Merge branch 'akpm' (patches from Andrew)HEADmaster

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - v9fs updates

 - MM

 - procfs updates

 - lib/ updates

 - autofs updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  autofs: small cleanup in autofs_getpath()
  autofs: clean up includes
  autofs: comment on selinux changes needed for module autoload
  autofs: update MAINTAINERS entry for autofs
  autofs: use autofs instead of autofs4 in documentation
  autofs: rename autofs documentation files
  autofs: create autofs Kconfig and Makefile
  autofs: delete fs/autofs4 source files
  autofs: update fs/autofs4/Makefile
  autofs: update fs/autofs4/Kconfig
  autofs: copy autofs4 to autofs
  autofs4: use autofs instead of autofs4 everywhere
  autofs4: merge auto_fs.h and auto_fs4.h
  fs/binfmt_misc.c: do not allow offset overflow
  checkpatch: improve patch recognition
  lib/ucs2_string.c: add MODULE_LICENSE()
  lib/mpi: headers cleanup
  lib/percpu_ida.c: use _irqsave() instead of local_irq_save() + spin_lock
  lib/idr.c: remove simple_ida_lock
  lib/bitmap.c: micro-optimization for __bitmap_complement()
  ...

6 files changed, 35 insertions, 125 deletions

diff --git a/lib/bitmap.c b/lib/bitmap.c
index a42eff7e8c48b..58f9750e49c68 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -64,12 +64,9 @@ EXPORT_SYMBOL(__bitmap_equal);
 
 void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits)
 {
-	unsigned int k, lim = bits/BITS_PER_LONG;
+	unsigned int k, lim = BITS_TO_LONGS(bits);
 	for (k = 0; k < lim; ++k)
 		dst[k] = ~src[k];
-
-	if (bits % BITS_PER_LONG)
-		dst[k] = ~src[k];
 }
 EXPORT_SYMBOL(__bitmap_complement);
 
diff --git a/lib/bucket_locks.c b/lib/bucket_locks.c
index 266a97c5708ba..ade3ce6c4af6a 100644
--- a/lib/bucket_locks.c
+++ b/lib/bucket_locks.c
@@ -30,10 +30,7 @@ int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *locks_mask,
 	}
 
 	if (sizeof(spinlock_t) != 0) {
-		if (gfpflags_allow_blocking(gfp))
-			tlocks = kvmalloc(size * sizeof(spinlock_t), gfp);
-		else
-			tlocks = kmalloc_array(size, sizeof(spinlock_t), gfp);
+		tlocks = kvmalloc_array(size, sizeof(spinlock_t), gfp);
 		if (!tlocks)
 			return -ENOMEM;
 		for (i = 0; i < size; i++)
diff --git a/lib/idr.c b/lib/idr.c
index 823b813f08f86..ed9c169c12bdc 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -4,9 +4,9 @@
 #include <linux/idr.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/xarray.h>
 
 DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
-static DEFINE_SPINLOCK(simple_ida_lock);
 
 /**
  * idr_alloc_u32() - Allocate an ID.
@@ -581,7 +581,7 @@ again:
 	if (!ida_pre_get(ida, gfp_mask))
 		return -ENOMEM;
 
-	spin_lock_irqsave(&simple_ida_lock, flags);
+	xa_lock_irqsave(&ida->ida_rt, flags);
 	ret = ida_get_new_above(ida, start, &id);
 	if (!ret) {
 		if (id > max) {
@@ -591,7 +591,7 @@ again:
 			ret = id;
 		}
 	}
-	spin_unlock_irqrestore(&simple_ida_lock, flags);
+	xa_unlock_irqrestore(&ida->ida_rt, flags);
 
 	if (unlikely(ret == -EAGAIN))
 		goto again;
@@ -615,8 +615,8 @@ void ida_simple_remove(struct ida *ida, unsigned int id)
 	unsigned long flags;
 
