From ad3d6c7263e368abdc151e1cc13dc78aa39cc7a7 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 7 Nov 2017 14:57:46 -0500
Subject: xarray: Add XArray load operation

The xa_load function brings with it a lot of infrastructure; xa_empty(),
xa_is_err(), and large chunks of the XArray advanced API that are used
to implement xa_load.

As the test-suite demonstrates, it is possible to use the XArray functions
on a radix tree.  The radix tree functions depend on the GFP flags being
stored in the root of the tree, so it's not possible to use the radix
tree functions on an XArray.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/include/linux/kernel.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/include')

diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 0ad884452c5c..6935ef94e77a 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -70,6 +70,7 @@
 #define BUG_ON(cond) assert(!(cond))
 #endif
 #endif
+#define BUG()	BUG_ON(1)
 
 #if __BYTE_ORDER == __BIG_ENDIAN
 #define cpu_to_le16 bswap_16
-- 
cgit v1.2.3


From 9b89a0355144685a787b0dc5bcf7bdd6f2d02968 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 10 Nov 2017 09:34:31 -0500
Subject: xarray: Add XArray marks

XArray marks are like the radix tree tags, only slightly more strongly
typed.  They are renamed in order to distinguish them from tagged
pointers.  This commit adds the basic get/set/clear operations.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/xarray.h                        |  63 +++++++
 lib/test_xarray.c                             |  34 ++++
 lib/xarray.c                                  | 232 +++++++++++++++++++++++++-
 tools/include/asm-generic/bitops.h            |   1 +
 tools/include/asm-generic/bitops/atomic.h     |   9 -
 tools/include/asm-generic/bitops/non-atomic.h | 109 ++++++++++++
 tools/include/linux/spinlock.h                |  10 +-
 7 files changed, 445 insertions(+), 13 deletions(-)
 create mode 100644 tools/include/asm-generic/bitops/non-atomic.h

(limited to 'tools/include')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index a0df8217068c..2de504ae9ba4 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -11,6 +11,7 @@
 
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/gfp.h>
 #include <linux/kconfig.h>
 #include <linux/kernel.h>
 #include <linux/rcupdate.h>
@@ -197,6 +198,20 @@ static inline int xa_err(void *entry)
 	return 0;
 }
 
+typedef unsigned __bitwise xa_mark_t;
+#define XA_MARK_0		((__force xa_mark_t)0U)
+#define XA_MARK_1		((__force xa_mark_t)1U)
+#define XA_MARK_2		((__force xa_mark_t)2U)
+#define XA_PRESENT		((__force xa_mark_t)8U)
+#define XA_MARK_MAX		XA_MARK_2
+
+/*
+ * Values for xa_flags.  The radix tree stores its GFP flags in the xa_flags,
+ * and we remain compatible with that.
+ */
+#define XA_FLAGS_MARK(mark)	((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
+						(__force unsigned)(mark)))
+
 /**
  * struct xarray - The anchor of the XArray.
  * @xa_lock: Lock that protects the contents of the XArray.
@@ -252,6 +267,9 @@ struct xarray {
 
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
+bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t);
+void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
+void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
 
 /**
  * xa_init() - Initialise an empty XArray.
@@ -278,6 +296,19 @@ static inline bool xa_empty(const struct xarray *xa)
 	return xa->xa_head == NULL;
 }
 
+/**
+ * xa_marked() - Inquire whether any entry in this array has a mark set
+ * @xa: Array
+ * @mark: Mark value
+ *
+ * Context: Any context.
+ * Return: %true if any entry has this mark set.
+ */
+static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
+{
+	return xa->xa_flags & XA_FLAGS_MARK(mark);
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -290,6 +321,12 @@ static inline bool xa_empty(const struct xarray *xa)
 #define xa_unlock_irqrestore(xa, flags) \
 				spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
+/*
+ * Versions of the normal API which require the caller to hold the xa_lock.
+ */
+void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
+void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
+
 /* Everything below here is the Advanced API.  Proceed with caution. */
 
 /*
@@ -388,6 +425,22 @@ static inline void *xa_entry_locked(const struct xarray *xa,
 						lockdep_is_held(&xa->xa_lock));
 }
 
+/* Private */
+static inline struct xa_node *xa_parent(const struct xarray *xa,
+					const struct xa_node *node)
+{
+	return rcu_dereference_check(node->parent,
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline struct xa_node *xa_parent_locked(const struct xarray *xa,
+					const struct xa_node *node)
+{
+	return rcu_dereference_protected(node->parent,
+						lockdep_is_held(&xa->xa_lock));
+}
+
 /* Private */
 static inline struct xa_node *xa_to_node(const void *entry)
 {
@@ -588,6 +641,12 @@ static inline bool xas_valid(const struct xa_state *xas)
 	return !xas_invalid(xas);
 }
 
+/* True if the pointer is something other than a node */
+static inline bool xas_not_node(struct xa_node *node)
+{
+	return ((unsigned long)node & 3) || !node;
+}
+
 /**
  * xas_reset() - Reset an XArray operation state.
  * @xas: XArray operation state.
@@ -625,6 +684,10 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry)
 
 void *xas_load(struct xa_state *);
 
+bool xas_get_mark(const struct xa_state *, xa_mark_t);
+void xas_set_mark(const struct xa_state *, xa_mark_t);
+void xas_clear_mark(const struct xa_state *, xa_mark_t);
+
 /**
  * xas_reload() - Refetch an entry from the xarray.
  * @xas: XArray operation state.
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index a7248b87617f..f8b0e9ba80a4 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -67,11 +67,45 @@ static noinline void check_xa_load(struct xarray *xa)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
+{
+	/* NULL elements have no marks set */
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+
+	/* Storing a pointer will not make a mark appear */
+	XA_BUG_ON(xa, xa_store_index(xa, index, GFP_KERNEL) != NULL);
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
+
+	/* Setting one mark will not set another mark */
+	XA_BUG_ON(xa, xa_get_mark(xa, index + 1, XA_MARK_0));
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_1));
+
+	/* Storing NULL clears marks, and they can't be set again */
+	xa_erase_index(xa, index);
+	XA_BUG_ON(xa, !xa_empty(xa));
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+}
+
+static noinline void check_xa_mark(struct xarray *xa)
+{
+	unsigned long index;
+
+	for (index = 0; index < 16384; index += 4)
+		check_xa_mark_1(xa, index);
+}
+
 static RADIX_TREE(array, GFP_KERNEL);
 
 static int xarray_checks(void)
 {
 	check_xa_load(&array);
+	check_xa_mark(&array);
 
 	printk("XArray: %u of %u tests passed\n", tests_passed, tests_run);
 	return (tests_run == tests_passed) ? 0 : -EINVAL;
diff --git a/lib/xarray.c b/lib/xarray.c
index 19cfcbc69a68..aa86c47e532f 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -5,6 +5,7 @@
  * Author: Matthew Wilcox <willy@infradead.org>
  */
 
+#include <linux/bitmap.h>
 #include <linux/export.h>
 #include <linux/xarray.h>
 
@@ -24,6 +25,48 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark)
+{
+	if (!(xa->xa_flags & XA_FLAGS_MARK(mark)))
+		xa->xa_flags |= XA_FLAGS_MARK(mark);
+}
+
+static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark)
+{
+	if (xa->xa_flags & XA_FLAGS_MARK(mark))
+		xa->xa_flags &= ~(XA_FLAGS_MARK(mark));
+}
+
+static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark)
+{
+	return node->marks[(__force unsigned)mark];
+}
+
+static inline bool node_get_mark(struct xa_node *node,
+		unsigned int offset, xa_mark_t mark)
+{
+	return test_bit(offset, node_marks(node, mark));
+}
+
+/* returns true if the bit was set */
+static inline bool node_set_mark(struct xa_node *node, unsigned int offset,
+				xa_mark_t mark)
+{
+	return __test_and_set_bit(offset, node_marks(node, mark));
+}
+
+/* returns true if the bit was set */
+static inline bool node_clear_mark(struct xa_node *node, unsigned int offset,
+				xa_mark_t mark)
+{
+	return __test_and_clear_bit(offset, node_marks(node, mark));
+}
+
+static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark)
+{
+	return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE);
+}
+
 /* extracts the offset within this node from the index */
 static unsigned int get_offset(unsigned long index, struct xa_node *node)
 {
@@ -118,6 +161,85 @@ void *xas_load(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_load);
 
+/**
+ * xas_get_mark() - Returns the state of this mark.
+ * @xas: XArray operation state.
+ * @mark: Mark number.
+ *
+ * Return: true if the mark is set, false if the mark is clear or @xas
+ * is in an error state.
+ */
+bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark)
+{
+	if (xas_invalid(xas))
+		return false;
+	if (!xas->xa_node)
+		return xa_marked(xas->xa, mark);
+	return node_get_mark(xas->xa_node, xas->xa_offset, mark);
+}
+EXPORT_SYMBOL_GPL(xas_get_mark);
+
+/**
+ * xas_set_mark() - Sets the mark on this entry and its parents.
+ * @xas: XArray operation state.
+ * @mark: Mark number.
+ *
+ * Sets the specified mark on this entry, and walks up the tree setting it
+ * on all the ancestor entries.  Does nothing if @xas has not been walked to
+ * an entry, or is in an error state.
+ */
+void xas_set_mark(const struct xa_state *xas, xa_mark_t mark)
+{
+	struct xa_node *node = xas->xa_node;
+	unsigned int offset = xas->xa_offset;
+
+	if (xas_invalid(xas))
+		return;
+
+	while (node) {
+		if (node_set_mark(node, offset, mark))
+			return;
+		offset = node->offset;
+		node = xa_parent_locked(xas->xa, node);
+	}
+
+	if (!xa_marked(xas->xa, mark))
+		xa_mark_set(xas->xa, mark);
+}
+EXPORT_SYMBOL_GPL(xas_set_mark);
+
+/**
+ * xas_clear_mark() - Clears the mark on this entry and its parents.
+ * @xas: XArray operation state.
+ * @mark: Mark number.
+ *
+ * Clears the specified mark on this entry, and walks back to the head
+ * attempting to clear it on all the ancestor entries.  Does nothing if
+ * @xas has not been walked to an entry, or is in an error state.
+ */
+void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark)
+{
+	struct xa_node *node = xas->xa_node;
+	unsigned int offset = xas->xa_offset;
+
+	if (xas_invalid(xas))
+		return;
+
+	while (node) {
+		if (!node_clear_mark(node, offset, mark))
+			return;
+		if (node_any_mark(node, mark))
+			return;
+
+		offset = node->offset;
+		node = xa_parent_locked(xas->xa, node);
+	}
+
+	if (xa_marked(xas->xa, mark))
+		xa_mark_clear(xas->xa, mark);
+}
+EXPORT_SYMBOL_GPL(xas_clear_mark);
+
 /**
  * xa_init_flags() - Initialise an empty XArray with flags.
  * @xa: XArray.
@@ -160,6 +282,112 @@ void *xa_load(struct xarray *xa, unsigned long index)
 }
 EXPORT_SYMBOL(xa_load);
 
