Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 114 insertions, 26 deletions

diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 3d35d062970d..c253c1b46c6b 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -6,6 +6,7 @@ if HAVE_ARCH_KASAN
 config KASAN
 	bool "KASan: runtime memory debugger"
 	depends on SLUB || (SLAB && !DEBUG_SLAB)
+	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
 	select STACKDEPOT
 	help
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 7e43cd54c84c..8be175df3075 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -596,15 +596,70 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
 	return ret;
 }
 
+static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+				struct iov_iter *i)
+{
+	struct pipe_inode_info *pipe = i->pipe;
+	size_t n, off, xfer = 0;
+	int idx;
+
+	if (!sanity(i))
+		return 0;
+
+	bytes = n = push_pipe(i, bytes, &idx, &off);
+	if (unlikely(!n))
+		return 0;
+	for ( ; n; idx = next_idx(idx, pipe), off = 0) {
+		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
+		unsigned long rem;
+
+		rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr,
+				chunk);
+		i->idx = idx;
+		i->iov_offset = off + chunk - rem;
+		xfer += chunk - rem;
+		if (rem)
+			break;
+		n -= chunk;
+		addr += chunk;
+	}
+	i->count -= xfer;
+	return xfer;
+}
+
+/**
+ * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * @addr: source kernel address
+ * @bytes: total transfer length
+ * @iter: destination iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_to_iter() for protecting read/write to persistent memory.
+ * Unless / until an architecture can guarantee identical performance
+ * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
+ * performance regression to switch more users to the mcsafe version.
+ *
+ * Otherwise, the main differences between this and typical _copy_to_iter().
+ *
+ * * Typical tail/residue handling after a fault retries the copy
+ *   byte-by-byte until the fault happens again. Re-triggering machine
+ *   checks is potentially fatal so the implementation uses source
+ *   alignment and poison alignment assumptions to avoid re-triggering
+ *   hardware exceptions.
+ *
+ * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
+ *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
+ *   a short copy.
+ *
+ * See MCSAFE_TEST for self-test.
+ */
 size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
-	if (unlikely(i->type & ITER_PIPE)) {
-		WARN_ON(1);
-		return 0;
-	}
+	if (unlikely(i->type & ITER_PIPE))
+		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
 	iterate_and_advance(i, bytes, v,
@@ -701,6 +756,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 EXPORT_SYMBOL(_copy_from_iter_nocache);
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * _copy_from_iter_flushcache - write destination through cpu cache
+ * @addr: destination kernel address
+ * @bytes: total transfer length
+ * @iter: source iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_from_iter() for ensuring that writes to persistent memory
+ * are flushed through the CPU cache. It is differentiated from
+ * _copy_from_iter_nocache() in that guarantees all data is flushed for
+ * all iterator types. The _copy_from_iter_nocache() only attempts to
+ * bypass the cache for the ITER_IOVEC case, and on some archs may use
+ * instructions that strand dirty-data in the cache.
+ */
 size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 9bbd9c5d375a..beb14839b41a 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -141,7 +141,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
 	spin_lock_irqsave(&tags->lock, flags);
 
 	/* Fastpath */
-	if (likely(tags->nr_free >= 0)) {
+	if (likely(tags->nr_free)) {
 		tag = tags->freelist[--tags->nr_free];
 		spin_unlock_irqrestore(&tags->lock, flags);
 		return tag;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 9427b5766134..e5c8586cf717 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -774,7 +774,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 				skip++;
 				if (list == iter->list) {
 					iter->p = p;
-					skip = skip;
+					iter->skip = skip;
 					goto found;
 				}
 			}
@@ -964,8 +964,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop);
 
 static size_t rounded_hashtable_size(const struct rhashtable_params *params)
 {
-	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
-		   (unsigned long)params->min_size);
+	size_t retsize;
+
+	if (params->nelem_hint)
+		retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
+			      (unsigned long)params->min_size);
+	else
+		retsize = max(HASH_DEFAULT_SIZE,
+			      (unsigned long)params->min_size);
+
+	return retsize;
 }
 
 static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
@@ -1022,8 +1030,6 @@ int rhashtable_init(struct rhashtable *ht,
 	struct bucket_table *tbl;
 	size_t size;
 