 	BUG_ON((int)id < 0);
-	spin_lock_irqsave(&simple_ida_lock, flags);
+	xa_lock_irqsave(&ida->ida_rt, flags);
 	ida_remove(ida, id);
-	spin_unlock_irqrestore(&simple_ida_lock, flags);
+	xa_unlock_irqrestore(&ida->ida_rt, flags);
 }
 EXPORT_SYMBOL(ida_simple_remove);
diff --git a/lib/mpi/mpi-internal.h b/lib/mpi/mpi-internal.h
index 7eceeddb3fb88..c2d6f4efcfbc6 100644
--- a/lib/mpi/mpi-internal.h
+++ b/lib/mpi/mpi-internal.h
@@ -65,13 +65,6 @@
 typedef mpi_limb_t *mpi_ptr_t;	/* pointer to a limb */
 typedef int mpi_size_t;		/* (must be a signed type) */
 
-static inline int RESIZE_IF_NEEDED(MPI a, unsigned b)
-{
-	if (a->alloced < b)
-		return mpi_resize(a, b);
-	return 0;
-}
-
 /* Copy N limbs from S to D.  */
 #define MPN_COPY(d, s, n) \
 	do {					\
@@ -80,13 +73,6 @@ static inline int RESIZE_IF_NEEDED(MPI a, unsigned b)
 			(d)[_i] = (s)[_i];	\
 	} while (0)
 
-#define MPN_COPY_INCR(d, s, n) \
-	do {					\
-		mpi_size_t _i;			\
-		for (_i = 0; _i < (n); _i++)	\
-			(d)[_i] = (s)[_i];	\
-	} while (0)
-
 #define MPN_COPY_DECR(d, s, n) \
 	do {					\
 		mpi_size_t _i;			\
@@ -111,15 +97,6 @@ static inline int RESIZE_IF_NEEDED(MPI a, unsigned b)
 		}				\
 	} while (0)
 
-#define MPN_NORMALIZE_NOT_ZERO(d, n) \
-	do {				\
-		for (;;) {		\
-			if ((d)[(n)-1])	\
-				break;	\
-			(n)--;		\
-		}			\
-	} while (0)
-
 #define MPN_MUL_N_RECURSE(prodp, up, vp, size, tspace) \
 	do {							\
 		if ((size) < KARATSUBA_THRESHOLD)		\
@@ -128,46 +105,11 @@ static inline int RESIZE_IF_NEEDED(MPI a, unsigned b)
 			mul_n(prodp, up, vp, size, tspace);	\
 	} while (0);
 
-/* Divide the two-limb number in (NH,,NL) by D, with DI being the largest
- * limb not larger than (2**(2*BITS_PER_MP_LIMB))/D - (2**BITS_PER_MP_LIMB).
- * If this would yield overflow, DI should be the largest possible number
- * (i.e., only ones).  For correct operation, the most significant bit of D
- * has to be set.  Put the quotient in Q and the remainder in R.
- */
-#define UDIV_QRNND_PREINV(q, r, nh, nl, d, di) \
-	do {								\
-		mpi_limb_t _q, _ql, _r;					\
-		mpi_limb_t _xh, _xl;					\
-		umul_ppmm(_q, _ql, (nh), (di));				\
-		_q += (nh);	/* DI is 2**BITS_PER_MPI_LIMB too small */ \
-		umul_ppmm(_xh, _xl, _q, (d));				\
-		sub_ddmmss(_xh, _r, (nh), (nl), _xh, _xl);		\
-		if (_xh) {						\
-			sub_ddmmss(_xh, _r, _xh, _r, 0, (d));		\
-			_q++;						\
-			if (_xh) {					\
-				sub_ddmmss(_xh, _r, _xh, _r, 0, (d));	\
-				_q++;					\
-			}						\
-		}							\
-		if (_r >= (d)) {					\
-			_r -= (d);					\
-			_q++;						\
-		}							\
-		(r) = _r;						\
-		(q) = _q;						\
-	} while (0)
-
 /*-- mpiutil.c --*/
 mpi_ptr_t mpi_alloc_limb_space(unsigned nlimbs);
 void mpi_free_limb_space(mpi_ptr_t a);
 void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs);
 
