Merge branch 'irq/urgent' into irq/msi

to pick up the PCI/MSI-x fixes.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

18 files changed, 116 insertions, 45 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e7a163a3146b..755f38e893be 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -732,6 +732,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
+int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
 	.func = &_name##_func,					\
@@ -1352,28 +1353,16 @@ extern struct mutex bpf_stats_enabled_mutex;
  * kprobes, tracepoints) to prevent deadlocks on map operations as any of
  * these events can happen inside a region which holds a map bucket lock
  * and can deadlock on it.
- *
- * Use the preemption safe inc/dec variants on RT because migrate disable
- * is preemptible on RT and preemption in the middle of the RMW operation
- * might lead to inconsistent state. Use the raw variants for non RT
- * kernels as migrate_disable() maps to preempt_disable() so the slightly
- * more expensive save operation can be avoided.
  */
 static inline void bpf_disable_instrumentation(void)
 {
 	migrate_disable();
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_inc(bpf_prog_active);
-	else
-		__this_cpu_inc(bpf_prog_active);
+	this_cpu_inc(bpf_prog_active);
 }
 
 static inline void bpf_enable_instrumentation(void)
 {
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_dec(bpf_prog_active);
-	else
-		__this_cpu_dec(bpf_prog_active);
+	this_cpu_dec(bpf_prog_active);
 	migrate_enable();
 }
 
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 203eef993d76..0e1b6281fd8f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -245,7 +245,10 @@ struct kfunc_btf_id_set {
 	struct module *owner;
 };
 
-struct kfunc_btf_id_list;
+struct kfunc_btf_id_list {
+	struct list_head list;
+	struct mutex mutex;
+};
 
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
@@ -254,6 +257,9 @@ void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
 				 struct kfunc_btf_id_set *s);
 bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 			      struct module *owner);
+
+extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
+extern struct kfunc_btf_id_list prog_test_kfunc_list;
 #else
 static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
 					     struct kfunc_btf_id_set *s)
@@ -268,13 +274,13 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist,
 {
 	return false;
 }
+
+static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused;
+static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused;
 #endif
 
 #define DEFINE_KFUNC_BTF_ID_SET(set, name)                                     \
 	struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set),     \
 					 THIS_MODULE }
 
-extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
-extern struct kfunc_btf_id_list prog_test_kfunc_list;
-
 #endif
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 2f909ed084c6..4ff37cb763ae 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -3,7 +3,6 @@
 #define _LINUX_CACHEINFO_H
 
 #include <linux/bitops.h>
-#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 8eacf67eb212..039e7e0c7378 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -20,6 +20,7 @@
  */
 
 #include <linux/math.h>
+#include <linux/sched.h>
 
 extern unsigned long loops_per_jiffy;
 
@@ -58,7 +59,18 @@ void calibrate_delay(void);
 void __attribute__((weak)) calibration_delay_done(void);
 void msleep(unsigned int msecs);
 unsigned long msleep_interruptible(unsigned int msecs);
-void usleep_range(unsigned long min, unsigned long max);
+void usleep_range_state(unsigned long min, unsigned long max,
+			unsigned int state);
+
+static inline void usleep_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_UNINTERRUPTIBLE);
+}
+
+static inline void usleep_idle_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_IDLE);
+}
 
 static inline void ssleep(unsigned int seconds)
 {
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index a498ebcf4993..15e7c5e15d62 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -18,6 +18,7 @@
 #include <linux/klist.h>
 #include <linux/pm.h>
 #include <linux/device/bus.h>
+#include <linux/module.h>
 
 /**
  * enum probe_type - device driver probe type to try
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 24b7ed2677af..7f1e88e3e2b5 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -6,6 +6,7 @@
 #define __LINUX_FILTER_H__
 
 #include <linux/atomic.h>
+#include <linux/bpf.h>
 #include <linux/refcount.h>
 #include <linux/compat.h>
 #include <linux/skbuff.h>
@@ -26,7 +27,6 @@
 
 #include <asm/byteorder.h>
 #include <uapi/linux/filter.h>
-#include <uapi/linux/bpf.h>
 
 struct sk_buff;
 struct sock;
@@ -640,9 +640,6 @@ static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void
  * This uses migrate_disable/enable() explicitly to document that the
  * invocation of a BPF program does not require reentrancy protection
  * against a BPF program which is invoked from a preempting task.
- *
- * For non RT enabled kernels migrate_disable/enable() maps to
- * preempt_disable/enable(), i.e. it disables also preemption.
  */
 static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
 					  const void *ctx)
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 9e067f937dbc..f453be385bd4 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -840,6 +840,11 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev,
 	return hdev->ll_driver == driver;
 }
 
