Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-7.3-rc8).

No conflicts. Adjacent changes:

drivers/net/ethernet/microchip/lan865x/lan865x.c
  2a3f6d2a9ac3 ("microchip: lan865x: move setting of netops to fix crash")
  15358c2c3dca ("net: ethernet: oa_tc6: return ERR_PTR from oa_tc6_init()")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

238 files changed, 8273 insertions, 982 deletions

diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index e8d6d5d858b6..41ec69f5dceb 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -77,6 +77,7 @@ properties:
               - mscc,ocelot-spi
               - mscc,jaguar2-spi
               - sophgo,sg2042-spi
+              - syna,sl2610-spi
               - thead,th1520-spi
               - ultrarisc,dp1000-spi
           - const: snps,dw-apb-ssi
diff --git a/Documentation/filesystems/propagate_umount.txt b/Documentation/filesystems/propagate_umount.txt
index 9a7eb96df300..de58ce817582 100644
--- a/Documentation/filesystems/propagate_umount.txt
+++ b/Documentation/filesystems/propagate_umount.txt
@@ -32,12 +32,12 @@ of set.  They can be reparented to the place where the bottom of
 stack is attached to a mount that will survive.  NOTE: doing that
 will violate a constraint on having no more than one mount with
 the same parent/mountpoint pair; however, the caller (umount_tree())
-will immediately remedy that - it may keep unmounted element attached
-to parent, but only if the parent itself is unmounted.  Since all
-conflicts created by reparenting have common parent *not* in the
-set and one side of the conflict (bottom of the stack of overmounts)
-is in the set, it will be resolved.  However, we rely upon umount_tree()
-doing that pretty much immediately after the call of propagate_umount().
+will immediately remedy that - it detaches every element of the set
+from its parent.  Since all conflicts created by reparenting have
+common parent *not* in the set and one side of the conflict (bottom
+of the stack of overmounts) is in the set, it will be resolved.
+However, we rely upon umount_tree() doing that pretty much immediately
+after the call of propagate_umount().
 
 Algorithm is based on two statements:
 	1) for any set S, there is a maximal non-shifting subset of S
diff --git a/Documentation/filesystems/sharedsubtree.rst b/Documentation/filesystems/sharedsubtree.rst
index 8b7dc9159083..8bae6d9a7e04 100644
--- a/Documentation/filesystems/sharedsubtree.rst
+++ b/Documentation/filesystems/sharedsubtree.rst
@@ -564,8 +564,8 @@ f) Unmount semantics
    where 'A' is a mount mounted on mount 'B' at dentry 'b'.
 
    If mount 'B' is shared, then all most-recently-mounted mounts at dentry
-   'b' on mounts that receive propagation from mount 'B' and does not have
-   sub-mounts within them are unmounted.
+   'b' on mounts that receive propagation from mount 'B' are unmounted as
+   well, if every mount below them is also unmounted.
 
    Example: Let's say 'B1', 'B2', 'B3' are shared mounts that propagate to
    each other.
@@ -584,10 +584,18 @@ f) Unmount semantics
 
    So all 'C1', 'C2' and 'C3' should be unmounted.
 
-   If any of 'C2' or 'C3' has some child mounts, then that mount is not
-   unmounted, but all other mounts are unmounted. However if 'C1' is told
-   to be unmounted and 'C1' has some sub-mounts, the umount operation is
-   failed entirely.
+   If any of 'C2' or 'C3' has a child mount that cannot be unmounted
+   then that mount is not unmounted. But all other mounts are unmounted.
+   A child mount that is itself unmounted by the same unmount
+   propagation does not keep its parent mounted. However if 'C1' is
+   supposed to be unmounted and 'C1' has some sub-mounts, the unmount
+   fails.
+
+   A lazy umount (MNT_DETACH) takes a whole tree. Every mount of the
+   tree then propagates its unmount from its own parent as described
+   above, so the mounts that receive propagation lose the corresponding
+   trees as well. Documentation/filesystems/propagate_umount.txt has the
+   precise rules, including the ones for locked mounts.
 
 g) Clone Namespace
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 509b35b5a0e7..0413c1213963 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8172,7 +8172,6 @@ F:	drivers/gpu/drm/tiny/hx8357d.c
 
 DRM DRIVER FOR HYPERV SYNTHETIC VIDEO DEVICE
 M:	Dexuan Cui <decui@microsoft.com>
-M:	Long Li <longli@microsoft.com>
 M:	Saurabh Sengar <ssengar@linux.microsoft.com>
 L:	linux-hyperv@vger.kernel.org
 L:	dri-devel@lists.freedesktop.org
@@ -12163,11 +12162,9 @@ S:	Maintained
 F:	drivers/media/i2c/hi847.c
 
 Hyper-V/Azure CORE AND DRIVERS
-M:	"K. Y. Srinivasan" <kys@microsoft.com>
 M:	Haiyang Zhang <haiyangz@microsoft.com>
 M:	Wei Liu <wei.liu@kernel.org>
 M:	Dexuan Cui <decui@microsoft.com>
-M:	Long Li <longli@microsoft.com>
 L:	linux-hyperv@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
@@ -18831,6 +18828,7 @@ F:	drivers/net/ethernet/nebula-matrix/
 
 NETCONSOLE
 M:	Breno Leitao <leitao@debian.org>
+R:	Gustavo Luiz Duarte <gustavold@gmail.com>
 S:	Maintained
 F:	Documentation/networking/netconsole.rst
 F:	drivers/net/netconsole.c
diff --git a/Makefile b/Makefile
index 7c855e6fe544..0dc1a9f4e63e 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 3
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 87560d8b254e..1da277baacf7 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -421,8 +421,9 @@
 	mov	x2, xzr
 	mrs	x1, id_aa64dfr0_el1
 	ubfx	x1, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
-	cmp	x1, #ID_AA64DFR0_EL1_PMUVer_V3P9
-	b.lt	.Lskip_pmuv3p9_\@
+	cmp	x1, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF
+	ccmp	x1, #ID_AA64DFR0_EL1_PMUVer_V3P9, #8, ne
+	b.lt	.Lskip_pmuv3p9_\@		// Skip if < PMUv3p9 or IMP_DEF
 
 	orr	x0, x0, #HDFGRTR2_EL2_nPMICNTR_EL0
 	orr	x0, x0, #HDFGRTR2_EL2_nPMICFILTR_EL0
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index d2690c3ec528..ea66339435bf 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -25,6 +25,9 @@ KASAN_SANITIZE_stacktrace.o := n
 KCOV_INSTRUMENT_entry-common.o := n
 KCOV_INSTRUMENT_idle.o := n
 
+# Softirq stack switching can run outside interrupt context.
+KCOV_INSTRUMENT_irq.o := n
+
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-common.o process.o ptrace.o			\
diff --git a/arch/nios2/include/asm/checksum.h b/arch/nios2/include/asm/checksum.h
index 69004e07a1ba..b6b415ae17a0 100644
--- a/arch/nios2/include/asm/checksum.h
+++ b/arch/nios2/include/asm/checksum.h
@@ -27,7 +27,7 @@ static inline __sum16 csum_fold(__wsum sum)
 		"add	%0, %0, r8\n"
 		"nor	%0, %0, %0\n"
 		: "=r" (sum)
-		: "r" (sum << 16), "0" (sum)
+		: "r" ((__force u32)sum << 16), "0" (sum)
 		: "r8");
 	return (__force __sum16) sum;
 }
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d6c2dbf8455c..5874ca30f4f6 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -453,9 +453,10 @@ config SMP
 config NR_CPUS
 	int "Maximum number of CPUs (2-512)"
 	depends on SMP
-	range 2 512 if !RISCV_SBI_V01
-	range 2 32 if RISCV_SBI_V01 && 32BIT
+	range 2 512 if !RISCV_SBI_V01 && 64BIT
+	range 2 128 if !RISCV_SBI_V01 && 32BIT
 	range 2 64 if RISCV_SBI_V01 && 64BIT
+	range 2 32 if RISCV_SBI_V01 && 32BIT
 	default "32" if 32BIT
 	default "64" if RISCV_SBI_V01 && 64BIT
 	default "256" if !RISCV_SBI_V01 && 64BIT
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 3c945d086c7d..622ade116a2d 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -46,7 +46,7 @@ config ERRATA_MIPS_P8700_PAUSE_OPCODE
 
 config ERRATA_SIFIVE
 	bool "SiFive errata"
-	depends on RISCV_ALTERNATIVE
+	depends on RISCV_ALTERNATIVE && 64BIT
 	help
 	  All SiFive errata Kconfig depend on this Kconfig. Disabling
 	  this Kconfig will disable all SiFive errata. Please say "Y"
@@ -96,6 +96,20 @@ config ERRATA_STARFIVE_JH7100
 	  Say "Y" if you want to support the BeagleV Starlight and/or
 	  StarFive VisionFive V1 boards.
 
+config ERRATA_SIFIVE_MAL_9092
+	bool "Apply SiFive HLV/HLVX/HSV fence errata"
+	depends on ERRATA_SIFIVE && 64BIT
+	default y
+	help
+	  This will apply the SiFive MAL-9092 errata to add fence.rw
+	  instructions around all HLV/HLVX/HSV instructions.
+
+	  Note: HSTATUS.HU is cleared during KVM initialization. If future
+	  changes enable HSTATUS.HU to allow hypervisor instructions in
+	  U-mode, additional errata handling may be required.
+
+	  If you don't know what to do here, say "Y".
+
 config ERRATA_THEAD
 	bool "T-HEAD errata"
 	depends on RISCV_ALTERNATIVE
@@ -146,6 +160,7 @@ config ERRATA_THEAD_PMU
 config ERRATA_THEAD_GHOSTWRITE
 	bool "Apply T-Head Ghostwrite errata"
 	depends on ERRATA_THEAD && RISCV_ISA_XTHEADVECTOR
+	select RISCV_ALTERNATIVE_EARLY
 	default y
 	help
 	  The T-Head C9xx cores have a vulnerability in the xtheadvector
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 429e07589306..cecbce0c4983 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -34,6 +34,7 @@ config ARCH_RENESAS
 config ARCH_SIFIVE
 	bool "SiFive SoCs"
 	select ERRATA_SIFIVE
+	depends on 64BIT
 	help
 	  This enables support for SiFive SoC platform hardware.
 
diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c
index df80c9614df1..1a5d223ebf35 100644
--- a/arch/riscv/errata/sifive/errata.c
+++ b/arch/riscv/errata/sifive/errata.c
@@ -51,6 +51,22 @@ static bool errata_cip_1200_check_func(unsigned long  arch_id, unsigned long imp
 	return true;
 }
 
+static bool errata_mal_9092_check_func(unsigned long  arch_id, unsigned long impid)
+{
+	/*
+	 * Affected cores:
+	 * Architecture ID: 0x8000000000000109
+	 * Implementation ID: 0x19251031, 0x19251217, 0x19260320
+	 */
+
+	if (arch_id != 0x8000000000000109)
+		return false;
+	if (impid != 0x19251031 && impid != 0x19251217 && impid != 0x19260320)
+		return false;
+
+	return true;
+}
+
 static struct errata_info_t errata_list[ERRATA_SIFIVE_NUMBER] = {
 	{
 		.name = "cip-453",
@@ -60,6 +76,10 @@ static struct errata_info_t errata_list[ERRATA_SIFIVE_NUMBER] = {
 		.name = "cip-1200",
 		.check_func = errata_cip_1200_check_func
 	},
+	{
+		.name = "mal-9092",
+		.check_func = errata_mal_9092_check_func
+	},
 };
 
 static u32 __init_or_module sifive_errata_probe(unsigned long archid,
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 739fcc84bf7b..5efa72823475 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -40,6 +40,8 @@ extern u32 thead_vlenb_of;
 
 void __init riscv_user_isa_enable(void);
 
+void riscv_clear_hypervisor_csr(void);
+
 #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) {	\
 	.name = #_name,									\
 	.property = #_name,								\
diff --git a/arch/riscv/include/asm/errata_list_vendors.h b/arch/riscv/include/asm/errata_list_vendors.h
index ec7eba373437..c62a82f60468 100644
--- a/arch/riscv/include/asm/errata_list_vendors.h
+++ b/arch/riscv/include/asm/errata_list_vendors.h
@@ -11,7 +11,8 @@
 #ifdef CONFIG_ERRATA_SIFIVE
 #define	ERRATA_SIFIVE_CIP_453 0
 #define	ERRATA_SIFIVE_CIP_1200 1
-#define	ERRATA_SIFIVE_NUMBER 2
+#define	ERRATA_SIFIVE_MAL_9092 2
+#define	ERRATA_SIFIVE_NUMBER 3
 #endif
 
 #ifdef CONFIG_ERRATA_THEAD
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index 90c86b115e00..6f3bc9bdb85e 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -40,6 +40,7 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 
 	if (!access_ok(uaddr, sizeof(u32)))
 		return -EFAULT;
+	uaddr = untagged_addr(uaddr);
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -82,6 +83,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 
 	if (!access_ok(uaddr, sizeof(u32)))
 		return -EFAULT;
+	uaddr = untagged_addr(uaddr);
 
 	__enable_user_access();
 	__asm__ __volatile__ (
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
index 7c6daf116756..8fcc848c196e 100644
--- a/arch/riscv/include/asm/insn-def.h
+++ b/arch/riscv/include/asm/insn-def.h
@@ -192,18 +192,28 @@
 	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(49),		\
 	       __RD(0), RS1(gaddr), RS2(vmid))
 
+#define ALT_SIFIVE_MAL_9092_FENCE					\
+ALTERNATIVE("nop", "fence rw, rw", SIFIVE_VENDOR_ID,			\
+	    ERRATA_SIFIVE_MAL_9092, CONFIG_ERRATA_SIFIVE_MAL_9092)
+
 #define HLVX_HU(dest, addr)					\
+	ALT_SIFIVE_MAL_9092_FENCE "\n"				\
 	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(50),		\
-	       RD(dest), RS1(addr), __RS2(3))
+	       RD(dest), RS1(addr), __RS2(3)) "\n"		\
+	ALT_SIFIVE_MAL_9092_FENCE
 
 #define HLV_W(dest, addr)					\
+	ALT_SIFIVE_MAL_9092_FENCE "\n"				\
 	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(52),		\
-	       RD(dest), RS1(addr), __RS2(0))
+	       RD(dest), RS1(addr), __RS2(0)) "\n"		\
+	ALT_SIFIVE_MAL_9092_FENCE
 
 #ifdef CONFIG_64BIT
 #define HLV_D(dest, addr)					\
+	ALT_SIFIVE_MAL_9092_FENCE "\n"				\
 	INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(54),		\
-	       RD(dest), RS1(addr), __RS2(0))
+	       RD(dest), RS1(addr), __RS2(0)) "\n"		\
+	ALT_SIFIVE_MAL_9092_FENCE
 #else
 #define HLV_D(dest, addr)					\
 	__ASM_STR(.error "hlv.d requires 64-bit support")
diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h
index 023a412fe38d..49e40eef4ed7 100644
--- a/arch/riscv/include/asm/scs.h
+++ b/arch/riscv/include/asm/scs.h
@@ -4,6 +4,7 @@
 
 #ifdef __ASSEMBLER__
 #include <asm/asm-offsets.h>
+#include <asm/csr.h>
 
 #ifdef CONFIG_SHADOW_CALL_STACK
 
@@ -22,9 +23,17 @@
 	REG_L	gp, TASK_TI_SCS_SP(tp)
 .endm
 
-/* Load task_scs_sp(current) to gp, but only if tp has changed. */
-.macro scs_load_current_if_task_changed prev
-	beq	\prev, tp, _skip_scs
+/*
+ * Load task_scs_sp(current) to gp, but only when the trap came from U-mode.
+ * The source privilege level is taken from the saved sstatus.SPP bit (written
+ * by hardware on trap entry), not by comparing tp.  tp is a user-writable
+ * register, so gating the shadow call stack reload on it let a user task that
+ * set tp == &current skip the reload and run the kernel with an attacker
+ * controlled gp (the shadow call stack pointer).
+ */
+.macro scs_load_current_if_from_user status, tmp
+	andi	\tmp, \status, SR_SPP
+	bnez	\tmp, _skip_scs
 	scs_load_current
 _skip_scs:
 .endm
@@ -42,7 +51,7 @@ _skip_scs:
 .endm
 .macro scs_load_current
 .endm
-.macro scs_load_current_if_task_changed prev
+.macro scs_load_current_if_from_user status, tmp
 .endm
 .macro scs_save_current
 .endm
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index fffe72a77208..1f8dcae3af51 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -137,8 +137,8 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
 		"csrr	%0, " __stringify(CSR_VSTART) "\n\t"
 		"csrr	%1, " __stringify(CSR_VTYPE) "\n\t"
 		"csrr	%2, " __stringify(CSR_VL) "\n\t"
-		: "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl),
-		"=r" (dest->vcsr) : :);
+		: "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl)
+		: :);
 
 	if (has_xtheadvector()) {
 		unsigned long status;
@@ -230,7 +230,7 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
 			"add		%1, %1, %0\n\t"
 			"vse8.v		v24, (%1)\n\t"
 			".option pop\n\t"
-			: "=&r" (vl) : "r" (datap) : "memory");
+			: "=&r" (vl), "+r" (datap) : : "memory");
 	}
 	riscv_v_disable();
 }
@@ -266,7 +266,7 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
 			"add		%1, %1, %0\n\t"
 			"vle8.v		v24, (%1)\n\t"
 			".option pop\n\t"
-			: "=&r" (vl) : "r" (datap) : "memory");
+			: "=&r" (vl), "+r" (datap) : : "memory");
 	}
 	__vstate_csr_restore(restore_from);
 	riscv_v_disable();
diff --git a/arch/riscv/include/uapi/asm/vendor/mips.h b/arch/riscv/include/uapi/asm/vendor/mips.h
index e65ab268b265..a31c23afe74f 100644
--- a/arch/riscv/include/uapi/asm/vendor/mips.h
+++ b/arch/riscv/include/uapi/asm/vendor/mips.h
@@ -1,3 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 
-#define RISCV_HWPROBE_VENDOR_EXT_XMIPSEXECTL	BIT(0)
+#include <linux/const.h>
+
+#define RISCV_HWPROBE_VENDOR_EXT_XMIPSEXECTL	_BITULL(0)
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 61d21f714830..7329792978cc 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -1233,6 +1233,18 @@ void __init riscv_user_isa_enable(void)
 		pr_warn("Zicbop disabled as it is unavailable on some harts\n");
 }
 
+void riscv_clear_hypervisor_csr(void)
+{
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_H))
+		return;
+
+	/*
+	 * Clear HSTATUS.HU to restrict hypervisor instructions to HS-mode.
+	 * This prevents user-mode from executing HLV/HSV instructions.
+	 */
+	csr_clear(CSR_HSTATUS, HSTATUS_HU);
+}
+
 #ifdef CONFIG_RISCV_ALTERNATIVE
 /*
  * Alternative patch sites consider 48 bits when determining when to patch
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index d799c4e56f80..61b7a7716697 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -208,7 +208,7 @@ SYM_CODE_START(handle_exception)
 	load_global_pointer
 
 	/* Load the kernel shadow call stack pointer if coming from userspace */
-	scs_load_current_if_task_changed s5
+	scs_load_current_if_from_user s1, s5
 
 #ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
 	move a0, sp
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 2239c28981bc..2b5adf01c550 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -48,7 +48,7 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
 		if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
 			return addr;
 		phys = __pa_symbol(addr);
-	} else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) {
+	} else if (IS_ENABLED(CONFIG_EXECMEM)) {
 		struct page *page = vmalloc_to_page(addr);
 
 		BUG_ON(!page);
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index f336a183667e..a0055743d3ba 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -230,6 +230,7 @@ static int riscv_vr_set(struct task_struct *target,
 		return -ENODATA;
 
 	/* Copy rest of the vstate except datap */
+	memset(&ptrace_vstate, 0, sizeof(ptrace_vstate));
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ptrace_vstate, 0,
 				 sizeof(struct __riscv_v_regset_state));
 	if (unlikely(ret))
@@ -299,6 +300,9 @@ static int riscv_cfi_get(struct task_struct *target,
 	struct user_cfi_state user_cfi;
 	struct pt_regs *regs;
 
+	if (!is_user_lpad_enabled() && !is_user_shstk_enabled())
+		return -EINVAL;
+
 	memset(&user_cfi, 0, sizeof(user_cfi));
 	regs = task_pt_regs(target);
 
@@ -337,8 +341,12 @@ static int riscv_cfi_set(struct task_struct *target,
 	struct user_cfi_state user_cfi;
 	struct pt_regs *regs;
 
+	if (!is_user_lpad_enabled() && !is_user_shstk_enabled())
+		return -EINVAL;
+
 	regs = task_pt_regs(target);
 
+	memset(&user_cfi, 0, sizeof(user_cfi));
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_cfi, 0, -1);
 	if (ret)
 		return ret;
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index a32344bb220d..d79f99b86033 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -366,6 +366,8 @@ void __init setup_arch(char **cmdline_p)
 
 	if (!IS_ENABLED(CONFIG_RISCV_ISA_ZBB) || !riscv_isa_extension_available(NULL, ZBB))
 		static_branch_disable(&efficient_ffs_key);
+
+	riscv_clear_hypervisor_csr();
 }
 
 bool arch_cpu_is_hotpluggable(int cpu)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index f6ef57930b50..a9de2dae804c 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -244,6 +244,8 @@ asmlinkage __visible void smp_callin(void)
 
 	numa_add_cpu(curr_cpuid);
 
+	riscv_clear_hypervisor_csr();
+
 	pr_debug("CPU%u: Booted secondary hartid %lu\n", curr_cpuid,
 		cpuid_to_hartid_map(curr_cpuid));
 
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 3efbf7874f3b..db220966f782 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -43,6 +43,8 @@ void suspend_save_csrs(struct suspend_context *context)
 
 void suspend_restore_csrs(struct suspend_context *context)
 {
+	riscv_clear_hypervisor_csr();
+
 	csr_write(CSR_SCRATCH, 0);
 	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG))
 		csr_write(CSR_ENVCFG, context->envcfg);
diff --git a/arch/riscv/lib/strnlen.S b/arch/riscv/lib/strnlen.S
index a8911605c248..5b3bbf0a3098 100644
--- a/arch/riscv/lib/strnlen.S
+++ b/arch/riscv/lib/strnlen.S
@@ -87,9 +87,25 @@ strnlen_zbb:
 	 * Aligned boundary.  Use the address of the last valid byte
 	 * (s + count - 1) to avoid loading a word past the count
 	 * boundary in the loop below.  count == 0 is handled above.
+	 *
+	 * Saturate the boundary when s + count would wrap around (very
+	 * large counts, e.g. SIZE_MAX passed by FORTIFY strcat/strlcat
+	 * with a destination whose size is unknown at compile time).
+	 * Without this, the wrapped boundary lands before s and the
+	 * pre-loop guard below always exits, returning a truncated
+	 * length.
+	 *
+	 * Clamping the increment to ~s (== SIZE_MAX - s) keeps the
+	 * computation branchless and wrap-free:
+	 *
+	 *     s + min(count - 1, ~s) == saturating_add(s, count - 1)
+	 *
+	 * Saturating makes the scan equivalent to strlen().
 	 */
-	add	t4, a0, a1
-	addi	t4, t4, -1
+	addi	t4, a1, -1	/* count - 1 */
+	not	t1, a0		/* SIZE_MAX - s */
+	minu	t4, t4, t1	/* clamp, so s + t4 can never wrap */
+	add	t4, a0, t4	/* saturated s + count - 1 */
 	andi	t4, t4, -SZREG
 
 	/* Get the first word.  */
diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
index dd1530af3ef1..e252eba55ede 100644
--- a/arch/riscv/mm/extable.c
+++ b/arch/riscv/mm/extable.c
@@ -68,8 +68,8 @@ ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
 
 	addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
 
-	offset = addr & 0x7UL;
-	addr &= ~0x7UL;
+	offset = addr & (sizeof(data) - 1);
+	addr &= ~(sizeof(data) - 1);
 
 	data = *(unsigned long *)addr >> (offset * 8);
 
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 0b4a1c0b0b16..9900a5c59fd3 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -426,7 +426,7 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 	int ret;
 
 	/*
-	 * Continue afters errors in setting up stimer clockevents
+	 * Continue after errors in setting up stimer clockevents
 	 * as we can run with the LAPIC timer as a fallback.
 	 */
 	ret = hv_stimer_alloc(false);
@@ -434,7 +434,7 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 		pr_warn("stimer setup failed with error %d\n", ret);
 
 	/*
-	 * Still register the LAPIC timer to allows users
+	 * Still register the LAPIC timer to allow users
 	 * to switch to LAPIC timer via /sys, if they want to.
 	 */
 	if (old_setup_percpu_clockev)
@@ -727,7 +727,8 @@ int hv_apicid_to_vp_index(u32 apic_id)
 	input->partition_id = HV_PARTITION_ID_SELF;
 	input->apic_ids[0] = apic_id;
 
-	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+	/* Treat input as having 2 APIC IDs so output is 64-bit aligned */
+	output = (void *)input + struct_size(input, apic_ids, 2);
 
 	control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_INDEX_FROM_APIC_ID;
 	status = hv_do_hypercall(control, input, output);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f70ee74b5f92..fe84cf4e97d3 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -477,6 +477,8 @@
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
 #define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+
+#define X86_FEATURE_TLBSYNC_SFW_NO	(20*32+ 4) /* TLBI Erratum #1718 fixed in microcode */
 #define X86_FEATURE_VERW_CLEAR		(20*32+ 5) /* The memory form of VERW mitigates TSA */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* Null Selector Clears Base */
 
@@ -587,4 +589,5 @@
 #define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
 #define X86_BUG_VMSCAPE			X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */
 #define X86_BUG_SEAMRET_INVD_VMCS	X86_BUG( 1*32+11) /* "seamret_invd_vmcs" SEAMRET from P-SEAMLDR clears the current VMCS */
+#define X86_BUG_TLBI			X86_BUG( 1*32+12) /* "tlbi" AMD TLBI Erratum #1718 */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 866ea78ba156..eba925c85f52 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -110,6 +110,12 @@ static inline void __tlbsync(void)
 
 	/* TLBSYNC: supported in binutils >= 0.36. */
 	asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory");
+
+	if (!static_cpu_has_bug(X86_BUG_TLBI))
+		return;
+
+	/* TLBSYNC: supported in binutils >= 0.36. */
+	asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory");
 }
 #else
 /* Some compilers (I'm looking at you clang!) simply can't do DCE */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 54e14ed276b5..40463bad1078 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1049,6 +1049,10 @@ static void init_amd_zen5(struct cpuinfo_x86 *c)
 		msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
 		pr_emerg_once("RDSEED32 is broken. Disabling the corresponding CPUID bit.\n");
 	}
+
+	if (cpu_has(c, X86_FEATURE_INVLPGB) &&
+	    !cpu_has(c, X86_FEATURE_TLBSYNC_SFW_NO))
+		set_cpu_bug(c, X86_BUG_TLBI);
 }
 
 static void init_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 6b0a5861ccb8..d8dd2cadcbf7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -265,11 +265,39 @@ noinstr u32 kvm_read_and_reset_apf_flags(void)
 }
 EXPORT_SYMBOL_FOR_KVM(kvm_read_and_reset_apf_flags);
 
+static __always_inline bool kvm_apf_reason_pending(void)
+{
+	return __this_cpu_read(async_pf_enabled) &&
+	       __this_cpu_read(apf_reason.flags);
+}
+
 noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 {
-	u32 flags = kvm_read_and_reset_apf_flags();
 	irqentry_state_t state;
+	u32 flags;
+
+	if (!kvm_apf_reason_pending())
+		return false;
+
+	/*
+	 * The guest does not enable KVM_ASYNC_PF_SEND_ALWAYS, so the host
+	 * delivers async #PF only to user mode (or as a #PF VM-exit, which KVM
+	 * reads itself). A #PF from kernel mode can still arrive between that
+	 * delivery and the read of the reason flags, inside an NMI that
+	 * interrupted it, for instance perf reading user memory for a call
+	 * chain. Such a fault is not async, so leave the async PF flags
+	 * untouched for the outer handler.  Outside NMI context, on the other
+	 * hand, async PF flags on a kernel-mode fault mean the host is broken.
+	 */
+	if (!user_mode(regs)) {
+		if (likely(in_nmi()))
+			return false;
+		state = irqentry_enter(regs);
+		instrumentation_begin();
+		panic("Host injected async #PF in kernel mode\n");
+	}
 
+	flags = kvm_read_and_reset_apf_flags();
 	if (!flags)
 		return false;
 
@@ -285,8 +313,6 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 		panic("Host injected async #PF in interrupt disabled region\n");
 
 	if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) {
-		if (unlikely(!(user_mode(regs))))
-			panic("Host injected async #PF in kernel mode\n");
 		/* Page is swapped out by the host. */
 		kvm_async_pf_task_wait_schedule(token);
 	} else {
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 2ae7f9ed4cf8..b2a295a9f084 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -275,8 +275,18 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_pagewalk *w,
 				  unsigned pte_access, unsigned pte_pkey,
 				  u64 access)
 {
-	/* strip nested paging fault error codes */
-	unsigned int pfec = access;
+	/*
+	 * Of the error codes that do not contribute to the index in
+	 * fmt->permissions, PK and SS are not supported by shadow paging
+	 * and also not provided to EPT violations, but SS *is* included
+	 * in the NPT exit code.  RSVD faults are handled elsewhere.
+	 */
+	unsigned int pfec = access & ~PFERR_SS_MASK;
+	if (WARN_ON_ONCE(pfec & ~(PFERR_PRESENT_MASK | PFERR_WRITE_MASK |
+				  PFERR_USER_MASK | PFERR_FETCH_MASK)))
+		pfec &= (PFERR_PRESENT_MASK | PFERR_WRITE_MASK |
+			 PFERR_USER_MASK | PFERR_FETCH_MASK);
+
 	unsigned long rflags = kvm_x86_call(get_rflags)(vcpu);
 
 	/*
@@ -301,8 +311,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_pagewalk *w,
 	kvm_mmu_refresh_passthrough_bits(vcpu, w);
 
 	fault = (fmt->permissions[index] >> pte_access) & 1;
-
-	WARN_ON_ONCE(pfec & (PFERR_PK_MASK | PFERR_SS_MASK | PFERR_RSVD_MASK));
 	if (unlikely(fmt->pkru_mask)) {
 		u32 pkru_bits, offset;
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 27427e7f22fa..e5450faa669e 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -328,7 +328,6 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	int offset;
 	u64 walk_nx_mask = 0;
 	const int write_fault = access & PFERR_WRITE_MASK;
-	const int user_fault  = access & PFERR_USER_MASK;
 	const int fetch_fault = access & PFERR_FETCH_MASK;
 	/*
 	 * Note! Track the error_code that's common to legacy shadow paging
@@ -486,7 +485,7 @@ retry_walk:
 	return 1;
 
 error:
-	errcode |= write_fault | user_fault;
+	errcode |= access & (PFERR_WRITE_MASK | PFERR_USER_MASK | PFERR_SS_MASK);
 	if (fetch_fault && has_pferr_fetch(w))
 		errcode |= PFERR_FETCH_MASK;
 
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 3b037e385523..96ca39c0045f 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -395,6 +395,11 @@ static phys_addr_t avic_get_backing_page_address(struct vcpu_svm *svm)
 	return __sme_set(__pa(svm->vcpu.arch.apic->regs));
 }
 
+static bool avic_is_addressable_vcpu(struct kvm_vcpu *vcpu)
+{
+	return vcpu->vcpu_id <= __avic_get_max_physical_id(vcpu->kvm, NULL);
+}
+
 void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 {
 	struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm);
@@ -412,7 +417,6 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 
 static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 {
-	u32 max_id = x2avic_enabled ? x2avic_max_physical_id : AVIC_MAX_PHYSICAL_ID;
 	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 id = vcpu->vcpu_id;
@@ -425,7 +429,7 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	 * avic_vcpu_load() expects to be called if and only if the vCPU has
 	 * fully initialized AVIC.
 	 */
-	if (id > max_id) {
+	if (!avic_is_addressable_vcpu(vcpu)) {
 		kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG);
 		vcpu->arch.apic->apicv_active = false;
 		return 0;
@@ -885,6 +889,14 @@ int avic_init_vcpu(struct vcpu_svm *svm)
 	return ret;
 }
 
+void avic_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
+
+	if (kvm_svm->avic_physical_id_table && avic_is_addressable_vcpu(vcpu))
+		WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], 0);
+}
+
 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 {
 	avic_handle_dfr_update(vcpu);
@@ -1045,8 +1057,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu,
 	if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
 		return;
 
-	if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >=
-			 PAGE_SIZE << avic_get_physical_id_table_order(vcpu->kvm)))
+	if (WARN_ON_ONCE(!avic_is_addressable_vcpu(vcpu)))
 		return;
 
 	/*
@@ -1108,8 +1119,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action)
 
 	lockdep_assert_preemption_disabled();
 
-	if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >=
-			 PAGE_SIZE << avic_get_physical_id_table_order(vcpu->kvm)))
+	if (WARN_ON_ONCE(!avic_is_addressable_vcpu(vcpu)))
 		return;
 
 	/*
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0c1ebb16cec6..d24dbe633b11 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2421,7 +2421,7 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 		void *dst_vaddr = kmap_local_pfn(pfn);
 
 		memcpy(src_vaddr, dst_vaddr, PAGE_SIZE);
-		set_page_dirty(src_page);
+		set_page_dirty_lock(src_page);
 
 		kunmap_local(dst_vaddr);
 		kunmap_local(src_vaddr);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index fe0cba4731b2..c054803d4673 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1328,7 +1328,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 	svm->msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->msrpm) {
 		err = -ENOMEM;
-		goto error_free_sev;
+		goto error_free_avic;
 	}
 
 	svm->x2avic_msrs_intercepted = true;
@@ -1342,6 +1342,8 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 
 	return 0;
 
+error_free_avic:
+	avic_vcpu_free(vcpu);
 error_free_sev:
 	sev_free_vcpu(vcpu);
 error_free_vmcb_page:
@@ -1356,6 +1358,8 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 
 	WARN_ON_ONCE(!list_empty(&svm->ir_list));
 
+	avic_vcpu_free(vcpu);
+
 	svm_leave_nested(vcpu);
 	svm_free_nested(svm);
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 84f19026d3e8..29bde741874a 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -955,6 +955,7 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb);
 int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu);
 int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu);
 int avic_init_vcpu(struct vcpu_svm *svm);
+void avic_vcpu_free(struct kvm_vcpu *vcpu);
 void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void avic_vcpu_put(struct kvm_vcpu *vcpu);
 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b25216862740..5165275128fc 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3770,8 +3770,10 @@ vmentry_fail_vmexit_guest_mode:
 vmentry_fail_vmexit:
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
-	if (!from_vmentry)
+	if (!from_vmentry) {
+		nested_ept_uninit_mmu_context(vcpu);
 		return NVMX_VMENTRY_VMEXIT;
+	}
 
 	nested_put_vmcs12_pages(vcpu);
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 0f5919b092e4..f72897ae56bc 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -250,7 +250,7 @@ static inline bool is_noncanonical_invlpg_address(u64 la, struct kvm_vcpu *vcpu)
 static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
 					gva_t gva, gfn_t gfn, unsigned access)
 {
-	u64 gen = kvm_memslots(vcpu->kvm)->generation;
+	u64 gen = kvm_vcpu_memslots(vcpu)->generation;
 
 	if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
 		return;
@@ -267,7 +267,7 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
 
 static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
+	return vcpu->arch.mmio_gen == kvm_vcpu_memslots(vcpu)->generation;
 }
 
 /*
diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c
index f0ca221524db..394dc2408ed7 100644
--- a/drivers/block/zloop.c
+++ b/drivers/block/zloop.c
@@ -800,6 +800,27 @@ static void zloop_cmd_workfn(struct work_struct *work)
 	current->flags = orig_flags;
 }
 
+static void zloop_fill_zero_rq(struct request *rq, unsigned int zero_from)
+{
+	struct req_iterator iter;
+	struct bio_vec bv;
+	unsigned int pos = 0;
+	unsigned int end, off;
+
+	rq_for_each_segment(bv, rq, iter) {
+		end = pos + bv.bv_len;
+		if (end > zero_from) {
+			if (pos < zero_from)
+				off = zero_from - pos;
+			else
+				off = 0;
+			memzero_page(bv.bv_page, bv.bv_offset + off,
+				     bv.bv_len - off);
+		}
+		pos = end;
+	}
+}
+
 static void zloop_complete_rq(struct request *rq)
 {
 	struct zloop_cmd *cmd = blk_mq_rq_to_pdu(rq);
@@ -814,13 +835,9 @@ static void zloop_complete_rq(struct request *rq)
 			pr_err("Zone %u: failed read sector %llu, %llu sectors\n",
 			       zone_no, cmd->sector, cmd->nr_sectors);
 
-		if (cmd->ret >= 0 && cmd->ret != blk_rq_bytes(rq)) {
-			/* short read */
-			struct bio *bio;
-
-			__rq_for_each_bio(bio, rq)
-				zero_fill_bio(bio);
-		}
+		/* Short read. Zero out the unread tail beyond cmd->ret. */
+		if (cmd->ret >= 0 && cmd->ret != blk_rq_bytes(rq))
+			zloop_fill_zero_rq(rq, cmd->ret);
 		break;
 	case REQ_OP_WRITE:
 	case REQ_OP_ZONE_APPEND:
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 475235c402e8..0c0d11c72925 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2796,13 +2796,13 @@ static inline void decode_bus_error(int node_id, struct mce *m)
  * the instance_id. For example, instance_id=0xYXXXXX where Y is the channel
  * number.
  *
- * For DRAM ECC errors, the Chip Select number is given in bits [2:0] of
+ * For DRAM ECC errors, the Chip Select number is given in bits [1:0] of
  * the MCA_SYND[ErrorInformation] field.
  */
 static void umc_get_err_info(struct mce *m, struct err_info *err)
 {
 	err->channel = (m->ipid & GENMASK(31, 0)) >> 20;
-	err->csrow = m->synd & 0x7;
+	err->csrow = m->synd & 0x3;
 }
 
 static void decode_umc_error(int node_id, struct mce *m)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 054870e9078d..ca5860e493a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -598,14 +598,18 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd,
 		/* first get metadata_size by buffer = NULL */
 		r = amdgpu_bo_get_metadata(bo, NULL, 0,
 					   metadata_size, NULL);
+		if (r)
+			goto out_put;
 
 		/* user buf_size is bigger than bo metadata_size
 		 * allocate a buf at kernel space and copy */
 		if (*metadata_size <= buffer_size) {
 			*metadata_buffer = kzalloc(*metadata_size, GFP_KERNEL);
 
-			if (!*metadata_buffer)
-				return -ENOMEM;
+			if (!*metadata_buffer) {
+				r = -ENOMEM;
+				goto out_put;
+			}
 
 			r = amdgpu_bo_get_metadata(bo, *metadata_buffer, *metadata_size,
 						   NULL, &metadata_flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index aca1a8045afa..ab7ccfaea22a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -121,6 +121,20 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 
 	*pos &= (1UL << 22) - 1;
 
+	if (size > PAGE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Access the user buffer only while none of the locks below are held:
+	 * a fault takes mmap_lock, and grbm_idx_mutex and srbm_mutex nest
+	 * inside it.
+	 */
+	u32 *data __free(kfree) = kmalloc(size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	if (!read && copy_from_user(data, buf, size))
+		return -EFAULT;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -152,28 +166,16 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 		mutex_lock(&adev->pm.mutex);
 
 	while (size) {
-		uint32_t value;
-
-		if (read) {
-			value = RREG32(*pos >> 2);
-			r = put_user(value, (uint32_t *)buf);
-		} else {
-			r = get_user(value, (uint32_t *)buf);
-			if (!r)
-				amdgpu_mm_wreg_mmio_rlc(adev, *pos >> 2, value, 0);
-		}
-		if (r) {
-			result = r;
-			goto end;
-		}
+		if (read)
+			data[result >> 2] = RREG32(*pos >> 2);
+		else
+			amdgpu_mm_wreg_mmio_rlc(adev, *pos >> 2, data[result >> 2], 0);
 
 		result += 4;
-		buf += 4;
 		*pos += 4;
 		size -= 4;
 	}
 
-end:
 	if (use_bank) {
 		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, 0);
 		mutex_unlock(&adev->grbm_idx_mutex);
@@ -188,6 +190,10 @@ end:
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
+
+	if (read && copy_to_user(buf, data, result))
+		return -EFAULT;
+
 	return result;
 }
 
@@ -238,11 +244,24 @@ static ssize_t amdgpu_debugfs_regs2_op(struct file *f, char __user *buf, u32 off
 	struct amdgpu_device *adev = rd->adev;
 	ssize_t result = 0;
 	int r;
-	uint32_t value;
 
 	if (size & 0x3 || offset & 0x3)
 		return -EINVAL;
 
+	if (size > PAGE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Access the user buffer only while none of the locks below are held:
+	 * a fault takes mmap_lock, and grbm_idx_mutex and srbm_mutex nest
+	 * inside it.
+	 */
+	u32 *data __free(kfree) = kmalloc(size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	if (write_en && copy_from_user(data, buf, size))
+		return -EFAULT;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -281,24 +300,16 @@ static ssize_t amdgpu_debugfs_regs2_op(struct file *f, char __user *buf, u32 off
 		mutex_lock(&adev->pm.mutex);
 
 	while (size) {
-		if (!write_en) {
-			value = RREG32(offset >> 2);
-			r = put_user(value, (uint32_t *)buf);
-		} else {
-			r = get_user(value, (uint32_t *)buf);
-			if (!r)
-				amdgpu_mm_wreg_mmio_rlc(adev, offset >> 2, value, rd->id.xcc_id);
-		}
-		if (r) {
-			result = r;
-			goto end;
-		}
+		if (!write_en)
+			data[result >> 2] = RREG32(offset >> 2);
+		else
+			amdgpu_mm_wreg_mmio_rlc(adev, offset >> 2, data[result >> 2],
+						rd->id.xcc_id);
 		offset += 4;
 		size -= 4;
 		result += 4;
-		buf += 4;
 	}
-end:
+
 	if (rd->id.use_grbm) {
 		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, rd->id.xcc_id);
 		mutex_unlock(&adev->grbm_idx_mutex);
@@ -317,6 +328,10 @@ end:
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 
 	amdgpu_virt_disable_access_debugfs(adev);
+
+	if (!write_en && copy_to_user(buf, data, result))
+		return -EFAULT;
+
 	return result;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 3dc8faa091d7..61dc2a6be7e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -1080,20 +1080,17 @@ void amdgpu_gmc_init_vga_resv_regions(struct amdgpu_device *adev)
 	case CHIP_RENOIR:
 		adev->mman.keep_stolen_vga_memory = true;
 		break;
-	case CHIP_POLARIS10:
-	case CHIP_POLARIS11:
-	case CHIP_POLARIS12:
-		/* MacBookPros with switchable graphics put VRAM at 0 when
-		 * the iGPU is enabled which results in cursor issues if
-		 * the cursor ends up at 0.  Reserve vram at 0 in that case.
-		 */
-		if (adev->gmc.vram_start == 0)
-			adev->mman.keep_stolen_vga_memory = true;
-		break;
 	default:
 		adev->mman.keep_stolen_vga_memory = false;
 		break;
 	}
+	/* MacBookPros with switchable graphics put VRAM at 0 when
+	 * the iGPU is enabled which results in cursor issues if
+	 * the cursor ends up at 0.  Reserve vram at 0 in that case.
+	 */
+	if ((adev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) &&
+	    (adev->gmc.vram_start == 0))
+		adev->mman.keep_stolen_vga_memory = true;
 
 	if (amdgpu_sriov_vf(adev) ||
 	    !amdgpu_device_has_display_hardware(adev)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 242c48e85912..7c081b338fe2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -30,6 +30,7 @@
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_vblank.h>
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
 #include "atom.h"
@@ -1660,6 +1661,9 @@ u32 amdgpu_get_vblank_counter_kms(struct drm_crtc *crtc)
 		DRM_ERROR("Invalid crtc %u\n", pipe);
 		return -EINVAL;
 	}
+	if (!down_read_trylock(&adev->reset_domain->sem))
+		return drm_crtc_vblank_count(crtc);
+
 
 	/* The hw increments its frame counter at start of vsync, not at start
 	 * of vblank, as is required by DRM core vblank counter handling.
@@ -1705,6 +1709,7 @@ u32 amdgpu_get_vblank_counter_kms(struct drm_crtc *crtc)
 		DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
 	}
 
+	up_read(&adev->reset_domain->sem);
 	return count;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index cc8e7af18834..9316423f9340 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -472,6 +472,7 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 	u64 doorbell_index;
 	struct drm_gem_object *gobj;
 	struct amdgpu_userq_obj *db_obj = db_info->db_obj;
+	struct amdgpu_bo *abo;
 	int r, db_size;
 
 	gobj = drm_gem_object_lookup(filp, db_info->doorbell_handle);
@@ -480,7 +481,17 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 		return -EINVAL;
 	}
 
-	db_obj->obj = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
+	/*
+	 * Pinning a regular BO into the doorbell domain would discard its
+	 * contents, possibly those of a buffer shared by another client.
+	 */
+	abo = gem_to_amdgpu_bo(gobj);
+	if (!(abo->preferred_domains & AMDGPU_GEM_DOMAIN_DOORBELL)) {
+		drm_gem_object_put(gobj);
+		return -EINVAL;
+	}
+
+	db_obj->obj = amdgpu_bo_ref(abo);
 	drm_gem_object_put(gobj);
 
 	r = amdgpu_bo_reserve(db_obj->obj, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
index 14a5abe42d1f..8d5dcaf4fea6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
@@ -361,8 +361,7 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 
 		compute_mqd = memdup_user(u64_to_user_ptr(mqd_user->mqd), mqd_user->mqd_size);
 		if (IS_ERR(compute_mqd)) {
-			DRM_ERROR("Failed to read user MQD\n");
-			r = -ENOMEM;
+			r = PTR_ERR(compute_mqd);
 			goto free_mqd;
 		}
 
@@ -406,8 +405,7 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 
 		mqd_gfx_v11 = memdup_user(u64_to_user_ptr(mqd_user->mqd), mqd_user->mqd_size);
 		if (IS_ERR(mqd_gfx_v11)) {
-			DRM_ERROR("Failed to read user MQD\n");
-			r = -ENOMEM;
+			r = PTR_ERR(mqd_gfx_v11);
 			goto free_mqd;
 		}
 
@@ -451,8 +449,7 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 
 		mqd_sdma_v11 = memdup_user(u64_to_user_ptr(mqd_user->mqd), mqd_user->mqd_size);
 		if (IS_ERR(mqd_sdma_v11)) {
-			DRM_ERROR("Failed to read sdma user MQD\n");
-			r = -ENOMEM;
+			r = PTR_ERR(mqd_sdma_v11);
 			goto free_mqd;
 		}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 2f78395a0c31..4594824985e1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -572,12 +572,32 @@ static int allocate_doorbell(struct qcm_process_device *qpd,
 		 * we need the physical sdma engine id in order to get the
 		 * correct doorbell offset.
 		 */
-		uint32_t valid_id = idx_offset[qpd->dqm->dev->node_id *
-					       get_num_all_sdma_engines(qpd->dqm) +
-					       q->properties.sdma_engine_id]
-						+ (q->properties.sdma_queue_id & 1)
-						* KFD_QUEUE_DOORBELL_MIRROR_OFFSET
-						+ (q->properties.sdma_queue_id >> 1);
+		u32 engine_base = idx_offset[dev->node_id *
+					     get_num_all_sdma_engines(qpd->dqm) +
+					     q->properties.sdma_engine_id];
+		u32 valid_id;
+
+		/*
+		 * With the aqua_vanjaram doorbell layout, a shader doorbell
+		 * write whose 32-byte block starts in the previous engine's
+		 * range rings that engine instead. Engine ranges are 10
+		 * indices apart (sdma_doorbell_range = 20 dwords, halved for
+		 * 8-byte doorbells, in aqua_vanjaram_doorbell_index_init()),
+		 * which puts odd engines 2 indices into a shared block.
+		 * Aligning costs at most 2 indices, and 8 queues per engine use
+		 * only 4 of the 10, so the aligned base stays in range. The
+		 * 512-index mirror offset keeps the alignment.
+		 */
+		if (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 3) ||
+		    KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 4) ||
+		    KFD_GC_VERSION(dev) == IP_VERSION(9, 5, 0))
+			engine_base = ALIGN(engine_base,
+					    KFD_SDMA_SHADER_DOORBELL_GRANULARITY);
+
+		valid_id = engine_base +
+			   (q->properties.sdma_queue_id & 1) *
+			   KFD_QUEUE_DOORBELL_MIRROR_OFFSET +
+			   (q->properties.sdma_queue_id >> 1);
 
 		if (restore_id && *restore_id != valid_id)
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d8631847f0eb..435bf2692968 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -133,6 +133,13 @@
  */
 #define KFD_QUEUE_DOORBELL_MIRROR_OFFSET 512
 
+/*
+ * On GC 9.4.3, 9.4.4 and 9.5.0, doorbell writes issued from shaders are
+ * routed to an SDMA engine at 32-byte granularity, i.e. 4 indices with the
+ * 8-byte SDMA doorbells used on SOC15.
+ */
+#define KFD_SDMA_SHADER_DOORBELL_GRANULARITY 4
+
 /**
  * enum kfd_ioctl_flags - KFD ioctl flags
  * Various flags that can be set in &amdkfd_ioctl_desc.flags to control how
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1b42c4606002..47a0ff2ed035 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3708,6 +3708,13 @@ static void amdgpu_dm_enable_self_refresh(struct amdgpu_display_manager *dm,
 	struct amdgpu_dm_connector *aconn =
 		(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
 
+	if (!acrtc_state->base.async_flip) {
+		amdgpu_dm_psr_set_event(dm, acrtc_state->stream, false,
+			psr_event_immediate_flip, false);
+		amdgpu_dm_replay_set_event(dm, acrtc_state->stream, false,
+			replay_event_immediate_flip, false);
+	}
+
 	/* Decrement skip count when SR is enabled and we're doing fast updates. */
 	if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
 	    (psr->psr_feature_enabled || pr->replay_feature_enabled)) {
@@ -4118,6 +4125,18 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_commit *state,
 			spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
 		}
 		mutex_lock(&dm->dc_lock);
+		/*
+		 * Tearing (immediate) flips cannot work with panel self-refresh
+		 * features. The event is cleared by
+		 * amdgpu_dm_enable_self_refresh() once async flips stop.
+		 */
+		if (immediate_flip) {
+			dc_exit_ips_for_hw_access(dm->dc);
+			amdgpu_dm_psr_set_event(dm, acrtc_state->stream, true,
+				psr_event_immediate_flip, true);
+			amdgpu_dm_replay_set_event(dm, acrtc_state->stream, true,
+				replay_event_immediate_flip, true);
+		}
 		update_planes_and_stream_adapter(dm->dc,
 					 acrtc_state->update_type,
 					 planes_count,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c
index d386bb1475bb..45a69bf43971 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_connector.c
@@ -1012,10 +1012,15 @@ decide_crtc_timing_for_drm_display_mode(struct drm_display_mode *drm_mode,
 					const struct drm_display_mode *native_mode,
 					bool scale_enabled)
 {
+	/* Inserted modes copy the native sync; a sink mode with equal totals may not */
 	if (scale_enabled || (
 	    native_mode->clock == drm_mode->clock &&
 	    native_mode->htotal == drm_mode->htotal &&
-	    native_mode->vtotal == drm_mode->vtotal)) {
+	    native_mode->vtotal == drm_mode->vtotal &&
+	    native_mode->hsync_start == drm_mode->hsync_start &&
+	    native_mode->hsync_end == drm_mode->hsync_end &&
+	    native_mode->vsync_start == drm_mode->vsync_start &&
+	    native_mode->vsync_end == drm_mode->vsync_end)) {
 		if (native_mode->crtc_clock)
 			copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
 	} else {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index e13b96358208..a2b8f7033616 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -112,25 +112,7 @@ void amdgpu_dm_plane_fill_blending_from_plane_state(const struct drm_plane_state
 
 	if (plane_state->pixel_blend_mode == DRM_MODE_BLEND_PREMULTI ||
 		plane_state->pixel_blend_mode == DRM_MODE_BLEND_COVERAGE) {
-		static const uint32_t alpha_formats[] = {
-			DRM_FORMAT_ARGB8888,
-			DRM_FORMAT_RGBA8888,
-			DRM_FORMAT_ABGR8888,
-			DRM_FORMAT_ARGB2101010,
-			DRM_FORMAT_ABGR2101010,
-			DRM_FORMAT_ARGB16161616,
-			DRM_FORMAT_ABGR16161616,
-			DRM_FORMAT_ARGB16161616F,
-		};
-		uint32_t format = plane_state->fb->format->format;
-		unsigned int i;
-
-		for (i = 0; i < ARRAY_SIZE(alpha_formats); ++i) {
-			if (format == alpha_formats[i]) {
-				*per_pixel_alpha = true;
-				break;
-			}
-		}
+		*per_pixel_alpha = plane_state->fb->format->has_alpha;
 
 		if (*per_pixel_alpha && plane_state->pixel_blend_mode == DRM_MODE_BLEND_COVERAGE)
 			*pre_multiplied_alpha = false;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c
index 59ce682f491b..b61771749ca0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/tests/amdgpu_dm_connector_test.c
@@ -1572,6 +1572,46 @@ static void dm_test_decide_crtc_timing_no_crtc_clock(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, drm_mode.crtc_hdisplay, 0);
 }
 
