Merge drm/drm-next into drm-intel-gt-next

Backmerging to pull in the new dma_resv iterators requested by
Maarten and Matt.

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

18 files changed, 264 insertions, 439 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index e1c705fdfa7c..db2e147e069f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
  * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains
  * per-socket cgroup information except for memcg association.
  *
- * On legacy hierarchies, net_prio and net_cls controllers directly set
- * attributes on each sock which can then be tested by the network layer.
- * On the default hierarchy, each sock is associated with the cgroup it was
- * created in and the networking layer can match the cgroup directly.
- *
- * To avoid carrying all three cgroup related fields separately in sock,
- * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.
- * On boot, sock_cgroup_data records the cgroup that the sock was created
- * in so that cgroup2 matches can be made; however, once either net_prio or
- * net_cls starts being used, the area is overridden to carry prioidx and/or
- * classid.  The two modes are distinguished by whether the lowest bit is
- * set.  Clear bit indicates cgroup pointer while set bit prioidx and
- * classid.
- *
- * While userland may start using net_prio or net_cls at any time, once
- * either is used, cgroup2 matching no longer works.  There is no reason to
- * mix the two and this is in line with how legacy and v2 compatibility is
- * handled.  On mode switch, cgroup references which are already being
- * pointed to by socks may be leaked.  While this can be remedied by adding
- * synchronization around sock_cgroup_data, given that the number of leaked
- * cgroups is bound and highly unlikely to be high, this seems to be the
- * better trade-off.
+ * On legacy hierarchies, net_prio and net_cls controllers directly
+ * set attributes on each sock which can then be tested by the network
+ * layer. On the default hierarchy, each sock is associated with the
+ * cgroup it was created in and the networking layer can match the
+ * cgroup directly.
  */
 struct sock_cgroup_data {
-	union {
-#ifdef __LITTLE_ENDIAN
-		struct {
-			u8	is_data : 1;
-			u8	no_refcnt : 1;
-			u8	unused : 6;
-			u8	padding;
-			u16	prioidx;
-			u32	classid;
-		} __packed;
-#else
-		struct {
-			u32	classid;
-			u16	prioidx;
-			u8	padding;
-			u8	unused : 6;
-			u8	no_refcnt : 1;
-			u8	is_data : 1;
-		} __packed;
+	struct cgroup	*cgroup; /* v2 */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	u32		classid; /* v1 */
+#endif
+#ifdef CONFIG_CGROUP_NET_PRIO
+	u16		prioidx; /* v1 */
 #endif
-		u64		val;
-	};
 };
 
-/*
- * There's a theoretical window where the following accessors race with
- * updaters and return part of the previous pointer as the prioidx or
- * classid.  Such races are short-lived and the result isn't critical.
- */
 static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 1 which is always the ID of the root cgroup */
-	return (skcd->is_data & 1) ? skcd->prioidx : 1;
+#ifdef CONFIG_CGROUP_NET_PRIO
+	return READ_ONCE(skcd->prioidx);
+#else
+	return 1;
+#endif
 }
 
 static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 0 which is the unconfigured default classid */
-	return (skcd->is_data & 1) ? skcd->classid : 0;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	return READ_ONCE(skcd->classid);
+#else
+	return 0;
+#endif
 }
 
-/*
- * If invoked concurrently, the updaters may clobber each other.  The
- * caller is responsible for synchronization.
- */
 static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 					   u16 prioidx)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_prioidx(&skcd_buf) == prioidx)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.prioidx = prioidx;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_PRIO
+	WRITE_ONCE(skcd->prioidx, prioidx);
+#endif
 }
 
 static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
 					   u32 classid)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_classid(&skcd_buf) == classid)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.classid = classid;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	WRITE_ONCE(skcd->classid, classid);
+#endif
 }
 
 #else	/* CONFIG_SOCK_CGROUP_DATA */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 7bf60454a313..75c151413fda 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
  */
 #ifdef CONFIG_SOCK_CGROUP_DATA
 