+/**
+ * __xa_set_mark() - Set this mark on this entry while locked.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Attempting to set a mark on a NULL entry does not succeed.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.
+ */
+void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	XA_STATE(xas, xa, index);
+	void *entry = xas_load(&xas);
+
+	if (entry)
+		xas_set_mark(&xas, mark);
+}
+EXPORT_SYMBOL_GPL(__xa_set_mark);
+
+/**
+ * __xa_clear_mark() - Clear this mark on this entry while locked.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.
+ */
+void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	XA_STATE(xas, xa, index);
+	void *entry = xas_load(&xas);
+
+	if (entry)
+		xas_clear_mark(&xas, mark);
+}
+EXPORT_SYMBOL_GPL(__xa_clear_mark);
+
+/**
+ * xa_get_mark() - Inquire whether this mark is set on this entry.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * This function uses the RCU read lock, so the result may be out of date
+ * by the time it returns.  If you need the result to be stable, use a lock.
+ *
+ * Context: Any context.  Takes and releases the RCU lock.
+ * Return: True if the entry at @index has this mark set, false if it doesn't.
+ */
+bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+
+	rcu_read_lock();
+	entry = xas_start(&xas);
+	while (xas_get_mark(&xas, mark)) {
+		if (!xa_is_node(entry))
+			goto found;
+		entry = xas_descend(&xas, xa_to_node(entry));
+	}
+	rcu_read_unlock();
+	return false;
+ found:
+	rcu_read_unlock();
+	return true;
+}
+EXPORT_SYMBOL(xa_get_mark);
+
+/**
+ * xa_set_mark() - Set this mark on this entry.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Attempting to set a mark on a NULL entry does not succeed.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.
+ */
+void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	xa_lock(xa);
+	__xa_set_mark(xa, index, mark);
+	xa_unlock(xa);
+}
+EXPORT_SYMBOL(xa_set_mark);
+
+/**
+ * xa_clear_mark() - Clear this mark on this entry.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Clearing a mark always succeeds.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.
+ */
+void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	xa_lock(xa);
+	__xa_clear_mark(xa, index, mark);
+	xa_unlock(xa);
+}
+EXPORT_SYMBOL(xa_clear_mark);
+
 #ifdef XA_DEBUG
 void xa_dump_node(const struct xa_node *node)
 {
@@ -230,8 +458,8 @@ void xa_dump(const struct xarray *xa)
 	unsigned int shift = 0;
 
 	pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry,
-			xa->xa_flags, radix_tree_tagged(xa, 0),
-			radix_tree_tagged(xa, 1), radix_tree_tagged(xa, 2));
+			xa->xa_flags, xa_marked(xa, XA_MARK_0),
+			xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2));
 	if (xa_is_node(entry))
 		shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT;
 	xa_dump_entry(entry, 0, shift);
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 9bce3b56b5e7..5d2ab38965cc 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -27,5 +27,6 @@
 #include <asm-generic/bitops/hweight.h>
 
 #include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
 
 #endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 21c41ccd1266..2f6ea28764a7 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -15,13 +15,4 @@ static inline void clear_bit(int nr, unsigned long *addr)
 	addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG));
 }
 
-static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
-{
-	return ((1UL << (nr % __BITS_PER_LONG)) &
-		(((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
-}
-
-#define __set_bit(nr, addr)	set_bit(nr, addr)
-#define __clear_bit(nr, addr)	clear_bit(nr, addr)
-
 #endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h
new file mode 100644
index 000000000000..7e10c4b50c5d
--- /dev/null
+++ b/tools/include/asm-generic/bitops/non-atomic.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <asm/types.h>
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 1738c0391da4..622266b197d0 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -8,8 +8,14 @@
 #define spinlock_t		pthread_mutex_t
 #define DEFINE_SPINLOCK(x)	pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER
 #define __SPIN_LOCK_UNLOCKED(x)	(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER
-#define spin_lock_init(x)      pthread_mutex_init(x, NULL)
-
+#define spin_lock_init(x)	pthread_mutex_init(x, NULL)
+
+#define spin_lock(x)			pthread_mutex_lock(x)
+#define spin_unlock(x)			pthread_mutex_unlock(x)
+#define spin_lock_bh(x)			pthread_mutex_lock(x)
+#define spin_unlock_bh(x)		pthread_mutex_unlock(x)
+#define spin_lock_irq(x)		pthread_mutex_lock(x)
+#define spin_unlock_irq(x)		pthread_mutex_unlock(x)
 #define spin_lock_irqsave(x, f)		(void)f, pthread_mutex_lock(x)
 #define spin_unlock_irqrestore(x, f)	(void)f, pthread_mutex_unlock(x)
 
-- 
cgit v1.2.3


From 58d6ea3085f2e53714810a513c61629f6d2be0a6 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 10 Nov 2017 15:15:08 -0500
Subject: xarray: Add XArray unconditional store operations

xa_store() differs from radix_tree_insert() in that it will overwrite an
existing element in the array rather than returning an error.  This is
the behaviour which most users want, and those that want more complex
behaviour generally want to use the xas family of routines anyway.

For memory allocation, xa_store() will first attempt to request memory
from the slab allocator; if memory is not immediately available, it will
drop the xa_lock and allocate memory, keeping a pointer in the xa_state.
It does not use the per-CPU cache, although those will continue to exist
until all radix tree users are converted to the xarray.

This patch also includes xa_erase() and __xa_erase() for a streamlined
way to store NULL.  Since there is no need to allocate memory in order
to store a NULL in the XArray, we do not need to trouble the user with
deciding what memory allocation flags to use.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/xarray.h                   | 147 ++++++-
 lib/radix-tree.c                         |   4 +-
 lib/test_xarray.c                        | 177 +++++++-
 lib/xarray.c                             | 693 +++++++++++++++++++++++++++++++
 tools/include/linux/bitmap.h             |   1 +
 tools/include/linux/spinlock.h           |   2 +
 tools/testing/radix-tree/Makefile        |   2 +-
 tools/testing/radix-tree/bitmap.c        |  23 +
 tools/testing/radix-tree/linux/kernel.h  |   4 +
 tools/testing/radix-tree/linux/lockdep.h |  11 +
 10 files changed, 1055 insertions(+), 9 deletions(-)
 create mode 100644 tools/testing/radix-tree/bitmap.c
 create mode 100644 tools/testing/radix-tree/linux/lockdep.h

(limited to 'tools/include')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 2de504ae9ba4..15eab63286ed 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -205,10 +205,17 @@ typedef unsigned __bitwise xa_mark_t;
 #define XA_PRESENT		((__force xa_mark_t)8U)
 #define XA_MARK_MAX		XA_MARK_2
 
+enum xa_lock_type {
+	XA_LOCK_IRQ = 1,
+	XA_LOCK_BH = 2,
+};
+
 /*
  * Values for xa_flags.  The radix tree stores its GFP flags in the xa_flags,
  * and we remain compatible with that.
  */
+#define XA_FLAGS_LOCK_IRQ	((__force gfp_t)XA_LOCK_IRQ)
+#define XA_FLAGS_LOCK_BH	((__force gfp_t)XA_LOCK_BH)
 #define XA_FLAGS_MARK(mark)	((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
 						(__force unsigned)(mark)))
 
@@ -267,6 +274,7 @@ struct xarray {
 
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
+void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t);
 void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
 void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
@@ -309,6 +317,23 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
 	return xa->xa_flags & XA_FLAGS_MARK(mark);
 }
 
+/**
+ * xa_erase() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase(struct xarray *xa, unsigned long index)
+{
+	return xa_store(xa, index, NULL, 0);
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -322,11 +347,65 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
 				spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
 /*
- * Versions of the normal API which require the caller to hold the xa_lock.
- */
+ * Versions of the normal API which require the caller to hold the
+ * xa_lock.  If the GFP flags allow it, they will drop the lock to
+ * allocate memory, then reacquire it afterwards.  These functions
+ * may also re-enable interrupts if the XArray flags indicate the
+ * locking should be interrupt safe.
+ */
+void *__xa_erase(struct xarray *, unsigned long index);
+void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
 void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
 
+/**
+ * xa_erase_bh() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock while
+ * disabling softirqs.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase_bh(struct xarray *xa, unsigned long index)
+{
+	void *entry;
+
+	xa_lock_bh(xa);
+	entry = __xa_erase(xa, index);
+	xa_unlock_bh(xa);
+
+	return entry;
+}
+
+/**
+ * xa_erase_irq() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock while
+ * disabling interrupts.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase_irq(struct xarray *xa, unsigned long index)
+{
+	void *entry;
+
+	xa_lock_irq(xa);
+	entry = __xa_erase(xa, index);
+	xa_unlock_irq(xa);
+
+	return entry;
+}
+
 /* Everything below here is the Advanced API.  Proceed with caution. */
 
 /*
@@ -441,6 +520,12 @@ static inline struct xa_node *xa_parent_locked(const struct xarray *xa,
 						lockdep_is_held(&xa->xa_lock));
 }
 
+/* Private */
+static inline void *xa_mk_node(const struct xa_node *node)
+{
+	return (void *)((unsigned long)node | 2);
+}
+
 /* Private */
 static inline struct xa_node *xa_to_node(const void *entry)
 {
@@ -647,6 +732,12 @@ static inline bool xas_not_node(struct xa_node *node)
 	return ((unsigned long)node & 3) || !node;
 }
 
+/* True if the node represents head-of-tree, RESTART or BOUNDS */
+static inline bool xas_top(struct xa_node *node)
+{
+	return node <= XAS_RESTART;
+}
+
 /**
  * xas_reset() - Reset an XArray operation state.
  * @xas: XArray operation state.
@@ -683,10 +774,14 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry)
 }
 
 void *xas_load(struct xa_state *);
+void *xas_store(struct xa_state *, void *entry);
 
 bool xas_get_mark(const struct xa_state *, xa_mark_t);
 void xas_set_mark(const struct xa_state *, xa_mark_t);
 void xas_clear_mark(const struct xa_state *, xa_mark_t);
+void xas_init_marks(const struct xa_state *);
+
+bool xas_nomem(struct xa_state *, gfp_t);
 
 /**
  * xas_reload() - Refetch an entry from the xarray.
@@ -711,4 +806,52 @@ static inline void *xas_reload(struct xa_state *xas)
 	return xa_head(xas->xa);
 }
 
+/**
+ * xas_set() - Set up XArray operation state for a different index.
+ * @xas: XArray operation state.
+ * @index: New index into the XArray.
+ *
+ * Move the operation state to refer to a different index.  This will
+ * have the effect of starting a walk from the top; see xas_next()
+ * to move to an adjacent index.
+ */
+static inline void xas_set(struct xa_state *xas, unsigned long index)
+{
+	xas->xa_index = index;
+	xas->xa_node = XAS_RESTART;
+}
+
+/**
+ * xas_set_order() - Set up XArray operation state for a multislot entry.
+ * @xas: XArray operation state.
+ * @index: Target of the operation.
+ * @order: Entry occupies 2^@order indices.
+ */
+static inline void xas_set_order(struct xa_state *xas, unsigned long index,
+					unsigned int order)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0;
+	xas->xa_shift = order - (order % XA_CHUNK_SHIFT);
+	xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+	xas->xa_node = XAS_RESTART;
+#else
+	BUG_ON(order > 0);
+	xas_set(xas, index);
+#endif
+}
+
+/**
+ * xas_set_update() - Set up XArray operation state for a callback.
+ * @xas: XArray operation state.
+ * @update: Function to call when updating a node.
+ *
+ * The XArray can notify a caller after it has updated an xa_node.
+ * This is advanced functionality and is only needed by the page cache.
+ */
+static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update)
+{
+	xas->xa_update = update;
+}
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index b8e961428484..3479d93c32b9 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -47,7 +47,7 @@ static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly;
 /*
  * Radix tree node cache.
  */
-static struct kmem_cache *radix_tree_node_cachep;
+struct kmem_cache *radix_tree_node_cachep;
 
 /*
  * The radix tree is variable-height, so an insert operation not only has
@@ -365,7 +365,7 @@ out:
 	return ret;
 }
 