+static void dm_test_decide_crtc_timing_sink_mode_same_totals(struct kunit *test)
+{
+	struct drm_display_mode native_mode = {
+		DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4016, 4104,
+			 4400, 0, 2160, 2168, 2178, 2250, 0,
+			 DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) };
+	struct drm_display_mode drm_mode = {
+		DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 594000, 4096, 4184, 4272,
+			 4400, 0, 2160, 2168, 2178, 2250, 0,
+			 DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) };
+
+	drm_mode_set_crtcinfo(&native_mode, 0);
+	drm_mode_set_crtcinfo(&drm_mode, 0);
+
+	decide_crtc_timing_for_drm_display_mode(&drm_mode, &native_mode, false);
+
+	KUNIT_EXPECT_EQ(test, drm_mode.crtc_hdisplay, 4096);
+	KUNIT_EXPECT_EQ(test, drm_mode.crtc_hsync_start, 4184);
+}
+
+static void dm_test_decide_crtc_timing_inserted_mode(struct kunit *test)
+{
+	struct drm_display_mode native_mode = {
+		DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4016, 4104,
+			 4400, 0, 2160, 2168, 2178, 2250, 0,
+			 DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) };
+	struct drm_display_mode drm_mode;
+
+	drm_mode_set_crtcinfo(&native_mode, 0);
+	drm_mode = native_mode;
+	drm_mode.hdisplay = 1920;
+	drm_mode.vdisplay = 1080;
+	drm_mode_set_crtcinfo(&drm_mode, 0);
+
+	decide_crtc_timing_for_drm_display_mode(&drm_mode, &native_mode, false);
+
+	KUNIT_EXPECT_EQ(test, drm_mode.crtc_hdisplay, 3840);
+	KUNIT_EXPECT_EQ(test, drm_mode.crtc_vdisplay, 2160);
+}
+
 /* Tests for amdgpu_dm_connector_funcs_reset() */
 
 static const struct drm_connector_funcs dm_test_connector_funcs = {
@@ -5635,6 +5675,8 @@ static struct kunit_case amdgpu_dm_connector_tests[] = {
 	KUNIT_CASE(dm_test_decide_crtc_timing_matching_mode),
 	KUNIT_CASE(dm_test_decide_crtc_timing_no_copy),
 	KUNIT_CASE(dm_test_decide_crtc_timing_no_crtc_clock),
+	KUNIT_CASE(dm_test_decide_crtc_timing_sink_mode_same_totals),
+	KUNIT_CASE(dm_test_decide_crtc_timing_inserted_mode),
 	/* amdgpu_dm_connector_funcs_reset */
 	KUNIT_CASE(dm_test_funcs_reset_sets_defaults),
 	KUNIT_CASE(dm_test_funcs_reset_edp_abm_level),
diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
index d4577663a1f0..aa36b79d0f6c 100644
--- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
+++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
@@ -189,13 +189,12 @@ static int aspeed_gfx_load(struct drm_device *drm)
 	}
 	reset_control_deassert(priv->rst);
 
-	priv->clk = devm_clk_get(drm->dev, NULL);
+	priv->clk = devm_clk_get_enabled(drm->dev, NULL);
 	if (IS_ERR(priv->clk)) {
 		dev_err(&pdev->dev,
-			"missing or invalid clk device tree entry");
+			"failed to get and enable clock\n");
 		return PTR_ERR(priv->clk);
 	}
-	clk_prepare_enable(priv->clk);
 
 	/* Sanitize control registers */
 	writel(0, priv->base + CRT_CTRL1);
diff --git a/drivers/gpu/drm/bridge/th1520-dw-hdmi.c b/drivers/gpu/drm/bridge/th1520-dw-hdmi.c
index cbea8b14cd4b..2fa7f2d46b3d 100644
--- a/drivers/gpu/drm/bridge/th1520-dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/th1520-dw-hdmi.c
@@ -135,8 +135,8 @@ static int th1520_dw_hdmi_probe(struct platform_device *pdev)
 	plat_data->priv_data = hdmi;
 
 	hdmi->dw_hdmi = dw_hdmi_probe(pdev, plat_data);
-	if (IS_ERR(hdmi))
-		return PTR_ERR(hdmi);
+	if (IS_ERR(hdmi->dw_hdmi))
+		return PTR_ERR(hdmi->dw_hdmi);
 
 	platform_set_drvdata(pdev, hdmi);
 
@@ -145,9 +145,9 @@ static int th1520_dw_hdmi_probe(struct platform_device *pdev)
 
 static void th1520_dw_hdmi_remove(struct platform_device *pdev)
 {
-	struct dw_hdmi *hdmi = platform_get_drvdata(pdev);
+	struct th1520_hdmi *hdmi = platform_get_drvdata(pdev);
 
-	dw_hdmi_remove(hdmi);
+	dw_hdmi_remove(hdmi->dw_hdmi);
 }
 
 static const struct of_device_id th1520_dw_hdmi_of_table[] = {
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index e623ccb4c1d8..488fd123a01a 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -4634,7 +4634,9 @@ static int dp_aux_backlight_update_status(struct backlight_device *bd)
 
 	if (!backlight_is_blank(bd)) {
 		if (!bl->enabled) {
-			drm_edp_backlight_enable(bl->aux, &bl->info, brightness);
+			ret = drm_edp_backlight_enable(bl->aux, &bl->info, brightness);
+			if (ret)
+				return ret;
 			bl->enabled = true;
 			return 0;
 		}
diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
index 83f1809a5d37..a52d5f5b9f05 100644
--- a/drivers/gpu/drm/drm_bridge.c
+++ b/drivers/gpu/drm/drm_bridge.c
@@ -454,8 +454,10 @@ void drm_bridge_add(struct drm_bridge *bridge)
 	 * in bridge_lingering_list. Remove it or bridge_lingering_list will be
 	 * corrupted when adding this bridge to bridge_list below.
 	 */
+	mutex_lock(&bridge_lock);
 	if (!list_empty(&bridge->list))
 		list_del_init(&bridge->list);
+	mutex_unlock(&bridge_lock);
 
 	mutex_init(&bridge->hpd_state_mutex);
 	mutex_init(&bridge->hpd_mutex);
@@ -593,8 +595,10 @@ int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge,
 	if (!bridge->container)
 		DRM_WARN("DRM bridge corrupted or not allocated by devm_drm_bridge_alloc()\n");
 
-	if (list_empty(&bridge->list))
-		DRM_WARN("Missing drm_bridge_add() before attach\n");
+	scoped_guard(mutex, &bridge_lock) {
+		if (list_empty(&bridge->list))
+			DRM_WARN("Missing drm_bridge_add() before attach\n");
+	}
 
 	drm_bridge_get(bridge);
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index d4664ed468b2..0817b639b3fa 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1724,10 +1724,10 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper)
 
 	ret = drm_fb_helper_single_fb_probe(fb_helper);
 	if (ret < 0) {
-		if (ret == -EAGAIN) {
-			fb_helper->deferred_setup = true;
+		/* modesets are probed but fb_helper->fb isn't; defer restore too */
+		fb_helper->deferred_setup = true;
+		if (ret == -EAGAIN)
 			ret = 0;
-		}
 		mutex_unlock(&fb_helper->lock);
 
 		goto err_drm_fb_helper_release_info;
diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c
index aa7792966287..5aa5ac2f3727 100644
--- a/drivers/gpu/drm/gud/gud_pipe.c
+++ b/drivers/gpu/drm/gud/gud_pipe.c
@@ -507,6 +507,7 @@ int gud_plane_atomic_check(struct drm_plane *plane,
 	for_each_new_connector_in_state(state, connector, connector_state, i) {
 		if (connector_state->crtc)
 			break;
+		connector_state = NULL;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 1f303d4eaa4d..d5aadced7da0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1766,6 +1766,7 @@ static int eb_reinit_userptr(struct i915_execbuffer *eb)
 
 static noinline int eb_relocate_parse_slow(struct i915_execbuffer *eb)
 {
+	const unsigned int count = eb->buffer_count;
 	bool have_copy = false;
 	struct eb_vma *ev;
 	int err = 0;
@@ -1868,7 +1869,6 @@ err:
 
 out:
 	if (have_copy) {
-		const unsigned int count = eb->buffer_count;
 		unsigned int i;
 
 		for (i = 0; i < count; i++) {
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index a33b19c04737..0f9b4f1dd3cb 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -1904,7 +1904,8 @@ static void rps_work(struct work_struct *work)
 
 out:
 	spin_lock_irq(gt->irq_lock);
-	gen6_gt_pm_unmask_irq(gt, rps->pm_events);
+	if (intel_rps_is_active(rps))
+		gen6_gt_pm_unmask_irq(gt, rps->pm_events);
 	spin_unlock_irq(gt->irq_lock);
 }
 
diff --git a/drivers/gpu/drm/imagination/pvr_mmu.c b/drivers/gpu/drm/imagination/pvr_mmu.c
index 62eae7fcd5a2..67e73d7d5d0e 100644
--- a/drivers/gpu/drm/imagination/pvr_mmu.c
+++ b/drivers/gpu/drm/imagination/pvr_mmu.c
@@ -2337,7 +2337,7 @@ void pvr_mmu_op_context_destroy(struct pvr_mmu_op_context *op_ctx)
  * @ctx: MMU context associated with owning VM context.
  * @sgt: Scatter gather table containing pages pinned for use by this context.
  * @device_addr: Virtual device address at the start of the requested mapping.
- * @sgt_offset: Start offset of the requested device-virtual memory mapping.
+ * @sgt_offset: Offset into @sgt of the start of the requested mapping.
  * @size: Size in bytes of the requested device-virtual memory mapping. For an
  * unmapping, this should be zero so that no page tables are allocated.
  *
@@ -2350,7 +2350,6 @@ struct pvr_mmu_op_context *
 pvr_mmu_op_context_create(struct pvr_mmu_context *ctx, struct sg_table *sgt,
 			  u64 device_addr, u64 sgt_offset, u64 size)
 {
-	u64 start_addr = device_addr + sgt_offset;
 	int err;
 
 	struct pvr_mmu_op_context *op_ctx = kzalloc_obj(*op_ctx);
@@ -2365,18 +2364,18 @@ pvr_mmu_op_context_create(struct pvr_mmu_context *ctx, struct sg_table *sgt,
 
 	if (size) {
 		/*
-		 * The number of page table objects we need to prealloc is
-		 * indicated by the mapping size, start address and the sizes
-		 * of the areas mapped per PT or PD. The range calculation is
-		 * identical to that for the index into a table for a device
-		 * address, so we reuse those functions here.
+		 * The page tables needed are set by the device-virtual range
+		 * being mapped: one level 1 table per 1GiB region and one
+		 * level 0 table per 2MiB region the range touches. Tables that
+		 * already exist are not consumed, so this is an upper bound.
 		 */
-		const u32 l1_start_idx = pvr_page_table_l2_idx(start_addr);
-		const u32 l1_end_idx = pvr_page_table_l2_idx(start_addr + size);
-		const u32 l1_count = l1_end_idx - l1_start_idx + 1;
-		const u32 l0_start_idx = pvr_page_table_l1_idx(start_addr);
-		const u32 l0_end_idx = pvr_page_table_l1_idx(start_addr + size);
-		const u32 l0_count = l0_end_idx - l0_start_idx + 1;
+		const u64 last_addr = device_addr + size - 1;
+		const u64 l1_count =
+			(last_addr >> ROGUE_MMUCTRL_VADDR_PC_INDEX_SHIFT) -
+			(device_addr >> ROGUE_MMUCTRL_VADDR_PC_INDEX_SHIFT) + 1;
+		const u64 l0_count =
+			(last_addr >> ROGUE_MMUCTRL_VADDR_PD_INDEX_SHIFT) -
+			(device_addr >> ROGUE_MMUCTRL_VADDR_PD_INDEX_SHIFT) + 1;
 
 		/*
 		 * Alloc and push page table entries until we have enough of
diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
index 55cc999f3708..cbdd15ed74fd 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.c
+++ b/drivers/gpu/drm/imagination/pvr_vm.c
@@ -418,6 +418,8 @@ pvr_vm_gpuva_unmap(struct drm_gpuva_op *op, void *op_ctx)
 static int
 pvr_vm_gpuva_remap(struct drm_gpuva_op *op, void *op_ctx)
 {
+	/* The split parts belong to the object of the mapping being split. */
+	struct drm_gpuvm_bo *vm_bo = op->remap.unmap->va->vm_bo;
 	struct pvr_vm_bind_op *ctx = op_ctx;
 	u64 va_start = 0, va_range = 0;
 	int err;
@@ -433,14 +435,12 @@ pvr_vm_gpuva_remap(struct drm_gpuva_op *op, void *op_ctx)
 	drm_gpuva_remap(&ctx->prev_va->base, &ctx->next_va->base, &op->remap);
 
 	if (op->remap.prev) {
-		pvr_gem_object_get(gem_to_pvr_gem(ctx->prev_va->base.gem.obj));
-		drm_gpuva_link(&ctx->prev_va->base, ctx->gpuvm_bo);
+		drm_gpuva_link(&ctx->prev_va->base, vm_bo);
 		ctx->prev_va = NULL;
 	}
 
 	if (op->remap.next) {
-		pvr_gem_object_get(gem_to_pvr_gem(ctx->next_va->base.gem.obj));
-		drm_gpuva_link(&ctx->next_va->base, ctx->gpuvm_bo);
+		drm_gpuva_link(&ctx->next_va->base, vm_bo);
 		ctx->next_va = NULL;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index 4542d5f4ded8..b776030460f7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -488,7 +488,7 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 			goto done;
 		break;
 	case NV_DEVICE_INFO_V0_TURING:
-		if (engine != NV_DEVICE_HOST_RUNLIST_ENGINES_NVDEC) {
+		if (engine == NV_DEVICE_HOST_RUNLIST_ENGINES_GR) {
 			ret = nvif_object_ctor(&chan->chan->user, "abi16CeWar",
 					       0, TURING_DMA_COPY_A, NULL, 0,
 					       &chan->ce);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
index f78e6b9b4292..b841d66f8bb3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
@@ -201,7 +201,7 @@ nvkm_udevice_gcx_ready(struct nvkm_udevice *udev, void *data, u32 size)
 	} *args = data;
 	int ret = -ENOSYS;
 
-	if (!gsp) {
+	if (!gsp || !gsp->rm) {
 		args->v0.ready = NV_DEVICE_GC6_READY | NV_DEVICE_GCOFF_READY;
 		return 0;
 	}
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index 5778e23e20a0..653c6755896c 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -3674,6 +3674,9 @@ int panthor_group_create(struct panthor_file *pfile,
 	    hweight64(group_args->tiler_core_mask) < group_args->max_tiler_cores)
 		return -EINVAL;
 
+	if (group_args->queues.count > sched->cs_slot_count)
+		return -EINVAL;
+
 	group = kzalloc_obj(*group);
 	if (!group)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 49ea2ed0996b..7b8b3364000f 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -204,7 +204,7 @@ static struct list_head *vc4_get_cache_list_for_size(struct drm_device *dev,
 		struct list_head *new_list;
 		uint32_t i;
 
-		new_list = kmalloc_objs(struct list_head, new_size);
+		new_list = kvmalloc_objs(struct list_head, new_size);
 		if (!new_list)
 			return NULL;
 
@@ -224,7 +224,7 @@ static struct list_head *vc4_get_cache_list_for_size(struct drm_device *dev,
 		for (i = vc4->bo_cache.size_list_size; i < new_size; i++)
 			INIT_LIST_HEAD(&new_list[i]);
 
-		kfree(vc4->bo_cache.size_list);
+		kvfree(vc4->bo_cache.size_list);
 		vc4->bo_cache.size_list = new_list;
 		vc4->bo_cache.size_list_size = new_size;
 	}
@@ -1052,6 +1052,7 @@ static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused)
 	cancel_work_sync(&vc4->bo_cache.time_work);
 
 	vc4_bo_cache_purge(dev);
+	kvfree(vc4->bo_cache.size_list);
 
 	for (i = 0; i < vc4->num_labels; i++) {
 		if (vc4->bo_labels[i].num_allocated) {
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 616caf9d9915..7b64e1ed02d4 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -360,8 +360,11 @@ static int vc4_drm_bind(struct device *dev)
 	}
 
 	ret = aperture_remove_all_conflicting_devices(driver->name);
-	if (ret)
+	if (ret) {
+		if (firmware)
+			rpi_firmware_put(firmware);
 		goto err;
+	}
 
 	if (firmware) {
 		ret = rpi_firmware_property(firmware,
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 0f5958c1e6b6..b0e82c2dc1ba 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -1051,7 +1051,7 @@ void vc4_plane_async_set_fb(struct drm_plane *plane,
 /* vc4_v3d.c */
 extern struct platform_driver vc4_v3d_driver;
 extern const struct of_device_id vc4_v3d_dt_match[];
-int vc4_v3d_get_bin_slot(struct vc4_dev *vc4);
+int vc4_v3d_get_bin_slot(struct vc4_dev *vc4, long timeout);
 int vc4_v3d_bin_bo_get(struct vc4_dev *vc4, bool *used);
 void vc4_v3d_bin_bo_put(struct vc4_dev *vc4);
 int vc4_v3d_pm_get(struct vc4_dev *vc4);
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index e231c906709c..6ee4bd77d433 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -877,11 +877,17 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 		drm_gem_object_put(&bo->base.base);
 	}
 
-	/* Free up the allocation of any bin slots we used. */
+	/* Free up the allocation of any bin slots we used. Jobs that ran to
+	 * completion had their slots released in vc4_irq_finish_render_job().
+	 * Only jobs that never completed still have slots to be released here.
+	 */
 	spin_lock_irqsave(&vc4->job_lock, irqflags);
 	vc4->bin_alloc_used &= ~exec->bin_slots;
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 
+	/* Let anyone waiting on the binner pool retry. */
+	wake_up_all(&vc4->job_wait_queue);
+
 	/* Release the reference on the binner BO if needed. */
 	if (exec->bin_bo_used)
 		vc4_v3d_bin_bo_put(vc4);
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index 7877d493d80e..dc10d3a4d90f 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -74,7 +74,7 @@ vc4_overflow_mem_work(struct work_struct *work)
 
 	bo = vc4->bin_bo;
 
-	bin_bo_slot = vc4_v3d_get_bin_slot(vc4);
+	bin_bo_slot = vc4_v3d_get_bin_slot(vc4, msecs_to_jiffies(500));
 	if (bin_bo_slot < 0) {
 		drm_err(&vc4->base, "Couldn't allocate binner overflow mem\n");
 		goto complete;
@@ -165,6 +165,10 @@ vc4_irq_finish_render_job(struct drm_device *dev)
 	trace_vc4_rcl_end_irq(dev, exec->seqno);
 
 	vc4->finished_seqno++;
+
+	vc4->bin_alloc_used &= ~exec->bin_slots;
+	exec->bin_slots = 0;
+
 	list_move_tail(&exec->head, &vc4->job_done_list);
 
 	nextbin = vc4_first_bin_job(vc4);
@@ -276,7 +280,7 @@ vc4_irq_disable(struct drm_device *dev)
 	V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS);
 
 	/* Finish any interrupt handler still in flight. */
-	synchronize_irq(vc4->irq);
+	disable_irq(vc4->irq);
 
 	cancel_work_sync(&vc4->overflow_mem_work);
 }
@@ -284,7 +288,6 @@ vc4_irq_disable(struct drm_device *dev)
 int vc4_irq_install(struct drm_device *dev, int irq)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	int ret;
 
 	if (WARN_ON_ONCE(vc4->gen > VC4_GEN_4))
 		return -ENODEV;
@@ -298,19 +301,8 @@ int vc4_irq_install(struct drm_device *dev, int irq)
 	init_waitqueue_head(&vc4->job_wait_queue);
 	INIT_WORK(&vc4->overflow_mem_work, vc4_overflow_mem_work);
 
-	/* Clear any pending interrupts someone might have left around
-	 * for us.
-	 */
-	V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS);
-
-	ret = devm_request_irq(dev->dev, irq, vc4_irq, 0,
-			       dev_name(dev->dev), dev);
-	if (ret)
-		return ret;
-
-	vc4_irq_enable(dev);
-
-	return 0;
+	return devm_request_irq(dev->dev, irq, vc4_irq, IRQF_NO_AUTOEN,
+				dev_name(dev->dev), dev);
 }
 
 void vc4_irq_uninstall(struct drm_device *dev)
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index f32410420d3e..6844e8f3948c 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -9,6 +9,7 @@
 #include <linux/component.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/timer.h>
 
 #include <drm/drm_print.h>
 
@@ -172,46 +173,42 @@ static void vc4_v3d_init_hw(struct drm_device *dev)
 	V3D_WRITE(V3D_VPMBASE, 0);
 }
 
-int vc4_v3d_get_bin_slot(struct vc4_dev *vc4)
+static int bin_slot_try_alloc(struct vc4_dev *vc4)
 {
-	struct drm_device *dev = &vc4->base;
-	unsigned long irqflags;
 	int slot;
-	uint64_t seqno = 0;
-	struct vc4_exec_info *exec;
 
-	if (WARN_ON_ONCE(vc4->gen > VC4_GEN_4))
-		return -ENODEV;
+	guard(spinlock_irqsave)(&vc4->job_lock);
 
-try_again:
-	spin_lock_irqsave(&vc4->job_lock, irqflags);
 	slot = ffs(~vc4->bin_alloc_used);
 	if (slot != 0) {
 		/* Switch from ffs() bit index to a 0-based index. */
 		slot--;
 		vc4->bin_alloc_used |= BIT(slot);
-		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
-		return slot;
+	} else {
+		slot = -ENOMEM;
 	}
 
-	/* Couldn't find an open slot.  Wait for render to complete
-	 * and try again.
-	 */
-	exec = vc4_last_render_job(vc4);
-	if (exec)
-		seqno = exec->seqno;
-	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
+	return slot;
+}
 
-	if (seqno) {
-		int ret = vc4_wait_for_seqno(dev, seqno, ~0ull, true);
+int vc4_v3d_get_bin_slot(struct vc4_dev *vc4, long timeout)
+{
+	int slot;
+	long ret;
 
-		if (ret == 0)
-			goto try_again;
+	if (WARN_ON_ONCE(vc4->gen > VC4_GEN_4))
+		return -ENODEV;
 
+	/* If the pool is full, wait for a job to release its slots. */
+	ret = wait_event_interruptible_timeout(vc4->job_wait_queue,
+					       (slot = bin_slot_try_alloc(vc4)) >= 0,
+					       timeout);
+	if (ret < 0)
 		return ret;
-	}
+	if (ret == 0)
+		return -ENOMEM;
 
-	return -ENOMEM;
+	return slot;
 }
 
 /*
@@ -396,6 +393,7 @@ static int vc4_v3d_runtime_resume(struct device *dev)
 	vc4_v3d_init_hw(&vc4->base);
 
 	vc4_irq_enable(&vc4->base);
+	enable_irq(vc4->irq);
 
 	return 0;
 }
@@ -452,6 +450,12 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	vc4->irq = ret;
 
+	ret = vc4_irq_install(drm, vc4->irq);
+	if (ret) {
+		drm_err(drm, "Failed to install IRQ handler\n");
+		return ret;
+	}
+
 	ret = devm_pm_runtime_enable(dev);
 	if (ret)
 		return ret;
@@ -473,12 +477,6 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 	V3D_WRITE(V3D_BPOA, 0);
 	V3D_WRITE(V3D_BPOS, 0);
 
-	ret = vc4_irq_install(drm, vc4->irq);
-	if (ret) {
-		drm_err(drm, "Failed to install IRQ handler\n");
-		goto err_put_runtime_pm;
-	}
-
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, 40); /* a little over 2 frames. */
 	pm_runtime_put_autosuspend(dev);
@@ -497,8 +495,15 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master,
 	struct drm_device *drm = data;
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 
+	/* A straggler vc4_reset() re-enables the interrupt. */
+	timer_shutdown_sync(&vc4->hangcheck.timer);
+	cancel_work_sync(&vc4->hangcheck.reset_work);
+
 	vc4_irq_uninstall(drm);
 
+	/* Flush rather than cancel, so queued completions release their jobs. */
+	flush_work(&vc4->job_done_work);
+
 	/* Disable the binner's overflow memory address, so the next
 	 * driver probe (if any) doesn't try to reuse our old
 	 * allocation.
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index d2a65c968b1f..565227657b43 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -402,7 +402,7 @@ validate_tile_binning_config(VALIDATE_ARGS)
 		return -EINVAL;
 	}
 
-	bin_slot = vc4_v3d_get_bin_slot(vc4);
+	bin_slot = vc4_v3d_get_bin_slot(vc4, MAX_SCHEDULE_TIMEOUT);
 	if (bin_slot < 0) {
 		if (bin_slot != -EINTR && bin_slot != -ERESTARTSYS) {
 			drm_err(dev, "Failed to allocate binner memory: %d\n",
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
index d1e7df500190..5a69606a0593 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
@@ -324,6 +324,7 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 	unsigned long kmap_num;
 	SVGA3dCopyBox *box;
 	u32 box_count;
+	u64 src_extent;
 	void *virtual;
 	bool is_iomem;
 	struct vmw_dma_cmd {
@@ -335,6 +336,8 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 		vmw_surface_get_desc(VMW_CURSOR_SNOOP_FORMAT);
 	const u32 image_pitch = VMW_CURSOR_SNOOP_WIDTH * desc->pitchBytesPerBlock;
 
+	BUILD_BUG_ON(sizeof(*srf->snooper.image) != desc->pitchBytesPerBlock);
+
 	cmd = container_of(header, struct vmw_dma_cmd, header);
 
 	/* No snooper installed, nothing to copy */
@@ -372,8 +375,19 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 		return;
 	}
 
+	if (box->w == 0 || box->h == 0)
+		return;
+
+	src_extent = (u64)(box->h - 1) * cmd->dma.guest.pitch +
+		     (u64)box->w * desc->pitchBytesPerBlock;
+	if (src_extent > bo->base.size) {
+		DRM_ERROR("Cursor snoop source of %llu bytes exceeds the %zu byte buffer\n",
+			  src_extent, bo->base.size);
+		return;
+	}
+
 	kmap_offset = cmd->dma.guest.ptr.offset >> PAGE_SHIFT;
-	kmap_num = (VMW_CURSOR_SNOOP_HEIGHT * image_pitch) >> PAGE_SHIFT;
+	kmap_num = PFN_UP(src_extent);
 
 	ret = ttm_bo_reserve(bo, true, false, NULL);
 	if (unlikely(ret != 0)) {
@@ -387,14 +401,16 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 
 	virtual = ttm_kmap_obj_virtual(&map, &is_iomem);
 
-	if (box->w == VMW_CURSOR_SNOOP_WIDTH && cmd->dma.guest.pitch == image_pitch) {
+	if (box->w == VMW_CURSOR_SNOOP_WIDTH &&
+	    box->h == VMW_CURSOR_SNOOP_HEIGHT &&
+	    cmd->dma.guest.pitch == image_pitch) {
 		memcpy(srf->snooper.image, virtual,
 		       VMW_CURSOR_SNOOP_HEIGHT * image_pitch);
 	} else {
-		/* Image is unsigned pointer. */
+		/* The destination stride is in pixels. */
 		for (i = 0; i < box->h; i++)
-			memcpy(srf->snooper.image + i * image_pitch,
-			       virtual + i * cmd->dma.guest.pitch,
+			memcpy(srf->snooper.image + i * VMW_CURSOR_SNOOP_WIDTH,
+			       virtual + (size_t)i * cmd->dma.guest.pitch,
 			       box->w * desc->pitchBytesPerBlock);
 	}
 	srf->snooper.id++;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 1b407b61f683..31d3ee0825ca 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -20,10 +20,18 @@
 #include <drm/drm_rect.h>
 #include <drm/drm_sysfs.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_blend.h>
 
 void vmw_du_init(struct vmw_display_unit *du)
 {
 	vmw_vkms_crtc_init(&du->crtc);
+	drm_plane_create_blend_mode_property(&du->primary,
+					     BIT(DRM_MODE_BLEND_PIXEL_NONE) |
+					     BIT(DRM_MODE_BLEND_PREMULTI));
+	// Check that the cursor plane was actually initialized
+	if (du->crtc.cursor == &du->cursor.base)
+		drm_plane_create_blend_mode_property(&du->cursor.base,
+						     BIT(DRM_MODE_BLEND_PREMULTI));
 }
 
 void vmw_du_cleanup(struct vmw_display_unit *du)
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 73469ea5f333..f1dbdc802df8 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -356,7 +356,7 @@ static struct i915_vma *__xe_pin_fb_vma(struct drm_gem_object *obj, bool is_dpt,
 		drm_exec_retry_on_contention(&exec);
 		xe_validation_retry_on_oom(&ctx, &ret);
 		if (!ret)
-			ttm_bo_pin(&bo->ttm);
+			xe_bo_pin_account(bo);
 	}
 	if (ret)
 		goto err;
@@ -373,7 +373,7 @@ static struct i915_vma *__xe_pin_fb_vma(struct drm_gem_object *obj, bool is_dpt,
 
 err_unpin:
 	ttm_bo_reserve(&bo->ttm, false, false, NULL);
-	ttm_bo_unpin(&bo->ttm);
+	xe_bo_unpin_account(bo);
 	ttm_bo_unreserve(&bo->ttm);
 err:
 	kfree(vma);
@@ -393,7 +393,7 @@ static void __xe_unpin_fb_vma(struct i915_vma *vma)
 		xe_ggtt_node_remove(vma->node, false);
 
 	ttm_bo_reserve(&vma->bo->ttm, false, false, NULL);
-	ttm_bo_unpin(&vma->bo->ttm);
+	xe_bo_unpin_account(vma->bo);
 	ttm_bo_unreserve(&vma->bo->ttm);
 	kfree(vma);
 }
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index b4921a627ff3..7b95ce0445a9 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -455,6 +455,100 @@ static void xe_ttm_tt_account_subtract(struct xe_device *xe, struct ttm_tt *tt)
 		xe_shrinker_mod_pages(xe->mem.shrinker, -(long)tt->num_pages, 0);
 }
 
+static bool xe_ttm_bo_is_imported(struct ttm_buffer_object *tbo)
+{
+	dma_resv_assert_held(tbo->base.resv);
+
+	return tbo->ttm &&
+		(tbo->ttm->page_flags & (TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE)) ==
+		TTM_TT_FLAG_EXTERNAL;
+}
+
+/*
+ * Account @bo's pages as pinned for the shrinker. Removes @bo's pages
+ * from the shrinker's shrinkable / purgeable counts on the transition
+ * from unpinned to pinned. Must be called with @bo's dma-resv held,
+ * after &ttm_buffer_object.pin_count has been incremented by
+ * ttm_bo_pin(). Safe to call unconditionally regardless of which pin
+ * path (kernel, external, framebuffer, backup object, ...) is pinning
+ * @bo, since it only acts on the true 0->1 pin_count transition.
+ *
+ * Imported bos (xe_ttm_bo_is_imported()) are excluded: for those,
+ * xe_ttm_tt_populate() never actually populates the tt or calls
+ * xe_ttm_tt_account_add(), but TTM core's ttm_tt_populate() still
+ * unconditionally marks the tt as populated on driver-hook success.
+ * Relying on ttm_tt_is_populated() for these would subtract pages that
+ * were never added, underflowing the shrinker's counts.
+ */
+static void xe_bo_account_pin(struct xe_bo *bo)
+{
+	struct xe_device *xe = xe_bo_device(bo);
+
+	if (bo->ttm.pin_count == 1 && bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm) &&
+	    !xe_ttm_bo_is_imported(&bo->ttm))
+		xe_ttm_tt_account_subtract(xe, bo->ttm.ttm);
+}
+
+/*
+ * Counterpart to xe_bo_account_pin(). Must be called with @bo's dma-resv
+ * held, before &ttm_buffer_object.pin_count is decremented by
+ * ttm_bo_unpin(), so that the check against the true 1->0 transition sees
+ * the pin count that is about to be released. See xe_bo_account_pin() for
+ * why imported bos are excluded.
+ *
+ * On the true last unpin, also removes @bo from whichever pinned-bo list
+ * (external or kernel_bo_present) it may currently be linked on, since a
+ * bo's final unpin can happen through a pin path (e.g. framebuffer,
+ * backup object) that has no notion of, or ownership over, that list.
+ * This is safe and list-agnostic: list_del_init() only needs the node
+ * itself, not knowledge of which list it is threaded through, and is a
+ * no-op if @bo is not linked.
+ */
+static void xe_bo_account_unpin(struct xe_bo *bo)
+{
+	struct xe_device *xe = xe_bo_device(bo);
+	bool last_unpin = bo->ttm.pin_count == 1;
+
+	if (last_unpin && !list_empty(&bo->pinned_link)) {
+		spin_lock(&xe->pinned.lock);
+		list_del_init(&bo->pinned_link);
+		spin_unlock(&xe->pinned.lock);
+	}
+
+	if (last_unpin && bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm) &&
+	    !xe_ttm_bo_is_imported(&bo->ttm))
+		xe_ttm_tt_account_add(xe, bo->ttm.ttm);
+}
+
+/**
+ * xe_bo_pin_account() - Pin a bo and account its pages for the shrinker
+ * @bo: The buffer object to pin.
+ *
+ * Pins @bo via ttm_bo_pin() and updates the shrinker's shrinkable /
+ * purgeable page accounting to match. Must be called with @bo's dma-resv
+ * held. Safe to call regardless of which pin path (kernel, external,
+ * framebuffer, backup object, ...) is pinning @bo.
+ */
+void xe_bo_pin_account(struct xe_bo *bo)
+{
+	ttm_bo_pin(&bo->ttm);
+	xe_bo_account_pin(bo);
+}
+
+/**
+ * xe_bo_unpin_account() - Unpin a bo and account its pages for the shrinker
+ * @bo: The buffer object to unpin.
+ *
+ * Counterpart to xe_bo_pin_account(). Updates the shrinker's shrinkable /
+ * purgeable page accounting to match, then unpins @bo via ttm_bo_unpin().
+ * Must be called with @bo's dma-resv held.
+ */
+void xe_bo_unpin_account(struct xe_bo *bo)
+{
+	xe_bo_account_unpin(bo);
+	ttm_bo_unpin(&bo->ttm);
+}
+
 static void update_global_total_pages(struct ttm_device *ttm_dev,
 				      long num_pages)
 {
@@ -1389,7 +1483,8 @@ int xe_bo_notifier_prepare_pinned(struct xe_bo *bo)
 		}
 
 		backup->parent_obj = xe_bo_get(bo); /* Released by bo_destroy */
-		ttm_bo_pin(&backup->ttm);
+		/* Note: XE_BO_FLAG_SYSTEM resolves to XE_PL_TT so already populated. */
+		xe_bo_pin_account(backup);
 		bo->backup_obj = backup;
 	}
 
@@ -1409,7 +1504,7 @@ int xe_bo_notifier_unprepare_pinned(struct xe_bo *bo)
 {
 	xe_bo_lock(bo, false);
 	if (bo->backup_obj) {
-		ttm_bo_unpin(&bo->backup_obj->ttm);
+		xe_bo_unpin_account(bo->backup_obj);
 		xe_bo_put(bo->backup_obj);
 		bo->backup_obj = NULL;
 	}
@@ -1620,7 +1715,7 @@ out_backup:
 	xe_bo_vunmap(backup);
 	if (!bo->backup_obj) {
 		if (xe_bo_is_pinned(backup))
-			ttm_bo_unpin(&backup->ttm);
+			xe_bo_unpin_account(backup);
 		xe_bo_put(backup);
 	}
 out_unlock_bo:
@@ -2012,15 +2107,6 @@ static vm_fault_t xe_err_to_fault_t(int err)
 	return VM_FAULT_SIGBUS;
 }
 
-static bool xe_ttm_bo_is_imported(struct ttm_buffer_object *tbo)
-{
-	dma_resv_assert_held(tbo->base.resv);
-
-	return tbo->ttm &&
-		(tbo->ttm->page_flags & (TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE)) ==
-		TTM_TT_FLAG_EXTERNAL;
-}
-
 static vm_fault_t xe_bo_cpu_fault_fastpath(struct vm_fault *vmf, struct xe_device *xe,
 					   struct xe_bo *bo, bool needs_rpm)
 {
@@ -3141,12 +3227,13 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res)
 int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec)
 {
 	struct xe_device *xe = xe_bo_device(bo);
+	bool first_pin = !xe_bo_is_pinned(bo);
 	int err;
 
 	xe_assert(xe, !bo->vm);
 	xe_assert(xe, xe_bo_is_user(bo));
 
-	if (!xe_bo_is_pinned(bo)) {
+	if (first_pin) {
 		if (!in_place) {
 			err = xe_bo_validate(bo, NULL, false, exec);
 			if (err)
@@ -3158,9 +3245,7 @@ int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec)
 		spin_unlock(&xe->pinned.lock);
 	}
 
-	ttm_bo_pin(&bo->ttm);
-	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
-		xe_ttm_tt_account_subtract(xe, bo->ttm.ttm);
+	xe_bo_pin_account(bo);
 
 	/*
 	 * FIXME: If we always use the reserve / unreserve functions for locking
@@ -3216,9 +3301,7 @@ int xe_bo_pin(struct xe_bo *bo, struct drm_exec *exec)
 		spin_unlock(&xe->pinned.lock);
 	}
 
-	ttm_bo_pin(&bo->ttm);
-	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
-		xe_ttm_tt_account_subtract(xe, bo->ttm.ttm);
+	xe_bo_pin_account(bo);
 
 	/*
 	 * FIXME: If we always use the reserve / unreserve functions for locking
@@ -3247,14 +3330,7 @@ void xe_bo_unpin_external(struct xe_bo *bo)
 	xe_assert(xe, xe_bo_is_pinned(bo));
 	xe_assert(xe, xe_bo_is_user(bo));
 
-	spin_lock(&xe->pinned.lock);
-	if (bo->ttm.pin_count == 1 && !list_empty(&bo->pinned_link))
-		list_del_init(&bo->pinned_link);
-	spin_unlock(&xe->pinned.lock);
-
-	ttm_bo_unpin(&bo->ttm);
-	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
-		xe_ttm_tt_account_add(xe, bo->ttm.ttm);
+	xe_bo_unpin_account(bo);
 
 	/*
 	 * FIXME: If we always use the reserve / unreserve functions for locking
@@ -3272,21 +3348,16 @@ void xe_bo_unpin(struct xe_bo *bo)
 	xe_assert(xe, xe_bo_is_pinned(bo));
 
 	if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) {
-		spin_lock(&xe->pinned.lock);
 		xe_assert(xe, !list_empty(&bo->pinned_link));
-		list_del_init(&bo->pinned_link);
-		spin_unlock(&xe->pinned.lock);
 
 		if (bo->backup_obj) {
 			if (xe_bo_is_pinned(bo->backup_obj))
-				ttm_bo_unpin(&bo->backup_obj->ttm);
+				xe_bo_unpin_account(bo->backup_obj);
 			xe_bo_put(bo->backup_obj);
 			bo->backup_obj = NULL;
 		}
 	}
-	ttm_bo_unpin(&bo->ttm);
-	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
-		xe_ttm_tt_account_add(xe, bo->ttm.ttm);
+	xe_bo_unpin_account(bo);
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 152bfcffe399..53a701d3d242 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -229,6 +229,8 @@ int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec);
 int xe_bo_pin(struct xe_bo *bo, struct drm_exec *exec);
 void xe_bo_unpin_external(struct xe_bo *bo);
 void xe_bo_unpin(struct xe_bo *bo);
+void xe_bo_pin_account(struct xe_bo *bo);
+void xe_bo_unpin_account(struct xe_bo *bo);
 int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict,
 		   struct drm_exec *exec);
 
diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c
index f4f381988289..b82caaff80d7 100644
--- a/drivers/gpu/drm/xe/xe_i2c.c
+++ b/drivers/gpu/drm/xe/xe_i2c.c
@@ -324,12 +324,15 @@ static void xe_i2c_remove(void *data)
 	xe_i2c_irq_reset(xe);
 	xe_amc_exit(i2c);
 
+	/* Stop the notifier from arming the client work before teardown. */
+	bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier);
+	cancel_work_sync(&i2c->work);
+
 	for (i = 0; i < XE_I2C_MAX_CLIENTS; i++) {
 		i2c_unregister_device(i2c->client[i]);
 		i2c->client[i] = NULL;
 	}
 
-	bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier);
 	xe_i2c_unregister_adapter(i2c);
 	xe->i2c = NULL;
 }
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 35b4e8289b5f..e4388a960490 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1099,8 +1099,7 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
 #define CONTEXT_ACTIVE XE_LRC_CTX_TIMESTAMP_ACTIVE
 static ssize_t setup_utilization_wa(struct xe_lrc *lrc,
 				    struct xe_hw_engine *hwe,
-				    u32 *batch,
-				    size_t max_len)
+				    u32 *batch, size_t max_len, bool indirect)
 {
 	u32 *cmd = batch;
 
@@ -1131,19 +1130,25 @@ static ssize_t setup_utilization_wa(struct xe_lrc *lrc,
 }
 
 static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
-				  u32 *batch, size_t max_len)
+				  u32 *batch, size_t max_len, bool indirect)
 {
 	const u32 ts_addr = __xe_lrc_ctx_timestamp_ggtt_addr(lrc);
 	u32 *cmd = batch;
 
-	if (!XE_GT_WA(lrc->gt, 16010904313) ||
-	    !(hwe->class == XE_ENGINE_CLASS_RENDER ||
-	      hwe->class == XE_ENGINE_CLASS_COMPUTE ||
-	      hwe->class == XE_ENGINE_CLASS_COPY ||
+	if (!XE_GT_WA(lrc->gt, 16010904313))
+		return 0;
+
+	if (!indirect &&
+	    !(hwe->class == XE_ENGINE_CLASS_COPY ||
 	      hwe->class == XE_ENGINE_CLASS_VIDEO_DECODE ||
 	      hwe->class == XE_ENGINE_CLASS_VIDEO_ENHANCE))
 		return 0;
 
+	if (indirect &&
+	    !(hwe->class == XE_ENGINE_CLASS_RENDER ||
+	      hwe->class == XE_ENGINE_CLASS_COMPUTE))
+		return 0;
+
 	if (xe_gt_WARN_ON(lrc->gt, max_len < 12))
 		return -ENOSPC;
 
@@ -1169,7 +1174,8 @@ static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 
 static ssize_t setup_configfs_post_ctx_restore_bb(struct xe_lrc *lrc,
 						  struct xe_hw_engine *hwe,
-						  u32 *batch, size_t max_len)
+						  u32 *batch, size_t max_len,
+						  bool indirect)
 {
 	struct xe_device *xe = gt_to_xe(lrc->gt);
 	const u32 *user_batch;
@@ -1198,7 +1204,8 @@ static ssize_t setup_configfs_post_ctx_restore_bb(struct xe_lrc *lrc,
 
 static ssize_t setup_configfs_mid_ctx_restore_bb(struct xe_lrc *lrc,
 						 struct xe_hw_engine *hwe,
-						 u32 *batch, size_t max_len)
+						 u32 *batch, size_t max_len,
+						 bool indirect)
 {
 	struct xe_device *xe = gt_to_xe(lrc->gt);
 	const u32 *user_batch;
@@ -1227,7 +1234,8 @@ static ssize_t setup_configfs_mid_ctx_restore_bb(struct xe_lrc *lrc,
 
 static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
 					       struct xe_hw_engine *hwe,
-					       u32 *batch, size_t max_len)
+					       u32 *batch, size_t max_len,
+					       bool indirect)
 {
 	u32 *cmd = batch;
 
@@ -1247,7 +1255,8 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
 
 static ssize_t setup_invalidate_auxccs_wa(struct xe_lrc *lrc,
 					  struct xe_hw_engine *hwe,
-					  u32 *batch, size_t max_len)
+					  u32 *batch, size_t max_len,
+					  bool indirect)
 {
 	struct xe_gt *gt = lrc->gt;
 	u32 *(*emit)(struct xe_gt *gt, u32 *cmd) =
@@ -1264,7 +1273,7 @@ static ssize_t setup_invalidate_auxccs_wa(struct xe_lrc *lrc,
 
 struct bo_setup {
 	ssize_t (*setup)(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
-			 u32 *batch, size_t max_size);
+			 u32 *batch, size_t max_size, bool indirect);
 };
 
 struct bo_setup_state {
@@ -1273,6 +1282,7 @@ struct bo_setup_state {
 	struct xe_hw_engine	*hwe;
 	size_t			max_size;
 	size_t                  reserve_dw;
+	bool			indirect;
 	unsigned int		offset;
 	const struct bo_setup	*funcs;
 	unsigned int		num_funcs;
@@ -1298,7 +1308,8 @@ static int setup_bo(struct bo_setup_state *state)
 
 	for (size_t i = 0; i < state->num_funcs; i++) {
 		ssize_t len = state->funcs[i].setup(state->lrc, state->hwe,
-						    state->ptr, remain);
+						    state->ptr, remain,
+						    state->indirect);
 
 		remain -= len;
 
@@ -1404,6 +1415,7 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 	struct bo_setup_state state = {
 		.lrc = lrc,
 		.hwe = hwe,
+		.indirect = true,
 		.max_size = (63 * 64) /* max 63 cachelines */,
 		.buffer = NULL,
 		.offset = __xe_lrc_indirect_ctx_offset(lrc),
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index 7fa18dfcb5a2..455a07d79cd9 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -320,6 +320,7 @@ u64 xe_mmio_read64_2x32(struct xe_mmio *mmio, struct xe_reg reg)
 	return (u64)udw << 32 | ldw;
 }
 
+#define __XE_MMIO_WAIT_MAX_BACKOFF_100MS (100 * USEC_PER_MSEC)
 static int __xe_mmio_wait32(struct xe_mmio *mmio, struct xe_reg reg, u32 mask, u32 val,
 			    u32 timeout_us, u32 *out_val, bool atomic, bool expect_match)
 {
@@ -350,10 +351,10 @@ static int __xe_mmio_wait32(struct xe_mmio *mmio, struct xe_reg reg, u32 mask, u
 			wait = ktime_us_delta(end, cur);
 
 		if (atomic)
-			udelay(wait);
+			udelay(min_t(s64, wait, (MAX_UDELAY_MS * 1000)));
 		else
 			usleep_range(wait, wait << 1);
-		wait <<= 1;
+		wait = min_t(s64, wait << 1, __XE_MMIO_WAIT_MAX_BACKOFF_100MS);
 	}
 
 	if (ret != 0) {
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c
index 72baf1aa4b3a..a0179e62abaa 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c
@@ -19,20 +19,20 @@
 #include "xe_sysctrl_mailbox_types.h"
 
 struct xe_sysctrl_mailbox_msg_hdr {
-	__le32 data;
-} __packed;
+	u32 data;
+};
 
 #define XE_SYSCTRL_HDR_GROUP_ID(hdr) \
-	FIELD_GET(SYSCTRL_HDR_GROUP_ID_MASK, le32_to_cpu((hdr)->data))
+	FIELD_GET(SYSCTRL_HDR_GROUP_ID_MASK, (hdr)->data)
 
 #define XE_SYSCTRL_HDR_COMMAND(hdr) \
-	FIELD_GET(SYSCTRL_HDR_COMMAND_MASK, le32_to_cpu((hdr)->data))
+	FIELD_GET(SYSCTRL_HDR_COMMAND_MASK, (hdr)->data)
 
 #define XE_SYSCTRL_HDR_IS_RESPONSE(hdr) \
-	FIELD_GET(SYSCTRL_HDR_IS_RESPONSE, le32_to_cpu((hdr)->data))
+	FIELD_GET(SYSCTRL_HDR_IS_RESPONSE, (hdr)->data)
 
 #define XE_SYSCTRL_HDR_RESULT(hdr) \
-	FIELD_GET(SYSCTRL_HDR_RESULT_MASK, le32_to_cpu((hdr)->data))
+	FIELD_GET(SYSCTRL_HDR_RESULT_MASK, (hdr)->data)
 
 static bool sysctrl_wait_bit_clear(struct xe_sysctrl *sc, u32 bit_mask,
 				   unsigned int timeout_ms)
@@ -126,8 +126,8 @@ static int sysctrl_prepare_command(struct xe_device *xe,
 		return -ENOMEM;
 
 	hdr = (struct xe_sysctrl_mailbox_msg_hdr *)buffer;
-	hdr->data = cpu_to_le32(FIELD_PREP(SYSCTRL_HDR_GROUP_ID_MASK, group_id) |
-				     FIELD_PREP(SYSCTRL_HDR_COMMAND_MASK, command));
+	hdr->data = FIELD_PREP(SYSCTRL_HDR_GROUP_ID_MASK, group_id) |
+		    FIELD_PREP(SYSCTRL_HDR_COMMAND_MASK, command);
 
 	if (data_in && data_in_len)
 		memcpy(buffer + sizeof(*hdr), data_in, data_in_len);
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 7e4cc6f55237..a0883ddf32e2 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -79,7 +79,7 @@ static inline u32 hv_ring_gpadl_send_hvpgoffset(u32 offset)
 	 * therefore leaving a (PAGE_SIZE - HV_HYP_PAGE_SIZE) gap.
 	 *
 	 * And to calculate the effective send offset in gpadl, we need to
-	 * substract this gap.
+	 * subtract this gap.
 	 */
 	return (offset - (PAGE_SIZE - HV_HYP_PAGE_SIZE)) >> HV_HYP_PAGE_SHIFT;
 }
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index a044fd3b3c4e..c42def04ac41 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -752,13 +752,14 @@ static void init_vp_index(struct vmbus_channel *channel)
 	u32 i, ncpu = num_online_cpus();
 	cpumask_var_t available_mask;
 	struct cpumask *allocated_mask;
+	const struct cpumask *node_mask;
 	const struct cpumask *hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
 	u32 target_cpu;
 	int numa_node;
 
 	if (!perf_chn ||
 	    !alloc_cpumask_var(&available_mask, GFP_KERNEL) ||
-	    cpumask_empty(hk_mask)) {
+	    !cpumask_intersects(hk_mask, cpu_online_mask)) {
 		/*
 		 * If the channel is not a performance critical
 		 * channel, bind it to VMBUS_CONNECT_CPU.
@@ -780,14 +781,19 @@ static void init_vp_index(struct vmbus_channel *channel)
 				next_numa_node_id = 0;
 				continue;
 			}
-			if (cpumask_empty(cpumask_of_node(numa_node)))
+			/*
+			 * Try next NUMA node if current NUMA node has no CPU
+			 * or doesn't contain any housekeeping CPU.
+			 */
+			node_mask = cpumask_of_node(numa_node);
+			if (!cpumask_intersects(node_mask, hk_mask))
 				continue;
 			break;
 		}
 		allocated_mask = &hv_context.hv_numa_map[numa_node];
 
 retry:
-		cpumask_xor(available_mask, allocated_mask, cpumask_of_node(numa_node));
+		cpumask_xor(available_mask, allocated_mask, node_mask);
 		cpumask_and(available_mask, available_mask, hk_mask);
 
 		if (cpumask_empty(available_mask)) {
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 1ab3581b096a..818667ef9c74 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -346,7 +346,6 @@ int vmbus_connect(void)
 cleanup:
 	pr_err("Unable to connect to host\n");
 
-	vmbus_connection.conn_state = DISCONNECTED;
 	vmbus_disconnect();
 
 	kfree(msginfo);
diff --git a/drivers/hv/mshv_vtl_main.c b/drivers/hv/mshv_vtl_main.c
index 6e3c11c68171..d8225242c73f 100644
--- a/drivers/hv/mshv_vtl_main.c
+++ b/drivers/hv/mshv_vtl_main.c
@@ -819,6 +819,9 @@ static vm_fault_t mshv_vtl_fault(struct vm_fault *vmf)
 		return VM_FAULT_NOPAGE;
 	}
 
+	if (!page)
+		return VM_FAULT_SIGBUS;
+
 	get_page(page);
 	vmf->page = page;
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 5ebdbe24b5a1..4692687cdbf3 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2923,23 +2923,19 @@ static void hv_crash_handler(struct pt_regs *regs)
 static int hv_synic_suspend(void *data)
 {
 	/*
-	 * When we reach here, all the non-boot CPUs have been offlined.
-	 * If we're in a legacy configuration where stimer Direct Mode is
-	 * not enabled, the stimers on the non-boot CPUs have been unbound
-	 * in hv_synic_cleanup() -> hv_stimer_legacy_cleanup() ->
-	 * hv_stimer_cleanup() -> clockevents_unbind_device().
+	 * When we reach here, all the non-boot CPUs have been offlined,
+	 * and their stimers have been cleaned up by the cpuhp teardown
+	 * callback hv_stimer_cleanup().
 	 *
 	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled.
-	 * Here we do not call hv_stimer_legacy_cleanup() on CPU0 because:
-	 * 1) it's unnecessary as interrupts remain disabled between
-	 * syscore_suspend() and syscore_resume(): see create_image() and
+	 * The stimer on CPU0 is not explicitly cleaned up here because:
+	 * 1) it's harmless as interrupts remain disabled between
+	 * syscore_suspend() and syscore_resume(), so the stimer cannot
+	 * fire during this window: see create_image() and
 	 * resume_target_kernel()
 	 * 2) the stimer on CPU0 is automatically disabled later by
 	 * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
 	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown()
-	 * 3) a warning would be triggered if we call
-	 * clockevents_unbind_device(), which may sleep, in an
-	 * interrupts-disabled context.
 	 */
 
 	hv_hyp_synic_disable_regs(0);
@@ -3043,7 +3039,6 @@ static void __exit vmbus_exit(void)
 
 	hv_remove_kexec_handler();
 	hv_remove_crash_handler();
-	vmbus_connection.conn_state = DISCONNECTED;
 	hv_stimer_global_cleanup();
 	vmbus_disconnect();
 	if (vmbus_irq == -1)
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 6a39e21d5ed4..ed6495ef811c 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -1003,13 +1003,14 @@ static int geni_i2c_xfer(struct i2c_adapter *adap,
 
 	ret = gi2c->dev_data->set_rate(&gi2c->se, gi2c->clk_freq_out);
 	if (ret)
-		return ret;
+		goto out_pm;
 
 	if (gi2c->gpi_mode)
 		ret = geni_i2c_gpi_xfer(gi2c, msgs, num);
 	else
 		ret = geni_i2c_fifo_xfer(gi2c, msgs, num);
 