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-extern spinlock_t cgroup_sk_update_lock;
-#endif
-
-void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
 void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 {
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-	unsigned long v;
-
-	/*
-	 * @skcd->val is 64bit but the following is safe on 32bit too as we
-	 * just need the lower ulong to be written and read atomically.
-	 */
-	v = READ_ONCE(skcd->val);
-
-	if (v & 3)
-		return &cgrp_dfl_root.cgrp;
-
-	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
-#else
-	return (struct cgroup *)(unsigned long)skcd->val;
-#endif
+	return skcd->cgroup;
 }
 
 #else	/* CONFIG_CGROUP_DATA */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 49b0ac8b6fd3..3c4de9b6c6e3 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -62,19 +62,6 @@
 #define __no_sanitize_coverage
 #endif
 
-/*
- * Not all versions of clang implement the type-generic versions
- * of the builtin overflow checkers. Fortunately, clang implements
- * __has_builtin allowing us to avoid awkward version
- * checks. Unfortunately, we don't know which version of gcc clang
- * pretends to be, so the macro may or may not be defined.
- */
-#if __has_builtin(__builtin_mul_overflow) && \
-    __has_builtin(__builtin_add_overflow) && \
-    __has_builtin(__builtin_sub_overflow)
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 21c36b69eb06..bd2b881c6b63 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -95,10 +95,8 @@
 
 #if GCC_VERSION >= 70000
 #define KASAN_ABI_VERSION 5
-#elif GCC_VERSION >= 50000
+#else
 #define KASAN_ABI_VERSION 4
-#elif GCC_VERSION >= 40902
-#define KASAN_ABI_VERSION 3
 #endif
 
 #if __has_attribute(__no_sanitize_address__)
@@ -125,10 +123,6 @@
 #define __no_sanitize_coverage
 #endif
 
-#if GCC_VERSION >= 50100
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 /*
  * Turn individual warnings and errors on and off locally, depending
  * on version.
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index b67261a1e3e9..3d5af56337bd 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
     (typeof(ptr)) (__ptr + (off)); })
 #endif
 
+#define absolute_pointer(val)	RELOC_HIDE((void *)(val), 0)
+
 #ifndef OPTIMIZER_HIDE_VAR
 /* Make the optimizer believe the variable can be manipulated arbitrarily. */
 #define OPTIMIZER_HIDE_VAR(var)						\
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 8f2106e9e5c1..e6ec63403965 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -21,29 +21,6 @@
  */
 
 /*
- * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17.
- * In the meantime, to support gcc < 5, we implement __has_attribute
- * by hand.
- */
-#ifndef __has_attribute
-# define __has_attribute(x) __GCC4_has_attribute_##x
-# define __GCC4_has_attribute___assume_aligned__      1
-# define __GCC4_has_attribute___copy__                0
-# define __GCC4_has_attribute___designated_init__     0
-# define __GCC4_has_attribute___error__               1
-# define __GCC4_has_attribute___externally_visible__  1
-# define __GCC4_has_attribute___no_caller_saved_registers__ 0
-# define __GCC4_has_attribute___noclone__             1
-# define __GCC4_has_attribute___no_profile_instrument_function__ 0
-# define __GCC4_has_attribute___nonstring__           0
-# define __GCC4_has_attribute___no_sanitize_address__ 1
-# define __GCC4_has_attribute___no_sanitize_undefined__ 1
-# define __GCC4_has_attribute___no_sanitize_coverage__ 0
-# define __GCC4_has_attribute___fallthrough__         0
-# define __GCC4_has_attribute___warning__             1
-#endif
-
-/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute
  */
 #define __alias(symbol)                 __attribute__((__alias__(#symbol)))
@@ -77,7 +54,6 @@
  * compiler should see some alignment anyway, when the return value is
  * massaged by 'flags = ptr & 3; ptr &= ~3;').
  *
- * Optional: only supported since gcc >= 4.9
  * Optional: not supported by icc
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 8b32b4bdd590..02c2eb874da6 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -420,6 +420,13 @@ struct dma_buf {
 	 * - Dynamic importers should set fences for any access that they can't
 	 *   disable immediately from their &dma_buf_attach_ops.move_notify
 	 *   callback.
+	 *
+	 * IMPORTANT:
+	 *
+	 * All drivers must obey the struct dma_resv rules, specifically the
+	 * rules for updating fences, see &dma_resv.fence_excl and
+	 * &dma_resv.fence. If these dependency rules are broken access tracking
+	 * can be lost resulting in use after free issues.
 	 */
 	struct dma_resv *resv;
 
