21 files changed, 342 insertions, 107 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 14b8c571c0d1..aed195a71cbf 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2239,9 +2239,12 @@ IO Latency
 ~~~~~~~~~~
 
 This is a cgroup v2 controller for IO workload protection.  You provide a group
-with a latency target, and if the average latency exceeds that target the
-controller will throttle any peers that have a lower latency target than the
-protected workload.
+with a latency target, and if the group misses its target the controller will
+throttle any peers that have a lower latency target than the protected
+workload.  How a miss is detected depends on the device: on rotational devices
+the average latency over the window must exceed the target, while on
+non-rotational devices a miss is counted once enough of the IOs in the window
+individually exceed the target.
 
 The limits are only applied at the peer level in the hierarchy.  This means that
 in the diagram below, only groups A, B, and C will influence each other, and
@@ -2258,10 +2261,12 @@ So the ideal way to configure this is to set io.latency in groups A, B, and C.
 Generally you do not want to set a value lower than the latency your device
 supports.  Experiment to find the value that works best for your workload.
 Start at higher than the expected latency for your device and, with
-blkcg_debug_stats enabled, watch the avg_lat value in io.stat for your
-workload group to get an idea of the latency you see during normal operation.
-Use the avg_lat value as a basis for your real setting, setting at 10-15%
-higher than the value in io.stat.
+blkcg_debug_stats enabled, observe io.stat for your workload group to get an
+idea of the latency you see during normal operation.  On rotational devices,
+use the avg_lat value as a basis for your real setting, setting it 10-15%
+higher.  On non-rotational devices io.stat reports no average latency; set
+the target based on your device and use the missed/total fields to verify it
+is being met.
 
 How IO Latency Throttling Works
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -2303,19 +2308,36 @@ IO Latency Interface Files
 	the blkcg_debug_stats module parameter is enabled (it is disabled by
 	default).
 
+	The reported latency fields depend on the device.  Rotational devices
+	report avg_lat and win; non-rotational devices report missed and total
+	instead.  missed and total are live counters for the current window and
+	may change between reads.
+
 	  depth
 		This is the current queue depth for the group.
 
 	  avg_lat
-		This is an exponential moving average with a decay rate of 1/exp
-		bound by the sampling interval.  The decay rate interval can be
-		calculated by multiplying the win value in io.stat by the
-		corresponding number of samples based on the win value.
+		(Rotational devices only.)  This is an exponential moving
+		average with a decay rate of 1/exp bound by the sampling
+		interval.  The decay rate interval can be calculated by
+		multiplying the win value in io.stat by the corresponding number
+		of samples based on the win value.
 
 	  win
-		The sampling window size in milliseconds.  This is the minimum
-		duration of time between evaluation events.  Windows only elapse
-		with IO activity.  Idle periods extend the most recent window.
+		(Rotational devices only.)  The sampling window size in
+		milliseconds.  This is the minimum duration of time between
+		evaluation events.  Windows only elapse with IO activity.  Idle
+		periods extend the most recent window.
+
+	  missed
+		(Non-rotational devices only.)  The number of IOs in the
+		current window whose latency exceeded the target.  A group is
+		considered to be missing its target once missed reaches a
+		certain ratio of total.
+
+	  total
+		(Non-rotational devices only.)  The total number of IOs
+		accounted in the current window.
 
 IO Priority
 ~~~~~~~~~~~
diff --git a/Makefile b/Makefile
index 060834cd0a4d..902f3f3d54b7 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index ce0cc737f870..1363e5bef35c 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -168,7 +168,7 @@ vdso_prepare: prepare0
 endif
 endif
 
-vdso-install-y			+= arch/riscv/kernel/vdso/vdso.so.dbg
+vdso-install-$(CONFIG_MMU)		+= arch/riscv/kernel/vdso/vdso.so.dbg
 vdso-install-$(CONFIG_RISCV_USER_CFI)	+= arch/riscv/kernel/vdso_cfi/vdso-cfi.so.dbg
 vdso-install-$(CONFIG_COMPAT)	+= arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg
 
diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c
index d0c61f86cba3..df80c9614df1 100644
--- a/arch/riscv/errata/sifive/errata.c
+++ b/arch/riscv/errata/sifive/errata.c
@@ -93,10 +93,8 @@ void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 	for (alt = begin; alt < end; alt++) {
 		if (alt->vendor_id != SIFIVE_VENDOR_ID)
 			continue;
-		if (alt->patch_id >= ERRATA_SIFIVE_NUMBER) {
-			WARN(1, "This errata id:%d is not in kernel errata list", alt->patch_id);
+		if (alt->patch_id >= ERRATA_SIFIVE_NUMBER)
 			continue;
-		}
 
