15 files changed, 97 insertions, 77 deletions

diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index ca3cd9aaa6ce..7b4afb7d96db 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  * Copyright (c) 2016 Facebook
  */
diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h
index e546b18d27da..a4b040793f44 100644
--- a/kernel/bpf/disasm.h
+++ b/kernel/bpf/disasm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  * Copyright (c) 2016 Facebook
  */
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index e8eefdf8cf3e..09a3fd97d329 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -179,7 +179,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	 * with build_id.
 	 */
 	if (!user || !current || !current->mm || irq_work_busy ||
-	    !mmap_read_trylock_non_owner(current->mm)) {
+	    !mmap_read_trylock(current->mm)) {
 		/* cannot access current->mm, fall back to ips */
 		for (i = 0; i < trace_nr; i++) {
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
@@ -204,9 +204,15 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	}
 
 	if (!work) {
-		mmap_read_unlock_non_owner(current->mm);
+		mmap_read_unlock(current->mm);
 	} else {
 		work->mm = current->mm;
+
+		/* The lock will be released once we're out of interrupt
+		 * context. Tell lockdep that we've released it now so
+		 * it doesn't complain that we forgot to release it.
+		 */
+		rwsem_release(&current->mm->mmap_lock.dep_map, _RET_IP_);
 		irq_work_queue(&work->irq_work);
 	}
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 047ac4b4703b..e76b55917905 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9912,6 +9912,8 @@ static int check_btf_line(struct bpf_verifier_env *env,
 	nr_linfo = attr->line_info_cnt;
 	if (!nr_linfo)
 		return 0;
+	if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info))
+		return -EINVAL;
 
 	rec_size = attr->line_info_rec_size;
 	if (rec_size < MIN_BPF_LINEINFO_SIZE ||
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 881ce1470beb..8afa8690d288 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6572,74 +6572,44 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v)
  */
 #ifdef CONFIG_SOCK_CGROUP_DATA
 
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-
-DEFINE_SPINLOCK(cgroup_sk_update_lock);
-static bool cgroup_sk_alloc_disabled __read_mostly;
-
-void cgroup_sk_alloc_disable(void)
-{
-	if (cgroup_sk_alloc_disabled)
-		return;
-	pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n");
-	cgroup_sk_alloc_disabled = true;
-}
-
-#else
-
-#define cgroup_sk_alloc_disabled	false
-
-#endif
-
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled) {
-		skcd->no_refcnt = 1;
-		return;
-	}
-
 	/* Don't associate the sock with unrelated interrupted task's cgroup. */
 	if (in_interrupt())
 		return;
 
 	rcu_read_lock();
-
 	while (true) {
 		struct css_set *cset;
 
 		cset = task_css_set(current);
 		if (likely(cgroup_tryget(cset->dfl_cgrp))) {
-			skcd->val = (unsigned long)cset->dfl_cgrp;
+			skcd->cgroup = cset->dfl_cgrp;
 			cgroup_bpf_get(cset->dfl_cgrp);
 			break;
 		}
 		cpu_relax();
 	}
-
 	rcu_read_unlock();
 }
 
 void cgroup_sk_clone(struct sock_cgroup_data *skcd)
 {
-	if (skcd->val) {
-		if (skcd->no_refcnt)
-			return;
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
-		cgroup_bpf_get(sock_cgroup_ptr(skcd));
-	}
+	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
+
+	/*
+	 * We might be cloning a socket which is left in an empty
+	 * cgroup and the cgroup might have already been rmdir'd.
+	 * Don't use cgroup_get_live().
+	 */
+	cgroup_get(cgrp);
+	cgroup_bpf_get(cgrp);
 }
 