@@ -433,7 +440,7 @@ struct dma_buf {
 		wait_queue_head_t *poll;
 
 		__poll_t active;
-	} cb_excl, cb_shared;
+	} cb_in, cb_out;
 #ifdef CONFIG_DMABUF_SYSFS_STATS
 	/**
 	 * @sysfs_entry:
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 6ffb4b2c6371..a706b7bf51d7 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -214,19 +214,15 @@ struct dma_fence_ops {
 	 * Custom wait implementation, defaults to dma_fence_default_wait() if
 	 * not set.
 	 *
-	 * The dma_fence_default_wait implementation should work for any fence, as long
-	 * as @enable_signaling works correctly. This hook allows drivers to
-	 * have an optimized version for the case where a process context is
-	 * already available, e.g. if @enable_signaling for the general case
-	 * needs to set up a worker thread.
+	 * Deprecated and should not be used by new implementations. Only used
+	 * by existing implementations which need special handling for their
+	 * hardware reset procedure.
 	 *
 	 * Must return -ERESTARTSYS if the wait is intr = true and the wait was
 	 * interrupted, and remaining jiffies if fence has signaled, or 0 if wait
 	 * timed out. Can also return other error values on custom implementations,
 	 * which should be treated as if the fence is signaled. For example a hardware
 	 * lockup could be reported like that.
-	 *
-	 * This callback is optional.
 	 */
 	signed long (*wait)(struct dma_fence *fence,
 			    bool intr, signed long timeout);
@@ -590,26 +586,4 @@ struct dma_fence *dma_fence_get_stub(void);
 struct dma_fence *dma_fence_allocate_private_stub(void);
 u64 dma_fence_context_alloc(unsigned num);
 
-#define DMA_FENCE_TRACE(f, fmt, args...) \
-	do {								\
-		struct dma_fence *__ff = (f);				\
-		if (IS_ENABLED(CONFIG_DMA_FENCE_TRACE))			\
-			pr_info("f %llu#%llu: " fmt,			\
-				__ff->context, __ff->seqno, ##args);	\
-	} while (0)
-
-#define DMA_FENCE_WARN(f, fmt, args...) \
-	do {								\
-		struct dma_fence *__ff = (f);				\
-		pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\
-			 ##args);					\
-	} while (0)
-
-#define DMA_FENCE_ERR(f, fmt, args...) \
-	do {								\
-		struct dma_fence *__ff = (f);				\
-		pr_err("f %llu#%llu: " fmt, __ff->context, __ff->seqno,	\
-			##args);					\
-	} while (0)
-
 #endif /* __LINUX_DMA_FENCE_H */
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index 39fefb86780b..8b6c20636a79 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -62,19 +62,188 @@ struct dma_resv_list {
 
 /**
  * struct dma_resv - a reservation object manages fences for a buffer
- * @lock: update side lock
- * @seq: sequence count for managing RCU read-side synchronization
- * @fence_excl: the exclusive fence, if there is one currently
- * @fence: list of current shared fences
+ *
+ * There are multiple uses for this, with sometimes slightly different rules in
+ * how the fence slots are used.
+ *
+ * One use is to synchronize cross-driver access to a struct dma_buf, either for
+ * dynamic buffer management or just to handle implicit synchronization between
+ * different users of the buffer in userspace. See &dma_buf.resv for a more
+ * in-depth discussion.
+ *
+ * The other major use is to manage access and locking within a driver in a
+ * buffer based memory manager. struct ttm_buffer_object is the canonical
+ * example here, since this is where reservation objects originated from. But
+ * use in drivers is spreading and some drivers also manage struct
+ * drm_gem_object with the same scheme.
  */
 struct dma_resv {
+	/**
+	 * @lock:
+	 *
+	 * Update side lock. Don't use directly, instead use the wrapper
+	 * functions like dma_resv_lock() and dma_resv_unlock().
+	 *
+	 * Drivers which use the reservation object to manage memory dynamically
+	 * also use this lock to protect buffer object state like placement,
+	 * allocation policies or throughout command submission.
+	 */
 	struct ww_mutex lock;
+
+	/**
+	 * @seq:
+	 *
+	 * Sequence count for managing RCU read-side synchronization, allows
+	 * read-only access to @fence_excl and @fence while ensuring we take a
+	 * consistent snapshot.
+	 */
 	seqcount_ww_mutex_t seq;
 