 		tmp = (1U << alt->patch_id);
 		if (cpu_req_errata & tmp) {
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index a06697846e69..d41acfb3959d 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -22,13 +22,13 @@ static inline cycles_t get_cycles(void)
 #else /* !CONFIG_64BIT */
 static inline u32 get_cycles(void)
 {
-	return readl_relaxed(((u32 *)clint_time_val));
+	return readl_relaxed(((u32 __iomem *)clint_time_val));
 }
 #define get_cycles get_cycles
 
 static inline u32 get_cycles_hi(void)
 {
-	return readl_relaxed(((u32 *)clint_time_val) + 1);
+	return readl_relaxed(((u32 __iomem *)clint_time_val) + 1);
 }
 #define get_cycles_hi get_cycles_hi
 #endif /* CONFIG_64BIT */
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index bb57eb5d19df..5a5aa22124e7 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -289,7 +289,7 @@ free:
 }
 
 /* Measure unaligned access speed on all CPUs present at boot in parallel. */
-static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
 {
 	schedule_on_each_cpu(check_vector_unaligned_access);
 	riscv_hwprobe_complete_async_probe();
@@ -297,7 +297,7 @@ static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __alway
 	return 0;
 }
 #else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */
-static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
 {
 	return 0;
 }
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 422efa11824b..01d252c741d2 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -165,7 +165,9 @@ static void print_vm_layout(void) { }
 
 void __init arch_mm_preinit(void)
 {
-	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
+	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit) &&
+		       memblock_start_of_DRAM() < dma32_phys_limit;
+	unsigned int swiotlb_flags = SWIOTLB_VERBOSE;
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif /* CONFIG_FLATMEM */
@@ -173,17 +175,22 @@ void __init arch_mm_preinit(void)
 	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
 	    dma_cache_alignment != 1) {
 		/*
-		 * If no bouncing needed for ZONE_DMA, allocate 1MB swiotlb
-		 * buffer per 1GB of RAM for kmalloc() bouncing on
-		 * non-coherent platforms.
+		 * No 32-bit DMA bouncing needed (either all DRAM is within
+		 * the 32-bit limit, or it all starts above it), but
+		 * kmalloc() buffers whose sizes are not cache-line-aligned
+		 * still require bouncing for non-coherent DMA.  Use
+		 * SWIOTLB_ANY so that the buffer can be allocated from high
+		 * memory when DRAM starts above dma32_phys_limit.  Allocate
+		 * ~1 MB per 1 GB of RAM.
 		 */
 		unsigned long size =
 			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
 		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
 		swiotlb = true;
+		swiotlb_flags |= SWIOTLB_ANY;
 	}
 
-	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
+	swiotlb_init(swiotlb, swiotlb_flags);
 
 	print_vm_layout();
 }
@@ -1619,7 +1626,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un
 
 	for (; addr < end; addr = next) {
 		next = pud_addr_end(addr, end);
-		pudp = pud_base + pud_index(addr);
+		pudp = pgtable_l4_enabled ? pud_base + pud_index(addr) : pud_base;
 		pud = pudp_get(pudp);
 		if (!pud_present(pud))
 			continue;
@@ -1650,7 +1657,7 @@ static void __meminit remove_p4d_mapping(p4d_t *p4d_base, unsigned long addr, un
 
 	for (; addr < end; addr = next) {
 		next = p4d_addr_end(addr, end);
-		p4dp = p4d_base + p4d_index(addr);
+		p4dp = pgtable_l5_enabled ? p4d_base + p4d_index(addr) : p4d_base;
 		p4d = p4dp_get(p4dp);
 		if (!p4d_present(p4d))
 			continue;
diff --git a/fs/attr.c b/fs/attr.c
index 4f437fabb7f0..71888ac903c2 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -176,7 +176,7 @@ int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * covered by the open-time check because sys_truncate() takes a
 		 * path, not an open file.
 		 */
-		if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
+		if (IS_VERITY(inode))
 			return -EPERM;
 
 		error = inode_newsize_ok(inode, attr->ia_size);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 9915e39362db..c80b24a941ad 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -534,7 +534,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
 		return -EFAULT;
 	policy.version = version;
 
-	if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
+	if (!inode_owner_or_capable(file_mnt_idmap(filp), inode))
 		return -EACCES;
 
 	ret = mnt_want_write_file(filp);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1360409d8de9..5709c6fea85b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10364,6 +10364,7 @@ static void nfs41_free_stateid_release(void *calldata)
 	struct nfs_free_stateid_data *data = calldata;
 	struct nfs_client *clp = data->server->nfs_client;
 
