Merge 5.10.193 into android12-5.10-lts

Changes in 5.10.193
	objtool/x86: Fix SRSO mess
	NFSv4: fix out path in __nfs4_get_acl_uncached
	xprtrdma: Remap Receive buffers after a reconnect
	PCI: acpiphp: Reassign resources on bridge if necessary
	dlm: improve plock logging if interrupted
	dlm: replace usage of found with dedicated list iterator variable
	fs: dlm: add pid to debug log
	fs: dlm: change plock interrupted message to debug again
	fs: dlm: use dlm_plock_info for do_unlock_close
	fs: dlm: fix mismatch of plock results from userspace
	MIPS: cpu-features: Enable octeon_cache by cpu_type
	MIPS: cpu-features: Use boot_cpu_type for CPU type based features
	fbdev: Improve performance of sys_imageblit()
	fbdev: Fix sys_imageblit() for arbitrary image widths
	fbdev: fix potential OOB read in fast_imageblit()
	dm integrity: increase RECALC_SECTORS to improve recalculate speed
	dm integrity: reduce vmalloc space footprint on 32-bit architectures
	ALSA: pcm: Fix potential data race at PCM memory allocation helpers
	drm/amd/display: do not wait for mpc idle if tg is disabled
	drm/amd/display: check TG is non-null before checking if enabled
	libceph, rbd: ignore addr->type while comparing in some cases
	rbd: make get_lock_owner_info() return a single locker or NULL
	rbd: retrieve and check lock owner twice before blocklisting
	rbd: prevent busy loop when requesting exclusive lock
	tracing: Fix cpu buffers unavailable due to 'record_disabled' missed
	tracing: Fix memleak due to race between current_tracer and trace
	octeontx2-af: SDP: fix receive link config
	sock: annotate data-races around prot->memory_pressure
	dccp: annotate data-races in dccp_poll()
	ipvlan: Fix a reference count leak warning in ipvlan_ns_exit()
	net: bgmac: Fix return value check for fixed_phy_register()
	net: bcmgenet: Fix return value check for fixed_phy_register()
	net: validate veth and vxcan peer ifindexes
	ice: fix receive buffer size miscalculation
	igb: Avoid starting unnecessary workqueues
	net/sched: fix a qdisc modification with ambiguous command request
	netfilter: nf_tables: fix out of memory error handling
	rtnetlink: return ENODEV when ifname does not exist and group is given
	rtnetlink: Reject negative ifindexes in RTM_NEWLINK
	net: remove bond_slave_has_mac_rcu()
	bonding: fix macvlan over alb bond support
	ibmveth: Use dcbf rather than dcbfl
	NFSv4: Fix dropped lock for racing OPEN and delegation return
	clk: Fix slab-out-of-bounds error in devm_clk_release()
	mm: add a call to flush_cache_vmap() in vmap_pfn()
	NFS: Fix a use after free in nfs_direct_join_group()
	nfsd: Fix race to FREE_STATEID and cl_revoked
	selinux: set next pointer before attaching to list
	batman-adv: Trigger events for auto adjusted MTU
	batman-adv: Don't increase MTU when set by user
	batman-adv: Do not get eth header before batadv_check_management_packet
	batman-adv: Fix TT global entry leak when client roamed back
	batman-adv: Fix batadv_v_ogm_aggr_send memory leak
	batman-adv: Hold rtnl lock during MTU update via netlink
	lib/clz_ctz.c: Fix __clzdi2() and __ctzdi2() for 32-bit kernels
	radix tree: remove unused variable
	of: dynamic: Refactor action prints to not use "%pOF" inside devtree_lock
	media: vcodec: Fix potential array out-of-bounds in encoder queue_setup
	PCI: acpiphp: Use pci_assign_unassigned_bridge_resources() only for non-root bus
	drm/vmwgfx: Fix shader stage validation
	drm/display/dp: Fix the DP DSC Receiver cap size
	x86/fpu: Set X86_FEATURE_OSXSAVE feature after enabling OSXSAVE in CR4
	torture: Fix hang during kthread shutdown phase
	tick: Detect and fix jiffies update stall
	timers/nohz: Switch to ONESHOT_STOPPED in the low-res handler when the tick is stopped
	cgroup/cpuset: Rename functions dealing with DEADLINE accounting
	sched/cpuset: Bring back cpuset_mutex
	sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets
	cgroup/cpuset: Iterate only if DEADLINE tasks are present
	sched/deadline: Create DL BW alloc, free & check overflow interface
	cgroup/cpuset: Free DL BW in case can_attach() fails
	drm/i915: Fix premature release of request's reusable memory
	ASoC: rt711: add two jack detection modes
	scsi: snic: Fix double free in snic_tgt_create()
	scsi: core: raid_class: Remove raid_component_add()
	clk: Fix undefined reference to `clk_rate_exclusive_{get,put}'
	pinctrl: renesas: rza2: Add lock around pinctrl_generic{{add,remove}_group,{add,remove}_function}
	dma-buf/sw_sync: Avoid recursive lock during fence signal
	mm,hwpoison: refactor get_any_page
	mm: fix page reference leak in soft_offline_page()
	mm: memory-failure: kill soft_offline_free_page()
	mm: memory-failure: fix unexpected return value in soft_offline_page()
	ASoC: Intel: sof_sdw: include rt711.h for RT711 JD mode
	mm,hwpoison: fix printing of page flags
	Linux 5.10.193

