summaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig6
-rw-r--r--lib/Kconfig.debug45
-rw-r--r--lib/Makefile1
-rw-r--r--lib/assoc_array.c2
-rw-r--r--lib/bitmap.c18
-rw-r--r--lib/cmdline.c1
-rw-r--r--lib/cpumask.c16
-rw-r--r--lib/debugobjects.c3
-rw-r--r--lib/errseq.c17
-rw-r--r--lib/hexdump.c5
-rw-r--r--lib/idr.c66
-rw-r--r--lib/interval_tree_test.c4
-rw-r--r--lib/kobject_uevent.c2
-rw-r--r--lib/locking-selftest.c123
-rw-r--r--lib/mpi/longlong.h24
-rw-r--r--lib/mpi/mpicoder.c4
-rw-r--r--lib/nlattr.c54
-rw-r--r--lib/oid_registry.c4
-rw-r--r--lib/radix-tree.c16
-rw-r--r--lib/raid6/Makefile4
-rw-r--r--lib/raid6/algos.c3
-rw-r--r--lib/raid6/avx512.c2
-rw-r--r--lib/raid6/neon.uc33
-rw-r--r--lib/raid6/recov_neon.c110
-rw-r--r--lib/raid6/recov_neon_inner.c117
-rw-r--r--lib/rbtree.c65
-rw-r--r--lib/rbtree_test.c230
-rw-r--r--lib/string.c207
-rw-r--r--lib/string_helpers.c4
-rw-r--r--lib/swiotlb.c57
-rw-r--r--lib/test_bitmap.c91
-rw-r--r--lib/test_bpf.c364
-rw-r--r--lib/test_debug_virtual.c49
-rw-r--r--lib/test_firmware.c710
-rw-r--r--lib/test_kmod.c4
35 files changed, 2303 insertions, 158 deletions
diff --git a/lib/Kconfig b/lib/Kconfig
index 0d49ed0..b1445b2 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -570,9 +570,6 @@ config ARCH_HAS_PMEM_API
config ARCH_HAS_UACCESS_FLUSHCACHE
bool
-config ARCH_HAS_MMIO_FLUSH
- bool
-
config STACKDEPOT
bool
select STACKTRACE
@@ -586,4 +583,7 @@ config PARMAN
config PRIME_NUMBERS
tristate
+config STRING_SELFTEST
+ bool "Test string functions"
+
endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 98fe715..b19c491 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -374,6 +374,9 @@ config STACK_VALIDATION
pointers (if CONFIG_FRAME_POINTER is enabled). This helps ensure
that runtime stack traces are more reliable.
+ This is also a prerequisite for generation of ORC unwind data, which
+ is needed for CONFIG_ORC_UNWINDER.
+
For more information, see
tools/objtool/Documentation/stack-validation.txt.
@@ -798,6 +801,13 @@ config HARDLOCKUP_DETECTOR_PERF
select SOFTLOCKUP_DETECTOR
#
+# Enables a timestamp based low pass filter to compensate for perf based
+# hard lockup detection which runs too fast due to turbo modes.
+#
+config HARDLOCKUP_CHECK_TIMESTAMP
+ bool
+
+#
# arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard
# lockup detector rather than the perf based detector.
#
@@ -1081,6 +1091,8 @@ config PROVE_LOCKING
select DEBUG_MUTEXES
select DEBUG_RT_MUTEXES if RT_MUTEXES
select DEBUG_LOCK_ALLOC
+ select LOCKDEP_CROSSRELEASE
+ select LOCKDEP_COMPLETIONS
select TRACE_IRQFLAGS
default n
help
@@ -1121,7 +1133,7 @@ config LOCKDEP
bool
depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
select STACKTRACE
- select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE
+ select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE && !X86
select KALLSYMS
select KALLSYMS_ALL
@@ -1150,6 +1162,22 @@ config LOCK_STAT
CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
(CONFIG_LOCKDEP defines "acquire" and "release" events.)
+config LOCKDEP_CROSSRELEASE
+ bool
+ help
+ This makes lockdep work for crosslock which is a lock allowed to
+ be released in a different context from the acquisition context.
+ Normally a lock must be released in the context acquiring the lock.
+ However, relexing this constraint helps synchronization primitives
+ such as page locks or completions can use the lock correctness
+ detector, lockdep.
+
+config LOCKDEP_COMPLETIONS
+ bool
+ help
+ A deadlock caused by wait_for_completion() and complete() can be
+ detected by lockdep using crossrelease feature.
+
config DEBUG_LOCKDEP
bool "Lock dependency engine debugging"
depends on DEBUG_KERNEL && LOCKDEP
@@ -1540,7 +1568,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
depends on !X86_64
select STACKTRACE
- select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE
+ select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE && !X86
help
Provide stacktrace filter for fault-injection capabilities
@@ -1549,7 +1577,7 @@ config LATENCYTOP
depends on DEBUG_KERNEL
depends on STACKTRACE_SUPPORT
depends on PROC_FS
- select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC
+ select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !X86
select KALLSYMS
select KALLSYMS_ALL
select STACKTRACE
@@ -1902,6 +1930,17 @@ config TEST_KMOD
If unsure, say N.
+config TEST_DEBUG_VIRTUAL
+ tristate "Test CONFIG_DEBUG_VIRTUAL feature"
+ depends on DEBUG_VIRTUAL
+ help
+ Test the kernel's ability to detect incorrect calls to
+ virt_to_phys() done against the non-linear part of the
+ kernel's virtual address map.
+
+ If unsure, say N.
+
+
source "samples/Kconfig"
source "lib/Kconfig.kgdb"
diff --git a/lib/Makefile b/lib/Makefile
index d5c8a4f..dafa796 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
obj-$(CONFIG_TEST_UUID) += test_uuid.o
obj-$(CONFIG_TEST_PARMAN) += test_parman.o
obj-$(CONFIG_TEST_KMOD) += test_kmod.o
+obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
ifeq ($(CONFIG_DEBUG_KOBJECT),y)
CFLAGS_kobject.o += -DDEBUG
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 59fd7c0..155c55d 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -1,6 +1,6 @@
/* Generic associative array implementation.
*
- * See Documentation/assoc_array.txt for information.
+ * See Documentation/core-api/assoc_array.rst for information.
*
* Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 9a53280..c82c61b 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -513,7 +513,7 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
int nmaskbits)
{
unsigned int a, b, old_a, old_b;
- unsigned int group_size, used_size;
+ unsigned int group_size, used_size, off;
int c, old_c, totaldigits, ndigits;
const char __user __force *ubuf = (const char __user __force *)buf;
int at_start, in_range, in_partial_range;
@@ -599,6 +599,8 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
a = old_a;
b = old_b;
old_a = old_b = 0;
+ } else {
+ used_size = group_size = b - a + 1;
}
/* if no digit is after '-', it's wrong*/
if (at_start && in_range)
@@ -608,17 +610,9 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
if (b >= nmaskbits)
return -ERANGE;
while (a <= b) {
- if (in_partial_range) {
- static int pos_in_group = 1;
-
- if (pos_in_group <= used_size)
- set_bit(a, maskp);
-
- if (a == b || ++pos_in_group > group_size)
- pos_in_group = 1;
- } else
- set_bit(a, maskp);
- a++;
+ off = min(b - a + 1, used_size);
+ bitmap_set(maskp, a, off);
+ a += group_size;
}
} while (buflen && c == ',');
return 0;
diff --git a/lib/cmdline.c b/lib/cmdline.c
index 4c0888c..171c19b 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -244,5 +244,4 @@ char *next_arg(char *args, char **param, char **val)
/* Chew up trailing spaces. */
return skip_spaces(next);
- //return next;
}
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 4731a08..8b1a1bd 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -6,6 +6,22 @@
#include <linux/bootmem.h>
/**
+ * cpumask_next - get the next cpu in a cpumask
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set.
+ */
+unsigned int cpumask_next(int n, const struct cpumask *srcp)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpumask_check(n);
+ return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
+}
+EXPORT_SYMBOL(cpumask_next);
+
+/**
* cpumask_next_and - get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (ie. return will be > @n)
* @src1p: the first cpumask pointer
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 17afb04..2f5349c 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -18,6 +18,7 @@
#include <linux/debugfs.h>
#include <linux/slab.h>
#include <linux/hash.h>
+#include <linux/kmemleak.h>
#define ODEBUG_HASH_BITS 14
#define ODEBUG_HASH_SIZE (1 << ODEBUG_HASH_BITS)
@@ -110,6 +111,7 @@ static void fill_pool(void)
if (!new)
return;
+ kmemleak_ignore(new);
raw_spin_lock_irqsave(&pool_lock, flags);
hlist_add_head(&new->node, &obj_pool);
debug_objects_allocated++;
@@ -1080,6 +1082,7 @@ static int __init debug_objects_replace_static_objects(void)
obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL);
if (!obj)
goto free;
+ kmemleak_ignore(obj);
hlist_add_head(&obj->node, &objects);
}
diff --git a/lib/errseq.c b/lib/errseq.c
index 841fa24..7b900c2 100644
--- a/lib/errseq.c
+++ b/lib/errseq.c
@@ -41,23 +41,20 @@
#define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1))
/**
- * __errseq_set - set a errseq_t for later reporting
+ * errseq_set - set a errseq_t for later reporting
* @eseq: errseq_t field that should be set
- * @err: error to set
+ * @err: error to set (must be between -1 and -MAX_ERRNO)
*
* This function sets the error in *eseq, and increments the sequence counter
* if the last sequence was sampled at some point in the past.
*
* Any error set will always overwrite an existing error.
*
- * Most callers will want to use the errseq_set inline wrapper to efficiently
- * handle the common case where err is 0.
- *
- * We do return an errseq_t here, primarily for debugging purposes. The return
- * value should not be used as a previously sampled value in later calls as it
- * will not have the SEEN flag set.
+ * We do return the latest value here, primarily for debugging purposes. The
+ * return value should not be used as a previously sampled value in later calls
+ * as it will not have the SEEN flag set.
*/
-errseq_t __errseq_set(errseq_t *eseq, int err)
+errseq_t errseq_set(errseq_t *eseq, int err)
{
errseq_t cur, old;
@@ -107,7 +104,7 @@ errseq_t __errseq_set(errseq_t *eseq, int err)
}
return cur;
}
-EXPORT_SYMBOL(__errseq_set);
+EXPORT_SYMBOL(errseq_set);
/**
* errseq_sample - grab current errseq_t value
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 992457b..81b70ed 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -9,6 +9,7 @@
#include <linux/types.h>
#include <linux/ctype.h>
+#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <asm/unaligned.h>
@@ -42,7 +43,7 @@ EXPORT_SYMBOL(hex_to_bin);
* @src: ascii hexadecimal string
* @count: result length
*
- * Return 0 on success, -1 in case of bad input.
+ * Return 0 on success, -EINVAL in case of bad input.
*/
int hex2bin(u8 *dst, const char *src, size_t count)
{
@@ -51,7 +52,7 @@ int hex2bin(u8 *dst, const char *src, size_t count)
int lo = hex_to_bin(*src++);
if ((hi < 0) || (lo < 0))
- return -1;
+ return -EINVAL;
*dst++ = (hi << 4) | lo;
}
diff --git a/lib/idr.c b/lib/idr.c
index b13682b..f9adf48 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -7,45 +7,32 @@
DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
static DEFINE_SPINLOCK(simple_ida_lock);
-/**
- * idr_alloc - allocate an id
- * @idr: idr handle
- * @ptr: pointer to be associated with the new id
- * @start: the minimum id (inclusive)
- * @end: the maximum id (exclusive)
- * @gfp: memory allocation flags
- *
- * Allocates an unused ID in the range [start, end). Returns -ENOSPC
- * if there are no unused IDs in that range.
- *
- * 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.
- *
- * Simultaneous modifications to the @idr are not allowed and should be
- * prevented by the user, usually with a lock. idr_alloc() may be called
- * concurrently with read-only accesses to the @idr, such as idr_find() and
- * idr_for_each_entry().