-	size = HASH_DEFAULT_SIZE;
-
 	if ((!params->key_len && !params->obj_hashfn) ||
 	    (params->obj_hashfn && !params->obj_cmpfn))
 		return -EINVAL;
@@ -1050,8 +1056,7 @@ int rhashtable_init(struct rhashtable *ht,
 
 	ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);
 
-	if (params->nelem_hint)
-		size = rounded_hashtable_size(&ht->p);
+	size = rounded_hashtable_size(&ht->p);
 
 	if (params->locks_mul)
 		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
@@ -1143,13 +1148,14 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 				 void (*free_fn)(void *ptr, void *arg),
 				 void *arg)
 {
-	struct bucket_table *tbl;
+	struct bucket_table *tbl, *next_tbl;
 	unsigned int i;
 
 	cancel_work_sync(&ht->run_work);
 
 	mutex_lock(&ht->mutex);
 	tbl = rht_dereference(ht->tbl, ht);
+restart:
 	if (free_fn) {
 		for (i = 0; i < tbl->size; i++) {
 			struct rhash_head *pos, *next;
@@ -1166,7 +1172,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 		}
 	}
 
+	next_tbl = rht_dereference(tbl->future_tbl, ht);
 	bucket_table_free(tbl);
+	if (next_tbl) {
+		tbl = next_tbl;
+		goto restart;
+	}
 	mutex_unlock(&ht->mutex);
 }
 EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 1642fd507a96..7c6096a71704 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -24,9 +24,6 @@
  **/
 struct scatterlist *sg_next(struct scatterlist *sg)
 {
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sg->sg_magic != SG_MAGIC);
-#endif
 	if (sg_is_last(sg))
 		return NULL;
 
@@ -111,10 +108,7 @@ struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
 	for_each_sg(sgl, sg, nents, i)
 		ret = sg;
 
-#ifdef CONFIG_DEBUG_SG
-	BUG_ON(sgl[0].sg_magic != SG_MAGIC);
 	BUG_ON(!sg_is_last(ret));
-#endif
 	return ret;
 }
 EXPORT_SYMBOL(sg_last);
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 60aedc879361..08d3d59dca17 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5282,21 +5282,31 @@ static struct bpf_test tests[] = {
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Ctx heavy transformations",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ },
 		{
 			{  1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
 			{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
 		},
 		.fill_helper = bpf_fill_maxinsns6,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Call heavy transformations",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC | FLAG_NO_DATA,
+#endif
 		{ },
 		{ { 1, 0 }, { 10, 0 } },
 		.fill_helper = bpf_fill_maxinsns7,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Jump heavy test",
@@ -5347,18 +5357,28 @@ static struct bpf_test tests[] = {
 	{
 		"BPF_MAXINSNS: exec all MSH",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ 0xfa, 0xfb, 0xfc, 0xfd, },
 		{ { 4, 0xababab83 } },
 		.fill_helper = bpf_fill_maxinsns13,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{
 		"BPF_MAXINSNS: ld_abs+get_processor_id",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ },
 		{ { 1, 0xbee } },
 		.fill_helper = bpf_fill_ld_abs_get_processor_id,
+		.expected_errcode = -ENOTSUPP,
 	},
 	/*
 	 * LD_IND / LD_ABS on fragmented SKBs
diff --git a/lib/test_printf.c b/lib/test_printf.c
index b2aa8f514844..cea592f402ed 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -260,13 +260,6 @@ plain(void)
 {
 	int err;
 
-	/*
-	 * Make sure crng is ready. Otherwise we get "(ptrval)" instead
-	 * of a hashed address when printing '%p' in plain_hash() and
-	 * plain_format().
-	 */
-	wait_for_random_bytes();
-
 	err = plain_hash();
 	if (err) {
 		pr_warn("plain 'p' does not appear to be hashed\n");