+	/**
+	 * @fence_excl:
+	 *
+	 * The exclusive fence, if there is one currently.
+	 *
+	 * There are two ways to update this fence:
+	 *
+	 * - First by calling dma_resv_add_excl_fence(), which replaces all
+	 *   fences attached to the reservation object. To guarantee that no
+	 *   fences are lost, this new fence must signal only after all previous
+	 *   fences, both shared and exclusive, have signalled. In some cases it
+	 *   is convenient to achieve that by attaching a struct dma_fence_array
+	 *   with all the new and old fences.
+	 *
+	 * - Alternatively the fence can be set directly, which leaves the
+	 *   shared fences unchanged. To guarantee that no fences are lost, this
+	 *   new fence must signal only after the previous exclusive fence has
+	 *   signalled. Since the shared fences are staying intact, it is not
+	 *   necessary to maintain any ordering against those. If semantically
+	 *   only a new access is added without actually treating the previous
+	 *   one as a dependency the exclusive fences can be strung together
+	 *   using struct dma_fence_chain.
+	 *
+	 * Note that actual semantics of what an exclusive or shared fence mean
+	 * is defined by the user, for reservation objects shared across drivers
+	 * see &dma_buf.resv.
+	 */
 	struct dma_fence __rcu *fence_excl;
+
+	/**
+	 * @fence:
+	 *
+	 * List of current shared fences.
+	 *
+	 * There are no ordering constraints of shared fences against the
+	 * exclusive fence slot. If a waiter needs to wait for all access, it
+	 * has to wait for both sets of fences to signal.
+	 *
+	 * A new fence is added by calling dma_resv_add_shared_fence(). Since
+	 * this often needs to be done past the point of no return in command
+	 * submission it cannot fail, and therefore sufficient slots need to be
+	 * reserved by calling dma_resv_reserve_shared().
+	 *
+	 * Note that actual semantics of what an exclusive or shared fence mean
+	 * is defined by the user, for reservation objects shared across drivers
+	 * see &dma_buf.resv.
+	 */
 	struct dma_resv_list __rcu *fence;
 };
 