+out_pm:
 	pm_runtime_put_autosuspend(gi2c->se.dev);
 	gi2c->cur = NULL;
 	gi2c->err = 0;
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 6406ceab988a..810e52782ae8 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -302,6 +302,8 @@ static const struct xpad_device {
 	{ 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 },
 	{ 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 },
 	{ 0x1a86, 0xe310, "Legion Go S", 0, XTYPE_XBOX360 },
+	{ 0x1b1c, 0x2b1f, "Corsair Novablade Pro (Wired)", 0, XTYPE_XBOX360 },
+	{ 0x1b1c, 0x2b2b, "Corsair Novablade Pro (2.4 GHz Receiver)", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0130, "Ion Drum Rocker", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
@@ -379,6 +381,7 @@ static const struct xpad_device {
 	{ 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x200f, "8BitDo Ultimate 3-mode Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
+	{ 0x2dc8, 0x201e, "8BitDo Pro 2 Wired Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
@@ -545,6 +548,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x17ef),		/* Lenovo */
 	XPAD_XBOX360_VENDOR(0x1949),		/* Amazon controllers */
 	XPAD_XBOX360_VENDOR(0x1a86),		/* Nanjing Qinheng Microelectronics (WCH) */
+	XPAD_XBOX360_VENDOR(0x1b1c),		/* Corsair controllers */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
 	XPAD_XBOX360_VENDOR(0x1ee9),		/* ZOTAC Technology Limited */
 	XPAD_XBOX360_VENDOR(0x20bc),		/* BETOP wireless dongles */
diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c
index 8db2dca84975..3e0f874e9b16 100644
--- a/drivers/input/misc/ati_remote2.c
+++ b/drivers/input/misc/ati_remote2.c
@@ -672,8 +672,7 @@ static ssize_t ati_remote2_show_channel_mask(struct device *dev,
 					     struct device_attribute *attr,
 					     char *buf)
 {
-	struct usb_device *udev = to_usb_device(dev);
-	struct usb_interface *intf = usb_ifnum_to_if(udev, 0);
+	struct usb_interface *intf = to_usb_interface(dev);
 	struct ati_remote2 *ar2 = usb_get_intfdata(intf);
 
 	return sprintf(buf, "0x%04x\n", ar2->channel_mask);
@@ -683,8 +682,7 @@ static ssize_t ati_remote2_store_channel_mask(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
 {
-	struct usb_device *udev = to_usb_device(dev);
-	struct usb_interface *intf = usb_ifnum_to_if(udev, 0);
+	struct usb_interface *intf = to_usb_interface(dev);
 	struct ati_remote2 *ar2 = usb_get_intfdata(intf);
 	unsigned int mask;
 	int r;
@@ -720,8 +718,7 @@ static ssize_t ati_remote2_show_mode_mask(struct device *dev,
 					  struct device_attribute *attr,
 					  char *buf)
 {
-	struct usb_device *udev = to_usb_device(dev);
-	struct usb_interface *intf = usb_ifnum_to_if(udev, 0);
+	struct usb_interface *intf = to_usb_interface(dev);
 	struct ati_remote2 *ar2 = usb_get_intfdata(intf);
 
 	return sprintf(buf, "0x%02x\n", ar2->mode_mask);
@@ -731,8 +728,7 @@ static ssize_t ati_remote2_store_mode_mask(struct device *dev,
 					   struct device_attribute *attr,
 					   const char *buf, size_t count)
 {
-	struct usb_device *udev = to_usb_device(dev);
-	struct usb_interface *intf = usb_ifnum_to_if(udev, 0);
+	struct usb_interface *intf = to_usb_interface(dev);
 	struct ati_remote2 *ar2 = usb_get_intfdata(intf);
 	unsigned int mask;
 	int err;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 58c624513cd4..68ee57800fef 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1228,9 +1228,9 @@ dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 	 * If both the physical buffer start address and size are page aligned,
 	 * we don't need to use a bounce page.
 	 */
-	if (dev_use_swiotlb(dev, size, dir) &&
+	if (!(attrs & DMA_ATTR_MMIO) && dev_use_swiotlb(dev, size, dir) &&
 	    iova_unaligned(iovad, phys, size)) {
-		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
+		if (attrs & DMA_ATTR_REQUIRE_COHERENT)
 			return DMA_MAPPING_ERROR;
 
 		phys = iommu_dma_map_swiotlb(dev, phys, size, dir, attrs);
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index c418add65bb5..79af154767c1 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -2416,7 +2416,7 @@ static int em28xx_v4l2_fini(struct em28xx *dev)
 	if (video_is_registered(&v4l2->radio_dev)) {
 		dev_info(&dev->intf->dev, "V4L2 device %s deregistered\n",
 			 video_device_node_name(&v4l2->radio_dev));
-		vb2_video_unregister_device(&v4l2->radio_dev);
+		video_unregister_device(&v4l2->radio_dev);
 	}
 	if (video_is_registered(&v4l2->vbi_dev)) {
 		dev_info(&dev->intf->dev, "V4L2 device %s deregistered\n",
@@ -3082,7 +3082,7 @@ unregister_dev:
 		dev_info(&dev->intf->dev,
 			 "V4L2 device %s deregistered\n",
 			 video_device_node_name(&v4l2->radio_dev));
-		vb2_video_unregister_device(&v4l2->radio_dev);
+		video_unregister_device(&v4l2->radio_dev);
 	}
 	if (video_is_registered(&v4l2->vbi_dev)) {
 		dev_info(&dev->intf->dev,
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index e03989c4e99e..0d15f48ef51d 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -370,9 +370,7 @@ int memstick_set_rw_addr(struct memstick_dev *card)
 {
 	card->next_request = h_memstick_set_rw_addr;
 	memstick_new_req(card->host);
-	if (!wait_for_completion_timeout(&card->mrq_complete,
-			msecs_to_jiffies(500)))
-		card->current_mrq.error = -ETIMEDOUT;
+	wait_for_completion(&card->mrq_complete);
 
 	return card->current_mrq.error;
 }
@@ -405,9 +403,7 @@ static struct memstick_dev *memstick_alloc_card(struct memstick_host *host)
 
 		card->next_request = h_memstick_read_dev_id;
 		memstick_new_req(host);
-		if (!wait_for_completion_timeout(&card->mrq_complete,
-				msecs_to_jiffies(500)))
-			card->current_mrq.error = -ETIMEDOUT;
+		wait_for_completion(&card->mrq_complete);
 
 		if (card->current_mrq.error)
 			goto err_out;
diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c
index beadc389f15f..d5b3a96fc609 100644
--- a/drivers/memstick/host/rtsx_usb_ms.c
+++ b/drivers/memstick/host/rtsx_usb_ms.c
@@ -27,7 +27,6 @@ struct rtsx_usb_ms {
 	struct memstick_host	*msh;
 	struct memstick_request	*req;
 
-	struct mutex		host_mutex;
 	struct work_struct	handle_req;
 	struct delayed_work	poll_card;
 
@@ -514,6 +513,13 @@ static void rtsx_usb_ms_handle_req(struct work_struct *work)
 	struct memstick_host *msh = host->msh;
 	int rc;
 
+	/* Fail requests after eject so their waiters are released. */
+	if (host->eject) {
+		while (!memstick_next_req(msh, &host->req))
+			host->req->error = -ENOMEDIUM;
+		return;
+	}
+
 	if (!host->req) {
 		pm_runtime_get_sync(ms_dev(host));
 		do {
@@ -547,8 +553,7 @@ static void rtsx_usb_ms_request(struct memstick_host *msh)
 
 	dev_dbg(ms_dev(host), "--> %s\n", __func__);
 
-	if (!host->eject)
-		schedule_work(&host->handle_req);
+	schedule_work(&host->handle_req);
 }
 
 static int rtsx_usb_ms_set_param(struct memstick_host *msh,
@@ -781,7 +786,6 @@ static int rtsx_usb_ms_drv_probe(struct platform_device *pdev)
 	host->power_mode = MEMSTICK_POWER_OFF;
 	platform_set_drvdata(pdev, host);
 
-	mutex_init(&host->host_mutex);
 	INIT_WORK(&host->handle_req, rtsx_usb_ms_handle_req);
 
 	INIT_DELAYED_WORK(&host->poll_card, rtsx_usb_ms_poll_card);
@@ -812,27 +816,12 @@ static void rtsx_usb_ms_drv_remove(struct platform_device *pdev)
 {
 	struct rtsx_usb_ms *host = platform_get_drvdata(pdev);
 	struct memstick_host *msh = host->msh;
-	int err;
 
 	host->eject = true;
 	msh->removing = true;
-	cancel_work_sync(&host->handle_req);
+	flush_work(&host->handle_req);
 	cancel_delayed_work_sync(&host->poll_card);
 
-	mutex_lock(&host->host_mutex);
-	if (host->req) {
-		dev_dbg(ms_dev(host),
-			"%s: Controller removed during transfer\n",
-			dev_name(&msh->dev));
-		host->req->error = -ENOMEDIUM;
-		do {
-			err = memstick_next_req(msh, &host->req);
-			if (!err)
-				host->req->error = -ENOMEDIUM;
-		} while (!err);
-	}
-	mutex_unlock(&host->host_mutex);
-
 	/* Balance possible unbalanced usage count
 	 * e.g. unconditional module removal
 	 */
@@ -841,6 +830,8 @@ static void rtsx_usb_ms_drv_remove(struct platform_device *pdev)
 
 	pm_runtime_disable(ms_dev(host));
 	memstick_remove_host(msh);
+	/* No card, no new requests; wait for the last failed one to finish. */
+	cancel_work_sync(&host->handle_req);
 	dev_dbg(ms_dev(host),
 		": Realtek USB Memstick controller has been removed\n");
 	memstick_free_host(msh);
diff --git a/drivers/mmc/host/cavium-octeon.c b/drivers/mmc/host/cavium-octeon.c
index 1bfc1a4f9fe9..671dd1a36a74 100644
--- a/drivers/mmc/host/cavium-octeon.c
+++ b/drivers/mmc/host/cavium-octeon.c
@@ -295,9 +295,12 @@ static void octeon_mmc_remove(struct platform_device *pdev)
 	u64 dma_cfg;
 	int i;
 
-	for (i = 0; i < CAVIUM_MAX_MMC; i++)
+	for (i = 0; i < CAVIUM_MAX_MMC; i++) {
 		if (host->slot[i])
 			cvm_mmc_of_slot_remove(host->slot[i]);
+		if (host->slot_pdev[i])
+			of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+	}
 
 	dma_cfg = readq(host->dma_base + MIO_EMM_DMA_CFG(host));
 	dma_cfg &= ~MIO_EMM_DMA_CFG_EN;
diff --git a/drivers/mmc/host/cavium-thunderx.c b/drivers/mmc/host/cavium-thunderx.c
index 84ff6d82ae3c..2635ac94ec5d 100644
--- a/drivers/mmc/host/cavium-thunderx.c
+++ b/drivers/mmc/host/cavium-thunderx.c
@@ -173,9 +173,12 @@ static void thunder_mmc_remove(struct pci_dev *pdev)
 	u64 dma_cfg;
 	int i;
 
-	for (i = 0; i < CAVIUM_MAX_MMC; i++)
+	for (i = 0; i < CAVIUM_MAX_MMC; i++) {
 		if (host->slot[i])
 			cvm_mmc_of_slot_remove(host->slot[i]);
+		if (host->slot_pdev[i])
+			of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+	}
 
 	dma_cfg = readq(host->dma_base + MIO_EMM_DMA_CFG(host));
 	dma_cfg &= ~MIO_EMM_DMA_CFG_EN;
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 01ea3adbdf3b..5b160fdad3f0 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -3216,6 +3216,7 @@ static void msdc_drv_remove(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, NULL);
 	mmc_remove_host(mmc);
+	cancel_delayed_work_sync(&host->req_timeout);
 	msdc_deinit_hw(host);
 	msdc_gate_clock(host);
 
diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c
index 3584a2b314a9..0c8f389fe584 100644
--- a/drivers/mmc/host/sdhci-sprd.c
+++ b/drivers/mmc/host/sdhci-sprd.c
@@ -890,6 +890,10 @@ static void sdhci_sprd_remove(struct platform_device *pdev)
 	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_sprd_host *sprd_host = TO_SPRD_HOST(host);
 
+	pm_runtime_get_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
+
 	sdhci_remove_host(host, 0);
 
 	clk_disable_unprepare(sprd_host->clk_sdio);
diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c
index 0a08da799255..2538275a1e57 100644
--- a/drivers/net/ethernet/actions/owl-emac.c
+++ b/drivers/net/ethernet/actions/owl-emac.c
@@ -1552,6 +1552,8 @@ static int owl_emac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	netdev->netdev_ops = &owl_emac_netdev_ops;
+
 	ret = owl_emac_phy_init(netdev);
 	if (ret) {
 		dev_err(dev, "failed to initialize PHY\n");
@@ -1563,7 +1565,6 @@ static int owl_emac_probe(struct platform_device *pdev)
 	netdev->min_mtu = OWL_EMAC_MTU_MIN;
 	netdev->max_mtu = OWL_EMAC_MTU_MAX;
 	netdev->watchdog_timeo = OWL_EMAC_TX_TIMEOUT;
-	netdev->netdev_ops = &owl_emac_netdev_ops;
 	netdev->ethtool_ops = &owl_emac_ethtool_ops;
 	netif_napi_add(netdev, &priv->napi, owl_emac_poll);
 
diff --git a/drivers/net/ethernet/adi/adin1140.c b/drivers/net/ethernet/adi/adin1140.c
index adc6e2ef44f8..107cf2f2aa17 100644
--- a/drivers/net/ethernet/adi/adin1140.c
+++ b/drivers/net/ethernet/adi/adin1140.c
@@ -733,6 +733,8 @@ static int adin1140_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
+	netdev->netdev_ops = &adin1140_netdev_ops;
+
 	ret = adin1140_phy_init(priv, spi);
 	if (ret)
 		return ret;
@@ -748,7 +750,6 @@ static int adin1140_probe(struct spi_device *spi)
 
 	netdev->if_port = IF_PORT_10BASET;
 	netdev->irq = spi->irq;
-	netdev->netdev_ops = &adin1140_netdev_ops;
 	netdev->ethtool_ops = &adin1140_ethtool_ops;
 	netdev->netns_immutable = true;
 	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE |
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index a593adc16c78..fccb67beebee 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1421,6 +1421,8 @@ static int greth_of_probe(struct platform_device *ofdev)
 	/* Check if MAC can handle MDIO interrupts */
 	greth->mdio_int_en = (tmp >> 26) & 1;
 
+	dev->netdev_ops = &greth_netdev_ops;
+
 	err = greth_mdio_init(greth);
 	if (err) {
 		if (netif_msg_probe(greth))
@@ -1498,7 +1500,6 @@ static int greth_of_probe(struct platform_device *ofdev)
 		dev->flags &= ~IFF_MULTICAST;
 	}
 
-	dev->netdev_ops = &greth_netdev_ops;
 	dev->ethtool_ops = &greth_ethtool_ops;
 
 	err = register_netdev(dev);
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 5a04056e38fa..8682323d693f 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1225,6 +1225,8 @@ static int au1000_probe(struct platform_device *pdev)
 		goto err_mdiobus_reg;
 	}
 
+	dev->netdev_ops = &au1000_netdev_ops;
+
 	err = au1000_mii_probe(dev);
 	if (err != 0)
 		goto err_out;
@@ -1263,7 +1265,6 @@ static int au1000_probe(struct platform_device *pdev)
 
 	dev->base_addr = base->start;
 	dev->irq = irq;
-	dev->netdev_ops = &au1000_netdev_ops;
 	dev->ethtool_ops = &au1000_ethtool_ops;
 	dev->watchdog_timeo = ETH_TX_TIMEOUT;
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 4c9db2f9fc25..a6b7797558b0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2148,6 +2148,16 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
+	/* We store Tx state in the control block, so the skb must not be
+	 * shared, but ether_setup() leaves IFF_TX_SKB_SHARING set.
+	 */
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb) {
+		BCMGENET_STATS64_INC((&ring->stats64), dropped);
+		ret = NETDEV_TX_OK;
+		goto out;
+	}
+
 	/* Retain how many bytes will be sent on the wire, without TSB inserted
 	 * by transmit checksum offload
 	 */
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 0c418557264c..e5b7df43e8f6 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1211,6 +1211,8 @@ static int ethoc_probe(struct platform_device *pdev)
 		goto free3;
 	}
 
+	netdev->netdev_ops = &ethoc_netdev_ops;
+
 	ret = ethoc_mdio_probe(netdev);
 	if (ret) {
 		dev_err(&netdev->dev, "failed to probe MDIO bus\n");
@@ -1218,7 +1220,6 @@ static int ethoc_probe(struct platform_device *pdev)
 	}
 
 	/* setup the net_device structure */
-	netdev->netdev_ops = &ethoc_netdev_ops;
 	netdev->watchdog_timeo = ETHOC_TIMEOUT;
 	netdev->features |= 0;
 	netdev->ethtool_ops = &ethoc_ethtool_ops;
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 2920985144bf..8f0fac38dee6 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -977,6 +977,8 @@ static int hip04_mac_probe(struct platform_device *pdev)
 		goto init_fail;
 	}
 
+	ndev->netdev_ops = &hip04_netdev_ops;
+
 	priv->phy_node = of_parse_phandle(node, "phy-handle", 0);
 	if (priv->phy_node) {
 		priv->phy = of_phy_connect(ndev, priv->phy_node,
@@ -990,7 +992,6 @@ static int hip04_mac_probe(struct platform_device *pdev)
 
 	INIT_WORK(&priv->tx_timeout_task, hip04_tx_timeout_task);
 
-	ndev->netdev_ops = &hip04_netdev_ops;
 	ndev->ethtool_ops = &hip04_ethtool_ops;
 	ndev->watchdog_timeo = TX_TIMEOUT;
 	ndev->priv_flags |= IFF_UNICAST_FLT;
diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c
index d244a40df430..016605e86f0b 100644
--- a/drivers/net/ethernet/hisilicon/hisi_femac.c
+++ b/drivers/net/ethernet/hisilicon/hisi_femac.c
@@ -830,6 +830,8 @@ static int hisi_femac_drv_probe(struct platform_device *pdev)
 		hisi_femac_phy_reset(priv);
 	}
 
+	ndev->netdev_ops = &hisi_femac_netdev_ops;
+
 	phy = of_phy_get_and_connect(ndev, node, hisi_femac_adjust_link);
 	if (!phy) {
 		dev_err(dev, "connect to PHY failed!\n");
@@ -850,7 +852,6 @@ static int hisi_femac_drv_probe(struct platform_device *pdev)
 
 	ndev->watchdog_timeo = 6 * HZ;
 	ndev->priv_flags |= IFF_UNICAST_FLT;
-	ndev->netdev_ops = &hisi_femac_netdev_ops;
 	ndev->ethtool_ops = &hisi_femac_ethtools_ops;
 	netif_napi_add_weight(ndev, &priv->napi, hisi_femac_poll,
 			      FEMAC_POLL_WEIGHT);
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 9caa1e47c174..38b4d65f58a5 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -3171,6 +3171,8 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	netif_set_real_num_tx_queues(dev, mp->txq_count);
 	netif_set_real_num_rx_queues(dev, mp->rxq_count);
 
+	dev->netdev_ops = &mv643xx_eth_netdev_ops;
+
 	err = 0;
 	if (pd->phy_node) {
 		phydev = of_phy_connect(mp->dev, pd->phy_node,
@@ -3221,8 +3223,6 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	}
 	dev->irq = irq;
 
-	dev->netdev_ops = &mv643xx_eth_netdev_ops;
-
 	dev->watchdog_timeo = 2 * HZ;
 	dev->base_addr = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index da6e57c103d6..c5ab0e0f7d26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -929,6 +929,7 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
 			goto free_actions;
 		}
 		(*ractions)[num_actions].aso_meter.offset =
+			(fte_action->exe_aso.object_id - fte_action->exe_aso.base_id) * 2 +
 			fte_action->exe_aso.flow_meter.meter_idx;
 		(*ractions)[num_actions].aso_meter.init_color =
 			fte_action->exe_aso.flow_meter.init_color;
@@ -1406,8 +1407,8 @@ static void mlx5_cmd_hws_packet_reformat_dealloc(struct mlx5_flow_root_namespace
 						    pr_data->data_size);
 		break;
 	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
-		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools,
-						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+		pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol3tnl_pools,
+						    MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3,
 						    pr_data->data_size);
 		break;
 	case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c
index 127afb9e9f14..d7e5dfc22396 100644
--- a/drivers/net/ethernet/microchip/lan865x/lan865x.c
+++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c
@@ -346,6 +346,8 @@ static int lan865x_probe(struct spi_device *spi)
 	spi_set_drvdata(spi, priv);
 	INIT_WORK(&priv->multicast_work, lan865x_multicast_work_handler);
 
+	netdev->netdev_ops = &lan865x_netdev_ops;
+
 	priv->tc6 = oa_tc6_init(spi, netdev, NULL);
 	if (IS_ERR(priv->tc6)) {
 		ret = PTR_ERR(priv->tc6);
@@ -397,7 +399,6 @@ static int lan865x_probe(struct spi_device *spi)
 
 	netdev->if_port = IF_PORT_10BASET;
 	netdev->irq = spi->irq;
-	netdev->netdev_ops = &lan865x_netdev_ops;
 	netdev->ethtool_ops = &lan865x_ethtool_ops;
 
 	ret = register_netdev(netdev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index d4ace3924891..66337cfd9824 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -312,6 +312,12 @@ static int dwmac1000_irq_status(struct stmmac_priv *priv,
 	if (intr_status & (PCS_ANE_IRQ | PCS_LINK_IRQ))
 		stmmac_integrated_pcs_irq(priv, intr_status, x);
 
+	/* Reading RGSMIIIS clears the interrupt the MAC reset unmasks. */
+	if (intr_status & PCS_RGSMIIIS_IRQ) {
+		readl(ioaddr + GMAC_RGSMIIIS);
+		x->irq_rgmii_n++;
+	}
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth.c b/drivers/net/ethernet/ti/icssm/icssm_prueth.c
index b7e94244355a..b42c98e861e0 100644
--- a/drivers/net/ethernet/ti/icssm/icssm_prueth.c
+++ b/drivers/net/ethernet/ti/icssm/icssm_prueth.c
@@ -1563,6 +1563,8 @@ static int icssm_prueth_netdev_init(struct prueth *prueth,
 	}
 	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
 
+	ndev->netdev_ops = &emac_netdev_ops;
+
 	/* connect PHY */
 	emac->phydev = of_phy_get_and_connect(ndev, eth_node,
 					      icssm_emac_adjust_link);
@@ -1590,7 +1592,6 @@ static int icssm_prueth_netdev_init(struct prueth *prueth,
 	}
 
 	ndev->dev.of_node = eth_node;
-	ndev->netdev_ops = &emac_netdev_ops;
 
 	netif_napi_add(ndev, &emac->napi, icssm_emac_napi_poll);
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9bcab3dc4c11..7eb0f9fe6b18 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -598,6 +598,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		break;
 	case NVME_CTRL_RESETTING:
 		switch (old_state) {
+		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
 			changed = true;
 			atomic_long_inc(&ctrl->nr_reset);
@@ -2616,10 +2617,19 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns->head);
-		ret = nvme_mpath_revalidate_zones(ns->head);
 
 unfreeze_head_queue:
 		blk_mq_unfreeze_queue(ns->head->disk->queue, memflags);
+
+		/*
+		 * Wait until the head queue is unfrozen before revalidating
+		 * its zones. blk_revalidate_disk_zones() takes the queue limits
+		 * lock and then freezes the queue on its own, so it must not be
+		 * called with the queue already frozen. This is also what
+		 * nvme_update_ns_info_block() does for ns->disk.
+		 */
+		if (!ret)
+			ret = nvme_mpath_revalidate_zones(ns->head);
 	}
 
 	return ret;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 8eea0a504308..07a74c2e1f58 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1325,7 +1325,7 @@ static int nvmet_req_alloc_p2pmem_sgls(struct pci_dev *p2p_dev,
 
 	return 0;
 out_free_sg:
-	pci_p2pmem_free_sgl(req->p2p_dev, req->sg);
+	pci_p2pmem_free_sgl(p2p_dev, req->sg);
 out_err:
 	return -ENOMEM;
 }
diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c
index 09d8c63f5680..81f48cb00aee 100644
--- a/drivers/nvme/target/pr.c
+++ b/drivers/nvme/target/pr.c
@@ -51,6 +51,8 @@ u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask)
 
 	if (nsid != U32_MAX) {
 		status = nvmet_req_find_ns(req);
+		if (status == (NVME_SC_INVALID_NS | NVME_STATUS_DNR))
+			return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
 		if (status)
 			return status;
 		if (!req->ns->pr.enable)
@@ -75,6 +77,8 @@ u16 nvmet_get_feat_resv_notif_mask(struct nvmet_req *req)
 	u16 status;
 
 	status = nvmet_req_find_ns(req);
+	if (status == (NVME_SC_INVALID_NS | NVME_STATUS_DNR))
+		return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
 	if (status)
 		return status;
 
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index af26a07c0c9e..1c8fdbd4cd17 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -421,23 +421,9 @@ static void rockchip_pcie_stop_link(struct dw_pcie *pci)
 static int rockchip_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct rockchip_pcie *rockchip = to_rockchip_pcie(pci);
-	struct device *dev = rockchip->pci.dev;
-	int irq, ret;
-
-	irq = of_irq_get_byname(dev->of_node, "legacy");
-	if (irq < 0)
-		return irq;
 
 	pci->dbi_base2 = pci->dbi_base + PCIE_TYPE0_HDR_DBI2_OFFSET;
 
-	ret = rockchip_pcie_init_irq_domain(rockchip);
-	if (ret < 0)
-		dev_err(dev, "failed to init irq domain\n");
-
-	irq_set_chained_handler_and_data(irq, rockchip_pcie_intx_handler,
-					 rockchip);
-
 	rockchip_pcie_configure_l1ss(pci);
 	rockchip_pcie_enable_l0s(pci);
 	pp->bridge->reset_root_port = rockchip_pcie_rc_reset_root_port;
@@ -730,6 +716,19 @@ static int rockchip_pcie_configure_rc(struct platform_device *pdev,
 				 PCIE_CLIENT_SET_MODE(PCIE_CLIENT_MODE_RC),
 				 PCIE_CLIENT_GENERAL_CON);
 
+	irq = of_irq_get_byname(dev->of_node, "legacy");
+	if (irq < 0)
+		return irq;
+
+	ret = rockchip_pcie_init_irq_domain(rockchip);
+	if (ret < 0) {
+		dev_err(dev, "failed to init irq domain\n");
+		return ret;
+	}
+
+	irq_set_chained_handler_and_data(irq, rockchip_pcie_intx_handler,
+					 rockchip);
+
 	pp = &rockchip->pci.pp;
 	pp->ops = &rockchip_pcie_host_ops;
 
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 89816a2bd7cd..85d826f8f68d 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1040,19 +1040,38 @@ static void put_pcichild(struct hv_pci_dev *hpdev)
 
 /*
  * There is no good way to get notified from vmbus_onoffer_rescind(),
- * so let's use polling here, since this is not a hot path.
+ * so let's use polling here, since this is not a hot path. If
+ * wait_for_response() has been polling for 2 minutes
+ * without either a rescind or completion, add a warning.
  */
+#define PCI_RESPONSE_WARN_POLL_COUNT 1200
+
 static int wait_for_response(struct hv_device *hdev,
-			     struct completion *comp)
+			     struct completion *comp,
+			     const char *msg_type)
 {
+	u64 counter = 0;
+
 	while (true) {
 		if (hdev->channel->rescind) {
 			dev_warn_once(&hdev->device, "The device is gone.\n");
 			return -ENODEV;
 		}
 
-		if (wait_for_completion_timeout(comp, HZ / 10))
+		counter++;
+
+		if (wait_for_completion_timeout(comp, HZ / 10)) {
+			if (counter > PCI_RESPONSE_WARN_POLL_COUNT)
+				dev_warn(&hdev->device,
+					 "Late %s completion arrived.\n", msg_type);
 			break;
+		}
+
+		if (counter == PCI_RESPONSE_WARN_POLL_COUNT) {
+			dev_err(&hdev->device,
+				"%s stuck waiting for response, relid = %u\n",
+				msg_type, hdev->channel->offermsg.child_relid);
+		}
 	}
 
 	return 0;
@@ -1518,7 +1537,8 @@ static int hv_read_config_block(struct pci_dev *pdev, void *buf,
 	if (ret)
 		return ret;
 
-	ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event);
+	ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event,
+				"PCI_READ_BLOCK");
 	if (ret)
 		return ret;
 
@@ -1607,7 +1627,8 @@ static int hv_write_config_block(struct pci_dev *pdev, void *buf,
 	if (ret)
 		return ret;
 
-	ret = wait_for_response(hbus->hdev, &comp_pkt.host_event);
+	ret = wait_for_response(hbus->hdev, &comp_pkt.host_event,
+				"PCI_WRITE_BLOCK");
 	if (ret)
 		return ret;
 
@@ -2624,7 +2645,8 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus,
 	if (ret)
 		goto error;
 
-	if (wait_for_response(hbus->hdev, &comp_pkt.host_event))
+	if (wait_for_response(hbus->hdev, &comp_pkt.host_event,
+			      "PCI_QUERY_RESOURCE_REQUIREMENTS"))
 		goto error;
 
 	hpdev->desc = *desc;
@@ -3256,7 +3278,8 @@ static int hv_pci_protocol_negotiation(struct hv_device *hdev,
 				(unsigned long)pkt, VM_PKT_DATA_INBAND,
 				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 		if (!ret)
-			ret = wait_for_response(hdev, &comp_pkt.host_event);
+			ret = wait_for_response(hdev, &comp_pkt.host_event,
+						"PCI_QUERY_PROTOCOL_VERSION");
 
 		if (ret) {
 			dev_err(&hdev->device,
@@ -3476,7 +3499,8 @@ enter_d0_retry:
 			       (unsigned long)pkt, VM_PKT_DATA_INBAND,
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (!ret)
-		ret = wait_for_response(hdev, &comp_pkt.host_event);
+		ret = wait_for_response(hdev, &comp_pkt.host_event,
+					"PCI_BUS_D0ENTRY");
 
 	if (ret)
 		goto exit;
@@ -3553,7 +3577,8 @@ static int hv_pci_query_relations(struct hv_device *hdev)
 	ret = vmbus_sendpacket(hdev->channel, &message, sizeof(message),
 			       0, VM_PKT_DATA_INBAND, 0);
 	if (!ret)
-		ret = wait_for_response(hdev, &comp);
+		ret = wait_for_response(hdev, &comp,
+					"PCI_QUERY_BUS_RELATIONS");
 
 	/*
 	 * In the case of fast device addition/removal, it's possible that
@@ -3644,7 +3669,8 @@ static int hv_send_resources_allocated(struct hv_device *hdev)
 				VM_PKT_DATA_INBAND,
 				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 		if (!ret)
-			ret = wait_for_response(hdev, &comp_pkt.host_event);
+			ret = wait_for_response(hdev, &comp_pkt.host_event,
+						"PCI_RESOURCE_ASSIGNED");
 		if (ret)
 			break;
 
@@ -4155,6 +4181,9 @@ static struct hv_driver hv_pci_drv = {
 	.remove		= hv_pci_remove,
 	.suspend	= hv_pci_suspend,
 	.resume		= hv_pci_resume,
+	.driver = {
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+	},
 };
 
 static void __exit exit_hv_pci_drv(void)
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index d8dcd238fda1..732f75a31760 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -428,7 +428,8 @@ void pci_aer_init(struct pci_dev *dev)
 	 * Advisory Non-Fatal Errors are masked by default (PCIe r7.0, sec
 	 * 7.8.4.6).
 	 */
-	if (pcie_aer_is_native(dev) && dev->devcap & PCI_EXP_DEVCAP_RBER)
+	if (pcie_aer_is_native(dev) && dev->devcap & PCI_EXP_DEVCAP_RBER &&
+	    !dev->no_aer_anfe)
 		pci_clear_and_set_config_dword(dev,
 					       dev->aer_cap + PCI_ERR_COR_MASK,
 					       PCI_ERR_COR_ADV_NFAT, 0);
@@ -1360,8 +1361,10 @@ static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry,
 
 static void aer_recover_work_func(struct work_struct *work)
 {
+	struct aer_capability_regs *regs;
 	struct aer_recover_entry entry;
 	struct pci_dev *pdev;
+	u32 err;
 
 	while (kfifo_get(&aer_recover_ring, &entry)) {
 		pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus,
@@ -1375,6 +1378,12 @@ static void aer_recover_work_func(struct work_struct *work)
 		}
 		pci_print_aer(pdev, entry.severity, entry.regs);
 
+		regs = entry.regs;
+		if (entry.severity == AER_CORRECTABLE)
+			err = regs->cor_status & ~regs->cor_mask;
+		else
+			err = regs->uncor_status & ~regs->uncor_mask;
+
 		/*
 		 * Memory for aer_capability_regs(entry.regs) is being
 		 * allocated from the ghes_estatus_pool to protect it from
@@ -1385,12 +1394,14 @@ static void aer_recover_work_func(struct work_struct *work)
 		ghes_estatus_pool_region_free((unsigned long)entry.regs,
 					    sizeof(struct aer_capability_regs));
 
-		if (entry.severity == AER_NONFATAL)
-			pcie_do_recovery(pdev, pci_channel_io_normal,
-					 aer_root_reset);
-		else if (entry.severity == AER_FATAL)
-			pcie_do_recovery(pdev, pci_channel_io_frozen,
-					 aer_root_reset);
+		if (err) {
+			if (entry.severity == AER_NONFATAL)
+				pcie_do_recovery(pdev, pci_channel_io_normal,
+						 aer_root_reset);
+			else if (entry.severity == AER_FATAL)
+				pcie_do_recovery(pdev, pci_channel_io_frozen,
+						 aer_root_reset);
+		}
 		pci_dev_put(pdev);
 	}
 }
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index de9bbccda21f..677cd8797d19 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2575,6 +2575,17 @@ static void quirk_p64h2_1k_io(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1460, quirk_p64h2_1k_io);
 
 /*
+ * Unmasking Advisory Non-Fatal Errors on the Apple T2 Secure Enclave
+ * causes a MacBookPro16,1 to lose power.  Set this before pci_aer_init()
+ * so that it leaves the ANFE mask bit unchanged.
+ */
+static void quirk_no_aer_anfe(struct pci_dev *dev)
+{
+	dev->no_aer_anfe = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_APPLE, 0x1802, quirk_no_aer_anfe);
+
+/*
  * Under some circumstances, AER is not linked with extended capabilities.
  * Force it to be linked by setting the corresponding control bit in the
  * config space.
diff --git a/drivers/pmdomain/imx/imx8m-blk-ctrl.c b/drivers/pmdomain/imx/imx8m-blk-ctrl.c
index 479789009c7f..f8105e87ea3c 100644
--- a/drivers/pmdomain/imx/imx8m-blk-ctrl.c
+++ b/drivers/pmdomain/imx/imx8m-blk-ctrl.c
@@ -15,6 +15,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/clk.h>
+#include <linux/mutex.h>
 
 #include <dt-bindings/power/imx8mm-power.h>
 #include <dt-bindings/power/imx8mn-power.h>
@@ -34,6 +35,12 @@ struct imx8m_blk_ctrl {
 	struct regmap *regmap;
 	struct imx8m_blk_ctrl_domain *domains;
 	struct genpd_onecell_data onecell_data;
+	/*
+	 * Serializes the blk-ctrl reset/clock sequence across sibling domains;
+	 * their transitions interact through the shared VPUMIX bus domain,
+	 * VPU_NOC and the not-ack-verified ADB400 handshake (ERR050531).
+	 */
+	struct mutex power_lock;
 };
 
 struct imx8m_blk_ctrl_domain_data {
@@ -98,6 +105,8 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd)
 	struct imx8m_blk_ctrl *bc = domain->bc;
 	int ret;
 
+	guard(mutex)(&bc->power_lock);
+
 	/* make sure bus domain is awake */
 	ret = pm_runtime_get_sync(bc->bus_power_dev);
 	if (ret < 0) {
@@ -164,6 +173,8 @@ static int imx8m_blk_ctrl_power_off(struct generic_pm_domain *genpd)
 	const struct imx8m_blk_ctrl_domain_data *data = domain->data;
 	struct imx8m_blk_ctrl *bc = domain->bc;
 
+	guard(mutex)(&bc->power_lock);
+
 	/* put devices into reset and disable clocks */
 	if (data->mipi_phy_rst_mask)
 		regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask);
@@ -202,6 +213,10 @@ static int imx8m_blk_ctrl_probe(struct platform_device *pdev)
 
 	bc->dev = dev;
 
+	ret = devm_mutex_init(dev, &bc->power_lock);
+	if (ret)
+		return ret;
+
 	bc_data = of_device_get_match_data(dev);
 
 	base = devm_platform_ioremap_resource(pdev, 0);
diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c
index ba66ae719428..e193f978d5f3 100644
--- a/drivers/pmdomain/rockchip/pm-domains.c
+++ b/drivers/pmdomain/rockchip/pm-domains.c
@@ -759,7 +759,19 @@ static int rockchip_pd_attach_dev(struct generic_pm_domain *genpd,
 	}
 
 	i = 0;
-	while ((clk = of_clk_get(dev->of_node, i++)) && !IS_ERR(clk)) {
+	while (1) {
+		clk = of_clk_get(dev->of_node, i++);
+		if (IS_ERR(clk)) {
+			error = PTR_ERR(clk);
+			if (error == -ENOENT)
+				break;
+
+			dev_err(dev, "failed to get clock %d: %d\n", i - 1,
+				error);
+			pm_clk_destroy(dev);
+			return error;
+		}
+
 		dev_dbg(dev, "adding clock '%pC' to list of PM clocks\n", clk);
 		error = pm_clk_add_clk(dev, clk);
 		if (error) {
@@ -842,7 +854,7 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu,
 			dev_err(pmu->dev,
 				"%pOFn: failed to get clk at index %d: %d\n",
 				node, i, error);
-			return error;
+			goto err_put_clocks;
 		}
 	}
 
@@ -1018,7 +1030,9 @@ static int rockchip_pm_add_subdomain(struct rockchip_pmu *pmu,
 				parent_domain->name, child_domain->name);
 		}
 
-		rockchip_pm_add_subdomain(pmu, np);
+		error = rockchip_pm_add_subdomain(pmu, np);
+		if (error)
+			return error;
 	}
 
 	return 0;
diff --git a/drivers/power/supply/ds2780_battery.c b/drivers/power/supply/ds2780_battery.c
index 5b57bbba79d4..ef2446386c2a 100644
--- a/drivers/power/supply/ds2780_battery.c
+++ b/drivers/power/supply/ds2780_battery.c
@@ -304,7 +304,7 @@ static int ds2780_get_capacity(struct ds2780_device_info *dev_info,
 		return ret;
 
 	*capacity = raw;
-	return raw;
+	return 0;
 }
 
 static int ds2780_get_status(struct ds2780_device_info *dev_info, int *status)
diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c
index 185f55d2fd70..f11a5c794e7e 100644
--- a/drivers/power/supply/generic-adc-battery.c
+++ b/drivers/power/supply/generic-adc-battery.c
@@ -90,12 +90,17 @@ static int gab_read_channel(struct gab *adc_bat, enum gab_chan_type channel,
 	int ret;
 
 	ret = iio_read_channel_processed(adc_bat->channel[channel], result);
-	if (ret < 0)
+	if (ret < 0) {
 		dev_err(&adc_bat->psy->dev, "read channel error: %d\n", ret);
+		return ret;
+	}
+
+	if (channel == GAB_TEMP)
+		*result /= 100; /* Convert from milli- to deci-degree */
 	else
 		*result *= 1000;
 
-	return ret;
+	return 0;
 }
 
 static int gab_get_property(struct power_supply *psy,
diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c
index cbf3ac9c3e14..505a68c26463 100644
--- a/drivers/power/supply/max17042_battery.c
+++ b/drivers/power/supply/max17042_battery.c
@@ -1233,7 +1233,7 @@ static int max17042_parse_dt(struct max17042_chip *chip)
 	if (of_property_read_u32(np, "maxim,over-volt", &prop))
 		chip->vmax = INT_MAX;
 	else
-		chip->vmin = prop;
+		chip->vmax = prop;
 
 	return 0;
 }
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 47e307709e5e..1279785645fb 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1530,6 +1530,19 @@ void power_supply_external_power_changed(struct power_supply *psy)
 			!psy->desc->external_power_changed)
 		return;
 
+	/*
+	 * Keep power_supply_unregister() from returning, and thus from letting
+	 * the driver's data be freed, while the callback is running. The
+	 * ->removing check has to happen under the lock: on its own, just like
+	 * the use_cnt check above, it only tells us the supply was still there
+	 * when we looked, not that it still is by the time the callback
+	 * dereferences its driver data.
+	 */
+	guard(rwsem_read)(&psy->epc_sem);
+
+	if (psy->removing)
+		return;
+
 	psy->desc->external_power_changed(psy);
 }
 EXPORT_SYMBOL_GPL(power_supply_external_power_changed);
@@ -1774,6 +1787,7 @@ __power_supply_register(struct device *parent,
 	}
 
 	spin_lock_init(&psy->changed_lock);
+	init_rwsem(&psy->epc_sem);
 	init_rwsem(&psy->extensions_sem);
 	INIT_LIST_HEAD(&psy->extensions);
 
@@ -1914,7 +1928,17 @@ EXPORT_SYMBOL_GPL(devm_power_supply_register);
 void power_supply_unregister(struct power_supply *psy)
 {
 	WARN_ON(atomic_dec_return(&psy->use_cnt));
-	psy->removing = true;
+
+	/*
+	 * Publish ->removing so that no new ->external_power_changed() call can
+	 * start, and wait via semaphore for one that is already running: it may
+	 * be a supplier's changed_work, which cancel_work_sync() below does not
+	 * cover, and it may still dereference driver data that the caller is
+	 * about to free.
+	 */
+	scoped_guard(rwsem_write, &psy->epc_sem)
+		psy->removing = true;
+
 	cancel_work_sync(&psy->changed_work);
 	cancel_delayed_work_sync(&psy->deferred_register_work);
 	sysfs_remove_link(&psy->dev.kobj, "powers");
diff --git a/drivers/regulator/ltc3676.c b/drivers/regulator/ltc3676.c
index 307c6f7a155d..d67cee4e0be0 100644
--- a/drivers/regulator/ltc3676.c
+++ b/drivers/regulator/ltc3676.c
@@ -232,7 +232,7 @@ static const struct regulator_desc ltc3676_regulators[LTC3676_NUM_REGULATORS] =
 	LTC3676_FIXED_REG(LDO4, ldo4, LDOB, 2),
 };
 
-static bool ltc3676_readable_writeable_reg(struct device *dev, unsigned int reg)
+static bool ltc3676_writeable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case LTC3676_BUCK1 ... LTC3676_IRQSTAT:
@@ -243,6 +243,15 @@ static bool ltc3676_readable_writeable_reg(struct device *dev, unsigned int reg)
 	return false;
 }
 
+static bool ltc3676_readable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case LTC3676_BUCK1 ... LTC3676_IRQSTAT:
+		return true;
+	}
+	return false;
+}
+
 static bool ltc3676_volatile_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -255,8 +264,8 @@ static bool ltc3676_volatile_reg(struct device *dev, unsigned int reg)
 static const struct regmap_config ltc3676_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
-	.writeable_reg = ltc3676_readable_writeable_reg,
-	.readable_reg = ltc3676_readable_writeable_reg,
+	.writeable_reg = ltc3676_writeable_reg,
+	.readable_reg = ltc3676_readable_reg,
 	.volatile_reg = ltc3676_volatile_reg,
 	.max_register = LTC3676_CLIRQ,
 	.use_single_read = true,
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index c0cc6cc0afd8..09e26febfc83 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -929,21 +929,26 @@ static int is_supply_name(const char *name)
  * before returning to the caller, and @consumers will not be
  * changed.
  *
+ * On success the array is allocated here and handed to the caller, which
+ * owns it from then on: release the regulators with regulator_bulk_free()
+ * and free the array itself with kfree(). The supply names live in the
+ * same allocation, so they are gone once the array is freed.
+ *
  * Return: Number of regulators on success, or a negative error number
  *	   on failure.
  */
 int of_regulator_bulk_get_all(struct device *dev, struct device_node *np,
 			      struct regulator_bulk_data **consumers)
 {
-	int num_consumers = 0;
+	int num_consumers = 0, names_len = 0;
 	struct regulator *tmp;
 	struct regulator_bulk_data *_consumers = NULL;
 	struct property *prop;
+	char *names;
 	int i, n = 0, ret;
-	char name[64];
 
 	/*
-	 * first pass: get numbers of xxx-supply
+	 * first pass: get numbers of xxx-supply and the room their names take
 	 * second pass: fill consumers
 	 */
 restart:
@@ -953,16 +958,19 @@ restart:
 			continue;
 		if (!_consumers) {
 			num_consumers++;
+			names_len += i + 1;
 			continue;
 		} else {
-			memcpy(name, prop->name, i);
-			name[i] = '\0';
-			tmp = regulator_get(dev, name);
+			memcpy(names, prop->name, i);
+			names[i] = '\0';
+			tmp = regulator_get(dev, names);
 			if (IS_ERR(tmp)) {
 				ret = PTR_ERR(tmp);
 				goto error;
 			}
+			_consumers[n].supply = names;
 			_consumers[n].consumer = tmp;
+			names += i + 1;
 			n++;
 			continue;
 		}
@@ -973,9 +981,16 @@ restart:
 	}
 	if (num_consumers == 0)
 		return 0;
-	_consumers = kmalloc_objs(struct regulator_bulk_data, num_consumers);
+	/*
+	 * The supply names are kept in the same allocation as the array, so
+	 * that they share its lifetime and the caller has nothing extra to
+	 * free.
+	 */
+	_consumers = kzalloc(size_add(size_mul(num_consumers, sizeof(*_consumers)),
+				      names_len), GFP_KERNEL);
 	if (!_consumers)
 		return -ENOMEM;
+	names = (char *)(_consumers + num_consumers);
 	goto restart;
 
 error:
diff --git a/drivers/regulator/tps6594-regulator.c b/drivers/regulator/tps6594-regulator.c
index 31a5218d5510..503b89a2f5f8 100644
--- a/drivers/regulator/tps6594-regulator.c
+++ b/drivers/regulator/tps6594-regulator.c
@@ -241,21 +241,21 @@ static const struct regulator_desc tps65224_buck_regs[] = {
 			  TPS65224_MASK_BUCKS_VSET,
 			  TPS6594_REG_BUCKX_CTRL(1),
 			  TPS6594_BIT_BUCK_EN, 0, 0, tps65224_bucks_2_3_4_ranges,
-			  4, 0, 0, NULL, 0, 0),
+			  ARRAY_SIZE(tps65224_bucks_2_3_4_ranges), 0, 0, NULL, 0, 0),
 	TPS6594_REGULATOR("BUCK3", "buck3", TPS6594_BUCK_3,
 			  REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS65224_MASK_BUCKS_VSET,
 			  TPS6594_REG_BUCKX_VOUT_1(2),
 			  TPS65224_MASK_BUCKS_VSET,
 			  TPS6594_REG_BUCKX_CTRL(2),
 			  TPS6594_BIT_BUCK_EN, 0, 0, tps65224_bucks_2_3_4_ranges,
-			  4, 0, 0, NULL, 0, 0),
+			  ARRAY_SIZE(tps65224_bucks_2_3_4_ranges), 0, 0, NULL, 0, 0),
 	TPS6594_REGULATOR("BUCK4", "buck4", TPS6594_BUCK_4,
 			  REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS65224_MASK_BUCKS_VSET,
 			  TPS6594_REG_BUCKX_VOUT_1(3),
 			  TPS65224_MASK_BUCKS_VSET,
 			  TPS6594_REG_BUCKX_CTRL(3),
 			  TPS6594_BIT_BUCK_EN, 0, 0, tps65224_bucks_2_3_4_ranges,
-			  4, 0, 0, NULL, 0, 0),
+			  ARRAY_SIZE(tps65224_bucks_2_3_4_ranges), 0, 0, NULL, 0, 0),
 };
 
 static const struct tps6594_regulator_irq_type tps6594_buck1_irq_types[] = {
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 4010fdbf813c..c36539c83ed1 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -112,7 +112,6 @@ typedef struct {
 	int                 minor;
 	char                name[8];
 	struct scsi_device  *device;
-	struct scsi_device  **dt;        /* ptrs to data transfer elements */
 	u_int               firsts[CH_TYPES];
 	u_int               counts[CH_TYPES];
 	u_int		    voltags;
@@ -363,15 +362,10 @@ ch_readconfig(scsi_changer *ch)
 			vendor_labels[i]);
 	}
 
-	/* look up the devices of the data transfer elements */
-	ch->dt = kzalloc_objs(*ch->dt, ch->counts[CHET_DT]);
-
-	if (!ch->dt) {
-		kfree(buffer);
-		return -ENOMEM;
-	}
-
+	/* report the devices of the data transfer elements */
 	for (elem = 0; elem < ch->counts[CHET_DT]; elem++) {
+		struct scsi_device *sdev;
+
 		id  = -1;
 		lun = 0;
 		if (elem < CH_DT_MAX  &&  -1 != dt_id[elem]) {
@@ -387,10 +381,8 @@ ch_readconfig(scsi_changer *ch)
 			VPRINTK(KERN_INFO, "dt 0x%x: ",elem+ch->firsts[CHET_DT]);
 			if (data[6] & 0x80) {
 				VPRINTK(KERN_CONT, "not this SCSI bus\n");
-				ch->dt[elem] = NULL;
 			} else if (0 == (data[6] & 0x30)) {
 				VPRINTK(KERN_CONT, "ID/LUN unknown\n");
-				ch->dt[elem] = NULL;
 			} else {
 				id  = ch->device->id;
 				lun = 0;
@@ -400,18 +392,16 @@ ch_readconfig(scsi_changer *ch)
 		}
 		if (-1 != id) {
 			VPRINTK(KERN_CONT, "ID %i, LUN %i, ",id,lun);
-			ch->dt[elem] =
-				scsi_device_lookup(ch->device->host,
-						   ch->device->channel,
-						   id,lun);
-			if (!ch->dt[elem]) {
+			sdev = scsi_device_lookup(ch->device->host,
+						  ch->device->channel,
+						  id, lun);
+			if (!sdev) {
 				/* should not happen */
 				VPRINTK(KERN_CONT, "Huh? device not found!\n");
 			} else {
 				VPRINTK(KERN_CONT, "name: %8.8s %16.16s %4.4s\n",
-					ch->dt[elem]->vendor,
-					ch->dt[elem]->model,
-					ch->dt[elem]->rev);
+					sdev->vendor, sdev->model, sdev->rev);
+				scsi_device_put(sdev);
 			}
 		}
 	}
@@ -575,7 +565,6 @@ static void ch_destroy(struct kref *ref)
 	scsi_changer *ch = container_of(ref, scsi_changer, ref);
 
 	ch->device = NULL;
-	kfree(ch->dt);
 	kfree(ch);
 }
 
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 227ff7bd1bdc..f394fcbb97e7 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -2652,8 +2652,6 @@ retry_probe:
 	snprintf(host_buf, sizeof(host_buf), "host_%d", qedi->shost->host_no);
 	qedi_ops->common->set_name(qedi->cdev, host_buf);
 
-	qedi_ops->register_ops(qedi->cdev, &qedi_cb_ops, qedi);
-
 	memset(&params, 0, sizeof(params));
 	params.mtu = DEF_PATH_MTU + IPV6_HDR_LEN + TCP_HDR_LEN;
 	qedi->ll2_mtu = DEF_PATH_MTU;
@@ -2670,6 +2668,7 @@ retry_probe:
 		spin_lock_init(&qedi->task_idx_lock);
 		mutex_init(&qedi->stats_lock);
 	}
+	qedi_ops->register_ops(qedi->cdev, &qedi_cb_ops, qedi);
 	qedi_ops->ll2->register_cb_ops(qedi->cdev, &qedi_ll2_cb_ops, qedi);
 	qedi_ops->ll2->start(qedi->cdev, &params);
 
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index ecb0be394696..5a5f1a852cbe 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1056,8 +1056,7 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata,
 	 * care of polling the status register.
 	 */
 	if (cqspi->wr_completion) {
-		reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
-		reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+		reg = CQSPI_REG_WR_DISABLE_AUTO_POLL;
 		writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
 		/*
 		 * DAC mode require auto polling as flash needs to be polled
diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c
index 67d991dd249d..66cb58f95fdb 100644
--- a/drivers/spi/spi-nxp-fspi.c
+++ b/drivers/spi/spi-nxp-fspi.c
@@ -898,10 +898,10 @@ static int nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi,
 	dev_dbg(f->dev, "Target device [CS:%x] selected\n", spi_get_chipselect(spi, 0));
 