-static void radix_tree_node_rcu_free(struct rcu_head *head)
+void radix_tree_node_rcu_free(struct rcu_head *head)
 {
 	struct radix_tree_node *node =
 			container_of(head, struct radix_tree_node, rcu_head);
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index f8b0e9ba80a4..b711030fbc32 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -30,13 +30,49 @@ void xa_dump(const struct xarray *xa) { }
 
 static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp)
 {
-	radix_tree_insert(xa, index, xa_mk_value(index));
-	return NULL;
+	return xa_store(xa, index, xa_mk_value(index & LONG_MAX), gfp);
 }
 
 static void xa_erase_index(struct xarray *xa, unsigned long index)
 {
-	radix_tree_delete(xa, index);
+	XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_value(index & LONG_MAX));
+	XA_BUG_ON(xa, xa_load(xa, index) != NULL);
+}
+
+/*
+ * If anyone needs this, please move it to xarray.c.  We have no current
+ * users outside the test suite because all current multislot users want
+ * to use the advanced API.
+ */
+static void *xa_store_order(struct xarray *xa, unsigned long index,
+		unsigned order, void *entry, gfp_t gfp)
+{
+	XA_STATE_ORDER(xas, xa, index, order);
+	void *curr;
+
+	do {
+		xas_lock(&xas);
+		curr = xas_store(&xas, entry);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, gfp));
+
+	return curr;
+}
+
+static noinline void check_xa_err(struct xarray *xa)
+{
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 0, GFP_NOWAIT)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_erase(xa, 0)) != 0);
+#ifndef __KERNEL__
+	/* The kernel does not fail GFP_NOWAIT allocations */
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM);
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM);
+#endif
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_KERNEL)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_store(xa, 1, xa_mk_value(0), GFP_KERNEL)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_erase(xa, 1)) != 0);
+// kills the test-suite :-(
+//	XA_BUG_ON(xa, xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) != -EINVAL);
 }
 
 static noinline void check_xa_load(struct xarray *xa)
@@ -69,6 +105,9 @@ static noinline void check_xa_load(struct xarray *xa)
 
 static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 {
+	unsigned int order;
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 8 : 1;
+
 	/* NULL elements have no marks set */
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
 	xa_set_mark(xa, index, XA_MARK_0);
@@ -90,6 +129,37 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
 	xa_set_mark(xa, index, XA_MARK_0);
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+
+	/*
+	 * Storing a multi-index entry over entries with marks gives the
+	 * entire entry the union of the marks
+	 */
+	BUG_ON((index % 4) != 0);
+	for (order = 2; order < max_order; order++) {
+		unsigned long base = round_down(index, 1UL << order);
+		unsigned long next = base + (1UL << order);
+		unsigned long i;
+
+		XA_BUG_ON(xa, xa_store_index(xa, index + 1, GFP_KERNEL));
+		xa_set_mark(xa, index + 1, XA_MARK_0);
+		XA_BUG_ON(xa, xa_store_index(xa, index + 2, GFP_KERNEL));
+		xa_set_mark(xa, index + 2, XA_MARK_1);
+		XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL));
+		xa_store_order(xa, index, order, xa_mk_value(index),
+				GFP_KERNEL);
+		for (i = base; i < next; i++) {
+			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0));
+			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_1));
+			XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_2));
+		}
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_0));
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_1));
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_2));
+		xa_erase_index(xa, index);
+		xa_erase_index(xa, next);
+		XA_BUG_ON(xa, !xa_empty(xa));
+	}
+	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
 static noinline void check_xa_mark(struct xarray *xa)
@@ -100,12 +170,111 @@ static noinline void check_xa_mark(struct xarray *xa)
 		check_xa_mark_1(xa, index);
 }
 
-static RADIX_TREE(array, GFP_KERNEL);
+static noinline void check_xa_shrink(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 1);
+	struct xa_node *node;
+
+	XA_BUG_ON(xa, !xa_empty(xa));
+	XA_BUG_ON(xa, xa_store_index(xa, 0, GFP_KERNEL) != NULL);
+	XA_BUG_ON(xa, xa_store_index(xa, 1, GFP_KERNEL) != NULL);
+
+	/*
+	 * Check that erasing the entry at 1 shrinks the tree and properly
+	 * marks the node as being deleted.
+	 */
+	xas_lock(&xas);
+	XA_BUG_ON(xa, xas_load(&xas) != xa_mk_value(1));
+	node = xas.xa_node;
+	XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xas_store(&xas, NULL) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 1) != NULL);
+	XA_BUG_ON(xa, xas.xa_node != XAS_BOUNDS);
+	XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != XA_RETRY_ENTRY);
+	XA_BUG_ON(xa, xas_load(&xas) != NULL);
+	xas_unlock(&xas);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	xa_erase_index(xa, 0);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
+static noinline void check_multi_store(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned long i, j, k;
+	unsigned int max_order = (sizeof(long) == 4) ? 30 : 60;
+
+	/* Loading from any position returns the same value */
+	xa_store_order(xa, 0, 1, xa_mk_value(0), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 2) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 2);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2);
+	rcu_read_unlock();
+
+	/* Storing adjacent to the value does not alter the value */
+	xa_store(xa, 3, xa, GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 2) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 3);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2);
+	rcu_read_unlock();
+
+	/* Overwriting multiple indexes works */
+	xa_store_order(xa, 0, 2, xa_mk_value(1), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 2) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 3) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 4) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 4);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 4);
+	rcu_read_unlock();
+
+	/* We can erase multiple values with a single store */
+	xa_store_order(xa, 0, 63, NULL, GFP_KERNEL);
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	/* Even when the first slot is empty but the others aren't */
+	xa_store_index(xa, 1, GFP_KERNEL);
+	xa_store_index(xa, 2, GFP_KERNEL);
+	xa_store_order(xa, 0, 2, NULL, GFP_KERNEL);
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	for (i = 0; i < max_order; i++) {
+		for (j = 0; j < max_order; j++) {
+			xa_store_order(xa, 0, i, xa_mk_value(i), GFP_KERNEL);
+			xa_store_order(xa, 0, j, xa_mk_value(j), GFP_KERNEL);
+
+			for (k = 0; k < max_order; k++) {
+				void *entry = xa_load(xa, (1UL << k) - 1);
+				if ((i < k) && (j < k))
+					XA_BUG_ON(xa, entry != NULL);
+				else
+					XA_BUG_ON(xa, entry != xa_mk_value(j));
+			}
+
+			xa_erase(xa, 0);
+			XA_BUG_ON(xa, !xa_empty(xa));
+		}
+	}
+#endif
+}
+
+static DEFINE_XARRAY(array);
 
 static int xarray_checks(void)
 {
+	check_xa_err(&array);
 	check_xa_load(&array);
 	check_xa_mark(&array);
+	check_xa_shrink(&array);
+	check_multi_store(&array);
 
 	printk("XArray: %u of %u tests passed\n", tests_passed, tests_run);
 	return (tests_run == tests_passed) ? 0 : -EINVAL;
diff --git a/lib/xarray.c b/lib/xarray.c
index aa86c47e532f..4596a95ed9cd 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -7,6 +7,8 @@
 
 #include <linux/bitmap.h>
 #include <linux/export.h>
+#include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/xarray.h>
 
 /*
@@ -25,6 +27,31 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+static inline unsigned int xa_lock_type(const struct xarray *xa)
+{
+	return (__force unsigned int)xa->xa_flags & 3;
+}
+
+static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type)
+{
+	if (lock_type == XA_LOCK_IRQ)
+		xas_lock_irq(xas);
+	else if (lock_type == XA_LOCK_BH)
+		xas_lock_bh(xas);
+	else
+		xas_lock(xas);
+}
+
+static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type)
+{
+	if (lock_type == XA_LOCK_IRQ)
+		xas_unlock_irq(xas);
+	else if (lock_type == XA_LOCK_BH)
+		xas_unlock_bh(xas);
+	else
+		xas_unlock(xas);
+}
+
 static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark)
 {
 	if (!(xa->xa_flags & XA_FLAGS_MARK(mark)))
@@ -67,6 +94,34 @@ static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark)
 	return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE);
 }
 
+#define mark_inc(mark) do { \
+	mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \
+} while (0)
+
+/*
+ * xas_squash_marks() - Merge all marks to the first entry
+ * @xas: Array operation state.
+ *
+ * Set a mark on the first entry if any entry has it set.  Clear marks on
+ * all sibling entries.
+ */
+static void xas_squash_marks(const struct xa_state *xas)
+{
+	unsigned int mark = 0;
+	unsigned int limit = xas->xa_offset + xas->xa_sibs + 1;
+
+	if (!xas->xa_sibs)
+		return;
+
+	do {
+		unsigned long *marks = xas->xa_node->marks[mark];
+		if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit)
+			continue;
+		__set_bit(xas->xa_offset, marks);
+		bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs);
+	} while (mark++ != (__force unsigned)XA_MARK_MAX);
+}
+
 /* extracts the offset within this node from the index */
 static unsigned int get_offset(unsigned long index, struct xa_node *node)
 {
@@ -161,6 +216,516 @@ void *xas_load(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_load);
 