+static inline bool hid_is_usb(struct hid_device *hdev)
+{
+	return hid_is_using_ll_driver(hdev, &usb_hid_driver);
+}
+
 #define	PM_HINT_FULLON	1<<5
 #define PM_HINT_NORMAL	1<<1
 
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 723985879035..a5cc4cdf9cc8 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -664,6 +664,19 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl);
 int mhi_pm_resume(struct mhi_controller *mhi_cntrl);
 
 /**
+ * mhi_pm_resume_force - Force resume MHI from suspended state
+ * @mhi_cntrl: MHI controller
+ *
+ * Resume the device irrespective of its MHI state. As per the MHI spec, devices
+ * has to be in M3 state during resume. But some devices seem to be in a
+ * different MHI state other than M3 but they continue working fine if allowed.
+ * This API is intented to be used for such devices.
+ *
+ * Return: 0 if the resume succeeds, a negative error code otherwise
+ */
+int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl);
+
+/**
  * mhi_download_rddm_image - Download ramdump image from device for
  *                           debugging purpose.
  * @mhi_cntrl: MHI controller
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index b31d3f3312ce..d73a1c08c3e3 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -51,9 +51,9 @@
 #define _LINUX_PERCPU_REFCOUNT_H
 
 #include <linux/atomic.h>
-#include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/rcupdate.h>
+#include <linux/types.h>
 #include <linux/gfp.h>
 
 struct percpu_ref;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 96e43fbb2dd8..cbf03a5f9cf5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -538,11 +538,12 @@ struct macsec_ops;
  * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY
  * @state: State of the PHY for management purposes
  * @dev_flags: Device-specific flags used by the PHY driver.
- *		Bits [15:0] are free to use by the PHY driver to communicate
- *			    driver specific behavior.
- *		Bits [23:16] are currently reserved for future use.
- *		Bits [31:24] are reserved for defining generic
- *			     PHY driver behavior.
+ *
+ *      - Bits [15:0] are free to use by the PHY driver to communicate
+ *        driver specific behavior.
+ *      - Bits [23:16] are currently reserved for future use.
+ *      - Bits [31:24] are reserved for defining generic
+ *        PHY driver behavior.
  * @irq: IRQ number of the PHY's interrupt (-1 if none)
  * @phy_timer: The timer for handling the state machine
  * @phylink: Pointer to phylink instance for this PHY
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 222da43b7096..eddd66d426ca 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -129,7 +129,7 @@ static inline bool pm_runtime_suspended(struct device *dev)
  * pm_runtime_active - Check whether or not a device is runtime-active.
  * @dev: Target device.
  *
- * Return %true if runtime PM is enabled for @dev and its runtime PM status is
+ * Return %true if runtime PM is disabled for @dev or its runtime PM status is
  * %RPM_ACTIVE, or %false otherwise.
  *
  * Note that the return value of this function can only be trusted if it is
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index bd7a73db2e66..54cf566616ae 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -499,7 +499,8 @@ struct regulator_irq_data {
  *		best to shut-down regulator(s) or reboot the SOC if error
  *		handling is repeatedly failing. If fatal_cnt is given the IRQ
  *		handling is aborted if it fails for fatal_cnt times and die()
- *		callback (if populated) or BUG() is called to try to prevent
+ *		callback (if populated) is called. If die() is not populated
+ *		poweroff for the system is attempted in order to prevent any
  *		further damage.
  * @reread_ms:	The time which is waited before attempting to re-read status
  *		at the worker if IC reading fails. Immediate re-read is done
@@ -516,11 +517,12 @@ struct regulator_irq_data {
  * @data:	Driver private data pointer which will be passed as such to
  *		the renable, map_event and die callbacks in regulator_irq_data.
  * @die:	Protection callback. If IC status reading or recovery actions
- *		fail fatal_cnt times this callback or BUG() is called. This
- *		callback should implement a final protection attempt like
- *		disabling the regulator. If protection succeeded this may
- *		return 0. If anything else is returned the core assumes final
- *		protection failed and calls BUG() as a last resort.
+ *		fail fatal_cnt times this callback is called or system is
+ *		powered off. This callback should implement a final protection
+ *		attempt like disabling the regulator. If protection succeeded
+ *		die() may return 0. If anything else is returned the core
+ *		assumes final protection failed and attempts to perform a
+ *		poweroff as a last resort.
  * @map_event:	Driver callback to map IRQ status into regulator devices with
  *		events / errors. NOTE: callback MUST initialize both the
  *		errors and notifs for all rdevs which it signals having
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2d0df57c9902..851e07da2583 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -217,6 +217,7 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void
 void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
 void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
 void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
+void __wake_up_pollfree(struct wait_queue_head *wq_head);
 