- */
-int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
+int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index,
+ unsigned long start, unsigned long end, gfp_t gfp,
+ bool ext)
{
- void __rcu **slot;
struct radix_tree_iter iter;
+ void __rcu **slot;
- if (WARN_ON_ONCE(start < 0))
- return -EINVAL;
if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
return -EINVAL;
radix_tree_iter_init(&iter, start);
- slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
+ if (ext)
+ slot = idr_get_free_ext(&idr->idr_rt, &iter, gfp, end);
+ else
+ slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
if (IS_ERR(slot))
return PTR_ERR(slot);
radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr);
radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE);
- return iter.index;
+
+ if (index)
+ *index = iter.index;
+ return 0;
}
-EXPORT_SYMBOL_GPL(idr_alloc);
+EXPORT_SYMBOL_GPL(idr_alloc_cmn);
/**
* idr_alloc_cyclic - allocate new idr entry in a cyclical fashion
@@ -134,6 +121,20 @@ void *idr_get_next(struct idr *idr, int *nextid)
}
EXPORT_SYMBOL(idr_get_next);
+void *idr_get_next_ext(struct idr *idr, unsigned long *nextid)
+{
+ struct radix_tree_iter iter;
+ void __rcu **slot;
+
+ slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid);
+ if (!slot)
+ return NULL;
+
+ *nextid = iter.index;
+ return rcu_dereference_raw(*slot);
+}
+EXPORT_SYMBOL(idr_get_next_ext);
+
/**
* idr_replace - replace pointer for given id
* @idr: idr handle
@@ -150,12 +151,19 @@ EXPORT_SYMBOL(idr_get_next);
*/
void *idr_replace(struct idr *idr, void *ptr, int id)
{
+ if (id < 0)
+ return ERR_PTR(-EINVAL);
+
+ return idr_replace_ext(idr, ptr, id);
+}
+EXPORT_SYMBOL(idr_replace);
+
+void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id)
+{
struct radix_tree_node *node;
void __rcu **slot = NULL;
void *entry;
- if (WARN_ON_ONCE(id < 0))
- return ERR_PTR(-EINVAL);
if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
return ERR_PTR(-EINVAL);
@@ -167,7 +175,7 @@ void *idr_replace(struct idr *idr, void *ptr, int id)
return entry;
}
-EXPORT_SYMBOL(idr_replace);
+EXPORT_SYMBOL(idr_replace_ext);
/**
* DOC: IDA description
diff --git a/lib/interval_tree_test.c b/lib/interval_tree_test.c
index df495fe..0e343fd 100644
--- a/lib/interval_tree_test.c
+++ b/lib/interval_tree_test.c
@@ -19,14 +19,14 @@ __param(bool, search_all, false, "Searches will iterate all nodes in the tree");
__param(uint, max_endpoint, ~0, "Largest value for the interval's endpoint");
-static struct rb_root root = RB_ROOT;
+static struct rb_root_cached root = RB_ROOT_CACHED;
static struct interval_tree_node *nodes = NULL;
static u32 *queries = NULL;
static struct rnd_state rnd;
static inline unsigned long
-search(struct rb_root *root, unsigned long start, unsigned long last)
+search(struct rb_root_cached *root, unsigned long start, unsigned long last)
{
struct interval_tree_node *node;
unsigned long results = 0;
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 719c155..e590523 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -52,6 +52,8 @@ static const char *kobject_actions[] = {
[KOBJ_MOVE] = "move",
[KOBJ_ONLINE] = "online",
[KOBJ_OFFLINE] = "offline",
+ [KOBJ_BIND] = "bind",
+ [KOBJ_UNBIND] = "unbind",
};
static int kobject_action_type(const char *buf, size_t count,
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 6f2b135..cd0b5c9 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -363,6 +363,103 @@ static void rsem_AA3(void)
}
/*
+ * read_lock(A)
+ * spin_lock(B)
+ * spin_lock(B)
+ * write_lock(A)
+ */
+static void rlock_ABBA1(void)
+{
+ RL(X1);
+ L(Y1);
+ U(Y1);
+ RU(X1);
+
+ L(Y1);
+ WL(X1);
+ WU(X1);
+ U(Y1); // should fail
+}
+
+static void rwsem_ABBA1(void)
+{
+ RSL(X1);
+ ML(Y1);
+ MU(Y1);
+ RSU(X1);
+
+ ML(Y1);
+ WSL(X1);
+ WSU(X1);
+ MU(Y1); // should fail
+}
+
+/*
+ * read_lock(A)
+ * spin_lock(B)
+ * spin_lock(B)
+ * read_lock(A)
+ */
+static void rlock_ABBA2(void)
+{
+ RL(X1);
+ L(Y1);
+ U(Y1);
+ RU(X1);
+
+ L(Y1);
+ RL(X1);
+ RU(X1);
+ U(Y1); // should NOT fail
+}
+
+static void rwsem_ABBA2(void)
+{
+ RSL(X1);
+ ML(Y1);
+ MU(Y1);
+ RSU(X1);
+
+ ML(Y1);
+ RSL(X1);
+ RSU(X1);
+ MU(Y1); // should fail
+}
+
+
+/*
+ * write_lock(A)
+ * spin_lock(B)
+ * spin_lock(B)
+ * write_lock(A)
+ */
+static void rlock_ABBA3(void)
+{
+ WL(X1);
+ L(Y1);
+ U(Y1);
+ WU(X1);
+
+ L(Y1);
+ WL(X1);
+ WU(X1);
+ U(Y1); // should fail
+}
+
+static void rwsem_ABBA3(void)
+{
+ WSL(X1);
+ ML(Y1);
+ MU(Y1);
+ WSU(X1);
+
+ ML(Y1);
+ WSL(X1);
+ WSU(X1);
+ MU(Y1); // should fail
+}
+
+/*
* ABBA deadlock:
*/
@@ -1056,8 +1153,6 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask)
if (debug_locks != expected) {
unexpected_testcase_failures++;
pr_cont("FAILED|");
-
- dump_stack();
} else {
testcase_successes++;
pr_cont(" ok |");
@@ -1933,6 +2028,30 @@ void locking_selftest(void)
dotest(rsem_AA3, FAILURE, LOCKTYPE_RWSEM);
pr_cont("\n");
+ print_testname("mixed read-lock/lock-write ABBA");
+ pr_cont(" |");
+ dotest(rlock_ABBA1, FAILURE, LOCKTYPE_RWLOCK);
+ /*
+ * Lockdep does indeed fail here, but there's nothing we can do about
+ * that now. Don't kill lockdep for it.
+ */
+ unexpected_testcase_failures--;
+
+ pr_cont(" |");
+ dotest(rwsem_ABBA1, FAILURE, LOCKTYPE_RWSEM);
+
+ print_testname("mixed read-lock/lock-read ABBA");
+ pr_cont(" |");
+ dotest(rlock_ABBA2, SUCCESS, LOCKTYPE_RWLOCK);
+ pr_cont(" |");
+ dotest(rwsem_ABBA2, FAILURE, LOCKTYPE_RWSEM);
+
+ print_testname("mixed write-lock/lock-write ABBA");
+ pr_cont(" |");
+ dotest(rlock_ABBA3, FAILURE, LOCKTYPE_RWLOCK);
+ pr_cont(" |");
+ dotest(rwsem_ABBA3, FAILURE, LOCKTYPE_RWSEM);
+
printk(" --------------------------------------------------------------------------\n");
/*
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index 9333650..57fd45a 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -176,8 +176,8 @@ extern UDItype __udiv_qrnnd(UDItype *, UDItype, UDItype, UDItype);
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("adds %1, %4, %5\n" \
"adc %0, %2, %3" \
- : "=r" ((USItype)(sh)), \
- "=&r" ((USItype)(sl)) \
+ : "=r" (sh), \
+ "=&r" (sl) \
: "%r" ((USItype)(ah)), \
"rI" ((USItype)(bh)), \
"%r" ((USItype)(al)), \
@@ -185,15 +185,15 @@ extern UDItype __udiv_qrnnd(UDItype *, UDItype, UDItype, UDItype);
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("subs %1, %4, %5\n" \
"sbc %0, %2, %3" \
- : "=r" ((USItype)(sh)), \
- "=&r" ((USItype)(sl)) \
+ : "=r" (sh), \
+ "=&r" (sl) \
: "r" ((USItype)(ah)), \
"rI" ((USItype)(bh)), \
"r" ((USItype)(al)), \
"rI" ((USItype)(bl)))
#if defined __ARM_ARCH_2__ || defined __ARM_ARCH_3__
#define umul_ppmm(xh, xl, a, b) \
- __asm__ ("%@ Inlined umul_ppmm\n" \
+ __asm__ ("@ Inlined umul_ppmm\n" \
"mov %|r0, %2, lsr #16 @ AAAA\n" \
"mov %|r2, %3, lsr #16 @ BBBB\n" \
"bic %|r1, %2, %|r0, lsl #16 @ aaaa\n" \
@@ -206,19 +206,19 @@ extern UDItype __udiv_qrnnd(UDItype *, UDItype, UDItype, UDItype);
"addcs %|r2, %|r2, #65536\n" \
"adds %1, %|r1, %|r0, lsl #16\n" \
"adc %0, %|r2, %|r0, lsr #16" \
- : "=&r" ((USItype)(xh)), \
- "=r" ((USItype)(xl)) \
+ : "=&r" (xh), \
+ "=r" (xl) \
: "r" ((USItype)(a)), \
"r" ((USItype)(b)) \
: "r0", "r1", "r2")
#else
#define umul_ppmm(xh, xl, a, b) \
- __asm__ ("%@ Inlined umul_ppmm\n" \
- "umull %r1, %r0, %r2, %r3" \
- : "=&r" ((USItype)(xh)), \
- "=&r" ((USItype)(xl)) \
+ __asm__ ("@ Inlined umul_ppmm\n" \
+ "umull %1, %0, %2, %3" \
+ : "=&r" (xh), \
+ "=&r" (xl) \
: "r" ((USItype)(a)), \
- "r" ((USItype)(b)) \
+ "r" ((USItype)(b)) \
: "r0", "r1")
#endif
#define UMUL_TIME 20
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 5a0f75a..eead4b3 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -364,11 +364,11 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
}
miter.consumed = lzeros;
- sg_miter_stop(&miter);
nbytes -= lzeros;
nbits = nbytes * 8;
if (nbits > MAX_EXTERN_MPI_BITS) {
+ sg_miter_stop(&miter);
pr_info("MPI: mpi too large (%u bits)\n", nbits);
return NULL;
}
@@ -376,6 +376,8 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
if (nbytes > 0)
nbits -= count_leading_zeros(*buff) - (BITS_PER_LONG - 8);
+ sg_miter_stop(&miter);
+
nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
val = mpi_alloc(nlimbs);
if (!val)
diff --git a/lib/nlattr.c b/lib/nlattr.c
index fb52435..927c2f1 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -27,6 +27,30 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
[NLA_S64] = sizeof(s64),
};
+static int validate_nla_bitfield32(const struct nlattr *nla,
+ u32 *valid_flags_allowed)
+{
+ const struct nla_bitfield32 *bf = nla_data(nla);
+ u32 *valid_flags_mask = valid_flags_allowed;
+
+ if (!valid_flags_allowed)
+ return -EINVAL;
+
+ /*disallow invalid bit selector */
+ if (bf->selector & ~*valid_flags_mask)
+ return -EINVAL;
+
+ /*disallow invalid bit values */
+ if (bf->value & ~*valid_flags_mask)
+ return -EINVAL;
+
+ /*disallow valid bit values that are not selected*/
+ if (bf->value & ~bf->selector)
+ return -EINVAL;
+
+ return 0;
+}
+
static int validate_nla(const struct nlattr *nla, int maxtype,
const struct nla_policy *policy)
{
@@ -46,6 +70,12 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
return -ERANGE;
break;
+ case NLA_BITFIELD32:
+ if (attrlen != sizeof(struct nla_bitfield32))
+ return -ERANGE;
+
+ return validate_nla_bitfield32(nla, pt->validation_data);
+
case NLA_NUL_STRING:
if (pt->len)
minlen = min_t(int, attrlen, pt->len + 1);
@@ -272,6 +302,30 @@ size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize)
EXPORT_SYMBOL(nla_strlcpy);
/**
+ * nla_strdup - Copy string attribute payload into a newly allocated buffer
+ * @nla: attribute to copy the string from
+ * @flags: the type of memory to allocate (see kmalloc).
+ *
+ * Returns a pointer to the allocated buffer or NULL on error.
+ */
+char *nla_strdup(const struct nlattr *nla, gfp_t flags)
+{
+ size_t srclen = nla_len(nla);
+ char *src = nla_data(nla), *dst;
+
+ if (srclen > 0 && src[srclen - 1] == '\0')
+ srclen--;
+
+ dst = kmalloc(srclen + 1, flags);
+ if (dst != NULL) {
+ memcpy(dst, src, srclen);
+ dst[srclen] = '\0';
+ }
+ return dst;
+}
+EXPORT_SYMBOL(nla_strdup);
+
+/**
* nla_memcpy - Copy a netlink attribute into another memory area
* @dest: where to copy to memcpy
* @src: netlink attribute to copy from
diff --git a/lib/oid_registry.c b/lib/oid_registry.c
index 318f382..41b9e50 100644
--- a/lib/oid_registry.c
+++ b/lib/oid_registry.c
@@ -142,9 +142,9 @@ int sprint_oid(const void *data, size_t datasize, char *buffer, size_t bufsize)
}
ret += count = snprintf(buffer, bufsize, ".%lu", num);
buffer += count;
- bufsize -= count;
- if (bufsize == 0)
+ if (bufsize <= count)
return -ENOBUFS;
+ bufsize -= count;
}
return ret;
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 898e879..8b1feca 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -463,7 +463,7 @@ radix_tree_node_free(struct radix_tree_node *node)
* To make use of this facility, the radix tree must be initialised without
* __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE().