Change-Id: I7c6ce55cbc73cef27a5cbe8954131a052b67dac2
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 192
+SUBLEVEL = 193
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/mips/include/asm/cpu-features.h

@@ -126,7 +126,24 @@
 #define cpu_has_tx39_cache	__opt(MIPS_CPU_TX39_CACHE)
 #endif
 #ifndef cpu_has_octeon_cache
-#define cpu_has_octeon_cache	0
+#define cpu_has_octeon_cache						\
+({									\
+	int __res;							\
+									\
+	switch (boot_cpu_type()) {					\
+	case CPU_CAVIUM_OCTEON:						\
+	case CPU_CAVIUM_OCTEON_PLUS:					\
+	case CPU_CAVIUM_OCTEON2:					\
+	case CPU_CAVIUM_OCTEON3:					\
+		__res = 1;						\
+		break;							\
+									\
+	default:							\
+		__res = 0;						\
+	}								\
+									\
+	__res;								\
+})
 #endif
 /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work.  */
 #ifndef cpu_has_fpu
@@ -353,7 +370,7 @@
 ({									\
 	int __res;							\
 									\
-	switch (current_cpu_type()) {					\
+	switch (boot_cpu_type()) {					\
 	case CPU_M14KC:							\
 	case CPU_74K:							\
 	case CPU_1074K:							\

arch/x86/kernel/fpu/xstate.c

@@ -892,6 +892,14 @@ void __init fpu__init_system_xstate(void)
 	setup_init_fpu_buf();
 	setup_xstate_comp_offsets();
 	setup_supervisor_only_offsets();
+
+	/*
+	 * CPU capabilities initialization runs before FPU init. So
+	 * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely
+	 * functional, set the feature bit so depending code works.
+	 */
+	setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+
 	print_xstate_offset_size();
 
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",

drivers/block/rbd.c

@@ -3740,7 +3740,7 @@ static int rbd_lock(struct rbd_device *rbd_dev)
 	ret = ceph_cls_lock(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc,
 			    RBD_LOCK_NAME, CEPH_CLS_LOCK_EXCLUSIVE, cookie,
 			    RBD_LOCK_TAG, "", 0);
-	if (ret)
+	if (ret && ret != -EEXIST)
 		return ret;
 
 	__rbd_lock(rbd_dev, cookie);
@@ -3914,10 +3914,26 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result)
 	list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list);
 }
 
-static int get_lock_owner_info(struct rbd_device *rbd_dev,
-			       struct ceph_locker **lockers, u32 *num_lockers)
+static bool locker_equal(const struct ceph_locker *lhs,
+			 const struct ceph_locker *rhs)
+{
+	return lhs->id.name.type == rhs->id.name.type &&
+	       lhs->id.name.num == rhs->id.name.num &&
+	       !strcmp(lhs->id.cookie, rhs->id.cookie) &&
+	       ceph_addr_equal_no_type(&lhs->info.addr, &rhs->info.addr);
+}
+
+static void free_locker(struct ceph_locker *locker)
+{
+	if (locker)
+		ceph_free_lockers(locker, 1);
+}
+
+static struct ceph_locker *get_lock_owner_info(struct rbd_device *rbd_dev)
 {
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+	struct ceph_locker *lockers;
+	u32 num_lockers;
 	u8 lock_type;
 	char *lock_tag;
 	int ret;
@@ -3926,39 +3942,45 @@ static int get_lock_owner_info(struct rbd_device *rbd_dev,
 
 	ret = ceph_cls_lock_info(osdc, &rbd_dev->header_oid,
 				 &rbd_dev->header_oloc, RBD_LOCK_NAME,
-				 &lock_type, &lock_tag, lockers, num_lockers);
-	if (ret)
-		return ret;
+				 &lock_type, &lock_tag, &lockers, &num_lockers);
+	if (ret) {
+		rbd_warn(rbd_dev, "failed to get header lockers: %d", ret);
+		return ERR_PTR(ret);
+	}
 