+	nfs_sb_deactive(data->server->super);
 	nfs_put_client(clp);
 	kfree(calldata);
 }
@@ -10402,17 +10403,22 @@ static int nfs41_free_stateid(struct nfs_server *server,
 	struct nfs_free_stateid_data *data;
 	struct rpc_task *task;
 	struct nfs_client *clp = server->nfs_client;
+	int ret = -EIO;
 
 	if (!refcount_inc_not_zero(&clp->cl_count))
-		return -EIO;
+		return ret;
+	if (!nfs_sb_active(server->super))
+		goto out_put_clp;
 
 	nfs4_state_protect(clp, NFS_SP4_MACH_CRED_STATEID,
 		&task_setup.rpc_client, &msg);
 
 	dprintk("NFS call  free_stateid %p\n", stateid);
 	data = kmalloc_obj(*data);
-	if (!data)
-		return -ENOMEM;
+	if (!data) {
+		ret = -ENOMEM;
+		goto out_put_server;
+	}
 	data->server = server;
 	nfs4_stateid_copy(&data->args.stateid, stateid);
 
@@ -10428,6 +10434,11 @@ static int nfs41_free_stateid(struct nfs_server *server,
 	rpc_put_task(task);
 	stateid->type = NFS4_FREED_STATEID_TYPE;
 	return 0;
+out_put_server:
+	nfs_sb_deactive(server->super);
+out_put_clp:
+	nfs_put_client(clp);
+	return ret;
 }
 
 static void
@@ -10585,7 +10596,8 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
 	ssize_t error, error2, error3;
-	size_t left = size;
+	ssize_t left = size;
+	ssize_t left2;
 
 	error = generic_listxattr(dentry, list, left);
 	if (error < 0)
@@ -10595,10 +10607,13 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 		left -= error;
 	}
 
-	error2 = security_inode_listsecurity(d_inode(dentry), &list, &left);
+	left2 = left;
+	error2 = security_inode_listsecurity(d_inode(dentry), &list, &left2);
 	if (error2 < 0)
 		return error2;
-	error2 = size - error - left;
+	error2 = left - left2;
+	if (list)
+		left -= error2;
 
 	error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left);
 	if (error3 < 0)
diff --git a/include/linux/psi.h b/include/linux/psi.h
index e0745873e3f2..7966e3ac03b9 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -25,7 +25,9 @@ void psi_memstall_leave(unsigned long *flags);
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
 struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
 				       enum psi_res res, struct file *file,
-				       struct kernfs_open_file *of);
+				       struct kernfs_open_file *of,
+				       bool *need_rtpoll_worker);
+int psi_trigger_create_rtpoll_worker(struct psi_group *group);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 20b2343aa344..87e353f7e011 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -244,11 +244,11 @@ struct sched_ext_entity {
 	 * to %SCHED_EXT with -%EACCES.
 	 *
 	 * Can be set from ops.init_task() while the BPF scheduler is being
-	 * loaded (!scx_init_task_args->fork). If set and the task's policy is
-	 * already %SCHED_EXT, the task's policy is rejected and forcefully
-	 * reverted to %SCHED_NORMAL. The number of such events are reported
-	 * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag
-	 * during fork is not allowed.
+	 * loaded. If set and the task's policy is already %SCHED_EXT, the
+	 * task's policy is rejected and forcefully reverted to %SCHED_NORMAL.
+	 * The number of such events are reported through
+	 * /sys/kernel/sched_ext/nr_rejected. Setting this flag from any other
+	 * ops.init_task() invocation, such as during fork, fails the scheduler.
 	 */
 	bool			disallow;	/* reject switching into SCX */
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 38f8d9df8fbc..b5b461d4418b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3996,6 +3996,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	struct psi_trigger *new;
 	struct cgroup *cgrp;
 	struct psi_group *psi;
+	bool need_rtpoll_worker;
 	ssize_t ret = 0;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
@@ -4015,12 +4016,32 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_psi(cgrp);
-	new = psi_trigger_create(psi, buf, res, of->file, of);
+	new = psi_trigger_create(psi, buf, res, of->file, of,
+				 &need_rtpoll_worker);
 	if (IS_ERR(new)) {
 		ret = PTR_ERR(new);
 		goto out_unlock;
 	}
 
+	/*
+	 * The worker fork must run with neither cgroup_mutex nor the file's
+	 * kernfs active reference held. The latter is broken since
+	 * cgroup_kn_lock_live(). @of->priv may be released while unlocked, so
+	 * recheck before publishing @new.
+	 */
+	if (need_rtpoll_worker) {
+		cgroup_unlock();
+		ret = psi_trigger_create_rtpoll_worker(psi);
+		cgroup_lock();
+
+		if (!ret && !of->priv)
+			ret = -ENODEV;
+		if (ret) {
+			psi_trigger_destroy(new);
+			goto out_unlock;
+		}
+	}
+
 	smp_store_release(&ctx->psi.trigger, new);
 
 out_unlock:
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 179b26e9c934..2650d1e52803 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -982,8 +982,11 @@ retry:
 		return -1;
 