*/
-static int __radix_tree_preload(gfp_t gfp_mask, unsigned nr)
+static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr)
{
struct radix_tree_preload *rtp;
struct radix_tree_node *node;
@@ -2022,6 +2022,7 @@ void radix_tree_iter_delete(struct radix_tree_root *root,
if (__radix_tree_delete(root, iter->node, slot))
iter->index = iter->next_index;
}
+EXPORT_SYMBOL(radix_tree_iter_delete);
/**
* radix_tree_delete_item - delete an item from a radix tree
@@ -2103,7 +2104,8 @@ EXPORT_SYMBOL(radix_tree_tagged);
*/
void idr_preload(gfp_t gfp_mask)
{
- __radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE);
+ if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE))
+ preempt_disable();
}
EXPORT_SYMBOL(idr_preload);
@@ -2117,13 +2119,13 @@ EXPORT_SYMBOL(idr_preload);
*/
int ida_pre_get(struct ida *ida, gfp_t gfp)
{
- __radix_tree_preload(gfp, IDA_PRELOAD_SIZE);
/*
* The IDA API has no preload_end() equivalent. Instead,
* ida_get_new() can return -EAGAIN, prompting the caller
* to return to the ida_pre_get() step.
*/
- preempt_enable();
+ if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE))
+ preempt_enable();
if (!this_cpu_read(ida_bitmap)) {
struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp);
@@ -2137,13 +2139,13 @@ int ida_pre_get(struct ida *ida, gfp_t gfp)
}
EXPORT_SYMBOL(ida_pre_get);
-void __rcu **idr_get_free(struct radix_tree_root *root,
- struct radix_tree_iter *iter, gfp_t gfp, int end)
+void __rcu **idr_get_free_cmn(struct radix_tree_root *root,
+ struct radix_tree_iter *iter, gfp_t gfp,
+ unsigned long max)
{
struct radix_tree_node *node = NULL, *child;
void __rcu **slot = (void __rcu **)&root->rnode;
unsigned long maxindex, start = iter->next_index;
- unsigned long max = end > 0 ? end - 1 : INT_MAX;
unsigned int shift, offset = 0;
grow:
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 3057011..a93adf6 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -5,7 +5,7 @@ raid6_pq-y += algos.o recov.o tables.o int1.o int2.o int4.o \
raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
-raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
+raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
raid6_pq-$(CONFIG_TILEGX) += tilegx8.o
raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
@@ -26,7 +26,9 @@ NEON_FLAGS := -ffreestanding
ifeq ($(ARCH),arm)
NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
endif
+CFLAGS_recov_neon_inner.o += $(NEON_FLAGS)
ifeq ($(ARCH),arm64)
+CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 7857049..4769947 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -113,6 +113,9 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
#ifdef CONFIG_S390
&raid6_recov_s390xc,
#endif
+#if defined(CONFIG_KERNEL_MODE_NEON)
+ &raid6_recov_neon,
+#endif
&raid6_recov_intx1,
NULL
};
diff --git a/lib/raid6/avx512.c b/lib/raid6/avx512.c
index f524a79..46df797 100644
--- a/lib/raid6/avx512.c
+++ b/lib/raid6/avx512.c
@@ -29,7 +29,7 @@
static const struct raid6_avx512_constants {
u64 x1d[8];
-} raid6_avx512_constants __aligned(512) = {
+} raid6_avx512_constants __aligned(512/8) = {
{ 0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,
0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,
0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,
diff --git a/lib/raid6/neon.uc b/lib/raid6/neon.uc
index 4fa51b7..d5242f5 100644
--- a/lib/raid6/neon.uc
+++ b/lib/raid6/neon.uc
@@ -46,8 +46,12 @@ static inline unative_t SHLBYTE(unative_t v)
*/
static inline unative_t MASK(unative_t v)
{
- const uint8x16_t temp = NBYTES(0);
- return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp);
+ return (unative_t)vshrq_n_s8((int8x16_t)v, 7);
+}
+
+static inline unative_t PMUL(unative_t v, unative_t u)
+{
+ return (unative_t)vmulq_p8((poly8x16_t)v, (poly8x16_t)u);
}
void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
@@ -110,7 +114,30 @@ void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
wq$$ = veorq_u8(w1$$, wd$$);
}
/* P/Q left side optimization */
- for ( z = start-1 ; z >= 0 ; z-- ) {
+ for ( z = start-1 ; z >= 3 ; z -= 4 ) {
+ w2$$ = vshrq_n_u8(wq$$, 4);
+ w1$$ = vshlq_n_u8(wq$$, 4);
+
+ w2$$ = PMUL(w2$$, x1d);
+ wq$$ = veorq_u8(w1$$, w2$$);
+ }
+
+ switch (z) {
+ case 2:
+ w2$$ = vshrq_n_u8(wq$$, 5);
+ w1$$ = vshlq_n_u8(wq$$, 3);
+
+ w2$$ = PMUL(w2$$, x1d);
+ wq$$ = veorq_u8(w1$$, w2$$);
+ break;
+ case 1:
+ w2$$ = vshrq_n_u8(wq$$, 6);
+ w1$$ = vshlq_n_u8(wq$$, 2);
+
+ w2$$ = PMUL(w2$$, x1d);
+ wq$$ = veorq_u8(w1$$, w2$$);
+ break;
+ case 0:
w2$$ = MASK(wq$$);
w1$$ = SHLBYTE(wq$$);
diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c
new file mode 100644
index 0000000..eeb5c40
--- /dev/null
+++ b/lib/raid6/recov_neon.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2012 Intel Corporation
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * 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; version 2
+ * of the License.
+ */
+
+#include <linux/raid/pq.h>
+
+#ifdef __KERNEL__
+#include <asm/neon.h>
+#else
+#define kernel_neon_begin()
+#define kernel_neon_end()
+#define cpu_has_neon() (1)
+#endif
+
+static int raid6_has_neon(void)
+{
+ return cpu_has_neon();
+}
+
+void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
+ uint8_t *dq, const uint8_t *pbmul,
+ const uint8_t *qmul);
+
+void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
+ const uint8_t *qmul);
+
+static void raid6_2data_recov_neon(int disks, size_t bytes, int faila,
+ int failb, void **ptrs)
+{
+ u8 *p, *q, *dp, *dq;
+ const u8 *pbmul; /* P multiplier table for B data */
+ const u8 *qmul; /* Q multiplier table (for both) */
+
+ p = (u8 *)ptrs[disks - 2];
+ q = (u8 *)ptrs[disks - 1];
+
+ /*
+ * Compute syndrome with zero for the missing data pages
+ * Use the dead data pages as temporary storage for
+ * delta p and delta q
+ */
+ dp = (u8 *)ptrs[faila];
+ ptrs[faila] = (void *)raid6_empty_zero_page;
+ ptrs[disks - 2] = dp;
+ dq = (u8 *)ptrs[failb];
+ ptrs[failb] = (void *)raid6_empty_zero_page;
+ ptrs[disks - 1] = dq;
+
+ raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+ /* Restore pointer table */
+ ptrs[faila] = dp;
+ ptrs[failb] = dq;
+ ptrs[disks - 2] = p;
+ ptrs[disks - 1] = q;
+
+ /* Now, pick the proper data tables */
+ pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
+ qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
+ raid6_gfexp[failb]]];
+
+ kernel_neon_begin();
+ __raid6_2data_recov_neon(bytes, p, q, dp, dq, pbmul, qmul);
+ kernel_neon_end();
+}
+
+static void raid6_datap_recov_neon(int disks, size_t bytes, int faila,
+ void **ptrs)
+{
+ u8 *p, *q, *dq;
+ const u8 *qmul; /* Q multiplier table */
+
+ p = (u8 *)ptrs[disks - 2];
+ q = (u8 *)ptrs[disks - 1];
+
+ /*
+ * Compute syndrome with zero for the missing data page
+ * Use the dead data page as temporary storage for delta q
+ */
+ dq = (u8 *)ptrs[faila];
+ ptrs[faila] = (void *)raid6_empty_zero_page;
+ ptrs[disks - 1] = dq;
+
+ raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+ /* Restore pointer table */
+ ptrs[faila] = dq;
+ ptrs[disks - 1] = q;
+
+ /* Now, pick the proper data tables */
+ qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+ kernel_neon_begin();
+ __raid6_datap_recov_neon(bytes, p, q, dq, qmul);
+ kernel_neon_end();
+}
+
+const struct raid6_recov_calls raid6_recov_neon = {
+ .data2 = raid6_2data_recov_neon,
+ .datap = raid6_datap_recov_neon,
+ .valid = raid6_has_neon,
+ .name = "neon",
+ .priority = 10,
+};
diff --git a/lib/raid6/recov_neon_inner.c b/lib/raid6/recov_neon_inner.c
new file mode 100644
index 0000000..8cd20c9
--- /dev/null
+++ b/lib/raid6/recov_neon_inner.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright (C) 2012 Intel Corporation
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * 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; version 2
+ * of the License.
+ */
+
+#include <arm_neon.h>
+
+static const uint8x16_t x0f = {
+ 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+ 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+};
+
+#ifdef CONFIG_ARM
+/*
+ * AArch32 does not provide this intrinsic natively because it does not
+ * implement the underlying instruction. AArch32 only provides a 64-bit
+ * wide vtbl.8 instruction, so use that instead.
+ */
+static uint8x16_t vqtbl1q_u8(uint8x16_t a, uint8x16_t b)
+{
+ union {
+ uint8x16_t val;
+ uint8x8x2_t pair;
+ } __a = { a };
+
+ return vcombine_u8(vtbl2_u8(__a.pair, vget_low_u8(b)),
+ vtbl2_u8(__a.pair, vget_high_u8(b)));
+}
+#endif
+
+void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
+ uint8_t *dq, const uint8_t *pbmul,
+ const uint8_t *qmul)
+{
+ uint8x16_t pm0 = vld1q_u8(pbmul);
+ uint8x16_t pm1 = vld1q_u8(pbmul + 16);
+ uint8x16_t qm0 = vld1q_u8(qmul);
+ uint8x16_t qm1 = vld1q_u8(qmul + 16);
+
+ /*
+ * while ( bytes-- ) {
+ * uint8_t px, qx, db;
+ *
+ * px = *p ^ *dp;
+ * qx = qmul[*q ^ *dq];
+ * *dq++ = db = pbmul[px] ^ qx;
+ * *dp++ = db ^ px;
+ * p++; q++;
+ * }
+ */
+
+ while (bytes) {
+ uint8x16_t vx, vy, px, qx, db;
+
+ px = veorq_u8(vld1q_u8(p), vld1q_u8(dp));
+ vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
+
+ vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
+ vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
+ vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
+ qx = veorq_u8(vx, vy);
+
+ vy = (uint8x16_t)vshrq_n_s16((int16x8_t)px, 4);
+ vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
+ vy = vqtbl1q_u8(pm1, vandq_u8(vy, x0f));
+ vx = veorq_u8(vx, vy);
+ db = veorq_u8(vx, qx);
+
+ vst1q_u8(dq, db);
+ vst1q_u8(dp, veorq_u8(db, px));
+
+ bytes -= 16;
+ p += 16;
+ q += 16;
+ dp += 16;
+ dq += 16;
+ }
+}
+
+void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
+ const uint8_t *qmul)
+{
+ uint8x16_t qm0 = vld1q_u8(qmul);
+ uint8x16_t qm1 = vld1q_u8(qmul + 16);
+
+ /*
+ * while (bytes--) {
+ * *p++ ^= *dq = qmul[*q ^ *dq];
+ * q++; dq++;
+ * }
+ */
+
+ while (bytes) {
+ uint8x16_t vx, vy;
+
+ vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
+
+ vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
+ vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
+ vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
+ vx = veorq_u8(vx, vy);
+ vy = veorq_u8(vx, vld1q_u8(p));
+
+ vst1q_u8(dq, vx);
+ vst1q_u8(p, vy);
+
+ bytes -= 16;
+ p += 16;
+ q += 16;
+ dq += 16;
+ }
+}
diff --git a/lib/rbtree.c b/lib/rbtree.c
index 4ba2828..ba4a9d1 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -95,22 +95,35 @@ __rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
static __always_inline void
__rb_insert(struct rb_node *node, struct rb_root *root,
+ bool newleft, struct rb_node **leftmost,
void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
{
struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+ if (newleft)
+ *leftmost = node;
+
while (true) {
/*
- * Loop invariant: node is red
- *
- * If there is a black parent, we are done.
- * Otherwise, take some corrective action as we don't
- * want a red root or two consecutive red nodes.
+ * Loop invariant: node is red.