-	if (*num_lockers == 0) {
+	if (num_lockers == 0) {
 		dout("%s rbd_dev %p no lockers detected\n", __func__, rbd_dev);
+		lockers = NULL;
 		goto out;
 	}
 
 	if (strcmp(lock_tag, RBD_LOCK_TAG)) {
 		rbd_warn(rbd_dev, "locked by external mechanism, tag %s",
 			 lock_tag);
-		ret = -EBUSY;
-		goto out;
+		goto err_busy;
 	}
 
 	if (lock_type == CEPH_CLS_LOCK_SHARED) {
 		rbd_warn(rbd_dev, "shared lock type detected");
-		ret = -EBUSY;
-		goto out;
+		goto err_busy;
 	}
 
-	if (strncmp((*lockers)[0].id.cookie, RBD_LOCK_COOKIE_PREFIX,
+	WARN_ON(num_lockers != 1);
+	if (strncmp(lockers[0].id.cookie, RBD_LOCK_COOKIE_PREFIX,
 		    strlen(RBD_LOCK_COOKIE_PREFIX))) {
 		rbd_warn(rbd_dev, "locked by external mechanism, cookie %s",
-			 (*lockers)[0].id.cookie);
-		ret = -EBUSY;
-		goto out;
+			 lockers[0].id.cookie);
+		goto err_busy;
 	}
 
 out:
 	kfree(lock_tag);
-	return ret;
+	return lockers;
+
+err_busy:
+	kfree(lock_tag);
+	ceph_free_lockers(lockers, num_lockers);
+	return ERR_PTR(-EBUSY);
 }
 
 static int find_watcher(struct rbd_device *rbd_dev,
@@ -3974,13 +3996,19 @@ static int find_watcher(struct rbd_device *rbd_dev,
 	ret = ceph_osdc_list_watchers(osdc, &rbd_dev->header_oid,
 				      &rbd_dev->header_oloc, &watchers,
 				      &num_watchers);
-	if (ret)
+	if (ret) {
+		rbd_warn(rbd_dev, "failed to get watchers: %d", ret);
 		return ret;
+	}
 
 	sscanf(locker->id.cookie, RBD_LOCK_COOKIE_PREFIX " %llu", &cookie);
 	for (i = 0; i < num_watchers; i++) {
-		if (!memcmp(&watchers[i].addr, &locker->info.addr,
-			    sizeof(locker->info.addr)) &&
+		/*
+		 * Ignore addr->type while comparing.  This mimics
+		 * entity_addr_t::get_legacy_str() + strcmp().
+		 */
+		if (ceph_addr_equal_no_type(&watchers[i].addr,
+					    &locker->info.addr) &&
 		    watchers[i].cookie == cookie) {
 			struct rbd_client_id cid = {
 				.gid = le64_to_cpu(watchers[i].name.num),
@@ -4008,51 +4036,72 @@ out:
 static int rbd_try_lock(struct rbd_device *rbd_dev)
 {
 	struct ceph_client *client = rbd_dev->rbd_client->client;
-	struct ceph_locker *lockers;
-	u32 num_lockers;
+	struct ceph_locker *locker, *refreshed_locker;
 	int ret;
 
 	for (;;) {
+		locker = refreshed_locker = NULL;
+
 		ret = rbd_lock(rbd_dev);
-		if (ret != -EBUSY)
-			return ret;
+		if (!ret)
+			goto out;
+		if (ret != -EBUSY) {
+			rbd_warn(rbd_dev, "failed to lock header: %d", ret);
+			goto out;
+		}
 
 		/* determine if the current lock holder is still alive */
-		ret = get_lock_owner_info(rbd_dev, &lockers, &num_lockers);
-		if (ret)
-			return ret;
-
-		if (num_lockers == 0)
+		locker = get_lock_owner_info(rbd_dev);
+		if (IS_ERR(locker)) {
+			ret = PTR_ERR(locker);
+			locker = NULL;
+			goto out;
+		}
+		if (!locker)
 			goto again;
 