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
 
-	if (skcd->no_refcnt)
-		return;
 	cgroup_bpf_put(cgrp);
 	cgroup_put(cgrp);
 }
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 6c90c69e5311..95445bd6eb72 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -567,7 +567,8 @@ static void add_dma_entry(struct dma_debug_entry *entry)
 		pr_err("cacheline tracking ENOMEM, dma-debug disabled\n");
 		global_disable = true;
 	} else if (rc == -EEXIST) {
-		pr_err("cacheline tracking EEXIST, overlapping mappings aren't supported\n");
+		err_printk(entry->dev, entry,
+			"cacheline tracking EEXIST, overlapping mappings aren't supported\n");
 	}
 }
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 7ee5284bff58..06fec5547e7c 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -206,7 +206,8 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 /**
  * dma_map_sg_attrs - Map the given buffer for DMA
  * @dev:	The device for which to perform the DMA operation
- * @sg:	The sg_table object describing the buffer
+ * @sg:		The sg_table object describing the buffer
+ * @nents:	Number of entries to map
  * @dir:	DMA direction
  * @attrs:	Optional DMA attributes for the map operation
  *
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index bf16395b9e13..d5a61d565ad5 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -171,10 +171,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 			handle_signal_work(regs, ti_work);
 
-		if (ti_work & _TIF_NOTIFY_RESUME) {
+		if (ti_work & _TIF_NOTIFY_RESUME)
 			tracehook_notify_resume(regs);
-			rseq_handle_notify_resume(NULL, regs);
-		}
 
 		/* Architecture specific TIF work */
 		arch_exit_to_user_mode_work(regs, ti_work);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 744e8726c5b2..0c000cb01eeb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10193,7 +10193,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 		return;
 
 	if (ifh->nr_file_filters) {
-		mm = get_task_mm(event->ctx->task);
+		mm = get_task_mm(task);
 		if (!mm)
 			goto restart;
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 19e83e9b723c..4d8fc65cf38f 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -136,7 +136,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode);
  * Allocates and initializes an irq_domain structure.
  * Returns pointer to IRQ domain, or NULL on failure.
  */
-struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
+struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size,
 				    irq_hw_number_t hwirq_max, int direct_max,
 				    const struct irq_domain_ops *ops,
 				    void *host_data)
diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c
index 4ba15088e640..88191f6e252c 100644
--- a/kernel/locking/rwbase_rt.c
+++ b/kernel/locking/rwbase_rt.c
@@ -41,6 +41,12 @@
  * The risk of writer starvation is there, but the pathological use cases
  * which trigger it are not necessarily the typical RT workloads.
  *
+ * Fast-path orderings:
+ * The lock/unlock of readers can run in fast paths: lock and unlock are only
+ * atomic ops, and there is no inner lock to provide ACQUIRE and RELEASE
+ * semantics of rwbase_rt. Atomic ops should thus provide _acquire()
+ * and _release() (or stronger).
+ *
  * Common code shared between RT rw_semaphore and rwlock
  */
 
@@ -53,6 +59,7 @@ static __always_inline int rwbase_read_trylock(struct rwbase_rt *rwb)
 	 * set.
 	 */
 	for (r = atomic_read(&rwb->readers); r < 0;) {
+		/* Fully-ordered if cmpxchg() succeeds, provides ACQUIRE */
 		if (likely(atomic_try_cmpxchg(&rwb->readers, &r, r + 1)))
 			return 1;
 	}
@@ -162,6 +169,8 @@ static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb,
 	/*
 	 * rwb->readers can only hit 0 when a writer is waiting for the
 	 * active readers to leave the critical section.
+	 *
+	 * dec_and_test() is fully ordered, provides RELEASE.
 	 */
 	if (unlikely(atomic_dec_and_test(&rwb->readers)))
 		__rwbase_read_unlock(rwb, state);
@@ -172,7 +181,11 @@ static inline void __rwbase_write_unlock(struct rwbase_rt *rwb, int bias,
 {
 	struct rt_mutex_base *rtm = &rwb->rtmutex;
 
-	atomic_add(READER_BIAS - bias, &rwb->readers);
+	/*
+	 * _release() is needed in case that reader is in fast path, pairing
+	 * with atomic_try_cmpxchg() in rwbase_read_trylock(), provides RELEASE
+	 */
+	(void)atomic_add_return_release(READER_BIAS - bias, &rwb->readers);
 	raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
 	rwbase_rtmutex_unlock(rtm);
 }
@@ -196,6 +209,23 @@ static inline void rwbase_write_downgrade(struct rwbase_rt *rwb)
 	__rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags);
 }
 