 	/*
-	 * Special case for regular (non PI) futexes. The unlock path in
-	 * user space has two race scenarios:
+	 * Special case for regular (non PI) futexes. Ordinarily, we do
+	 * not perform any processing here unless the current thread was
+	 * the owner of the futex (by the TID check below).
+	 *
+	 * However, the unlock path has three race scenarios:
 	 *
 	 * 1. The unlock path releases the user space futex value and
 	 *    before it can execute the futex() syscall to wake up
@@ -992,42 +995,70 @@ retry:
 	 * 2. A woken up waiter is killed before it can acquire the
 	 *    futex in user space.
 	 *
-	 * In the second case, the wake up notification could be generated
-	 * by the unlock path in user space after setting the futex value
-	 * to zero or by the kernel after setting the OWNER_DIED bit below.
+	 * 3. A woken up waiter is killed in user space after another
+	 *    thread has acquired the futex, but before it can set
+	 *    FUTEX_WAITERS.
+	 *
+	 * Note that, if userspace uses the FUTEX_ROBUST_UNLOCK flag, we
+	 * will not see case 1 here.
+	 *
+	 * In the second and third case, the wake up notification could
+	 * be generated from any of:
+	 *
+	 *    i.   An ordinary futex wakeup after unlock (with or
+	 *         without FUTEX_ROBUST_UNLOCK)
+	 *    ii.  A robust wakeup from another thread's death
+	 *    iii. A previous round through this special case
+	 *
+	 * As a result, the futex world will be in one of four states:
+	 *
+	 *    A. The futex word is 0 (unlocked)
+	 *    B. The futex word is owned by another thread
+	 *       (FUTEX_WAITERS is not set)
+	 *    C. The futex word is owned by another thread
+	 *       (FUTEX_WAITERS set)
+	 *    D. The futex's owner died and OWNER_DIED is set
+	 *       (the owner part of the word is 0)
 	 *
-	 * In both cases the TID validation below prevents a wakeup of
-	 * potential waiters which can cause these waiters to block
-	 * forever.
+	 * The key issue is that the kernel usually (at least from
+	 * sources ii. and iii. or when so requested by userspace from
+	 * source i.) only ever wakes *one* waiter at a time. If this
+	 * waiter dies before acquiring the futex (or setting the
+	 * FUTEX_WAITERS bit), the kernel *must* still wake the next
+	 * waiter down the line to uphold the futex invariants and
+	 * avoid lost wakeups. Note we do not need to handle state C,
+	 * as it does not matter to us whether *we* successfully set
+	 * the bit or a third thread did so in the meantime.
 	 *
-	 * In both cases the following conditions are met:
+	 * Therefore, in these cases we must issue an additional
+	 * futex_wake(). Note however that we *must not* set OWNER_DIED
+	 * here. Our thread is *not* the owner of the futex.
 	 *
-	 *	1) task->futex.robust_list->list_op_pending != NULL
-	 *	   @pending_op == true
-	 *	2) The owner part of user space futex value == 0
+	 * Thus to summarize, the conditions for needing the additional
+	 * futex_wake() are:
+	 *
+	 *	1) @pending_op == true (the thread has not finished the
+	 *	   mutex operation)
+	 *	2) The futex word is in one of the states A, B or D
 	 *	3) Regular futex: @pi == false
 	 *
-	 * If these conditions are met, it is safe to attempt waking up a
-	 * potential waiter without touching the user space futex value and
-	 * trying to set the OWNER_DIED bit. If the futex value is zero,
-	 * the rest of the user space mutex state is consistent, so a woken
-	 * waiter will just take over the uncontended futex. Setting the
-	 * OWNER_DIED bit would create inconsistent state and malfunction
-	 * of the user space owner died handling. Otherwise, the OWNER_DIED
-	 * bit is already set, and the woken waiter is expected to deal with
-	 * this.
+	 * Note in particular that in all of the states A-D the owner
+	 * portion of the futex word differs from our thread's TID
+	 * (unless the actual owner has the same TID in another PID
+	 * namespace, but we cannot currently distinguish that
+	 * scenario), so this can be a special-case wakeup in the bail
+	 * path of the ordinary TID check.
 	 */
 	owner = uval & FUTEX_TID_MASK;
 