 	/*
-	 * Per the FlexSPI reference manual (initialization sequence), MCR0 and
-	 * the DLL control registers should be configured while the module is in
-	 * stop mode (MCR0[MDIS] = 1). Enter stop mode before reconfiguring the
-	 * RX sample clock source and the DLL, then exit stop mode afterwards.
+	 * Per the FlexSPI reference manual (initialization sequence), MCR0
+	 * should be configured while the module is in stop mode (MCR0[MDIS] = 1).
+	 * Enter stop mode before reconfiguring the RX sample clock source, then
+	 * exit stop mode afterwards.
 	 */
 	reg = fspi_readl(f, f->iobase + FSPI_MCR0);
 	fspi_writel(f, reg | FSPI_MCR0_MDIS, f->iobase + FSPI_MCR0);
@@ -937,6 +937,16 @@ static int nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi,
 		return ret;
 
 	/*
+	 * Exit stop mode before running the DLL calibration. The DLL
+	 * reference clock is derived from the module clock domain, which is
+	 * gated while MCR0[MDIS] = 1. Calibrating the DLL in stop mode leaves
+	 * the STS2 lock bits stuck at 0 (the DLL never runs), so clear MDIS
+	 * first and let the module and reference clock run.
+	 */
+	reg = fspi_readl(f, f->iobase + FSPI_MCR0);
+	fspi_writel(f, reg & ~FSPI_MCR0_MDIS, f->iobase + FSPI_MCR0);
+
+	/*
 	 * If clock rate > 100MHz, then switch from DLL override mode to
 	 * DLL calibration mode.
 	 */
@@ -945,10 +955,6 @@ static int nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi,
 	else
 		nxp_fspi_dll_override(f);
 
-	/* Exit stop mode now that MCR0 and the DLL have been reconfigured. */
-	reg = fspi_readl(f, f->iobase + FSPI_MCR0);
-	fspi_writel(f, reg & ~FSPI_MCR0_MDIS, f->iobase + FSPI_MCR0);
-
 	f->pre_op_rate = op->max_freq;
 
 	f->selected = spi_get_chipselect(spi, 0);
diff --git a/drivers/spi/spi-sg2044-nor.c b/drivers/spi/spi-sg2044-nor.c
index f3bcb8a1b92b..bc9a8ee9bce4 100644
--- a/drivers/spi/spi-sg2044-nor.c
+++ b/drivers/spi/spi-sg2044-nor.c
@@ -307,15 +307,15 @@ static ssize_t sg2044_spifmc_tran_cmd(struct sg2044_spifmc *spifmc,
 	return 0;
 }
 
-static void sg2044_spifmc_trans(struct sg2044_spifmc *spifmc,
-				const struct spi_mem_op *op)
+static int sg2044_spifmc_trans(struct sg2044_spifmc *spifmc,
+			       const struct spi_mem_op *op)
 {
 	if (op->data.dir == SPI_MEM_DATA_IN)
-		sg2044_spifmc_read(spifmc, op);
+		return sg2044_spifmc_read(spifmc, op);
 	else if (op->data.dir == SPI_MEM_DATA_OUT)
-		sg2044_spifmc_write(spifmc, op);
+		return sg2044_spifmc_write(spifmc, op);
 	else
-		sg2044_spifmc_tran_cmd(spifmc, op);
+		return sg2044_spifmc_tran_cmd(spifmc, op);
 }
 
 static ssize_t sg2044_spifmc_trans_reg(struct sg2044_spifmc *spifmc,
@@ -385,29 +385,64 @@ static ssize_t sg2044_spifmc_trans_reg(struct sg2044_spifmc *spifmc,
 	return 0;
 }
 
+static int sg2044_spifmc_set_speed(struct sg2044_spifmc *spifmc,
+				   unsigned int speed_hz)
+{
+	unsigned long rate = clk_get_rate(spifmc->clk);
+	u64 div;
+	u32 reg;
+
+	if (!rate)
+		return -EINVAL;
+
+	/* SCK = HCLK / (2 * (SckDiv + 1)); round down the resulting SCK. */
+	div = speed_hz ? DIV_ROUND_UP_ULL(rate, 2ULL * speed_hz) : 1;
+	if (div > SPIFMC_CTRL_SCK_DIV_MASK + 1)
+		return -EINVAL;
+
+	reg = readl(spifmc->io_base + SPIFMC_CTRL);
+	reg &= ~SPIFMC_CTRL_SCK_DIV_MASK;
+	reg |= div - 1;
+	writel(reg, spifmc->io_base + SPIFMC_CTRL);
+
+	return 0;
+}
+
 static int sg2044_spifmc_exec_op(struct spi_mem *mem,
 				 const struct spi_mem_op *op)
 {
 	struct sg2044_spifmc *spifmc;
+	int ret;
 
 	spifmc = spi_controller_get_devdata(mem->spi->controller);
 
 	mutex_lock(&spifmc->lock);
 
+	ret = sg2044_spifmc_set_speed(spifmc, op->max_freq ?
+				    min(op->max_freq, mem->spi->max_speed_hz) :
+				    mem->spi->max_speed_hz);
+	if (ret)
+		goto out_unlock;
+
 	if (op->addr.nbytes == 0)
-		sg2044_spifmc_trans_reg(spifmc, op);
+		ret = sg2044_spifmc_trans_reg(spifmc, op);
 	else
-		sg2044_spifmc_trans(spifmc, op);
+		ret = sg2044_spifmc_trans(spifmc, op);
 
+out_unlock:
 	mutex_unlock(&spifmc->lock);
 
-	return 0;
+	return ret;
 }
 
 static const struct spi_controller_mem_ops sg2044_spifmc_mem_ops = {
 	.exec_op = sg2044_spifmc_exec_op,
 };
 
+static const struct spi_controller_mem_caps sg2044_spifmc_mem_caps = {
+	.per_op_freq = true,
+};
+
 static void sg2044_spifmc_init(struct sg2044_spifmc *spifmc)
 {
 	u32 tran_csr;
@@ -447,6 +482,10 @@ static int sg2044_spifmc_probe(struct platform_device *pdev)
 	if (IS_ERR(spifmc->clk))
 		return dev_err_probe(dev, PTR_ERR(spifmc->clk), "Cannot get and enable AHB clock\n");
 
+	ctrl->max_speed_hz = clk_get_rate(spifmc->clk) / 2;
+	if (!ctrl->max_speed_hz)
+		return dev_err_probe(dev, -EINVAL, "Invalid AHB clock rate\n");
+
 	spifmc->dev = &pdev->dev;
 	spifmc->ctrl = ctrl;
 
@@ -458,6 +497,7 @@ static int sg2044_spifmc_probe(struct platform_device *pdev)
 	ctrl->bits_per_word_mask = SPI_BPW_MASK(8);
 	ctrl->auto_runtime_pm = false;
 	ctrl->mem_ops = &sg2044_spifmc_mem_ops;
+	ctrl->mem_caps = &sg2044_spifmc_mem_caps;
 	ctrl->mode_bits = SPI_RX_DUAL | SPI_TX_DUAL | SPI_RX_QUAD | SPI_TX_QUAD;
 
 	ret = devm_mutex_init(dev, &spifmc->lock);
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 8106d55f4041..df293b66350d 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -312,20 +312,24 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, struct cq_entry *cqe)
 		UFSHCD_NUM_RESERVED;
 }
 
+static void ufshcd_mcq_compl_cqe(struct ufs_hba *hba, struct cq_entry *cqe)
+{
+	int tag = ufshcd_mcq_get_tag(hba, cqe);
+
+	ufshcd_compl_one_cqe(hba, tag, cqe);
+	/* After processing the CQE, mark it as an empty (invalid) entry. */
+	cqe->command_desc_base_addr = 0;
+}
+
 static void ufshcd_mcq_process_cqe(struct ufs_hba *hba,
 				   struct ufs_hw_queue *hwq)
 {
 	struct cq_entry *cqe = ufshcd_mcq_cur_cqe(hwq);
 
-	if (cqe->command_desc_base_addr) {
-		int tag = ufshcd_mcq_get_tag(hba, cqe);
-
-		ufshcd_compl_one_cqe(hba, tag, cqe);
-		/* After processed the cqe, mark it empty (invalid) entry */
-		cqe->command_desc_base_addr = 0;
-	} else {
+	if (cqe->command_desc_base_addr)
+		ufshcd_mcq_compl_cqe(hba, cqe);
+	else
 		dev_err(hba->dev, "Abnormal CQ entry!\n");
-	}
 }
 
 /*
@@ -333,7 +337,7 @@ static void ufshcd_mcq_process_cqe(struct ufs_hba *hba,
  * controller disabled (HCE = 0). Reading host controller registers, e.g. the
  * CQ tail pointer (CQTPy), may not be safe with the host controller disabled.
  * Hence, iterate over all completion queue entries. This won't result in
- * double completions because ufshcd_mcq_process_cqe() clears a CQE after it
+ * double completions because ufshcd_mcq_compl_cqe() clears a CQE after it
  * has been processed.
  */
 void ufshcd_mcq_compl_all_cqes_lock(struct ufs_hba *hba,
@@ -344,13 +348,13 @@ void ufshcd_mcq_compl_all_cqes_lock(struct ufs_hba *hba,
 
 	spin_lock_irqsave(&hwq->cq_lock, flags);
 	while (entries > 0) {
-		ufshcd_mcq_process_cqe(hba, hwq);
+		struct cq_entry *cqe = ufshcd_mcq_cur_cqe(hwq);
+
+		if (cqe->command_desc_base_addr)
+			ufshcd_mcq_compl_cqe(hba, cqe);
 		ufshcd_mcq_inc_cq_head_slot(hwq);
 		entries--;
 	}
-
-	ufshcd_mcq_update_cq_tail_slot(hwq);
-	hwq->cq_head_slot = hwq->cq_tail_slot;
 	spin_unlock_irqrestore(&hwq->cq_lock, flags);
 }
 
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 54f4e7d7de02..ca8329052cbc 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6044,8 +6044,6 @@ static bool ufshcd_mcq_force_compl_one(struct request *rq, void *priv)
 	if (blk_mq_is_reserved_rq(rq) || !hwq)
 		return true;
 
-	ufshcd_mcq_compl_all_cqes_lock(hba, hwq);
-
 	/*
 	 * For those cmds of which the cqes are not present in the cq, complete
 	 * them explicitly.
@@ -6061,19 +6059,6 @@ static bool ufshcd_mcq_force_compl_one(struct request *rq, void *priv)
 	return true;
 }
 
-static bool ufshcd_mcq_compl_one(struct request *rq, void *priv)
-{
-	struct scsi_device *sdev = rq->q->queuedata;
-	struct Scsi_Host *shost = sdev->host;
-	struct ufs_hba *hba = shost_priv(shost);
-	struct ufs_hw_queue *hwq = ufshcd_mcq_req_to_hwq(hba, rq);
-
-	if (!blk_mq_is_reserved_rq(rq) && hwq)
-		ufshcd_mcq_poll_cqe_lock(hba, hwq);
-
-	return true;
-}
-
 /**
  * ufshcd_mcq_compl_pending_transfer - MCQ mode function. It is
  * invoked from the error handler context or ufshcd_host_reset_and_restore()
@@ -6088,10 +6073,18 @@ static bool ufshcd_mcq_compl_one(struct request *rq, void *priv)
 static void ufshcd_mcq_compl_pending_transfer(struct ufs_hba *hba,
 					      bool force_compl)
 {
-	blk_mq_tagset_busy_iter(&hba->host->tag_set,
-				force_compl ? ufshcd_mcq_force_compl_one :
-					      ufshcd_mcq_compl_one,
-				NULL);
+	int i;
+
+	for (i = 0; i < hba->nr_hw_queues; i++) {
+		if (force_compl)
+			ufshcd_mcq_compl_all_cqes_lock(hba, &hba->uhq[i]);
+		else
+			ufshcd_mcq_poll_cqe_lock(hba, &hba->uhq[i]);
+	}
+
+	if (force_compl)
+		blk_mq_tagset_busy_iter(&hba->host->tag_set,
+					ufshcd_mcq_force_compl_one, NULL);
 }
 
 /**
@@ -9556,6 +9549,7 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 	ret = ufshcd_add_lus(hba);
 
 out:
+	ufshcd_release(hba);
 	pm_runtime_put_sync(hba->dev);
 
 	if (ret)
@@ -11278,6 +11272,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	ufshcd_init_clk_gating(hba);
 
+	/* Released by ufshcd_async_scan(), or by out_release on failure. */
+	ufshcd_hold(hba);
+
 	ufshcd_init_clk_scaling(hba);
 
 	/*
@@ -11298,7 +11295,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	err = devm_request_irq(dev, irq, ufshcd_intr, IRQF_SHARED, UFSHCD, hba);
 	if (err) {
 		dev_err(hba->dev, "request irq failed\n");
-		goto out_disable;
+		goto out_release;
 	} else {
 		hba->is_irq_enabled = true;
 	}
@@ -11314,7 +11311,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		dev_err(hba->dev, "Host controller enable failed\n");
 		ufshcd_print_evt_hist(hba);
 		ufshcd_print_host_state(hba);
-		goto out_disable;
+		goto out_release;
 	}
 
 	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work, ufshcd_rpm_dev_flush_recheck_work);
@@ -11328,7 +11325,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	err = ufshcd_add_scsi_host(hba);
 	if (err)
-		goto out_disable;
+		goto out_release;
 
 	/* Hold auto suspend until async scan completes */
 	pm_runtime_get_sync(dev);
@@ -11348,7 +11345,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	err = ufshcd_link_startup(hba);
 	if (err)
-		goto out_disable;
+		goto out_release;
 
 	if (hba->mcq_enabled)
 		ufshcd_config_mcq(hba);
@@ -11365,23 +11362,23 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	/* Verify device initialization by sending NOP OUT UPIU */
 	err = ufshcd_verify_dev_init(hba);
 	if (err)
-		goto out_disable;
+		goto out_release;
 
 	/* Initiate UFS initialization, and waiting until completion */
 	err = ufshcd_complete_dev_init(hba);
 	if (err)
-		goto out_disable;
+		goto out_release;
 
 	err = ufshcd_device_params_init(hba);
 	if (err)
-		goto out_disable;
+		goto out_release;
 
 	err = ufshcd_post_device_init(hba);
 
 initialized:
 	ufshcd_process_probe_result(hba, probe_start, err);
 	if (err)
-		goto out_disable;
+		goto out_release;
 
 	ufs_sysfs_add_nodes(hba->dev);
 	hba->dme_qos_sysfs_handle = sysfs_get_dirent(hba->dev->kobj.sd,
@@ -11392,6 +11389,8 @@ initialized:
 	ufshcd_pm_qos_init(hba);
 	return 0;
 
+out_release:
+	ufshcd_release(hba);
 out_disable:
 	hba->is_irq_enabled = false;
 	ufshcd_hba_exit(hba);
diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c
index 814c1b7343b9..12a6d4138e44 100644
--- a/drivers/ufs/host/ufs-mediatek.c
+++ b/drivers/ufs/host/ufs-mediatek.c
@@ -509,6 +509,7 @@ static int ufs_mtk_mphy_power_on(struct ufs_hba *hba, bool on)
 	struct ufs_mtk_host *host = ufshcd_get_variant(hba);
 	struct phy *mphy = host->mphy;
 	struct arm_smccc_res res;
+	int err;
 	int ret = 0;
 
 	if (!mphy || !(on ^ host->mphy_powered_on))
@@ -523,7 +524,18 @@ static int ufs_mtk_mphy_power_on(struct ufs_hba *hba, bool on)
 			usleep_range(200, 210);
 			ufs_mtk_va09_pwr_ctrl(res, 1);
 		}
-		phy_power_on(mphy);
+		ret = phy_power_on(mphy);
+		if (ret) {
+			if (ufs_mtk_is_va09_supported(hba)) {
+				ufs_mtk_va09_pwr_ctrl(res, 0);
+				err = regulator_disable(host->reg_va09);
+				if (err)
+					dev_err(hba->dev,
+						"failed to unwind va09: %d\n", err);
+			}
+			dev_err(hba->dev, "failed to enable mphy: %d\n", ret);
+			return ret;
+		}
 	} else {
 		phy_power_off(mphy);
 		if (ufs_mtk_is_va09_supported(hba)) {
@@ -1295,7 +1307,9 @@ static int ufs_mtk_init(struct ufs_hba *hba)
 	 *
 	 * Enable phy clocks specifically here.
 	 */
-	ufs_mtk_mphy_power_on(hba, true);
+	err = ufs_mtk_mphy_power_on(hba, true);
+	if (err)
+		goto out_variant_clear;
 
 	if (ufs_mtk_is_rtff_mtcmos(hba)) {
 		/* First Restore here, to avoid backup unexpected value */
diff --git a/fs/dcache.c b/fs/dcache.c
index a66be85f9d01..f44c7b39c3b3 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1583,6 +1583,8 @@ EXPORT_SYMBOL(path_has_submounts);
  *
  * Only one of d_invalidate() and d_set_mounted() must succeed.  For
  * this reason take rename_lock and d_lock on dentry and ancestors.
+ * Likewise for dont_mount() which marks a dentry that is being removed
+ * under d_lock.
  */
 int d_set_mounted(struct dentry *dentry)
 {
@@ -1599,7 +1601,7 @@ int d_set_mounted(struct dentry *dentry)
 		spin_unlock(&p->d_lock);
 	}
 	spin_lock(&dentry->d_lock);
-	if (!d_unlinked(dentry)) {
+	if (!d_unlinked(dentry) && !cant_mount(dentry)) {
 		ret = -EBUSY;
 		if (!d_mountpoint(dentry)) {
 			dentry->d_flags |= DCACHE_MOUNTED;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index c158f082f1da..9b71bc9d71d1 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -372,6 +372,9 @@ static long fcntl_set_rw_hint(struct file *file, unsigned long arg)
 	u64 __user *argp = (u64 __user *)arg;
 	u64 hint;
 
+	/* nothing is ever written to it */
+	if (IS_IMMUTABLE(inode))
+		return -EPERM;
 	if (!inode_owner_or_capable(file_mnt_idmap(file), inode))
 		return -EPERM;
 
diff --git a/fs/fhandle.c b/fs/fhandle.c
index f8829231e3d7..d22f2e065677 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -298,6 +298,22 @@ static bool capable_wrt_mount(struct mount *mount)
 	return mnt_ns && ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN);
 }
 
+/*
+ * Does the caller have an unobstructed way to everything below @root? Only
+ * if the mount is mounted, the caller is privileged over its mount namespace
+ * and no locked child covers something below @root->dentry. One answer from
+ * under mount_lock: an umount in between clears ->mnt_ns and takes the
+ * children off the mount, the locked ones too.
+ */
+static bool subtree_unobstructed(const struct path *root)
+{
+	struct mount *mnt = real_mount(root->mnt);
+
+	guard(mount_locked_reader)();
+	return is_mounted(root->mnt) && capable_wrt_mount(mnt) &&
+	       !has_locked_children(mnt, root->dentry);
+}
+
 static inline int may_decode_fh(struct handle_to_path_ctx *ctx,
 				unsigned int o_flags)
 {
@@ -332,9 +348,7 @@ static inline int may_decode_fh(struct handle_to_path_ctx *ctx,
 
 	if (ns_capable(root->mnt->mnt_sb->s_user_ns, CAP_SYS_ADMIN))
 		ctx->flags = HANDLE_CHECK_PERMS;
-	else if (is_mounted(root->mnt) &&
-		 capable_wrt_mount(real_mount(root->mnt)) &&
-		 !has_locked_children(real_mount(root->mnt), root->dentry))
+	else if (subtree_unobstructed(root))
 		ctx->flags = HANDLE_CHECK_PERMS | HANDLE_CHECK_SUBTREE;
 	else
 		return -EPERM;
diff --git a/fs/file_table.c b/fs/file_table.c
index c68b8c0a4097..e2665eaa6f8c 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -520,7 +520,8 @@ static void __fput(struct file *file)
 	dput(dentry);
 	if (unlikely(mode & FMODE_NEED_UNMOUNT))
 		dissolve_on_fput(mnt);
-	mntput(mnt);
+	else
+		mntput(mnt);
 out:
 	file_free(file);
 }
diff --git a/fs/fs_context.c b/fs/fs_context.c
index 23ad66cd94e1..a50584df97be 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -315,6 +315,10 @@ struct fs_context *fs_context_for_reconfigure(struct dentry *dentry,
 					unsigned int sb_flags,
 					unsigned int sb_flags_mask)
 {
+	/* kernel-internal superblocks are nobody's to reconfigure */
+	if (dentry->d_sb->s_flags & SB_NOUSER)
+		return ERR_PTR(-EINVAL);
+
 	return alloc_fs_context(dentry->d_sb->s_type, dentry, sb_flags,
 				sb_flags_mask, FS_CONTEXT_FOR_RECONFIGURE);
 }
diff --git a/fs/mount.h b/fs/mount.h
index 94fcc306d21e..4d23cade9f6c 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -6,6 +6,8 @@
 #include <linux/fs_pin.h>
 
 extern struct file_system_type nullfs_fs_type;
+extern struct dentry *nullfs_new_file(struct super_block *sb);
+extern struct vfsmount *knullfs;
 extern struct list_head notify_list;
 
 struct mnt_namespace {
@@ -33,16 +35,20 @@ struct mnt_namespace {
 } __randomize_layout;
 
 struct mnt_pcp {
-	int mnt_count;
+	unsigned int mnt_gets;
+	unsigned int mnt_puts;
 	int mnt_writers;
 };
 
 struct mountpoint {
 	struct hlist_node m_hash;
 	struct dentry *m_dentry;
-	struct hlist_head m_list;
+	struct hlist_head m_list;	/* mounts on it and pins */
+	struct hlist_head m_covers;	/* covers of unmounted parents */
 };
 
+struct mnt_cover;
+
 struct mount {
 	struct hlist_node mnt_hash;
 	struct mount *mnt_parent;
@@ -84,7 +90,7 @@ struct mount {
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	union {
 		struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
-		struct hlist_node mnt_umount;
+		struct hlist_node mnt_umount;	/* on the unmounted list */
 	};
 #ifdef CONFIG_FSNOTIFY
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
@@ -98,7 +104,8 @@ struct mount {
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
-	struct hlist_head mnt_stuck_children;
+	struct mnt_cover *mnt_cover;	/* the one it may leave behind */
+	struct hlist_head mnt_covers;	/* left behind by its unmounted children */
 	struct hlist_node mnt_ns_visible; /* link in ns->mnt_visible_mounts */
 	struct mount *overmount;	/* mounted on ->mnt_root */
 } __randomize_layout;
@@ -233,6 +240,9 @@ static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
 #ifdef CONFIG_FSNOTIFY
 static inline void mnt_notify_add(struct mount *m)
 {
+	/* queued already under this namespace_sem hold */
+	if (!list_empty(&m->to_notify))
+		return;
 	/* Optimize the case where there are no watches */
 	if ((m->mnt_ns && m->mnt_ns->n_fsnotify_marks) ||
 	    (m->prev_ns && m->prev_ns->n_fsnotify_marks))
diff --git a/fs/namei.c b/fs/namei.c
index 20a6534ea3ef..c87c14ee1a25 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2087,6 +2087,33 @@ all_done: // pure jump
 }
 
 /*
+ * Be careful in case the dentry is unlinked or renamed. Any mounts
+ * stacked on top of it are going away. We need to make sure that we
+ * don't reveal the underyling dentry during refwalk. In rcuwalk we
+ * catch this via d_seq and another lookup for the name. Give the same
+ * guarantee in refwalk.
+ */
+static bool unlink_may_reveal(struct nameidata *nd, int flags,
+			      struct path *path, struct dentry *dentry)
+{
+	/* ".." and LOOKUP_DOWN may land on an unhashed directory */
+	if (flags & WALK_NOFOLLOW)
+		return false;
+	if (nd->flags & LOOKUP_REVAL)
+		return false;
+	/* We crossed onto a mount and the name led us here while it still existed */
+	if (path->mnt != nd->path.mnt)
+		return false;
+	/* only a name on its way out is flagged */
+	if (likely(!cant_mount(dentry)))
+		return false;
+	if (!d_unlinked(dentry))
+		return false;
+	dput(no_free_ptr(path->dentry));
+	return true;
+}
+
+/*
  * Do we need to follow links? We _really_ want to be able
  * to do this check without having to look at inode->i_op,
  * so we keep a cache of "no, this doesn't need follow_link"
@@ -2115,6 +2142,8 @@ static noinline const char *step_into_slowpath(struct nameidata *nd, int flags,
 			if (unlikely(!inode))
 				return ERR_PTR(-ENOENT);
 		} else {
+			if (unlikely(unlink_may_reveal(nd, flags, &path, dentry)))
+				return ERR_PTR(-ESTALE);
 			dput(nd->path.dentry);
 			if (nd->path.mnt != path.mnt)
 				mntput(nd->path.mnt);
diff --git a/fs/namespace.c b/fs/namespace.c
index 580877e46b1a..3ed3766f3a18 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -80,6 +80,8 @@ static u64 mnt_id_ctr = MNT_UNIQUE_ID_OFFSET;
 static struct hlist_head *mount_hashtable __ro_after_init;
 static struct hlist_head *mountpoint_hashtable __ro_after_init;
 static struct kmem_cache *mnt_cache __ro_after_init;
+struct vfsmount *knullfs __ro_after_init;	/* private nullfs instance */
+static struct vfsmount *knullfs_file __ro_after_init;	/* its regular file */
 static DECLARE_RWSEM(namespace_sem);
 static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
@@ -130,7 +132,6 @@ static void mnt_ns_release(struct mnt_namespace *ns)
 {
 	/* keep alive for {list,stat}mount() */
 	if (ns && refcount_dec_and_test(&ns->passive)) {
-		fsnotify_mntns_delete(ns);
 		put_user_ns(ns->user_ns);
 		kfree(ns);
 	}
@@ -210,6 +211,19 @@ static inline struct hlist_head *mp_hash(struct dentry *dentry)
 	return &mountpoint_hashtable[tmp & mp_hash_mask];
 }
 
+/*
+ * What an unmounted mount leaves behind at its unmounted parent instead of
+ * staying attached to it. A lookup on the parent at the mountpoint finds
+ * a stand-in for as long as the cover is there. The parent frees it.
+ */
+struct mnt_cover {
+	struct hlist_node node;		/* parent->mnt_covers, RCU */
+	struct hlist_node pin;		/* mp->m_covers, keeps the mountpoint */
+	struct dentry *dentry;
+	struct mountpoint *mp;
+	struct rcu_head rcu;
+};
+
 static int mnt_alloc_id(struct mount *mnt)
 {
 	int res;
@@ -249,16 +263,24 @@ void mnt_release_group_id(struct mount *mnt)
 	mnt->mnt_group_id = 0;
 }
 
-/*
- * vfsmount lock must be held for read
- */
-static inline void mnt_add_count(struct mount *mnt, int n)
+static inline void mnt_inc_count(struct mount *mnt)
+{
+#ifdef CONFIG_SMP
+	this_cpu_inc(mnt->mnt_pcp->mnt_gets);
+#else
+	preempt_disable();
+	mnt->mnt_count++;
+	preempt_enable();
+#endif
+}
+
+static inline void mnt_dec_count(struct mount *mnt)
 {
 #ifdef CONFIG_SMP
-	this_cpu_add(mnt->mnt_pcp->mnt_count, n);
+	this_cpu_inc(mnt->mnt_pcp->mnt_puts);
 #else
 	preempt_disable();
-	mnt->mnt_count += n;
+	mnt->mnt_count--;
 	preempt_enable();
 #endif
 }
@@ -269,14 +291,17 @@ static inline void mnt_add_count(struct mount *mnt, int n)
 int mnt_get_count(struct mount *mnt)
 {
 #ifdef CONFIG_SMP
-	int count = 0;
+	unsigned int gets = 0, puts = 0;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
-		count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count;
-	}
+	/* puts first, so a put counted here has its get counted below */
+	for_each_possible_cpu(cpu)
+		puts += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_puts;
+	smp_mb();	/* pairs with the smp_wmb() in mntput_no_expire() */
+	for_each_possible_cpu(cpu)
+		gets += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_gets;
 
-	return count;
+	return gets - puts;
 #else
 	return mnt->mnt_count;
 #endif
@@ -288,6 +313,10 @@ static struct mount *alloc_vfsmnt(const char *name)
 	if (mnt) {
 		int err;
 
+		mnt->mnt_cover = kzalloc_obj(struct mnt_cover, GFP_KERNEL_ACCOUNT);
+		if (!mnt->mnt_cover)
+			goto out_free_cache;
+
 		err = mnt_alloc_id(mnt);
 		if (err)
 			goto out_free_cache;
@@ -305,7 +334,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		if (!mnt->mnt_pcp)
 			goto out_free_devname;
 
-		this_cpu_add(mnt->mnt_pcp->mnt_count, 1);
+		this_cpu_inc(mnt->mnt_pcp->mnt_gets);
 #else
 		mnt->mnt_count = 1;
 		mnt->mnt_writers = 0;
@@ -320,8 +349,11 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_HLIST_HEAD(&mnt->mnt_slave_list);
 		INIT_HLIST_NODE(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-		INIT_HLIST_HEAD(&mnt->mnt_stuck_children);
+		INIT_HLIST_HEAD(&mnt->mnt_covers);
 		INIT_HLIST_NODE(&mnt->mnt_ns_visible);
+#ifdef CONFIG_FSNOTIFY
+		INIT_LIST_HEAD(&mnt->to_notify);
+#endif
 		RB_CLEAR_NODE(&mnt->mnt_node);
 		mnt->mnt.mnt_idmap = &nop_mnt_idmap;
 	}
@@ -334,6 +366,7 @@ out_free_devname:
 out_free_id:
 	mnt_free_id(mnt);
 out_free_cache:
+	kfree(mnt->mnt_cover);
 	kmem_cache_free(mnt_cache, mnt);
 	return NULL;
 }
@@ -725,6 +758,8 @@ int sb_prepare_remount_readonly(struct super_block *sb)
 static void free_vfsmnt(struct mount *mnt)
 {
 	mnt_idmap_put(mnt_idmap(&mnt->mnt));
+	/* NULL if it left it behind */
+	kfree(mnt->mnt_cover);
 	kfree_const(mnt->mnt_devname);
 #ifdef CONFIG_SMP
 	free_percpu(mnt->mnt_pcp);
@@ -746,13 +781,13 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 	if (bastard == NULL)
 		return 0;
 	mnt = real_mount(bastard);
-	mnt_add_count(mnt, 1);
-	smp_mb();		// see mntput_no_expire() and do_umount()
+	mnt_inc_count(mnt);
+	smp_mb();	/* see mntput_no_expire_slowpath() and do_umount() */
 	if (likely(!read_seqretry(&mount_lock, seq)))
 		return 0;
 	lock_mount_hash();
 	if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) {
-		mnt_add_count(mnt, -1);
+		mnt_dec_count(mnt);
 		unlock_mount_hash();
 		return 1;
 	}
@@ -781,20 +816,31 @@ static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
  * @dentry:	dentry of mountpoint
  *
  * If @mnt has a child mount @c mounted on @dentry find and return it.
+ * If @mnt is unmounted and a child that was unmounted with it left its
+ * cover behind at @dentry, return the stand-in for it instead: knullfs
+ * for a directory, its regular file for anything else.
  * Caller must either hold the spinlock component of @mount_lock or
  * hold rcu_read_lock(), sample the seqcount component before the call
  * and recheck it afterwards.
  *
- * Return: The child of @mnt mounted on @dentry or %NULL.
+ * Return: The child of @mnt mounted on @dentry, a stand-in or %NULL.
  */
 struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct hlist_head *head = m_hash(mnt, dentry);
+	struct mnt_cover *cover;
 	struct mount *p;
 
 	hlist_for_each_entry_rcu(p, head, mnt_hash)
 		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
 			return p;
+	/* an unmounted mount keeps the covers its unmounted children left */
+	/* a lockless caller rechecks mount_lock after a miss, a stale flag is harmless */
+	if (unlikely(data_race(mnt->mnt_flags) & MNT_UMOUNT)) {
+		hlist_for_each_entry_rcu(cover, &real_mount(mnt)->mnt_covers, node)
+			if (cover->dentry == dentry)
+				return real_mount(d_is_dir(dentry) ? knullfs : knullfs_file);
+	}
 	return NULL;
 }
 
@@ -910,6 +956,7 @@ mountpoint:
 	mp->m_dentry = dget(dentry);
 	hlist_add_head(&mp->m_hash, mp_hash(dentry));
 	INIT_HLIST_HEAD(&mp->m_list);
+	INIT_HLIST_HEAD(&mp->m_covers);
 	hlist_add_head(&m->node, &mp->m_list);
 	m->mp = no_free_ptr(mp);
 	read_sequnlock_excl(&mount_lock);
@@ -922,7 +969,7 @@ mountpoint:
  */
 static void maybe_free_mountpoint(struct mountpoint *mp, struct list_head *list)
 {
-	if (hlist_empty(&mp->m_list)) {
+	if (hlist_empty(&mp->m_list) && hlist_empty(&mp->m_covers)) {
 		struct dentry *dentry = mp->m_dentry;
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
@@ -1010,6 +1057,36 @@ static void umount_mnt(struct mount *mnt)
 }
 
 /*
+ * @mnt is unmounted together with its parent and would have stayed attached
+ * to it. Leave its cover behind before it is detached so that a lookup on the
+ * parent at the mountpoint keeps finding a mount instead of what @mnt covered.
+ *
+ * locks: mount_lock[write_seqlock]
+ */
+static void leave_cover(struct mount *mnt)
+{
+	struct mnt_cover *cover = mnt->mnt_cover;
+
+	mnt->mnt_cover = NULL;
+	cover->dentry = mnt->mnt_mountpoint;
+	cover->mp = mnt->mnt_mp;
+	/* keeps the mountpoint once @mnt has let go of it */
+	hlist_add_head(&cover->pin, &cover->mp->m_covers);
+	hlist_add_head_rcu(&cover->node, &mnt->mnt_parent->mnt_covers);
+}
+
+/*
+ * locks: mount_lock[write_seqlock]
+ */
+static void drop_cover(struct mnt_cover *cover, struct list_head *shrink_list)
+{
+	hlist_del_rcu(&cover->node);
+	hlist_del(&cover->pin);
+	maybe_free_mountpoint(cover->mp, shrink_list);
+	kfree_rcu(cover, rcu);
+}
+
+/*
  * vfsmount lock must be held for write
  */
 void mnt_set_mountpoint(struct mount *mnt,
@@ -1058,7 +1135,10 @@ static void attach_mnt(struct mount *mnt, struct mount *parent,
 void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
 	struct mountpoint *old_mp = mnt->mnt_mp;
+	struct mount *old_parent = mnt->mnt_parent;
 
+	if (old_parent->overmount == mnt)
+		old_parent->overmount = NULL;
 	list_del_init(&mnt->mnt_child);
 	hlist_del_init(&mnt->mnt_mp_list);
 	hlist_del_init_rcu(&mnt->mnt_hash);
@@ -1254,6 +1334,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 
 	mnt->mnt.mnt_flags = READ_ONCE(old->mnt.mnt_flags) &
 			     ~MNT_INTERNAL_FLAGS;
+	mnt->mnt_t_flags = old->mnt_t_flags & T_UNBINDABLE;
 
 	if (flag & (CL_SLAVE | CL_PRIVATE))
 		mnt->mnt_group_id = 0; /* not a peer of original */
@@ -1296,8 +1377,6 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 
 static void cleanup_mnt(struct mount *mnt)
 {
-	struct hlist_node *p;
-	struct mount *m;
 	/*
 	 * The warning here probably indicates that somebody messed
 	 * up a mnt_want/drop_write() pair.  If this happens, the
@@ -1308,10 +1387,6 @@ static void cleanup_mnt(struct mount *mnt)
 	WARN_ON(mnt_get_writers(mnt));
 	if (unlikely(mnt->mnt_pins.first))
 		mnt_pin_kill(mnt);
-	hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) {
-		hlist_del(&m->mnt_umount);
-		mntput(&m->mnt);
-	}
 	fsnotify_vfsmount_delete(&mnt->mnt);
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
@@ -1337,6 +1412,8 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
 
 static void noinline mntput_no_expire_slowpath(struct mount *mnt)
 {
+	struct mnt_cover *cover;
+	struct hlist_node *n;
 	LIST_HEAD(list);
 	int count;
 
@@ -1347,7 +1424,7 @@ static void noinline mntput_no_expire_slowpath(struct mount *mnt)
 	 * mount_lock, we'll see their refcount increment here.
 	 */
 	smp_mb();
-	mnt_add_count(mnt, -1);
+	mnt_dec_count(mnt);
 	count = mnt_get_count(mnt);
 	if (count != 0) {
 		WARN_ON(count < 0);
@@ -1367,13 +1444,10 @@ static void noinline mntput_no_expire_slowpath(struct mount *mnt)
 	if (unlikely(!list_empty(&mnt->mnt_expire)))
 		list_del(&mnt->mnt_expire);
 
-	if (unlikely(!list_empty(&mnt->mnt_mounts))) {
-		struct mount *p, *tmp;
-		list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts,  mnt_child) {
-			__umount_mnt(p, &list);
-			hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children);
-		}
-	}
+	/* nothing stays attached to an unmounted mount */
+	VFS_WARN_ON_ONCE(!list_empty(&mnt->mnt_mounts));
+	hlist_for_each_entry_safe(cover, n, &mnt->mnt_covers, node)
+		drop_cover(cover, &list);
 	unlock_mount_hash();
 	shrink_dentry_list(&list);
 
@@ -1404,7 +1478,8 @@ static void mntput_no_expire(struct mount *mnt)
 		 * non-NULL under rcu_read_lock(), the reference
 		 * we are dropping is not the final one.
 		 */
-		mnt_add_count(mnt, -1);
+		smp_wmb();	/* pairs with the smp_mb() in mnt_get_count() */
+		mnt_dec_count(mnt);
 		rcu_read_unlock();
 		return;
 	}
@@ -1426,7 +1501,7 @@ EXPORT_SYMBOL(mntput);
 struct vfsmount *mntget(struct vfsmount *mnt)
 {
 	if (mnt)
-		mnt_add_count(real_mount(mnt), 1);
+		mnt_inc_count(real_mount(mnt));
 	return mnt;
 }
 EXPORT_SYMBOL(mntget);
@@ -1737,36 +1812,17 @@ static inline void namespace_lock(void)
 enum umount_tree_flags {
 	UMOUNT_SYNC = 1,
 	UMOUNT_PROPAGATE = 2,
-	UMOUNT_CONNECTED = 4,
+	UMOUNT_COVER = 4,
 };
 
-static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how)
+/* Do we need to leave the mountpoint on the parent covered? */
+static bool needs_cover(struct mount *mnt, enum umount_tree_flags how)
 {
-	/* Leaving mounts connected is only valid for lazy umounts */
 	if (how & UMOUNT_SYNC)
-		return true;
-
-	/* A mount without a parent has nothing to be connected to */
-	if (!mnt_has_parent(mnt))
-		return true;
-
-	/* Because the reference counting rules change when mounts are
-	 * unmounted and connected, umounted mounts may not be
-	 * connected to mounted mounts.
-	 */
-	if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT))
-		return true;
-
-	/* Has it been requested that the mount remain connected? */
-	if (how & UMOUNT_CONNECTED)
 		return false;
-
-	/* Is the mount locked such that it needs to remain connected? */
-	if (IS_MNT_LOCKED(mnt))
+	if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT))
 		return false;
-
-	/* By default disconnect the mount */
-	return true;
+	return (how & UMOUNT_COVER) || IS_MNT_LOCKED(mnt);
 }
 
 /*
@@ -1783,6 +1839,8 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 
 	/* Gather the mounts to umount */
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
+		/* A mount is unmounted once. */
+		VFS_WARN_ON_ONCE(p->mnt.mnt_flags & MNT_UMOUNT);
 		p->mnt.mnt_flags |= MNT_UMOUNT;
 		if (mnt_ns_attached(p))
 			move_from_ns(p);
@@ -1802,7 +1860,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 
 	while (!list_empty(&tmp_list)) {
 		struct mnt_namespace *ns;
-		bool disconnect;
 		p = list_first_entry(&tmp_list, struct mount, mnt_list);
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
@@ -1815,17 +1872,12 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		if (how & UMOUNT_SYNC)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 
-		disconnect = disconnect_mount(p, how);
 		if (mnt_has_parent(p)) {
-			if (!disconnect) {
-				/* Don't forget about p */
-				list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts);
-			} else {
-				umount_mnt(p);
-			}
+			if (needs_cover(p, how))
+				leave_cover(p);
+			umount_mnt(p);
 		}
-		if (disconnect)
-			hlist_add_head(&p->mnt_umount, &unmounted);
+		hlist_add_head(&p->mnt_umount, &unmounted);
 
 		/*
 		 * At this point p->mnt_ns is NULL, notification will be queued
@@ -1976,11 +2028,16 @@ out:
  * detach_mounts allows lazily unmounting those mounts instead of
  * leaking them.
  *
+ * The dentry is unhashed before the mounts go so that no lookup finds
+ * what they covered. The caller removes it for good afterwards.
+ *
  * The caller may hold dentry->d_inode->i_rwsem.
  */
 void __detach_mounts(struct dentry *dentry)
 {
 	struct pinned_mountpoint mp = {};
+	struct mnt_cover *cover;
+	struct hlist_node *n;
 	struct mount *mnt;
 
 	guard(namespace_excl)();
@@ -1989,15 +2046,16 @@ void __detach_mounts(struct dentry *dentry)
 	if (!lookup_mountpoint(dentry, &mp))
 		return;
 
+	/* the name goes first, what covered it goes second */
+	d_drop(dentry);
 	event++;
 	while (mp.node.next) {
 		mnt = hlist_entry(mp.node.next, struct mount, mnt_mp_list);
-		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
-			umount_mnt(mnt);
-			hlist_add_head(&mnt->mnt_umount, &unmounted);
-		}
-		else umount_tree(mnt, UMOUNT_CONNECTED);
+		umount_tree(mnt, UMOUNT_COVER);
 	}
+	/* the dentry goes away, so do the covers left behind on it */
+	hlist_for_each_entry_safe(cover, n, &mp.mp->m_covers, pin)
+		drop_cover(cover, &ex_mountpoints);
 	unpin_mountpoint(&mp);
 }
 
@@ -2294,9 +2352,11 @@ void drop_collected_paths(const struct path *paths, const struct path *prealloc)
 
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool);
 
+/* Consumes the caller's reference to @mnt. */
 void dissolve_on_fput(struct vfsmount *mnt)
 {
-	struct mount *m = real_mount(mnt);
+	struct vfsmount *p __free(mntput) = mnt;
+	struct mount *m = real_mount(p);
 
 	/*
 	 * m used to be the root of anon namespace; if it still is one,
@@ -2319,13 +2379,14 @@ void dissolve_on_fput(struct vfsmount *mnt)
 
 		emptied_ns = m->mnt_ns;
 		lock_mount_hash();
-		umount_tree(m, UMOUNT_CONNECTED);
+		umount_tree(m, UMOUNT_COVER);
 		unlock_mount_hash();
+		mntput(no_free_ptr(p));
 	}
 }
 
 /* locks: namespace_shared && pinned(mnt) || mount_locked_reader */
-static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
+bool has_locked_children(struct mount *mnt, struct dentry *dentry)
 {
 	struct mount *child;
 
@@ -2339,10 +2400,16 @@ static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
 	return false;
 }
 
-bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+/* locks: namespace_shared && pinned(mnt) || mount_locked_reader */
+static bool __has_children(struct mount *mnt, struct dentry *dentry)
 {
-	guard(mount_locked_reader)();
-	return __has_locked_children(mnt, dentry);
+	struct mount *child;
+
+	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+		if (is_subdir(child->mnt_mountpoint, dentry))
+			return true;
+	}
+	return false;
 }
 
 /*
@@ -2401,7 +2468,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	if (__has_locked_children(old_mnt, path->dentry))
+	if (has_locked_children(old_mnt, path->dentry))
 		return ERR_PTR(-EINVAL);
 
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
@@ -2564,11 +2631,11 @@ enum mnt_tree_flags_t {
 static int attach_recursive_mnt(struct mount *source_mnt,
 				const struct pinned_mountpoint *dest)
 {
-	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	struct mount *dest_mnt = dest->parent;
 	struct mountpoint *dest_mp = dest->mp;
 	HLIST_HEAD(tree_list);
 	struct mnt_namespace *ns = dest_mnt->mnt_ns;
+	struct user_namespace *user_ns = ns->user_ns;
 	struct pinned_mountpoint root = {};
 	struct mountpoint *shorter = NULL;
 	struct mount *child, *p;
@@ -2578,12 +2645,30 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	bool moving = mnt_has_parent(source_mnt);
 
 	/*
+	 * A caller in an unprivileged mount namespaces may trigger an
+	 * automount and propagate locked mounts into privileged mount
+	 * namespaces. Take ownership from the target mount namespace.
+	 * It's equivalent for everything but the automount case.
+	 *
+	 * Detached trees in anonymous mount namespaces by be handed
+	 * over via SCM_RIGHTS or inherited in other ways on purpose
+	 * the attaching task's mount namespace is authoritative, not
+	 * the creator of the detached tree.
+	 */
+	if (is_anon_ns(ns))
+		user_ns = current->nsproxy->mnt_ns->user_ns;
+	else
+		user_ns = ns->user_ns;
+
+	/*
 	 * Preallocate a mountpoint in case the new mounts need to be
 	 * mounted beneath mounts on the same mountpoint.
 	 */
-	for (top = source_mnt; unlikely(top->overmount); top = top->overmount) {
+	for (top = source_mnt; ; top = top->overmount) {
 		if (!shorter && is_mnt_ns_file(top->mnt.mnt_root))
 			shorter = top->mnt_mp;
+		if (likely(!top->overmount))
+			break;
 	}
 	err = get_mountpoint(top->mnt.mnt_root, &root);
 	if (err)
@@ -2654,15 +2739,17 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			/*
 			 * If @q was locked it was meant to hide
 			 * whatever was under it. Let @child take over
-			 * that job and lock it, then we can unlock @q.
-			 * That'll allow another namespace to shed @q
-			 * and reveal @child. Clearly, that mounter
-			 * consented to this by not severing the mount
-			 * relationship. Otherwise, what's the point.
+			 * that job and lock it. If @child is the mount
+			 * the caller placed we can then unlock @q:
+			 * nothing another namespace does removes it
+			 * again. A propagated copy goes away when the
+			 * mounter of the original unmounts it, so @q
+			 * keeps its lock.
 			 */
 			if (IS_MNT_LOCKED(q)) {
 				child->mnt.mnt_flags |= MNT_LOCKED;
-				q->mnt.mnt_flags &= ~MNT_LOCKED;
+				if (child == source_mnt)
+					q->mnt.mnt_flags &= ~MNT_LOCKED;
 			}
 			mnt_change_mountpoint(r, mp, q);
 		}
@@ -2759,6 +2846,11 @@ static void do_lock_mount(const struct path *path,
 
 		scoped_guard(mount_locked_reader) {
 			m = where_to_mount(path, &dentry, beneath);
+			/* sticky, so it takes no locks to refuse it */
+			if (unlikely(cant_mount(dentry))) {
+				res->parent = ERR_PTR(-ENOENT);
+				return;
+			}
 			if (&m->mnt != path->mnt) {
 				mntget(&m->mnt);
 				dget(dentry);
@@ -2989,7 +3081,14 @@ static struct mount *__do_loopback(const struct path *old_path,
 	if (!may_copy_tree(old_path))
 		return ERR_PTR(-EINVAL);
 
-	if (!recurse && __has_locked_children(old, old_path->dentry))
+	/* a pseudo dentry is freed without an RCU delay, no walk may find it */
+	if (old_path->dentry->d_flags & DCACHE_NORCU)
+		return ERR_PTR(-EINVAL);
+
+	if (recurse && !old->mnt_ns)
+		return ERR_PTR(-EINVAL);
+
+	if (!recurse && has_locked_children(old, old_path->dentry))
 		return ERR_PTR(-EINVAL);
 
 	if (recurse)
@@ -3028,7 +3127,11 @@ static int do_loopback(const struct path *path, const char *old_name,
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
-	err = graft_tree(mnt, &mp);
+	/* the copy may carry mount namespace files from below the source */
+	if (recurse && !check_for_nsfs_mounts(mnt))
+		err = -EINVAL;
+	else
+		err = graft_tree(mnt, &mp);
 	if (err) {
 		lock_mount_hash();
 		umount_tree(mnt, UMOUNT_SYNC);
@@ -3088,7 +3191,7 @@ static struct file *open_detached_copy(struct path *path, unsigned int flags)
 	path->mnt = mntget(&ns->root->mnt);
 	file = dentry_open(path, O_PATH, current_cred());
 	if (IS_ERR(file))
-		dissolve_on_fput(path->mnt);
+		dissolve_on_fput(no_free_ptr(path->mnt));
 	else
 		file->f_mode |= FMODE_NEED_UNMOUNT;
 	return file;
@@ -3110,12 +3213,18 @@ static struct mnt_namespace *create_new_namespace(struct path *path,
 	struct mount *mnt;
 	unsigned int copy_flags = 0;
 	bool locked = false, recurse = flags & MOUNT_COPY_RECURSIVE;
+	bool foreign = user_ns != ns->user_ns;
 
 	if (unlikely(!d_can_lookup(path->dentry)))
 		return ERR_PTR(-ENOTDIR);
 
-	if (user_ns != ns->user_ns)
-		copy_flags |= CL_SLAVE;
+	/*
+	 * Without privileges over the mount namespace the copy is made from
+	 * nothing mounted below @path may be left out. It would reveal what
+	 * it covers. That's what unshare() gives such a caller as well.
+	 */
+	if (foreign)
+		copy_flags |= CL_SLAVE | CL_COPY_UNBINDABLE;
 
 	new_ns = alloc_mnt_ns(user_ns, false);
 	if (IS_ERR(new_ns))
@@ -3149,10 +3258,14 @@ static struct mnt_namespace *create_new_namespace(struct path *path,
 	/*
 	 * We don't emulate unshare()ing a mount namespace. We stick to
 	 * the restrictions of creating detached bind-mounts. It has a
-	 * lot saner and simpler semantics.
+	 * lot saner and simpler semantics. A caller without privileges
+	 * over the mount namespace can't leave out any child though.
 	 */
 	if (flags & MOUNT_COPY_NEW)
 		mnt = clone_mnt(real_mount(path->mnt), path->dentry, copy_flags);
+	else if (foreign && !recurse &&
+		 __has_children(real_mount(path->mnt), path->dentry))
+		mnt = ERR_PTR(-EINVAL);
 	else
 		mnt = __do_loopback(path, recurse, copy_flags);
 	scoped_guard(mount_writer) {
@@ -3169,7 +3282,7 @@ static struct mnt_namespace *create_new_namespace(struct path *path,
 		 * of the real rootfs we created.
 		 */
 		attach_mnt(mnt, new_ns_root, mp.mp);
-		if (user_ns != ns->user_ns)
+		if (foreign)
 			lock_mnt_tree(new_ns_root);
 	}
 
@@ -3463,11 +3576,11 @@ static int do_set_group(const struct path *from_path, const struct path *to_path
 		return -EINVAL;
 
 	/* From mount should not have locked children in place of To's root */
-	if (__has_locked_children(from, to->mnt.mnt_root))
+	if (has_locked_children(from, to->mnt.mnt_root))
 		return -EINVAL;
 
 	/* Setting sharing groups is only allowed on private mounts */
-	if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to))
+	if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to) || IS_MNT_UNBINDABLE(to))
 		return -EINVAL;
 
 	/* From should not be private */
@@ -3743,7 +3856,7 @@ static int do_add_mount(struct mount *newmnt, const struct pinned_mountpoint *mp
 		if (!(mnt_flags & MNT_SHRINKABLE))
 			return -EINVAL;
 		/* ... and for those we'd better have mountpoint still alive */
-		if (!parent->mnt_ns)
+		if (!is_mounted(&parent->mnt))
 			return -EINVAL;
 	}
 
@@ -3953,6 +4066,8 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 	list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
 		if (!is_mounted(&mnt->mnt))
 			continue;
+		/* lock_mnt_tree() leaves expirable mounts alone */
+		VFS_WARN_ON_ONCE(IS_MNT_LOCKED(mnt));
 		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
 			propagate_mount_busy(mnt, 1))
 			continue;
@@ -3960,6 +4075,11 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 	}
 	while (!list_empty(&graveyard)) {
 		mnt = list_first_entry(&graveyard, struct mount, mnt_expire);
+		/* an earlier umount_tree() may have moved a busy mount here */
+		if (propagate_mount_busy(mnt, 1)) {
+			list_move(&mnt->mnt_expire, mounts);
+			continue;
+		}
 		touch_mnt_namespace(mnt->mnt_ns);
 		umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
 	}
@@ -3968,16 +4088,37 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);
 