+static inline bool __rwbase_write_trylock(struct rwbase_rt *rwb)
+{
+	/* Can do without CAS because we're serialized by wait_lock. */
+	lockdep_assert_held(&rwb->rtmutex.wait_lock);
+
+	/*
+	 * _acquire is needed in case the reader is in the fast path, pairing
+	 * with rwbase_read_unlock(), provides ACQUIRE.
+	 */
+	if (!atomic_read_acquire(&rwb->readers)) {
+		atomic_set(&rwb->readers, WRITER_BIAS);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
 				     unsigned int state)
 {
@@ -210,34 +240,30 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
 	atomic_sub(READER_BIAS, &rwb->readers);
 
 	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
-	/*
-	 * set_current_state() for rw_semaphore
-	 * current_save_and_set_rtlock_wait_state() for rwlock
-	 */
-	rwbase_set_and_save_current_state(state);
+	if (__rwbase_write_trylock(rwb))
+		goto out_unlock;
 
-	/* Block until all readers have left the critical section. */
-	for (; atomic_read(&rwb->readers);) {
+	rwbase_set_and_save_current_state(state);
+	for (;;) {
 		/* Optimized out for rwlocks */
 		if (rwbase_signal_pending_state(state, current)) {
-			__set_current_state(TASK_RUNNING);
+			rwbase_restore_current_state();
 			__rwbase_write_unlock(rwb, 0, flags);
 			return -EINTR;
 		}
+
+		if (__rwbase_write_trylock(rwb))
+			break;
+
 		raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
+		rwbase_schedule();
+		raw_spin_lock_irqsave(&rtm->wait_lock, flags);
 
-		/*
-		 * Schedule and wait for the readers to leave the critical
-		 * section. The last reader leaving it wakes the waiter.
-		 */
-		if (atomic_read(&rwb->readers) != 0)
-			rwbase_schedule();
 		set_current_state(state);
-		raw_spin_lock_irqsave(&rtm->wait_lock, flags);
 	}
-
-	atomic_set(&rwb->readers, WRITER_BIAS);
 	rwbase_restore_current_state();
+
+out_unlock:
 	raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
 	return 0;
 }
@@ -253,8 +279,7 @@ static inline int rwbase_write_trylock(struct rwbase_rt *rwb)
 	atomic_sub(READER_BIAS, &rwb->readers);
 
 	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
-	if (!atomic_read(&rwb->readers)) {
-		atomic_set(&rwb->readers, WRITER_BIAS);
+	if (__rwbase_write_trylock(rwb)) {
 		raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
 		return 1;
 	}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 825277e1e742..a8d0a58deebc 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early)
 	return;
 
 err_free_descs:
-	memblock_free(__pa(new_descs), new_descs_size);
+	memblock_free_ptr(new_descs, new_descs_size);
 err_free_log_buf:
-	memblock_free(__pa(new_log_buf), new_log_buf_len);
+	memblock_free_ptr(new_log_buf, new_log_buf_len);
 }
 
 static bool __read_mostly ignore_loglevel;
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 35f7bd0fced0..6d45ac3dae7f 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -282,9 +282,17 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 
 	if (unlikely(t->flags & PF_EXITING))
 		return;
-	ret = rseq_ip_fixup(regs);
-	if (unlikely(ret < 0))
-		goto error;
+
+	/*
+	 * regs is NULL if and only if the caller is in a syscall path.  Skip
+	 * fixup and leave rseq_cs as is so that rseq_sycall() will detect and
+	 * kill a misbehaving userspace on debug kernels.
+	 */
+	if (regs) {
+		ret = rseq_ip_fixup(regs);
+		if (unlikely(ret < 0))
+			goto error;
+	}
 	if (unlikely(rseq_update_cpu_id(t)))
 		goto error;
 	return;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index ee736861b18f..643d412ac623 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1404,7 +1404,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid,
 			}
 		}
 
-		*newval += now;
+		if (*newval)
+			*newval += now;
 	}
 
 	/*
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c221e4c3f625..fa91f398f28b 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1605,6 +1605,14 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
+	if (bt->trace_state == Blktrace_running) {
+		bt->trace_state = Blktrace_stopped;
+		spin_lock_irq(&running_trace_lock);
+		list_del_init(&bt->running_list);
+		spin_unlock_irq(&running_trace_lock);
+		relay_flush(bt->rchan);
+	}
+
 	put_probe_ref();
 	synchronize_rcu();
 	blk_trace_free(bt);