+/* Move the radix tree node cache here */
+extern struct kmem_cache *radix_tree_node_cachep;
+extern void radix_tree_node_rcu_free(struct rcu_head *head);
+
+#define XA_RCU_FREE	((struct xarray *)1)
+
+static void xa_node_free(struct xa_node *node)
+{
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	node->array = XA_RCU_FREE;
+	call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
+}
+
+/*
+ * xas_destroy() - Free any resources allocated during the XArray operation.
+ * @xas: XArray operation state.
+ *
+ * This function is now internal-only.
+ */
+static void xas_destroy(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_alloc;
+
+	if (!node)
+		return;
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	kmem_cache_free(radix_tree_node_cachep, node);
+	xas->xa_alloc = NULL;
+}
+
+/**
+ * xas_nomem() - Allocate memory if needed.
+ * @xas: XArray operation state.
+ * @gfp: Memory allocation flags.
+ *
+ * If we need to add new nodes to the XArray, we try to allocate memory
+ * with GFP_NOWAIT while holding the lock, which will usually succeed.
+ * If it fails, @xas is flagged as needing memory to continue.  The caller
+ * should drop the lock and call xas_nomem().  If xas_nomem() succeeds,
+ * the caller should retry the operation.
+ *
+ * Forward progress is guaranteed as one node is allocated here and
+ * stored in the xa_state where it will be found by xas_alloc().  More
+ * nodes will likely be found in the slab allocator, but we do not tie
+ * them up here.
+ *
+ * Return: true if memory was needed, and was successfully allocated.
+ */
+bool xas_nomem(struct xa_state *xas, gfp_t gfp)
+{
+	if (xas->xa_node != XA_ERROR(-ENOMEM)) {
+		xas_destroy(xas);
+		return false;
+	}
+	xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+	if (!xas->xa_alloc)
+		return false;
+	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
+	xas->xa_node = XAS_RESTART;
+	return true;
+}
+EXPORT_SYMBOL_GPL(xas_nomem);
+
+/*
+ * __xas_nomem() - Drop locks and allocate memory if needed.
+ * @xas: XArray operation state.
+ * @gfp: Memory allocation flags.
+ *
+ * Internal variant of xas_nomem().
+ *
+ * Return: true if memory was needed, and was successfully allocated.
+ */
+static bool __xas_nomem(struct xa_state *xas, gfp_t gfp)
+	__must_hold(xas->xa->xa_lock)
+{
+	unsigned int lock_type = xa_lock_type(xas->xa);
+
+	if (xas->xa_node != XA_ERROR(-ENOMEM)) {
+		xas_destroy(xas);
+		return false;
+	}
+	if (gfpflags_allow_blocking(gfp)) {
+		xas_unlock_type(xas, lock_type);
+		xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+		xas_lock_type(xas, lock_type);
+	} else {
+		xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+	}
+	if (!xas->xa_alloc)
+		return false;
+	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
+	xas->xa_node = XAS_RESTART;
+	return true;
+}
+
+static void xas_update(struct xa_state *xas, struct xa_node *node)
+{
+	if (xas->xa_update)
+		xas->xa_update(node);
+	else
+		XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+}
+
+static void *xas_alloc(struct xa_state *xas, unsigned int shift)
+{
+	struct xa_node *parent = xas->xa_node;
+	struct xa_node *node = xas->xa_alloc;
+
+	if (xas_invalid(xas))
+		return NULL;
+
+	if (node) {
+		xas->xa_alloc = NULL;
+	} else {
+		node = kmem_cache_alloc(radix_tree_node_cachep,
+					GFP_NOWAIT | __GFP_NOWARN);
+		if (!node) {
+			xas_set_err(xas, -ENOMEM);
+			return NULL;
+		}
+	}
+
+	if (parent) {
+		node->offset = xas->xa_offset;
+		parent->count++;
+		XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE);
+		xas_update(xas, parent);
+	}
+	XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	node->shift = shift;
+	node->count = 0;
+	node->nr_values = 0;
+	RCU_INIT_POINTER(node->parent, xas->xa_node);
+	node->array = xas->xa;
+
+	return node;
+}
+
+/*
+ * Use this to calculate the maximum index that will need to be created
+ * in order to add the entry described by @xas.  Because we cannot store a
+ * multiple-index entry at index 0, the calculation is a little more complex
+ * than you might expect.
+ */
+static unsigned long xas_max(struct xa_state *xas)
+{
+	unsigned long max = xas->xa_index;
+
+#ifdef CONFIG_XARRAY_MULTI
+	if (xas->xa_shift || xas->xa_sibs) {
+		unsigned long mask;
+		mask = (((xas->xa_sibs + 1UL) << xas->xa_shift) - 1);
+		max |= mask;
+		if (mask == max)
+			max++;
+	}
+#endif
+
+	return max;
+}
+
+/* The maximum index that can be contained in the array without expanding it */
+static unsigned long max_index(void *entry)
+{
+	if (!xa_is_node(entry))
+		return 0;
+	return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1;
+}
+
+static void xas_shrink(struct xa_state *xas)
+{
+	struct xarray *xa = xas->xa;
+	struct xa_node *node = xas->xa_node;
+
+	for (;;) {
+		void *entry;
+
+		XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+		if (node->count != 1)
+			break;
+		entry = xa_entry_locked(xa, node, 0);
+		if (!entry)
+			break;
+		if (!xa_is_node(entry) && node->shift)
+			break;
+		xas->xa_node = XAS_BOUNDS;
+
+		RCU_INIT_POINTER(xa->xa_head, entry);
+
+		node->count = 0;
+		node->nr_values = 0;
+		if (!xa_is_node(entry))
+			RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY);
+		xas_update(xas, node);
+		xa_node_free(node);
+		if (!xa_is_node(entry))
+			break;
+		node = xa_to_node(entry);
+		node->parent = NULL;
+	}
+}
+
+/*
+ * xas_delete_node() - Attempt to delete an xa_node
+ * @xas: Array operation state.
+ *
+ * Attempts to delete the @xas->xa_node.  This will fail if xa->node has
+ * a non-zero reference count.
+ */
+static void xas_delete_node(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_node;
+
+	for (;;) {
+		struct xa_node *parent;
+
+		XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+		if (node->count)
+			break;
+
+		parent = xa_parent_locked(xas->xa, node);
+		xas->xa_node = parent;
+		xas->xa_offset = node->offset;
+		xa_node_free(node);
+
+		if (!parent) {
+			xas->xa->xa_head = NULL;
+			xas->xa_node = XAS_BOUNDS;
+			return;
+		}
+
+		parent->slots[xas->xa_offset] = NULL;
+		parent->count--;
+		XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE);
+		node = parent;
+		xas_update(xas, node);
+	}
+
+	if (!node->parent)
+		xas_shrink(xas);
+}
+
+/**
+ * xas_free_nodes() - Free this node and all nodes that it references
+ * @xas: Array operation state.
+ * @top: Node to free
+ *
+ * This node has been removed from the tree.  We must now free it and all
+ * of its subnodes.  There may be RCU walkers with references into the tree,
+ * so we must replace all entries with retry markers.
+ */
+static void xas_free_nodes(struct xa_state *xas, struct xa_node *top)
+{
+	unsigned int offset = 0;
+	struct xa_node *node = top;
+
+	for (;;) {
+		void *entry = xa_entry_locked(xas->xa, node, offset);
+
+		if (xa_is_node(entry)) {
+			node = xa_to_node(entry);
+			offset = 0;
+			continue;
+		}
+		if (entry)
+			RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY);
+		offset++;
+		while (offset == XA_CHUNK_SIZE) {
+			struct xa_node *parent;
+
+			parent = xa_parent_locked(xas->xa, node);
+			offset = node->offset + 1;
+			node->count = 0;
+			node->nr_values = 0;
+			xas_update(xas, node);
+			xa_node_free(node);
+			if (node == top)
+				return;
+			node = parent;
+		}
+	}
+}
+
+/*
+ * xas_expand adds nodes to the head of the tree until it has reached
+ * sufficient height to be able to contain @xas->xa_index
+ */
+static int xas_expand(struct xa_state *xas, void *head)
+{
+	struct xarray *xa = xas->xa;
+	struct xa_node *node = NULL;
+	unsigned int shift = 0;
+	unsigned long max = xas_max(xas);
+
+	if (!head) {
+		if (max == 0)
+			return 0;
+		while ((max >> shift) >= XA_CHUNK_SIZE)
+			shift += XA_CHUNK_SHIFT;
+		return shift + XA_CHUNK_SHIFT;
+	} else if (xa_is_node(head)) {
+		node = xa_to_node(head);
+		shift = node->shift + XA_CHUNK_SHIFT;
+	}
+	xas->xa_node = NULL;
+
+	while (max > max_index(head)) {
+		xa_mark_t mark = 0;
+
+		XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
+		node = xas_alloc(xas, shift);
+		if (!node)
+			return -ENOMEM;
+
+		node->count = 1;
+		if (xa_is_value(head))
+			node->nr_values = 1;
+		RCU_INIT_POINTER(node->slots[0], head);
+
+		/* Propagate the aggregated mark info to the new child */
+		for (;;) {
+			if (xa_marked(xa, mark))
+				node_set_mark(node, 0, mark);
+			if (mark == XA_MARK_MAX)
+				break;
+			mark_inc(mark);
+		}
+
+		/*
+		 * Now that the new node is fully initialised, we can add
+		 * it to the tree
+		 */
+		if (xa_is_node(head)) {
+			xa_to_node(head)->offset = 0;
+			rcu_assign_pointer(xa_to_node(head)->parent, node);
+		}
+		head = xa_mk_node(node);
+		rcu_assign_pointer(xa->xa_head, head);
+		xas_update(xas, node);
+
+		shift += XA_CHUNK_SHIFT;
+	}
+
+	xas->xa_node = node;
+	return shift;
+}
+
+/*
+ * xas_create() - Create a slot to store an entry in.
+ * @xas: XArray operation state.
+ *
+ * Most users will not need to call this function directly, as it is called
+ * by xas_store().  It is useful for doing conditional store operations
+ * (see the xa_cmpxchg() implementation for an example).
+ *
+ * Return: If the slot already existed, returns the contents of this slot.
+ * If the slot was newly created, returns NULL.  If it failed to create the
+ * slot, returns NULL and indicates the error in @xas.
+ */
+static void *xas_create(struct xa_state *xas)
+{
+	struct xarray *xa = xas->xa;
+	void *entry;
+	void __rcu **slot;
+	struct xa_node *node = xas->xa_node;
+	int shift;
+	unsigned int order = xas->xa_shift;
+
+	if (xas_top(node)) {
+		entry = xa_head_locked(xa);
+		xas->xa_node = NULL;
+		shift = xas_expand(xas, entry);
+		if (shift < 0)
+			return NULL;
+		entry = xa_head_locked(xa);
+		slot = &xa->xa_head;
+	} else if (xas_error(xas)) {
+		return NULL;
+	} else if (node) {
+		unsigned int offset = xas->xa_offset;
+
+		shift = node->shift;
+		entry = xa_entry_locked(xa, node, offset);
+		slot = &node->slots[offset];
+	} else {
+		shift = 0;
+		entry = xa_head_locked(xa);
+		slot = &xa->xa_head;
+	}
+
+	while (shift > order) {
+		shift -= XA_CHUNK_SHIFT;
+		if (!entry) {
+			node = xas_alloc(xas, shift);
+			if (!node)
+				break;
+			rcu_assign_pointer(*slot, xa_mk_node(node));
+		} else if (xa_is_node(entry)) {
+			node = xa_to_node(entry);
+		} else {
+			break;
+		}
+		entry = xas_descend(xas, node);
+		slot = &node->slots[xas->xa_offset];
+	}
+
+	return entry;
+}
+
+static void update_node(struct xa_state *xas, struct xa_node *node,
+		int count, int values)
+{
+	if (!node || (!count && !values))
+		return;
+
+	node->count += count;
+	node->nr_values += values;
+	XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+	XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE);
+	xas_update(xas, node);
+	if (count < 0)
+		xas_delete_node(xas);
+}
+
+/**
+ * xas_store() - Store this entry in the XArray.
+ * @xas: XArray operation state.
+ * @entry: New entry.
+ *
+ * If @xas is operating on a multi-index entry, the entry returned by this
+ * function is essentially meaningless (it may be an internal entry or it
+ * may be %NULL, even if there are non-NULL entries at some of the indices
+ * covered by the range).  This is not a problem for any current users,
+ * and can be changed if needed.
+ *
+ * Return: The old entry at this index.
+ */
+void *xas_store(struct xa_state *xas, void *entry)
+{
+	struct xa_node *node;
+	void __rcu **slot = &xas->xa->xa_head;
+	unsigned int offset, max;
+	int count = 0;
+	int values = 0;
+	void *first, *next;
+	bool value = xa_is_value(entry);
+
+	if (entry)
+		first = xas_create(xas);
+	else
+		first = xas_load(xas);
+
+	if (xas_invalid(xas))
+		return first;
+	node = xas->xa_node;
+	if (node && (xas->xa_shift < node->shift))
+		xas->xa_sibs = 0;
+	if ((first == entry) && !xas->xa_sibs)
+		return first;
+
+	next = first;
+	offset = xas->xa_offset;
+	max = xas->xa_offset + xas->xa_sibs;
+	if (node) {
+		slot = &node->slots[offset];
+		if (xas->xa_sibs)
+			xas_squash_marks(xas);
+	}
+	if (!entry)
+		xas_init_marks(xas);
+
+	for (;;) {
+		/*
+		 * Must clear the marks before setting the entry to NULL,
+		 * otherwise xas_for_each_marked may find a NULL entry and
+		 * stop early.  rcu_assign_pointer contains a release barrier
+		 * so the mark clearing will appear to happen before the
+		 * entry is set to NULL.
+		 */
+		rcu_assign_pointer(*slot, entry);
+		if (xa_is_node(next))
+			xas_free_nodes(xas, xa_to_node(next));
+		if (!node)
+			break;
+		count += !next - !entry;
+		values += !xa_is_value(first) - !value;
+		if (entry) {
+			if (offset == max)
+				break;
+			if (!xa_is_sibling(entry))
+				entry = xa_mk_sibling(xas->xa_offset);
+		} else {
+			if (offset == XA_CHUNK_MASK)
+				break;
+		}
+		next = xa_entry_locked(xas->xa, node, ++offset);
+		if (!xa_is_sibling(next)) {
+			if (!entry && (offset > max))
+				break;
+			first = next;
+		}
+		slot++;
+	}
+
+	update_node(xas, node, count, values);
+	return first;
+}
+EXPORT_SYMBOL_GPL(xas_store);
+
 /**
  * xas_get_mark() - Returns the state of this mark.
  * @xas: XArray operation state.
@@ -240,6 +805,30 @@ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark)
 }
 EXPORT_SYMBOL_GPL(xas_clear_mark);
 
+/**
+ * xas_init_marks() - Initialise all marks for the entry
+ * @xas: Array operations state.
+ *
+ * Initialise all marks for the entry specified by @xas.  If we're tracking
+ * free entries with a mark, we need to set it on all entries.  All other
+ * marks are cleared.
+ *
+ * This implementation is not as efficient as it could be; we may walk
+ * up the tree multiple times.
+ */
+void xas_init_marks(const struct xa_state *xas)
+{
+	xa_mark_t mark = 0;
+
+	for (;;) {
+		xas_clear_mark(xas, mark);
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
+}
+EXPORT_SYMBOL_GPL(xas_init_marks);
+
 /**
  * xa_init_flags() - Initialise an empty XArray with flags.
  * @xa: XArray.
@@ -253,9 +842,19 @@ EXPORT_SYMBOL_GPL(xas_clear_mark);
  */
 void xa_init_flags(struct xarray *xa, gfp_t flags)
 {
+	unsigned int lock_type;
+	static struct lock_class_key xa_lock_irq;
+	static struct lock_class_key xa_lock_bh;
+
 	spin_lock_init(&xa->xa_lock);
 	xa->xa_flags = flags;
 	xa->xa_head = NULL;
+
+	lock_type = xa_lock_type(xa);
+	if (lock_type == XA_LOCK_IRQ)
+		lockdep_set_class(&xa->xa_lock, &xa_lock_irq);
+	else if (lock_type == XA_LOCK_BH)
+		lockdep_set_class(&xa->xa_lock, &xa_lock_bh);
 }
 EXPORT_SYMBOL(xa_init_flags);
 
@@ -282,6 +881,100 @@ void *xa_load(struct xarray *xa, unsigned long index)
 }
 EXPORT_SYMBOL(xa_load);
 