-		ret = find_watcher(rbd_dev, lockers);
+		ret = find_watcher(rbd_dev, locker);
 		if (ret)
 			goto out; /* request lock or error */
 
+		refreshed_locker = get_lock_owner_info(rbd_dev);
+		if (IS_ERR(refreshed_locker)) {
+			ret = PTR_ERR(refreshed_locker);
+			refreshed_locker = NULL;
+			goto out;
+		}
+		if (!refreshed_locker ||
+		    !locker_equal(locker, refreshed_locker))
+			goto again;
+
 		rbd_warn(rbd_dev, "breaking header lock owned by %s%llu",
-			 ENTITY_NAME(lockers[0].id.name));
+			 ENTITY_NAME(locker->id.name));
 
 		ret = ceph_monc_blocklist_add(&client->monc,
-					      &lockers[0].info.addr);
+					      &locker->info.addr);
 		if (ret) {
-			rbd_warn(rbd_dev, "blocklist of %s%llu failed: %d",
-				 ENTITY_NAME(lockers[0].id.name), ret);
+			rbd_warn(rbd_dev, "failed to blocklist %s%llu: %d",
+				 ENTITY_NAME(locker->id.name), ret);
 			goto out;
 		}
 
 		ret = ceph_cls_break_lock(&client->osdc, &rbd_dev->header_oid,
 					  &rbd_dev->header_oloc, RBD_LOCK_NAME,
-					  lockers[0].id.cookie,
-					  &lockers[0].id.name);
-		if (ret && ret != -ENOENT)
+					  locker->id.cookie, &locker->id.name);
+		if (ret && ret != -ENOENT) {
+			rbd_warn(rbd_dev, "failed to break header lock: %d",
+				 ret);
 			goto out;
+		}
 
 again:
-		ceph_free_lockers(lockers, num_lockers);
+		free_locker(refreshed_locker);
+		free_locker(locker);
 	}
 
 out:
-	ceph_free_lockers(lockers, num_lockers);
+	free_locker(refreshed_locker);
+	free_locker(locker);
 	return ret;
 }
 
@@ -4102,11 +4151,8 @@ static int rbd_try_acquire_lock(struct rbd_device *rbd_dev)
 
 	ret = rbd_try_lock(rbd_dev);
 	if (ret < 0) {
-		rbd_warn(rbd_dev, "failed to lock header: %d", ret);
-		if (ret == -EBLOCKLISTED)
-			goto out;
-
-		ret = 1; /* request lock anyway */
+		rbd_warn(rbd_dev, "failed to acquire lock: %d", ret);
+		goto out;
 	}
 	if (ret > 0) {
 		up_write(&rbd_dev->lock_rwsem);
@@ -6656,12 +6702,11 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
 		cancel_delayed_work_sync(&rbd_dev->lock_dwork);
 		if (!ret)
 			ret = -ETIMEDOUT;
-	}
 
-	if (ret) {
-		rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret);
-		return ret;
+		rbd_warn(rbd_dev, "failed to acquire lock: %ld", ret);
 	}
+	if (ret)
+		return ret;
 
 	/*
 	 * The lock may have been released by now, unless automatic lock

drivers/clk/clk-devres.c

@@ -205,18 +205,19 @@ EXPORT_SYMBOL(devm_clk_put);
 struct clk *devm_get_clk_from_child(struct device *dev,
 				    struct device_node *np, const char *con_id)
 {
-	struct clk **ptr, *clk;
+	struct devm_clk_state *state;
+	struct clk *clk;
 
-	ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
+	state = devres_alloc(devm_clk_release, sizeof(*state), GFP_KERNEL);
+	if (!state)
 		return ERR_PTR(-ENOMEM);
 
 	clk = of_clk_get_by_name(np, con_id);
 	if (!IS_ERR(clk)) {
-		*ptr = clk;
-		devres_add(dev, ptr);
+		state->clk = clk;
+		devres_add(dev, state);
 	} else {
-		devres_free(ptr);
+		devres_free(state);
 	}
 
 	return clk;

drivers/dma-buf/sw_sync.c

@@ -191,6 +191,7 @@ static const struct dma_fence_ops timeline_fence_ops = {
  */
 static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
 {
+	LIST_HEAD(signalled);
 	struct sync_pt *pt, *next;
 
 	trace_sync_timeline(obj);
@@ -203,21 +204,20 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
 		if (!timeline_fence_signaled(&pt->base))
 			break;
 