*/
- if (!parent) {
+ if (unlikely(!parent)) {
+ /*
+ * The inserted node is root. Either this is the
+ * first node, or we recursed at Case 1 below and
+ * are no longer violating 4).
+ */
rb_set_parent_color(node, NULL, RB_BLACK);
break;
- } else if (rb_is_black(parent))
+ }
+
+ /*
+ * If there is a black parent, we are done.
+ * Otherwise, take some corrective action as,
+ * per 4), we don't want a red root or two
+ * consecutive red nodes.
+ */
+ if(rb_is_black(parent))
break;
gparent = rb_red_parent(parent);
@@ -119,7 +132,7 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
if (parent != tmp) { /* parent == gparent->rb_left */
if (tmp && rb_is_red(tmp)) {
/*
- * Case 1 - color flips
+ * Case 1 - node's uncle is red (color flips).
*
* G g
* / \ / \
@@ -142,7 +155,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
tmp = parent->rb_right;
if (node == tmp) {
/*
- * Case 2 - left rotate at parent
+ * Case 2 - node's uncle is black and node is
+ * the parent's right child (left rotate at parent).
*
* G G
* / \ / \
@@ -166,7 +180,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
}
/*
- * Case 3 - right rotate at gparent
+ * Case 3 - node's uncle is black and node is
+ * the parent's left child (right rotate at gparent).
*
* G P
* / \ / \
@@ -434,19 +449,38 @@ static const struct rb_augment_callbacks dummy_callbacks = {
void rb_insert_color(struct rb_node *node, struct rb_root *root)
{
- __rb_insert(node, root, dummy_rotate);
+ __rb_insert(node, root, false, NULL, dummy_rotate);
}
EXPORT_SYMBOL(rb_insert_color);
void rb_erase(struct rb_node *node, struct rb_root *root)
{
struct rb_node *rebalance;
- rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+ rebalance = __rb_erase_augmented(node, root,
+ NULL, &dummy_callbacks);
if (rebalance)
____rb_erase_color(rebalance, root, dummy_rotate);
}
EXPORT_SYMBOL(rb_erase);
+void rb_insert_color_cached(struct rb_node *node,
+ struct rb_root_cached *root, bool leftmost)
+{
+ __rb_insert(node, &root->rb_root, leftmost,
+ &root->rb_leftmost, dummy_rotate);
+}
+EXPORT_SYMBOL(rb_insert_color_cached);
+
+void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root)
+{
+ struct rb_node *rebalance;
+ rebalance = __rb_erase_augmented(node, &root->rb_root,
+ &root->rb_leftmost, &dummy_callbacks);
+ if (rebalance)
+ ____rb_erase_color(rebalance, &root->rb_root, dummy_rotate);
+}
+EXPORT_SYMBOL(rb_erase_cached);
+
/*
* Augmented rbtree manipulation functions.
*
@@ -455,9 +489,10 @@ EXPORT_SYMBOL(rb_erase);
*/
void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ bool newleft, struct rb_node **leftmost,
void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
{
- __rb_insert(node, root, augment_rotate);
+ __rb_insert(node, root, newleft, leftmost, augment_rotate);
}
EXPORT_SYMBOL(__rb_insert_augmented);
@@ -502,7 +537,7 @@ struct rb_node *rb_next(const struct rb_node *node)
* as we can.
*/
if (node->rb_right) {
- node = node->rb_right;
+ node = node->rb_right;
while (node->rb_left)
node=node->rb_left;
return (struct rb_node *)node;
@@ -534,7 +569,7 @@ struct rb_node *rb_prev(const struct rb_node *node)
* as we can.
*/
if (node->rb_left) {
- node = node->rb_left;
+ node = node->rb_left;
while (node->rb_right)
node=node->rb_right;
return (struct rb_node *)node;
diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c
index 8b3c9dc..191a238 100644
--- a/lib/rbtree_test.c
+++ b/lib/rbtree_test.c
@@ -1,11 +1,18 @@
#include <linux/module.h>
+#include <linux/moduleparam.h>
#include <linux/rbtree_augmented.h>
#include <linux/random.h>
+#include <linux/slab.h>
#include <asm/timex.h>
-#define NODES 100
-#define PERF_LOOPS 100000
-#define CHECK_LOOPS 100
+#define __param(type, name, init, msg) \
+ static type name = init; \
+ module_param(name, type, 0444); \
+ MODULE_PARM_DESC(name, msg);
+
+__param(int, nnodes, 100, "Number of nodes in the rb-tree");
+__param(int, perf_loops, 100000, "Number of iterations modifying the rb-tree");
+__param(int, check_loops, 100, "Number of iterations modifying and verifying the rb-tree");
struct test_node {
u32 key;
@@ -16,14 +23,14 @@ struct test_node {
u32 augmented;
};
-static struct rb_root root = RB_ROOT;
-static struct test_node nodes[NODES];
+static struct rb_root_cached root = RB_ROOT_CACHED;
+static struct test_node *nodes = NULL;
static struct rnd_state rnd;
-static void insert(struct test_node *node, struct rb_root *root)
+static void insert(struct test_node *node, struct rb_root_cached *root)
{
- struct rb_node **new = &root->rb_node, *parent = NULL;
+ struct rb_node **new = &root->rb_root.rb_node, *parent = NULL;
u32 key = node->key;
while (*new) {
@@ -35,14 +42,40 @@ static void insert(struct test_node *node, struct rb_root *root)
}
rb_link_node(&node->rb, parent, new);
- rb_insert_color(&node->rb, root);
+ rb_insert_color(&node->rb, &root->rb_root);
+}
+
+static void insert_cached(struct test_node *node, struct rb_root_cached *root)
+{
+ struct rb_node **new = &root->rb_root.rb_node, *parent = NULL;
+ u32 key = node->key;
+ bool leftmost = true;
+
+ while (*new) {
+ parent = *new;
+ if (key < rb_entry(parent, struct test_node, rb)->key)
+ new = &parent->rb_left;
+ else {
+ new = &parent->rb_right;
+ leftmost = false;
+ }
+ }
+
+ rb_link_node(&node->rb, parent, new);
+ rb_insert_color_cached(&node->rb, root, leftmost);
}
-static inline void erase(struct test_node *node, struct rb_root *root)
+static inline void erase(struct test_node *node, struct rb_root_cached *root)
{
- rb_erase(&node->rb, root);
+ rb_erase(&node->rb, &root->rb_root);
}
+static inline void erase_cached(struct test_node *node, struct rb_root_cached *root)
+{
+ rb_erase_cached(&node->rb, root);
+}
+
+
static inline u32 augment_recompute(struct test_node *node)
{
u32 max = node->val, child_augmented;
@@ -64,9 +97,10 @@ static inline u32 augment_recompute(struct test_node *node)
RB_DECLARE_CALLBACKS(static, augment_callbacks, struct test_node, rb,
u32, augmented, augment_recompute)
-static void insert_augmented(struct test_node *node, struct rb_root *root)
+static void insert_augmented(struct test_node *node,
+ struct rb_root_cached *root)
{
- struct rb_node **new = &root->rb_node, *rb_parent = NULL;
+ struct rb_node **new = &root->rb_root.rb_node, *rb_parent = NULL;
u32 key = node->key;
u32 val = node->val;
struct test_node *parent;
@@ -84,18 +118,53 @@ static void insert_augmented(struct test_node *node, struct rb_root *root)
node->augmented = val;
rb_link_node(&node->rb, rb_parent, new);
- rb_insert_augmented(&node->rb, root, &augment_callbacks);
+ rb_insert_augmented(&node->rb, &root->rb_root, &augment_callbacks);
+}
+
+static void insert_augmented_cached(struct test_node *node,
+ struct rb_root_cached *root)
+{
+ struct rb_node **new = &root->rb_root.rb_node, *rb_parent = NULL;
+ u32 key = node->key;
+ u32 val = node->val;
+ struct test_node *parent;
+ bool leftmost = true;
+
+ while (*new) {
+ rb_parent = *new;
+ parent = rb_entry(rb_parent, struct test_node, rb);
+ if (parent->augmented < val)
+ parent->augmented = val;
+ if (key < parent->key)
+ new = &parent->rb.rb_left;
+ else {
+ new = &parent->rb.rb_right;
+ leftmost = false;
+ }
+ }
+
+ node->augmented = val;
+ rb_link_node(&node->rb, rb_parent, new);
+ rb_insert_augmented_cached(&node->rb, root,
+ leftmost, &augment_callbacks);
+}
+
+
+static void erase_augmented(struct test_node *node, struct rb_root_cached *root)
+{
+ rb_erase_augmented(&node->rb, &root->rb_root, &augment_callbacks);
}
-static void erase_augmented(struct test_node *node, struct rb_root *root)
+static void erase_augmented_cached(struct test_node *node,
+ struct rb_root_cached *root)
{
- rb_erase_augmented(&node->rb, root, &augment_callbacks);
+ rb_erase_augmented_cached(&node->rb, root, &augment_callbacks);
}
static void init(void)
{
int i;
- for (i = 0; i < NODES; i++) {
+ for (i = 0; i < nnodes; i++) {
nodes[i].key = prandom_u32_state(&rnd);
nodes[i].val = prandom_u32_state(&rnd);
}
@@ -118,7 +187,7 @@ static void check_postorder_foreach(int nr_nodes)
{
struct test_node *cur, *n;
int count = 0;
- rbtree_postorder_for_each_entry_safe(cur, n, &root, rb)
+ rbtree_postorder_for_each_entry_safe(cur, n, &root.rb_root, rb)
count++;
WARN_ON_ONCE(count != nr_nodes);
@@ -128,7 +197,7 @@ static void check_postorder(int nr_nodes)
{
struct rb_node *rb;
int count = 0;
- for (rb = rb_first_postorder(&root); rb; rb = rb_next_postorder(rb))
+ for (rb = rb_first_postorder(&root.rb_root); rb; rb = rb_next_postorder(rb))
count++;
WARN_ON_ONCE(count != nr_nodes);
@@ -140,7 +209,7 @@ static void check(int nr_nodes)
int count = 0, blacks = 0;
u32 prev_key = 0;
- for (rb = rb_first(&root); rb; rb = rb_next(rb)) {
+ for (rb = rb_first(&root.rb_root); rb; rb = rb_next(rb)) {
struct test_node *node = rb_entry(rb, struct test_node, rb);
WARN_ON_ONCE(node->key < prev_key);
WARN_ON_ONCE(is_red(rb) &&
@@ -155,7 +224,7 @@ static void check(int nr_nodes)
}
WARN_ON_ONCE(count != nr_nodes);
- WARN_ON_ONCE(count < (1 << black_path_count(rb_last(&root))) - 1);
+ WARN_ON_ONCE(count < (1 << black_path_count(rb_last(&root.rb_root))) - 1);
check_postorder(nr_nodes);
check_postorder_foreach(nr_nodes);
@@ -166,7 +235,7 @@ static void check_augmented(int nr_nodes)
struct rb_node *rb;
check(nr_nodes);
- for (rb = rb_first(&root); rb; rb = rb_next(rb)) {
+ for (rb = rb_first(&root.rb_root); rb; rb = rb_next(rb)) {
struct test_node *node = rb_entry(rb, struct test_node, rb);
WARN_ON_ONCE(node->augmented != augment_recompute(node));
}
@@ -176,6 +245,11 @@ static int __init rbtree_test_init(void)
{
int i, j;
cycles_t time1, time2, time;
+ struct rb_node *node;
+
+ nodes = kmalloc(nnodes * sizeof(*nodes), GFP_KERNEL);
+ if (!nodes)
+ return -ENOMEM;
printk(KERN_ALERT "rbtree testing");
@@ -184,27 +258,88 @@ static int __init rbtree_test_init(void)
time1 = get_cycles();
- for (i = 0; i < PERF_LOOPS; i++) {
- for (j = 0; j < NODES; j++)
+ for (i = 0; i < perf_loops; i++) {
+ for (j = 0; j < nnodes; j++)