+static void *xas_result(struct xa_state *xas, void *curr)
+{
+	XA_NODE_BUG_ON(xas->xa_node, xa_is_internal(curr));
+	if (xas_error(xas))
+		curr = xas->xa_node;
+	return curr;
+}
+
+/**
+ * __xa_erase() - Erase this entry from the XArray while locked.
+ * @xa: XArray.
+ * @index: Index into array.
+ *
+ * If the entry at this index is a multi-index entry then all indices will
+ * be erased, and the entry will no longer be a multi-index entry.
+ * This function expects the xa_lock to be held on entry.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.  May
+ * release and reacquire xa_lock if @gfp flags permit.
+ * Return: The old entry at this index.
+ */
+void *__xa_erase(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	return xas_result(&xas, xas_store(&xas, NULL));
+}
+EXPORT_SYMBOL_GPL(__xa_erase);
+
+/**
+ * xa_store() - Store this entry in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * After this function returns, loads from this index will return @entry.
+ * Storing into an existing multislot entry updates the entry of every index.
+ * The marks associated with @index are unaffected unless @entry is %NULL.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.  May sleep
+ * if the @gfp flags permit.
+ * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry
+ * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation
+ * failed.
+ */
+void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
+{
+	XA_STATE(xas, xa, index);
+	void *curr;
+
+	if (WARN_ON_ONCE(xa_is_internal(entry)))
+		return XA_ERROR(-EINVAL);
+
+	do {
+		xas_lock(&xas);
+		curr = xas_store(&xas, entry);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, gfp));
+
+	return xas_result(&xas, curr);
+}
+EXPORT_SYMBOL(xa_store);
+
+/**
+ * __xa_store() - Store this entry in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * You must already be holding the xa_lock when calling this function.
+ * It will drop the lock if needed to allocate memory, and then reacquire
+ * it afterwards.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.  May
+ * release and reacquire xa_lock if @gfp flags permit.
+ * Return: The old entry at this index or xa_err() if an error happened.
+ */
+void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
+{
+	XA_STATE(xas, xa, index);
+	void *curr;
+
+	if (WARN_ON_ONCE(xa_is_internal(entry)))
+		return XA_ERROR(-EINVAL);
+
+	do {
+		curr = xas_store(&xas, entry);
+	} while (__xas_nomem(&xas, gfp));
+
+	return xas_result(&xas, curr);
+}
+EXPORT_SYMBOL(__xa_store);
+
 /**
  * __xa_set_mark() - Set this mark on this entry while locked.
  * @xa: XArray.
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index e63662db131b..05dca5c203f3 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -15,6 +15,7 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
 int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int bits);
+void bitmap_clear(unsigned long *map, unsigned int start, int len);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 622266b197d0..c934572d935c 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -37,4 +37,6 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
 	return true;
 }
 
+#include <linux/lockdep.h>
+
 #endif
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 1379f1d78d0b..acf1afa01c5b 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder xarray
-CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o
+CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
 
diff --git a/tools/testing/radix-tree/bitmap.c b/tools/testing/radix-tree/bitmap.c
new file mode 100644
index 000000000000..66ec4a24a203
--- /dev/null
+++ b/tools/testing/radix-tree/bitmap.c
@@ -0,0 +1,23 @@
+/* lib/bitmap.c pulls in at least two other files. */
+
+#include <linux/bitmap.h>
+
+void bitmap_clear(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 5d06ac75a14d..4568248222ae 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -18,4 +18,8 @@
 #define pr_debug printk
 #define pr_cont printk
 
+#define __acquires(x)
+#define __releases(x)
+#define __must_hold(x)
+
 #endif /* _KERNEL_H */
diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h
new file mode 100644
index 000000000000..565fccdfe6e9
--- /dev/null
+++ b/tools/testing/radix-tree/linux/lockdep.h
@@ -0,0 +1,11 @@
+#ifndef _LINUX_LOCKDEP_H
+#define _LINUX_LOCKDEP_H
+struct lock_class_key {
+	unsigned int a;
+};
+
+static inline void lockdep_set_class(spinlock_t *lock,
+					struct lock_class_key *key)
+{
+}
+#endif /* _LINUX_LOCKDEP_H */
-- 
cgit v1.2.3


From f443f38c5789ece6ebe59ae21c27bf861e61c4e2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 24 Oct 2018 14:31:12 -0300
Subject: tools include uapi: Grab a copy of linux/fs.h

We'll use it to create tables for the 'flags' argument to the 'mount'
and 'umount' syscalls.

Add it to check_headers.sh so that when a new protocol gets added we get
a notification during the build process.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-yacf9jvkwfwg2g95r2us3xb3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h | 393 ++++++++++++++++++++++++++++++++++++++++++
 tools/perf/check-headers.sh   |   1 +
 2 files changed, 394 insertions(+)
 create mode 100644 tools/include/uapi/linux/fs.h

(limited to 'tools/include')

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
new file mode 100644
index 000000000000..73e01918f996
--- /dev/null
+++ b/tools/include/uapi/linux/fs.h
@@ -0,0 +1,393 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
+
+/*
+ * This file has definitions for some important file table structures
+ * and constants and structures used by various generic file system
+ * ioctl's.  Please do not make any changes in this file before
+ * sending patches for review to linux-fsdevel@vger.kernel.org and
+ * linux-api@vger.kernel.org.
+ */
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
+ * the file limit at runtime and only root can increase the per-process
+ * nr_file rlimit, so it's safe to set up a ridiculously high absolute
+ * upper limit on files-per-process.
+ *
+ * Some programs (notably those using select()) may have to be 
+ * recompiled to take full advantage of the new limits..  
+ */
+
+/* Fixed constants first: */
+#undef NR_OPEN
+#define INR_OPEN_CUR 1024	/* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096	/* Hard limit for nfile rlimits */
+
+#define BLOCK_SIZE_BITS 10
+#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+
+#define SEEK_SET	0	/* seek relative to beginning of file */
+#define SEEK_CUR	1	/* seek relative to current file position */
+#define SEEK_END	2	/* seek relative to end of file */
+#define SEEK_DATA	3	/* seek to the next data */
+#define SEEK_HOLE	4	/* seek to the next hole */
+#define SEEK_MAX	SEEK_HOLE
+
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
+
+struct file_clone_range {
+	__s64 src_fd;
+	__u64 src_offset;
+	__u64 src_length;
+	__u64 dest_offset;
+};
+
+struct fstrim_range {
+	__u64 start;
+	__u64 len;
+	__u64 minlen;
+};
+
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME		0
+#define FILE_DEDUPE_RANGE_DIFFERS	1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+	__s64 dest_fd;		/* in - destination file */
+	__u64 dest_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file. */
+	/* status of this dedupe operation:
+	 * < 0 for error
+	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;		/* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+	__u64 src_offset;	/* in - start of extent in source */
+	__u64 src_length;	/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;	/* must be zero */
+	__u32 reserved2;	/* must be zero */
+	struct file_dedupe_range_info info[0];
+};
+
+/* And dynamically-tunable limits and defaults: */
+struct files_stat_struct {
+	unsigned long nr_files;		/* read only */
+	unsigned long nr_free_files;	/* read only */
+	unsigned long max_files;		/* tunable */
+};
+
+struct inodes_stat_t {
+	long nr_inodes;
+	long nr_unused;
+	long dummy[5];		/* padding for sysctl ABI compatibility */
+};
+
+
+#define NR_FILE  8192	/* this can well be larger on a larger system */
+
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+/*
+ * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
+ */
+struct fsxattr {
+	__u32		fsx_xflags;	/* xflags field value (get/set) */
+	__u32		fsx_extsize;	/* extsize field value (get/set)*/
+	__u32		fsx_nextents;	/* nextents field value (get)	*/
+	__u32		fsx_projid;	/* project identifier (get/set) */
+	__u32		fsx_cowextsize;	/* CoW extsize field value (get/set)*/
+	unsigned char	fsx_pad[8];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
+#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
+#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
+#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
+#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
+#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
+#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG	0x00002000	/* do not defragment */
+#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
+#define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
+#define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
+
+/* the read-only stuff doesn't really belong here, but any other place is
+   probably as bad and I don't want to create yet another include file. */
+
+#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
+#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
+#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
+#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
+#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
+#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
+#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
+#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
+#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
+#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
+#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
+#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
+#if 0
+#define BLKPG      _IO(0x12,105)/* See blkpg.h */
+
+/* Some people are morons.  Do not use sizeof! */
+
+#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
+#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
+/* This was here just to show that the number is taken -
+   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
+#endif
+/* A jump here: 108-111 have been used for various private purposes. */
+#define BLKBSZGET  _IOR(0x12,112,size_t)
+#define BLKBSZSET  _IOW(0x12,113,size_t)
+#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
+/*
+ * A jump here: 130-131 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
+
+#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
+#define FIBMAP	   _IO(0x00,1)	/* bmap access */
+#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
+#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
+#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
+#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
+#define FICLONE		_IOW(0x94, 9, int)
+#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
+
+#define FSLABEL_MAX 256	/* Max chars for the interface; each fs may differ */
+
+#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
+#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
+#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
+#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
+#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
+#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
+#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
+
+/*
+ * File system encryption support
+ */
+/* Policy provided via an ioctl on the topmost directory */
+#define FS_KEY_DESCRIPTOR_SIZE	8
+
+#define FS_POLICY_FLAGS_PAD_4		0x00
+#define FS_POLICY_FLAGS_PAD_8		0x01
+#define FS_POLICY_FLAGS_PAD_16		0x02
+#define FS_POLICY_FLAGS_PAD_32		0x03
+#define FS_POLICY_FLAGS_PAD_MASK	0x03
+#define FS_POLICY_FLAGS_VALID		0x03
+
+/* Encryption algorithms */
+#define FS_ENCRYPTION_MODE_INVALID		0
+#define FS_ENCRYPTION_MODE_AES_256_XTS		1
+#define FS_ENCRYPTION_MODE_AES_256_GCM		2
+#define FS_ENCRYPTION_MODE_AES_256_CBC		3
+#define FS_ENCRYPTION_MODE_AES_256_CTS		4
+#define FS_ENCRYPTION_MODE_AES_128_CBC		5
+#define FS_ENCRYPTION_MODE_AES_128_CTS		6
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8
+
+struct fscrypt_policy {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
+
+/* Parameters for passing an encryption key into the kernel keyring */
+#define FS_KEY_DESC_PREFIX		"fscrypt:"
+#define FS_KEY_DESC_PREFIX_SIZE		8
+
+/* Structure that userspace passes to the kernel keyring */
+#define FS_MAX_KEY_SIZE			64
+
+struct fscrypt_key {
+	__u32 mode;
+	__u8 raw[FS_MAX_KEY_SIZE];
+	__u32 size;
+};
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ *
+ * Note: for historical reasons, these flags were originally used and
+ * defined for use by ext2/ext3, and then other file systems started
+ * using these flags so they wouldn't need to write their own version
+ * of chattr/lsattr (which was shipped as part of e2fsprogs).  You
+ * should think twice before trying to use these flags in new
+ * contexts, or trying to assign these flags, since they are used both
+ * as the UAPI and the on-disk encoding for ext2/3/4.  Also, we are
+ * almost out of 32-bit flags.  :-)
+ *
+ * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
+ * XFS to the generic FS level interface.  This uses a structure that
+ * has padding and hence has more room to grow, so it may be more
+ * appropriate for many new use cases.
+ *
+ * Please do not change these flags or interfaces before checking with
+ * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
+ */
+#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
+#define	FS_UNRM_FL			0x00000002 /* Undelete */
+#define	FS_COMPR_FL			0x00000004 /* Compress file */
+#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
+#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL			0x00000040 /* do not dump file */
+#define FS_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL			0x00000100
+#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
+/* End compression flags --- maybe not all used */
+#define FS_ENCRYPT_FL			0x00000800 /* Encrypted file */
+#define FS_BTREE_FL			0x00001000 /* btree format dir */
+#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
+#define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
+#define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
+#define FS_NOCOW_FL			0x00800000 /* Do not cow file */
+#define FS_INLINE_DATA_FL		0x10000000 /* Reserved for ext4 */
+#define FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
+#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+
+
+#define SYNC_FILE_RANGE_WAIT_BEFORE	1
+#define SYNC_FILE_RANGE_WRITE		2
+#define SYNC_FILE_RANGE_WAIT_AFTER	4
+
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+			 RWF_APPEND)
+
+#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c72cc73a6b09..9531f7bd7d9b 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -5,6 +5,7 @@ HEADERS='
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
-- 
cgit v1.2.3


From 733ac4f9935c4b257aff2ec476e6c20665daf6c2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 12:27:37 -0300
Subject: tools include uapi: Update linux/fs.h copy

To silence this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/fs.h' differs from latest version at 'include/uapi/linux/fs.h'
  diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h

Due to just two comments added by:

  Fixes: 578bdaabd015 ("crypto: speck - remove Speck")

So nothing that entails changes in tools/, that so far uses fs.h to
generate the mount and umount syscalls 'flags' argument integer->string
tables with:

  $ tools/perf/trace/beauty/mount_flags.sh
  static const char *mount_flags[] = {
	[4096 ? (ilog2(4096) + 1) : 0] = "BIND",
<SNIP>
	[30 + 1] = "ACTIVE",
	[31 + 1] = "NOUSER",
  };
  $
  # trace -e mount,umount mount --bind /proc /mnt
     1.228 ( 2.581 ms): mount/1068 mount(dev_name: /mnt, dir_name: 0x55f011c354a0, type: 0x55f011c38170, flags: BIND) = 0
  # trace -e mount,umount umount /proc /mnt
  umount: /proc: target is busy.
     1.587 ( 0.010 ms): umount/1070 umount2(name: /proc) = -1 EBUSY Device or resource busy
     1.799 (12.660 ms): umount/1070 umount2(name: /mnt) = 0
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lkml.kernel.org/n/tip-c00bqzclscgah26z2g5zxm73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/include')

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 73e01918f996..a441ea1bfe6d 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -279,8 +279,8 @@ struct fsxattr {
 #define FS_ENCRYPTION_MODE_AES_256_CTS		4
 #define FS_ENCRYPTION_MODE_AES_128_CBC		5
 #define FS_ENCRYPTION_MODE_AES_128_CTS		6
-#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7
-#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
 
 struct fscrypt_policy {
 	__u8 version;
-- 
cgit v1.2.3


From 8dd4c0f68c0db4c0f01af60a99a7ed34fd3dee2b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 13:10:50 -0300
Subject: tools arch uapi: Update asm-generic/unistd.h and arm64 unistd.h
 copies

To get the changes in:

  82b355d161c9 ("y2038: Remove newstat family from default syscall set")

Which will make the syscall table used by 'perf trace' for arm64 to be
updated from the changes in that patch.