 #define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
@@ -245,6 +246,31 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
 #define wake_up_interruptible_sync_poll_locked(x, m)				\
 	__wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
 
+/**
+ * wake_up_pollfree - signal that a polled waitqueue is going away
+ * @wq_head: the wait queue head
+ *
+ * In the very rare cases where a ->poll() implementation uses a waitqueue whose
+ * lifetime is tied to a task rather than to the 'struct file' being polled,
+ * this function must be called before the waitqueue is freed so that
+ * non-blocking polls (e.g. epoll) are notified that the queue is going away.
+ *
+ * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via
+ * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU.
+ */
+static inline void wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+	/*
+	 * For performance reasons, we don't always take the queue lock here.
+	 * Therefore, we might race with someone removing the last entry from
+	 * the queue, and proceed while they still hold the queue lock.
+	 * However, rcu_read_lock() is required to be held in such cases, so we
+	 * can safely proceed with an RCU-delayed free.
+	 */
+	if (waitqueue_active(wq_head))
+		__wake_up_pollfree(wq_head);
+}
+
 #define ___wait_cond_timeout(condition)						\
 ({										\
 	bool __cond = (condition);						\
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
index f6af76c87a6c..191c36afa1f4 100644
--- a/include/net/bond_alb.h
+++ b/include/net/bond_alb.h
@@ -126,7 +126,7 @@ struct tlb_slave_info {
 struct alb_bond_info {
 	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
 	u32			unbalanced_load;
-	int			tx_rebalance_counter;
+	atomic_t		tx_rebalance_counter;
 	int			lp_counter;
 	/* -------- rlb parameters -------- */
 	int rlb_enabled;
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 7994455ec714..c4898fcbf923 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -136,6 +136,19 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 	sk_rx_queue_update(sk, skb);
 }
 
+/* Variant of sk_mark_napi_id() for passive flow setup,
+ * as sk->sk_napi_id and sk->sk_rx_queue_mapping content
+ * needs to be set.
+ */
+static inline void sk_mark_napi_id_set(struct sock *sk,
+				       const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+#endif
+	sk_rx_queue_set(sk, skb);
+}
+
 static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index cc663c68ddc4..d24b0a34c8f0 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -276,14 +276,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
 /* jiffies until ct expires, 0 if already expired */
 static inline unsigned long nf_ct_expires(const struct nf_conn *ct)
 {
-	s32 timeout = ct->timeout - nfct_time_stamp;
+	s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
 
 	return timeout > 0 ? timeout : 0;
 }
 
 static inline bool nf_ct_is_expired(const struct nf_conn *ct)
 {
-	return (__s32)(ct->timeout - nfct_time_stamp) <= 0;
+	return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0;
 }
 
 /* use after obtaining a reference count */
@@ -302,7 +302,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct)
 static inline void nf_ct_offload_timeout(struct nf_conn *ct)
 {
 	if (nf_ct_expires(ct) < NF_CT_DAY / 2)
-		ct->timeout = nfct_time_stamp + NF_CT_DAY;
+		WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY);
 }
 
 struct kernel_param;
diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h
index 41b509f410bf..f9c520ce4bf4 100644
--- a/include/uapi/asm-generic/poll.h
+++ b/include/uapi/asm-generic/poll.h
@@ -29,7 +29,7 @@
 #define POLLRDHUP       0x2000
 #endif
 
-#define POLLFREE	(__force __poll_t)0x4000	/* currently only for epoll */
+#define POLLFREE	(__force __poll_t)0x4000
 
 #define POLL_BUSY_LOOP	(__force __poll_t)0x8000
 
diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h
index 74ef57b38f9f..ac5d6a3031db 100644
--- a/include/uapi/linux/resource.h
+++ b/include/uapi/linux/resource.h
@@ -66,10 +66,17 @@ struct rlimit64 {
 #define _STK_LIM	(8*1024*1024)
 
 /*
- * GPG2 wants 64kB of mlocked memory, to make sure pass phrases
- * and other sensitive information are never written to disk.
+ * Limit the amount of locked memory by some sane default:
+ * root can always increase this limit if needed.
+ *
+ * The main use-cases are (1) preventing sensitive memory
+ * from being swapped; (2) real-time operations; (3) via
+ * IOURING_REGISTER_BUFFERS.
+ *
+ * The first two don't need much. The latter will take as
+ * much as it can get. 8MB is a reasonably sane default.
  */
-#define MLOCK_LIMIT	((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024)
+#define MLOCK_LIMIT	(8*1024*1024)
 
 /*
  * Due to binary compatibility, the actual resource numbers