-		list_del_init(&pt->link);
+		dma_fence_get(&pt->base);
+
+		list_move_tail(&pt->link, &signalled);
 		rb_erase(&pt->node, &obj->pt_tree);
 
-		/*
-		 * A signal callback may release the last reference to this
-		 * fence, causing it to be freed. That operation has to be
-		 * last to avoid a use after free inside this loop, and must
-		 * be after we remove the fence from the timeline in order to
-		 * prevent deadlocking on timeline->lock inside
-		 * timeline_fence_release().
-		 */
 		dma_fence_signal_locked(&pt->base);
 	}
 
 	spin_unlock_irq(&obj->lock);
+
+	list_for_each_entry_safe(pt, next, &signalled, link) {
+		list_del_init(&pt->link);
+		dma_fence_put(&pt->base);
+	}
 }
 
 /**

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -3282,7 +3282,9 @@ void dcn10_wait_for_mpcc_disconnect(
 		if (pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst]) {
 			struct hubp *hubp = get_hubp_by_inst(res_pool, mpcc_inst);
 
-			res_pool->mpc->funcs->wait_for_idle(res_pool->mpc, mpcc_inst);
+			if (pipe_ctx->stream_res.tg &&
+				pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg))
+				res_pool->mpc->funcs->wait_for_idle(res_pool->mpc, mpcc_inst);
 			pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst] = false;
 			hubp->funcs->set_blank(hubp, true);
 		}

drivers/gpu/drm/i915/i915_active.c

@@ -457,8 +457,11 @@ int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence)
 		}
 	} while (unlikely(is_barrier(active)));
 
-	if (!__i915_active_fence_set(active, fence))
+	fence = __i915_active_fence_set(active, fence);
+	if (!fence)
 		__i915_active_acquire(ref);
+	else
+		dma_fence_put(fence);
 
 out:
 	i915_active_release(ref);
@@ -477,13 +480,9 @@ __i915_active_set_fence(struct i915_active *ref,
 		return NULL;
 	}
 
-	rcu_read_lock();
 	prev = __i915_active_fence_set(active, fence);
-	if (prev)
-		prev = dma_fence_get_rcu(prev);
-	else
+	if (!prev)
 		__i915_active_acquire(ref);
-	rcu_read_unlock();
 
 	return prev;
 }
@@ -1050,10 +1049,11 @@ void i915_request_add_active_barriers(struct i915_request *rq)
  *
  * Records the new @fence as the last active fence along its timeline in
  * this active tracker, moving the tracking callbacks from the previous
- * fence onto this one. Returns the previous fence (if not already completed),
- * which the caller must ensure is executed before the new fence. To ensure
- * that the order of fences within the timeline of the i915_active_fence is
- * understood, it should be locked by the caller.
+ * fence onto this one. Gets and returns a reference to the previous fence
+ * (if not already completed), which the caller must put after making sure
+ * that it is executed before the new fence. To ensure that the order of
+ * fences within the timeline of the i915_active_fence is understood, it
+ * should be locked by the caller.
  */
 struct dma_fence *
 __i915_active_fence_set(struct i915_active_fence *active,
@@ -1062,7 +1062,23 @@ __i915_active_fence_set(struct i915_active_fence *active,
 	struct dma_fence *prev;
 	unsigned long flags;
 
-	if (fence == rcu_access_pointer(active->fence))
+	/*
+	 * In case of fences embedded in i915_requests, their memory is
+	 * SLAB_FAILSAFE_BY_RCU, then it can be reused right after release
+	 * by new requests.  Then, there is a risk of passing back a pointer
+	 * to a new, completely unrelated fence that reuses the same memory
+	 * while tracked under a different active tracker.  Combined with i915
+	 * perf open/close operations that build await dependencies between
+	 * engine kernel context requests and user requests from different
+	 * timelines, this can lead to dependency loops and infinite waits.
+	 *
+	 * As a countermeasure, we try to get a reference to the active->fence
+	 * first, so if we succeed and pass it back to our user then it is not
+	 * released and potentially reused by an unrelated request before the
+	 * user has a chance to set up an await dependency on it.
+	 */
+	prev = i915_active_fence_get(active);
+	if (fence == prev)
 		return fence;
 