This silences these perf build warnings:

  Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/unistd.h' differs from latest version at 'arch/arm64/include/uapi/asm/unistd.h'
  diff -u tools/arch/arm64/include/uapi/asm/unistd.h arch/arm64/include/uapi/asm/unistd.h
  Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h'
  diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h

Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-3euy7c4yy5mvnp5bm16t9vqg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm64/include/uapi/asm/unistd.h | 1 +
 tools/include/uapi/asm-generic/unistd.h    | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'tools/include')

diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 5072cbd15c82..dae1584cf017 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -16,5 +16,6 @@
  */
 
 #define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_NEW_STAT
 
 #include <asm-generic/unistd.h>
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index df4bedb9b01c..538546edbfbd 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -242,10 +242,12 @@ __SYSCALL(__NR_tee, sys_tee)
 /* fs/stat.c */
 #define __NR_readlinkat 78
 __SYSCALL(__NR_readlinkat, sys_readlinkat)
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
 #define __NR3264_fstatat 79
 __SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
 #define __NR3264_fstat 80
 __SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+#endif
 
 /* fs/sync.c */
 #define __NR_sync 81
-- 
cgit v1.2.3


From 89eb1f3b7f2a9156ce6f78713d7924c1bb2fab9f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 14:20:07 -0300
Subject: tools include uapi: Update asound.h copy

To silence this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/sound/asound.h' differs from latest version at 'include/uapi/sound/asound.h'
  diff -u tools/include/uapi/sound/asound.h include/uapi/sound/asound.h

Due to this cset:

  a98401518def ("ALSA: timer: fix wrong comment to refer to 'SNDRV_TIMER_PSFLG_*'")

Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: Takashi Iwai <tiwai@suse.de>
Link: https://lkml.kernel.org/n/tip-76gsvs0w2g0x723ivqa2xua3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/sound/asound.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/include')

diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index ed0a120d4f08..404d4b9ffe76 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -752,7 +752,7 @@ struct snd_timer_info {
 #define SNDRV_TIMER_PSFLG_EARLY_EVENT	(1<<2)	/* write early event to the poll queue */
 
 struct snd_timer_params {
-	unsigned int flags;		/* flags - SNDRV_MIXER_PSFLG_* */
+	unsigned int flags;		/* flags - SNDRV_TIMER_PSFLG_* */
 	unsigned int ticks;		/* requested resolution in ticks */
 	unsigned int queue_size;	/* total size of queue (32-1024) */
 	unsigned int reserved0;		/* reserved, was: failure locations */
-- 
cgit v1.2.3


From 685626dc26bd9cead850d06520708acbd16bcfda Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 16:50:08 -0300
Subject: tools include uapi: Update linux/mmap.h copy

To pick up the changes from:

  20916d4636a9 ("mm/hugetlb: add mmap() encodings for 32MB and 512MB page sizes")

That do not entail changes in in tools, this just shows that we have to
consider bits [26:31] of flags to beautify that in tools like 'perf
trace'

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/mman.h' differs from latest version at 'include/uapi/linux/mman.h'
  diff -u tools/include/uapi/linux/mman.h include/uapi/linux/mman.h

Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-3rvc39lon93kgt5pl31d8g4x@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/mman.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/include')

diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index bfd5938fede6..d0f515d53299 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -28,7 +28,9 @@
 #define MAP_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
 #define MAP_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
 #define MAP_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_32MB	HUGETLB_FLAG_ENCODE_32MB
 #define MAP_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_512MB	HUGETLB_FLAG_ENCODE_512MB
 #define MAP_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
 #define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
 #define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
-- 
cgit v1.2.3


From 827758129a0f84fbd0b2dda15e14a77a7604803d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 17:01:46 -0300
Subject: tools headers: Sync the various kvm.h header copies

For powerpc, s390, x86 and the main uapi linux/kvm.h header, none of
them entail changes in tooling.

Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-avn7iy8f4tcm2y40sbsdk31m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/powerpc/include/uapi/asm/kvm.h |  1 +
 tools/arch/s390/include/uapi/asm/kvm.h    |  2 ++
 tools/arch/x86/include/uapi/asm/kvm.h     |  6 ++----
 tools/include/uapi/linux/kvm.h            | 21 +++++++++++++++++++--
 4 files changed, 24 insertions(+), 6 deletions(-)

(limited to 'tools/include')

diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 1b32b56a03d3..8c876c166ef2 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -634,6 +634,7 @@ struct kvm_ppc_cpu_char {
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
 #define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
+#define KVM_REG_PPC_PTCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 9a50f02b9894..16511d97e8dc 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -160,6 +160,8 @@ struct kvm_s390_vm_cpu_subfunc {
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
 #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW	2
 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW	3
+#define KVM_S390_VM_CRYPTO_ENABLE_APIE		4
+#define KVM_S390_VM_CRYPTO_DISABLE_APIE		5
 
 /* kvm attributes for migration mode */
 #define KVM_S390_VM_MIGRATION_STOP	0
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 8a6eff9c27f3..dabfcf7c3941 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -300,10 +300,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		union {
-			__u8 pad;
-			__u8 pending;
-		};
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -387,6 +384,7 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
+#define KVM_STATE_NESTED_EVMCS		0x00000004
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 2875ce85b322..2b7a652c9fa4 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -420,13 +420,19 @@ struct kvm_run {
 struct kvm_coalesced_mmio_zone {
 	__u64 addr;
 	__u32 size;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 };
 
 struct kvm_coalesced_mmio {
 	__u64 phys_addr;
 	__u32 len;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 	__u8  data[8];
 };
 
@@ -751,6 +757,15 @@ struct kvm_ppc_resize_hpt {
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
+/*
+ * On arm64, machine type can be used to request the physical
+ * address size for the VM. Bits[7-0] are reserved for the guest
+ * PA size shift (i.e, log2(PA_Size)). For backward compatibility,
+ * value 0 implies the default IPA size, 40bits.
+ */
+#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK	0xffULL
+#define KVM_VM_TYPE_ARM_IPA_SIZE(x)		\
+	((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
 /*
  * ioctls for /dev/kvm fds:
  */
@@ -958,6 +973,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_SEND_IPI 161
 #define KVM_CAP_COALESCED_PIO 162
 #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
+#define KVM_CAP_EXCEPTION_PAYLOAD 164
+#define KVM_CAP_ARM_VM_IPA_SIZE 165
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From d45a57fff0a657045a77b395ae713ffae0cb4e46 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 17:04:47 -0300
Subject: tools headers uapi: Update linux/netlink.h header copy

Picking the changes from:

  89d35528d17d ("netlink: Add new socket option to enable strict checking on dumps")

To silence this build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Leblond <eric@regit.org>
Link: https://lkml.kernel.org/n/tip-1xymkfjpmhxfzrs46t8z8mjw@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/netlink.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/include')

diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
index 776bc92e9118..486ed1f0c0bc 100644
--- a/tools/include/uapi/linux/netlink.h
+++ b/tools/include/uapi/linux/netlink.h
@@ -155,6 +155,7 @@ enum nlmsgerr_attrs {
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
 #define NETLINK_EXT_ACK			11
+#define NETLINK_DUMP_STRICT_CHK		12
 
 struct nl_pktinfo {
 	__u32	group;
-- 
cgit v1.2.3


From 76b0b801782b34b3028dcef3de36cb634e3908a8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 17:06:57 -0300
Subject: tools headers uapi: Update linux/if_link.h header copy

To pick the changes from:

  9163a0fc1f0c ("net: bridge: add support for per-port vlan stats")

And silence this build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Leblond <eric@regit.org>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Link: https://lkml.kernel.org/n/tip-7p53ghippywz7fqkwo3nkzet@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/if_link.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/include')

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 58faab897201..1debfa42cba1 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -287,6 +287,7 @@ enum {
 	IFLA_BR_MCAST_STATS_ENABLED,
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
+	IFLA_BR_VLAN_STATS_PER_PORT,
 	__IFLA_BR_MAX,
 };
 
-- 
cgit v1.2.3


From 4f8f382e635707ddaddf8269a116e4f8cc8835c0 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 30 Oct 2018 22:24:04 -0700
Subject: perf tools: Don't clone maps from parent when synthesizing forks

When synthesizing FORK events, we are trying to create thread objects
for the already running tasks on the machine.

Normally, for a kernel FORK event, we want to clone the parent's maps
because that is what the kernel just did.

But when synthesizing, this should not be done.  If we do, we end up
with overlapping maps as we process the sythesized MMAP2 events that
get delivered shortly thereafter.

Use the FORK event misc flags in an internal way to signal this
situation, so we can elide the map clone when appropriate.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Link: http://lkml.kernel.org/r/20181030.222404.2085088822877051075.davem@davemloft.net
[ Added comment about flag use in machine__process_fork_event(),
  use ternary op in thread__clone_map_groups() as suggested by Jiri ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 include/uapi/linux/perf_event.h       |  2 ++
 tools/include/uapi/linux/perf_event.h |  2 ++
 tools/perf/util/event.c               |  1 +
 tools/perf/util/machine.c             | 19 ++++++++++++++++++-
 tools/perf/util/thread.c              | 13 +++++--------
 tools/perf/util/thread.h              |  2 +-
 6 files changed, 29 insertions(+), 10 deletions(-)

(limited to 'tools/include')

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc646185f8d9..e9c108a6b1c3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -308,6 +308,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	event->fork.pid  = tgid;
 	event->fork.tid  = pid;
 	event->fork.header.type = PERF_RECORD_FORK;
+	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8ee8ab39d8ac..8f36ce813bc5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	bool do_maps_clone = true;
 	int err = 0;
 
 	if (dump_trace)
@@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
+	/*
+	 * When synthesizing FORK events, we are trying to create thread
+	 * objects for the already running tasks on the machine.
+	 *
+	 * Normally, for a kernel FORK event, we want to clone the parent's
+	 * maps because that is what the kernel just did.
+	 *
+	 * But when synthesizing, this should not be done.  If we do, we end up
+	 * with overlapping maps as we process the sythesized MMAP2 events that
+	 * get delivered shortly thereafter.
+	 *
+	 * Use the FORK event misc flags in an internal way to signal this
+	 * situation, so we can elide the map clone when appropriate.
+	 */
+	if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+		do_maps_clone = false;
 
 	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent, sample->time) < 0) {
+	    thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		err = -1;
 	}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d393ece6..3d9ed7d0e281 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -330,7 +330,8 @@ static int thread__prepare_access(struct thread *thread)
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-				    struct thread *parent)
+				    struct thread *parent,
+				    bool do_maps_clone)
 {
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
@@ -341,15 +342,11 @@ static int thread__clone_map_groups(struct thread *thread,
 			 thread->pid_, thread->tid, parent->pid_, parent->tid);
 		return 0;
 	}
-
 	/* But this one is new process, copy maps. */
-	if (map_groups__clone(thread, parent->mg) < 0)
-		return -ENOMEM;
-
-	return 0;
+	return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
 	if (parent->comm_set) {
 		const char *comm = thread__comm_str(parent);
@@ -362,7 +359,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 	}
 
 	thread->ppid = parent->tid;
-	return thread__clone_map_groups(thread, parent);
+	return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 36c09a9904e6..30e2b4c165fe 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -89,7 +89,7 @@ struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
-- 
cgit v1.2.3


From 49a249c387268882e8393dd1fafc51e3b21cb7a2 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 7 Nov 2018 19:55:36 -0800
Subject: tools/bpftool: copy a few net uapi headers to tools directory

Commit f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
added certain networking support to bpftool.
The implementation relies on a relatively recent uapi header file
linux/tc_act/tc_bpf.h on the host which contains the marco
definition of TCA_ACT_BPF_ID.

