Merge branch 'tip/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git

arch/x86/kernel/cet.c

@@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code)
 
 static __ro_after_init bool ibt_fatal = true;
 
+/*
+ * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR.
+ *
+ * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered,
+ * the WFE state of the interrupted context needs to be cleared to let execution
+ * continue.  Otherwise when the CPU resumes from the instruction that just
+ * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU
+ * enters a dead loop.
+ *
+ * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't
+ * set WFE.  But FRED provides space on the entry stack (in an expanded CS area)
+ * to save and restore the WFE state, thus the WFE state is no longer clobbered,
+ * so software must clear it.
+ */
+static void ibt_clear_fred_wfe(struct pt_regs *regs)
+{
+	/*
+	 * No need to do any FRED checks.
+	 *
+	 * For IDT event delivery, the high-order 48 bits of CS are pushed
+	 * as 0s into the stack, and later IRET ignores these bits.
+	 *
+	 * For FRED, a test to check if fred_cs.wfe is set would be dropped
+	 * by compilers.
+	 */
+	regs->fred_cs.wfe = 0;
+}
+
 static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code)
 {
 	if ((error_code & CP_EC) != CP_ENDBR) {
@@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code)
 
 	if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) {
 		regs->ax = 0;
+		ibt_clear_fred_wfe(regs);
 		return;
 	}
 
@@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code)
 	if (!ibt_fatal) {
 		printk(KERN_DEFAULT CUT_HERE);
 		__warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL);
+		ibt_clear_fred_wfe(regs);
 		return;
 	}
 	BUG();

drivers/pci/msi/irqdomain.c

@@ -350,8 +350,11 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask,
 
 	domain = dev_get_msi_domain(&pdev->dev);
 
-	if (!domain || !irq_domain_is_hierarchy(domain))
+	if (!domain || !irq_domain_is_hierarchy(domain)) {
+		if (IS_ENABLED(CONFIG_PCI_MSI_ARCH_FALLBACKS))
 			return mode == ALLOW_LEGACY;
+		return false;
+	}
 
 	if (!irq_domain_is_msi_parent(domain)) {
 		/*

drivers/pci/msi/msi.c

@@ -433,6 +433,10 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 	if (WARN_ON_ONCE(dev->msi_enabled))
 		return -EINVAL;
 
+	/* Test for the availability of MSI support */
+	if (!pci_msi_domain_supports(dev, 0, ALLOW_LEGACY))
+		return -ENOTSUPP;
+
 	nvec = pci_msi_vec_count(dev);
 	if (nvec < 0)
 		return nvec;

drivers/virt/coco/tdx-guest/tdx-guest.c

@@ -124,10 +124,8 @@ static void *alloc_quote_buf(void)
 	if (!addr)
 		return NULL;
 
-	if (set_memory_decrypted((unsigned long)addr, count)) {
-		free_pages_exact(addr, len);
+	if (set_memory_decrypted((unsigned long)addr, count))
 		return NULL;
-	}
 
 	return addr;
 }

include/linux/sched.h

@@ -1637,8 +1637,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state,
 	 * We're lying here, but rather than expose a completely new task state
 	 * to userspace, we can make this appear as if the task has gone through
 	 * a regular rt_mutex_lock() call.
+	 * Report the frozen task uninterruptible.
 	 */
-	if (tsk_state & TASK_RTLOCK_WAIT)
+	if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN))
 		state = TASK_UNINTERRUPTIBLE;
 
 	return fls(state);

kernel/locking/rtmutex.c

@@ -1292,7 +1292,13 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 	 */
 	get_task_struct(owner);
 
+	preempt_disable();
 	raw_spin_unlock_irq(&lock->wait_lock);
+	/* wake up any tasks on the wake_q before calling rt_mutex_adjust_prio_chain */
+	wake_up_q(wake_q);
+	wake_q_init(wake_q);
+	preempt_enable();
+
 
 	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
@@ -1596,6 +1602,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
  *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
+ * @wake_q:		 wake_q of tasks to wake when we drop the lock->wait_lock
  *
  * Must be called with lock->wait_lock held and interrupts disabled
  */
@@ -1603,7 +1610,8 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 					   struct ww_acquire_ctx *ww_ctx,
 					   unsigned int state,
 					   struct hrtimer_sleeper *timeout,
-					   struct rt_mutex_waiter *waiter)
+					   struct rt_mutex_waiter *waiter,
+					   struct wake_q_head *wake_q)
 	__releases(&lock->wait_lock) __acquires(&lock->wait_lock)
 {
 	struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex);
@@ -1634,7 +1642,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 			owner = rt_mutex_owner(lock);
 		else
 			owner = NULL;
+		preempt_disable();
 		raw_spin_unlock_irq(&lock->wait_lock);
+		if (wake_q) {
+			wake_up_q(wake_q);
+			wake_q_init(wake_q);
+		}
+		preempt_enable();
 
 		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
 			rt_mutex_schedule();
@@ -1708,7 +1722,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk, wake_q);
 	if (likely(!ret))
-		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter);
+		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter, wake_q);
 
 	if (likely(!ret)) {
 		/* acquired the lock */

kernel/locking/rtmutex_api.c

@@ -383,7 +383,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
 	raw_spin_lock_irq(&lock->wait_lock);
 	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
-	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter);
+	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.