer that generated by vbin_printf.
*
* The format follows C99 vsnprintf, but has some extensions:
- * %pS output the name of a text symbol
- * %pF output the name of a function pointer with its offset
- * %pf output the name of a function pointer without its offset
- * %pR output the address range in a struct resource
- * %n is ignored
+ * see vsnprintf comment for details.
*
* The return value is the number of characters which would
* be generated for the given input, excluding the trailing
@@ -1439,13 +1544,8 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
struct printf_spec spec = {0};
- if (unlikely((int) size < 0)) {
- /* There can be only one.. */
- static char warn = 1;
- WARN_ON(warn);
- warn = 0;
+ if (WARN_ON_ONCE((int) size < 0))
return 0;
- }
str = buf;
end = buf + size;
@@ -1671,7 +1771,7 @@ int vsscanf(const char * buf, const char * fmt, va_list args)
* advance both strings to next white space
*/
if (*fmt == '*') {
- while (!isspace(*fmt) && *fmt)
+ while (!isspace(*fmt) && *fmt != '%' && *fmt)
fmt++;
while (!isspace(*str) && *str)
str++;
diff --git a/lib/zlib_deflate/deflate.c b/lib/zlib_deflate/deflate.c
index c3e4a2baf835..46a31e5f49c3 100644
--- a/lib/zlib_deflate/deflate.c
+++ b/lib/zlib_deflate/deflate.c
@@ -135,7 +135,7 @@ static const config configuration_table[10] = {
/* ===========================================================================
* Update a hash value with the given input byte
- * IN assertion: all calls to to UPDATE_HASH are made with consecutive
+ * IN assertion: all calls to UPDATE_HASH are made with consecutive
* input characters, so that a running hash key can be computed from the
* previous key instead of complete recalculation each time.
*/
@@ -146,7 +146,7 @@ static const config configuration_table[10] = {
* Insert string str in the dictionary and set match_head to the previous head
* of the hash chain (the most recent string with same hash key). Return
* the previous length of the hash chain.
- * IN assertion: all calls to to INSERT_STRING are made with consecutive
+ * IN assertion: all calls to INSERT_STRING are made with consecutive
* input characters and the first MIN_MATCH bytes of str are valid
* (except for the last MIN_MATCH-1 bytes of the input file).
*/
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-17 14:44:01 +0000