Unfortunately, this is not the case for all distributions.
See the email message below where rhel-7.2 does not have
an up-to-date linux/tc_act/tc_bpf.h.
  https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1799211.html
Further investigation found that linux/pkt_cls.h is also needed for macro
TCA_BPF_TAG.

This patch fixed the issue by copying linux/tc_act/tc_bpf.h
and linux/pkt_cls.h from kernel include/uapi directory to
tools/include/uapi directory so building the bpftool does not depend
on host system for these files.

Fixes: f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Cc: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/pkt_cls.h       | 612 +++++++++++++++++++++++++++++++
 tools/include/uapi/linux/tc_act/tc_bpf.h |  37 ++
 2 files changed, 649 insertions(+)
 create mode 100644 tools/include/uapi/linux/pkt_cls.h
 create mode 100644 tools/include/uapi/linux/tc_act/tc_bpf.h

(limited to 'tools/include')

diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
new file mode 100644
index 000000000000..401d0c1e612d
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+	TCA_ACT_UNSPEC,
+	TCA_ACT_KIND,
+	TCA_ACT_OPTIONS,
+	TCA_ACT_INDEX,
+	TCA_ACT_STATS,
+	TCA_ACT_PAD,
+	TCA_ACT_COOKIE,
+	__TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND	1
+#define TCA_ACT_NOBIND	0
+#define TCA_ACT_UNBIND	1
+#define TCA_ACT_NOUNBIND	0
+#define TCA_ACT_REPLACE		1
+#define TCA_ACT_NOREPLACE	0
+
+#define TC_ACT_UNSPEC	(-1)
+#define TC_ACT_OK		0
+#define TC_ACT_RECLASSIFY	1
+#define TC_ACT_SHOT		2
+#define TC_ACT_PIPE		3
+#define TC_ACT_STOLEN		4
+#define TC_ACT_QUEUED		5
+#define TC_ACT_REPEAT		6
+#define TC_ACT_REDIRECT		7
+#define TC_ACT_TRAP		8 /* For hw path, this means "trap to cpu"
+				   * and don't further process the frame
+				   * in hardware. For sw path, this is
+				   * equivalent of TC_ACT_STOLEN - drop
+				   * the skb and act like everything
+				   * is alright.
+				   */
+#define TC_ACT_VALUE_MAX	TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+	TCA_ID_UNSPEC=0,
+	TCA_ID_POLICE=1,
+	/* other actions go here */
+	__TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+	__u32			index;
+	int			action;
+#define TC_POLICE_UNSPEC	TC_ACT_UNSPEC
+#define TC_POLICE_OK		TC_ACT_OK
+#define TC_POLICE_RECLASSIFY	TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT		TC_ACT_SHOT
+#define TC_POLICE_PIPE		TC_ACT_PIPE
+
+	__u32			limit;
+	__u32			burst;
+	__u32			mtu;
+	struct tc_ratespec	rate;
+	struct tc_ratespec	peakrate;
+	int			refcnt;
+	int			bindcnt;
+	__u32			capab;
+};
+
+struct tcf_t {
+	__u64   install;
+	__u64   lastuse;
+	__u64   expires;
+	__u64   firstuse;
+};
+
+struct tc_cnt {
+	int                   refcnt;
+	int                   bindcnt;
+};
+
+#define tc_gen \
+	__u32                 index; \
+	__u32                 capab; \
+	int                   action; \
+	int                   refcnt; \
+	int                   bindcnt
+
+enum {
+	TCA_POLICE_UNSPEC,
+	TCA_POLICE_TBF,
+	TCA_POLICE_RATE,
+	TCA_POLICE_PEAKRATE,
+	TCA_POLICE_AVRATE,
+	TCA_POLICE_RESULT,
+	TCA_POLICE_TM,
+	TCA_POLICE_PAD,
+	__TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW	(1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW	(1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW	(1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE	(1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC	0
+#define TC_U32_ROOT	(0xFFF00000)
+
+enum {
+	TCA_U32_UNSPEC,
+	TCA_U32_CLASSID,
+	TCA_U32_HASH,
+	TCA_U32_LINK,
+	TCA_U32_DIVISOR,
+	TCA_U32_SEL,
+	TCA_U32_POLICE,
+	TCA_U32_ACT,
+	TCA_U32_INDEV,
+	TCA_U32_PCNT,
+	TCA_U32_MARK,
+	TCA_U32_FLAGS,
+	TCA_U32_PAD,
+	__TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+	__be32		mask;
+	__be32		val;
+	int		off;
+	int		offmask;
+};
+
+struct tc_u32_sel {
+	unsigned char		flags;
+	unsigned char		offshift;
+	unsigned char		nkeys;
+
+	__be16			offmask;
+	__u16			off;
+	short			offoff;
+
+	short			hoff;
+	__be32			hmask;
+	struct tc_u32_key	keys[0];
+};
+
+struct tc_u32_mark {
+	__u32		val;
+	__u32		mask;
+	__u32		success;
+};
+
+struct tc_u32_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+	__u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL		1
+#define TC_U32_OFFSET		2
+#define TC_U32_VAROFFSET	4
+#define TC_U32_EAT		8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
+/* ROUTE filter */
+
+enum {
+	TCA_ROUTE4_UNSPEC,
+	TCA_ROUTE4_CLASSID,
+	TCA_ROUTE4_TO,
+	TCA_ROUTE4_FROM,
+	TCA_ROUTE4_IIF,
+	TCA_ROUTE4_POLICE,
+	TCA_ROUTE4_ACT,
+	__TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+	TCA_FW_UNSPEC,
+	TCA_FW_CLASSID,
+	TCA_FW_POLICE,
+	TCA_FW_INDEV, /*  used by CONFIG_NET_CLS_IND */
+	TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+	TCA_FW_MASK,
+	__TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+	FLOW_KEY_SRC,
+	FLOW_KEY_DST,
+	FLOW_KEY_PROTO,
+	FLOW_KEY_PROTO_SRC,
+	FLOW_KEY_PROTO_DST,
+	FLOW_KEY_IIF,
+	FLOW_KEY_PRIORITY,
+	FLOW_KEY_MARK,
+	FLOW_KEY_NFCT,
+	FLOW_KEY_NFCT_SRC,
+	FLOW_KEY_NFCT_DST,
+	FLOW_KEY_NFCT_PROTO_SRC,
+	FLOW_KEY_NFCT_PROTO_DST,
+	FLOW_KEY_RTCLASSID,
+	FLOW_KEY_SKUID,
+	FLOW_KEY_SKGID,
+	FLOW_KEY_VLAN_TAG,
+	FLOW_KEY_RXHASH,
+	__FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX	(__FLOW_KEY_MAX - 1)
+
+enum {
+	FLOW_MODE_MAP,
+	FLOW_MODE_HASH,
+};
+
+enum {
+	TCA_FLOW_UNSPEC,
+	TCA_FLOW_KEYS,
+	TCA_FLOW_MODE,
+	TCA_FLOW_BASECLASS,
+	TCA_FLOW_RSHIFT,
+	TCA_FLOW_ADDEND,
+	TCA_FLOW_MASK,
+	TCA_FLOW_XOR,
+	TCA_FLOW_DIVISOR,
+	TCA_FLOW_ACT,
+	TCA_FLOW_POLICE,
+	TCA_FLOW_EMATCHES,
+	TCA_FLOW_PERTURB,
+	__TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX	(__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+	TCA_BASIC_UNSPEC,
+	TCA_BASIC_CLASSID,
+	TCA_BASIC_EMATCHES,
+	TCA_BASIC_ACT,
+	TCA_BASIC_POLICE,
+	__TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+	TCA_CGROUP_UNSPEC,
+	TCA_CGROUP_ACT,
+	TCA_CGROUP_POLICE,
+	TCA_CGROUP_EMATCHES,
+	__TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT		(1 << 0)
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	TCA_BPF_FD,
+	TCA_BPF_NAME,
+	TCA_BPF_FLAGS,
+	TCA_BPF_FLAGS_GEN,
+	TCA_BPF_TAG,
+	TCA_BPF_ID,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+	TCA_FLOWER_UNSPEC,
+	TCA_FLOWER_CLASSID,
+	TCA_FLOWER_INDEV,
+	TCA_FLOWER_ACT,
+	TCA_FLOWER_KEY_ETH_DST,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_DST_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_TYPE,	/* be16 */
+	TCA_FLOWER_KEY_IP_PROTO,	/* u8 */
+	TCA_FLOWER_KEY_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_SRC_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_SRC_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_TCP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_TCP_DST,		/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_UDP_DST,		/* be16 */
+
+	TCA_FLOWER_FLAGS,
+	TCA_FLOWER_KEY_VLAN_ID,		/* be16 */
+	TCA_FLOWER_KEY_VLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_VLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_KEY_ID,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+	TCA_FLOWER_KEY_TCP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_TCP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_SCTP_SRC,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_FLAGS,		/* be32 */
+	TCA_FLOWER_KEY_FLAGS_MASK,	/* be32 */
+
+	TCA_FLOWER_KEY_ICMPV4_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+	TCA_FLOWER_KEY_ARP_SIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_SIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_OP,		/* u8 */
+	TCA_FLOWER_KEY_ARP_OP_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ARP_SHA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_SHA_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA_MASK,	/* ETH_ALEN */
+
+	TCA_FLOWER_KEY_MPLS_TTL,	/* u8 - 8 bits */
+	TCA_FLOWER_KEY_MPLS_BOS,	/* u8 - 1 bit */
+	TCA_FLOWER_KEY_MPLS_TC,		/* u8 - 3 bits */
+	TCA_FLOWER_KEY_MPLS_LABEL,	/* be32 - 20 bits */
+
+	TCA_FLOWER_KEY_TCP_FLAGS,	/* be16 */
+	TCA_FLOWER_KEY_TCP_FLAGS_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_IP_TOS,		/* u8 */
+	TCA_FLOWER_KEY_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_IP_TTL,		/* u8 */
+	TCA_FLOWER_KEY_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_CVLAN_ID,	/* be16 */
+	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_ENC_OPTS,
+	TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+	TCA_FLOWER_IN_HW_COUNT,
+
+	__TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+					 * attributes
+					 */
+	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,            /* u16 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,             /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,             /* 4 to 128 bytes */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+	TCA_MATCHALL_UNSPEC,
+	TCA_MATCHALL_CLASSID,
+	TCA_MATCHALL_ACT,
+	TCA_MATCHALL_FLAGS,
+	__TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+	__u16		nmatches;
+	__u16		progid;
+};
+
+enum {
+	TCA_EMATCH_TREE_UNSPEC,
+	TCA_EMATCH_TREE_HDR,
+	TCA_EMATCH_TREE_LIST,
+	__TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+	__u16		matchid;
+	__u16		kind;
+	__u16		flags;
+	__u16		pad; /* currently unused */
+};
+
+/*  0                   1
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 
+ * +-----------------------+-+-+---+
+ * |         Unused        |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ *          where: 0 0 END (last ematch)
+ *                 0 1 AND
+ *                 1 0 OR
+ *                 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END	0
+#define TCF_EM_REL_AND	(1<<0)
+#define TCF_EM_REL_OR	(1<<1)
+#define TCF_EM_INVERT	(1<<2)
+#define TCF_EM_SIMPLE	(1<<3)
+
+#define TCF_EM_REL_MASK	3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+	TCF_LAYER_LINK,
+	TCF_LAYER_NETWORK,
+	TCF_LAYER_TRANSPORT,
+	__TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ *   1..32767		Reserved for ematches inside kernel tree
+ *   32768..65535	Free to use, not reliable
+ */
+#define	TCF_EM_CONTAINER	0
+#define	TCF_EM_CMP		1
+#define	TCF_EM_NBYTE		2
+#define	TCF_EM_U32		3
+#define	TCF_EM_META		4
+#define	TCF_EM_TEXT		5
+#define	TCF_EM_VLAN		6
+#define	TCF_EM_CANID		7
+#define	TCF_EM_IPSET		8
+#define	TCF_EM_IPT		9
+#define	TCF_EM_MAX		9
+
+enum {
+	TCF_EM_PROG_TC
+};
+
+enum {
+	TCF_EM_OPND_EQ,
+	TCF_EM_OPND_GT,
+	TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 000000000000..6e89a5df49a4
--- /dev/null
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+	tc_gen;
+};
+
+enum {
+	TCA_ACT_BPF_UNSPEC,
+	TCA_ACT_BPF_TM,
+	TCA_ACT_BPF_PARMS,
+	TCA_ACT_BPF_OPS_LEN,
+	TCA_ACT_BPF_OPS,
+	TCA_ACT_BPF_FD,
+	TCA_ACT_BPF_NAME,
+	TCA_ACT_BPF_PAD,
+	TCA_ACT_BPF_TAG,
+	TCA_ACT_BPF_ID,
+	__TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
-- 
cgit v1.2.3


From 53f00f4548ef700e3c6867a35fd7d4f824cd165a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 19 Nov 2018 12:17:42 -0800
Subject: tools headers uapi: Synchronize i915_drm.h

To pick up the changes in:

  900ccf30f9e1 ("drm/i915: Only force GGTT coherency w/a on required chipsets")

No changes are required in tools/ nor does anything gets automatically
generated to be used in the 'perf trace' syscall arg beautifiers.