insert(nodes + j, &root);
- for (j = 0; j < NODES; j++)
+ for (j = 0; j < nnodes; j++)
erase(nodes + j, &root);
}
time2 = get_cycles();
time = time2 - time1;
- time = div_u64(time, PERF_LOOPS);
- printk(" -> %llu cycles\n", (unsigned long long)time);
+ time = div_u64(time, perf_loops);
+ printk(" -> test 1 (latency of nnodes insert+delete): %llu cycles\n",
+ (unsigned long long)time);
+
+ time1 = get_cycles();
+
+ for (i = 0; i < perf_loops; i++) {
+ for (j = 0; j < nnodes; j++)
+ insert_cached(nodes + j, &root);
+ for (j = 0; j < nnodes; j++)
+ erase_cached(nodes + j, &root);
+ }
+
+ time2 = get_cycles();
+ time = time2 - time1;
+
+ time = div_u64(time, perf_loops);
+ printk(" -> test 2 (latency of nnodes cached insert+delete): %llu cycles\n",
+ (unsigned long long)time);
+
+ for (i = 0; i < nnodes; i++)
+ insert(nodes + i, &root);
+
+ time1 = get_cycles();
+
+ for (i = 0; i < perf_loops; i++) {
+ for (node = rb_first(&root.rb_root); node; node = rb_next(node))
+ ;
+ }
+
+ time2 = get_cycles();
+ time = time2 - time1;
+
+ time = div_u64(time, perf_loops);
+ printk(" -> test 3 (latency of inorder traversal): %llu cycles\n",
+ (unsigned long long)time);
+
+ time1 = get_cycles();
+
+ for (i = 0; i < perf_loops; i++)
+ node = rb_first(&root.rb_root);
+
+ time2 = get_cycles();
+ time = time2 - time1;
+
+ time = div_u64(time, perf_loops);
+ printk(" -> test 4 (latency to fetch first node)\n");
+ printk(" non-cached: %llu cycles\n", (unsigned long long)time);
+
+ time1 = get_cycles();
+
+ for (i = 0; i < perf_loops; i++)
+ node = rb_first_cached(&root);
+
+ time2 = get_cycles();
+ time = time2 - time1;
+
+ time = div_u64(time, perf_loops);
+ printk(" cached: %llu cycles\n", (unsigned long long)time);
- for (i = 0; i < CHECK_LOOPS; i++) {
+ for (i = 0; i < nnodes; i++)
+ erase(nodes + i, &root);
+
+ /* run checks */
+ for (i = 0; i < check_loops; i++) {
init();
- for (j = 0; j < NODES; j++) {
+ for (j = 0; j < nnodes; j++) {
check(j);
insert(nodes + j, &root);
}
- for (j = 0; j < NODES; j++) {
- check(NODES - j);
+ for (j = 0; j < nnodes; j++) {
+ check(nnodes - j);
erase(nodes + j, &root);
}
check(0);
@@ -216,32 +351,49 @@ static int __init rbtree_test_init(void)
time1 = get_cycles();
- for (i = 0; i < PERF_LOOPS; i++) {
- for (j = 0; j < NODES; j++)
+ for (i = 0; i < perf_loops; i++) {
+ for (j = 0; j < nnodes; j++)
insert_augmented(nodes + j, &root);
- for (j = 0; j < NODES; j++)
+ for (j = 0; j < nnodes; j++)
erase_augmented(nodes + j, &root);
}
time2 = get_cycles();
time = time2 - time1;
- time = div_u64(time, PERF_LOOPS);
- printk(" -> %llu cycles\n", (unsigned long long)time);
+ time = div_u64(time, perf_loops);
+ printk(" -> test 1 (latency of nnodes insert+delete): %llu cycles\n", (unsigned long long)time);
+
+ time1 = get_cycles();
+
+ for (i = 0; i < perf_loops; i++) {
+ for (j = 0; j < nnodes; j++)
+ insert_augmented_cached(nodes + j, &root);
+ for (j = 0; j < nnodes; j++)
+ erase_augmented_cached(nodes + j, &root);
+ }
+
+ time2 = get_cycles();
+ time = time2 - time1;
+
+ time = div_u64(time, perf_loops);
+ printk(" -> test 2 (latency of nnodes cached insert+delete): %llu cycles\n", (unsigned long long)time);
- for (i = 0; i < CHECK_LOOPS; i++) {
+ for (i = 0; i < check_loops; i++) {
init();
- for (j = 0; j < NODES; j++) {
+ for (j = 0; j < nnodes; j++) {
check_augmented(j);
insert_augmented(nodes + j, &root);
}
- for (j = 0; j < NODES; j++) {
- check_augmented(NODES - j);
+ for (j = 0; j < nnodes; j++) {
+ check_augmented(nnodes - j);
erase_augmented(nodes + j, &root);
}
check_augmented(0);
}
+ kfree(nodes);
+
return -EAGAIN; /* Fail will directly unload the module */
}
diff --git a/lib/string.c b/lib/string.c
index ebbb99c..9921dc2 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -723,6 +723,72 @@ void memzero_explicit(void *s, size_t count)
}
EXPORT_SYMBOL(memzero_explicit);
+#ifndef __HAVE_ARCH_MEMSET16
+/**
+ * memset16() - Fill a memory area with a uint16_t
+ * @s: Pointer to the start of the area.
+ * @v: The value to fill the area with
+ * @count: The number of values to store
+ *
+ * Differs from memset() in that it fills with a uint16_t instead
+ * of a byte. Remember that @count is the number of uint16_ts to
+ * store, not the number of bytes.
+ */
+void *memset16(uint16_t *s, uint16_t v, size_t count)
+{
+ uint16_t *xs = s;
+
+ while (count--)
+ *xs++ = v;
+ return s;
+}
+EXPORT_SYMBOL(memset16);
+#endif
+
+#ifndef __HAVE_ARCH_MEMSET32
+/**
+ * memset32() - Fill a memory area with a uint32_t
+ * @s: Pointer to the start of the area.
+ * @v: The value to fill the area with
+ * @count: The number of values to store
+ *
+ * Differs from memset() in that it fills with a uint32_t instead
+ * of a byte. Remember that @count is the number of uint32_ts to
+ * store, not the number of bytes.
+ */
+void *memset32(uint32_t *s, uint32_t v, size_t count)
+{
+ uint32_t *xs = s;
+
+ while (count--)
+ *xs++ = v;
+ return s;
+}
+EXPORT_SYMBOL(memset32);
+#endif
+
+#ifndef __HAVE_ARCH_MEMSET64
+/**
+ * memset64() - Fill a memory area with a uint64_t
+ * @s: Pointer to the start of the area.
+ * @v: The value to fill the area with
+ * @count: The number of values to store
+ *
+ * Differs from memset() in that it fills with a uint64_t instead
+ * of a byte. Remember that @count is the number of uint64_ts to
+ * store, not the number of bytes.
+ */
+void *memset64(uint64_t *s, uint64_t v, size_t count)
+{
+ uint64_t *xs = s;
+
+ while (count--)
+ *xs++ = v;
+ return s;
+}
+EXPORT_SYMBOL(memset64);
+#endif
+
#ifndef __HAVE_ARCH_MEMCPY
/**
* memcpy - Copy one area of memory to another
@@ -985,3 +1051,144 @@ void fortify_panic(const char *name)
BUG();
}
EXPORT_SYMBOL(fortify_panic);
+
+#ifdef CONFIG_STRING_SELFTEST
+#include <linux/slab.h>
+#include <linux/module.h>
+
+static __init int memset16_selftest(void)
+{
+ unsigned i, j, k;
+ u16 v, *p;
+
+ p = kmalloc(256 * 2 * 2, GFP_KERNEL);
+ if (!p)
+ return -1;
+
+ for (i = 0; i < 256; i++) {
+ for (j = 0; j < 256; j++) {
+ memset(p, 0xa1, 256 * 2 * sizeof(v));
+ memset16(p + i, 0xb1b2, j);
+ for (k = 0; k < 512; k++) {
+ v = p[k];
+ if (k < i) {
+ if (v != 0xa1a1)
+ goto fail;
+ } else if (k < i + j) {
+ if (v != 0xb1b2)
+ goto fail;
+ } else {
+ if (v != 0xa1a1)
+ goto fail;
+ }
+ }
+ }
+ }
+
+fail:
+ kfree(p);
+ if (i < 256)
+ return (i << 24) | (j << 16) | k;
+ return 0;
+}
+
+static __init int memset32_selftest(void)
+{
+ unsigned i, j, k;
+ u32 v, *p;
+
+ p = kmalloc(256 * 2 * 4, GFP_KERNEL);
+ if (!p)
+ return -1;
+
+ for (i = 0; i < 256; i++) {
+ for (j = 0; j < 256; j++) {
+ memset(p, 0xa1, 256 * 2 * sizeof(v));
+ memset32(p + i, 0xb1b2b3b4, j);
+ for (k = 0; k < 512; k++) {
+ v = p[k];
+ if (k < i) {
+ if (v != 0xa1a1a1a1)
+ goto fail;
+ } else if (k < i + j) {
+ if (v != 0xb1b2b3b4)
+ goto fail;
+ } else {
+ if (v != 0xa1a1a1a1)
+ goto fail;
+ }
+ }
+ }
+ }
+
+fail:
+ kfree(p);
+ if (i < 256)
+ return (i << 24) | (j << 16) | k;
+ return 0;
+}
+
+static __init int memset64_selftest(void)
+{
+ unsigned i, j, k;
+ u64 v, *p;
+
+ p = kmalloc(256 * 2 * 8, GFP_KERNEL);
+ if (!p)
+ return -1;
+
+ for (i = 0; i < 256; i++) {
+ for (j = 0; j < 256; j++) {
+ memset(p, 0xa1, 256 * 2 * sizeof(v));
+ memset64(p + i, 0xb1b2b3b4b5b6b7b8ULL, j);
+ for (k = 0; k < 512; k++) {
+ v = p[k];
+ if (k < i) {
+ if (v != 0xa1a1a1a1a1a1a1a1ULL)
+ goto fail;
+ } else if (k < i + j) {
+ if (v != 0xb1b2b3b4b5b6b7b8ULL)
+ goto fail;
+ } else {
+ if (v != 0xa1a1a1a1a1a1a1a1ULL)
+ goto fail;
+ }
+ }
+ }
+ }
+
+fail:
+ kfree(p);
+ if (i < 256)
+ return (i << 24) | (j << 16) | k;
+ return 0;
+}
+
+static __init int string_selftest_init(void)
+{
+ int test, subtest;
+
+ test = 1;
+ subtest = memset16_selftest();
+ if (subtest)
+ goto fail;
+
+ test = 2;
+ subtest = memset32_selftest();
+ if (subtest)
+ goto fail;
+
+ test = 3;
+ subtest = memset64_selftest();
+ if (subtest)
+ goto fail;
+
+ pr_info("String selftests succeeded\n");
+ return 0;
+fail:
+ pr_crit("String selftest failure %d.%08x\n", test, subtest);
+ return 0;
+}
+
+module_init(string_selftest_init);
+#endif /* CONFIG_STRING_SELFTEST */
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index ecaac2c..29c490e 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -576,7 +576,7 @@ char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp)
char *buffer, *quoted;
int i, res;
- buffer = kmalloc(PAGE_SIZE, GFP_TEMPORARY);
+ buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!buffer)
return NULL;
@@ -612,7 +612,7 @@ char *kstrdup_quotable_file(struct file *file, gfp_t gfp)
return kstrdup("<unknown>", gfp);
/* We add 11 spaces for ' (deleted)' to be appended */
- temp = kmalloc(PATH_MAX + 11, GFP_TEMPORARY);
+ temp = kmalloc(PATH_MAX + 11, GFP_KERNEL);
if (!temp)
return kstrdup("<no_memory>", gfp);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index a8d74a7..8c6c83e 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -30,6 +30,7 @@
#include <linux/highmem.h>
#include <linux/gfp.h>
#include <linux/scatterlist.h>
+#include <linux/mem_encrypt.h>
#include <asm/io.h>
#include <asm/dma.h>
@@ -155,6 +156,15 @@ unsigned long swiotlb_size_or_default(void)
return size ? size : (IO_TLB_DEFAULT_SIZE);
}
+void __weak swiotlb_set_mem_attributes(void *vaddr, unsigned long size) { }
+
+/* For swiotlb, clear memory encryption mask from dma addresses */
+static dma_addr_t swiotlb_phys_to_dma(struct device *hwdev,
+ phys_addr_t address)
+{
+ return __sme_clr(phys_to_dma(hwdev, address));
+}
+
/* Note that this doesn't work with highmem page */
static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
volatile void *address)
@@ -183,6 +193,31 @@ void swiotlb_print_info(void)
bytes >> 20, vstart, vend - 1);
}
+/*
+ * Early SWIOTLB allocation may be too early to allow an architecture to
+ * perform the desired operations. This function allows the architecture to
+ * call SWIOTLB when the operations are possible. It needs to be called
+ * before the SWIOTLB memory is used.