-	if (pending_op && !pi && !owner) {
-		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
-			   FUTEX_BITSET_MATCH_ANY);
+	if (owner != task_pid_vnr(curr)) {
+		if (pending_op && !pi && (!owner || !(uval & FUTEX_WAITERS))) {
+			futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
+				   FUTEX_BITSET_MATCH_ANY);
+		}
 		return 0;
 	}
 
-	if (owner != task_pid_vnr(curr))
-		return 0;
-
 	/*
 	 * Ok, this dying thread is truly holding a futex
 	 * of interest. Set the OWNER_DIED bit atomically
diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c
index 4834a809985a..175c08a6e41e 100644
--- a/kernel/liveupdate/kexec_handover.c
+++ b/kernel/liveupdate/kexec_handover.c
@@ -38,6 +38,16 @@
 #include "../kexec_internal.h"
 #include "kexec_handover_internal.h"
 
+/*
+ * This is the minimal alignment required by deferred struct page init.
+ * deferred_init_memmap_chunk frees memory to the buddy allocator, which looks
+ * at the neighboring pages (up to MAX_PAGE_ORDER) to merge them.
+ * If KHO scratch is not aligned to that value, buddy can access uninitialized
+ * struct pages, which can cause a crash.
+ */
+#define SCRATCH_ALIGNMENT_BYTES (PAGE_SIZE * MAX_ORDER_NR_PAGES)
+static_assert(SCRATCH_ALIGNMENT_BYTES >= CMA_MIN_ALIGNMENT_BYTES);
+
 /* The magic token for preserved pages */
 #define KHO_PAGE_MAGIC 0x4b484f50U /* ASCII for 'KHOP' */
 
@@ -640,8 +650,8 @@ static void __init scratch_size_update(void)
 	 * Scratch areas are released as MIGRATE_CMA. Round them up to the right
 	 * size.
 	 */
-	scratch_size_lowmem = round_up(scratch_size_lowmem, CMA_MIN_ALIGNMENT_BYTES);
-	scratch_size_global = round_up(scratch_size_global, CMA_MIN_ALIGNMENT_BYTES);
+	scratch_size_lowmem = round_up(scratch_size_lowmem, SCRATCH_ALIGNMENT_BYTES);
+	scratch_size_global = round_up(scratch_size_global, SCRATCH_ALIGNMENT_BYTES);
 }
 
 static phys_addr_t __init scratch_size_node(int nid)
@@ -656,7 +666,7 @@ static phys_addr_t __init scratch_size_node(int nid)
 		size = scratch_size_pernode;
 	}
 
-	return round_up(size, CMA_MIN_ALIGNMENT_BYTES);
+	return round_up(size, SCRATCH_ALIGNMENT_BYTES);
 }
 
 /**
@@ -692,7 +702,7 @@ static void __init kho_reserve_scratch(void)
 	 * next kernel
 	 */
 	size = scratch_size_lowmem;
-	addr = memblock_phys_alloc_range(size, CMA_MIN_ALIGNMENT_BYTES, 0,
+	addr = memblock_phys_alloc_range(size, SCRATCH_ALIGNMENT_BYTES, 0,
 					 ARCH_LOW_ADDRESS_LIMIT);
 	if (!addr) {
 		pr_err("Failed to reserve lowmem scratch buffer\n");
@@ -705,7 +715,7 @@ static void __init kho_reserve_scratch(void)
 
 	/* reserve large contiguous area for allocations without nid */
 	size = scratch_size_global;
-	addr = memblock_phys_alloc(size, CMA_MIN_ALIGNMENT_BYTES);
+	addr = memblock_phys_alloc(size, SCRATCH_ALIGNMENT_BYTES);
 	if (!addr) {
 		pr_err("Failed to reserve global scratch buffer\n");
 		goto err_free_scratch_areas;
@@ -721,7 +731,7 @@ static void __init kho_reserve_scratch(void)
 	 */
 	for_each_node_state(nid, N_MEMORY) {
 		size = scratch_size_node(nid);
-		addr = memblock_alloc_range_nid(size, CMA_MIN_ALIGNMENT_BYTES,
+		addr = memblock_alloc_range_nid(size, SCRATCH_ALIGNMENT_BYTES,
 						0, MEMBLOCK_ALLOC_ACCESSIBLE,
 						nid, true);
 		if (!addr) {
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index e3fa7b2fac9d..18183062f751 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -3606,6 +3606,9 @@ static int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fo
 		} else if (unlikely(fork)) {
 			scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] during fork",
 				  p->comm, p->pid);
+		} else if (unlikely(scx_enable_state() != SCX_ENABLING)) {
+			scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] outside the enable path",
+				  p->comm, p->pid);
 		} else {
 			struct rq *rq;
 			struct rq_flags rf;
@@ -4577,20 +4580,25 @@ static struct cgroup *root_cgroup(void)
 	return &cgrp_dfl_root.cgrp;
 }
 