-/*-- mpi-bit.c --*/
-void mpi_rshift_limbs(MPI a, unsigned int count);
-int mpi_lshift_limbs(MPI a, unsigned int count);
-
-/*-- mpihelp-add.c --*/
 static inline mpi_limb_t mpihelp_add_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_size_t s1_size, mpi_limb_t s2_limb);
 mpi_limb_t mpihelp_add_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
@@ -175,7 +117,6 @@ mpi_limb_t mpihelp_add_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 static inline mpi_limb_t mpihelp_add(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
 		       mpi_ptr_t s2_ptr, mpi_size_t s2_size);
 
-/*-- mpihelp-sub.c --*/
 static inline mpi_limb_t mpihelp_sub_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_size_t s1_size, mpi_limb_t s2_limb);
 mpi_limb_t mpihelp_sub_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
@@ -183,10 +124,10 @@ mpi_limb_t mpihelp_sub_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 static inline mpi_limb_t mpihelp_sub(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
 		       mpi_ptr_t s2_ptr, mpi_size_t s2_size);
 
-/*-- mpihelp-cmp.c --*/
+/*-- mpih-cmp.c --*/
 int mpihelp_cmp(mpi_ptr_t op1_ptr, mpi_ptr_t op2_ptr, mpi_size_t size);
 
-/*-- mpihelp-mul.c --*/
+/*-- mpih-mul.c --*/
 
 struct karatsuba_ctx {
 	struct karatsuba_ctx *next;
@@ -202,7 +143,6 @@ mpi_limb_t mpihelp_addmul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			    mpi_size_t s1_size, mpi_limb_t s2_limb);
 mpi_limb_t mpihelp_submul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			    mpi_size_t s1_size, mpi_limb_t s2_limb);
-int mpihelp_mul_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size);
 int mpihelp_mul(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize,
 		mpi_ptr_t vp, mpi_size_t vsize, mpi_limb_t *_result);
 void mpih_sqr_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size);
@@ -214,21 +154,16 @@ int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp,
 			       mpi_ptr_t vp, mpi_size_t vsize,
 			       struct karatsuba_ctx *ctx);
 
-/*-- mpihelp-mul_1.c (or xxx/cpu/ *.S) --*/
+/*-- generic_mpih-mul1.c --*/
 mpi_limb_t mpihelp_mul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_size_t s1_size, mpi_limb_t s2_limb);
 
-/*-- mpihelp-div.c --*/
-mpi_limb_t mpihelp_mod_1(mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
-			 mpi_limb_t divisor_limb);
+/*-- mpih-div.c --*/
 mpi_limb_t mpihelp_divrem(mpi_ptr_t qp, mpi_size_t qextra_limbs,
 			  mpi_ptr_t np, mpi_size_t nsize,
 			  mpi_ptr_t dp, mpi_size_t dsize);
-mpi_limb_t mpihelp_divmod_1(mpi_ptr_t quot_ptr,
-			    mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
-			    mpi_limb_t divisor_limb);
 
-/*-- mpihelp-shift.c --*/
+/*-- generic_mpih-[lr]shift.c --*/
 mpi_limb_t mpihelp_lshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize,
 			  unsigned cnt);
 mpi_limb_t mpihelp_rshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize,
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 6016f1deb1f5f..9bbd9c5d375a2 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -112,18 +112,6 @@ static inline void alloc_global_tags(struct percpu_ida *pool,
 		  min(pool->nr_free, pool->percpu_batch_size));
 }
 
-static inline unsigned alloc_local_tag(struct percpu_ida_cpu *tags)
-{
-	int tag = -ENOSPC;
-
-	spin_lock(&tags->lock);
-	if (tags->nr_free)
-		tag = tags->freelist[--tags->nr_free];
-	spin_unlock(&tags->lock);
-
-	return tag;
-}
-
 /**
  * percpu_ida_alloc - allocate a tag
  * @pool: pool to allocate from
@@ -147,20 +135,22 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
 	DEFINE_WAIT(wait);
 	struct percpu_ida_cpu *tags;
 	unsigned long flags;
-	int tag;
+	int tag = -ENOSPC;
 
-	local_irq_save(flags);
-	tags = this_cpu_ptr(pool->tag_cpu);
+	tags = raw_cpu_ptr(pool->tag_cpu);
+	spin_lock_irqsave(&tags->lock, flags);
 