 /*
+ * Unmount @mnt if it's a shrinkable mount without children that nobody uses.
+ *
+ * mount_lock must be held for write
+ */
+static bool shrink_submount(struct mount *mnt)
+{
+	/* not the kernel's to remove either */
+	if (IS_MNT_LOCKED(mnt) || propagate_mount_busy(mnt, 1))
+		return false;
+	touch_mnt_namespace(mnt->mnt_ns);
+	umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
+	return true;
+}
+
+/*
  * Ripoff of 'select_parent()'
  *
- * search the list of submounts for a given mountpoint, and move any
- * shrinkable submounts to the 'graveyard' list.
+ * unmount the shrinkable submounts of @parent that aren't busy, children
+ * before their parent, and say whether anything went
+ *
+ * The cursor into the children of @this_parent survives the umount of a
+ * child mount without child mounts. The mounts that get umounted together with
+ * it are located under receiving mounts of @this_parent and never under
+ * @this_parent itself. The one exception is @this_parent getting unmounted
+ * then the walk starts over.
  */
-static int select_submounts(struct mount *parent, struct list_head *graveyard)
+static bool __shrink_submounts(struct mount *parent)
 {
 	struct mount *this_parent = parent;
 	struct list_head *next;
-	int found = 0;
+	bool shrunk = false;
 
 repeat:
 	next = this_parent->mnt_mounts.next;
@@ -3996,42 +4137,45 @@ resume:
 			this_parent = mnt;
 			goto repeat;
 		}
-
-		if (!propagate_mount_busy(mnt, 1)) {
-			list_move_tail(&mnt->mnt_expire, graveyard);
-			found++;
-		}
+		if (!shrink_submount(mnt))
+			continue;
+		shrunk = true;
+		if (unlikely(this_parent->mnt.mnt_flags & MNT_UMOUNT))
+			return true;
 	}
 	/*
 	 * All done at this level ... ascend and resume the search
 	 */
 	if (this_parent != parent) {
-		next = this_parent->mnt_child.next;
-		this_parent = this_parent->mnt_parent;
+		struct mount *mnt = this_parent;
+
+		next = mnt->mnt_child.next;
+		this_parent = mnt->mnt_parent;
+		/* its children are gone, maybe it can go as well */
+		if (shrink_submount(mnt)) {
+			shrunk = true;
+			if (unlikely(this_parent->mnt.mnt_flags & MNT_UMOUNT))
+				return true;
+		}
 		goto resume;
 	}
-	return found;
+	return shrunk;
 }
 
 /*
- * process a list of expirable mountpoints with the intent of discarding any
- * submounts of a specific parent mountpoint
+ * unmount the shrinkable submounts of @mnt that aren't busy
+ *
+ * The busy check and the umount of a mount are adjacent. An umount can
+ * still empty or move a mount in a part of the tree that was walked
+ * already, so walk again until nothing goes.
  *
  * mount_lock must be held for write
  */
 static void shrink_submounts(struct mount *mnt)
 {
-	LIST_HEAD(graveyard);
-	struct mount *m;
-
-	/* extract submounts of 'mountpoint' from the expiration list */
-	while (select_submounts(mnt, &graveyard)) {
-		while (!list_empty(&graveyard)) {
-			m = list_first_entry(&graveyard, struct mount,
-						mnt_expire);
-			touch_mnt_namespace(m->mnt_ns);
-			umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC);
-		}
+	for (;;) {
+		if (!__shrink_submounts(mnt))
+			break;
 	}
 }
 
@@ -4196,6 +4340,8 @@ static void free_mnt_ns(struct mnt_namespace *ns)
 	if (!is_anon_ns(ns))
 		ns_common_free(ns);
 	dec_mnt_namespaces(ns->ucounts);
+	/* the last active reference is gone, no mark can show up anymore */
+	fsnotify_mntns_delete(ns);
 	mnt_ns_tree_remove(ns);
 }
 
@@ -4545,7 +4691,7 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
 	FD_PREPARE(fdf, (flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0,
 		   dentry_open(&new_path, O_PATH, fc->cred));
 	if (fdf.err) {
-		dissolve_on_fput(new_path.mnt);
+		dissolve_on_fput(no_free_ptr(new_path.mnt));
 		return fdf.err;
 	}
 
@@ -4697,14 +4843,15 @@ int path_pivot_root(struct path *new, struct path *old)
 
 	new_mnt = real_mount(new->mnt);
 	root_mnt = real_mount(root.mnt);
+	/* only a mounted mount has a parent that namespace_sem pins */
+	if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
+		return -EINVAL;
 	ex_parent = new_mnt->mnt_parent;
 	root_parent = root_mnt->mnt_parent;
 	if (IS_MNT_SHARED(old_mnt) ||
 		IS_MNT_SHARED(ex_parent) ||
 		IS_MNT_SHARED(root_parent))
 		return -EINVAL;
-	if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
-		return -EINVAL;
 	if (new_mnt->mnt.mnt_flags & MNT_LOCKED)
 		return -EINVAL;
 	if (d_unlinked(new->dentry))
@@ -4955,6 +5102,11 @@ static int do_mount_setattr(const struct path *path, struct mount_kattr *kattr)
 		 * propagation.
 		 */
 		namespace_lock();
+		/* invent_group_ids() walks the tree, only walk a mounted one */
+		if (!anon_ns_root(mnt) && !check_mnt(mnt)) {
+			namespace_unlock();
+			return -EINVAL;
+		}
 		if (kattr->propagation == MS_SHARED) {
 			err = invent_group_ids(mnt, kattr->kflags & MOUNT_KATTR_RECURSE);
 			if (err) {
@@ -4967,6 +5119,7 @@ static int do_mount_setattr(const struct path *path, struct mount_kattr *kattr)
 	err = -EINVAL;
 	lock_mount_hash();
 
+	/* Checked under namespace_sem already if the propagation changes. */
 	if (!anon_ns_root(mnt) && !check_mnt(mnt))
 		goto out;
 
@@ -5319,15 +5472,25 @@ static void statmount_sb_basic(struct kstatmount *s)
 	s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME);
 }
 
+static void statmount_mnt_parent(struct kstatmount *s, const struct mount *m)
+{
+	s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique;
+	s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id;
+}
+
 static void statmount_mnt_basic(struct kstatmount *s)
 {
 	struct mount *m = real_mount(s->mnt);
 
 	s->sm.mask |= STATMOUNT_MNT_BASIC;
 	s->sm.mnt_id = m->mnt_id_unique;
-	s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique;
 	s->sm.mnt_id_old = m->mnt_id;
-	s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id;
+	/* An unmounted mount is cut loose from its parent under mount_lock alone. */
+	if (likely(is_mounted(s->mnt)))
+		statmount_mnt_parent(s, m);
+	else
+		scoped_guard(mount_locked_reader)
+			statmount_mnt_parent(s, m);
 	s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt);
 	s->sm.mnt_propagation = mnt_to_propagation_flags(m);
 	s->sm.mnt_peer_group = m->mnt_group_id;
@@ -6199,6 +6362,25 @@ static void __init mount_rootfs_on_nullfs(struct vfsmount *mnt,
 		attach_mnt(real_mount(mnt), mp.parent, mp.mp);
 }
 
+static struct vfsmount *__init knullfs_file_mount(void)
+{
+	struct dentry *file;
+	struct mount *mnt;
+
+	file = nullfs_new_file(knullfs->mnt_sb);
+	if (IS_ERR(file))
+		return ERR_CAST(file);
+	mnt = clone_mnt(real_mount(knullfs), file, CL_PRIVATE);
+	dput(file);
+	if (IS_ERR(mnt))
+		return ERR_CAST(mnt);
+	mnt->mnt_ns = MNT_NS_INTERNAL;
+	mnt->mnt.mnt_flags |= MNT_INTERNAL;
+	mnt->mnt.mnt_flags &= ~MNT_READONLY;
+	dont_mount(mnt->mnt.mnt_root);
+	return &mnt->mnt;
+}
+
 static void __init init_mount_tree(void)
 {
 	struct vfsmount *mnt, *nullfs_mnt;
@@ -6210,10 +6392,14 @@ static void __init init_mount_tree(void)
 	 *
 	 * (1) nullfs with mount id 1
 	 * (2) mutable rootfs with mount id 2
-	 * (3) private nullfs for kthreads (SB_KERNMOUNT)
+	 * (3) private nullfs for kthreads (SB_KERNMOUNT), kept in knullfs
+	 * (4) a second mount of (3) rooted on a regular file, kept in
+	 *     knullfs_file
 	 *
 	 * with (2) mounted on top of (1). The init_task's root and pwd
 	 * are pointed at (3) so all kthreads start isolated in nullfs.
+	 * A lookup at the cover an unmounted mount left behind finds (3)
+	 * or (4), see __lookup_mnt().
 	 */
 	nullfs_mnt = vfs_kern_mount(&nullfs_fs_type, 0, "nullfs", NULL);
 	if (IS_ERR(nullfs_mnt))
@@ -6245,11 +6431,18 @@ static void __init init_mount_tree(void)
 		init_mnt_ns.nr_mounts++;
 	}
 
-	nullfs_mnt = kern_mount(&nullfs_fs_type);
-	if (IS_ERR(nullfs_mnt))
+	knullfs = kern_mount(&nullfs_fs_type);
+	if (IS_ERR(knullfs))
 		panic("VFS: Failed to create private nullfs instance");
-	root.mnt	= nullfs_mnt;
-	root.dentry	= nullfs_mnt->mnt_root;
+	/* nothing is ever mounted on the root of a kernel thread */
+	dont_mount(knullfs->mnt_root);
+	/* and nothing is ever written through it */
+	knullfs->mnt_flags |= MNT_READONLY;
+	knullfs_file = knullfs_file_mount();
+	if (IS_ERR(knullfs_file))
+		panic("VFS: Failed to create the nullfs file stand-in");
+	root.mnt	= knullfs;
+	root.dentry	= knullfs->mnt_root;
 
 	init_task.nsproxy->mnt_ns = &init_mnt_ns;
 	get_mnt_ns(&init_mnt_ns);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index b2640d836a71..d17628580a57 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -903,6 +903,10 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj,
 	if (WARN_ON(!fsnotify_valid_obj_type(obj_type)))
 		return -EINVAL;
 
+	/* the filesystem doesn't want its objects watched */
+	if (sb && (sb->s_type->fs_flags & FS_DISALLOW_NOTIFY))
+		return -EINVAL;
+
 	/*
 	 * Attach the sb info before attaching a connector to any object on sb.
 	 * The sb info will remain attached as long as sb lives.
diff --git a/fs/nullfs.c b/fs/nullfs.c
index e06352c7b2cc..e7221bc8aedb 100644
--- a/fs/nullfs.c
+++ b/fs/nullfs.c
@@ -3,6 +3,8 @@
 #include <linux/fs/super_types.h>
 #include <linux/fs_context.h>
 #include <linux/magic.h>
+#include <linux/splice.h>
+#include <linux/uio.h>
 
 #include "mount.h"
 
@@ -10,6 +12,121 @@ static const struct super_operations nullfs_super_operations = {
 	.statfs	= simple_statfs,
 };
 
+static loff_t nullfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	/* an empty directory has two entries . and .. at offsets 0 and 1 */
+	return generic_file_llseek_size(file, offset, whence, 2, 2);
+}
+
+static int nullfs_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	dir_emit_dots(file, ctx);
+	return 0;
+}
+
+/* the one inode of nullfs is shared by every holder, so no locks on it */
+static int nullfs_nolock(struct file *file, int cmd, struct file_lock *fl)
+{
+	return -ENOLCK;
+}
+
+/* what libfs gives an empty directory, plus the refusal of file locks */
+static const struct file_operations nullfs_dir_operations = {
+	.llseek		= nullfs_dir_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= nullfs_dir_readdir,
+	.fsync		= noop_fsync,
+	.lock		= nullfs_nolock,
+	.flock		= nullfs_nolock,
+	.fop_flags	= FOP_IMMUTABLE,
+};
+
+static ssize_t nullfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	return 0;
+}
+
+static ssize_t nullfs_file_splice_read(struct file *in, loff_t *ppos,
+				       struct pipe_inode_info *pipe,
+				       size_t len, unsigned int flags)
+{
+	return 0;
+}
+
+static ssize_t nullfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	size_t count = iov_iter_count(from);
+
+	iov_iter_advance(from, count);
+	return count;
+}
+
+static int nullfs_pipe_to_null(struct pipe_inode_info *pipe,
+			       struct pipe_buffer *buf, struct splice_desc *sd)
+{
+	return sd->len;
+}
+
+static ssize_t nullfs_file_splice_write(struct pipe_inode_info *pipe,
+					struct file *out, loff_t *ppos,
+					size_t len, unsigned int flags)
+{
+	return splice_from_pipe(pipe, out, ppos, len, flags, nullfs_pipe_to_null);
+}
+
+static int nullfs_file_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			       struct iattr *attr)
+{
+	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+		return -EPERM;
+	return 0;
+}
+
+static const struct inode_operations nullfs_file_inode_operations = {
+	.setattr	= nullfs_file_setattr,
+};
+
+static const struct file_operations nullfs_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read_iter	= nullfs_file_read_iter,
+	.write_iter	= nullfs_file_write_iter,
+	.splice_read	= nullfs_file_splice_read,
+	.splice_write	= nullfs_file_splice_write,
+	.fsync		= noop_fsync,
+	.lock		= nullfs_nolock,
+	.flock		= nullfs_nolock,
+};
+
+/*
+ * An empty regular file on @sb as a dentry of its own, never hashed under
+ * the root so no lookup finds it.
+ */
+struct dentry *nullfs_new_file(struct super_block *sb)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	/* the root directory is 1 */
+	inode->i_ino = 2;
+	inode->i_mode = S_IFREG | 0666;
+	inode->i_op = &nullfs_file_inode_operations;
+	inode->i_fop = &nullfs_file_operations;
+	simple_inode_init_ts(inode);
+	inode->i_flags |= S_NOATIME;
+
+	dentry = d_alloc_anon(sb);
+	if (!dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	d_instantiate(dentry, inode);
+	return dentry;
+}
+
 static int nullfs_fs_fill_super(struct super_block *s, struct fs_context *fc)
 {
 	struct inode *inode;
@@ -30,10 +147,11 @@ static int nullfs_fs_fill_super(struct super_block *s, struct fs_context *fc)
 
 	/* nullfs is permanently empty... */
 	make_empty_dir_inode(inode);
+	inode->i_fop = &nullfs_dir_operations;
 	simple_inode_init_ts(inode);
 	inode->i_ino	= 1;
-	/* ... and immutable. */
-	inode->i_flags |= S_IMMUTABLE;
+	/* ... and immutable, reading it leaves no trace either. */
+	inode->i_flags |= S_IMMUTABLE | S_NOATIME;
 
 	s->s_root = d_make_root(inode);
 	if (!s->s_root)
@@ -61,6 +179,7 @@ static int nullfs_init_fs_context(struct fs_context *fc)
 
 struct file_system_type nullfs_fs_type = {
 	.name			= "nullfs",
+	.fs_flags		= FS_DISALLOW_NOTIFY,
 	.init_fs_context	= nullfs_init_fs_context,
 	.kill_sb		= kill_anon_super,
 };
diff --git a/fs/pnode.c b/fs/pnode.c
index 5d91c3e58d2a..5f07fa14099b 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -410,19 +410,99 @@ bool propagation_would_overmount(const struct mount *from,
 	return false;
 }
 
+/* Does @m receive propagation from @parent? */
+static bool receives_from(struct mount *m, struct mount *parent)
+{
+	if (m == parent)
+		return false;
+	for (; m; m = m->mnt_master)
+		if (m == parent || peers(m, parent))
+			return true;
+	return false;
+}
+
+/*
+ * Does @m receive propagation from the victim's parent as well? If so, then
+ * the mount at the victim's mountpoint inside of @m is a umount candidate as
+ * well. So it's the next candidate in the chain. Otherwise the chain ends at
+ * @m.
+ */
+static struct mount *next_candidate(struct mount *m, struct mount *victim)
+{
+	if (!receives_from(m, victim->mnt_parent))
+		return NULL;
+	return __lookup_mnt(&m->mnt, victim->mnt_mountpoint);
+}
+
+/*
+ * Would propagate_umount() pull out a mount of the chain of candidates that
+ * starts at @c, and does that mount have references beyond its own?
+ *
+ * This mirrors how trim_one(), trim_ancestors() and handle_locked() handle a
+ * synchronous umount:
+ *
+ * - single victim
+ * - without children
+ * - with MNT_LOCKED already cleared on every candidate by propagate_mount_unlock()
+ *
+ * A copy of the victim gets unmounted when each of its children is
+ * the next candidate in the chain or its overmount, unless the next
+ * unmount candidate is not its overmount and some unmount candidate further
+ * down has a child outside the chain.  Keep this in sync with
+ * Documentation/filesystems/propagate_umount.txt.
+ */
+static bool chain_busy(struct mount *c, struct mount *victim)
+{
+	struct mount *m, *n, *next, *deepest = NULL;
+	bool above;
+
+	/* the deepest candidate with a child outside the chain */
+	for (m = c; m; m = next) {
+		next = next_candidate(m, victim);
+		list_for_each_entry(n, &m->mnt_mounts, mnt_child) {
+			if (n != next && n != victim) {
+				deepest = m;
+				break;
+			}
+		}
+	}
+
+	above = deepest != NULL;	/* @deepest is at or below @m */
+	for (m = c; m; m = next) {
+		bool goes = true;
+
+		next = next_candidate(m, victim);
+		list_for_each_entry(n, &m->mnt_mounts, mnt_child) {
+			if (n != next && n != m->overmount && n != victim) {
+				goes = false;
+				break;
+			}
+		}
+		if (goes && next && next != m->overmount && above && m != deepest)
+			goes = false;
+		if (m == deepest)
+			above = false;
+		if (goes && do_refcount_check(m, 1))
+			return true;
+	}
+	return false;
+}
+
 /*
  * check if the mount 'mnt' can be unmounted successfully.
  * @mnt: the mount to be checked for unmount
  * NOTE: unmounting 'mnt' would naturally propagate to all
  * other mounts its parent propagates to.
- * Check if any of these mounts that **do not have submounts**
- * have more references than 'refcnt'. If so return busy.
+ * Check if any of the mounts that propagate_umount() would pull out
+ * along with it have more references than their own. If so return busy.
  *
  * vfsmount lock must be held for write
  */
 int propagate_mount_busy(struct mount *mnt, int refcnt)
 {
 	struct mount *parent = mnt->mnt_parent;
+	struct dentry *mp = mnt->mnt_mountpoint;
+	struct mount *m;
 
 	/*
 	 * quickly check if the current mount can be unmounted.
@@ -435,24 +515,16 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
 	if (mnt == parent)
 		return 0;
 
-	for (struct mount *m = propagation_next(parent, parent); m;
-	     		m = propagation_next(m, parent)) {
-		struct list_head *head;
-		struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
+	/* the candidates are the mounts at @mp below the receivers */
+	for (m = propagation_next(parent, parent); m;
+	     m = propagation_next(m, parent)) {
+		struct mount *c = __lookup_mnt(&m->mnt, mp);
 
-		if (!child)
+		/* each chain once, from its top: skip receivers that are candidates */
+		if (!c || (mnt_has_parent(m) && m->mnt_mountpoint == mp &&
+			   receives_from(m->mnt_parent, parent)))
 			continue;
-
-		head = &child->mnt_mounts;
-		if (!list_empty(head)) {
-			/*
-			 * a mount that covers child completely wouldn't prevent
-			 * it being pulled out; any other would.
-			 */
-			if (!list_is_singular(head) || !child->overmount)
-				continue;
-		}
-		if (do_refcount_check(child, 1))
+		if (chain_busy(c, mnt))
 			return 1;
 	}
 	return 0;
@@ -625,8 +697,8 @@ static void handle_locked(struct mount *m, struct list_head *to_umount)
  * the same parent and mountpoint; that will be remedied as soon as we
  * return from propagate_umount() - its caller (umount_tree()) will detach
  * the stack from the parent it (and now @m) is attached to.  umount_tree()
- * might choose to keep unmounted pieces stuck to each other, but it always
- * detaches them from the mounts that remain in the tree.
+ * detaches every unmounted mount from its parent, whether that parent
+ * remains in the tree or not.
  */
 static void reparent(struct mount *m)
 {
diff --git a/fs/readdir.c b/fs/readdir.c
index 76bb1ae3a450..f2288841337a 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -87,6 +87,8 @@ EXPORT_SYMBOL(wrap_directory_iterator);
 int iterate_dir(struct file *file, struct dir_context *ctx)
 {
 	struct inode *inode = file_inode(file);
+	/* never an entry, never removed: nothing for the lock to keep still */
+	bool locked = !(file->f_op->fop_flags & FOP_IMMUTABLE);
 	int res = -ENOTDIR;
 
 	if (!file->f_op->iterate_shared)
@@ -100,9 +102,11 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
 	if (res)
 		goto out;
 
-	res = down_read_killable(&inode->i_rwsem);
-	if (res)
-		goto out;
+	if (locked) {
+		res = down_read_killable(&inode->i_rwsem);
+		if (res)
+			goto out;
+	}
 
 	res = -ENOENT;
 	if (!IS_DEADDIR(inode)) {
@@ -112,7 +116,8 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
 		fsnotify_access(file);
 		file_accessed(file);
 	}
-	inode_unlock_shared(inode);
+	if (locked)
+		inode_unlock_shared(inode);
 out:
 	return res;
 }
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index 881d46f25e08..6f85f63861aa 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -11,6 +11,7 @@
 #define pr_fmt(fmt) "fs-verity: " fmt
 
 #include <linux/fsverity.h>
+#include <linux/rcupdate.h>
 #include <linux/rhashtable.h>
 
 /*
@@ -76,7 +77,19 @@ struct merkle_tree_params {
 struct fsverity_info {
 	struct rhash_head rhash_head;
 	struct merkle_tree_params tree_params;
-	u8 root_hash[FS_VERITY_MAX_DIGEST_SIZE];
+	union {
+		u8 root_hash[FS_VERITY_MAX_DIGEST_SIZE];
+
+		/*
+		 * Used for final freeing of the struct, in which case root_hash
+		 * is no longer needed.  Specifically, the only fields needed
+		 * besides the rcu_head are those needed by fsverity_free_info()
+		 * itself, and those that can be accessed by fsverity_get_info()
+		 * (rhash_head and inode) during the RCU-protected rhashtable
+		 * chain search trying to find another inode's fsverity_info.
+		 */
+		struct rcu_head rcu_head;
+	};
 	u8 file_digest[FS_VERITY_MAX_DIGEST_SIZE];
 	struct inode *inode;
 	unsigned long *hash_block_verified;
diff --git a/fs/verity/open.c b/fs/verity/open.c
index d0c56a7faa3b..52c8cd014921 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -399,11 +399,22 @@ void fsverity_free_info(struct fsverity_info *vi)
 	kmem_cache_free(fsverity_info_cachep, vi);
 }
 
+static void fsverity_free_info_rcu(struct rcu_head *head)
+{
+	fsverity_free_info(container_of(head, struct fsverity_info, rcu_head));
+}
+
 void fsverity_remove_info(struct fsverity_info *vi)
 {
 	rhashtable_remove_fast(&fsverity_info_hash, &vi->rhash_head,
 			       fsverity_info_hash_params);
-	fsverity_free_info(vi);
+	/*
+	 * The freeing must be RCU-delayed because __fsverity_get_info() for a
+	 * *different* inode's fsverity_info in the same rhashtable hash chain
+	 * can still be accessing *this* fsverity_info's rhash_head and inode
+	 * fields as part of the RCU-protected hash chain search.
+	 */
+	call_rcu(&vi->rcu_head, fsverity_free_info_rcu);
 }
 
 void fsverity_cleanup_inode(struct inode *inode)
diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c
index 6a66b6075e0a..f527fce46def 100644
--- a/fs/xfs/libxfs/xfs_exchmaps.c
+++ b/fs/xfs/libxfs/xfs_exchmaps.c
@@ -49,7 +49,7 @@ struct xfs_exchmaps_adjacent {
 	.right2 = { .br_startblock = HOLESTARTBLOCK }, \
 }
 
-/* Information to reset reflink flag / CoW fork state after an exchange. */
+/* Information to reset CoW fork state after an exchange. */
 
 /*
  * If the reflink flag is set on either inode, make sure it has an incore CoW
@@ -127,9 +127,7 @@ xmi_has_more_exchange_work(const struct xfs_exchmaps_intent *xmi)
 static inline bool
 xmi_has_postop_work(const struct xfs_exchmaps_intent *xmi)
 {
-	return xmi->xmi_flags & (XFS_EXCHMAPS_CLEAR_INO1_REFLINK |
-				 XFS_EXCHMAPS_CLEAR_INO2_REFLINK |
-				 __XFS_EXCHMAPS_INO2_SHORTFORM);
+	return xmi->xmi_flags & __XFS_EXCHMAPS_INO2_SHORTFORM;
 }
 
 /* Check all mappings to make sure we can actually exchange them. */
@@ -525,18 +523,6 @@ free:
 	return error;
 }
 
-/* Clear the reflink flag after an exchange. */
-static inline void
-xfs_exchmaps_clear_reflink(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*ip)
-{
-	trace_xfs_reflink_unset_inode_flag(ip);
-
-	ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-}
-
 /* Finish whatever work might come after an exchange operation. */
 static int
 xfs_exchmaps_do_postop_work(
@@ -557,16 +543,6 @@ xfs_exchmaps_do_postop_work(
 			return error;
 	}
 
-	if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO1_REFLINK) {
-		xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip1);
-		xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO1_REFLINK;
-	}
-
-	if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO2_REFLINK) {
-		xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip2);
-		xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO2_REFLINK;
-	}
-
 	return 0;
 }
 
@@ -948,46 +924,14 @@ xfs_exchmaps_intent_destroy_cache(void)
 }
 
 /*
- * Decide if we will exchange the reflink flags between the two files after the
- * exchange.  The only time we want to do this is if we're exchanging all
- * mappings under EOF and the inode reflink flags have different states.
+ * Allocate and initialize a new incore intent item from a request.
  */
-static inline bool
-xmi_can_exchange_reflink_flags(
-	const struct xfs_exchmaps_req	*req,
-	unsigned int			reflink_state)
-{
-	struct xfs_mount		*mp = req->ip1->i_mount;
-
-	/*
-	 * The INO1_WRITTEN optimization can skip exchanging hole and
-	 * unwritten mappings, which means we cannot guarantee that all
-	 * shared extents actually moved to the other file.  Clearing the
-	 * reflink flag of an inode that still holds shared extents breaks
-	 * the CoW write path, so refuse to exchange the flags in that case.
-	 */
-	if (req->flags & XFS_EXCHMAPS_INO1_WRITTEN)
-		return false;
-
-	if (hweight32(reflink_state) != 1)
-		return false;
-	if (req->startoff1 != 0 || req->startoff2 != 0)
-		return false;
-	if (req->blockcount != XFS_B_TO_FSB(mp, req->ip1->i_disk_size))
-		return false;
-	if (req->blockcount != XFS_B_TO_FSB(mp, req->ip2->i_disk_size))
-		return false;
-	return true;
-}
-
-
-/* Allocate and initialize a new incore intent item from a request. */
 struct xfs_exchmaps_intent *
 xfs_exchmaps_init_intent(
 	const struct xfs_exchmaps_req	*req)
 {
 	struct xfs_exchmaps_intent	*xmi;
-	unsigned int			rs = 0;
+	struct xfs_mount		*mp = req->ip1->i_mount;
 
 	xmi = kmem_cache_zalloc(xfs_exchmaps_intent_cache,
 			GFP_NOFS | __GFP_NOFAIL);
@@ -1005,27 +949,18 @@ xfs_exchmaps_init_intent(
 		return xmi;
 	}
 
-	if (req->flags & XFS_EXCHMAPS_SET_SIZES) {
-		xmi->xmi_flags |= XFS_EXCHMAPS_SET_SIZES;
-		xmi->xmi_isize1 = req->ip2->i_disk_size;
-		xmi->xmi_isize2 = req->ip1->i_disk_size;
-	}
-
-	/* Record the state of each inode's reflink flag before the op. */
-	if (xfs_is_reflink_inode(req->ip1))
-		rs |= 1;
-	if (xfs_is_reflink_inode(req->ip2))
-		rs |= 2;
-
 	/*
-	 * Figure out if we're clearing the reflink flags (which effectively
-	 * exchanges them) after the operation.
+	 * If the caller wanted, set each file's size to that file's exchange
+	 * offset + length exchanged from the other file because the ranges in
+	 * each file might be different lengths.
 	 */
-	if (xmi_can_exchange_reflink_flags(req, rs)) {
-		if (rs & 1)
-			xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO1_REFLINK;
-		if (rs & 2)
-			xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO2_REFLINK;
+	if (req->flags & XFS_EXCHMAPS_SET_SIZES) {
+		loff_t	off1 = XFS_FSB_TO_B(mp, xmi->xmi_startoff1);
+		loff_t	off2 = XFS_FSB_TO_B(mp, xmi->xmi_startoff2);
+
+		xmi->xmi_flags |= XFS_EXCHMAPS_SET_SIZES;
+		xmi->xmi_isize1 = off1 + (req->ip2->i_disk_size - off2);
+		xmi->xmi_isize2 = off2 + (req->ip1->i_disk_size - off1);
 	}
 
 	if (S_ISDIR(VFS_I(xmi->xmi_ip2)->i_mode) ||
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index a4e1b3eb425c..6e620380d5dc 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -927,10 +927,8 @@ struct xfs_xmi_log_format {
  */
 #define XFS_EXCHMAPS_INO1_WRITTEN	(1ULL << 2)
 
-/* Clear the reflink flag from inode1 after the operation. */
+/* No longer set, but older intents may carry them; keep them valid. */
 #define XFS_EXCHMAPS_CLEAR_INO1_REFLINK	(1ULL << 3)
-
-/* Clear the reflink flag from inode2 after the operation. */
 #define XFS_EXCHMAPS_CLEAR_INO2_REFLINK	(1ULL << 4)
 
 #define XFS_EXCHMAPS_LOGGED_FLAGS	(XFS_EXCHMAPS_ATTR_FORK | \
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 268d159339d0..865aec3ae5ab 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1544,7 +1544,6 @@ xfs_swap_extents(
 	struct xfs_bstat	*sbp = &sxp->sx_stat;
 	int			src_log_flags, target_log_flags;
 	int			error = 0;
-	uint64_t		f;
 	int			resblks = 0;
 	unsigned int		flags = 0;
 	struct timespec64	ctime, mtime;
@@ -1700,14 +1699,12 @@ xfs_swap_extents(
 	if (error)
 		goto out_trans_cancel;
 
-	/* Do we have to swap reflink flags? */
-	if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
-	    (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) {
-		f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
-		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
-		ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK;
-		tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
-		tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK;
+	/* Either inode may now own shared blocks; flag both, with CoW forks. */
+	if ((ip->i_diflags2 | tip->i_diflags2) & XFS_DIFLAG2_REFLINK) {
+		ip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
+		tip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
+		xfs_ifork_init_cow(ip);
+		xfs_ifork_init_cow(tip);
 	}
 
 	/* Swap the cow forks. */
diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c
index fafb4e3f065c..935b561dfd3c 100644
--- a/fs/xfs/xfs_exchrange.c
+++ b/fs/xfs/xfs_exchrange.c
@@ -290,17 +290,20 @@ retry:
 		goto out_unlock;
 
 	/*
-	 * If the caller wanted us to exchange the contents of two complete
-	 * files of unequal length, exchange the incore sizes now.  This should
-	 * be safe because we flushed both files' page caches, exchanged all
-	 * the mappings, and updated the ondisk sizes.
+	 * If the caller wanted, set each file's size to that file's exchange
+	 * offset + length exchanged from the other file because the ranges in
+	 * each file might be different lengths.  This should be safe because
+	 * we flushed both files' page caches, exchanged all the mappings, and
+	 * updated the ondisk sizes.
 	 */
 	if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) {
-		loff_t	temp;
+		loff_t	old_ip1_size = i_size_read(VFS_I(ip1));
+		loff_t	old_ip2_size = i_size_read(VFS_I(ip2));
 
-		temp = i_size_read(VFS_I(ip2));
-		i_size_write(VFS_I(ip2), i_size_read(VFS_I(ip1)));
-		i_size_write(VFS_I(ip1), temp);
+		i_size_write(VFS_I(ip2), fxr->file2_offset +
+				(old_ip1_size - fxr->file1_offset));
+		i_size_write(VFS_I(ip1), fxr->file1_offset +
+				(old_ip2_size - fxr->file2_offset));
 	}
 
 out_unlock:
@@ -445,6 +448,30 @@ xfs_exchange_range_checks(
 	return blen == fxr->length ? 0 : -EINVAL;
 }
 
+/* Flush all relevant dirty pagecache near the range to be exchanged. */
+static inline int
+xfs_exchange_range_flush(
+	struct xfs_inode		*ip,
+	const struct xfs_exchrange	*fxr,
+	loff_t				offset)
+{
+	/*
+	 * If TO_EOF is set, the ondisk file size update logic depends on the
+	 * ondisk file size matching the incore file size.  Flush everything.
+	 */
+	if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF)
+		return filemap_write_and_wait(VFS_I(ip)->i_mapping);
+
+	/*
+	 * Because we're updating the ondisk mappings, flush all dirty data
+	 * between the ondisk size and the exchange offset to reduce the chance
+	 * of zeroed file contents in that gap after a crash.
+	 */
+	return filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+			min(offset, ip->i_disk_size),
+			offset + fxr->length - 1);
+}
+
 /*
  * Check that the two inodes are eligible for range exchanges, the ranges make
  * sense, and then flush all dirty data.  Caller must ensure that the inodes
@@ -470,15 +497,11 @@ xfs_exchange_range_prep(
 	if (!same_inode)
 		inode_dio_wait(inode2);
 
-	error = filemap_write_and_wait_range(inode1->i_mapping,
-			fxr->file1_offset,
-			fxr->file1_offset + fxr->length - 1);
+	error = xfs_exchange_range_flush(XFS_I(inode1), fxr, fxr->file1_offset);
 	if (error)
 		return error;
 
-	error = filemap_write_and_wait_range(inode2->i_mapping,
-			fxr->file2_offset,
-			fxr->file2_offset + fxr->length - 1);
+	error = xfs_exchange_range_flush(XFS_I(inode2), fxr, fxr->file2_offset);
 	if (error)
 		return error;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f9d1e05e8ae6..deb411e86661 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1978,6 +1978,8 @@ struct file_operations {
 #define FOP_ASYNC_LOCK		((__force fop_flags_t)(1 << 6))
 /* File system supports uncached read/write buffered IO */
 #define FOP_DONTCACHE		((__force fop_flags_t)(1 << 7))
+/* Never changes and is never removed, readdir of a directory takes no lock */
+#define FOP_IMMUTABLE		((__force fop_flags_t)(1 << 8))
 
 /* Wrap a directory iterator that needs exclusive inode access */
 int wrap_directory_iterator(struct file *, struct dir_context *,
@@ -2296,6 +2298,7 @@ struct file_system_type {
 #define FS_POWER_FREEZE		256	/* Always freeze on suspend/hibernate */
 #define FS_USERNS_MOUNT_RESTRICTED 512	/* Restrict mount in userns if not already visible */
 #define FS_USERNS_DELEGATABLE	1024	/* Can be mounted inside userns from outside */
+#define FS_DISALLOW_NOTIFY	2048	/* No fsnotify marks on its objects */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 39629ee77b91..8126af652845 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -322,6 +322,8 @@ enum {
 	IO_RING_F_DRAIN_DISABLED	= BIT(10),
 	IO_RING_F_COMPAT		= BIT(11),
 	IO_RING_F_IOWQ_LIMITS_SET	= BIT(12),
+	/* restrictions were inherited from the task that created the ring */
+	IO_RING_F_RESTRICT_INHERITED	= BIT(13),
 };
 
 struct iou_ctx {};
diff --git a/include/linux/mount.h b/include/linux/mount.h
index acfe7ef86a1b..b16ba5d45605 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -52,7 +52,7 @@ enum mount_flags {
 	MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME,
 
 	MNT_INTERNAL_FLAGS = MNT_INTERNAL | MNT_DOOMED |
-			     MNT_SYNC_UMOUNT | MNT_LOCKED
+			     MNT_SYNC_UMOUNT | MNT_LOCKED | MNT_UMOUNT
 };
 
 struct vfsmount {
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 5a67648721c7..dc2447f5f092 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -100,6 +100,7 @@ void exit_cred_namespaces(struct task_struct *tsk);
 void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new);
 int exec_task_namespaces(void);
 void deactivate_nsproxy(struct nsproxy *ns);
+void nsproxy_free(struct nsproxy *ns);
 int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **,
 	struct cred *, struct fs_struct *);
 int __init nsproxy_cache_init(void);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 91ce434a7e8d..6248711784b3 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1266,8 +1266,8 @@ enum {
 	NVME_ZRASF_ZONE_STATE_IMP_OPEN	= 0x02,
 	NVME_ZRASF_ZONE_STATE_EXP_OPEN	= 0x03,
 	NVME_ZRASF_ZONE_STATE_CLOSED	= 0x04,
-	NVME_ZRASF_ZONE_STATE_READONLY	= 0x05,
-	NVME_ZRASF_ZONE_STATE_FULL	= 0x06,
+	NVME_ZRASF_ZONE_STATE_FULL	= 0x05,
+	NVME_ZRASF_ZONE_STATE_READONLY	= 0x06,
 	NVME_ZRASF_ZONE_STATE_OFFLINE	= 0x07,
 	NVME_REPORT_ZONE_PARTIAL	= 1,
 };
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d31a8d107b1e..5ffcf5ce8c96 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -467,6 +467,7 @@ struct pci_dev {
 
 	unsigned int	is_busmaster:1;		/* Is busmaster */
 	unsigned int	no_msi:1;		/* May not use MSI */
+	unsigned int	no_aer_anfe:1;		/* Do not unmask ANFE */
 	unsigned int	block_cfg_access:1;	/* Config space access blocked */
 	unsigned int	broken_parity_status:1;	/* Generates false positive parity */
 	unsigned int	irq_reroute_variant:2;	/* Needs IRQ rerouting variant */
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index e749d2189335..0a4ea490d5ea 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -351,6 +351,16 @@ struct power_supply {
 	bool removing;
 	atomic_t use_cnt;
 	struct power_supply_battery_info *battery_info;
+	/*
+	 * Held for read while ->external_power_changed() runs, and for write by
+	 * power_supply_unregister() when it publishes @removing, so that it
+	 * waits for an in-flight callback to finish. Without this a driver's
+	 * data, typically devm-allocated on its own device, can be freed while
+	 * the callback is still using it.
+	 * Must not be shared with extensions_sem: callbacks may read their own
+	 * properties, which takes that one for read.
+	 */
+	struct rw_semaphore epc_sem;
 	struct rw_semaphore extensions_sem; /* protects "extensions" */
 	struct list_head extensions;
 #ifdef CONFIG_THERMAL
@@ -414,9 +424,9 @@ struct power_supply_vbat_ri_table {
  * @charge_voltage_max_uv: maintenance charging voltage that is usually a bit
  *   lower than the constant_charge_voltage_max_uv. We can apply this settings
  *   charge_current_max_ua until we get back up to this voltage.
- * @safety_timer_minutes: maintenance charging safety timer, with an expiry
- *   time in minutes. We will only use maintenance charging in this setting
- *   for a certain amount of time, then we will first move to the next
+ * @charge_safety_timer_minutes: maintenance charging safety timer, with an
+ *   expiry time in minutes. We will only use maintenance charging in this
+ *   setting for a certain amount of time, then we will first move to the next
  *   maintenance charge current and voltage pair in respective array and wait
  *   for the next safety timer timeout, or, if we reached the last maintencance
  *   charging setting, disable charging until we reach
diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 45a5df574aa6..747e10ec1a27 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -312,6 +312,7 @@ struct snd_ctl_elem_value;
 
 #define CS35L56_SDW1_PLAYBACK_PORT			1
 #define CS35L56_SDW1_CAPTURE_PORT			3
+#define CS35L56_OT25_CAPTURE_PORT			4
 
 #define CS35L56_NUM_BULK_SUPPLIES			3
 #define CS35L56_NUM_DSP_REGIONS				5
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 7d7820eab878..4f706aff14fc 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -634,12 +634,11 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 		prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
 		io_run_task_work();
 		io_uring_drop_tctx_refs(current);
+		/* only skip the sleep for local work this task may run */
 		xa_for_each(&tctx->xa, index, node) {
-			if (io_local_work_pending(node->ctx)) {
-				WARN_ON_ONCE(node->ctx->submitter_task &&
-					     node->ctx->submitter_task != current);
+			if (io_local_work_pending(node->ctx) &&
+			    io_allowed_defer_tw_run(node->ctx))
 				goto end_wait;
-			}
 		}
 		/*
 		 * If we've seen completions, retry without waiting. This
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index cbea989c5a7c..cf5218d100d9 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2070,8 +2070,9 @@ int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 
 static void io_rings_free(struct io_ring_ctx *ctx)
 {
-	io_free_region(ctx->user, &ctx->sq_region);
-	io_free_region(ctx->user, &ctx->ring_region);
+	/* ring memory is not charged to RLIMIT_MEMLOCK, hence no user */
+	io_free_region(NULL, &ctx->sq_region);
+	io_free_region(NULL, &ctx->ring_region);
 	ctx->rings = NULL;
 	RCU_INIT_POINTER(ctx->rings_rcu, NULL);
 	ctx->sq_sqes = NULL;
@@ -2735,7 +2736,8 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 		rd.user_addr = p->cq_off.user_addr;
 		rd.flags |= IORING_MEM_REGION_TYPE_USER;
 	}
-	ret = io_create_region(ctx, &ctx->ring_region, &rd, IORING_OFF_CQ_RING);
+	/* ring memory is not charged to RLIMIT_MEMLOCK, hence no user */
+	ret = io_create_region(NULL, &ctx->ring_region, &rd, IORING_OFF_CQ_RING);
 	if (ret)
 		return ret;
 	ctx->rings = rings = io_region_get_ptr(&ctx->ring_region);
@@ -2749,7 +2751,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 		rd.user_addr = p->sq_off.user_addr;
 		rd.flags |= IORING_MEM_REGION_TYPE_USER;
 	}
-	ret = io_create_region(ctx, &ctx->sq_region, &rd, IORING_OFF_SQES);
+	ret = io_create_region(NULL, &ctx->sq_region, &rd, IORING_OFF_SQES);
 	if (ret) {
 		io_rings_free(ctx);
 		return ret;
@@ -2960,7 +2962,8 @@ static void io_ctx_restriction_clone(struct io_ring_ctx *ctx,
 	if (dst->op_registered)
 		ctx->int_flags |= IO_RING_F_OP_RESTRICTED;
 	if (dst->reg_registered)
-		ctx->int_flags |= IO_RING_F_REG_RESTRICTED;
+		ctx->int_flags |= IO_RING_F_REG_RESTRICTED |
+				  IO_RING_F_RESTRICT_INHERITED;
 }
 
 static __cold int io_uring_create(struct io_ctx_config *config)
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 7c309173dd19..6e2facf34bfa 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -459,7 +459,7 @@ static int io_remove_buffers_legacy(struct io_ring_ctx *ctx,
 static void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
 {
 	if (bl->flags & IOBL_BUF_RING)
-		io_free_region(ctx->user, &bl->region);
+		io_free_region(NULL, &bl->region);
 	else
 		io_remove_buffers_legacy(ctx, bl, -1U);
 
@@ -676,7 +676,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 		rd.user_addr = reg.ring_addr;
 		rd.flags |= IORING_MEM_REGION_TYPE_USER;
 	}
-	ret = io_create_region(ctx, &bl->region, &rd, mmap_offset);
+	ret = io_create_region(NULL, &bl->region, &rd, mmap_offset);
 	if (ret)
 		goto fail;
 	br = io_region_get_ptr(&bl->region);
@@ -709,7 +709,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	if (!ret)
 		return 0;
 fail:
-	io_free_region(ctx->user, &bl->region);
+	io_free_region(NULL, &bl->region);
 	kfree(bl);
 	return ret;
 }
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 48c0eb012412..d4d716946971 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -204,7 +204,7 @@ done:
 	return 0;
 }
 
-int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
+int io_create_region(struct user_struct *user, struct io_mapped_region *mr,
 		     struct io_uring_region_desc *reg,
 		     unsigned long mmap_offset)
 {
@@ -230,8 +230,8 @@ int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
 		return -EOVERFLOW;
 
 	nr_pages = reg->size >> PAGE_SHIFT;
-	if (ctx->user) {
-		ret = __io_account_mem(ctx->user, nr_pages);
+	if (user) {
+		ret = __io_account_mem(user, nr_pages);
 		if (ret)
 			return ret;
 	}
@@ -240,7 +240,7 @@ int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
 	if (reg->flags & IORING_MEM_REGION_TYPE_USER)
 		ret = io_region_pin_pages(mr, reg);
 	else
-		ret = io_region_allocate_pages(mr, reg, mmap_offset, ctx->user);
+		ret = io_region_allocate_pages(mr, reg, mmap_offset, user);
 	if (ret)
 		goto out_free;
 
@@ -249,7 +249,7 @@ int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
 		goto out_free;
 	return 0;
 out_free:
-	io_free_region(ctx->user, mr);
+	io_free_region(user, mr);
 	return ret;
 }
 
diff --git a/io_uring/memmap.h b/io_uring/memmap.h
index f4cfbb6b9a1f..0714bb5a9616 100644
--- a/io_uring/memmap.h
+++ b/io_uring/memmap.h
@@ -18,7 +18,7 @@ unsigned long io_uring_get_unmapped_area(struct file *file, unsigned long addr,
 int io_uring_mmap(struct file *file, struct vm_area_struct *vma);
 
 void io_free_region(struct user_struct *user, struct io_mapped_region *mr);
-int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
+int io_create_region(struct user_struct *user, struct io_mapped_region *mr,
 		     struct io_uring_region_desc *reg,
 		     unsigned long mmap_offset);
 
diff --git a/io_uring/net.c b/io_uring/net.c
index 050ed274170a..f5f4f3ce6ef3 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -7,6 +7,7 @@
 #include <linux/un.h>
 #include <linux/compat.h>
 #include <net/compat.h>
+#include <net/ipv6.h>
 #include <linux/io_uring.h>
 
 #include <uapi/linux/io_uring.h>
@@ -1741,7 +1742,8 @@ void io_connect_bpf_populate(struct io_uring_bpf_ctx *bctx, struct io_kiocb *req
 	case AF_INET6: {
 		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)ss;
 
-		if (conn->addr_len < (int)sizeof(*sin6))
+		/* The IPv6 stack accepts SIN6_LEN_RFC2133; port and addr are in it. */
+		if (conn->addr_len < SIN6_LEN_RFC2133)
 			break;
 		bctx->connect.port = sin6->sin6_port;
 		memcpy(bctx->connect.v6_addr, &sin6->sin6_addr,
diff --git a/io_uring/register.c b/io_uring/register.c
index 02bc103bcc9d..dab3eb4258df 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -480,8 +480,9 @@ struct io_ring_ctx_rings {
 static void io_register_free_rings(struct io_ring_ctx *ctx,
 				   struct io_ring_ctx_rings *r)
 {
-	io_free_region(ctx->user, &r->sq_region);
-	io_free_region(ctx->user, &r->ring_region);
+	/* ring memory is not charged to RLIMIT_MEMLOCK, hence no user */
+	io_free_region(NULL, &r->sq_region);
+	io_free_region(NULL, &r->ring_region);
 }
 
 #define swap_old(ctx, o, n, field)		\
@@ -529,7 +530,7 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 		rd.user_addr = p->cq_off.user_addr;
 		rd.flags |= IORING_MEM_REGION_TYPE_USER;
 	}
-	ret = io_create_region(ctx, &n.ring_region, &rd, IORING_OFF_CQ_RING);
+	ret = io_create_region(NULL, &n.ring_region, &rd, IORING_OFF_CQ_RING);
 	if (ret)
 		return ret;
 
@@ -559,7 +560,7 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 		rd.user_addr = p->sq_off.user_addr;
 		rd.flags |= IORING_MEM_REGION_TYPE_USER;
 	}
-	ret = io_create_region(ctx, &n.sq_region, &rd, IORING_OFF_SQES);
+	ret = io_create_region(NULL, &n.sq_region, &rd, IORING_OFF_SQES);
 	if (ret) {
 		io_register_free_rings(ctx, &n);
 		return ret;
@@ -730,7 +731,8 @@ static int io_register_mem_region(struct io_ring_ctx *ctx, void __user *uarg)
 	    !(ctx->flags & IORING_SETUP_R_DISABLED))
 		return -EINVAL;
 
-	ret = io_create_region(ctx, &region, &rd, IORING_MAP_OFF_PARAM_REGION);
+	ret = io_create_region(ctx->user, &region, &rd,
+			       IORING_MAP_OFF_PARAM_REGION);
 	if (ret)
 		return ret;
 	if (copy_to_user(rd_uptr, &rd, sizeof(rd))) {
@@ -764,7 +766,14 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	if (ctx->submitter_task && ctx->submitter_task != current)
 		return -EEXIST;
 
-	if ((ctx->int_flags & IO_RING_F_REG_RESTRICTED) && !(ctx->flags & IORING_SETUP_R_DISABLED)) {
+	/*
+	 * A disabled ring is exempt from its own register restrictions, so
+	 * that the creator can set them up and then enable the ring. That
+	 * does not apply to restrictions inherited from the task.
+	 */
+	if ((ctx->int_flags & IO_RING_F_REG_RESTRICTED) &&
+	    (!(ctx->flags & IORING_SETUP_R_DISABLED) ||
+	     (ctx->int_flags & IO_RING_F_RESTRICT_INHERITED))) {
 		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
 		if (!test_bit(opcode, ctx->restrictions.register_op))
 			return -EACCES;
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index dcff0b995d34..cc9df7e64a40 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -432,7 +432,7 @@ static int io_allocate_rbuf_ring(struct io_ring_ctx *ctx,
 	mmap_offset = IORING_MAP_OFF_ZCRX_REGION;
 	mmap_offset += (u64)id << IORING_OFF_ZCRX_SHIFT;
 
-	ret = io_create_region(ctx, &ifq->rq_region, rd, mmap_offset);
+	ret = io_create_region(ctx->user, &ifq->rq_region, rd, mmap_offset);
 	if (ret < 0)
 		return ret;
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index aa2f1c4588b9..5edea93ec635 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1844,10 +1844,10 @@ phys_addr_t default_swiotlb_base(void)
 phys_addr_t default_swiotlb_limit(void)
 {
 #ifdef CONFIG_SWIOTLB_DYNAMIC
-	return io_tlb_default_mem.phys_limit;
-#else
-	return io_tlb_default_mem.defpool.end - 1;
+	if (io_tlb_default_mem.can_grow)
+		return io_tlb_default_mem.phys_limit;
 #endif
+	return io_tlb_default_mem.defpool.end - 1;
 }
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/kernel/fork.c b/kernel/fork.c
index 10f2d05d816a..eb198c8dfdc7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3317,14 +3317,17 @@ int ksys_unshare(unsigned long unshare_flags)
 			shm_init_task(current);
 		}
 
+		if (new_fs) {
+			new_fs = switch_fs_struct(new_fs);
+			if (new_fs)
+				free_fs_struct(no_free_ptr(new_fs));
+		}
+
 		if (new_nsproxy) {
 			switch_task_namespaces(current, new_nsproxy);
 			new_nsproxy = NULL;
 		}
 
-		if (new_fs)
-			new_fs = switch_fs_struct(new_fs);
-
 		if (new_fd) {
 			guard(task_lock)(current);
 			swap(current->files, new_fd);
@@ -3340,8 +3343,9 @@ int ksys_unshare(unsigned long unshare_flags)
 	perf_event_namespaces(current);
 
 bad_unshare_cleanup_nsproxy:
+	/* never installed, so no active references to drop */
 	if (new_nsproxy)
-		put_nsproxy(new_nsproxy);
+		nsproxy_free(new_nsproxy);
 bad_unshare_cleanup_cred:
 	if (new_cred)
 		put_cred(new_cred);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index d9d3d5973bf5..3fb1595a4a59 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -61,7 +61,7 @@ static inline struct nsproxy *create_nsproxy(void)
 	return nsproxy;
 }
 
-static inline void nsproxy_free(struct nsproxy *ns)
+void nsproxy_free(struct nsproxy *ns)
 {
 	put_mnt_ns(ns->mnt_ns);
 	put_uts_ns(ns->uts_ns);
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 5fe980da545d..f1b9d52f624a 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -1149,6 +1149,10 @@ void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 
 			guard(raw_spinlock_irqsave)(&rq->scx.deferred_reenq_lock);
 
+			/* @dsq is being destroyed, see free_dsq_irq_workfn() */
+			if (unlikely(READ_ONCE(dsq->id) == SCX_DSQ_INVALID))
+				return;
+
 			if (list_empty(&dru->node))
 				list_move_tail(&dru->node, &rq->scx.deferred_reenq_users);
 			WRITE_ONCE(dru->flags, dru->flags | reenq_flags);
@@ -2403,11 +2407,14 @@ static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_fl
 void scx_move_local_task_to_local_dsq(struct scx_sched *sch, struct task_struct *p,
 				      u64 enq_flags, struct rq *dst_rq)
 {
-	struct scx_dispatch_q *dst_dsq = scx_resolve_local_dsq(sch, dst_rq, p, &enq_flags);
+	struct scx_dispatch_q *dst_dsq;
 
 	lockdep_assert_rq_held(dst_rq);
 
 	WARN_ON_ONCE(p->scx.holding_cpu >= 0);
+	scx_wait_dispatching(p);
+
+	dst_dsq = scx_resolve_local_dsq(sch, dst_rq, p, &enq_flags);
 
 	if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT))
 		dsq_insert_head(dst_dsq, p);
@@ -2587,8 +2594,12 @@ static bool unlink_dsq_and_switch_rq_lock(struct task_struct *p,
 	switch_rq_lock(locked_rq, src_rq);
 