+/*
+ * cgroup_lock() must nest outside the rwsem write side: a writer waiting
+ * for cgroup_mutex deadlocks with cgroup teardown, which holds it while
+ * draining a set_* file write blocked on the rwsem behind the writer.
+ */
 static void scx_cgroup_lock(void)
 {
+	cgroup_lock();
 #ifdef CONFIG_EXT_GROUP_SCHED
 	percpu_down_write(&scx_cgroup_ops_rwsem);
 #endif
-	cgroup_lock();
 }
 
 static void scx_cgroup_unlock(void)
 {
-	cgroup_unlock();
 #ifdef CONFIG_EXT_GROUP_SCHED
 	percpu_up_write(&scx_cgroup_ops_rwsem);
 #endif
+	cgroup_unlock();
 }
 #else	/* CONFIG_EXT_GROUP_SCHED || CONFIG_EXT_SUB_SCHED */
 static inline struct cgroup *root_cgroup(void) { return NULL; }
@@ -5929,6 +5937,15 @@ static void scx_sub_disable(struct scx_sched *sch)
 	percpu_down_write(&scx_fork_rwsem);
 	scx_cgroup_lock();
 
+	/*
+	 * An enable that failed before scx_link_sched() never owned a cgroup or
+	 * task and won't be waited on by an ancestor's drain_descendants().
+	 * Nothing to reparent and walking the tasks can misbehave as the task
+	 * ownership invariant (either owned by self or parent) does not hold.
+	 */
+	if (list_empty(&sch->sibling))
+		goto dump;
+
 	set_cgroup_sched(sch_cgroup(sch), parent);
 
 	scx_task_iter_start(&sti, sch->cgrp);
@@ -5941,8 +5958,8 @@ static void scx_sub_disable(struct scx_sched *sch)
 			continue;
 
 		/*
-		 * By the time control reaches here, all descendant schedulers
-		 * should already have been disabled.
+		 * By the time control reaches here, all linked descendant
+		 * schedulers should have been disabled.
 		 */
 		WARN_ON_ONCE(!scx_task_on_sched(sch, p));
 
@@ -5993,15 +6010,22 @@ static void scx_sub_disable(struct scx_sched *sch)
 			/*
 			 * $p is initialized for $parent and still attached to
 			 * @sch. Disable and exit for @sch, switch over to
-			 * $parent, override the state to READY to account for
-			 * $p having already been initialized, and then enable.
+			 * $parent and override the state to READY to account
+			 * for $p having already been initialized.
 			 */
 			scx_disable_and_exit_task(sch, p);
 			scx_set_task_state(p, SCX_TASK_INIT_BEGIN);
 			scx_set_task_state(p, SCX_TASK_INIT);
 			scx_set_task_sched(p, parent);
 			scx_set_task_state(p, SCX_TASK_READY);
-			scx_enable_task(parent, p);
+
+			/*
+			 * A task on a non-ext class, possible under an
+			 * %SCX_OPS_SWITCH_PARTIAL root, stays READY and is
+			 * enabled by switching_to_scx() if it switches over.
+			 */
+			if (p->sched_class == &ext_sched_class)
+				scx_enable_task(parent, p);
 		}
 
 		task_rq_unlock(rq, p, &rf);
@@ -6009,6 +6033,7 @@ static void scx_sub_disable(struct scx_sched *sch)
 	}
 	scx_task_iter_stop(&sti);
 
+dump:
 	scx_disable_dump(sch);
 
 	scx_cgroup_unlock();
@@ -7708,10 +7733,14 @@ static void scx_sub_enable_workfn(struct kthread_work *work)
 
 			/*
 			 * $p is now only initialized for @sch and READY, which
-			 * is what we want. Assign it to @sch and enable.
+			 * is what we want. Assign it to @sch and, if it's on
+			 * the ext class, enable. A non-ext task, possible under
+			 * an %SCX_OPS_SWITCH_PARTIAL root, stays READY and is
+			 * enabled by switching_to_scx() if it switches over.
 			 */
 			scx_set_task_sched(p, sch);
-			scx_enable_task(sch, p);
+			if (p->sched_class == &ext_sched_class)
+				scx_enable_task(sch, p);
 
 			p->scx.flags &= ~SCX_TASK_SUB_INIT;
 		}
diff --git a/kernel/sched/ext/idle.c b/kernel/sched/ext/idle.c
index 8e8c6201b7df..6f93cc32b650 100644
--- a/kernel/sched/ext/idle.c
+++ b/kernel/sched/ext/idle.c
@@ -554,8 +554,10 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
 		    cpu_rq(cpu)->scx.local_dsq.nr == 0 &&
 		    (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) &&
 		    !cpumask_empty(idle_cpumask(waker_node)->cpu)) {
-			if (cpumask_test_cpu(cpu, allowed))
+			if (cpumask_test_cpu(cpu, allowed)) {
+				scx_idle_test_and_clear_cpu(cpu);
 				goto out_unlock;
+			}
 		}
 	}
 