+ */
+void __init swiotlb_update_mem_attributes(void)
+{
+ void *vaddr;
+ unsigned long bytes;
+
+ if (no_iotlb_memory || late_alloc)
+ return;
+
+ vaddr = phys_to_virt(io_tlb_start);
+ bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
+ swiotlb_set_mem_attributes(vaddr, bytes);
+ memset(vaddr, 0, bytes);
+
+ vaddr = phys_to_virt(io_tlb_overflow_buffer);
+ bytes = PAGE_ALIGN(io_tlb_overflow);
+ swiotlb_set_mem_attributes(vaddr, bytes);
+ memset(vaddr, 0, bytes);
+}
+
int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
{
void *v_overflow_buffer;
@@ -320,6 +355,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
io_tlb_start = virt_to_phys(tlb);
io_tlb_end = io_tlb_start + bytes;
+ swiotlb_set_mem_attributes(tlb, bytes);
memset(tlb, 0, bytes);
/*
@@ -330,6 +366,8 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
if (!v_overflow_buffer)
goto cleanup2;
+ swiotlb_set_mem_attributes(v_overflow_buffer, io_tlb_overflow);
+ memset(v_overflow_buffer, 0, io_tlb_overflow);
io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
/*
@@ -469,6 +507,9 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
if (no_iotlb_memory)
panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+ if (sme_active())
+ pr_warn_once("SME is active and system is using DMA bounce buffers\n");
+
mask = dma_get_seg_boundary(hwdev);
tbl_dma_addr &= mask;
@@ -581,7 +622,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size,
return SWIOTLB_MAP_ERROR;
}
- start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
+ start_dma_addr = swiotlb_phys_to_dma(hwdev, io_tlb_start);
return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
dir, attrs);
}
@@ -702,7 +743,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
goto err_warn;
ret = phys_to_virt(paddr);
- dev_addr = phys_to_dma(hwdev, paddr);
+ dev_addr = swiotlb_phys_to_dma(hwdev, paddr);
/* Confirm address can be DMA'd by device */
if (dev_addr + size - 1 > dma_mask) {
@@ -812,10 +853,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
map = map_single(dev, phys, size, dir, attrs);
if (map == SWIOTLB_MAP_ERROR) {
swiotlb_full(dev, size, dir, 1);
- return phys_to_dma(dev, io_tlb_overflow_buffer);
+ return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
}
- dev_addr = phys_to_dma(dev, map);
+ dev_addr = swiotlb_phys_to_dma(dev, map);
/* Ensure that the address returned is DMA'ble */
if (dma_capable(dev, dev_addr, size))
@@ -824,7 +865,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
attrs |= DMA_ATTR_SKIP_CPU_SYNC;
swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
- return phys_to_dma(dev, io_tlb_overflow_buffer);
+ return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
}
EXPORT_SYMBOL_GPL(swiotlb_map_page);
@@ -958,7 +999,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
sg_dma_len(sgl) = 0;
return 0;
}
- sg->dma_address = phys_to_dma(hwdev, map);
+ sg->dma_address = swiotlb_phys_to_dma(hwdev, map);
} else
sg->dma_address = dev_addr;
sg_dma_len(sg) = sg->length;
@@ -1026,7 +1067,7 @@ EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
int
swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
{
- return (dma_addr == phys_to_dma(hwdev, io_tlb_overflow_buffer));
+ return (dma_addr == swiotlb_phys_to_dma(hwdev, io_tlb_overflow_buffer));
}
EXPORT_SYMBOL(swiotlb_dma_mapping_error);
@@ -1039,6 +1080,6 @@ EXPORT_SYMBOL(swiotlb_dma_mapping_error);
int
swiotlb_dma_supported(struct device *hwdev, u64 mask)
{
- return phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
+ return swiotlb_phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
}
EXPORT_SYMBOL(swiotlb_dma_supported);
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 2526a29..aa1f266 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -165,6 +165,96 @@ static void __init test_zero_fill_copy(void)
expect_eq_pbl("128-1023", bmap2, 1024);
}
+#define PARSE_TIME 0x1
+
+struct test_bitmap_parselist{
+ const int errno;
+ const char *in;
+ const unsigned long *expected;
+ const int nbits;
+ const int flags;
+};
+
+static const unsigned long exp[] __initconst = {
+ BITMAP_FROM_U64(1),
+ BITMAP_FROM_U64(2),
+ BITMAP_FROM_U64(0x0000ffff),
+ BITMAP_FROM_U64(0xffff0000),
+ BITMAP_FROM_U64(0x55555555),
+ BITMAP_FROM_U64(0xaaaaaaaa),
+ BITMAP_FROM_U64(0x11111111),
+ BITMAP_FROM_U64(0x22222222),
+ BITMAP_FROM_U64(0xffffffff),
+ BITMAP_FROM_U64(0xfffffffe),
+ BITMAP_FROM_U64(0x3333333311111111ULL),
+ BITMAP_FROM_U64(0xffffffff77777777ULL)
+};
+
+static const unsigned long exp2[] __initconst = {
+ BITMAP_FROM_U64(0x3333333311111111ULL),
+ BITMAP_FROM_U64(0xffffffff77777777ULL)
+};
+
+static const struct test_bitmap_parselist parselist_tests[] __initconst = {
+#define step (sizeof(u64) / sizeof(unsigned long))
+
+ {0, "0", &exp[0], 8, 0},
+ {0, "1", &exp[1 * step], 8, 0},
+ {0, "0-15", &exp[2 * step], 32, 0},
+ {0, "16-31", &exp[3 * step], 32, 0},
+ {0, "0-31:1/2", &exp[4 * step], 32, 0},
+ {0, "1-31:1/2", &exp[5 * step], 32, 0},
+ {0, "0-31:1/4", &exp[6 * step], 32, 0},
+ {0, "1-31:1/4", &exp[7 * step], 32, 0},
+ {0, "0-31:4/4", &exp[8 * step], 32, 0},
+ {0, "1-31:4/4", &exp[9 * step], 32, 0},
+ {0, "0-31:1/4,32-63:2/4", &exp[10 * step], 64, 0},
+ {0, "0-31:3/4,32-63:4/4", &exp[11 * step], 64, 0},
+
+ {0, "0-31:1/4,32-63:2/4,64-95:3/4,96-127:4/4", exp2, 128, 0},
+
+ {0, "0-2047:128/256", NULL, 2048, PARSE_TIME},
+
+ {-EINVAL, "-1", NULL, 8, 0},
+ {-EINVAL, "-0", NULL, 8, 0},
+ {-EINVAL, "10-1", NULL, 8, 0},
+ {-EINVAL, "0-31:10/1", NULL, 8, 0},
+};
+
+static void __init test_bitmap_parselist(void)
+{
+ int i;
+ int err;
+ cycles_t cycles;
+ DECLARE_BITMAP(bmap, 2048);
+
+ for (i = 0; i < ARRAY_SIZE(parselist_tests); i++) {
+#define ptest parselist_tests[i]
+
+ cycles = get_cycles();
+ err = bitmap_parselist(ptest.in, bmap, ptest.nbits);
+ cycles = get_cycles() - cycles;
+
+ if (err != ptest.errno) {
+ pr_err("test %d: input is %s, errno is %d, expected %d\n",
+ i, ptest.in, err, ptest.errno);
+ continue;
+ }
+
+ if (!err && ptest.expected
+ && !__bitmap_equal(bmap, ptest.expected, ptest.nbits)) {
+ pr_err("test %d: input is %s, result is 0x%lx, expected 0x%lx\n",
+ i, ptest.in, bmap[0], *ptest.expected);
+ continue;
+ }
+
+ if (ptest.flags & PARSE_TIME)
+ pr_err("test %d: input is '%s' OK, Time: %llu\n",
+ i, ptest.in,
+ (unsigned long long)cycles);
+ }
+}
+
static void __init test_bitmap_u32_array_conversions(void)
{
DECLARE_BITMAP(bmap1, 1024);
@@ -365,6 +455,7 @@ static int __init test_bitmap_init(void)
{
test_zero_fill_copy();
test_bitmap_u32_array_conversions();
+ test_bitmap_parselist();
test_mem_optimisations();
if (failed_tests == 0)
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index d9d5a41..aa8812a 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -952,6 +952,32 @@ static struct bpf_test tests[] = {
{ { 2, 0 }, { 3, 1 }, { 4, MAX_K } },
},
{
+ "JGE (jt 0), test 1",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_LEN, 0),
+ BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2),
+ BPF_JUMP(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 1),
+ BPF_STMT(BPF_RET | BPF_K, 1),
+ BPF_STMT(BPF_RET | BPF_K, MAX_K)
+ },
+ CLASSIC,
+ { 4, 4, 4, 3, 3 },
+ { { 2, 0 }, { 3, 1 }, { 4, 1 } },
+ },
+ {
+ "JGE (jt 0), test 2",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_LEN, 0),
+ BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2),
+ BPF_JUMP(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 1),
+ BPF_STMT(BPF_RET | BPF_K, 1),
+ BPF_STMT(BPF_RET | BPF_K, MAX_K)
+ },
+ CLASSIC,
+ { 4, 4, 5, 3, 3 },
+ { { 4, 1 }, { 5, 1 }, { 6, MAX_K } },
+ },
+ {
"JGE",
.u.insns = {
BPF_STMT(BPF_LDX | BPF_LEN, 0),
@@ -4492,6 +4518,35 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JSLT | BPF_K */
+ {
+ "JMP_JSLT_K: Signed jump: if (-2 < -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 0xfffffffffffffffeLL),
+ BPF_JMP_IMM(BPF_JSLT, R1, -1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSLT_K: Signed jump: if (-1 < -1) return 0",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
+ BPF_JMP_IMM(BPF_JSLT, R1, -1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JSGT | BPF_K */
{
"JMP_JSGT_K: Signed jump: if (-1 > -2) return 1",
@@ -4521,6 +4576,73 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JSLE | BPF_K */
+ {
+ "JMP_JSLE_K: Signed jump: if (-2 <= -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 0xfffffffffffffffeLL),
+ BPF_JMP_IMM(BPF_JSLE, R1, -1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSLE_K: Signed jump: if (-1 <= -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 0xffffffffffffffffLL),
+ BPF_JMP_IMM(BPF_JSLE, R1, -1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSLE_K: Signed jump: value walk 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_JMP_IMM(BPF_JSLE, R1, 0, 6),
+ BPF_ALU64_IMM(BPF_SUB, R1, 1),
+ BPF_JMP_IMM(BPF_JSLE, R1, 0, 4),
+ BPF_ALU64_IMM(BPF_SUB, R1, 1),
+ BPF_JMP_IMM(BPF_JSLE, R1, 0, 2),
+ BPF_ALU64_IMM(BPF_SUB, R1, 1),
+ BPF_JMP_IMM(BPF_JSLE, R1, 0, 1),
+ BPF_EXIT_INSN(), /* bad exit */
+ BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSLE_K: Signed jump: value walk 2",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_JMP_IMM(BPF_JSLE, R1, 0, 4),
+ BPF_ALU64_IMM(BPF_SUB, R1, 2),
+ BPF_JMP_IMM(BPF_JSLE, R1, 0, 2),
+ BPF_ALU64_IMM(BPF_SUB, R1, 2),
+ BPF_JMP_IMM(BPF_JSLE, R1, 0, 1),
+ BPF_EXIT_INSN(), /* bad exit */
+ BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JSGE | BPF_K */
{
"JMP_JSGE_K: Signed jump: if (-1 >= -2) return 1",
@@ -4617,6 +4739,35 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JLT | BPF_K */
+ {
+ "JMP_JLT_K: if (2 < 3) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 2),
+ BPF_JMP_IMM(BPF_JLT, R1, 3, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JGT_K: Unsigned jump: if (1 < -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 1),
+ BPF_JMP_IMM(BPF_JLT, R1, -1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JGE | BPF_K */
{
"JMP_JGE_K: if (3 >= 2) return 1",
@@ -4632,6 +4783,21 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JLE | BPF_K */
+ {
+ "JMP_JLE_K: if (2 <= 3) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 2),
+ BPF_JMP_IMM(BPF_JLE, R1, 3, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JGT | BPF_K jump backwards */
{
"JMP_JGT_K: if (3 > 2) return 1 (jump backwards)",
@@ -4662,6 +4828,36 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JLT | BPF_K jump backwards */
+ {
+ "JMP_JGT_K: if (2 < 3) return 1 (jump backwards)",
+ .u.insns_int = {
+ BPF_JMP_IMM(BPF_JA, 0, 0, 2), /* goto start */
+ BPF_ALU32_IMM(BPF_MOV, R0, 1), /* out: */
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 0), /* start: */
+ BPF_LD_IMM64(R1, 2), /* note: this takes 2 insns */
+ BPF_JMP_IMM(BPF_JLT, R1, 3, -6), /* goto out */
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JLE_K: if (3 <= 3) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_JMP_IMM(BPF_JLE, R1, 3, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JNE | BPF_K */
{
"JMP_JNE_K: if (3 != 2) return 1",
@@ -4752,6 +4948,37 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JSLT | BPF_X */
+ {
+ "JMP_JSLT_X: Signed jump: if (-2 < -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -1),
+ BPF_LD_IMM64(R2, -2),
+ BPF_JMP_REG(BPF_JSLT, R2, R1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSLT_X: Signed jump: if (-1 < -1) return 0",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_LD_IMM64(R1, -1),
+ BPF_LD_IMM64(R2, -1),
+ BPF_JMP_REG(BPF_JSLT, R1, R2, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JSGE | BPF_X */
{
"JMP_JSGE_X: Signed jump: if (-1 >= -2) return 1",
@@ -4783,6 +5010,37 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JSLE | BPF_X */
+ {
+ "JMP_JSLE_X: Signed jump: if (-2 <= -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -1),
+ BPF_LD_IMM64(R2, -2),
+ BPF_JMP_REG(BPF_JSLE, R2, R1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSLE_X: Signed jump: if (-1 <= -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -1),
+ BPF_LD_IMM64(R2, -1),