 	/* Fastpath */
-	tag = alloc_local_tag(tags);
-	if (likely(tag >= 0)) {
-		local_irq_restore(flags);
+	if (likely(tags->nr_free >= 0)) {
+		tag = tags->freelist[--tags->nr_free];
+		spin_unlock_irqrestore(&tags->lock, flags);
 		return tag;
 	}
+	spin_unlock_irqrestore(&tags->lock, flags);
 
 	while (1) {
-		spin_lock(&pool->lock);
+		spin_lock_irqsave(&pool->lock, flags);
+		tags = this_cpu_ptr(pool->tag_cpu);
 
 		/*
 		 * prepare_to_wait() must come before steal_tags(), in case
@@ -184,8 +174,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
 						&pool->cpus_have_tags);
 		}
 
-		spin_unlock(&pool->lock);
-		local_irq_restore(flags);
+		spin_unlock_irqrestore(&pool->lock, flags);
 
 		if (tag >= 0 || state == TASK_RUNNING)
 			break;
@@ -196,9 +185,6 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
 		}
 
 		schedule();
-
-		local_irq_save(flags);
-		tags = this_cpu_ptr(pool->tag_cpu);
 	}
 	if (state != TASK_RUNNING)
 		finish_wait(&pool->wait, &wait);
@@ -222,28 +208,24 @@ void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
 
 	BUG_ON(tag >= pool->nr_tags);
 
-	local_irq_save(flags);
-	tags = this_cpu_ptr(pool->tag_cpu);
+	tags = raw_cpu_ptr(pool->tag_cpu);
 
-	spin_lock(&tags->lock);
+	spin_lock_irqsave(&tags->lock, flags);
 	tags->freelist[tags->nr_free++] = tag;
 
 	nr_free = tags->nr_free;
-	spin_unlock(&tags->lock);
 
 	if (nr_free == 1) {
 		cpumask_set_cpu(smp_processor_id(),
 				&pool->cpus_have_tags);
 		wake_up(&pool->wait);
 	}
+	spin_unlock_irqrestore(&tags->lock, flags);
 
 	if (nr_free == pool->percpu_max_size) {
-		spin_lock(&pool->lock);
+		spin_lock_irqsave(&pool->lock, flags);
+		spin_lock(&tags->lock);
 
-		/*
-		 * Global lock held and irqs disabled, don't need percpu
-		 * lock
-		 */
 		if (tags->nr_free == pool->percpu_max_size) {
 			move_tags(pool->freelist, &pool->nr_free,
 				  tags->freelist, &tags->nr_free,
@@ -251,10 +233,9 @@ void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
 
 			wake_up(&pool->wait);
 		}
-		spin_unlock(&pool->lock);
+		spin_unlock(&tags->lock);
+		spin_unlock_irqrestore(&pool->lock, flags);
 	}
-
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ida_free);
 
@@ -346,29 +327,27 @@ int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
 	struct percpu_ida_cpu *remote;
 	unsigned cpu, i, err = 0;
 
-	local_irq_save(flags);
 	for_each_possible_cpu(cpu) {
 		remote = per_cpu_ptr(pool->tag_cpu, cpu);
-		spin_lock(&remote->lock);
+		spin_lock_irqsave(&remote->lock, flags);
 		for (i = 0; i < remote->nr_free; i++) {
 			err = fn(remote->freelist[i], data);
 			if (err)
 				break;
 		}
-		spin_unlock(&remote->lock);
+		spin_unlock_irqrestore(&remote->lock, flags);
 		if (err)
 			goto out;
 	}
 
-	spin_lock(&pool->lock);
+	spin_lock_irqsave(&pool->lock, flags);
 	for (i = 0; i < pool->nr_free; i++) {
 		err = fn(pool->freelist[i], data);
 		if (err)
 			break;
 	}
-	spin_unlock(&pool->lock);
+	spin_unlock_irqrestore(&pool->lock, flags);
 out:
-	local_irq_restore(flags);
 	return err;
 }
 EXPORT_SYMBOL_GPL(percpu_ida_for_each_free);
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index d7e06b28de382..0a559a42359b8 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -112,3 +112,5 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
 	return j;
 }
 EXPORT_SYMBOL(ucs2_as_utf8);
+
+MODULE_LICENSE("GPL v2");