 	/* task_rq couldn't have changed if we're still the holding cpu */
-	return likely(p->scx.holding_cpu == cpu) &&
-		!WARN_ON_ONCE(src_rq != task_rq(p));
+	if (likely(p->scx.holding_cpu == cpu) && !WARN_ON_ONCE(src_rq != task_rq(p))) {
+		scx_wait_dispatching(p);
+		return true;
+	}
+
+	return false;
 }
 
 static bool consume_remote_task(struct scx_sched *sch, struct rq *this_rq,
@@ -2631,6 +2642,8 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
 	lockdep_assert_held(&src_dsq->lock);
 	lockdep_assert_rq_held(src_rq);
 
+	scx_wait_dispatching(p);
+
 	if (dst_dsq->id == SCX_DSQ_LOCAL) {
 		dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
 		if (src_rq != dst_rq &&
@@ -3213,8 +3226,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		/*
 		 * If @p is runnable but we're about to enter a lower
 		 * sched_class, %SCX_OPS_ENQ_LAST must be set. Tell
-		 * ops.enqueue() that @p is the only one available for this cpu,
-		 * which should trigger an explicit follow-up scheduling event.
+		 * ops.enqueue() that @p is the only one available for this cpu.
 		 * This doesn't apply if the baseline access on the CPU is lost.
 		 *
 		 * Under core scheduling, a pick dispatches only when nothing is
@@ -3226,6 +3238,16 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 			WARN_ON_ONCE(!sched_core_enabled(rq) &&
 				     !(sch->ops.flags & SCX_OPS_ENQ_LAST));
 			scx_do_enqueue_task(rq, p, SCX_ENQ_LAST, -1);
+
+			/*
+			 * A task put on the local DSQ runs, as anywhere else.
+			 * Here the insert can't reschedule on its own: the pick
+			 * has settled on @next and @p is still curr, so
+			 * resched_curr() would flag @p and __schedule() clears
+			 * that right after the pick. Flag @next instead.
+			 */
+			if (p->scx.dsq == &rq->scx.local_dsq)
+				set_tsk_need_resched(next);
 		} else {
 			scx_do_enqueue_task(rq, p, 0, -1);
 		}
@@ -4470,11 +4492,12 @@ static bool local_task_should_reenq(struct rq *rq, struct task_struct *p,
 }
 
 /*
- * The dispatcher stores the final ops_state after dropping the DSQ lock, so @p
- * can be found on a DSQ while still %SCX_OPSS_DISPATCHING. Reenqueueing @p
- * before that store lands would have it clobber the new %SCX_OPSS_QUEUED.
+ * The dispatcher runs ops.dequeue() and stores the final ops_state after
+ * dropping the DSQ lock, so @p can be found on a DSQ while still
+ * %SCX_OPSS_DISPATCHING. Wait for the dispatch to finish before operating on
+ * @p.
  */
-void scx_reenq_wait_dispatching(struct task_struct *p)
+void scx_wait_dispatching(struct task_struct *p)
 {
 	if (unlikely(atomic_long_read_acquire(&p->scx.ops_state) == SCX_OPSS_DISPATCHING))
 		wait_ops_state(p, SCX_OPSS_DISPATCHING);
@@ -4523,7 +4546,7 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags)
 		if (!local_task_should_reenq(rq, p, &reenq_flags, &reason))
 			continue;
 
-		scx_reenq_wait_dispatching(p);
+		scx_wait_dispatching(p);
 		scx_dispatch_dequeue(rq, p);
 
 		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
@@ -4647,7 +4670,7 @@ static void reenq_user(struct rq *rq, struct scx_dispatch_q *dsq, u64 reenq_flag
 		}
 
 		/* @p is on @dsq, its rq and @dsq are locked */
-		scx_reenq_wait_dispatching(p);
+		scx_wait_dispatching(p);
 		dispatch_dequeue_locked(p, dsq);
 		raw_spin_unlock(&dsq->lock);
 
@@ -5171,8 +5194,8 @@ static void exit_dsq(struct scx_dispatch_q *dsq)
 		struct rq *rq = cpu_rq(cpu);
 
 		/*
-		 * There must have been a RCU grace period since the last
-		 * insertion and @dsq should be off the deferred list by now.
+		 * free_dsq_irq_workfn() cancelled the reenqs before the grace
+		 * period and schedule_dsq_reenq() queues nothing after that.
 		 */
 		if (WARN_ON_ONCE(!list_empty(&dru->node))) {
 			guard(raw_spinlock_irqsave)(&rq->scx.deferred_reenq_lock);
@@ -5196,8 +5219,26 @@ static void free_dsq_irq_workfn(struct irq_work *irq_work)
 	struct llist_node *to_free = llist_del_all(&dsqs_to_free);
 	struct scx_dispatch_q *dsq, *tmp_dsq;
 
-	llist_for_each_entry_safe(dsq, tmp_dsq, to_free, free_node)
+	llist_for_each_entry_safe(dsq, tmp_dsq, to_free, free_node) {
+		s32 cpu;
+
+		/*
+		 * Cancel pending reenqs. Only a run_deferred() that started
+		 * before the grace period can hold one, and it keeps IRQs off,
+		 * so the grace period waits for it. After this sweep,
+		 * schedule_dsq_reenq() sees the invalid id under the same lock
+		 * and queues nothing.
+		 */
+		for_each_possible_cpu(cpu) {
+			struct scx_dsq_pcpu *pcpu = per_cpu_ptr(dsq->pcpu, cpu);
+			struct rq *rq = cpu_rq(cpu);
+
+			guard(raw_spinlock_irqsave)(&rq->scx.deferred_reenq_lock);
+			list_del_init(&pcpu->deferred_reenq_user.node);
+		}
+
 		call_rcu(&dsq->rcu, free_dsq_rcufn);
+	}
 }
 
 static DEFINE_IRQ_WORK(free_dsq_irq_work, free_dsq_irq_workfn);
@@ -6068,15 +6109,12 @@ static void enable_bypass_dsp(struct scx_sched *sch)
 
 	/*
 	 * When a sub-sched bypasses, its tasks are queued on the bypass DSQs of
-	 * the nearest non-bypassing ancestor or root. As enable_bypass_dsp() is
-	 * called iff @sch is not already bypassed due to an ancestor bypassing,
-	 * we can assume that the parent is not bypassing and thus will be the
-	 * host of the bypass DSQs.
-	 *
-	 * While the situation may change in the future, the following
-	 * guarantees that the nearest non-bypassing ancestor or root has bypass
-	 * dispatch enabled while a descendant is bypassing, which is all that's
-	 * required.
+	 * the nearest non-bypassing ancestor or root. The parent hosts them
+	 * unless it is bypassing too. Then they sit further up and the parent
+	 * consumes only its own bypass DSQs, empty until it leaves bypass and
+	 * becomes the host. Either way the nearest non-bypassing ancestor or
+	 * root has bypass dispatch enabled while a descendant is bypassing,
+	 * which is all that's required.
 	 *
 	 * scx_bypass_dsp_enabled() test is used to determine whether to enter
 	 * the bypass dispatch handling path from both bypassing and hosting
@@ -6185,35 +6223,46 @@ void scx_bypass(struct scx_sched *sch, bool bypass)
 	struct scx_sched *pos;
 	unsigned long flags;
 	int cpu;
+	bool changed;
 
 	raw_spin_lock_irqsave(&scx_bypass_lock, flags);
 
 	if (bypass) {
-		if (!inc_bypass_depth(sch))
-			goto unlock;
-
-		enable_bypass_dsp(sch);
+		changed = inc_bypass_depth(sch);
+		if (changed)
+			enable_bypass_dsp(sch);
 	} else {
-		if (!dec_bypass_depth(sch))
-			goto unlock;
+		changed = dec_bypass_depth(sch);
 	}
 
 	/*
 	 * Bypass state is propagated to all descendants - an scx_sched bypasses
-	 * if itself or any of its ancestors are in bypass mode.
+	 * if itself or any of its ancestors are in bypass mode. A descendant's
+	 * depth is the sum of its own bypasses and its ancestors', so every
+	 * call propagates whether or not @sch changed state. The descendants'
+	 * claims are released below with @sch's, after their tasks have moved.
 	 */
 	raw_spin_lock(&scx_sched_lock);
 	scx_for_each_descendant_pre(pos, sch) {
 		if (pos == sch)
 			continue;
-		if (bypass)
-			inc_bypass_depth(pos);
-		else
+		if (bypass) {
+			if (inc_bypass_depth(pos))
+				enable_bypass_dsp(pos);
+		} else {
 			dec_bypass_depth(pos);
+		}
 	}
 	raw_spin_unlock(&scx_sched_lock);
 
 	/*
+	 * A descendant's depth is at least @sch's, so no bypass state changed
+	 * unless @sch's did.
+	 */
+	if (!changed)
+		goto unlock;
+
+	/*
 	 * No task property is changing. We just need to make sure all currently
 	 * queued tasks are re-queued according to the new scx_bypassing()
 	 * state. As an optimization, walk each rq's runnable_list instead of
@@ -6291,8 +6340,12 @@ void scx_bypass(struct scx_sched *sch, bool bypass)
 	}
 
 	/* disarming must come after moving all tasks out of the bypass DSQs */
-	if (!bypass)
-		scx_disable_bypass_dsp(sch);
+	if (!bypass) {
+		guard(raw_spinlock)(&scx_sched_lock);
+		scx_for_each_descendant_pre(pos, sch)
+			if (!pos->bypass_depth)
+				scx_disable_bypass_dsp(pos);
+	}
 unlock:
 	raw_spin_unlock_irqrestore(&scx_bypass_lock, flags);
 }
diff --git a/kernel/sched/ext/idle.c b/kernel/sched/ext/idle.c
index aa9fb6de0ad6..28ed9e327085 100644
--- a/kernel/sched/ext/idle.c
+++ b/kernel/sched/ext/idle.c
@@ -952,12 +952,43 @@ static bool is_bpf_migration_disabled(const struct task_struct *p)
 	return p->migration_disabled;
 }
 
+static s32 select_cpu_restricted(struct task_struct *p, s32 prev_cpu,
+				 const struct cpumask *allowed, u64 flags,
+				 bool migration_disabled)
+{
+	s32 cpu;
+
+	if (migration_disabled)
+		cpu = task_cpu(p);
+	else
+		cpu = cpumask_first(p->cpus_ptr);
+
+	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+		return -EBUSY;
+
+	if (allowed && !cpumask_test_cpu(cpu, allowed))
+		return -EBUSY;
+
+	if (flags & SCX_PICK_IDLE_IN_NODE) {
+		int node = scx_cpu_node_if_enabled(prev_cpu);
+
+		if (scx_cpu_node_if_enabled(cpu) != node)
+			return -EBUSY;
+	}
+
+	if (!scx_idle_test_and_clear_cpu(cpu))
+		return -EBUSY;
+
+	return cpu;
+}
+
 static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p,
 				 s32 prev_cpu, u64 wake_flags,
 				 const struct cpumask *allowed, u64 flags)
 {
 	unsigned long irq_flags;
 	bool we_locked = false;
+	bool migration_disabled;
 	s32 cpu;
 
 	if (!scx_cpu_valid(sch, prev_cpu, NULL))
@@ -994,20 +1025,17 @@ static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p,
 
 	/*
 	 * This may also be called from ops.enqueue(), so we need to handle
-	 * per-CPU tasks as well. For these tasks, we can skip all idle CPU
-	 * selection optimizations and simply check whether the previously
-	 * used CPU is idle and within the allowed cpumask.
+	 * per-CPU tasks as well. For these tasks, skip general idle CPU
+	 * selection and validate the task's only usable CPU directly.
 	 */
-	if (p->nr_cpus_allowed == 1 || is_bpf_migration_disabled(p)) {
-		if (cpumask_test_cpu(prev_cpu, allowed ?: p->cpus_ptr) &&
-		    scx_idle_test_and_clear_cpu(prev_cpu))
-			cpu = prev_cpu;
-		else
-			cpu = -EBUSY;
-	} else {
+	migration_disabled = is_bpf_migration_disabled(p);
+
+	if (p->nr_cpus_allowed == 1 || migration_disabled)
+		cpu = select_cpu_restricted(p, prev_cpu, allowed, flags,
+					    migration_disabled);
+	else
 		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags,
 					 allowed ?: p->cpus_ptr, flags);
-	}
 
 	if (we_locked)
 		raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index 5b37faa532d6..352547aedbb7 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -1774,8 +1774,9 @@ enum scx_enq_flags {
 	 * %SCX_OPS_ENQ_LAST is specified, they're ops.enqueue()'d with the
 	 * %SCX_ENQ_LAST flag set.
 	 *
-	 * The BPF scheduler is responsible for triggering a follow-up
-	 * scheduling event. Otherwise, Execution may stall.
+	 * If the task is queued on the local DSQ of the CPU it was running on,
+	 * it continues to run. Otherwise, the CPU goes idle. A scheduler that
+	 * wants a full dispatch cycle on the CPU should kick it.
 	 */
 	SCX_ENQ_LAST		= 1LLU << 41,
 
@@ -2122,7 +2123,7 @@ void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags);
 u64 __scx_bpf_now(struct rq *rq);
 void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 			u64 reenq_flags, struct rq *locked_rq);
-void scx_reenq_wait_dispatching(struct task_struct *p);
+void scx_wait_dispatching(struct task_struct *p);
 int __scx_init_task(struct scx_sched *sch, struct task_struct *p,
 		    struct cgroup *cgrp, bool fork);
 void scx_enable_task(struct scx_sched *sch, struct task_struct *p);
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 90441206d3b9..212de1cb8502 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -797,7 +797,7 @@ void scx_reenq_reject(struct rq *rq)
 		if (WARN_ON_ONCE(p->migration_pending))
 			continue;
 
-		scx_reenq_wait_dispatching(p);
+		scx_wait_dispatching(p);
 		scx_dispatch_dequeue(rq, p);
 
 		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c56c042d1c35..c1cb328bce3c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6320,7 +6320,7 @@ bool current_is_workqueue_mem_reclaim(void)
 {
 	struct worker *worker = current_wq_worker();
 
-	return worker &&
+	return worker && worker->current_pwq &&
 		((worker->current_pwq->wq->flags &
 		  (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM);
 }
diff --git a/lib/crypto/arm64/poly1305-armv8.pl b/lib/crypto/arm64/poly1305-armv8.pl
index f1930c6b55ce..234398ff6b60 100644
--- a/lib/crypto/arm64/poly1305-armv8.pl
+++ b/lib/crypto/arm64/poly1305-armv8.pl
@@ -375,7 +375,7 @@ poly1305_blocks_neon:
 	adc	$h1,$h1,xzr
 	lsr	$h2,x14,#24
 	adds	$h1,$h1,x14,lsl#40
-	adc	$d2,$h2,xzr		// can be partially reduced...
+	adc	$h2,$h2,xzr		// preserve carry into top limb
 
 	ldp	$d0,$d1,[$inp],#16	// load input
 	sub	$len,$len,#16
diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c
index f313ccc4b4dd..048c7afe8613 100644
--- a/lib/crypto/poly1305.c
+++ b/lib/crypto/poly1305.c
@@ -78,7 +78,7 @@ void poly1305_final(struct poly1305_desc_ctx *desc, u8 *dst)
 	}
 
 	poly1305_emit(&desc->state.h, dst, desc->s);
-	*desc = (struct poly1305_desc_ctx){};
+	memzero_explicit(desc, sizeof(*desc));
 }
 EXPORT_SYMBOL(poly1305_final);
 
diff --git a/lib/crypto/tests/poly1305_kunit.c b/lib/crypto/tests/poly1305_kunit.c
index f3cb6245bc29..d4490ee27c3d 100644
--- a/lib/crypto/tests/poly1305_kunit.c
+++ b/lib/crypto/tests/poly1305_kunit.c
@@ -55,16 +55,17 @@ static int poly1305_suite_init(struct kunit_suite *suite)
  * - Using an all-one-bits r_key tests the key clamping.
  * - Using an all-one-bits s_key tests carries in implementations of the
  *   addition mod 2**128 during finalization.
- * - Using all-one-bits message, and to a lesser extent r_key, tends to maximize
- *   any intermediate accumulator values.  This increases the chance of
- *   detecting bugs that occur only in rare cases where the accumulator values
- *   get very large, for example the bug fixed by commit 678cce4019d746da
- *   ("crypto: x86/poly1305 - fix overflow during partial reduction").
+ * - Using all-one-bits message and r_key results in large values for the
+ *   internal products of r_key by (accumulator + message block).  This
+ *   increases the chance of detecting bugs that occur only in rare cases where
+ *   the sum of these internal products is very large, for example the bug fixed
+ *   by commit 678cce4019d7 ("crypto: x86/poly1305 - fix overflow during partial
+ *   reduction").
  *
- * Accumulator overflow bugs may be specific to particular update lengths (in
- * blocks) and/or particular values of the previous acculumator.  Note that the
- * accumulator starts at 0 which gives the lowest chance of an overflow.  Thus,
- * a single all-one-bits test vector may be insufficient.
+ * Bugs with the handling of large internal product sums may be specific to
+ * particular update lengths (in blocks) and/or require that the accumulator
+ * also have a large value.  Note that the accumulator starts at 0.  Thus, a
+ * single all-one-bits test vector may be insufficient.
  *
  * Considering that, do the following test: continuously update a single
  * Poly1305 context with all-one-bits data of varying lengths (0, 16, 32, ...,
@@ -141,10 +142,88 @@ static void test_poly1305_reduction_edge_cases(struct kunit *test)
 	}
 }
 
+/*
+ * Test that Poly1305 MACs are computed correctly when r_key=1, s_key=0, and the
+ * message consists of all-ones blocks.
+ *
+ * With r_key=1 and s_key=0, Poly1305 degrades to the sum of the padded blocks
+ * mod 2**130 - 5, then reduced mod 2**128.  A padded all-ones block maps to
+ * 2**128 + (2**128 - 1) = 2**129 - 1.  Two such blocks sum to 2**130 - 2, which
+ * is congruent to 3 mod 2**130 - 5.  Thus, the expected MAC is just 3 *
+ * floor(nblocks / 2), minus 1 if nblocks is odd, then reduced mod 2**128.  If
+ * nblocks == 1 this is 2**128 - 1, otherwise it's just a small integer.
+ *
+ * Inside the Poly1305 implementation in this case, the multiplication does
+ * nothing and each block just adds 2**129 - 1 to the accumulator.  Without the
+ * multiplication to mix things up, this results in some interesting values
+ * being reached where the limbs are at or near their maximum values, even after
+ * (lazy) reduction.  This can reproduce bugs that happen only in such cases.
+ *
+ * For example, this test case reproduces the bug fixed by commit 24f07e8c07a0
+ * ("lib/crypto: arm64: Fix lost Poly1305 carry when resuming NEON state").
+ *
+ * However, reaching that bug required two consecutive updates: one with >= 8
+ * blocks to cause NEON code to be used and leave the accumulator in base 2**26
+ * with its limbs in a certain pattern, then one with an odd number of blocks >=
+ * 9 to cause NEON to be used again, but first processing one block using scalar
+ * code as a special case, triggering a conversion to base 2**64 where the carry
+ * into the 2**128 bit was lost.  To cover this and other similar edge cases
+ * that may exist in other Poly1305 implementations, just test all possible
+ * block-aligned splits between three poly1305_update() calls.
+ */
+static void test_poly1305_split_update_carry(struct kunit *test)
+{
+	static const u8 key[POLY1305_KEY_SIZE] = { 1 }; /* r_key=1, s_key=0 */
+	/*
+	 * Use max_nblocks=66 so that it's a bit more than twice the AVX-512
+	 * threshold of 32 blocks.
+	 */
+	const int max_nblocks = 66;
+	u8 *data = alloc_buf(test, max_nblocks * POLY1305_BLOCK_SIZE);
+	u8 expected_mac[POLY1305_DIGEST_SIZE];
+	u8 actual_mac[POLY1305_DIGEST_SIZE];
+	struct poly1305_desc_ctx ctx;
+
+	KUNIT_ASSERT_LE(test, 3 * (max_nblocks / 2), U8_MAX);
+
+	memset(data, 0xff, max_nblocks * POLY1305_BLOCK_SIZE);
+
+	for (int nblocks = 0; nblocks <= max_nblocks; nblocks++) {
+		size_t len = nblocks * POLY1305_BLOCK_SIZE;
+
+		expected_mac[0] = 3 * (nblocks / 2) - (nblocks % 2);
+		memset(&expected_mac[1], nblocks == 1 ? 0xff : 0,
+		       POLY1305_DIGEST_SIZE - 1);
+		for (size_t part1_len = 0; part1_len <= len;
+		     part1_len += POLY1305_BLOCK_SIZE) {
+			for (size_t part2_len = 0; part2_len <= len - part1_len;
+			     part2_len += POLY1305_BLOCK_SIZE) {
+				size_t part3_len = len - part1_len - part2_len;
+
+				poly1305_init(&ctx, key);
+				poly1305_update(&ctx, data, part1_len);
+				poly1305_update(&ctx, &data[part1_len],
+						part2_len);
+				poly1305_update(&ctx,
+						&data[part1_len + part2_len],
+						part3_len);
+				poly1305_final(&ctx, actual_mac);
+				KUNIT_ASSERT_MEMEQ_MSG(
+					test, actual_mac, expected_mac,
+					POLY1305_DIGEST_SIZE,
+					"Failed with nblocks=%d, part1_len=%zu, part2_len=%zu, part3_len=%zu",
+					nblocks, part1_len, part2_len,
+					part3_len);
+			}
+		}
+	}
+}
+
 static struct kunit_case poly1305_test_cases[] = {
 	HASH_KUNIT_CASES,
 	KUNIT_CASE(test_poly1305_allones_keys_and_message),
 	KUNIT_CASE(test_poly1305_reduction_edge_cases),
+	KUNIT_CASE(test_poly1305_split_update_carry),
 	KUNIT_CASE(benchmark_hash),
 	{},
 };
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 194772ed0cb9..3017a456d289 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1318,7 +1318,7 @@ static int calipso_skbuff_setattr(struct sk_buff *skb,
 	struct ipv6hdr *ip6_hdr;
 	struct ipv6_opt_hdr *hop;
 	unsigned char buf[CALIPSO_MAX_BUFFER];
-	int len_delta, new_end, pad, payload;
+	int len_delta, new_end, pad;
 	unsigned int start, end;
 
 	ip6_hdr = ipv6_hdr(skb);
@@ -1357,8 +1357,8 @@ static int calipso_skbuff_setattr(struct sk_buff *skb,
 			sizeof(*ip6_hdr) + start);
 		skb_reset_network_header(skb);
 		ip6_hdr = ipv6_hdr(skb);
-		payload = ntohs(ip6_hdr->payload_len);
-		ip6_hdr->payload_len = htons(payload + len_delta);
+		/* 0 above IPV6_MAXPLEN (BIG TCP), the real length otherwise */
+		ipv6_set_payload_len(ip6_hdr, skb->len - sizeof(*ip6_hdr));
 	}
 
 	hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 6d2530e33540..a904dc3bcad6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -461,7 +461,7 @@ netlink_unlock_table(void)
 
 struct netlink_compare_arg
 {
-	possible_net_t pnet;
+	u64 net_cookie;
 	u32 portid;
 };
 
@@ -476,14 +476,14 @@ static inline int netlink_compare(struct rhashtable_compare_arg *arg,
 	const struct netlink_sock *nlk = ptr;
 
 	return nlk->portid != x->portid ||
-	       !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
+	       sock_net(&nlk->sk)->net_cookie != x->net_cookie;
 }
 
 static void netlink_compare_arg_init(struct netlink_compare_arg *arg,
 				     struct net *net, u32 portid)
 {
 	memset(arg, 0, sizeof(*arg));
-	write_pnet(&arg->pnet, net);
+	arg->net_cookie = net->net_cookie;
 	arg->portid = portid;
 }
 
@@ -1360,6 +1360,8 @@ retry:
 	if (netlink_is_kernel(sk))
 		return netlink_unicast_kernel(sk, skb, ssk);
 
+	skb_reset_network_header(skb);
+	skb_reset_mac_header(skb);
 	if (sk_filter(sk, skb)) {
 		err = skb->len;
 		kfree_skb(skb);
@@ -1494,6 +1496,8 @@ static void do_one_broadcast(struct sock *sk,
 		goto out;
 	}
 
+	skb_reset_network_header(p->skb2);
+	skb_reset_mac_header(p->skb2);
 	if (sk_filter(sk, p->skb2)) {
 		kfree_skb(p->skb2);
 		p->skb2 = NULL;
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 3f853004c490..12559a8ca912 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -52,7 +52,7 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 {
 	/* this can be null in the listening path */
 	struct rds_connection *conn = cm_id->context;
-	struct rds_transport *trans;
+	struct rds_transport *trans = &rds_ib_transport;
 	int ret = 0;
 	int *err;
 	u8 len;
@@ -60,9 +60,6 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 	rdsdebug("conn %p id %p handling event %u (%s)\n", conn, cm_id,
 		 event->event, rdma_event_msg(event->event));
 
-	if (cm_id->device->node_type == RDMA_NODE_IB_CA)
-		trans = &rds_ib_transport;
-
 	/* Prevent shutdown from tearing down the connection
 	 * while we're executing. */
 	if (conn) {
@@ -82,16 +79,47 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
+		/* Only the IB transport is supported, but RDS listens on
+		 * every RDMA device: reject a request that arrived on any
+		 * other kind.  A non-zero return has rdma_cm destroy the
+		 * request's id, which is what we want here and only here.
+		 */
+		if (cm_id->device->node_type != RDMA_NODE_IB_CA) {
+			ret = 1;
+			break;
+		}
 		ret = trans->cm_handle_connect(cm_id, event, isv6);
 		break;
 
 	case RDMA_CM_EVENT_ADDR_RESOLVED:
 		if (conn) {
+			/* The address resolved to a device RDS has no
+			 * transport for.  Do not go on to resolve a route:
+			 * an iWARP route leaves cm_id->route.path_rec
+			 * unset, which the ROUTE_RESOLVED case below
+			 * dereferences.  Drop the connection instead; the
+			 * id is still ic->i_cm_id, so return 0 and let the
+			 * shutdown destroy it.
+			 */
+			if (cm_id->device->node_type != RDMA_NODE_IB_CA) {
+				rds_conn_drop(conn);
+				break;
+			}
 			rdma_set_service_type(cm_id, conn->c_tos);
 			rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32);
-			/* XXX do we need to clean up if this fails? */
 			ret = rdma_resolve_route(cm_id,
 						 RDS_RDMA_RESOLVE_TIMEOUT_MS);
+			if (ret) {
+				/* A non-zero return has the rdma_cm destroy
+				 * the id, but it is still ic->i_cm_id, which
+				 * the connection's shutdown would then
+				 * disconnect and destroy again.  Drop the
+				 * connection and keep the id for that
+				 * shutdown.
+				 */
+				rds_conn_drop(conn);
+				ret = 0;
+			}
 		}
 		break;
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 6e48b4bc2d75..cd6e68e8af1b 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -372,9 +372,10 @@ static int __tcf_action_put(struct tc_action *p, bool bind)
 {
 	struct tcf_idrinfo *idrinfo = p->idrinfo;
 
-	if (refcount_dec_and_mutex_lock(&p->tcfa_refcnt, &idrinfo->lock)) {
-		if (bind)
-			atomic_dec(&p->tcfa_bindcnt);
+	mutex_lock(&idrinfo->lock);
+	if (bind)
+		atomic_dec(&p->tcfa_bindcnt);
+	if (refcount_dec_and_test(&p->tcfa_refcnt)) {
 		idr_remove(&idrinfo->action_idr, p->tcfa_index);
 		mutex_unlock(&idrinfo->lock);
 
@@ -382,9 +383,7 @@ static int __tcf_action_put(struct tc_action *p, bool bind)
 		return 1;
 	}
 
-	if (bind)
-		atomic_dec(&p->tcfa_bindcnt);
-
+	mutex_unlock(&idrinfo->lock);
 	return 0;
 }
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index e35692dd8d30..321898f22d80 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1786,6 +1786,18 @@ static int sctp_sendmsg_check_sflags(struct sctp_association *asoc,
 	return 1;
 }
 
+static int sctp_sendmsg_check_stream(struct sctp_association *asoc,
+				     struct sctp_sndrcvinfo *sinfo)
+{
+	if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt))
+		return -EINVAL;
+
+	if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext))
+		return sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream);
+
+	return 0;
+}
+
 static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 				struct msghdr *msg, size_t msg_len,
 				struct sctp_transport *transport,
@@ -1800,16 +1812,9 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 	long timeo;
 	int err;
 
-	if (sinfo->sinfo_stream >= asoc->stream.outcnt) {
-		err = -EINVAL;
+	err = sctp_sendmsg_check_stream(asoc, sinfo);
+	if (err)
 		goto err;
-	}
-
-	if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) {
-		err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream);
-		if (err)
-			goto err;
-	}
 
 	if (sp->disable_fragments && msg_len > asoc->frag_point) {
 		err = -EMSGSIZE;
@@ -1830,10 +1835,9 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 		err = sctp_wait_for_sndbuf(asoc, transport, &timeo, msg_len);
 		if (err)
 			goto err;
-		if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) {
-			err = -EINVAL;
+		err = sctp_sendmsg_check_stream(asoc, sinfo);
+		if (err)
 			goto err;
-		}
 	}
 
 	if (sctp_state(asoc, CLOSED)) {
@@ -1848,6 +1852,11 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 				err = -ESRCH;
 				goto err;
 			}
+			err = sctp_sendmsg_check_stream(asoc, sinfo);
+			if (err) {
+				err = -ESRCH;
+				goto err;
+			}
 		} else {
 			wait_connect = true;
 		}
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 1c2d1cea67f4..483af15a5109 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1836,23 +1836,22 @@ static int vsock_connect(struct socket *sock, struct sockaddr_unsized *addr,
 		timeout = schedule_timeout(timeout);
 		lock_sock(sk);
 
-		/* Connection established. Whatever happens to socket once we
-		 * release it, that's not connect()'s concern. No need to go
+		/* Connection was established. Whatever happens to socket once
+		 * we release it, that's not connect()'s concern. No need to go
 		 * into signal and timeout handling. Call it a day.
 		 *
 		 * Note that allowing to "reset" an already established socket
 		 * here is racy and insecure.
 		 */
-		if (sk->sk_state == TCP_ESTABLISHED)
-			break;
+		if (sk->sk_state == TCP_ESTABLISHED ||
+		    sk->sk_state == TCP_CLOSING) {
+			err = 0;
+			goto out_wait;
+		}
 
 		/* If connection was _not_ established and a signal/timeout came
 		 * to be, we want the socket's state reset. User space may want
-		 * to retry.
-		 *
-		 * sk_state != TCP_ESTABLISHED implies that socket is not on
-		 * vsock_connected_table. We keep the binding and the transport
-		 * assigned.
+		 * to retry, so we keep the binding and the transport assigned.
 		 */
 		if (signal_pending(current) || timeout == 0) {
 			err = timeout == 0 ? -ETIMEDOUT : sock_intr_errno(timeout);
diff --git a/security/landlock/domain.h b/security/landlock/domain.h
index caa3d19d2c43..428c1d9890db 100644
--- a/security/landlock/domain.h
+++ b/security/landlock/domain.h
@@ -242,9 +242,14 @@ struct landlock_domain {
 			 * to properly handle merged rulesets without
 			 * overlapping access rights.  These layers are set once
 			 * and never changed for the lifetime of the domain.
+			 *
+			 * Not annotated with __counted_by(num_layers): clang
+			 * miscomputes the counter address for a FAM nested in
+			 * an anonymous struct within a union, which trips
+			 * FORTIFY:
+			 * https://github.com/llvm/llvm-project/pull/228309
 			 */
-			struct access_masks
-				handled_masks[] __counted_by(num_layers);
+			struct access_masks handled_masks[];
 		};
 	};
 };
diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index be5482530aa2..1623cf926c71 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7646,6 +7646,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8be8, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8be9, "HP Envy x360 2-in-1 Laptop 15-fh0xxx", ALC245_FIXUP_HP_ENVY_X360_15_FH0XXX),
 	SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8bfd, "HP Pavilion 15-eg3xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c15, "HP Spectre x360 2-in-1 Laptop 14-eu0xxx", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
 	SND_PCI_QUIRK(0x103c, 0x8c16, "HP Spectre x360 2-in-1 Laptop 16-aa0xxx", ALC245_FIXUP_HP_SPECTRE_X360_16_AA0XXX),
 	SND_PCI_QUIRK(0x103c, 0x8c17, "HP Spectre x360 2-in-1 Laptop 16-aa0xxx", ALC245_FIXUP_HP_SPECTRE_X360_16_AA0XXX),
@@ -8346,6 +8347,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x9e56, "Lenovo ZhaoYang CF4620Z", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1849, 0x0269, "Positivo Master C6400", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK),
+	SND_PCI_QUIRK(0x1849, 0x6256, "ASRock NUC Box 358H", ALC233_FIXUP_NO_AUDIO_JACK),
 	SND_PCI_QUIRK(0x1849, 0xa233, "Positivo Master C6300", ALC269_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1854, 0x0440, "LG CQ6", ALC256_FIXUP_HEADPHONE_AMP_VOL),
 	SND_PCI_QUIRK(0x1854, 0x0441, "LG CQ6 AIO", ALC256_FIXUP_HEADPHONE_AMP_VOL),
diff --git a/sound/hda/codecs/side-codecs/tas2781_hda.c b/sound/hda/codecs/side-codecs/tas2781_hda.c
index b22f93424c62..e0da299df780 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda.c
@@ -139,9 +139,21 @@ static void tas2781_apply_calib(struct tasdevice_priv *p)
 		 */
 		crc = crc32(~0, data, 84) ^ ~0;
 		if (crc != tmp_val[21]) {
-			cali_data->total_sz = 0;
-			dev_err(p->dev, "%s: V1 CRC error\n", __func__);
-			return;
+			/*
+			 * Some Lenovo BIOSes (e.g. Legion Pro 7 16IRX9H,
+			 * SSID 17aa:38cd) store valid V1 calibration data
+			 * but leave TimeStamp and CRC zeroed.
+			 */
+			if (!tmp_val[20] && !tmp_val[21] &&
+			    tmp_val[0] && tmp_val[1]) {
+				dev_warn(p->dev,
+					 "%s: V1 data without CRC, accepting\n",
+					 __func__);
+			} else {
+				cali_data->total_sz = 0;
+				dev_err(p->dev, "%s: V1 CRC error\n", __func__);
+				return;
+			}
 		}
 
 		for (j = p->ndev - 1; j >= 0; j--) {
diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c
index 9be70c6862ab..27e502fa493e 100644
--- a/sound/pci/ctxfi/ctdaio.c
+++ b/sound/pci/ctxfi/ctdaio.c
@@ -221,14 +221,18 @@ static int dao_set_right_input(struct dao *dao, struct rsc *input)
 
 static int dao_clear_input(struct dao *dao, unsigned int start, unsigned int end)
 {
+	struct imapper *entry;
 	unsigned int i;
 
-	if (!dao->imappers[start])
+	entry = dao->imappers[start];
+	if (!entry)
 		return 0;
+
 	for (i = start; i < end; i++) {
 		dao->mgr->imap_delete(dao->mgr, dao->imappers[i]);
 		dao->imappers[i] = NULL;
 	}
+	kfree(entry);
 
 	return 0;
 }
diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c
index b3b73096ac74..3d48bb0f100f 100644
--- a/sound/soc/amd/acp-config.c
+++ b/sound/soc/amd/acp-config.c
@@ -31,6 +31,13 @@ static const struct dmi_system_id acp70_acpi_flag_override_table[] = {
 		},
 	},
 	{
+		/* ASUS EXPERTBOOK AM7406CKA (Kraken Point, ACP 7.0) */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK AM7406CKA"),
+		},
+	},
+	{
 		/* ASUS Zenbook S16 UM5606GA (Strix Point, ACP 7.0) */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/sound/soc/amd/acp/amd-acp70-acpi-match.c b/sound/soc/amd/acp/amd-acp70-acpi-match.c
index 2a9da6de7bbc..c2f0479301eb 100644
--- a/sound/soc/amd/acp/amd-acp70-acpi-match.c
+++ b/sound/soc/amd/acp/amd-acp70-acpi-match.c
@@ -335,6 +335,27 @@ static const struct snd_soc_acpi_adr_device cs42l43b_l0u1_adr[] = {
 	}
 };
 
+static const struct snd_soc_acpi_adr_device cs42l43b_l0u1_cs35l57x2_l0u01_adr[] = {
+	{
+		.adr = 0x00003101FA2A3B01ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	},
+	{
+		.adr = 0x00003001FA355701ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00003101FA355701ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+};
+
 static const struct snd_soc_acpi_adr_device cs42l43_l1u0_cs35l56x4_l1u0123_adr[] = {
 	{
 		.adr = 0x00013001FA424301ull,
@@ -438,6 +459,15 @@ static const struct snd_soc_acpi_link_adr acp70_cs42l43_l0u0_cs35l56x4_l1u3210[]
 	{}
 };
 
+static const struct snd_soc_acpi_link_adr acp70_cs42l43b_l0u1_cs35l57x2_l0u01[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l43b_l0u1_cs35l57x2_l0u01_adr),
+		.adr_d = cs42l43b_l0u1_cs35l57x2_l0u01_adr,
+	},
+	{}
+};
+
 static const struct snd_soc_acpi_link_adr acp70_cs42l43_l1u0_cs35l56x4_l1u0123[] = {
 	{
 		.mask = BIT(1),
@@ -821,6 +851,11 @@ struct snd_soc_acpi_mach snd_soc_acpi_amd_acp70_sdw_machines[] = {
 		.drv_name = "amd_sdw",
 	},
 	{
+		.link_mask = BIT(0),
+		.links = acp70_cs42l43b_l0u1_cs35l57x2_l0u01,
+		.drv_name = "amd_sdw",
+	},
+	{
 		.link_mask = BIT(1),
 		.links = acp70_cs42l43_l1u0_cs35l56x4_l1u0123,
 		.drv_name = "amd_sdw",
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index e798bf6a9cd0..1be8504571ad 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -790,6 +790,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "MDC"),
+			DMI_MATCH(DMI_BOARD_NAME, "Herbag2_MDU"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "System76"),
 			DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"),
 		}
diff --git a/sound/soc/codecs/adau1372.c b/sound/soc/codecs/adau1372.c
index cc174ec3a1f8..c3d3be898ba6 100644
--- a/sound/soc/codecs/adau1372.c
+++ b/sound/soc/codecs/adau1372.c
@@ -798,7 +798,7 @@ static int adau1372_set_power(struct adau1372 *adau1372, bool enable)
 		if (ret)
 			return ret;
 		if (adau1372->pd_gpio)
-			gpiod_set_value(adau1372->pd_gpio, 0);
+			gpiod_set_value_cansleep(adau1372->pd_gpio, 0);
 
 		if (adau1372->switch_mode)
 			adau1372->switch_mode(adau1372->dev);
@@ -818,8 +818,7 @@ static int adau1372_set_power(struct adau1372 *adau1372, bool enable)
 							   ADAU1372_CLK_CTRL_PLL_EN,
 							   0);
 				regcache_cache_only(adau1372->regmap, true);
-				if (adau1372->pd_gpio)
-					gpiod_set_value(adau1372->pd_gpio, 1);
+				gpiod_set_value_cansleep(adau1372->pd_gpio, 1);
 				clk_disable_unprepare(adau1372->mclk);
 				return ret;
 			}
@@ -836,7 +835,7 @@ static int adau1372_set_power(struct adau1372 *adau1372, bool enable)
 			 * map. No need to do any register writes to manually
 			 * turn things off.
 			 */
-			gpiod_set_value(adau1372->pd_gpio, 1);
+			gpiod_set_value_cansleep(adau1372->pd_gpio, 1);
 			regcache_mark_dirty(adau1372->regmap);
 		} else {
 			regmap_update_bits(adau1372->regmap, ADAU1372_REG_CLK_CTRL,
@@ -1003,6 +1002,17 @@ int adau1372_probe(struct device *dev, struct regmap *regmap,
 
 	regmap_write(regmap, ADAU1372_REG_OP_STAGE_MUTE, 0x0);
 
+	/*
+	 * Set sane default values for the Output ASRC and DAC input muxes,
+	 * since the power-on reset defaults are invalid "Reserved" states.
+	 */
+	regmap_write(regmap, ADAU1372_REG_ASRCO_SOURCE_0_1,
+		     0x54); /* Decimator0, Decimator1 */
+	regmap_write(regmap, ADAU1372_REG_ASRCO_SOURCE_2_3,
+		     0x76); /* Decimator2, Decimator3 */
+	regmap_write(regmap, ADAU1372_REG_DAC_SOURCE,
+		     0xdc); /* Input ASRC0, Input ASRC1 */
+
 	regmap_write(regmap, 0x7, 0x01); /* CLOCK OUT */
 
 	return  devm_snd_soc_register_component(dev, &adau1372_driver, &adau1372_dai_driver, 1);
diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c
index 98bb4542b914..e10f04d677f4 100644
--- a/sound/soc/codecs/cs35l56-sdw.c
+++ b/sound/soc/codecs/cs35l56-sdw.c
@@ -265,11 +265,11 @@ static int cs35l56_sdw_read_prop(struct sdw_slave *peripheral)
 	if (ret == 0)
 		prop->clk_stop_mode1 = !!clock_stop_1;
 
-	ports = devm_kcalloc(cs35l56->base.dev, 2, sizeof(*ports), GFP_KERNEL);
+	ports = devm_kcalloc(cs35l56->base.dev, 3, sizeof(*ports), GFP_KERNEL);
 	if (!ports)
 		return -ENOMEM;
 
-	prop->source_ports = BIT(CS35L56_SDW1_CAPTURE_PORT);
+	prop->source_ports = BIT(CS35L56_SDW1_CAPTURE_PORT) | BIT(CS35L56_OT25_CAPTURE_PORT);
 	prop->sink_ports = BIT(CS35L56_SDW1_PLAYBACK_PORT);
 	prop->paging_support = true;
 	prop->use_domain_irq = true;
@@ -286,6 +286,11 @@ static int cs35l56_sdw_read_prop(struct sdw_slave *peripheral)
 	ports[1].num = CS35L56_SDW1_CAPTURE_PORT;
 	ports[1].type = SDW_DPN_FULL;
 	ports[1].ch_prep_timeout = 10;
+
+	/* DP4 - capture */
+	ports[2].num = CS35L56_OT25_CAPTURE_PORT;
+	ports[2].type = SDW_DPN_FULL;
+	ports[2].ch_prep_timeout = 10;
 	prop->src_dpn_prop = &ports[1];
 
 	dev_dbg(&peripheral->dev, "clock stop mode 1 supported: %s\n",
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 35d210626627..279db3f13f1e 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -32,6 +32,7 @@
 #include <sound/cs-amp-lib.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
+#include <sound/sdw.h>
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>
 #include <sound/tlv.h>
@@ -324,6 +325,7 @@ static const struct snd_soc_dapm_widget cs35l56_dapm_widgets[] = {
 	SND_SOC_DAPM_SIGGEN("VDDBMON ADC"),
 	SND_SOC_DAPM_SIGGEN("VBSTMON ADC"),
 	SND_SOC_DAPM_SIGGEN("TEMPMON ADC"),
+	SND_SOC_DAPM_SIGGEN("OT25 Reference"),
 
 	SND_SOC_DAPM_INPUT("Calibrate"),
 };
@@ -388,6 +390,8 @@ static const struct snd_soc_dapm_route cs35l56_audio_map[] = {
 	{ "SDW1 Capture", NULL, "SDW1 TX2 Source" },
 	{ "SDW1 Capture", NULL, "SDW1 TX3 Source" },
 	{ "SDW1 Capture", NULL, "SDW1 TX4 Source" },
+
+	{ "OT25", NULL, "OT25 Reference" },
 };
 
 static int cs35l56_dsp_event(struct snd_soc_dapm_widget *w,
@@ -712,6 +716,37 @@ static int cs35l56_sdw_dai_set_stream(struct snd_soc_dai *dai,
 	return 0;
 }
 
+static int cs35l56_ot25_dai_hw_params(struct snd_pcm_substream *substream,
+				      struct snd_pcm_hw_params *params,
+				      struct snd_soc_dai *dai)
+{
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component);
+	struct sdw_stream_runtime *sdw_stream = snd_soc_dai_get_dma_data(dai, substream);
+	struct sdw_stream_config sconfig = { };
+	struct sdw_port_config pconfig = { };
+	int ret;
+
+	dev_dbg(cs35l56->base.dev, "%s: rate %d\n", __func__, params_rate(params));
+
+	if (!cs35l56->base.init_done)
+		return -ENODEV;
+
+	if (!sdw_stream)
+		return -EINVAL;
+
+	snd_sdw_params_to_config(substream, params, &sconfig, &pconfig);
+	pconfig.num = CS35L56_OT25_CAPTURE_PORT;
+
+	ret = sdw_stream_add_slave(cs35l56->sdw_peripheral, &sconfig, &pconfig,
+				   1, sdw_stream);
+	if (ret) {
+		dev_err(dai->dev, "Failed to add OT25 stream: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static const struct snd_soc_dai_ops cs35l56_sdw_dai_ops = {
 	.set_tdm_slot = cs35l56_sdw_dai_set_tdm_slot,
 	.shutdown = cs35l56_sdw_dai_shutdown,
@@ -720,6 +755,13 @@ static const struct snd_soc_dai_ops cs35l56_sdw_dai_ops = {
 	.set_stream = cs35l56_sdw_dai_set_stream,
 };
 
+static const struct snd_soc_dai_ops cs35l56_ot25_dai_ops = {
+	.shutdown = cs35l56_sdw_dai_shutdown,
+	.hw_params = cs35l56_ot25_dai_hw_params,
+	.hw_free = cs35l56_sdw_dai_hw_free,
+	.set_stream = cs35l56_sdw_dai_set_stream,
+};
+
 static struct snd_soc_dai_driver cs35l56_dai[] = {
 	{
 		.name = "cs35l56-asp1",
@@ -768,6 +810,18 @@ static struct snd_soc_dai_driver cs35l56_dai[] = {
 		.symmetric_rate = 1,
 		.ops = &cs35l56_sdw_dai_ops,
 	},
+	{
+		.name = "cs35l56-ot25",
+		.id = 3,
+		.capture = {
+			.stream_name = "OT25",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = CS35L56_RATES,
+			.formats = CS35L56_TX_FORMATS,
+		},
+		.ops = &cs35l56_ot25_dai_ops,
+	},
 };
 
 static int cs35l56_write_cal(struct cs35l56_private *cs35l56)
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 3e76cb81462f..442e70b107da 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -1534,9 +1534,16 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 		goto err_disable_pm;
 
 	priv->op_clk = clk_get_parent(priv->clk_table[CLK_I2S_RCLK_SRC]);
+	ret = clk_prepare_enable(priv->op_clk);
+	if (ret < 0) {
+		priv->op_clk = NULL;
+		goto err_unregister_clk;
+	}
 
 	return 0;
 
+err_unregister_clk:
+	i2s_unregister_clock_provider(priv);
 err_disable_pm:
 	pm_runtime_disable(&pdev->dev);
 err_del_sec:
@@ -1559,6 +1566,7 @@ static void samsung_i2s_remove(struct platform_device *pdev)
 
 	i2s_unregister_clock_provider(priv);
 	i2s_delete_secondary_device(priv);
+	clk_disable_unprepare(priv->op_clk);
 	clk_disable_unprepare(priv->clk);
 
 	pm_runtime_put_noidle(&pdev->dev);
diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c
index d2eeef4931c6..eda7c567f71e 100644
--- a/sound/soc/sdw_utils/soc_sdw_utils.c
+++ b/sound/soc/sdw_utils/soc_sdw_utils.c
@@ -808,7 +808,7 @@ struct asoc_sdw_codec_info codec_info_list[] = {
 			},
 			{
 				.direction = {false, true},
-				.dai_name = "cs35l56-sdw1c",
+				.dai_name = "cs35l56-ot25",
 				.dai_type = SOC_SDW_DAI_TYPE_AMP,
 				.dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID},
 			},
@@ -836,7 +836,7 @@ struct asoc_sdw_codec_info codec_info_list[] = {
 			},
 			{
 				.direction = {false, true},
-				.dai_name = "cs35l56-sdw1c",
+				.dai_name = "cs35l56-ot25",
 				.dai_type = SOC_SDW_DAI_TYPE_AMP,
 				.dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID},
 			},
@@ -864,7 +864,7 @@ struct asoc_sdw_codec_info codec_info_list[] = {
 			},
 			{
 				.direction = {false, true},
-				.dai_name = "cs35l56-sdw1c",
+				.dai_name = "cs35l56-ot25",
 				.dai_type = SOC_SDW_DAI_TYPE_AMP,
 				.dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID},
 			},
@@ -892,7 +892,7 @@ struct asoc_sdw_codec_info codec_info_list[] = {
 			},
 			{
 				.direction = {false, true},
-				.dai_name = "cs35l56-sdw1c",
+				.dai_name = "cs35l56-ot25",
 				.dai_type = SOC_SDW_DAI_TYPE_AMP,
 				.dailink = {SOC_SDW_UNUSED_DAI_ID, SOC_SDW_AMP_IN_DAI_ID},
 			},
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 3afc49565963..a54fabce7920 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2510,6 +2510,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_DSD_RAW),
 	DEVICE_FLG(0x21b4, 0x0232, /* Ayre QX-5 Twenty */
 		   QUIRK_FLAG_DSD_RAW),
+	DEVICE_FLG(0x22e8, 0xca10, /* Cambridge Audio streamers */
+		   QUIRK_FLAG_DSD_RAW),
 	DEVICE_FLG(0x2522, 0x0007, /* LH Labs Geek Out HD Audio 1V5 */
 		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x25aa, 0x600b, /* TAE1159 */
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 17d971d47f87..df0534035857 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -495,7 +495,8 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	footer.size = htole32(size);
 	footer.csum = htole32(csum);
 	memcpy(footer.magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
-	static_assert(sizeof(footer) == BOOTCONFIG_FOOTER_SIZE);
+	static_assert(sizeof(footer) == BOOTCONFIG_FOOTER_SIZE,
+		      "bootconfig footer size mismatch");
 	memcpy(data + size, &footer, BOOTCONFIG_FOOTER_SIZE);
 
 	total_size = size + BOOTCONFIG_FOOTER_SIZE;
diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh
index 268521234d4b..288821565eee 100755
--- a/tools/hv/hv_get_dns_info.sh
+++ b/tools/hv/hv_get_dns_info.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-# This example script parses /etc/resolv.conf to retrive DNS information.
+# This example script parses /etc/resolv.conf to retrieve DNS information.
 # In the interest of keeping the KVP daemon code free of distro specific
 # information; the kvp daemon code invokes this external script to gather
 # DNS information.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 920694c3c1ec..cb3d571f121e 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2034,8 +2034,11 @@ const struct dirent *pmt_diriter_begin(struct pmt_diriter_t *iter, const char *p
 			return NULL;
 
 		num_names = scandir(pmt_root_path, &iter->namelist, pmt_telemdir_filter, pmt_telemdir_sort);
-		if (num_names == -1)
+		if (num_names == -1) {
+			closedir(iter->dir);
+			iter->dir = NULL;
 			return NULL;
+		}
 	}
 
 	iter->current_name_idx = 0;
@@ -2063,8 +2066,10 @@ void pmt_diriter_remove(struct pmt_diriter_t *iter)
 	iter->num_names = 0;
 	iter->current_name_idx = 0;
 
-	closedir(iter->dir);
-	iter->dir = NULL;
+	if (iter->dir) {
+		closedir(iter->dir);
+		iter->dir = NULL;
+	}
 }
 
 unsigned int pmt_counter_get_width(const struct pmt_counter *p)
@@ -3636,7 +3641,7 @@ int format_counters(PER_THREAD_PARAMS)
 		if (p->gfx_rc6_ms == -1) {	/* detect GFX counter reset */
 			outp += sprintf(outp, "%s**.**", (printed++ ? delim : ""));
 		} else {
-			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), p->gfx_rc6_ms / 10.0 / interval_float);
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), pct(p->gfx_rc6_ms / 10.0, interval_float));
 		}
 	}
 
@@ -3653,7 +3658,7 @@ int format_counters(PER_THREAD_PARAMS)
 		if (p->sam_mc6_ms == -1) {	/* detect GFX counter reset */
 			outp += sprintf(outp, "%s**.**", (printed++ ? delim : ""));
 		} else {
-			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), p->sam_mc6_ms / 10.0 / interval_float);
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), pct(p->sam_mc6_ms / 10.0, interval_float));
 		}
 	}
 
@@ -5915,7 +5920,7 @@ void free_fd_msr(void)
 	if (!msr_counter_info)
 		return;
 
-	for (int cpu = 0; cpu < topo.max_cpu_num; ++cpu) {
+	for (int cpu = 0; cpu <= topo.max_cpu_num; ++cpu) {
 		if (msr_counter_info[cpu].fd_perf != -1)
 			close(msr_counter_info[cpu].fd_perf);
 	}
@@ -6311,33 +6316,35 @@ int for_all_proc_cpus(int (func) (int))
 
 #define PATH_EFFECTIVE_CPUS	"/sys/fs/cgroup/cpuset.cpus.effective"
 
-static char cpu_effective_str[1024];
+static char *cpu_effective_str;
 
 static int update_effective_str(bool startup)
 {
 	FILE *fp;
-	char *pos;
-	char buf[1024];
+	char *buf = NULL;
+	size_t size = 0;
 	int ret;
 