+ BPF_JMP_REG(BPF_JSLE, R1, R2, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JGT | BPF_X */
{
"JMP_JGT_X: if (3 > 2) return 1",
@@ -4814,6 +5072,37 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JLT | BPF_X */
+ {
+ "JMP_JLT_X: if (2 < 3) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_LD_IMM64(R2, 2),
+ BPF_JMP_REG(BPF_JLT, R2, R1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JLT_X: Unsigned jump: if (1 < -1) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -1),
+ BPF_LD_IMM64(R2, 1),
+ BPF_JMP_REG(BPF_JLT, R2, R1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JGE | BPF_X */
{
"JMP_JGE_X: if (3 >= 2) return 1",
@@ -4845,6 +5134,37 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ /* BPF_JMP | BPF_JLE | BPF_X */
+ {
+ "JMP_JLE_X: if (2 <= 3) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_LD_IMM64(R2, 2),
+ BPF_JMP_REG(BPF_JLE, R2, R1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JLE_X: if (3 <= 3) return 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_LD_IMM64(R2, 3),
+ BPF_JMP_REG(BPF_JLE, R1, R2, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
{
/* Mainly testing JIT + imm64 here. */
"JMP_JGE_X: ldimm64 test 1",
@@ -4890,6 +5210,50 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ {
+ "JMP_JLE_X: ldimm64 test 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_LD_IMM64(R2, 2),
+ BPF_JMP_REG(BPF_JLE, R2, R1, 2),
+ BPF_LD_IMM64(R0, 0xffffffffffffffffULL),
+ BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeULL),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 0xeeeeeeeeU } },
+ },
+ {
+ "JMP_JLE_X: ldimm64 test 2",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, 3),
+ BPF_LD_IMM64(R2, 2),
+ BPF_JMP_REG(BPF_JLE, R2, R1, 0),
+ BPF_LD_IMM64(R0, 0xffffffffffffffffULL),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 0xffffffffU } },
+ },
+ {
+ "JMP_JLE_X: ldimm64 test 3",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 1),
+ BPF_LD_IMM64(R1, 3),
+ BPF_LD_IMM64(R2, 2),
+ BPF_JMP_REG(BPF_JLE, R2, R1, 4),
+ BPF_LD_IMM64(R0, 0xffffffffffffffffULL),
+ BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeULL),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JNE | BPF_X */
{
"JMP_JNE_X: if (3 != 2) return 1",
diff --git a/lib/test_debug_virtual.c b/lib/test_debug_virtual.c
new file mode 100644
index 0000000..b9cdeec
--- /dev/null
+++ b/lib/test_debug_virtual.c
@@ -0,0 +1,49 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/sizes.h>
+
+#include <asm/page.h>
+#ifdef CONFIG_MIPS
+#include <asm/bootinfo.h>
+#endif
+
+struct foo {
+ unsigned int bar;
+};
+
+struct foo *foo;
+
+static int __init test_debug_virtual_init(void)
+{
+ phys_addr_t pa;
+ void *va;
+
+ va = (void *)VMALLOC_START;
+ pa = virt_to_phys(va);
+
+ pr_info("PA: %pa for VA: 0x%lx\n", &pa, (unsigned long)va);
+
+ foo = kzalloc(sizeof(*foo), GFP_KERNEL);
+ if (!foo)
+ return -ENOMEM;
+
+ pa = virt_to_phys(foo);
+ va = foo;
+ pr_info("PA: %pa for VA: 0x%lx\n", &pa, (unsigned long)va);
+
+ return 0;
+}
+module_init(test_debug_virtual_init);
+
+static void __exit test_debug_virtual_exit(void)
+{
+ kfree(foo);
+}
+module_exit(test_debug_virtual_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Test module for CONFIG_DEBUG_VIRTUAL");
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 09371b0..64a4c76 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -19,10 +19,85 @@
#include <linux/miscdevice.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+
+#define TEST_FIRMWARE_NAME "test-firmware.bin"
+#define TEST_FIRMWARE_NUM_REQS 4
static DEFINE_MUTEX(test_fw_mutex);
static const struct firmware *test_firmware;
+struct test_batched_req {
+ u8 idx;
+ int rc;
+ bool sent;
+ const struct firmware *fw;
+ const char *name;
+ struct completion completion;
+ struct task_struct *task;
+ struct device *dev;
+};
+
+/**
+ * test_config - represents configuration for the test for different triggers
+ *
+ * @name: the name of the firmware file to look for
+ * @sync_direct: when the sync trigger is used if this is true
+ * request_firmware_direct() will be used instead.
+ * @send_uevent: whether or not to send a uevent for async requests
+ * @num_requests: number of requests to try per test case. This is trigger
+ * specific.
+ * @reqs: stores all requests information
+ * @read_fw_idx: index of thread from which we want to read firmware results
+ * from through the read_fw trigger.
+ * @test_result: a test may use this to collect the result from the call
+ * of the request_firmware*() calls used in their tests. In order of
+ * priority we always keep first any setup error. If no setup errors were
+ * found then we move on to the first error encountered while running the
+ * API. Note that for async calls this typically will be a successful
+ * result (0) unless of course you've used bogus parameters, or the system
+ * is out of memory. In the async case the callback is expected to do a
+ * bit more homework to figure out what happened, unfortunately the only
+ * information passed today on error is the fact that no firmware was
+ * found so we can only assume -ENOENT on async calls if the firmware is
+ * NULL.
+ *
+ * Errors you can expect:
+ *
+ * API specific:
+ *
+ * 0: success for sync, for async it means request was sent
+ * -EINVAL: invalid parameters or request
+ * -ENOENT: files not found
+ *
+ * System environment:
+ *
+ * -ENOMEM: memory pressure on system
+ * -ENODEV: out of number of devices to test
+ * -EINVAL: an unexpected error has occurred
+ * @req_firmware: if @sync_direct is true this is set to
+ * request_firmware_direct(), otherwise request_firmware()
+ */
+struct test_config {
+ char *name;
+ bool sync_direct;
+ bool send_uevent;
+ u8 num_requests;
+ u8 read_fw_idx;
+
+ /*
+ * These below don't belong her but we'll move them once we create
+ * a struct fw_test_device and stuff the misc_dev under there later.
+ */
+ struct test_batched_req *reqs;
+ int test_result;
+ int (*req_firmware)(const struct firmware **fw, const char *name,
+ struct device *device);
+};
+
+struct test_config *test_fw_config;
+
static ssize_t test_fw_misc_read(struct file *f, char __user *buf,
size_t size, loff_t *offset)
{
@@ -42,6 +117,338 @@ static const struct file_operations test_fw_fops = {
.read = test_fw_misc_read,
};
+static void __test_release_all_firmware(void)
+{
+ struct test_batched_req *req;
+ u8 i;
+
+ if (!test_fw_config->reqs)
+ return;
+
+ for (i = 0; i < test_fw_config->num_requests; i++) {
+ req = &test_fw_config->reqs[i];
+ if (req->fw)
+ release_firmware(req->fw);
+ }
+
+ vfree(test_fw_config->reqs);
+ test_fw_config->reqs = NULL;
+}
+
+static void test_release_all_firmware(void)
+{
+ mutex_lock(&test_fw_mutex);
+ __test_release_all_firmware();
+ mutex_unlock(&test_fw_mutex);
+}
+
+
+static void __test_firmware_config_free(void)
+{
+ __test_release_all_firmware();
+ kfree_const(test_fw_config->name);
+ test_fw_config->name = NULL;
+}
+
+/*
+ * XXX: move to kstrncpy() once merged.
+ *
+ * Users should use kfree_const() when freeing these.
+ */
+static int __kstrncpy(char **dst, const char *name, size_t count, gfp_t gfp)
+{
+ *dst = kstrndup(name, count, gfp);
+ if (!*dst)
+ return -ENOSPC;
+ return count;
+}
+
+static int __test_firmware_config_init(void)
+{
+ int ret;
+
+ ret = __kstrncpy(&test_fw_config->name, TEST_FIRMWARE_NAME,
+ strlen(TEST_FIRMWARE_NAME), GFP_KERNEL);
+ if (ret < 0)
+ goto out;
+
+ test_fw_config->num_requests = TEST_FIRMWARE_NUM_REQS;
+ test_fw_config->send_uevent = true;
+ test_fw_config->sync_direct = false;
+ test_fw_config->req_firmware = request_firmware;
+ test_fw_config->test_result = 0;
+ test_fw_config->reqs = NULL;
+
+ return 0;
+
+out:
+ __test_firmware_config_free();
+ return ret;
+}
+
+static ssize_t reset_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret;
+
+ mutex_lock(&test_fw_mutex);
+
+ __test_firmware_config_free();
+
+ ret = __test_firmware_config_init();
+ if (ret < 0) {
+ ret = -ENOMEM;
+ pr_err("could not alloc settings for config trigger: %d\n",
+ ret);
+ goto out;
+ }
+
+ pr_info("reset\n");
+ ret = count;
+
+out:
+ mutex_unlock(&test_fw_mutex);
+
+ return ret;
+}
+static DEVICE_ATTR_WO(reset);
+
+static ssize_t config_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ int len = 0;
+
+ mutex_lock(&test_fw_mutex);
+
+ len += snprintf(buf, PAGE_SIZE,
+ "Custom trigger configuration for: %s\n",
+ dev_name(dev));
+
+ if (test_fw_config->name)
+ len += snprintf(buf+len, PAGE_SIZE,
+ "name:\t%s\n",
+ test_fw_config->name);
+ else
+ len += snprintf(buf+len, PAGE_SIZE,
+ "name:\tEMTPY\n");
+
+ len += snprintf(buf+len, PAGE_SIZE,
+ "num_requests:\t%u\n", test_fw_config->num_requests);
+
+ len += snprintf(buf+len, PAGE_SIZE,
+ "send_uevent:\t\t%s\n",
+ test_fw_config->send_uevent ?
+ "FW_ACTION_HOTPLUG" :
+ "FW_ACTION_NOHOTPLUG");
+ len += snprintf(buf+len, PAGE_SIZE,
+ "sync_direct:\t\t%s\n",
+ test_fw_config->sync_direct ? "true" : "false");
+ len += snprintf(buf+len, PAGE_SIZE,
+ "read_fw_idx:\t%u\n", test_fw_config->read_fw_idx);
+
+ mutex_unlock(&test_fw_mutex);
+
+ return len;
+}
+static DEVICE_ATTR_RO(config);
+
+static ssize_t config_name_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret;
+
+ mutex_lock(&test_fw_mutex);
+ kfree_const(test_fw_config->name);
+ ret = __kstrncpy(&test_fw_config->name, buf, count, GFP_KERNEL);
+ mutex_unlock(&test_fw_mutex);
+
+ return ret;
+}
+
+/*
+ * As per sysfs_kf_seq_show() the buf is max PAGE_SIZE.
+ */
+static ssize_t config_test_show_str(char *dst,
+ char *src)
+{
+ int len;
+
+ mutex_lock(&test_fw_mutex);
+ len = snprintf(dst, PAGE_SIZE, "%s\n", src);
+ mutex_unlock(&test_fw_mutex);
+
+ return len;
+}
+
+static int test_dev_config_update_bool(const char *buf, size_t size,
+ bool *cfg)
+{
+ int ret;
+
+ mutex_lock(&test_fw_mutex);
+ if (strtobool(buf, cfg) < 0)
+ ret = -EINVAL;
+ else
+ ret = size;
+ mutex_unlock(&test_fw_mutex);
+
+ return ret;
+}
+
+static ssize_t
+test_dev_config_show_bool(char *buf,
+ bool config)
+{
+ bool val;
+
+ mutex_lock(&test_fw_mutex);
+ val = config;
+ mutex_unlock(&test_fw_mutex);
+
+ return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t test_dev_config_show_int(char *buf, int cfg)
+{
+ int val;
+
+ mutex_lock(&test_fw_mutex);
+ val = cfg;
+ mutex_unlock(&test_fw_mutex);
+
+ return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
+{
+ int ret;
+ long new;
+
+ ret = kstrtol(buf, 10, &new);
+ if (ret)
+ return ret;
+
+ if (new > U8_MAX)
+ return -EINVAL;
+
+ mutex_lock(&test_fw_mutex);
+ *(u8 *)cfg = new;
+ mutex_unlock(&test_fw_mutex);
+
+ /* Always return full write size even if we didn't consume all */
+ return size;
+}
+
+static ssize_t test_dev_config_show_u8(char *buf, u8 cfg)
+{
+ u8 val;
+
+ mutex_lock(&test_fw_mutex);
+ val = cfg;
+ mutex_unlock(&test_fw_mutex);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static ssize_t config_name_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return config_test_show_str(buf, test_fw_config->name);
+}
+static DEVICE_ATTR(config_name, 0644, config_name_show, config_name_store);
+
+static ssize_t config_num_requests_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int rc;
+
+ mutex_lock(&test_fw_mutex);
+ if (test_fw_config->reqs) {
+ pr_err("Must call release_all_firmware prior to changing config\n");
+ rc = -EINVAL;
+ goto out;
+ }
+ mutex_unlock(&test_fw_mutex);
+
+ rc = test_dev_config_update_u8(buf, count,
+ &test_fw_config->num_requests);
+
+out:
+ return rc;
+}
+
+static ssize_t config_num_requests_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return test_dev_config_show_u8(buf, test_fw_config->num_requests);
+}
+static DEVICE_ATTR(config_num_requests, 0644, config_num_requests_show,
+ config_num_requests_store);
+
+static ssize_t config_sync_direct_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int rc = test_dev_config_update_bool(buf, count,
+ &test_fw_config->sync_direct);
+
+ if (rc == count)
+ test_fw_config->req_firmware = test_fw_config->sync_direct ?