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index d9c9d9480a45..e2e825dcd088 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1134,6 +1134,12 @@ void psi_cgroup_free(struct cgroup *cgroup)
 		return;
 
 	cancel_delayed_work_sync(&cgroup->psi->avgs_work);
+	/*
+	 * A psi_schedule_rtpoll_work() call racing the last trigger's
+	 * destruction may have re-armed the timer after psi_trigger_destroy()
+	 * deleted it. Spurious firing while the group is alive is harmless.
+	 */
+	timer_shutdown_sync(&cgroup->psi->rtpoll_timer);
 	free_percpu(cgroup->psi->pcpu);
 	/* All triggers must be removed by now */
 	WARN_ONCE(cgroup->psi->rtpoll_states, "psi: trigger leak\n");
@@ -1292,9 +1298,44 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 	return 0;
 }
 
+/*
+ * Create @group's rtpoll worker after psi_trigger_create() reported the need
+ * for one. kthread creation depends on the whole fork path and we don't want
+ * all of that nested inside cgroup_mutex, so the caller must drop it and any
+ * other lock that forks can wait behind. If two callers race, the loser stops
+ * its never-woken kthread.
+ */
+int psi_trigger_create_rtpoll_worker(struct psi_group *group)
+{
+	struct task_struct *task;
+
+	task = kthread_create(psi_rtpoll_worker, group, "psimon");
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+
+	scoped_guard(mutex, &group->rtpoll_trigger_lock) {
+		if (!rcu_access_pointer(group->rtpoll_task)) {
+			atomic_set(&group->rtpoll_wakeup, 0);
+			wake_up_process(task);
+			rcu_assign_pointer(group->rtpoll_task, task);
+
+			/*
+			 * Poll once to catch up on scheduling attempts dropped
+			 * while there was no rtpoll worker.
+			 */
+			psi_schedule_rtpoll_work(group, 1, true);
+			return 0;
+		}
+	}
+
+	kthread_stop(task);
+	return 0;
+}
+
 struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
 				       enum psi_res res, struct file *file,
-				       struct kernfs_open_file *of)
+				       struct kernfs_open_file *of,
+				       bool *need_rtpoll_worker)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
@@ -1302,6 +1343,8 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
 	bool privileged;
 	u32 window_us;
 
+	*need_rtpoll_worker = false;
+
 	if (static_branch_likely(&psi_disabled))
 		return ERR_PTR(-EOPNOTSUPP);
 
@@ -1362,26 +1405,14 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
 	if (privileged) {
 		mutex_lock(&group->rtpoll_trigger_lock);
 
-		if (!rcu_access_pointer(group->rtpoll_task)) {
-			struct task_struct *task;
-
-			task = kthread_create(psi_rtpoll_worker, group, "psimon");
-			if (IS_ERR(task)) {
-				kfree(t);
-				mutex_unlock(&group->rtpoll_trigger_lock);
-				return ERR_CAST(task);
-			}
-			atomic_set(&group->rtpoll_wakeup, 0);
-			wake_up_process(task);
-			rcu_assign_pointer(group->rtpoll_task, task);
-		}
-
 		list_add(&t->node, &group->rtpoll_triggers);
 		group->rtpoll_min_period = min(group->rtpoll_min_period,
 			div_u64(t->win.size, UPDATES_PER_WINDOW));
 		group->rtpoll_nr_triggers[t->state]++;
 		group->rtpoll_states |= (1 << t->state);
 
+		*need_rtpoll_worker = !rcu_access_pointer(group->rtpoll_task);
+
 		mutex_unlock(&group->rtpoll_trigger_lock);
 	} else {
 		mutex_lock(&group->avgs_lock);
@@ -1541,6 +1572,8 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 	size_t buf_size;
 	struct seq_file *seq;
 	struct psi_trigger *new;
+	bool need_rtpoll_worker;
+	int ret;
 
 	if (static_branch_likely(&psi_disabled))
 		return -EOPNOTSUPP;
@@ -1565,12 +1598,22 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, res, file, NULL);
+	new = psi_trigger_create(&psi_system, buf, res, file, NULL,
+				 &need_rtpoll_worker);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);
 	}
 