 	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags));
@@ -1071,27 +1087,56 @@ __i915_active_fence_set(struct i915_active_fence *active,
 	 * Consider that we have two threads arriving (A and B), with
 	 * C already resident as the active->fence.
 	 *
-	 * A does the xchg first, and so it sees C or NULL depending
-	 * on the timing of the interrupt handler. If it is NULL, the
-	 * previous fence must have been signaled and we know that
-	 * we are first on the timeline. If it is still present,
-	 * we acquire the lock on that fence and serialise with the interrupt
-	 * handler, in the process removing it from any future interrupt
-	 * callback. A will then wait on C before executing (if present).
-	 *
-	 * As B is second, it sees A as the previous fence and so waits for
-	 * it to complete its transition and takes over the occupancy for
-	 * itself -- remembering that it needs to wait on A before executing.
+	 * Both A and B have got a reference to C or NULL, depending on the
+	 * timing of the interrupt handler.  Let's assume that if A has got C
+	 * then it has locked C first (before B).
 	 *
 	 * Note the strong ordering of the timeline also provides consistent
 	 * nesting rules for the fence->lock; the inner lock is always the
 	 * older lock.
 	 */
 	spin_lock_irqsave(fence->lock, flags);
-	prev = xchg(__active_fence_slot(active), fence);
-	if (prev) {
-		GEM_BUG_ON(prev == fence);
+	if (prev)
 		spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING);
+
+	/*
+	 * A does the cmpxchg first, and so it sees C or NULL, as before, or
+	 * something else, depending on the timing of other threads and/or
+	 * interrupt handler.  If not the same as before then A unlocks C if
+	 * applicable and retries, starting from an attempt to get a new
+	 * active->fence.  Meanwhile, B follows the same path as A.
+	 * Once A succeeds with cmpxch, B fails again, retires, gets A from
+	 * active->fence, locks it as soon as A completes, and possibly
+	 * succeeds with cmpxchg.
+	 */
+	while (cmpxchg(__active_fence_slot(active), prev, fence) != prev) {
+		if (prev) {
+			spin_unlock(prev->lock);
+			dma_fence_put(prev);
+		}
+		spin_unlock_irqrestore(fence->lock, flags);
+
+		prev = i915_active_fence_get(active);
+		GEM_BUG_ON(prev == fence);
+
+		spin_lock_irqsave(fence->lock, flags);
+		if (prev)
+			spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING);
+	}
+
+	/*
+	 * If prev is NULL then the previous fence must have been signaled
+	 * and we know that we are first on the timeline.  If it is still
+	 * present then, having the lock on that fence already acquired, we
+	 * serialise with the interrupt handler, in the process of removing it
+	 * from any future interrupt callback.  A will then wait on C before
+	 * executing (if present).
+	 *
+	 * As B is second, it sees A as the previous fence and so waits for
+	 * it to complete its transition and takes over the occupancy for
+	 * itself -- remembering that it needs to wait on A before executing.
+	 */
+	if (prev) {
 		__list_del_entry(&active->cb.node);
 		spin_unlock(prev->lock); /* serialise with prev->cb_list */
 	}
@@ -1108,11 +1153,7 @@ int i915_active_fence_set(struct i915_active_fence *active,
 	int err = 0;
 
 	/* Must maintain timeline ordering wrt previous active requests */
-	rcu_read_lock();
 	fence = __i915_active_fence_set(active, &rq->fence);
-	if (fence) /* but the previous fence may not belong to that timeline! */
-		fence = dma_fence_get_rcu(fence);
-	rcu_read_unlock();
 	if (fence) {
 		err = i915_request_await_dma_fence(rq, fence);
 		dma_fence_put(fence);

drivers/gpu/drm/i915/i915_request.c

@@ -1525,6 +1525,8 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 &rq->dep,
 							 0);
 	}
+	if (prev)
+		i915_request_put(prev);
 
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after

drivers/gpu/drm/vmwgfx/vmwgfx_drv.h

@@ -1606,4 +1606,17 @@ static inline void vmw_mmio_write(u32 value, u32 *addr)
 {
 	WRITE_ONCE(*addr, value);
 }
+
+static inline bool vmw_shadertype_is_valid(enum vmw_sm_type shader_model,
+					   u32 shader_type)
+{
+	SVGA3dShaderType max_allowed = SVGA3D_SHADERTYPE_PREDX_MAX;
+
+	if (shader_model >= VMW_SM_5)
+		max_allowed = SVGA3D_SHADERTYPE_MAX;
+	else if (shader_model >= VMW_SM_4)
+		max_allowed = SVGA3D_SHADERTYPE_DX10_MAX;
+	return shader_type >= SVGA3D_SHADERTYPE_MIN && shader_type < max_allowed;
+}
+
 #endif

drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c

@@ -1998,7 +1998,7 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv,
 
 	cmd = container_of(header, typeof(*cmd), header);
 