+ request_firmware_direct :
+ request_firmware;
+ return rc;
+}
+
+static ssize_t config_sync_direct_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return test_dev_config_show_bool(buf, test_fw_config->sync_direct);
+}
+static DEVICE_ATTR(config_sync_direct, 0644, config_sync_direct_show,
+ config_sync_direct_store);
+
+static ssize_t config_send_uevent_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ return test_dev_config_update_bool(buf, count,
+ &test_fw_config->send_uevent);
+}
+
+static ssize_t config_send_uevent_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return test_dev_config_show_bool(buf, test_fw_config->send_uevent);
+}
+static DEVICE_ATTR(config_send_uevent, 0644, config_send_uevent_show,
+ config_send_uevent_store);
+
+static ssize_t config_read_fw_idx_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ return test_dev_config_update_u8(buf, count,
+ &test_fw_config->read_fw_idx);
+}
+
+static ssize_t config_read_fw_idx_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return test_dev_config_show_u8(buf, test_fw_config->read_fw_idx);
+}
+static DEVICE_ATTR(config_read_fw_idx, 0644, config_read_fw_idx_show,
+ config_read_fw_idx_store);
+
+
static ssize_t trigger_request_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
@@ -170,12 +577,301 @@ out:
}
static DEVICE_ATTR_WO(trigger_custom_fallback);
+static int test_fw_run_batch_request(void *data)
+{
+ struct test_batched_req *req = data;
+
+ if (!req) {
+ test_fw_config->test_result = -EINVAL;
+ return -EINVAL;
+ }
+
+ req->rc = test_fw_config->req_firmware(&req->fw, req->name, req->dev);
+ if (req->rc) {
+ pr_info("#%u: batched sync load failed: %d\n",
+ req->idx, req->rc);
+ if (!test_fw_config->test_result)
+ test_fw_config->test_result = req->rc;
+ } else if (req->fw) {
+ req->sent = true;
+ pr_info("#%u: batched sync loaded %zu\n",
+ req->idx, req->fw->size);
+ }
+ complete(&req->completion);
+
+ req->task = NULL;
+
+ return 0;
+}
+
+/*
+ * We use a kthread as otherwise the kernel serializes all our sync requests
+ * and we would not be able to mimic batched requests on a sync call. Batched
+ * requests on a sync call can for instance happen on a device driver when
+ * multiple cards are used and firmware loading happens outside of probe.
+ */
+static ssize_t trigger_batched_requests_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct test_batched_req *req;
+ int rc;
+ u8 i;
+
+ mutex_lock(&test_fw_mutex);
+
+ test_fw_config->reqs = vzalloc(sizeof(struct test_batched_req) *
+ test_fw_config->num_requests * 2);
+ if (!test_fw_config->reqs) {
+ rc = -ENOMEM;
+ goto out_unlock;
+ }
+
+ pr_info("batched sync firmware loading '%s' %u times\n",
+ test_fw_config->name, test_fw_config->num_requests);
+
+ for (i = 0; i < test_fw_config->num_requests; i++) {
+ req = &test_fw_config->reqs[i];
+ if (!req) {
+ WARN_ON(1);
+ rc = -ENOMEM;
+ goto out_bail;
+ }
+ req->fw = NULL;
+ req->idx = i;
+ req->name = test_fw_config->name;
+ req->dev = dev;
+ init_completion(&req->completion);
+ req->task = kthread_run(test_fw_run_batch_request, req,
+ "%s-%u", KBUILD_MODNAME, req->idx);
+ if (!req->task || IS_ERR(req->task)) {
+ pr_err("Setting up thread %u failed\n", req->idx);
+ req->task = NULL;
+ rc = -ENOMEM;
+ goto out_bail;
+ }
+ }
+
+ rc = count;
+
+ /*
+ * We require an explicit release to enable more time and delay of
+ * calling release_firmware() to improve our chances of forcing a
+ * batched request. If we instead called release_firmware() right away
+ * then we might miss on an opportunity of having a successful firmware
+ * request pass on the opportunity to be come a batched request.
+ */
+
+out_bail:
+ for (i = 0; i < test_fw_config->num_requests; i++) {
+ req = &test_fw_config->reqs[i];
+ if (req->task || req->sent)
+ wait_for_completion(&req->completion);
+ }
+
+ /* Override any worker error if we had a general setup error */
+ if (rc < 0)
+ test_fw_config->test_result = rc;
+
+out_unlock:
+ mutex_unlock(&test_fw_mutex);
+
+ return rc;
+}
+static DEVICE_ATTR_WO(trigger_batched_requests);
+
+/*
+ * We wait for each callback to return with the lock held, no need to lock here
+ */
+static void trigger_batched_cb(const struct firmware *fw, void *context)
+{
+ struct test_batched_req *req = context;
+
+ if (!req) {
+ test_fw_config->test_result = -EINVAL;
+ return;
+ }
+
+ /* forces *some* batched requests to queue up */
+ if (!req->idx)
+ ssleep(2);
+
+ req->fw = fw;
+
+ /*
+ * Unfortunately the firmware API gives us nothing other than a null FW
+ * if the firmware was not found on async requests. Best we can do is
+ * just assume -ENOENT. A better API would pass the actual return
+ * value to the callback.
+ */
+ if (!fw && !test_fw_config->test_result)
+ test_fw_config->test_result = -ENOENT;
+
+ complete(&req->completion);
+}
+
+static
+ssize_t trigger_batched_requests_async_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct test_batched_req *req;
+ bool send_uevent;
+ int rc;
+ u8 i;
+
+ mutex_lock(&test_fw_mutex);
+
+ test_fw_config->reqs = vzalloc(sizeof(struct test_batched_req) *
+ test_fw_config->num_requests * 2);
+ if (!test_fw_config->reqs) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ pr_info("batched loading '%s' custom fallback mechanism %u times\n",
+ test_fw_config->name, test_fw_config->num_requests);
+
+ send_uevent = test_fw_config->send_uevent ? FW_ACTION_HOTPLUG :
+ FW_ACTION_NOHOTPLUG;
+
+ for (i = 0; i < test_fw_config->num_requests; i++) {
+ req = &test_fw_config->reqs[i];
+ if (!req) {
+ WARN_ON(1);
+ goto out_bail;
+ }
+ req->name = test_fw_config->name;
+ req->fw = NULL;
+ req->idx = i;
+ init_completion(&req->completion);
+ rc = request_firmware_nowait(THIS_MODULE, send_uevent,
+ req->name,
+ dev, GFP_KERNEL, req,
+ trigger_batched_cb);
+ if (rc) {
+ pr_info("#%u: batched async load failed setup: %d\n",
+ i, rc);
+ req->rc = rc;
+ goto out_bail;
+ } else
+ req->sent = true;
+ }
+
+ rc = count;
+
+out_bail:
+
+ /*
+ * We require an explicit release to enable more time and delay of
+ * calling release_firmware() to improve our chances of forcing a
+ * batched request. If we instead called release_firmware() right away
+ * then we might miss on an opportunity of having a successful firmware
+ * request pass on the opportunity to be come a batched request.
+ */
+
+ for (i = 0; i < test_fw_config->num_requests; i++) {
+ req = &test_fw_config->reqs[i];
+ if (req->sent)
+ wait_for_completion(&req->completion);
+ }
+
+ /* Override any worker error if we had a general setup error */
+ if (rc < 0)
+ test_fw_config->test_result = rc;
+
+out:
+ mutex_unlock(&test_fw_mutex);
+
+ return rc;
+}
+static DEVICE_ATTR_WO(trigger_batched_requests_async);
+
+static ssize_t test_result_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return test_dev_config_show_int(buf, test_fw_config->test_result);
+}
+static DEVICE_ATTR_RO(test_result);
+
+static ssize_t release_all_firmware_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ test_release_all_firmware();
+ return count;
+}
+static DEVICE_ATTR_WO(release_all_firmware);
+
+static ssize_t read_firmware_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct test_batched_req *req;
+ u8 idx;
+ ssize_t rc = 0;
+
+ mutex_lock(&test_fw_mutex);
+
+ idx = test_fw_config->read_fw_idx;
+ if (idx >= test_fw_config->num_requests) {
+ rc = -ERANGE;
+ goto out;
+ }
+
+ if (!test_fw_config->reqs) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ req = &test_fw_config->reqs[idx];
+ if (!req->fw) {
+ pr_err("#%u: failed to async load firmware\n", idx);
+ rc = -ENOENT;
+ goto out;
+ }
+
+ pr_info("#%u: loaded %zu\n", idx, req->fw->size);
+
+ if (req->fw->size > PAGE_SIZE) {
+ pr_err("Testing interface must use PAGE_SIZE firmware for now\n");
+ rc = -EINVAL;
+ }
+ memcpy(buf, req->fw->data, req->fw->size);
+
+ rc = req->fw->size;
+out:
+ mutex_unlock(&test_fw_mutex);
+
+ return rc;
+}
+static DEVICE_ATTR_RO(read_firmware);
+
#define TEST_FW_DEV_ATTR(name) &dev_attr_##name.attr
static struct attribute *test_dev_attrs[] = {
+ TEST_FW_DEV_ATTR(reset),
+
+ TEST_FW_DEV_ATTR(config),
+ TEST_FW_DEV_ATTR(config_name),
+ TEST_FW_DEV_ATTR(config_num_requests),
+ TEST_FW_DEV_ATTR(config_sync_direct),
+ TEST_FW_DEV_ATTR(config_send_uevent),
+ TEST_FW_DEV_ATTR(config_read_fw_idx),
+
+ /* These don't use the config at all - they could be ported! */
TEST_FW_DEV_ATTR(trigger_request),
TEST_FW_DEV_ATTR(trigger_async_request),
TEST_FW_DEV_ATTR(trigger_custom_fallback),
+
+ /* These use the config and can use the test_result */
+ TEST_FW_DEV_ATTR(trigger_batched_requests),
+ TEST_FW_DEV_ATTR(trigger_batched_requests_async),
+
+ TEST_FW_DEV_ATTR(release_all_firmware),
+ TEST_FW_DEV_ATTR(test_result),
+ TEST_FW_DEV_ATTR(read_firmware),
NULL,
};
@@ -192,8 +888,17 @@ static int __init test_firmware_init(void)
{
int rc;
+ test_fw_config = kzalloc(sizeof(struct test_config), GFP_KERNEL);
+ if (!test_fw_config)
+ return -ENOMEM;
+
+ rc = __test_firmware_config_init();
+ if (rc)
+ return rc;
+
rc = misc_register(&test_fw_misc_device);
if (rc) {
+ kfree(test_fw_config);
pr_err("could not register misc device: %d\n", rc);
return rc;
}
@@ -207,8 +912,13 @@ module_init(test_firmware_init);
static void __exit test_firmware_exit(void)
{
+ mutex_lock(&test_fw_mutex);
release_firmware(test_firmware);
misc_deregister(&test_fw_misc_device);
+ __test_firmware_config_free();
+ kfree(test_fw_config);
+ mutex_unlock(&test_fw_mutex);
+
pr_warn("removed interface\n");
}
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index ff91489..fba78d25 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -924,7 +924,7 @@ static int test_dev_config_update_uint_range(struct kmod_test_device *test_dev,
if (ret)
return ret;
- if (new < min || new > max || new > UINT_MAX)
+ if (new < min || new > max)
return -EINVAL;
mutex_lock(&test_dev->config_mutex);
@@ -946,7 +946,7 @@ static int test_dev_config_update_int(struct kmod_test_device *test_dev,
if (ret)
return ret;
- if (new > INT_MAX || new < INT_MIN)
+ if (new < INT_MIN || new > INT_MAX)
return -EINVAL;
mutex_lock(&test_dev->config_mutex);
OpenPOWER on IntegriCloud