-	if (cpu_effective_str[0] == '\0' && !startup)
+	if (!cpu_effective_str && !startup)
 		return 0;
 
 	fp = fopen(PATH_EFFECTIVE_CPUS, "r");
 	if (!fp)
 		return 0;
 
-	pos = fgets(buf, 1024, fp);
-	if (!pos)
+	if (getline(&buf, &size, fp) < 0)
 		err(1, "%s: file read failed", PATH_EFFECTIVE_CPUS);
 
 	fclose(fp);
 
-	ret = strncmp(cpu_effective_str, buf, 1024);
-	if (!ret)
+	ret = cpu_effective_str ? strcmp(cpu_effective_str, buf) : 1;
+	if (!ret) {
+		free(buf);
 		return 0;
+	}
 
-	strncpy(cpu_effective_str, buf, 1024);
+	free(cpu_effective_str);
+	cpu_effective_str = buf;
 	return 1;
 }
 
@@ -8529,13 +8536,16 @@ end:
 	return ret;
 }
 
-char cpuset_buf[1024];
-int initialize_cpu_set_from_sysfs(cpu_set_t *cpu_set, char *sysfs_path, char *sysfs_file)
+int initialize_cpu_set_from_sysfs(cpu_set_t *cpu_set, const char *sysfs_path,
+				  const char *sysfs_file)
 {
 	FILE *fp;
+	char *cpuset_buf = NULL;
+	size_t size = 0;
 	char path[128];
+	int ret = -1;
 
-	if (snprintf(path, 128, "%s/%s", sysfs_path, sysfs_file) > 128)
+	if (snprintf(path, sizeof(path), "%s/%s", sysfs_path, sysfs_file) >= (int)sizeof(path))
 		err(-1, "%s %s", sysfs_path, sysfs_file);
 
 	fp = fopen(path, "r");
@@ -8543,19 +8553,20 @@ int initialize_cpu_set_from_sysfs(cpu_set_t *cpu_set, char *sysfs_path, char *sy
 		warn("open %s", path);
 		return -1;
 	}
-	if (fread(cpuset_buf, sizeof(char), 1024, fp) == 0) {
+	if (getline(&cpuset_buf, &size, fp) < 0) {
 		warn("read %s", sysfs_path);
-		goto err;
+		goto out;
 	}
 	if (parse_cpu_str(cpuset_buf, cpu_set, cpu_possible_setsize)) {
-		warnx("%s: cpu str malformat %s\n", sysfs_path, cpu_effective_str);
-		goto err;
+		warnx("%s: cpu str malformat %s\n", sysfs_path, cpuset_buf);
+		goto out;
 	}
-	return 0;
+	ret = 0;
 
-err:
+out:
 	fclose(fp);
-	return -1;
+	free(cpuset_buf);
+	return ret;
 }
 
 void print_cpu_set(char *s, cpu_set_t *set)
@@ -8655,6 +8666,8 @@ void rapl_perf_init(void)
 {
 	const unsigned int num_domains = get_rapl_num_domains();
 	bool *domain_visited = calloc(num_domains, sizeof(bool));
+	if (!domain_visited)
+		err(-1, "calloc domain_visited");
 
 	rapl_counter_info_perdomain = calloc(num_domains, sizeof(*rapl_counter_info_perdomain));
 	if (rapl_counter_info_perdomain == NULL)
@@ -9471,8 +9484,10 @@ void perf_l2_init(void)
 				free_fd_l2_percpu();
 				return;
 			}
-		} else
-			err(-1, "%s: cpu%d: type %d", __func__, cpu, cpus[cpu].type);
+		} else {
+			warn("%s: cpu%d: type %d: Update kernel perf support or use \"--hide L2MRPS,L2%%hit\" or \"--hide cache\" or \"--no-perf\"", __func__, cpu, cpus[cpu].type);
+			return;
+		}
 	}
 	BIC_PRESENT(BIC_L2_MRPS);
 	BIC_PRESENT(BIC_L2_HIT);
@@ -9999,6 +10014,8 @@ int added_perf_counters_init_(struct perf_counter_info *pinfo)
 	const size_t max_num_domains = MAX(topo.max_cpu_num + 1, MAX(topo.max_core_id + 1, topo.max_package_id + 1));
 
 	domain_visited = calloc(max_num_domains, sizeof(*domain_visited));
+	if (!domain_visited)
+		errx(1, "%s: alloc %s", __func__, "domain_visited");
 
 	while (pinfo) {
 		switch (pinfo->scope) {
@@ -10390,6 +10407,8 @@ int pmt_add_counter(unsigned int guid, unsigned int seq, const char *name, enum
 	pcounter = pmt_find_counter(*pmt_root, name);
 	if (!pcounter) {
 		pcounter = calloc(1, sizeof(*pcounter));
+		if (!pcounter)
+			return 1;
 		new_counter = true;
 	}
 
@@ -10439,7 +10458,7 @@ void pmt_init(void)
 		mod_num = 0;	/* Relative module number for current PMT file. */
 
 		/* Open the counter for each CPU. */
-		for (cpu_num = 0; cpu_num < topo.max_cpu_num;) {
+		for (cpu_num = 0; cpu_num <= topo.max_cpu_num;) {
 
 			if (cpu_is_not_allowed(cpu_num))
 				goto next_loop_iter;
@@ -10608,7 +10627,7 @@ int get_and_dump_counters(void)
 
 void print_version()
 {
-	fprintf(outf, "turbostat version 2026.04.21 - Len Brown <lenb@kernel.org>\n");
+	fprintf(outf, "turbostat version 2026.09.28 - Len Brown <lenb@kernel.org>\n");
 }
 
 #define COMMAND_LINE_SIZE 2048
@@ -10668,10 +10687,11 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 				fprintf(stderr, "%s: %s FOUND\n", __func__, name);
 			break;
 		}
-		if (sys.added_thread_counters++ >= MAX_ADDED_THREAD_COUNTERS) {
+		if (sys.added_thread_counters >= MAX_ADDED_THREAD_COUNTERS) {
 			warnx("ignoring thread counter %s", name);
 			return -1;
 		}
+		sys.added_thread_counters++;
 		break;
 	case SCOPE_CORE:
 		msrp = find_msrp_by_name(sys.cp, name);
@@ -10680,10 +10700,11 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 				fprintf(stderr, "%s: %s FOUND\n", __func__, name);
 			break;
 		}
-		if (sys.added_core_counters++ >= MAX_ADDED_CORE_COUNTERS) {
+		if (sys.added_core_counters >= MAX_ADDED_CORE_COUNTERS) {
 			warnx("ignoring core counter %s", name);
 			return -1;
 		}
+		sys.added_core_counters++;
 		break;
 	case SCOPE_PACKAGE:
 		msrp = find_msrp_by_name(sys.pp, name);
@@ -10692,10 +10713,11 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 				fprintf(stderr, "%s: %s FOUND\n", __func__, name);
 			break;
 		}
-		if (sys.added_package_counters++ >= MAX_ADDED_PACKAGE_COUNTERS) {
+		if (sys.added_package_counters >= MAX_ADDED_PACKAGE_COUNTERS) {
 			warnx("ignoring package counter %s", name);
 			return -1;
 		}
+		sys.added_package_counters++;
 		break;
 	default:
 		warnx("ignoring counter %s with unknown scope", name);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 273853937c25..bc4fdb6f5337 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -43,6 +43,7 @@ TARGETS += filesystems/open_tree_ns
 TARGETS += filesystems/overlayfs
 TARGETS += filesystems/statmount
 TARGETS += filesystems/mount-notify
+TARGETS += filesystems/mount_cycle
 TARGETS += filesystems/nsfs
 TARGETS += filesystems/fuse
 TARGETS += filesystems/move_mount
@@ -50,6 +51,8 @@ TARGETS += filesystems/empty_mntns
 TARGETS += filesystems/fsmount_ns
 TARGETS += filesystems/fscontext_ns
 TARGETS += filesystems/xattr
+TARGETS += filesystems/mntns_unbindable
+TARGETS += filesystems/umount_propagation
 TARGETS += firmware
 TARGETS += fpu
 TARGETS += ftrace
diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore
index 9eb185fb2f9d..62f7b1c46649 100644
--- a/tools/testing/selftests/filesystems/.gitignore
+++ b/tools/testing/selftests/filesystems/.gitignore
@@ -7,3 +7,4 @@ anon_inode_test
 kernfs_test
 idmapped_tmpfile
 ustat_test
+rw_hint_test
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 03be337c1f35..93e2cc9123b0 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 CFLAGS += $(KHDR_INCLUDES)
-TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog ustat_test
+TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog ustat_test rw_hint_test
 TEST_GEN_PROGS += idmapped_tmpfile
 TEST_GEN_PROGS_EXTENDED := dnotify_test
 
diff --git a/tools/testing/selftests/filesystems/empty_mntns/.gitignore b/tools/testing/selftests/filesystems/empty_mntns/.gitignore
index 99f89d329db2..27bcbcaeb1d1 100644
--- a/tools/testing/selftests/filesystems/empty_mntns/.gitignore
+++ b/tools/testing/selftests/filesystems/empty_mntns/.gitignore
@@ -2,3 +2,6 @@
 clone3_empty_mntns_test
 empty_mntns_test
 overmount_chroot_test
+internal_sb_reconfigure_test
+nullfs_atime_test
+root_readdir_test
diff --git a/tools/testing/selftests/filesystems/empty_mntns/Makefile b/tools/testing/selftests/filesystems/empty_mntns/Makefile
index 22e3fb915e81..22af2164c54e 100644
--- a/tools/testing/selftests/filesystems/empty_mntns/Makefile
+++ b/tools/testing/selftests/filesystems/empty_mntns/Makefile
@@ -4,9 +4,14 @@ CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 LDLIBS += -lcap
 
 TEST_GEN_PROGS := empty_mntns_test overmount_chroot_test clone3_empty_mntns_test
+TEST_GEN_PROGS += internal_sb_reconfigure_test nullfs_atime_test root_readdir_test
+
+LOCAL_HDRS += ../readdir_hold.h
 