-	if (cmd->body.type >= SVGA3D_SHADERTYPE_PREDX_MAX) {
+	if (!vmw_shadertype_is_valid(VMW_SM_LEGACY, cmd->body.type)) {
 		VMW_DEBUG_USER("Illegal shader type %u.\n",
 			       (unsigned int) cmd->body.type);
 		return -EINVAL;
@@ -2120,8 +2120,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv,
 				      SVGA3dCmdHeader *header)
 {
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetSingleConstantBuffer);
-	SVGA3dShaderType max_shader_num = has_sm5_context(dev_priv) ?
-		SVGA3D_NUM_SHADERTYPE : SVGA3D_NUM_SHADERTYPE_DX10;
 
 	struct vmw_resource *res = NULL;
 	struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context);
@@ -2138,6 +2136,14 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
+	if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type) ||
+	    cmd->body.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) {
+		VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n",
+			       (unsigned int) cmd->body.type,
+			       (unsigned int) cmd->body.slot);
+		return -EINVAL;
+	}
+
 	binding.bi.ctx = ctx_node->ctx;
 	binding.bi.res = res;
 	binding.bi.bt = vmw_ctx_binding_cb;
@@ -2146,14 +2152,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv,
 	binding.size = cmd->body.sizeInBytes;
 	binding.slot = cmd->body.slot;
 
-	if (binding.shader_slot >= max_shader_num ||
-	    binding.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) {
-		VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n",
-			       (unsigned int) cmd->body.type,
-			       (unsigned int) binding.slot);
-		return -EINVAL;
-	}
-
 	vmw_binding_add(ctx_node->staged, &binding.bi, binding.shader_slot,
 			binding.slot);
 
@@ -2174,15 +2172,13 @@ static int vmw_cmd_dx_set_shader_res(struct vmw_private *dev_priv,
 {
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShaderResources) =
 		container_of(header, typeof(*cmd), header);
-	SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ?
-		SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX;
 
 	u32 num_sr_view = (cmd->header.size - sizeof(cmd->body)) /
 		sizeof(SVGA3dShaderResourceViewId);
 
 	if ((u64) cmd->body.startView + (u64) num_sr_view >
 	    (u64) SVGA3D_DX_MAX_SRVIEWS ||
-	    cmd->body.type >= max_allowed) {
+	    !vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) {
 		VMW_DEBUG_USER("Invalid shader binding.\n");
 		return -EINVAL;
 	}
@@ -2206,8 +2202,6 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv,
 				 SVGA3dCmdHeader *header)
 {
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShader);
-	SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ?
-		SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX;
 	struct vmw_resource *res = NULL;
 	struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context);
 	struct vmw_ctx_bindinfo_shader binding;
@@ -2218,8 +2212,7 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv,
 
 	cmd = container_of(header, typeof(*cmd), header);
 
-	if (cmd->body.type >= max_allowed ||
-	    cmd->body.type < SVGA3D_SHADERTYPE_MIN) {
+	if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) {
 		VMW_DEBUG_USER("Illegal shader type %u.\n",
 			       (unsigned int) cmd->body.type);
 		return -EINVAL;

drivers/md/dm-integrity.c

@@ -31,11 +31,11 @@
 #define DEFAULT_BUFFER_SECTORS		128
 #define DEFAULT_JOURNAL_WATERMARK	50
 #define DEFAULT_SYNC_MSEC		10000
-#define DEFAULT_MAX_JOURNAL_SECTORS	131072
+#define DEFAULT_MAX_JOURNAL_SECTORS	(IS_ENABLED(CONFIG_64BIT) ? 131072 : 8192)
 #define MIN_LOG2_INTERLEAVE_SECTORS	3
 #define MAX_LOG2_INTERLEAVE_SECTORS	31
 #define METADATA_WORKQUEUE_MAX_ACTIVE	16
-#define RECALC_SECTORS			8192
+#define RECALC_SECTORS			(IS_ENABLED(CONFIG_64BIT) ? 32768 : 2048)
 #define RECALC_WRITE_SUPER		16
 #define BITMAP_BLOCK_SIZE		4096	/* don't change it */
 #define BITMAP_FLUSH_INTERVAL		(10 * HZ)

drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c

@@ -729,6 +729,8 @@ static int vb2ops_venc_queue_setup(struct vb2_queue *vq,
 		return -EINVAL;
 
 	if (*nplanes) {
+		if (*nplanes != q_data->fmt->num_planes)
+			return -EINVAL;
 		for (i = 0; i < *nplanes; i++)
 			if (sizes[i] < q_data->sizeimage[i])
 				return -EINVAL;

drivers/net/bonding/bond_alb.c

@@ -656,10 +656,10 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		return NULL;
 	arp = (struct arp_pkt *)skb_network_header(skb);
 
-	/* Don't modify or load balance ARPs that do not originate locally
-	 * (e.g.,arrive via a bridge).
+	/* Don't modify or load balance ARPs that do not originate
+	 * from the bond itself or a VLAN directly above the bond.
 	 */
-	if (!bond_slave_has_mac_rx(bond, arp->mac_src))
+	if (!bond_slave_has_mac_rcu(bond, arp->mac_src))
 		return NULL;
 
 	if (arp->op_code == htons(ARPOP_REPLY)) {

drivers/net/can/vxcan.c

@@ -179,12 +179,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev,
 
 		nla_peer = data[VXCAN_INFO_PEER];
 		ifmp = nla_data(nla_peer);
-		err = rtnl_nla_parse_ifla(peer_tb,
-					  nla_data(nla_peer) +
-					  sizeof(struct ifinfomsg),
-					  nla_len(nla_peer) -
-					  sizeof(struct ifinfomsg),
-					  NULL);
+		err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack);
 		if (err < 0)
 			return err;
 

drivers/net/ethernet/broadcom/bgmac.c

@@ -1448,7 +1448,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac)
 	int err;
 
 	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
-	if (!phy_dev || IS_ERR(phy_dev)) {
+	if (IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
 		return -ENODEV;
 	}

drivers/net/ethernet/broadcom/genet/bcmmii.c

@@ -568,7 +568,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 		};
 
 		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
-		if (!phydev || IS_ERR(phydev)) {
+		if (IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register fixed PHY device\n");
 			return -ENODEV;
 		}

drivers/net/ethernet/ibm/ibmveth.c

@@ -196,7 +196,7 @@ static inline void ibmveth_flush_buffer(void *addr, unsigned long length)
 	unsigned long offset;
 
 	for (offset = 0; offset < length; offset += SMP_CACHE_BYTES)
-		asm("dcbfl %0,%1" :: "b" (addr), "r" (offset));
+		asm("dcbf %0,%1,1" :: "b" (addr), "r" (offset));
 }
 
 /* replenish the buffers for a pool.  note that we don't need to

drivers/net/ethernet/intel/ice/ice_base.c

@@ -353,7 +353,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* Receive Packet Data Buffer Size.
 	 * The Packet Data Buffer Size is defined in 128 byte units.
 	 */
-	rlan_ctx.dbuf = ring->rx_buf_len >> ICE_RLAN_CTX_DBUF_S;
+	rlan_ctx.dbuf = DIV_ROUND_UP(ring->rx_buf_len,
+				     BIT_ULL(ICE_RLAN_CTX_DBUF_S));
 
 	/* use 32 byte descriptors */
 	rlan_ctx.dsize = 1;

drivers/net/ethernet/intel/igb/igb_ptp.c

@@ -1262,18 +1262,6 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		return;
 	}
 
-	spin_lock_init(&adapter->tmreg_lock);
-	INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work);
-
-	if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK)
-		INIT_DELAYED_WORK(&adapter->ptp_overflow_work,
-				  igb_ptp_overflow_check);
-
-	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
-	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
-
-	igb_ptp_reset(adapter);
-
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
@@ -1283,6 +1271,18 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		dev_info(&adapter->pdev->dev, "added PHC on %s\n",
 			 adapter->netdev->name);
 		adapter->ptp_flags |= IGB_PTP_ENABLED;
+
+		spin_lock_init(&adapter->tmreg_lock);
+		INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work);
+
+		if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK)
+			INIT_DELAYED_WORK(&adapter->ptp_overflow_work,
+					  igb_ptp_overflow_check);
+
+		adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+		adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+
+		igb_ptp_reset(adapter);
 	}
 }