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h'
  diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t2vor2wegv41gt5n49095kly@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/drm/i915_drm.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'tools/include')

diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7f5634ce8e88..a4446f452040 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -529,6 +529,28 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
 
+/*
+ * Once upon a time we supposed that writes through the GGTT would be
+ * immediately in physical memory (once flushed out of the CPU path). However,
+ * on a few different processors and chipsets, this is not necessarily the case
+ * as the writes appear to be buffered internally. Thus a read of the backing
+ * storage (physical memory) via a different path (with different physical tags
+ * to the indirect write via the GGTT) will see stale values from before
+ * the GGTT write. Inside the kernel, we can for the most part keep track of
+ * the different read/write domains in use (e.g. set-domain), but the assumption
+ * of coherency is baked into the ABI, hence reporting its true state in this
+ * parameter.
+ *
+ * Reports true when writes via mmap_gtt are immediately visible following an
+ * lfence to flush the WCB.
+ *
+ * Reports false when writes via mmap_gtt are indeterminately delayed in an in
+ * internal buffer and are _not_ immediately visible to third parties accessing
+ * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
+ * communications channel when reporting false is strongly disadvised.
+ */
+#define I915_PARAM_MMAP_GTT_COHERENT	52
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
-- 
cgit v1.2.3


From 83d9bdeaedd8f7aa9749828364f0018cacd1dad3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 19 Nov 2018 12:31:45 -0800
Subject: tools uapi asm-generic: Synchronize ioctls.h

To pick up the changes in:

  ad8c0eaa0a41 ("tty/serial_core: add ISO7816 infrastructure")

That is a change that imply a change to be made in tools/perf/trace/beauty/ioctl.c to
make 'perf trace' ioctl syscall argument beautifier to support these new
commands:  TIOCGISO7816 and TIOCSISO7816.

This is not yet done automatically by a script like is done for some
other headers, for instance:

  $ tools/perf/trace/beauty/drm_ioctl.sh | head
  #ifndef DRM_COMMAND_BASE
  #define DRM_COMMAND_BASE                0x40
  #endif
  static const char *drm_ioctl_cmds[] = {
	[0x00] = "VERSION",
	[0x01] = "GET_UNIQUE",
	[0x02] = "GET_MAGIC",
	[0x03] = "IRQ_BUSID",
	[0x04] = "GET_MAP",
	[0x05] = "GET_CLIENT",
  $

So we will need to change tools/perf/trace/beauty/ioctl.c in a follow up
patch until we switch to a generator script.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zin76fe6iykqsilvo6u47f9o@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/asm-generic/ioctls.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/include')

diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
index 040651735662..cdc9f4ca8c27 100644
--- a/tools/include/uapi/asm-generic/ioctls.h
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -79,6 +79,8 @@
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 #define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
+#define TIOCGISO7816	_IOR('T', 0x42, struct serial_iso7816)
+#define TIOCSISO7816	_IOWR('T', 0x43, struct serial_iso7816)
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451
-- 
cgit v1.2.3


From 9137bb27e60e554dab694eafa4cca241fa3a694f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 25 Nov 2018 19:33:53 +0100
Subject: x86/speculation: Add prctl() control for indirect branch speculation

Add the PR_SPEC_INDIRECT_BRANCH option for the PR_GET_SPECULATION_CTRL and
PR_SET_SPECULATION_CTRL prctls to allow fine grained per task control of
indirect branch speculation via STIBP and IBPB.

Invocations:
 Check indirect branch speculation status with
 - prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0);

 Enable indirect branch speculation with
 - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0);

 Disable indirect branch speculation with
 - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0);

 Force disable indirect branch speculation with
 - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0);

See Documentation/userspace-api/spec_ctrl.rst.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Casey Schaufler <casey.schaufler@intel.com>
Cc: Asit Mallick <asit.k.mallick@intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Jon Masters <jcm@redhat.com>
Cc: Waiman Long <longman9394@gmail.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Dave Stewart <david.c.stewart@intel.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20181125185005.866780996@linutronix.de
---
 Documentation/userspace-api/spec_ctrl.rst |  9 +++++
 arch/x86/include/asm/nospec-branch.h      |  1 +
 arch/x86/kernel/cpu/bugs.c                | 67 +++++++++++++++++++++++++++++++
 arch/x86/kernel/process.c                 |  5 +++
 include/linux/sched.h                     |  9 +++++
 include/uapi/linux/prctl.h                |  1 +
 tools/include/uapi/linux/prctl.h          |  1 +
 7 files changed, 93 insertions(+)

(limited to 'tools/include')

diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst
index 32f3d55c54b7..c4dbe6f7cdae 100644
--- a/Documentation/userspace-api/spec_ctrl.rst
+++ b/Documentation/userspace-api/spec_ctrl.rst
@@ -92,3 +92,12 @@ Speculation misfeature controls
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0);
+
+- PR_SPEC_INDIR_BRANCH: Indirect Branch Speculation in User Processes
+                        (Mitigate Spectre V2 style attacks against user processes)
+
+  Invocations:
+   * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0);
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index d4d35baf0430..2adbe7b047fa 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -232,6 +232,7 @@ enum spectre_v2_mitigation {
 enum spectre_v2_user_mitigation {
 	SPECTRE_V2_USER_NONE,
 	SPECTRE_V2_USER_STRICT,
+	SPECTRE_V2_USER_PRCTL,
 };
 
 /* The Speculative Store Bypass disable variants */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 9cab538e10f1..74359fff87fd 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -566,6 +566,8 @@ void arch_smt_update(void)
 	case SPECTRE_V2_USER_STRICT:
 		update_stibp_strict();
 		break;
+	case SPECTRE_V2_USER_PRCTL:
+		break;
 	}
 
 	mutex_unlock(&spec_ctrl_mutex);
@@ -752,12 +754,50 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 	return 0;
 }
 
+static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+			return 0;
+		/*
+		 * Indirect branch speculation is always disabled in strict
+		 * mode.
+		 */
+		if (spectre_v2_user == SPECTRE_V2_USER_STRICT)
+			return -EPERM;
+		task_clear_spec_ib_disable(task);
+		task_update_spec_tif(task);
+		break;
+	case PR_SPEC_DISABLE:
+	case PR_SPEC_FORCE_DISABLE:
+		/*
+		 * Indirect branch speculation is always allowed when
+		 * mitigation is force disabled.
+		 */
+		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+			return -EPERM;
+		if (spectre_v2_user == SPECTRE_V2_USER_STRICT)
+			return 0;
+		task_set_spec_ib_disable(task);
+		if (ctrl == PR_SPEC_FORCE_DISABLE)
+			task_set_spec_ib_force_disable(task);
+		task_update_spec_tif(task);
+		break;
+	default:
+		return -ERANGE;
+	}
+	return 0;
+}
+
 int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
 			     unsigned long ctrl)
 {
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
 		return ssb_prctl_set(task, ctrl);
+	case PR_SPEC_INDIRECT_BRANCH:
+		return ib_prctl_set(task, ctrl);
 	default:
 		return -ENODEV;
 	}
@@ -790,11 +830,34 @@ static int ssb_prctl_get(struct task_struct *task)
 	}
 }
 
+static int ib_prctl_get(struct task_struct *task)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		return PR_SPEC_NOT_AFFECTED;
+
+	switch (spectre_v2_user) {
+	case SPECTRE_V2_USER_NONE:
+		return PR_SPEC_ENABLE;
+	case SPECTRE_V2_USER_PRCTL:
+		if (task_spec_ib_force_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ib_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+	case SPECTRE_V2_USER_STRICT:
+		return PR_SPEC_DISABLE;
+	default:
+		return PR_SPEC_NOT_AFFECTED;
+	}
+}
+
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 {
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
 		return ssb_prctl_get(task);
+	case PR_SPEC_INDIRECT_BRANCH:
+		return ib_prctl_get(task);
 	default:
 		return -ENODEV;
 	}
@@ -974,6 +1037,8 @@ static char *stibp_state(void)
 		return ", STIBP: disabled";
 	case SPECTRE_V2_USER_STRICT:
 		return ", STIBP: forced";
+	case SPECTRE_V2_USER_PRCTL:
+		return "";
 	}
 	return "";
 }
@@ -986,6 +1051,8 @@ static char *ibpb_state(void)
 			return ", IBPB: disabled";
 		case SPECTRE_V2_USER_STRICT:
 			return ", IBPB: always-on";
+		case SPECTRE_V2_USER_PRCTL:
+			return "";
 		}
 	}
 	return "";
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index afbe2eb4a1c6..7d31192296a8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -450,6 +450,11 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
 			set_tsk_thread_flag(tsk, TIF_SSBD);
 		else
 			clear_tsk_thread_flag(tsk, TIF_SSBD);
+
+		if (task_spec_ib_disable(tsk))
+			set_tsk_thread_flag(tsk, TIF_SPEC_IB);
+		else
+			clear_tsk_thread_flag(tsk, TIF_SPEC_IB);
 	}
 	/* Return the updated threadinfo flags*/
 	return task_thread_info(tsk)->flags;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a51c13c2b1a0..d607db5fcc6a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1453,6 +1453,8 @@ static inline bool is_percpu_thread(void)
 #define PFA_SPREAD_SLAB			2	/* Spread some slab caches over cpuset */
 #define PFA_SPEC_SSB_DISABLE		3	/* Speculative Store Bypass disabled */
 #define PFA_SPEC_SSB_FORCE_DISABLE	4	/* Speculative Store Bypass force disabled*/
+#define PFA_SPEC_IB_DISABLE		5	/* Indirect branch speculation restricted */
+#define PFA_SPEC_IB_FORCE_DISABLE	6	/* Indirect branch speculation permanently restricted */
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
@@ -1484,6 +1486,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)
 TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
 TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
 
+TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable)
+TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable)
+TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable)
+
+TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
+TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
+
 static inline void
 current_restore_flags(unsigned long orig_flags, unsigned long flags)
 {
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index c0d7ea0bf5b6..b17201edfa09 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -212,6 +212,7 @@ struct prctl_mm_map {
 #define PR_SET_SPECULATION_CTRL		53
 /* Speculation control variants */
 # define PR_SPEC_STORE_BYPASS		0
+# define PR_SPEC_INDIRECT_BRANCH	1
 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */
 # define PR_SPEC_NOT_AFFECTED		0
 # define PR_SPEC_PRCTL			(1UL << 0)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index c0d7ea0bf5b6..b17201edfa09 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -212,6 +212,7 @@ struct prctl_mm_map {
 #define PR_SET_SPECULATION_CTRL		53
 /* Speculation control variants */
 # define PR_SPEC_STORE_BYPASS		0
+# define PR_SPEC_INDIRECT_BRANCH	1
 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */
 # define PR_SPEC_NOT_AFFECTED		0
 # define PR_SPEC_PRCTL			(1UL << 0)
-- 
cgit v1.2.3