+/**
+ * struct dma_resv_iter - current position into the dma_resv fences
+ *
+ * Don't touch this directly in the driver, use the accessor function instead.
+ */
+struct dma_resv_iter {
+	/** @obj: The dma_resv object we iterate over */
+	struct dma_resv *obj;
+
+	/** @all_fences: If all fences should be returned */
+	bool all_fences;
+
+	/** @fence: the currently handled fence */
+	struct dma_fence *fence;
+
+	/** @seq: sequence number to check for modifications */
+	unsigned int seq;
+
+	/** @index: index into the shared fences */
+	unsigned int index;
+
+	/** @fences: the shared fences */
+	struct dma_resv_list *fences;
+
+	/** @is_restarted: true if this is the first returned fence */
+	bool is_restarted;
+};
+
+struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor);
+struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor);
+
+/**
+ * dma_resv_iter_begin - initialize a dma_resv_iter object
+ * @cursor: The dma_resv_iter object to initialize
+ * @obj: The dma_resv object which we want to iterate over
+ * @all_fences: If all fences should be returned or just the exclusive one
+ */
+static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor,
+				       struct dma_resv *obj,
+				       bool all_fences)
+{
+	cursor->obj = obj;
+	cursor->all_fences = all_fences;
+	cursor->fence = NULL;
+}
+
+/**
+ * dma_resv_iter_end - cleanup a dma_resv_iter object
+ * @cursor: the dma_resv_iter object which should be cleaned up
+ *
+ * Make sure that the reference to the fence in the cursor is properly
+ * dropped.
+ */
+static inline void dma_resv_iter_end(struct dma_resv_iter *cursor)
+{
+	dma_fence_put(cursor->fence);
+}
+
+/**
+ * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one
+ * @cursor: the cursor of the current position
+ *
+ * Returns true if the currently returned fence is the exclusive one.
+ */
+static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor)
+{
+	return cursor->index == 0;
+}
+
+/**
+ * dma_resv_iter_is_restarted - test if this is the first fence after a restart
+ * @cursor: the cursor with the current position
+ *
+ * Return true if this is the first fence in an iteration after a restart.
+ */
+static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor)
+{
+	return cursor->is_restarted;
+}
+
+/**
+ * dma_resv_for_each_fence_unlocked - unlocked fence iterator
+ * @cursor: a struct dma_resv_iter pointer
+ * @fence: the current fence
+ *
+ * Iterate over the fences in a struct dma_resv object without holding the
+ * &dma_resv.lock and using RCU instead. The cursor needs to be initialized
+ * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside
+ * the iterator a reference to the dma_fence is held and the RCU lock dropped.
+ * When the dma_resv is modified the iteration starts over again.
+ */
+#define dma_resv_for_each_fence_unlocked(cursor, fence)			\
+	for (fence = dma_resv_iter_first_unlocked(cursor);		\
+	     fence; fence = dma_resv_iter_next_unlocked(cursor))
+
 #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base)
 #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base)
 
@@ -98,6 +267,13 @@ static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {}
  * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle
  * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation
  * object may be locked by itself by passing NULL as @ctx.
+ *
+ * When a die situation is indicated by returning -EDEADLK all locks held by
+ * @ctx must be unlocked and then dma_resv_lock_slow() called on @obj.
+ *
+ * Unlocked by calling dma_resv_unlock().
+ *
+ * See also dma_resv_lock_interruptible() for the interruptible variant.
  */
 static inline int dma_resv_lock(struct dma_resv *obj,
 				struct ww_acquire_ctx *ctx)
@@ -119,6 +295,12 @@ static inline int dma_resv_lock(struct dma_resv *obj,
  * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle
  * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation
  * object may be locked by itself by passing NULL as @ctx.
+ *
+ * When a die situation is indicated by returning -EDEADLK all locks held by
+ * @ctx must be unlocked and then dma_resv_lock_slow_interruptible() called on
+ * @obj.
+ *
+ * Unlocked by calling dma_resv_unlock().
  */
 static inline int dma_resv_lock_interruptible(struct dma_resv *obj,
 					      struct ww_acquire_ctx *ctx)
@@ -134,6 +316,8 @@ static inline int dma_resv_lock_interruptible(struct dma_resv *obj,
  * Acquires the reservation object after a die case. This function
  * will sleep until the lock becomes available. See dma_resv_lock() as
  * well.
+ *
+ * See also dma_resv_lock_slow_interruptible() for the interruptible variant.
  */
 static inline void dma_resv_lock_slow(struct dma_resv *obj,
 				      struct ww_acquire_ctx *ctx)
@@ -167,7 +351,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj,
  * if they overlap with a writer.
  *
  * Also note that since no context is provided, no deadlock protection is
- * possible.
+ * possible, which is also not needed for a trylock.
  *
  * Returns true if the lock was acquired, false otherwise.
  */
@@ -193,6 +377,11 @@ static inline bool dma_resv_is_locked(struct dma_resv *obj)
  *
  * Returns the context used to lock a reservation object or NULL if no context
  * was used or the object is not locked at all.
+ *
+ * WARNING: This interface is pretty horrible, but TTM needs it because it
+ * doesn't pass the struct ww_acquire_ctx around in some very long callchains.
+ * Everyone else just uses it to check whether they're holding a reservation or
+ * not.
  */
 static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj)
 {
diff --git a/include/linux/io.h b/include/linux/io.h
index 9595151d800d..5fc800390fe4 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -132,6 +132,8 @@ static inline int arch_phys_wc_index(int handle)
 #endif
 #endif
 