+	if (need_rtpoll_worker) {
+		ret = psi_trigger_create_rtpoll_worker(&psi_system);
+		if (ret) {
+			psi_trigger_destroy(new);
+			mutex_unlock(&seq->lock);
+			return ret;
+		}
+	}
+
 	smp_store_release(&seq->private, new);
 	mutex_unlock(&seq->lock);
 
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 18d0d9154317..ced2e131b061 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -274,8 +274,13 @@ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint,
 		} else {
 			set_bit(IMA_DIGSIG, &iint->atomic_flags);
 		}
-		if (xattr_len - sizeof(xattr_value->type) - hash_start >=
-				iint->ima_hash->length)
+		/*
+		 * Use addition, not subtraction: sizeof() forces unsigned
+		 * math and a short xattr_len would wrap around, bypassing
+		 * this bounds check.
+		 */
+		if (xattr_len >= (int)sizeof(xattr_value->type) + hash_start +
+				(int)iint->ima_hash->length)
 			/*
 			 * xattr length may be longer. md5 hash in previous
 			 * version occupied 20 bytes in xattr, instead of 16
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 5cea53fc36df..ff52becc3031 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -687,6 +687,43 @@ static int ima_file_check(struct file *file, int mask)
 					   MAY_APPEND), FILE_CHECK, 0, false);
 }
 
+/*
+ * ima_reset_action_flags - invalidate action flags after a content change
+ * @inode: inode of the file whose content is about to be truncated
+ *
+ * Clear IMA_DONE_MASK so the file is re-collected, re-measured,
+ * re-audited, and re-appraised on next access.
+ */
+static void ima_reset_action_flags(struct inode *inode)
+{
+	struct ima_iint_cache *iint;
+
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+		return;
+
+	iint = ima_iint_find(inode);
+	if (!iint)
+		return;
+
+	mutex_lock(&iint->mutex);
+	iint->flags &= ~IMA_DONE_MASK;
+	iint->measured_pcrs = 0;
+	mutex_unlock(&iint->mutex);
+	return;
+}
+
+static int ima_path_truncate(const struct path *path)
+{
+	ima_reset_action_flags(path->dentry->d_inode);
+	return 0;
+}
+
+static int ima_file_truncate(struct file *file)
+{
+	ima_reset_action_flags(file_inode(file));
+	return 0;
+}
+
 static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf,
 			    size_t buf_size)
 {
@@ -1300,11 +1337,13 @@ static struct security_hook_list ima_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(file_release, ima_file_free),
 	LSM_HOOK_INIT(mmap_file, ima_file_mmap),
 	LSM_HOOK_INIT(file_mprotect, ima_file_mprotect),
+	LSM_HOOK_INIT(file_truncate, ima_file_truncate),
 	LSM_HOOK_INIT(kernel_load_data, ima_load_data),
 	LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data),
 	LSM_HOOK_INIT(kernel_read_file, ima_read_file),
 	LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file),
 	LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod),
+	LSM_HOOK_INIT(path_truncate, ima_path_truncate),
 #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS
 	LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update),
 #endif
diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c
index 78cc49a7f9a6..6b4515c28aa0 100644
--- a/tools/testing/selftests/sched_ext/numa.bpf.c
+++ b/tools/testing/selftests/sched_ext/numa.bpf.c
@@ -34,7 +34,8 @@ static bool is_cpu_idle(s32 cpu, int node)
 s32 BPF_STRUCT_OPS(numa_select_cpu,
 		   struct task_struct *p, s32 prev_cpu, u64 wake_flags)
 {
-	int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p));
+	s32 task_cpu = scx_bpf_task_cpu(p);
+	int node = __COMPAT_scx_bpf_cpu_node(task_cpu);
 	s32 cpu;
 
 	/*
@@ -48,6 +49,16 @@ s32 BPF_STRUCT_OPS(numa_select_cpu,
 		cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node,
 						__COMPAT_SCX_PICK_IDLE_IN_NODE);
 
+	/*
+	 * @task_cpu may be outside of p->cpus_ptr if @p's affinity
+	 * changed while it was sleeping. This means it's possible for
+	 * p->cpus_ptr to not include any CPUs from @node.
+	 * If we failed to find a cpu in @node, check if @task_cpu
+	 * is outside of p->cpus_ptr and just return @prev_cpu if it is.
+	 */
+	if (cpu < 0 && !bpf_cpumask_test_cpu(task_cpu, p->cpus_ptr))
+		return prev_cpu;
+
 	if (is_cpu_idle(cpu, node))
 		scx_bpf_error("CPU %d should be marked as busy", cpu);