+int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size);
+
 enum {
 	/* See memremap() kernel-doc for usage description... */
 	MEMREMAP_WB = 1 << 0,
@@ -166,4 +168,7 @@ static inline void arch_io_free_memtype_wc(resource_size_t base,
 }
 #endif
 
+int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start,
+				    resource_size_t size);
+
 #endif /* _LINUX_IO_H */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b066024c62e3..34de69b3b8ba 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
 
 void memblock_free_all(void);
+void memblock_free_ptr(void *ptr, size_t size);
 void reset_node_managed_pages(pg_data_t *pgdat);
 void reset_all_zones_managed_pages(void);
 
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index b179f1e3541a..96e113e23d04 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm)
 	up_read(&mm->mmap_lock);
 }
 
-static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
-{
-	if (mmap_read_trylock(mm)) {
-		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
-		return true;
-	}
-	return false;
-}
-
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
 	__mmap_lock_trace_released(mm, false);
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 0f12345c21fb..4669632bd72b 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -6,12 +6,9 @@
 #include <linux/limits.h>
 
 /*
- * In the fallback code below, we need to compute the minimum and
- * maximum values representable in a given type. These macros may also
- * be useful elsewhere, so we provide them outside the
- * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
- *
- * It would seem more obvious to do something like
+ * We need to compute the minimum and maximum values representable in a given
+ * type. These macros may also be useful elsewhere. It would seem more obvious
+ * to do something like:
  *
  * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
  * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
@@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	return unlikely(overflow);
 }
 
-#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
  * a, b and *d having the same type (similar to the min() and max()
@@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	__builtin_mul_overflow(__a, __b, __d);	\
 }))
 
-#else
-
-
-/* Checking for unsigned overflow is relatively easy without causing UB. */
-#define __unsigned_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a + __b;			\
-	*__d < __a;				\
-})
-#define __unsigned_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a - __b;			\
-	__a < __b;				\
-})
-/*
- * If one of a or b is a compile-time constant, this avoids a division.
- */
-#define __unsigned_mul_overflow(a, b, d) ({		\
-	typeof(a) __a = (a);				\
-	typeof(b) __b = (b);				\
-	typeof(d) __d = (d);				\
-	(void) (&__a == &__b);				\
-	(void) (&__a == __d);				\
-	*__d = __a * __b;				\
-	__builtin_constant_p(__b) ?			\
-	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
-	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
-})
-
-/*
- * For signed types, detecting overflow is much harder, especially if
- * we want to avoid UB. But the interface of these macros is such that
- * we must provide a result in *d, and in fact we must produce the
- * result promised by gcc's builtins, which is simply the possibly
- * wrapped-around value. Fortunately, we can just formally do the
- * operations in the widest relevant unsigned type (u64) and then
- * truncate the result - gcc is smart enough to generate the same code
- * with and without the (u64) casts.
- */
-
-/*
- * Adding two signed integers can overflow only if they have the same
- * sign, and overflow has happened iff the result has the opposite
- * sign.
- */
-#define __signed_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a + (u64)__b;		\
-	(((~(__a ^ __b)) & (*__d ^ __a))	\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Subtraction is similar, except that overflow can now happen only
- * when the signs are opposite. In this case, overflow has happened if
- * the result has the opposite sign of a.
- */
-#define __signed_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a - (u64)__b;		\
-	((((__a ^ __b)) & (*__d ^ __a))		\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Signed multiplication is rather hard. gcc always follows C99, so
- * division is truncated towards 0. This means that we can write the
- * overflow check like this:
- *
- * (a > 0 && (b > MAX/a || b < MIN/a)) ||
- * (a < -1 && (b > MIN/a || b < MAX/a) ||
- * (a == -1 && b == MIN)
- *
- * The redundant casts of -1 are to silence an annoying -Wtype-limits
- * (included in -Wextra) warning: When the type is u8 or u16, the
- * __b_c_e in check_mul_overflow obviously selects
- * __unsigned_mul_overflow, but unfortunately gcc still parses this
- * code and warns about the limited range of __b.
- */
-
-#define __signed_mul_overflow(a, b, d) ({				\
-	typeof(a) __a = (a);						\
-	typeof(b) __b = (b);						\
-	typeof(d) __d = (d);						\
-	typeof(a) __tmax = type_max(typeof(a));				\
-	typeof(a) __tmin = type_min(typeof(a));				\
-	(void) (&__a == &__b);						\
-	(void) (&__a == __d);						\
-	*__d = (u64)__a * (u64)__b;					\
-	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
-	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
-	(__b == (typeof(__b))-1 && __a == __tmin);			\
-})
-
-
-#define check_add_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d)))
-
-#define check_sub_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d)))
-
-#define check_mul_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d)))
-
-#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
-
 /** check_shl_overflow() - Calculate a left-shifted value and check overflow
  *
  * @a: Value to be shifted
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e12b524426b0..39039ce8ac4c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1471,6 +1471,7 @@ struct task_struct {
 					mce_whole_page : 1,
 					__mce_reserved : 62;
 	struct callback_head		mce_kill_me;
+	int				mce_count;
 #endif
 
 #ifdef CONFIG_KRETPROBES
diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h
deleted file mode 100644
index 3cca2b8fac43..000000000000
--- a/include/linux/seqno-fence.h
+++ /dev/null
@@ -1,109 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * seqno-fence, using a dma-buf to synchronize fencing
- *
- * Copyright (C) 2012 Texas Instruments
- * Copyright (C) 2012 Canonical Ltd
- * Authors:
- *   Rob Clark <robdclark@gmail.com>
- *   Maarten Lankhorst <maarten.lankhorst@canonical.com>
- */
-
-#ifndef __LINUX_SEQNO_FENCE_H
-#define __LINUX_SEQNO_FENCE_H
-
-#include <linux/dma-fence.h>
-#include <linux/dma-buf.h>
-
-enum seqno_fence_condition {
-	SEQNO_FENCE_WAIT_GEQUAL,
-	SEQNO_FENCE_WAIT_NONZERO
-};
-
-struct seqno_fence {
-	struct dma_fence base;
-
-	const struct dma_fence_ops *ops;
-	struct dma_buf *sync_buf;
-	uint32_t seqno_ofs;
-	enum seqno_fence_condition condition;
-};
-
-extern const struct dma_fence_ops seqno_fence_ops;
-
-/**
- * to_seqno_fence - cast a fence to a seqno_fence
- * @fence: fence to cast to a seqno_fence
- *
- * Returns NULL if the fence is not a seqno_fence,
- * or the seqno_fence otherwise.
- */
-static inline struct seqno_fence *
-to_seqno_fence(struct dma_fence *fence)
-{
-	if (fence->ops != &seqno_fence_ops)
-		return NULL;
-	return container_of(fence, struct seqno_fence, base);
-}
-
-/**
- * seqno_fence_init - initialize a seqno fence
- * @fence: seqno_fence to initialize
- * @lock: pointer to spinlock to use for fence
- * @sync_buf: buffer containing the memory location to signal on
- * @context: the execution context this fence is a part of
- * @seqno_ofs: the offset within @sync_buf
- * @seqno: the sequence # to signal on
- * @cond: fence wait condition
- * @ops: the fence_ops for operations on this seqno fence
- *
- * This function initializes a struct seqno_fence with passed parameters,
- * and takes a reference on sync_buf which is released on fence destruction.
- *
- * A seqno_fence is a dma_fence which can complete in software when
- * enable_signaling is called, but it also completes when
- * (s32)((sync_buf)[seqno_ofs] - seqno) >= 0 is true
- *
- * The seqno_fence will take a refcount on the sync_buf until it's
- * destroyed, but actual lifetime of sync_buf may be longer if one of the
- * callers take a reference to it.
- *
- * Certain hardware have instructions to insert this type of wait condition
- * in the command stream, so no intervention from software would be needed.
- * This type of fence can be destroyed before completed, however a reference
- * on the sync_buf dma-buf can be taken. It is encouraged to re-use the same
- * dma-buf for sync_buf, since mapping or unmapping the sync_buf to the
- * device's vm can be expensive.
- *
- * It is recommended for creators of seqno_fence to call dma_fence_signal()
- * before destruction. This will prevent possible issues from wraparound at
- * time of issue vs time of check, since users can check dma_fence_is_signaled()
- * before submitting instructions for the hardware to wait on the fence.
- * However, when ops.enable_signaling is not called, it doesn't have to be
- * done as soon as possible, just before there's any real danger of seqno
- * wraparound.
- */
-static inline void
-seqno_fence_init(struct seqno_fence *fence, spinlock_t *lock,
-		 struct dma_buf *sync_buf,  uint32_t context,
-		 uint32_t seqno_ofs, uint32_t seqno,
-		 enum seqno_fence_condition cond,
-		 const struct dma_fence_ops *ops)
-{
-	BUG_ON(!fence || !sync_buf || !ops);
-	BUG_ON(!ops->wait || !ops->enable_signaling ||
-	       !ops->get_driver_name || !ops->get_timeline_name);
-
-	/*
-	 * ops is used in dma_fence_init for get_driver_name, so needs to be
-	 * initialized first
-	 */
-	fence->ops = ops;
-	dma_fence_init(&fence->base, &seqno_fence_ops, lock, context, seqno);
-	get_dma_buf(sync_buf);
-	fence->sync_buf = sync_buf;
-	fence->seqno_ofs = seqno_ofs;
-	fence->condition = cond;
-}
-
-#endif /* __LINUX_SEQNO_FENCE_H */
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 9814fff58a69..76fbf92b04d9 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -93,4 +93,5 @@ extern void register_shrinker_prepared(struct shrinker *shrinker);
 extern int register_shrinker(struct shrinker *shrinker);
 extern void unregister_shrinker(struct shrinker *shrinker);
 extern void free_prealloced_shrinker(struct shrinker *shrinker);
+extern void synchronize_shrinkers(void);
 #endif
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6bdb0db3e825..841e2f0f5240 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk,
 	WRITE_ONCE(newsk->prev, prev);
 	WRITE_ONCE(next->prev, newsk);
 	WRITE_ONCE(prev->next, newsk);
-	list->qlen++;
+	WRITE_ONCE(list->qlen, list->qlen + 1);
 }
 
 static inline void __skb_queue_splice(const struct sk_buff_head *list,
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 5265024e8b90..207101a9c5c3 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -27,6 +27,12 @@ enum iter_type {
 	ITER_DISCARD,
 };
 
+struct iov_iter_state {
+	size_t iov_offset;
+	size_t count;
+	unsigned long nr_segs;
+};
+
 struct iov_iter {
 	u8 iter_type;
 	bool data_source;
@@ -47,7 +53,6 @@ struct iov_iter {
 		};
 		loff_t xarray_start;
 	};
-	size_t truncated;
 };
 
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
@@ -55,6 +60,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 	return i->iter_type;
 }
 
+static inline void iov_iter_save_state(struct iov_iter *iter,
+				       struct iov_iter_state *state)
+{
+	state->iov_offset = iter->iov_offset;
+	state->count = iter->count;
+	state->nr_segs = iter->nr_segs;
+}
+
 static inline bool iter_is_iovec(const struct iov_iter *i)
 {
 	return iov_iter_type(i) == ITER_IOVEC;
@@ -233,6 +246,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
+void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state);
 
 const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
 
@@ -255,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
 	 * conversion in assignement is by definition greater than all
 	 * values of size_t, including old i->count.
 	 */
-	if (i->count > count) {
-		i->truncated += i->count - count;
+	if (i->count > count)
 		i->count = count;
-	}
 }
 
 /*
@@ -267,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
  */
 static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
-	i->truncated -= count - i->count;
 	i->count = count;
 }