 include ../../lib.mk
 
 $(OUTPUT)/empty_mntns_test: ../utils.c
 $(OUTPUT)/overmount_chroot_test: ../utils.c
 $(OUTPUT)/clone3_empty_mntns_test: ../utils.c
+$(OUTPUT)/internal_sb_reconfigure_test: ../utils.c
+$(OUTPUT)/root_readdir_test: LDLIBS += -pthread
diff --git a/tools/testing/selftests/filesystems/empty_mntns/internal_sb_reconfigure_test.c b/tools/testing/selftests/filesystems/empty_mntns/internal_sb_reconfigure_test.c
new file mode 100644
index 000000000000..cb645d1e5a9a
--- /dev/null
+++ b/tools/testing/selftests/filesystems/empty_mntns/internal_sb_reconfigure_test.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The root of an empty mount namespace is a nullfs mount. Its superblock is
+ * kernel-internal and shared by every mount namespace. It can't be
+ * reconfigured, neither through fspick() nor through mount(MS_REMOUNT) nor
+ * through umount() of the root which remounts it read-only.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/statfs.h>
+#include <sys/statvfs.h>
+#include <sys/syscall.h>
+#include <sys/vfs.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../utils.h"
+#include "../wrappers.h"
+#include "empty_mntns.h"
+#include "kselftest_harness.h"
+
+#ifndef __NR_fspick
+#define __NR_fspick 433
+#endif
+
+static int sys_fspick(int dfd, const char *path, unsigned int flags)
+{
+	return syscall(__NR_fspick, dfd, path, flags);
+}
+
+/* Child exit codes. */
+enum {
+	CHILD_OK,
+	CHILD_USERNS,		/* could not create the user namespace */
+	CHILD_UNSHARE,		/* could not create the empty mount namespace */
+	CHILD_FSPICK,		/* fspick() of the root was not refused with EINVAL */
+	CHILD_REMOUNT,		/* mount(MS_REMOUNT) was not refused with EINVAL */
+	CHILD_UMOUNT,		/* umount() of the root succeeded */
+	CHILD_STATFS,		/* statfs() of the root failed */
+	CHILD_RDONLY,		/* the root ended up read-only */
+};
+
+static int empty_mntns_child(void)
+{
+	struct statfs st;
+
+	if (enter_userns())
+		return CHILD_USERNS;
+	if (unshare(UNSHARE_EMPTY_MNTNS))
+		return CHILD_UNSHARE;
+
+	if (sys_fspick(AT_FDCWD, "/", 0) >= 0 || errno != EINVAL)
+		return CHILD_FSPICK;
+	if (!mount(NULL, "/", NULL, MS_REMOUNT | MS_RDONLY, NULL) ||
+	    errno != EINVAL)
+		return CHILD_REMOUNT;
+	if (!umount2("/", 0))
+		return CHILD_UMOUNT;
+	if (statfs("/", &st))
+		return CHILD_STATFS;
+	if (st.f_flags & ST_RDONLY)
+		return CHILD_RDONLY;
+	return CHILD_OK;
+}
+
+FIXTURE(internal_sb_reconfigure) {};
+
+FIXTURE_SETUP(internal_sb_reconfigure)
+{
+	pid_t pid;
+	int status;
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		if (enter_userns())
+			_exit(1);
+		if (unshare(UNSHARE_EMPTY_MNTNS))
+			_exit(1);
+		_exit(0);
+	}
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	if (!WIFEXITED(status) || WEXITSTATUS(status))
+		SKIP(return, "UNSHARE_EMPTY_MNTNS not supported");
+}
+
+FIXTURE_TEARDOWN(internal_sb_reconfigure) {}
+
+TEST_F(internal_sb_reconfigure, nullfs_root)
+{
+	pid_t pid;
+	int status;
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(empty_mntns_child());
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), CHILD_OK);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/empty_mntns/nullfs_atime_test.c b/tools/testing/selftests/filesystems/empty_mntns/nullfs_atime_test.c
new file mode 100644
index 000000000000..51e34f3c4f54
--- /dev/null
+++ b/tools/testing/selftests/filesystems/empty_mntns/nullfs_atime_test.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * The root of every empty mount namespace is the same nullfs inode. A read
+ * of it by one user must not change the access time another user sees.
+ */
+#define _GNU_SOURCE
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+#include "../../kselftest_harness.h"
+
+#ifndef UNSHARE_EMPTY_MNTNS
+#define UNSHARE_EMPTY_MNTNS	0x00100000
+#endif
+
+enum {
+	CHILD_OK,
+	CHILD_UNSUPPORTED,
+	CHILD_SETUP,
+	CHILD_CHANGED,
+};
+
+static int wait_byte(int fd)
+{
+	char c;
+
+	return read(fd, &c, 1) == 1 ? 0 : -1;
+}
+
+static int send_byte(int fd)
+{
+	return write(fd, "x", 1) == 1 ? 0 : -1;
+}
+
+static int empty_mntns(void)
+{
+	if (!unshare(UNSHARE_EMPTY_MNTNS))
+		return 0;
+	return errno == EINVAL ? CHILD_UNSUPPORTED : CHILD_SETUP;
+}
+
+/* the watcher: stats its root before and after the reader read its own */
+static int watcher(int to_reader, int from_reader)
+{
+	struct stat before, after;
+	int ret;
+
+	ret = empty_mntns();
+	if (ret)
+		return ret;
+	if (stat("/", &before))
+		return CHILD_SETUP;
+	if (send_byte(to_reader) || wait_byte(from_reader))
+		return CHILD_SETUP;
+	if (stat("/", &after))
+		return CHILD_SETUP;
+	if (before.st_atim.tv_sec != after.st_atim.tv_sec ||
+	    before.st_atim.tv_nsec != after.st_atim.tv_nsec)
+		return CHILD_CHANGED;
+	return CHILD_OK;
+}
+
+/* the reader: lists its own root, which is the same inode */
+static int reader(int to_watcher, int from_watcher)
+{
+	struct dirent *de;
+	DIR *d;
+	int ret;
+
+	ret = empty_mntns();
+	if (ret)
+		return ret;
+	if (wait_byte(from_watcher))
+		return CHILD_SETUP;
+	d = opendir("/");
+	if (!d)
+		return CHILD_SETUP;
+	while ((de = readdir(d)))
+		;
+	closedir(d);
+	return send_byte(to_watcher) ? CHILD_SETUP : CHILD_OK;
+}
+
+static int wait_child(pid_t pid)
+{
+	int status;
+
+	if (waitpid(pid, &status, 0) != pid || !WIFEXITED(status))
+		return -1;
+	return WEXITSTATUS(status);
+}
+
+TEST(empty_mntns_root_atime)
+{
+	int to_reader[2], to_watcher[2], w, r;
+	pid_t watcher_pid, reader_pid;
+
+	if (geteuid())
+		SKIP(return, "test requires root");
+	ASSERT_EQ(pipe(to_reader), 0);
+	ASSERT_EQ(pipe(to_watcher), 0);
+
+	watcher_pid = fork();
+	ASSERT_GE(watcher_pid, 0);
+	if (watcher_pid == 0)
+		_exit(watcher(to_reader[1], to_watcher[0]));
+	reader_pid = fork();
+	ASSERT_GE(reader_pid, 0);
+	if (reader_pid == 0)
+		_exit(reader(to_watcher[1], to_reader[0]));
+
+	r = wait_child(reader_pid);
+	w = wait_child(watcher_pid);
+	if (r == CHILD_UNSUPPORTED || w == CHILD_UNSUPPORTED)
+		SKIP(return, "UNSHARE_EMPTY_MNTNS not supported");
+	EXPECT_EQ(r, CHILD_OK);
+	EXPECT_EQ(w, CHILD_OK)
+		TH_LOG("the access time of the root changed while this namespace did nothing");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/empty_mntns/root_readdir_test.c b/tools/testing/selftests/filesystems/empty_mntns/root_readdir_test.c
new file mode 100644
index 000000000000..0ff544247027
--- /dev/null
+++ b/tools/testing/selftests/filesystems/empty_mntns/root_readdir_test.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Reading the root of an empty mount namespace holds nothing that anybody
+ * else waits for: the directory never has an entry, so a readdir stuck in
+ * the page fault of its buffer stalls neither a create nor a lookup in it.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "../../kselftest_harness.h"
+#include "../readdir_hold.h"
+#include "empty_mntns.h"
+
+TEST(readdir_blocks_nobody)
+{
+	struct readdir_hold hold;
+	bool stalled;
+	int dfd;
+
+	if (geteuid())
+		SKIP(return, "test requires root");
+	if (readdir_hold_init(&hold))
+		SKIP(return, "test requires userfaultfd");
+	if (unshare(UNSHARE_EMPTY_MNTNS)) {
+		readdir_hold_destroy(&hold);
+		if (errno == EINVAL)
+			SKIP(return, "UNSHARE_EMPTY_MNTNS not supported");
+		ASSERT_TRUE(false)
+			TH_LOG("unshare(UNSHARE_EMPTY_MNTNS): %m");
+	}
+	dfd = open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(dfd, 0);
+	ASSERT_EQ(readdir_hold_check(&hold, dfd, &stalled), 0);
+	/* the lookup came back while the readdir was stuck in its fault */
+	EXPECT_FALSE(stalled);
+	close(dfd);
+	readdir_hold_destroy(&hold);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mntns_unbindable/Makefile b/tools/testing/selftests/filesystems/mntns_unbindable/Makefile
new file mode 100644
index 000000000000..33a311c5bd72
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mntns_unbindable/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_GEN_PROGS := mntns_unbindable_test
+
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/mntns_unbindable/mntns_unbindable_test.c b/tools/testing/selftests/filesystems/mntns_unbindable/mntns_unbindable_test.c
new file mode 100644
index 000000000000..9aebc37cf74d
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mntns_unbindable/mntns_unbindable_test.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * An unbindable mount stays unbindable in a cloned mount namespace.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../../kselftest_harness.h"
+
+#ifndef OPEN_TREE_CLONE
+#define OPEN_TREE_CLONE		1
+#endif
+#ifndef OPEN_TREE_CLOEXEC
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC
+#endif
+
+static int sys_open_tree(int dfd, const char *filename, unsigned int flags)
+{
+	return syscall(__NR_open_tree, dfd, filename, flags);
+}
+
+/* Child exit codes. */
+enum {
+	CHILD_OK,		/* the operation failed with EINVAL as it must */
+	CHILD_ALLOWED,		/* the operation succeeded: the flag was lost */
+	CHILD_UNSHARE,		/* unshare(CLONE_NEWNS) failed */
+	CHILD_ERRNO,		/* the operation failed with some other errno */
+	CHILD_MOUNTINFO,	/* the mount was not found in mountinfo */
+};
+
+FIXTURE(mntns_unbindable)
+{
+	char base[64];
+	char src[80];
+	char dst[80];
+	bool mounted;
+};
+
+FIXTURE_SETUP(mntns_unbindable)
+{
+	self->mounted = false;
+
+	if (geteuid() != 0)
+		SKIP(return, "test requires CAP_SYS_ADMIN");
+
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+
+	snprintf(self->base, sizeof(self->base), "/tmp/mntns_unbindable.XXXXXX");
+	ASSERT_NE(mkdtemp(self->base), NULL);
+	ASSERT_EQ(mount("tmpfs", self->base, "tmpfs", 0, NULL), 0);
+	self->mounted = true;
+
+	snprintf(self->src, sizeof(self->src), "%s/src", self->base);
+	snprintf(self->dst, sizeof(self->dst), "%s/dst", self->base);
+	ASSERT_EQ(mkdir(self->src, 0755), 0);
+	ASSERT_EQ(mkdir(self->dst, 0755), 0);
+
+	ASSERT_EQ(mount("tmpfs", self->src, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(mount(NULL, self->src, NULL, MS_UNBINDABLE, NULL), 0);
+}
+
+FIXTURE_TEARDOWN(mntns_unbindable)
+{
+	if (self->mounted)
+		umount2(self->base, MNT_DETACH);
+	rmdir(self->base);
+}
+
+static int classify(int ret, int err)
+{
+	if (ret >= 0)
+		return CHILD_ALLOWED;
+	return err == EINVAL ? CHILD_OK : CHILD_ERRNO;
+}
+
+/* Is the mount on @mountpoint marked unbindable in /proc/self/mountinfo? */
+static int mountinfo_unbindable(const char *mountpoint)
+{
+	char line[4096];
+	FILE *f;
+	int ret = CHILD_MOUNTINFO;
+
+	f = fopen("/proc/self/mountinfo", "re");
+	if (!f)
+		return CHILD_ERRNO;
+
+	while (fgets(line, sizeof(line), f)) {
+		char *fields[6], *p = line, *opt;
+		int i;
+
+		for (i = 0; i < 6; i++) {
+			fields[i] = strsep(&p, " ");
+			if (!fields[i])
+				break;
+		}
+		if (i < 6 || strcmp(fields[4], mountpoint))
+			continue;
+
+		/* the optional fields, up to the "-" separator */
+		ret = CHILD_ALLOWED;
+		while ((opt = strsep(&p, " ")) && strcmp(opt, "-")) {
+			if (!strcmp(opt, "unbindable"))
+				ret = CHILD_OK;
+		}
+		break;
+	}
+	fclose(f);
+	return ret;
+}
+
+static int run_in_child(int (*fn)(const char *src, const char *dst),
+			const char *src, const char *dst)
+{
+	int status;
+	pid_t pid;
+
+	pid = fork();
+	if (pid < 0)
+		return -1;
+	if (pid == 0)
+		_exit(fn(src, dst));
+	if (waitpid(pid, &status, 0) != pid || !WIFEXITED(status))
+		return -1;
+	return WEXITSTATUS(status);
+}
+
+static int bind_after_clone(const char *src, const char *dst)
+{
+	int ret;
+
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	ret = mount(src, dst, NULL, MS_BIND, NULL);
+	return classify(ret, errno);
+}
+
+static int rbind_after_clone(const char *src, const char *dst)
+{
+	int ret;
+
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	ret = mount(src, dst, NULL, MS_BIND | MS_REC, NULL);
+	return classify(ret, errno);
+}
+
+static int open_tree_after_clone(const char *src, const char *dst)
+{
+	int ret;
+
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	ret = sys_open_tree(AT_FDCWD, src, OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	return classify(ret, errno);
+}
+
+static int mountinfo_after_clone(const char *src, const char *dst)
+{
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	return mountinfo_unbindable(src);
+}
+
+static int bind_after_two_clones(const char *src, const char *dst)
+{
+	int ret;
+
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	ret = mount(src, dst, NULL, MS_BIND, NULL);
+	return classify(ret, errno);
+}
+
+/* The namespace the mount was made unbindable in. */
+TEST_F(mntns_unbindable, refuses_bind)
+{
+	int ret = mount(self->src, self->dst, NULL, MS_BIND, NULL);
+
+	ASSERT_EQ(classify(ret, errno), CHILD_OK);
+	ASSERT_EQ(mountinfo_unbindable(self->src), CHILD_OK);
+}
+
+/* A copy of the namespace must not turn the mount bindable. */
+TEST_F(mntns_unbindable, refuses_bind_after_clone)
+{
+	ASSERT_EQ(run_in_child(bind_after_clone, self->src, self->dst), CHILD_OK)
+		TH_LOG("bind of an unbindable mount allowed in a copied mount namespace");
+}
+
+TEST_F(mntns_unbindable, refuses_rbind_after_clone)
+{
+	ASSERT_EQ(run_in_child(rbind_after_clone, self->src, self->dst), CHILD_OK)
+		TH_LOG("rbind of an unbindable mount allowed in a copied mount namespace");
+}
+
+TEST_F(mntns_unbindable, refuses_open_tree_after_clone)
+{
+	ASSERT_EQ(run_in_child(open_tree_after_clone, self->src, self->dst), CHILD_OK)
+		TH_LOG("OPEN_TREE_CLONE of an unbindable mount allowed in a copied mount namespace");
+}
+
+TEST_F(mntns_unbindable, mountinfo_after_clone)
+{
+	ASSERT_EQ(run_in_child(mountinfo_after_clone, self->src, self->dst), CHILD_OK)
+		TH_LOG("mountinfo does not show the mount as unbindable in a copied mount namespace");
+}
+
+TEST_F(mntns_unbindable, refuses_bind_after_two_clones)
+{
+	ASSERT_EQ(run_in_child(bind_after_two_clones, self->src, self->dst), CHILD_OK)
+		TH_LOG("bind of an unbindable mount allowed two mount namespace copies down");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount_cycle/.gitignore b/tools/testing/selftests/filesystems/mount_cycle/.gitignore
new file mode 100644
index 000000000000..30f7dd071bcb
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/.gitignore
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+loop_cycle_test
+unmounted_tree_test
+overmount_reparent_test
+mount_cover_test
+locked_handle_test
+nsfs_rbind_loop_test
+overmount_ns_file_test
diff --git a/tools/testing/selftests/filesystems/mount_cycle/Makefile b/tools/testing/selftests/filesystems/mount_cycle/Makefile
new file mode 100644
index 000000000000..fbe8c5e19d42
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_GEN_PROGS := loop_cycle_test unmounted_tree_test overmount_reparent_test mount_cover_test locked_handle_test
+TEST_GEN_PROGS += nsfs_rbind_loop_test overmount_ns_file_test
+
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+
+LOCAL_HDRS += ../readdir_hold.h
+
+include ../../lib.mk
+
+$(OUTPUT)/locked_handle_test: LDLIBS += -pthread
+$(OUTPUT)/mount_cover_test: LDLIBS += -pthread
diff --git a/tools/testing/selftests/filesystems/mount_cycle/config b/tools/testing/selftests/filesystems/mount_cycle/config
new file mode 100644
index 000000000000..3bd5ce46af74
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/config
@@ -0,0 +1,39 @@
+CONFIG_USER_NS=y
+CONFIG_TMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VFAT_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_MINIX_FS=y
+CONFIG_AUTOFS_FS=y
+CONFIG_ZRAM=y
+CONFIG_ZRAM_WRITEBACK=y
+CONFIG_KEYS=y
+CONFIG_ECRYPT_FS=y
+CONFIG_BINFMT_MISC=y
+CONFIG_FUSE_FS=y
+CONFIG_FUSE_PASSTHROUGH=y
+CONFIG_BLK_DEV_ZONED=y
+CONFIG_BLK_DEV_ZONED_LOOP=y
+CONFIG_CONFIGFS_FS=y
+CONFIG_USB_SUPPORT=y
+CONFIG_USB=y
+CONFIG_USB_STORAGE=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_DUMMY_HCD=y
+CONFIG_USB_CONFIGFS=y
+CONFIG_USB_CONFIGFS_MASS_STORAGE=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_MD_RAID1=y
+CONFIG_MD_BITMAP=y
+CONFIG_MD_BITMAP_FILE=y
+CONFIG_INOTIFY_USER=y
+CONFIG_DNOTIFY=y
+CONFIG_FANOTIFY=y
+CONFIG_FILE_LOCKING=y
+CONFIG_CRYPTO_AES=y
+CONFIG_USERFAULTFD=y
diff --git a/tools/testing/selftests/filesystems/mount_cycle/locked_handle_test.c b/tools/testing/selftests/filesystems/mount_cycle/locked_handle_test.c
new file mode 100644
index 000000000000..b21f43471e49
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/locked_handle_test.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * may_decode_fh() refuses a file handle below a mount with locked children
+ * to root in a user namespace. That has to hold while the mount is lazily
+ * unmounted and its children, the locked ones too, are taken off it.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdatomic.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+
+#include "../../kselftest_harness.h"
+
+#ifndef OPEN_TREE_CLONE
+#define OPEN_TREE_CLONE		1
+#endif
+#ifndef OPEN_TREE_CLOEXEC
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC
+#endif
+#ifndef AT_RECURSIVE
+#define AT_RECURSIVE		0x8000
+#endif
+
+#define DIR_LEN		64
+#define PATH_LEN	128
+
+#define ROUNDS		100	/* lazy umounts raced per test */
+#define RACERS		3	/* threads in open_by_handle_at() */
+#define EXTRA_MOUNTS	64	/* make umount_tree() hold mount_lock longer */
+#define MAX_DELAY_US	3000	/* before the umount */
+#define TAIL_US		2000	/* after it */
+
+struct handle {
+	struct file_handle fh;
+	unsigned char buf[MAX_HANDLE_SZ];
+};
+
+/* exit codes of the child */
+enum {
+	CHILD_OK,
+	CHILD_SETUP,
+	CHILD_DECODED,		/* decoded past a locked child */
+	CHILD_MOUNTED,		/* not refused while mounted */
+	CHILD_UNMOUNTED,	/* not refused once unmounted */
+	CHILD_ALLOWED,		/* refused where nothing is locked */
+	CHILD_NOUSERNS,		/* no user namespace to be had */
+};
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+/* Become root in a new user namespace with a private mount namespace. */
+static int enter_userns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[32];
+
+	prctl(PR_SET_DUMPABLE, 1);
+	/* EINVAL: no USER_NS, ENOSPC: user.max_user_namespaces is 0, EPERM: an LSM */
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS))
+		return errno == EINVAL || errno == ENOSPC || errno == EPERM ?
+		       CHILD_NOUSERNS : CHILD_SETUP;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return CHILD_SETUP;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return CHILD_SETUP;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return CHILD_SETUP;
+	if (setgid(0) || setuid(0))
+		return CHILD_SETUP;
+	if (mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL))
+		return CHILD_SETUP;
+	return CHILD_OK;
+}
+
+static int get_handle(const char *path, struct handle *h)
+{
+	int mntid;
+
+	h->fh.handle_bytes = MAX_HANDLE_SZ;
+	return name_to_handle_at(AT_FDCWD, path, &h->fh, &mntid, 0);
+}
+
+static int decode(int dfd, struct handle *h)
+{
+	return open_by_handle_at(dfd, &h->fh, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+}
+
+struct race {
+	int dfd;
+	struct handle *h;
+	atomic_int go;
+	atomic_int stop;
+	atomic_int won;		/* the first decoded descriptor */
+};
+
+static void *racer(void *arg)
+{
+	struct race *r = arg;
+
+	while (!atomic_load(&r->go))
+		;
+	while (!atomic_load(&r->stop)) {
+		int none = -1;
+		int fd;
+
+		fd = decode(r->dfd, r->h);
+		if (fd < 0)
+			continue;
+		if (!atomic_compare_exchange_strong(&r->won, &none, fd))
+			close(fd);
+	}
+	return NULL;
+}
+
+/* stop the @n racers started so far and wait for them, they spin on @r */
+static void stop_racers(struct race *r, pthread_t *th, int n)
+{
+	int i;
+
+	atomic_store(&r->stop, 1);
+	atomic_store(&r->go, 1);	/* one still waiting for the start sees stop next */
+	for (i = 0; i < n; i++)
+		pthread_join(th[i], NULL);
+}
+
+/*
+ * Bind @h recursively at @w, or take a detached copy of it, and race
+ * open_by_handle_at() of @inner against the lazy umount. The decoded
+ * descriptor, if there was one, is left in @won.
+ */
+static int race_round(const char *h, const char *w, struct handle *inner,
+		      bool dissolve, int *won)
+{
+	struct race r = { .h = inner, .won = -1 };
+	pthread_t th[RACERS];
+	int treefd = -1, fd, i;
+
+	if (dissolve) {
+		treefd = syscall(__NR_open_tree, AT_FDCWD, h,
+				 OPEN_TREE_CLONE | AT_RECURSIVE | OPEN_TREE_CLOEXEC);
+		if (treefd < 0)
+			return CHILD_SETUP;
+		/* an ordinary descriptor on the copy, treefd's close dissolves it */
+		r.dfd = openat(treefd, ".", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	} else {
+		if (mount(h, w, NULL, MS_BIND | MS_REC, NULL))
+			return CHILD_SETUP;
+		r.dfd = open(w, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	}
+	if (r.dfd < 0)
+		return CHILD_SETUP;
+
+	fd = decode(r.dfd, inner);
+	if (fd >= 0 || errno != EPERM) {
+		if (fd >= 0)
+			close(fd);
+		return CHILD_MOUNTED;
+	}
+
+	for (i = 0; i < RACERS; i++) {
+		if (pthread_create(&th[i], NULL, racer, &r)) {
+			stop_racers(&r, th, i);
+			return CHILD_SETUP;
+		}
+	}
+	atomic_store(&r.go, 1);
+	usleep(rand() % MAX_DELAY_US);
+	if (dissolve)
+		close(treefd);
+	else if (umount2(w, MNT_DETACH)) {
+		stop_racers(&r, th, RACERS);
+		return CHILD_SETUP;
+	}
+	usleep(TAIL_US);
+	stop_racers(&r, th, RACERS);
+
+	fd = decode(r.dfd, inner);
+	if (fd >= 0) {
+		close(fd);
+		return CHILD_UNMOUNTED;
+	}
+	close(r.dfd);
+	*won = atomic_load(&r.won);
+	return CHILD_OK;
+}
+
+static int race_child(const char *h, const char *w, struct handle *inner,
+		      bool dissolve)
+{
+	int ret, won, i;
+
+	srand(getpid());
+	ret = enter_userns();
+	if (ret)
+		return ret;
+	for (i = 0; i < ROUNDS; i++) {
+		ret = race_round(h, w, inner, dissolve, &won);
+		if (ret)
+			return ret;
+		if (won >= 0)
+			return CHILD_DECODED;
+	}
+	return CHILD_OK;
+}
+
+/* a bind without locked children decodes while mounted and not after */
+static int allowed_child(const char *plain, const char *w, struct handle *h)
+{
+	int dfd, fd, ret;
+
+	ret = enter_userns();
+	if (ret)
+		return ret;
+	if (mount(plain, w, NULL, MS_BIND | MS_REC, NULL))
+		return CHILD_SETUP;
+	dfd = open(w, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	if (dfd < 0)
+		return CHILD_SETUP;
+	fd = decode(dfd, h);
+	if (fd < 0)
+		return CHILD_ALLOWED;
+	close(fd);
+	if (umount2(w, MNT_DETACH))
+		return CHILD_SETUP;
+	fd = decode(dfd, h);
+	if (fd >= 0) {
+		close(fd);
+		return CHILD_UNMOUNTED;
+	}
+	return errno == EPERM ? CHILD_OK : CHILD_UNMOUNTED;
+}
+
+FIXTURE(locked_handle) {
+	char base[DIR_LEN];
+	char h[PATH_LEN];		/* the tree with the covered directory */
+	char plain[PATH_LEN];		/* a tree with no mount in it */
+	char w[PATH_LEN];		/* where the child binds either */
+	struct handle inner;		/* h/top/secret/inner, covered */
+	struct handle uncovered;	/* plain/inner */
+};
+
+FIXTURE_SETUP(locked_handle)
+{
+	char p[PATH_LEN], e[PATH_LEN];
+	int i;
+
+	if (geteuid())
+		SKIP(return, "test requires root");
+
+	snprintf(self->base, sizeof(self->base), "/tmp/locked_handle.XXXXXX");
+	ASSERT_NE(mkdtemp(self->base), NULL);
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+	ASSERT_EQ(mount("tmpfs", self->base, "tmpfs", 0, NULL), 0);
+
+	snprintf(self->h, sizeof(self->h), "%s/h", self->base);
+	snprintf(self->plain, sizeof(self->plain), "%s/plain", self->base);
+	snprintf(self->w, sizeof(self->w), "%s/w", self->base);
+	ASSERT_EQ(mkdir(self->h, 0755), 0);
+	ASSERT_EQ(mkdir(self->plain, 0755), 0);
+	ASSERT_EQ(mkdir(self->w, 0755), 0);
+	snprintf(p, sizeof(p), "%s/plain/inner", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	ASSERT_EQ(get_handle(p, &self->uncovered), 0);
+
+	/* the handle is for this filesystem */
+	ASSERT_EQ(mount("tmpfs", self->h, "tmpfs", 0, NULL), 0);
+	snprintf(p, sizeof(p), "%s/h/top", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	snprintf(p, sizeof(p), "%s/h/top/secret", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	snprintf(p, sizeof(p), "%s/h/top/secret/inner", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	ASSERT_EQ(get_handle(p, &self->inner), 0);
+	snprintf(e, sizeof(e), "%s/h/empty", self->base);
+	ASSERT_EQ(mkdir(e, 0755), 0);
+
+	/* cover it, and some more so the umount takes longer */
+	snprintf(p, sizeof(p), "%s/h/top/secret", self->base);
+	ASSERT_EQ(mount("tmpfs", p, "tmpfs", 0, NULL), 0);
+	for (i = 0; i < EXTRA_MOUNTS; i++) {
+		snprintf(p, sizeof(p), "%s/h/c%d", self->base, i);
+		ASSERT_EQ(mkdir(p, 0755), 0);
+		ASSERT_EQ(mount(e, p, NULL, MS_BIND, NULL), 0);
+	}
+}
+
+FIXTURE_TEARDOWN(locked_handle)
+{
+	umount2(self->base, MNT_DETACH);
+	rmdir(self->base);
+}
+
+static int wait_child(pid_t pid)
+{
+	int status;
+
+	if (waitpid(pid, &status, 0) != pid || !WIFEXITED(status))
+		return -1;
+	return WEXITSTATUS(status);
+}
+
+TEST_F(locked_handle, lazy_umount)
+{
+	pid_t pid;
+	int ret;
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(race_child(self->h, self->w, &self->inner, false));
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	if (ret == CHILD_NOUSERNS)
+		SKIP(return, "no user namespaces");
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
+TEST_F(locked_handle, dissolve)
+{
+	pid_t pid;
+	int ret;
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(race_child(self->h, self->w, &self->inner, true));
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	if (ret == CHILD_NOUSERNS)
+		SKIP(return, "no user namespaces");
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
+TEST_F(locked_handle, allowed_use)
+{
+	pid_t pid;
+	int ret;
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(allowed_child(self->plain, self->w, &self->uncovered));
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	if (ret == CHILD_NOUSERNS)
+		SKIP(return, "no user namespaces");
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount_cycle/loop_cycle_test.c b/tools/testing/selftests/filesystems/mount_cycle/loop_cycle_test.c
new file mode 100644
index 000000000000..6b4f5304c2e4
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/loop_cycle_test.c
@@ -0,0 +1,1542 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A mount that another namespace's rmdir detached, or that went down with
+ * the detached tree it was in when the tree's last fd was closed, keeps
+ * its submounts connected, and a connected submount is put by its
+ * parent's final mntput(). A submount whose filesystem keeps a file open
+ * on the parent then holds the parent's count above zero for good:
+ * nothing in userspace refers to either mount any more and nothing can
+ * release them. A loop device is the simplest such filesystem, its
+ * backing file sits on the parent.
+ */
+#define _GNU_SOURCE
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/fuse.h>
+#include <linux/keyctl.h>
+#include <linux/major.h>
+#include <linux/raid/md_u.h>
+#include <linux/raid/md_p.h>
+#include <linux/loop.h>
+#include <linux/magic.h>
+#include <sys/syscall.h>
+#include <sys/sysmacros.h>
+#include <sys/uio.h>
+
+#include "../wrappers.h"
+#include "../../kselftest_harness.h"
+
+#define IMAGE_SIZE	(1440 * 1024)
+#define SECTOR		512
+
+/*
+ * The tmpfs of the fixture. A directory of its own from mkdtemp(), so that
+ * the test needs no writable root directory and two instances don't take
+ * each other's mounts down.
+ */
+static char base[64];
+
+/* The configfs directory of the gadget, named after the test process. */
+static char gadget[96];
+
+/* A path below the base directory. Eight of them can be in use at a time. */
+static const char *at(const char *rel)
+{
+	static char buf[8][PATH_MAX];
+	static unsigned int next;
+	char *p = buf[next++ % 8];
+
+	snprintf(p, PATH_MAX, "%s/%s", base, rel);
+	return p;
+}
+
+/* A path below the gadget's configfs directory. */
+static const char *gat(const char *rel)
+{
+	static char buf[4][PATH_MAX];
+	static unsigned int next;
+	char *p = buf[next++ % 4];
+
+	snprintf(p, PATH_MAX, "%s%s", gadget, rel);
+	return p;
+}
+
+/* The loop devices this process has bound, to release them on every path. */
+#define MAX_LOOPS	4
+static int bound[MAX_LOOPS];
+static int nr_bound;
+
+/* What a child tells its parent: the loop devices it has bound, -1 for none. */
+struct report {
+	int n[2];
+};
+
+/* A blank FAT12 floppy image: boot sector, two FATs, an empty root directory. */
+static int write_fat12(int fd)
+{
+	struct stat st;
+	unsigned char sector[SECTOR] = {
+		0xeb, 0x3c, 0x90, 'M', 'S', 'W', 'I', 'N', '4', '.', '1',
+		[11] = 0x00, 0x02,	/* bytes per sector: 512 */
+		[13] = 1,		/* sectors per cluster */
+		[14] = 1, 0,		/* reserved sectors */
+		[16] = 2,		/* FATs */
+		[17] = 0xe0, 0x00,	/* root directory entries: 224 */
+		[19] = 0x40, 0x0b,	/* total sectors: 2880 */
+		[21] = 0xf0,		/* media descriptor */
+		[22] = 9, 0,		/* sectors per FAT */
+		[24] = 18, 0,		/* sectors per track */
+		[26] = 2, 0,		/* heads */
+		[38] = 0x29,		/* extended boot signature */
+		[39] = 0x12, 0x34, 0x56, 0x78,
+		[43] = 'N', 'O', ' ', 'N', 'A', 'M', 'E', ' ', ' ', ' ', ' ',
+		[54] = 'F', 'A', 'T', '1', '2', ' ', ' ', ' ',
+		[510] = 0x55, 0xaa,
+	};
+	unsigned char fat[SECTOR] = { 0xf0, 0xff, 0xff };
+
+	if (pwrite(fd, sector, SECTOR, 0) != SECTOR)
+		return -1;
+	/* the first FAT and the second one, one sector each is enough */
+	if (pwrite(fd, fat, SECTOR, 1 * SECTOR) != SECTOR ||
+	    pwrite(fd, fat, SECTOR, 10 * SECTOR) != SECTOR)
+		return -1;
+	if (fstat(fd, &st) || S_ISBLK(st.st_mode))
+		return 0;
+	return ftruncate(fd, IMAGE_SIZE);
+}
+
+/*
+ * A blank FAT12 image with 4 KiB sectors and @sectors of them, for a device
+ * with 4 KiB logical blocks (zram) or for a bigger image than a floppy.
+ */
+static int write_fat12_4k(int fd, unsigned int sectors)
+{
+	unsigned int fat_sectors = (sectors * 3 / 2 + 4095) / 4096;
+	unsigned char sector[4096] = {
+		0xeb, 0x3c, 0x90, 'M', 'S', 'W', 'I', 'N', '4', '.', '1',
+		[11] = 0x00, 0x10,	/* bytes per sector: 4096 */
+		[13] = 1,		/* sectors per cluster */
+		[14] = 1, 0,		/* reserved sectors */
+		[16] = 2,		/* FATs */
+		[17] = 128, 0,		/* root directory entries: one sector */
+		[19] = sectors & 0xff, sectors >> 8,
+		[21] = 0xf8,		/* media descriptor */
+		[22] = fat_sectors, 0,
+		[24] = 63, 0,		/* sectors per track */
+		[26] = 255, 0,		/* heads */
+		[38] = 0x29,		/* extended boot signature */
+		[39] = 0x12, 0x34, 0x56, 0x78,
+		[43] = 'N', 'O', ' ', 'N', 'A', 'M', 'E', ' ', ' ', ' ', ' ',
+		[54] = 'F', 'A', 'T', '1', '2', ' ', ' ', ' ',
+		[510] = 0x55, 0xaa,
+	};
+	unsigned char fat[4096] = { 0xf8, 0xff, 0xff };
+	struct stat st;
+
+	if (pwrite(fd, sector, sizeof(sector), 0) != sizeof(sector))
+		return -1;
+	if (pwrite(fd, fat, sizeof(fat), 1 * 4096) != sizeof(fat) ||
+	    pwrite(fd, fat, sizeof(fat), (1 + fat_sectors) * 4096) != sizeof(fat))
+		return -1;
+	if (fstat(fd, &st) || S_ISBLK(st.st_mode))
+		return 0;
+	return ftruncate(fd, (off_t)sectors * 4096);
+}
+
+#define MINIX_BLOCK	1024
+#define MINIX_BLOCKS	4096			/* a 4 MiB image */
+#define MINIX_INODES	512
+#define MINIX_ITABLE	(MINIX_INODES * 32 / MINIX_BLOCK)
+#define MINIX_FIRSTDATA	(2 + 1 + 1 + MINIX_ITABLE)	/* boot, super, imap, zmap, inodes */
+
+/*
+ * A blank minix v1 image, for the holders that need a FIFO or a device
+ * node on the dying mount, which vfat can't hold. Superblock in block 1,
+ * one block each for the inode and zone bitmaps, the inode table, and
+ * the root directory in the first data zone.
+ */
+static int write_minix(int fd)
+{
+	struct {
+		__u16 s_ninodes, s_nzones, s_imap_blocks, s_zmap_blocks;
+		__u16 s_firstdatazone, s_log_zone_size;
+		__u32 s_max_size;
+		__u16 s_magic, s_state;
+	} sb = {
+		.s_ninodes = MINIX_INODES,
+		.s_nzones = MINIX_BLOCKS,
+		.s_imap_blocks = 1,
+		.s_zmap_blocks = 1,
+		.s_firstdatazone = MINIX_FIRSTDATA,
+		.s_max_size = (7 + 512 + 512 * 512) * MINIX_BLOCK,
+		.s_magic = MINIX_SUPER_MAGIC,
+		.s_state = 1,		/* MINIX_VALID_FS */
+	};
+	struct {
+		__u16 i_mode, i_uid;
+		__u32 i_size, i_time;
+		__u8 i_gid, i_nlinks;
+		__u16 i_zone[9];
+	} root = {
+		.i_mode = S_IFDIR | 0755,
+		.i_size = 2 * 16,
+		.i_nlinks = 2,
+		.i_zone = { MINIX_FIRSTDATA },
+	};
+	unsigned char imap[MINIX_BLOCK], zmap[MINIX_BLOCK], dir[MINIX_BLOCK] = {};
+	int i;
+
+	/* bit 0 is reserved in both maps, the root inode and its zone are in use */
+	memset(imap, 0xff, sizeof(imap));
+	for (i = 2; i <= MINIX_INODES; i++)
+		imap[i / 8] &= ~(1 << (i % 8));
+	memset(zmap, 0xff, sizeof(zmap));
+	for (i = 2; i <= MINIX_BLOCKS - MINIX_FIRSTDATA; i++)
+		zmap[i / 8] &= ~(1 << (i % 8));
+	dir[0] = 1;
+	dir[2] = '.';
+	dir[16] = 1;
+	dir[18] = '.';
+	dir[19] = '.';
+
+	if (pwrite(fd, &sb, sizeof(sb), 1 * MINIX_BLOCK) != sizeof(sb) ||
+	    pwrite(fd, imap, sizeof(imap), 2 * MINIX_BLOCK) != sizeof(imap) ||
+	    pwrite(fd, zmap, sizeof(zmap), 3 * MINIX_BLOCK) != sizeof(zmap) ||
+	    pwrite(fd, &root, sizeof(root), 4 * MINIX_BLOCK) != sizeof(root) ||
+	    pwrite(fd, dir, sizeof(dir), MINIX_FIRSTDATA * MINIX_BLOCK) != sizeof(dir))
+		return -1;
+	return ftruncate(fd, (off_t)MINIX_BLOCKS * MINIX_BLOCK);
+}
+
+static int read_sysfs(const char *path, char *buf, size_t size)
+{
+	ssize_t n;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return -1;
+	n = read(fd, buf, size - 1);
+	close(fd);
+	if (n < 0)
+		return -1;
+	buf[n] = '\0';
+	return 0;
+}
+
+/* Is @dev the mount source of this line of mountinfo? loop1 is not loop10. */
+static bool line_has_source(const char *line, const char *dev)
+{
+	const char *sep, *src, *end;
+
+	sep = strstr(line, " - ");
+	if (!sep)
+		return false;
+	src = strchr(sep + 3, ' ');	/* skip the filesystem type */
+	if (!src)
+		return false;
+	src++;
+	end = strchr(src, ' ');
+	if (!end)
+		return false;
+	return (size_t)(end - src) == strlen(dev) && !strncmp(src, dev, end - src);
+}
+
+/*
+ * Does a mount namespace of a process that /proc shows have a mount of @dev?
+ * The mounts under test are in no namespace at this point on any kernel, so
+ * this only checks that the test got as far as it thinks.
+ */
+static bool mounted_anywhere(const char *dev)
+{
+	char path[PATH_MAX], line[4096];
+	struct dirent *de;
+	bool found = false;
+	DIR *proc;
+	FILE *f;
+
+	proc = opendir("/proc");
+	if (!proc)
+		return false;
+	while (!found && (de = readdir(proc))) {
+		if (de->d_name[0] < '0' || de->d_name[0] > '9')
+			continue;
+		snprintf(path, sizeof(path), "/proc/%s/mountinfo", de->d_name);
+		f = fopen(path, "re");
+		if (!f)
+			continue;
+		while (fgets(line, sizeof(line), f)) {
+			if (line_has_source(line, dev)) {
+				found = true;
+				break;
+			}
+		}
+		fclose(f);
+	}
+	closedir(proc);
+	return found;
+}
+
+/* Wait up to @ms milliseconds for the loop device to give up its backing file. */
+static bool loop_released(const char *sysfs, int ms)
+{
+	char buf[PATH_MAX];
+
+	for (; ms > 0; ms -= 100) {
+		if (read_sysfs(sysfs, buf, sizeof(buf)) < 0)
+			return errno == ENOENT;
+		usleep(100000);
+	}
+	return read_sysfs(sysfs, buf, sizeof(buf)) < 0 && errno == ENOENT;
+}
+
+/* Tell the loop device to give its file up, now or when its last user is gone. */
+static void loop_clear(int n)
+{
+	char dev[32];
+	int lfd;
+
+	if (n < 0)
+		return;
+	snprintf(dev, sizeof(dev), "/dev/loop%d", n);
+	lfd = open(dev, O_RDWR);
+	if (lfd < 0)
+		return;
+	ioctl(lfd, LOOP_CLR_FD);
+	close(lfd);
+}
+
+FIXTURE(loop_cycle) {
+	char dev[32];		/* the loop device the child set up */
+	char sysfs[64];		/* its backing_file attribute */
+	int loops[MAX_LOOPS];	/* every loop device the case has bound */
+	int nr_loops;
+	bool gadget;		/* the gadget's configfs directory exists */
+};
+
+static void remember_loop(FIXTURE_DATA(loop_cycle) *self, int n)
+{
+	if (n >= 0 && self->nr_loops < MAX_LOOPS)
+		self->loops[self->nr_loops++] = n;
+}
+
+FIXTURE_SETUP(loop_cycle)
+{
+	if (geteuid() != 0)
+		SKIP(return, "test requires CAP_SYS_ADMIN");
+	if (access("/dev/loop-control", R_OK | W_OK))
+		SKIP(return, "test requires loop devices");
+
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+
+	snprintf(base, sizeof(base), "/tmp/loop_cycle.XXXXXX");
+	ASSERT_NE(mkdtemp(base), NULL);
+	/* a failed assertion in the setup does not run the teardown */
+	ASSERT_EQ(mount("tmpfs", base, "tmpfs", 0, NULL), 0)
+		rmdir(base);
+	snprintf(gadget, sizeof(gadget),
+		 "/sys/kernel/config/usb_gadget/kselftest_cycle_%d", getpid());
+	self->dev[0] = '\0';
+	self->nr_loops = 0;
+	self->gadget = false;
+}
+
+static int mount_configfs(void);
+static void gadget_remove(void);
+
+FIXTURE_TEARDOWN(loop_cycle)
+{
+	if (self->gadget)
+		gadget_remove();
+	/* whatever a failed assertion has left bound */
+	for (int i = 0; i < self->nr_loops; i++)
+		loop_clear(self->loops[i]);
+	umount2(base, MNT_DETACH);
+	rmdir(base);
+}
+
+/* Child exit codes. */
+enum {
+	CHILD_OK,
+	CHILD_NS,		/* could not set up the namespace or the tmpfs */
+	CHILD_IMAGE,		/* could not write the image */
+	CHILD_LOOP,		/* could not set up the loop device */
+	CHILD_MOUNT,		/* could not mount it (vfat and msdos both refused) */
+	CHILD_PIPE,		/* the parent went away */
+	CHILD_HOLDER,		/* could not set the holder up below the mount */
+	CHILD_SKIP,		/* the kernel lacks what the holder needs */
+	CHILD_NOFS,		/* the kernel lacks the filesystem of the image */
+};
+
+/* Bind the loop device that LOOP_CTL_GET_FREE names to @ifd; the device number. */
+static int loop_bind_free(int ifd)
+{
+	int cfd, lfd, n;
+	char dev[32];
+
+	cfd = open("/dev/loop-control", O_RDWR);
+	if (cfd < 0)
+		return -1;
+	n = ioctl(cfd, LOOP_CTL_GET_FREE);
+	close(cfd);
+	if (n < 0)
+		return -1;
+	snprintf(dev, sizeof(dev), "/dev/loop%d", n);
+	lfd = open(dev, O_RDWR);
+	if (lfd < 0)
+		return -1;
+	if (ioctl(lfd, LOOP_SET_FD, ifd))
+		n = -1;
+	close(lfd);
+	return n;
+}
+
+/*
+ * Bind a free loop device to the open image @ifd; the device number. The
+ * device is free when LOOP_CTL_GET_FREE names it and may be somebody else's
+ * a moment later, so try again when it is busy.
+ */
+static int loop_bind(int ifd)
+{
+	int n = -1;
+
+	for (int i = 0; i < 64 && n < 0; i++) {
+		n = loop_bind_free(ifd);
+		if (n < 0 && errno != EBUSY)
+			return -1;
+	}
+	if (n >= 0 && nr_bound < MAX_LOOPS)
+		bound[nr_bound++] = n;
+	return n;
+}
+
+/* Mount a FAT image, as vfat or as msdos; -1 with ENODEV if the kernel has neither. */
+static int mount_fat(const char *dev, const char *mp)
+{
+	int err;
+
+	if (!mount(dev, mp, "vfat", 0, NULL))
+		return 0;
+	err = errno;
+	if (!mount(dev, mp, "msdos", 0, NULL))
+		return 0;
+	if (err != ENODEV)
+		errno = err;
+	return -1;
+}
+
+/*
+ * A child that gives up has to take down what it has set up: nobody else
+ * knows about it. Unmount, then tell the loop devices to let go. The mounts
+ * are released after this process is gone and the devices follow them.
+ */
+static int child_fails(int ret)
+{
+	umount2(at("vol"), MNT_DETACH);
+	umount2(at("vol2"), MNT_DETACH);
+	umount2(at("p"), MNT_DETACH);
+	umount2(at("img"), MNT_DETACH);
+	for (int i = 0; i < nr_bound; i++)
+		loop_clear(bound[i]);
+	return ret;
+}
+
+/* Write an image to @img, bind a loop device to it and mount that at @mp; the device number. */
+static int loop_mount(const char *img, const char *mp)
+{
+	char dev[32];
+	int ifd, n;
+
+	ifd = open(img, O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (ifd < 0 || write_fat12(ifd))
+		return -CHILD_IMAGE;
+	n = loop_bind(ifd);
+	close(ifd);	/* the loop device holds the file from now on */
+	if (n < 0)
+		return -CHILD_LOOP;
+	snprintf(dev, sizeof(dev), "/dev/loop%d", n);
+	if (mkdir(mp, 0755))
+		return -CHILD_MOUNT;
+	if (mount_fat(dev, mp))
+		return errno == ENODEV ? -CHILD_NOFS : -CHILD_MOUNT;
+	return n;
+}
+
+/*
+ * Two tmpfs mounts, each carrying the image of the loop mount below the
+ * other: the loop mount below vol has its image on vol2 and the other way
+ * round.
+ */
+static int crossed_child(int to_parent, int from_parent)
+{
+	struct report r;
+	char c;
+
+	if (unshare(CLONE_NEWNS) || mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL))
+		return CHILD_NS;
+	if (mkdir(at("vol"), 0755) || mount("tmpfs", at("vol"), "tmpfs", 0, NULL) ||
+	    mkdir(at("vol2"), 0755) || mount("tmpfs", at("vol2"), "tmpfs", 0, NULL))
+		return child_fails(CHILD_NS);
+	r.n[0] = loop_mount(at("vol2/img"), at("vol/mnt"));
+	if (r.n[0] < 0)
+		return child_fails(-r.n[0]);
+	r.n[1] = loop_mount(at("vol/img"), at("vol2/mnt"));
+	if (r.n[1] < 0)
+		return child_fails(-r.n[1]);
+	if (write(to_parent, &r, sizeof(r)) != sizeof(r))
+		return child_fails(CHILD_PIPE);
+	if (read(from_parent, &c, 1) != 1)
+		return child_fails(CHILD_PIPE);
+	return CHILD_OK;
+}
+
+/*
+ * In its own mount namespace the child mounts a tmpfs on vol,
+ * puts a filesystem image on it, binds a loop device to the image and
+ * mounts that loop device below. The loop device's backing file is a
+ * reference on the mount the image is on, held by the loop device, held
+ * by the mounted filesystem, held by the mount below.
+ */
+static int loop_child(int to_parent, int from_parent)
+{
+	struct report r = { { -1, -1 } };
+	char c;
+
+	if (unshare(CLONE_NEWNS) || mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL))
+		return CHILD_NS;
+	if (mkdir(at("vol"), 0755) || mount("tmpfs", at("vol"), "tmpfs", 0, NULL))
+		return child_fails(CHILD_NS);
+	r.n[0] = loop_mount(at("vol/img"), at("vol/mnt"));
+	if (r.n[0] < 0)
+		return child_fails(-r.n[0]);
+
+	if (write(to_parent, &r, sizeof(r)) != sizeof(r))
+		return child_fails(CHILD_PIPE);
+	/* keep the namespace alive while the parent removes the directory */
+	if (read(from_parent, &c, 1) != 1)
+		return child_fails(CHILD_PIPE);
+	return CHILD_OK;
+}
+
+/*
+ * The child did not report. Skip if the kernel lacks something, fail with
+ * what the child said otherwise. A child that a signal killed has failed.
+ */
+#define CHILD_GAVE_UP(pid) do {						\
+	int __status;							\
+									\
+	ASSERT_EQ(waitpid(pid, &__status, 0), pid);			\
+	if (WIFEXITED(__status) && WEXITSTATUS(__status) == CHILD_NOFS)	\
+		SKIP(return, "test requires the filesystem of the image (FAT or minix)"); \
+	if (WIFEXITED(__status) && WEXITSTATUS(__status) == CHILD_SKIP)	\
+		SKIP(return, "the kernel lacks what this holder needs"); \
+	ASSERT_TRUE(false)						\
+		TH_LOG("child failed to set up: %s %d",			\
+		       WIFEXITED(__status) ? "exit status" : "signal",	\
+		       WIFEXITED(__status) ? WEXITSTATUS(__status) : WTERMSIG(__status)); \
+} while (0)
+
+/* The child has to leave by itself and with nothing to complain about. */
+#define CHILD_LEFT(pid) do {						\
+	int __status;							\
+									\
+	ASSERT_EQ(waitpid(pid, &__status, 0), pid);			\
+	ASSERT_TRUE(WIFEXITED(__status));				\
+	ASSERT_EQ(WEXITSTATUS(__status), CHILD_OK);			\
+} while (0)
+
+/*
+ * An exclusive open of the device fails while a filesystem holds it, and
+ * the only filesystem that ever did is the one mounted below the dead
+ * mount. Give a release in flight a moment. Then the device must clear
+ * right away rather than only be marked for autoclear.
+ */
+static void assert_loop_released(struct __test_metadata *_metadata,
+				 FIXTURE_DATA(loop_cycle) *self)
+{
+	int lfd;
+
+	for (int i = 0; i < 20; i++) {
+		lfd = open(self->dev, O_RDONLY | O_EXCL);
+		if (lfd >= 0)
+			break;
+		usleep(100000);
+	}
+	EXPECT_GE(lfd, 0)
+		TH_LOG("%s is still held by the loop mount below the dead mount: nothing refers to either mount and nothing can release them",
+		       self->dev);
+	if (lfd >= 0)
+		close(lfd);
+
+	lfd = open(self->dev, O_RDWR);
+	ASSERT_GE(lfd, 0);
+	ASSERT_EQ(ioctl(lfd, LOOP_CLR_FD), 0);
+	close(lfd);
+	ASSERT_TRUE(loop_released(self->sysfs, 5000))
+		TH_LOG("%s kept its backing file after LOOP_CLR_FD: the filesystem on it is still mounted somewhere nobody can reach",
+		       self->dev);
+	/* somebody else may bind it from now on, so the teardown leaves it alone */
+	for (int i = 0; i < self->nr_loops; i++) {
+		char dev[32];
+
+		snprintf(dev, sizeof(dev), "/dev/loop%d", self->loops[i]);
+		if (!strcmp(dev, self->dev))
+			self->loops[i] = -1;
+	}
+}
+
+/*
+ * rmdir of vol from here, where it is not a mountpoint, detaches
+ * the child's tmpfs with the loop mount connected below it. Once the child
+ * is gone nothing refers to either mount. The loop device must then be
+ * free to give up its backing file, which only happens when the mounted
+ * filesystem below the detached tmpfs has been released.
+ */
+TEST_F(loop_cycle, detached_loop_mount_released)
+{
+	int to_parent[2], to_child[2];
+	struct report r = { { -1, -1 } };
+	char buf[PATH_MAX];
+	pid_t pid;
+
+	ASSERT_EQ(pipe(to_parent), 0);
+	ASSERT_EQ(pipe(to_child), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		close(to_parent[0]);
+		close(to_child[1]);
+		_exit(loop_child(to_parent[1], to_child[0]));
+	}
+	close(to_parent[1]);
+	close(to_child[0]);
+
+	if (read(to_parent[0], &r, sizeof(r)) != sizeof(r))
+		CHILD_GAVE_UP(pid);
+	remember_loop(self, r.n[0]);
+	snprintf(self->dev, sizeof(self->dev), "/dev/loop%d", r.n[0]);
+	snprintf(self->sysfs, sizeof(self->sysfs), "/sys/block/loop%d/loop/backing_file", r.n[0]);
+	ASSERT_EQ(read_sysfs(self->sysfs, buf, sizeof(buf)), 0);
+	ASSERT_NE(strstr(buf, "/vol/img"), NULL);
+
+	/* not a mountpoint in this namespace, so the directory can go */
+	ASSERT_EQ(rmdir(at("vol")), 0);
+
+	/* the child leaves: its namespace and every reference it held are gone */
+	ASSERT_EQ(write(to_child[1], "", 1), 1);
+	CHILD_LEFT(pid);
+	close(to_parent[0]);
+	close(to_child[1]);
+
+	/* nothing can reach the two mounts any more */
+	ASSERT_EQ(access(at("vol"), F_OK), -1);
+	ASSERT_FALSE(mounted_anywhere(self->dev));
+
+	assert_loop_released(_metadata, self);
+}
+
+/*
+ * The same two mounts in a detached tree: a clone of vol from
+ * open_tree(), the image opened through the clone so that the loop device
+ * holds the clone, and the loop mount moved below the clone. The last
+ * close of the tree's fd dissolves the tree with the loop mount left
+ * connected below the dead clone, and nothing refers to either afterwards.
+ */
+TEST_F(loop_cycle, dissolved_tree_loop_mount_released)
+{
+	int tfd, ifd, fsfd, mfd, n;
+	char buf[PATH_MAX];
+
+	fsfd = sys_fsopen("vfat", 0);
+	if (fsfd < 0)
+		fsfd = sys_fsopen("msdos", 0);
+	if (fsfd < 0)
+		SKIP(return, "test requires a FAT filesystem");
+
+	ASSERT_EQ(mkdir(at("vol"), 0755), 0);
+	ASSERT_EQ(mount("tmpfs", at("vol"), "tmpfs", 0, NULL), 0);
+	tfd = sys_open_tree(AT_FDCWD, at("vol"), OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(tfd, 0);
+
+	/* the image, opened through the clone: the loop device holds the clone */
+	ifd = openat(tfd, "img", O_RDWR | O_CREAT | O_EXCL, 0600);
+	ASSERT_GE(ifd, 0);
+	ASSERT_EQ(write_fat12(ifd), 0);
+	n = loop_bind(ifd);
+	close(ifd);
+	ASSERT_GE(n, 0);
+	remember_loop(self, n);
+	snprintf(self->dev, sizeof(self->dev), "/dev/loop%d", n);
+	snprintf(self->sysfs, sizeof(self->sysfs), "/sys/block/loop%d/loop/backing_file", n);
+
+	/* the loop mount, moved below the clone */
+	ASSERT_EQ(mkdirat(tfd, "mnt", 0755), 0);
+	ASSERT_EQ(sys_fsconfig(fsfd, FSCONFIG_SET_STRING, "source", self->dev, 0), 0);
+	ASSERT_EQ(sys_fsconfig(fsfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0), 0);
+	mfd = sys_fsmount(fsfd, 0, 0);
+	ASSERT_GE(mfd, 0);
+	close(fsfd);
+	ASSERT_EQ(sys_move_mount(mfd, "", tfd, "mnt", MOVE_MOUNT_F_EMPTY_PATH), 0);
+	close(mfd);
+
+	ASSERT_EQ(read_sysfs(self->sysfs, buf, sizeof(buf)), 0);
+	ASSERT_NE(strstr(buf, "img"), NULL);
+
+	/* the last fd of the tree: both mounts die, the loop mount connected */
+	close(tfd);
+
+	/* nothing can reach the two mounts any more */
+	ASSERT_FALSE(mounted_anywhere(self->dev));
+
+	assert_loop_released(_metadata, self);
+}
+
+/*
+ * The cycle in two steps: rmdir of vol leaves the loop mount below it
+ * connected while its image's mount, vol2, is alive; then rmdir of vol2
+ * takes that one with the loop mount whose image is on the dead vol. Each
+ * dead mount now owns a loop mount whose filesystem pins the other.
+ */
+TEST_F(loop_cycle, crossed_images_released)
+{
+	int to_parent[2], to_child[2];
+	struct report r = { { -1, -1 } };
+	char sysfs[2][64], dev[2][32];
+	pid_t pid;
+
+	ASSERT_EQ(pipe(to_parent), 0);
+	ASSERT_EQ(pipe(to_child), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		close(to_parent[0]);
+		close(to_child[1]);
+		_exit(crossed_child(to_parent[1], to_child[0]));
+	}
+	close(to_parent[1]);
+	close(to_child[0]);
+
+	if (read(to_parent[0], &r, sizeof(r)) != sizeof(r))
+		CHILD_GAVE_UP(pid);
+	for (int i = 0; i < 2; i++) {
+		remember_loop(self, r.n[i]);
+		snprintf(dev[i], sizeof(dev[i]), "/dev/loop%d", r.n[i]);
+		snprintf(sysfs[i], sizeof(sysfs[i]), "/sys/block/loop%d/loop/backing_file", r.n[i]);
+	}
+
+	/* step one: the mount with the first loop mount below it goes */
+	ASSERT_EQ(rmdir(at("vol")), 0);
+
+	/* step two: the other one, with the loop mount whose image is on the first */
+	ASSERT_EQ(rmdir(at("vol2")), 0);
+
+	/* the child leaves: its namespace and every reference it held are gone */
+	ASSERT_EQ(write(to_child[1], "", 1), 1);
+	CHILD_LEFT(pid);
+	close(to_parent[0]);
+	close(to_child[1]);
+
+	/* nothing can reach the four mounts any more */
+	for (int i = 0; i < 2; i++) {
+		ASSERT_FALSE(mounted_anywhere(dev[i]));
+		strcpy(self->dev, dev[i]);
+		strcpy(self->sysfs, sysfs[i]);
+		assert_loop_released(_metadata, self);
+	}
+}
+
+/*
+ * The holders. Each keeps a file or a path on a mount P for as long as
+ * its own filesystem or device lives, and each has that filesystem or
+ * device mounted at C below P. Once another namespace's rmdir has
+ * detached P with C connected below it and the child is gone, P is owned
+ * by nobody, C by P, and P is kept by whatever the holder still holds.
+ *
+ * P is a loop mount so that its death can be observed: the loop device
+ * gives its backing file up when P's superblock goes. The image sits on
+ * a tmpfs next to P, not above it, so the loop device's own reference is
+ * not part of the picture.
+ */
+enum holder {
+	HOLDER_AUTOFS,		/* a FIFO on P as the daemon's pipe */
+	HOLDER_ZRAM,		/* a device node on P as the writeback device */
+	HOLDER_ECRYPTFS,	/* a directory on P as the lower directory */
+	HOLDER_BINFMT_MISC,	/* an executable on P as an 'F' interpreter */
+	HOLDER_FUSE,		/* a file on P as a passthrough backing file */
+	HOLDER_ZLOOP,		/* a directory on P for the zone files */
+	HOLDER_GADGET,		/* a file on P as a mass storage LUN, over dummy_hcd */
+	HOLDER_MD,		/* a file on P as an array's bitmap file */
+};
+
+#define HOLDER_IMG	at("img/p.img")
+#define HOLDER_MNT	at("p")
+#define HOLDER_BELOW	at("p/c")
+
+static int write_file(const char *path, const char *s)
+{
+	int fd = open(path, O_WRONLY);
+	ssize_t n;
+
+	if (fd < 0)
+		return -1;
+	n = write(fd, s, strlen(s));
+	close(fd);
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+/* Bind a free loop device to @img; the device number. */
+static int loop_attach(const char *img)
+{
+	int ifd, n;
+
+	ifd = open(img, O_RDWR);
+	if (ifd < 0)
+		return -1;
+	n = loop_bind(ifd);
+	close(ifd);
+	return n;
+}
+
+static int holder_autofs(void)
+{
+	char opts[64];
+	int pfd;
+
+	if (mkfifo(at("p/pipe"), 0600))
+		return CHILD_HOLDER;
+	pfd = open(at("p/pipe"), O_RDWR);
+	if (pfd < 0)
+		return CHILD_HOLDER;
+	snprintf(opts, sizeof(opts), "fd=%d,minproto=5,maxproto=5", pfd);
+	if (mount("autofs", HOLDER_BELOW, "autofs", 0, opts))
+		return errno == ENODEV ? CHILD_SKIP : CHILD_HOLDER;
+	close(pfd);	/* the mount keeps its own */
+	return CHILD_OK;
+}
+
+/*
+ * zram's writeback device has to be a block device node, and that node has
+ * to be on P. Point it at a second loop device.
+ */
+static void zram_reset(void);
+
+static int holder_zram(void)
+{
+	char dev[32], buf[64];
+	struct stat st;
+	int fd, n;
+
+	if (access("/sys/block/zram0/backing_dev", W_OK))
+		return CHILD_SKIP;
+	/* somebody else's device, leave it alone */
+	if (read_sysfs("/sys/block/zram0/initstate", buf, sizeof(buf)) || buf[0] != '0')
+		return CHILD_SKIP;
+	fd = open(at("img/wb.img"), O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (fd < 0 || ftruncate(fd, IMAGE_SIZE))
+		return CHILD_HOLDER;
+	close(fd);
+	n = loop_attach(at("img/wb.img"));
+	if (n < 0)
+		return CHILD_HOLDER;
+	/* the minor is not the number of the device when loop has partitions */
+	snprintf(dev, sizeof(dev), "/dev/loop%d", n);
+	if (stat(dev, &st) || mknod(at("p/wbdev"), S_IFBLK | 0600, st.st_rdev))
+		return CHILD_HOLDER;
+	if (write_file("/sys/block/zram0/backing_dev", at("p/wbdev")))
+		return CHILD_HOLDER;
+	snprintf(buf, sizeof(buf), "%d", 4 * 1024 * 1024);
+	if (write_file("/sys/block/zram0/disksize", buf))
+		goto undo;
+	fd = open("/dev/zram0", O_RDWR);
+	if (fd < 0)
+		goto undo;
+	n = write_fat12_4k(fd, 1024);	/* zram has 4 KiB blocks */
+	close(fd);	/* the reset in undo is refused while the device is open */
+	if (n)
+		goto undo;
+	if (mount_fat("/dev/zram0", HOLDER_BELOW)) {
+		n = errno == ENODEV ? CHILD_NOFS : CHILD_HOLDER;
+		zram_reset();
+		return n;
+	}
+	return CHILD_OK;
+undo:
+	zram_reset();
+	return CHILD_HOLDER;
+}
+
+/* Is @alg in /proc/crypto? A module is listed once a request has loaded it. */
+static bool crypto_has(const char *alg)
+{
+	char line[256], name[64];
+	bool found = false;
+	FILE *f;
+
+	f = fopen("/proc/crypto", "r");
+	if (!f)
+		return true;	/* no way to tell, assume it is */
+	while (!found && fgets(line, sizeof(line), f))
+		found = sscanf(line, "name : %63s", name) == 1 && !strcmp(name, alg);
+	fclose(f);
+	return found;
+}
+
+/* The kernel's auth token layout, which userspace has to match byte for byte. */
+struct ecryptfs_auth_tok {
+	__u16 version;
+	__u16 token_type;
+	__u32 flags;
+	struct {
+		__u32 flags, encrypted_key_size, decrypted_key_size;
+		__u8 encrypted_key[512], decrypted_key[64];
+	} session_key;
+	__u8 reserved[32];
+	struct {
+		__u32 password_bytes;
+		__s32 hash_algo;
+		__u32 hash_iterations, session_key_encryption_key_bytes, flags;
+		__u8 session_key_encryption_key[64];
+		__u8 signature[17];
+		__u8 salt[8];
+	} password;
+} __attribute__((packed));
+
+#define ECRYPTFS_SIG	"0123456789abcdef"
+
+static int holder_ecryptfs(void)
+{
+	struct ecryptfs_auth_tok tok = {
+		.version = 0x0004,
+		.token_type = 0,		/* ECRYPTFS_PASSWORD */
+		.password.session_key_encryption_key_bytes = 16,
+		.password.flags = 0x02,		/* ECRYPTFS_SESSION_KEY_ENCRYPTION_KEY_SET */
+		.password.signature = ECRYPTFS_SIG,
+	};
+
+	/* a session keyring of this child's own, so that the key goes with it */
+	if (syscall(__NR_keyctl, KEYCTL_JOIN_SESSION_KEYRING, NULL) < 0)
+		return errno == ENOSYS ? CHILD_SKIP : CHILD_HOLDER;
+	if (syscall(__NR_add_key, "user", ECRYPTFS_SIG, &tok, sizeof(tok),
+		    KEY_SPEC_SESSION_KEYRING) < 0)
+		return CHILD_HOLDER;
+	if (mkdir(at("p/lower"), 0755))
+		return CHILD_HOLDER;
+	if (mount(at("p/lower"), HOLDER_BELOW, "ecryptfs", 0,
+		  "ecryptfs_sig=" ECRYPTFS_SIG ",ecryptfs_cipher=aes,ecryptfs_key_bytes=16")) {
+		/* EINVAL without the cipher; a module is loaded by the attempt */
+		if (errno == ENODEV || (errno == EINVAL && !crypto_has("aes")))
+			return CHILD_SKIP;
+		return CHILD_HOLDER;
+	}
+	return CHILD_OK;
+}
+
+/*
+ * binfmt_misc instances are per user namespace, so the mount below P is
+ * made from a new one, which gets a copy of P.
+ */
+static int holder_binfmt_misc(void)
+{
+	static const char interp[] = "#!/bin/true\n";
+	char reg[PATH_MAX];
+	int out;
+
+	/* 'F' opens the interpreter at registration, nothing runs it here */
+	out = open(at("p/interp"), O_WRONLY | O_CREAT | O_EXCL, 0755);
+	if (out < 0 || write(out, interp, sizeof(interp) - 1) != sizeof(interp) - 1)
+		return CHILD_HOLDER;
+	close(out);
+
+	/* ENOSPC: user.max_user_namespaces is 0, EPERM: an LSM says no */
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS)) {
+		if (errno == EINVAL || errno == ENOSPC || errno == EPERM)
+			return CHILD_SKIP;
+		return CHILD_HOLDER;
+	}
+	if (write_file("/proc/self/setgroups", "deny") ||
+	    write_file("/proc/self/uid_map", "0 0 1") ||
+	    write_file("/proc/self/gid_map", "0 0 1"))
+		return CHILD_HOLDER;
+	if (mount("binfmt_misc", HOLDER_BELOW, "binfmt_misc", 0, NULL))
+		return errno == ENODEV ? CHILD_SKIP : CHILD_HOLDER;
+	snprintf(reg, sizeof(reg), ":cycle:E::cyc::%s:F", at("p/interp"));
+	if (write_file(at("p/c/register"), reg))
+		return CHILD_HOLDER;
+	return CHILD_OK;
+}
+
+/*
+ * A fuse server that only ever answers FUSE_INIT, with passthrough on, and
+ * then registers a file on P as a backing file. The registration alone
+ * makes the fuse superblock hold the file.
+ */
+static int holder_fuse(void)
+{
+	struct fuse_backing_map map = {};
+	struct fuse_in_header *ih;
+	struct fuse_init_out init = {
+		.major = FUSE_KERNEL_VERSION,
+		.minor = FUSE_KERNEL_MINOR_VERSION,
+		.flags = FUSE_INIT_EXT,
+		.flags2 = FUSE_PASSTHROUGH >> 32,
+		.max_write = 4096,
+		.max_stack_depth = 1,
+	};
+	struct fuse_out_header oh = { .len = sizeof(oh) + sizeof(init) };
+	struct iovec iov[2] = { { &oh, sizeof(oh) }, { &init, sizeof(init) } };
+	char opts[64], buf[8192];
+	int ffd, bfd;
+	ssize_t n;
+
+	bfd = open(at("p/backing"), O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (bfd < 0)
+		return CHILD_HOLDER;
+	ffd = open("/dev/fuse", O_RDWR);
+	if (ffd < 0)
+		return CHILD_SKIP;
+	snprintf(opts, sizeof(opts), "fd=%d,rootmode=40000,user_id=0,group_id=0", ffd);
+	if (mount("fuse", HOLDER_BELOW, "fuse", 0, opts))
+		return errno == ENODEV ? CHILD_SKIP : CHILD_HOLDER;
+
+	n = read(ffd, buf, sizeof(buf));
+	ih = (void *)buf;
+	if (n < (ssize_t)sizeof(*ih) || ih->opcode != FUSE_INIT)
+		return CHILD_HOLDER;
+	oh.unique = ih->unique;
+	if (writev(ffd, iov, 2) != (ssize_t)oh.len)
+		return CHILD_HOLDER;
+
+	map.fd = bfd;
+	if (ioctl(ffd, FUSE_DEV_IOC_BACKING_OPEN, &map) < 0) {
+		/* EOPNOTSUPP: no FUSE_PASSTHROUGH, ENOTTY: no such ioctl */
+		if (errno == EPERM || errno == EOPNOTSUPP || errno == ENOTTY)
+			return CHILD_SKIP;
+		return CHILD_HOLDER;
+	}
+	close(bfd);	/* the connection keeps its own */
+	return CHILD_OK;	/* ffd stays open until the child exits */
+}
+
+/* Wait for a device node the kernel is about to create. */
+static int open_when_there(const char *dev, int flags, int ms)
+{
+	int fd;
+
+	for (; ms > 0; ms -= 100) {
+		fd = open(dev, flags);
+		if (fd >= 0)
+			return fd;
+		usleep(100000);
+	}
+	return -1;
+}
+
+/*
+ * zloop keeps every zone file open. One conventional zone is enough for a
+ * FAT image, the sequential one stays empty.
+ */
+static int holder_zloop(void)
+{
+	char cmd[PATH_MAX];
+	int fd, ret = CHILD_HOLDER;
+
+	if (access("/dev/zloop-control", W_OK))
+		return CHILD_SKIP;
+	/* somebody else's device, leave it alone */
+	if (!access("/sys/block/zloop0", F_OK))
+		return CHILD_SKIP;
+	if (mkdir(at("p/zl"), 0755) || mkdir(at("p/zl/0"), 0755))
+		return CHILD_HOLDER;
+	snprintf(cmd, sizeof(cmd),
+		 "add id=0,capacity_mb=8,zone_size_mb=4,conv_zones=1,base_dir=%s",
+		 at("p/zl"));
+	if (write_file("/dev/zloop-control", cmd))
+		return CHILD_HOLDER;
+	fd = open_when_there("/dev/zloop0", O_RDWR, 5000);
+	if (fd < 0 || write_fat12_4k(fd, 1024))	/* 4 KiB blocks, like P */
+		goto undo;
+	close(fd);
+	fd = -1;
+	if (mount_fat("/dev/zloop0", HOLDER_BELOW)) {
+		ret = errno == ENODEV ? CHILD_NOFS : CHILD_HOLDER;
+		goto undo;
+	}
+	return CHILD_OK;
+undo:
+	if (fd >= 0)
+		close(fd);
+	write_file("/dev/zloop-control", "remove id=0");
+	return ret;
+}
+
+static int mount_configfs(void)
+{
+	if (access("/sys/kernel/config", F_OK))
+		return -1;
+	if (mount("configfs", "/sys/kernel/config", "configfs", 0, NULL) && errno != EBUSY)
+		return -1;
+	return 0;
+}
+
+/* Take the gadget out of configfs again, in the reverse order of its creation. */
+static void gadget_remove(void)
+{
+	if (mount_configfs())
+		return;
+	write_file(gat("/functions/mass_storage.0/lun.0/file"), "\n");
+	write_file(gat("/UDC"), "\n");
+	unlink(gat("/configs/c.1/mass_storage.0"));
+	rmdir(gat("/configs/c.1/strings/0x409"));
+	rmdir(gat("/configs/c.1"));
+	rmdir(gat("/functions/mass_storage.0"));
+	rmdir(gat("/strings/0x409"));
+	rmdir(gat(""));
+}
+
+/* The disk usb-storage created for the gadget, by the LUN's inquiry string. */
+static int find_gadget_disk(char *dev, size_t len, int ms)
+{
+	char path[PATH_MAX], model[64];
+	struct dirent *de;
+	DIR *d;
+
+	for (; ms > 0; ms -= 100, usleep(100000)) {
+		d = opendir("/sys/block");
+		if (!d)
+			return -1;
+		while ((de = readdir(d))) {
+			if (strncmp(de->d_name, "sd", 2))
+				continue;
+			snprintf(path, sizeof(path), "/sys/block/%s/device/model", de->d_name);
+			if (read_sysfs(path, model, sizeof(model)) ||
+			    strncmp(model, "File-Stor Gadget", 16))
+				continue;
+			snprintf(dev, len, "/dev/%s", de->d_name);
+			closedir(d);
+			return 0;
+		}
+		closedir(d);
+	}
+	return -1;
+}
+
+/*
+ * A mass storage gadget bound to the dummy UDC, so that this kernel is
+ * also the USB host that sees the LUN as a SCSI disk. sd locks the
+ * medium on open, which is what keeps the LUN's file from being ejected.
+ */
+#define GADGET_STEP(x) do {						\
+	if (x) {							\
+		fprintf(stderr, "gadget: %s failed: %s\n", #x, strerror(errno)); \
+		gadget_remove();					\
+		return CHILD_HOLDER;					\
+	}								\
+} while (0)
+
+static int holder_gadget(void)
+{
+	char dev[PATH_MAX];
+	int fd;
+
+	if (mount_configfs())
+		return CHILD_SKIP;
+	if (access("/sys/kernel/config/usb_gadget", F_OK) ||
+	    access("/sys/class/udc/dummy_udc.0", F_OK))
+		return CHILD_SKIP;
+
+	fd = open(at("p/lun.img"), O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (fd < 0 || write_fat12(fd))
+		return CHILD_HOLDER;
+	close(fd);
+
+	GADGET_STEP(mkdir(gat(""), 0755));
+	GADGET_STEP(write_file(gat("/idVendor"), "0x1d6b"));
+	GADGET_STEP(write_file(gat("/idProduct"), "0x0104"));
+	GADGET_STEP(mkdir(gat("/strings/0x409"), 0755));
+	GADGET_STEP(write_file(gat("/strings/0x409/serialnumber"), "1"));
+	GADGET_STEP(write_file(gat("/strings/0x409/manufacturer"), "kselftest"));
+	GADGET_STEP(write_file(gat("/strings/0x409/product"), "cycle"));
+	GADGET_STEP(mkdir(gat("/configs/c.1"), 0755));
+	GADGET_STEP(mkdir(gat("/configs/c.1/strings/0x409"), 0755));
+	GADGET_STEP(write_file(gat("/configs/c.1/strings/0x409/configuration"), "c"));
+	GADGET_STEP(mkdir(gat("/functions/mass_storage.0"), 0755));
+	GADGET_STEP(write_file(gat("/functions/mass_storage.0/lun.0/removable"), "1"));
+	GADGET_STEP(write_file(gat("/functions/mass_storage.0/lun.0/file"), at("p/lun.img")));
+	GADGET_STEP(symlink(gat("/functions/mass_storage.0"), gat("/configs/c.1/mass_storage.0")));
+	/* EBUSY: the controller is somebody else's, leave it alone */
+	if (write_file(gat("/UDC"), "dummy_udc.0")) {
+		fd = errno == EBUSY ? CHILD_SKIP : CHILD_HOLDER;
+		gadget_remove();
+		return fd;
+	}
+
+	/* usb-storage waits a second before it scans the device */
+	if (find_gadget_disk(dev, sizeof(dev), 15000)) {
+		/* without usb-storage and sd the LUN never shows up as a disk */
+		fd = (access("/sys/bus/usb/drivers/usb-storage", F_OK) ||
+		      access("/sys/bus/scsi/drivers/sd", F_OK)) ? CHILD_SKIP : CHILD_HOLDER;
+		gadget_remove();
+		return fd;
+	}
+	fd = open_when_there(dev, O_RDONLY, 5000);
+	GADGET_STEP(fd < 0);
+	close(fd);
+	if (mount_fat(dev, HOLDER_BELOW)) {
+		fd = errno == ENODEV ? CHILD_NOFS : CHILD_HOLDER;
+		gadget_remove();
+		return fd;
+	}
+	return CHILD_OK;
+}
+
+#define BITMAP_MAGIC	0x6d746962
+
+/*
+ * A RAID1 of one loop device, not persistent, with its bitmap in a file
+ * on P. The bitmap file needs a superblock the kernel accepts; sync_size,
+ * uuid and events are not looked at for a non-persistent array.
+ */
+static int holder_md(void)
+{
+	struct {
+		__u32 magic, version;
+		__u8 uuid[16];
+		__u64 events, events_cleared, sync_size;
+		__u32 state, chunksize, daemon_sleep, write_behind;
+	} bsb = {
+		.magic = BITMAP_MAGIC,
+		.version = 4,
+		.chunksize = 64 * 1024,
+		.daemon_sleep = 5,
+	};
+	mdu_array_info_t info = {
+		.level = 1,
+		.raid_disks = 1,
+		.size = 8 * 1024,		/* KiB */
+		.not_persistent = 1,
+	};
+	mdu_disk_info_t disk = {
+		.major = 7,
+		.state = (1 << MD_DISK_ACTIVE) | (1 << MD_DISK_SYNC),
+	};
+	int fd, mdfd, bfd, n, ret = CHILD_HOLDER;
+	char dev[32], buf[4096];
+	struct stat st;
+
+	fd = open(at("img/md.img"), O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (fd < 0 || ftruncate(fd, 8 * 1024 * 1024))
+		return CHILD_HOLDER;
+	close(fd);
+	n = loop_attach(at("img/md.img"));
+	if (n < 0)
+		return CHILD_HOLDER;
+	/* the minor is not the number of the device when loop has partitions */
+	snprintf(dev, sizeof(dev), "/dev/loop%d", n);
+	if (stat(dev, &st))
+		return CHILD_HOLDER;
+	disk.major = major(st.st_rdev);
+	disk.minor = minor(st.st_rdev);
+
+	bfd = open(at("p/bitmap"), O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (bfd < 0 || write(bfd, &bsb, sizeof(bsb)) != sizeof(bsb) || ftruncate(bfd, 4096))
+		return CHILD_HOLDER;
+
+	if (read_sysfs("/proc/mdstat", buf, sizeof(buf))) {
+		fprintf(stderr, "md: no /proc/mdstat\n");
+		return CHILD_SKIP;
+	}
+	if (!strstr(buf, "[raid1]")) {
+		fprintf(stderr, "md: no raid1 personality: %s\n", buf);
+		return CHILD_SKIP;
+	}
+	/* a node of our own: /dev may not have one and is not ours to change */
+	if (mknod(at("img/md0"), S_IFBLK | 0600, makedev(MD_MAJOR, 0)))
+		return CHILD_HOLDER;
+	mdfd = open(at("img/md0"), O_RDWR);
+	if (mdfd < 0)
+		return CHILD_SKIP;
+	/* somebody else's array: SET_ARRAY_INFO would say EINVAL, not EBUSY */
+	if (!read_sysfs("/sys/block/md0/md/array_state", buf, sizeof(buf)) &&
+	    strncmp(buf, "clear", 5)) {
+		fprintf(stderr, "md: md0 is in use: %s", buf);
+		close(mdfd);
+		return CHILD_SKIP;
+	}
+	/* the bitmap ops are only installed once a bitmap type is chosen */
+	write_file("/sys/block/md0/md/bitmap_type", "bitmap");
+	/* EBUSY: somebody else's array, leave it alone */
+	if (ioctl(mdfd, SET_ARRAY_INFO, &info))
+		return errno == EBUSY ? CHILD_SKIP : CHILD_HOLDER;
+	/* the array is ours from here on and has to be stopped on every path */
+	if (ioctl(mdfd, ADD_NEW_DISK, &disk))
+		goto undo;
+	/* attach the bitmap file before the array runs, the way mdadm does */
+	if (ioctl(mdfd, SET_BITMAP_FILE, bfd)) {
+		fprintf(stderr, "md: SET_BITMAP_FILE: %s\n", strerror(errno));
+		if (errno == EINVAL)
+			ret = CHILD_SKIP;
+		goto undo;
+	}
+	close(bfd);	/* the array keeps its own */
+	if (ioctl(mdfd, RUN_ARRAY, NULL)) {
+		fprintf(stderr, "md: RUN_ARRAY: %s\n", strerror(errno));
+		goto undo;
+	}
+	if (write_fat12(mdfd))
+		goto undo;
+	close(mdfd);
+	if (mount_fat(at("img/md0"), HOLDER_BELOW)) {
+		ret = errno == ENODEV ? CHILD_NOFS : CHILD_HOLDER;
+		mdfd = open(at("img/md0"), O_RDWR);
+		goto undo;
+	}
+	return CHILD_OK;
+undo:
+	if (mdfd >= 0) {
+		ioctl(mdfd, STOP_ARRAY);
+		close(mdfd);
+	}
+	return ret;
+}
+
+/*
+ * A device keeps its file for as long as it is configured, so once nothing
+ * below the dead mount is left the device has to be told to let go. With
+ * the cycle unbroken C's filesystem still holds the device and every one
+ * of these refuses.
+ */
+static int holder_let_go_once(enum holder holder)
+{
+	int fd, ret;
+
+	switch (holder) {
+	case HOLDER_ZRAM:
+		return write_file("/sys/block/zram0/reset", "1");
+	case HOLDER_ZLOOP:
+		return write_file("/dev/zloop-control", "remove id=0");
+	case HOLDER_GADGET:
+		if (mount_configfs())
+			return -1;
+		/* a zero-length write is a no-op for configfs; a newline ejects */
+		return write_file(gat("/functions/mass_storage.0/lun.0/file"), "\n");
+	case HOLDER_MD:
+		fd = open(at("img/md0"), O_RDONLY);
+		if (fd < 0) {
+			/* the child's node went with its tmpfs */
+			mknod(at("md0"), S_IFBLK | 0600, makedev(MD_MAJOR, 0));
+			fd = open(at("md0"), O_RDONLY);
+		}
+		if (fd < 0)
+			return -1;
+		ret = ioctl(fd, STOP_ARRAY);
+		close(fd);
+		return ret;
+	default:
+		return 0;
+	}
+}
+
+static void zram_reset(void)
+{
+	holder_let_go_once(HOLDER_ZRAM);
+}
+
+/*
+ * In its own mount namespace the child puts the image on a tmpfs next to
+ * P, mounts P from a loop device, and sets the holder up with its own
+ * filesystem or device mounted at C below P.
+ */
+static int holder_child(int to_parent, int from_parent, enum holder holder)
+{
+	bool fifo = holder == HOLDER_AUTOFS || holder == HOLDER_ZRAM;
+	/* room for a 4 MiB zone file or a floppy image on P */
+	bool big = holder == HOLDER_ZLOOP || holder == HOLDER_GADGET;
+	struct report r = { { -1, -1 } };
+	char dev[32], c;
+	int ifd, n, ret;
+
+	if (unshare(CLONE_NEWNS) || mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL))
+		return CHILD_NS;
+	if (mkdir(at("img"), 0755) || mount("tmpfs", at("img"), "tmpfs", 0, NULL))
+		return child_fails(CHILD_NS);
+
+	ifd = open(HOLDER_IMG, O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (ifd < 0 || (fifo ? write_minix(ifd) :
+			big ? write_fat12_4k(ifd, 3072) : write_fat12(ifd)))
+		return child_fails(CHILD_IMAGE);
+	close(ifd);
+	n = loop_attach(HOLDER_IMG);
+	if (n < 0)
+		return child_fails(CHILD_LOOP);
+	snprintf(dev, sizeof(dev), "/dev/loop%d", n);
+	if (mkdir(HOLDER_MNT, 0755))
+		return child_fails(CHILD_MOUNT);
+	if (fifo ? mount(dev, HOLDER_MNT, "minix", 0, NULL) : mount_fat(dev, HOLDER_MNT))
+		return child_fails(errno == ENODEV ? CHILD_NOFS : CHILD_MOUNT);
+	if (mkdir(HOLDER_BELOW, 0755))
+		return child_fails(CHILD_MOUNT);
+
+	switch (holder) {
+	case HOLDER_AUTOFS:
+		ret = holder_autofs();
+		break;
+	case HOLDER_ZRAM:
+		ret = holder_zram();
+		break;
+	case HOLDER_ECRYPTFS:
+		ret = holder_ecryptfs();
+		break;
+	case HOLDER_BINFMT_MISC:
+		ret = holder_binfmt_misc();
+		break;
+	case HOLDER_FUSE:
+		ret = holder_fuse();
+		break;
+	case HOLDER_ZLOOP:
+		ret = holder_zloop();
+		break;
+	case HOLDER_GADGET:
+		ret = holder_gadget();
+		break;
+	case HOLDER_MD:
+		ret = holder_md();
+		break;
+	default:
+		ret = CHILD_HOLDER;
+	}
+	if (ret != CHILD_OK)
+		return child_fails(ret);
+
+	/* P's device first, then the one the holder has bound for itself */
+	r.n[0] = n;
+	if (nr_bound > 1)
+		r.n[1] = bound[1];
+	if (write(to_parent, &r, sizeof(r)) != sizeof(r) ||
+	    read(from_parent, &c, 1) != 1) {
+		/* the parent went away and will not tell the devices to let go */
+		umount2(HOLDER_BELOW, MNT_DETACH);
+		for (int i = 0; i < 50 && holder_let_go_once(holder); i++)
+			usleep(100000);
+		if (holder == HOLDER_GADGET)
+			gadget_remove();
+		return child_fails(CHILD_PIPE);
+	}
+	return CHILD_OK;
+}
+
+/*
+ * The release of C's filesystem may still be in flight when the child is
+ * gone, and a device that is still held refuses to let go, so try for a
+ * while. With the cycle unbroken it refuses for good.
+ */
+static void holder_let_go(enum holder holder)
+{
+	for (int i = 0; i < 50; i++) {
+		if (!holder_let_go_once(holder))
+			return;
+		usleep(100000);
+	}
+}
+
+/*
+ * rmdir of p from here, where it is a plain directory, detaches
+ * P in the child's namespace with C connected below it. Once the child is
+ * gone the holder's file on P is the only thing left that refers to P,
+ * and it is dropped only when C's filesystem dies, which waits for P.
+ * The loop device backing P tells whether that resolved.
+ */
+static void holder_cycle(struct __test_metadata *_metadata,
+			 FIXTURE_DATA(loop_cycle) *self, enum holder holder)
+{
+	struct report r = { { -1, -1 } };
+	int to_parent[2], from_parent[2];
+	pid_t pid;
+
+	ASSERT_EQ(pipe(to_parent), 0);
+	ASSERT_EQ(pipe(from_parent), 0);
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		close(to_parent[0]);
+		close(from_parent[1]);
+		_exit(holder_child(to_parent[1], from_parent[0], holder));
+	}
+	close(to_parent[1]);
+	close(from_parent[0]);
+
+	if (read(to_parent[0], &r, sizeof(r)) != sizeof(r))
+		CHILD_GAVE_UP(pid);
+	self->gadget = holder == HOLDER_GADGET;
+	remember_loop(self, r.n[0]);
+	remember_loop(self, r.n[1]);
+	snprintf(self->dev, sizeof(self->dev), "/dev/loop%d", r.n[0]);
+	snprintf(self->sysfs, sizeof(self->sysfs), "/sys/block/loop%d/loop/backing_file", r.n[0]);
+
+	ASSERT_EQ(rmdir(HOLDER_MNT), 0);
+	ASSERT_EQ(write(from_parent[1], "x", 1), 1);
+	CHILD_LEFT(pid);
+	close(to_parent[0]);
+	close(from_parent[1]);
+
+	holder_let_go(holder);
+	assert_loop_released(_metadata, self);
+	/* the teardown takes the gadget and the holder's own loop device away */
+}
+
+TEST_F(loop_cycle, autofs_pipe_on_dead_mount_released)
+{
+	holder_cycle(_metadata, self, HOLDER_AUTOFS);
+}
+
+TEST_F(loop_cycle, zram_writeback_node_on_dead_mount_released)
+{
+	holder_cycle(_metadata, self, HOLDER_ZRAM);
+}
+
+TEST_F(loop_cycle, ecryptfs_lower_on_dead_mount_released)
+{
+	holder_cycle(_metadata, self, HOLDER_ECRYPTFS);
+}
+
+TEST_F(loop_cycle, binfmt_misc_interpreter_on_dead_mount_released)
+{
+	holder_cycle(_metadata, self, HOLDER_BINFMT_MISC);
+}
+
+TEST_F(loop_cycle, fuse_backing_file_on_dead_mount_released)
+{
+	holder_cycle(_metadata, self, HOLDER_FUSE);
+}
+
+TEST_F(loop_cycle, zloop_zone_files_on_dead_mount_released)
+{
+	holder_cycle(_metadata, self, HOLDER_ZLOOP);
+}
+
+/* up to 15 s for the disk to show up and 12 s for a device that is held */
+TEST_F_TIMEOUT(loop_cycle, mass_storage_lun_on_dead_mount_released, 120)
+{
+	holder_cycle(_metadata, self, HOLDER_GADGET);
+}
+
+TEST_F(loop_cycle, md_bitmap_file_on_dead_mount_released)
+{
+	holder_cycle(_metadata, self, HOLDER_MD);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount_cycle/mount_cover_test.c b/tools/testing/selftests/filesystems/mount_cycle/mount_cover_test.c
new file mode 100644
index 000000000000..0a0b0c037691
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/mount_cover_test.c
@@ -0,0 +1,579 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * An unmounted mount that would have stayed attached to its unmounted parent
+ * leaves a cover behind instead. A lookup on the parent at the mountpoint
+ * finds knullfs: an empty read-only directory that is shared by every cover
+ * and every kernel thread, so it can't be watched or locked and nothing can
+ * be mounted on it. The mount itself is a root from then on. Where a file
+ * was mounted, the stand-in is an empty regular file of the same instance.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/fanotify.h>
+#include <sys/file.h>
+#include <sys/inotify.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/statvfs.h>
+#include <sys/syscall.h>
+#include <sys/vfs.h>
+#include <sys/wait.h>
+
+#include "../../kselftest_harness.h"
+#include "../readdir_hold.h"
+
+#ifndef NULL_FS_MAGIC
+#define NULL_FS_MAGIC 0x4E554C4C
+#endif
+
+#ifndef TMPFS_MAGIC
+#define TMPFS_MAGIC 0x01021994
+#endif
+
+#ifndef F_SETDELEG
+#define F_SETDELEG	(F_SETLEASE + 16)
+#endif
+
+/* struct delegation of <linux/fcntl.h>, which doesn't mix with <fcntl.h> */
+struct delegation_req {
+	uint32_t d_flags;
+	uint16_t d_type;
+	uint16_t __pad;
+};
+
+#define DIR_LEN 64
+#define PATH_LEN 128
+
+/* what the parent asks the child to do */
+#define CMD_RMDIR	'r'
+#define CMD_CLOSE_T	't'
+#define CMD_QUIT	'q'
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+static int touch(const char *path)
+{
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CREAT | O_EXCL | O_CLOEXEC, 0644);
+	if (fd < 0)
+		return -1;
+	close(fd);
+	return 0;
+}
+
+/* Become root in a new user namespace with a private mount namespace. */
+static int enter_userns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[32];
+
+	prctl(PR_SET_DUMPABLE, 1);
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	if (setgid(0) || setuid(0))
+		return -1;
+	return mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL);
+}
+
+/*
+ * The child mounts P on @base/p, C on P/covered and the file P/src on P/file
+ * in a mount namespace of its own, binds P a second time at @base/q and hands
+ * out descriptors on P and on C. rmdir() of @base/p from here unmounts P
+ * together with C and the file bind. P and C are held by the descriptors and
+ * the unmounted children leave their covers behind. On request the child
+ * removes C's mountpoint through the bind.
+ *
+ * It also mounts T on @base/t with a child on T/covered, binds T at @base/u
+ * with a second child on the same dentry and hands out descriptors on T and
+ * U. rmdir() of both from here leaves two covers on one mountpoint. On request
+ * the child lets go of T.
+ */
+static int cover_child(const char *base, int to_parent, int from_parent)
+{
+	char p[PATH_LEN], c[PATH_LEN], q[PATH_LEN], qc[PATH_LEN];
+	char f[PATH_LEN], src[PATH_LEN], t[PATH_LEN], u[PATH_LEN], tc[PATH_LEN];
+	int fds[4], ret;
+	char cmd;
+
+	if (unshare(CLONE_NEWNS) || mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL))
+		return 1;
+	snprintf(p, sizeof(p), "%s/p", base);
+	if (mkdir(p, 0755) || mount("tmpfs", p, "tmpfs", 0, NULL))
+		return 2;
+	snprintf(c, sizeof(c), "%s/p/covered", base);
+	if (mkdir(c, 0755) || mount("tmpfs", c, "tmpfs", 0, NULL))
+		return 3;
+	snprintf(f, sizeof(f), "%s/p/file", base);
+	snprintf(src, sizeof(src), "%s/p/src", base);
+	if (touch(src) || touch(f) || mount(src, f, NULL, MS_BIND, NULL))
+		return 4;
+	snprintf(q, sizeof(q), "%s/q", base);
+	if (mkdir(q, 0755) || mount(p, q, NULL, MS_BIND, NULL))
+		return 5;
+	snprintf(t, sizeof(t), "%s/t", base);
+	if (mkdir(t, 0755) || mount("tmpfs", t, "tmpfs", 0, NULL))
+		return 6;
+	snprintf(tc, sizeof(tc), "%s/t/covered", base);
+	if (mkdir(tc, 0755) || mount("tmpfs", tc, "tmpfs", 0, NULL))
+		return 7;
+	snprintf(u, sizeof(u), "%s/u", base);
+	if (mkdir(u, 0755) || mount(t, u, NULL, MS_BIND, NULL))
+		return 8;
+	snprintf(tc, sizeof(tc), "%s/u/covered", base);
+	if (mount("tmpfs", tc, "tmpfs", 0, NULL))
+		return 9;
+	fds[0] = open(p, O_PATH | O_DIRECTORY | O_CLOEXEC);
+	fds[1] = open(c, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	fds[2] = open(t, O_PATH | O_DIRECTORY | O_CLOEXEC);
+	fds[3] = open(u, O_PATH | O_DIRECTORY | O_CLOEXEC);
+	if (fds[0] < 0 || fds[1] < 0 || fds[2] < 0 || fds[3] < 0)
+		return 10;
+	if (write(to_parent, fds, sizeof(fds)) != sizeof(fds))
+		return 11;
+
+	snprintf(qc, sizeof(qc), "%s/q/covered", base);
+	for (;;) {
+		if (read(from_parent, &cmd, 1) != 1)
+			return 12;
+		switch (cmd) {
+		case CMD_RMDIR:
+			ret = rmdir(qc) ? errno : 0;
+			if (write(to_parent, &ret, sizeof(ret)) != sizeof(ret))
+				return 13;
+			break;
+		case CMD_CLOSE_T:
+			ret = close(fds[2]) ? errno : 0;
+			if (write(to_parent, &ret, sizeof(ret)) != sizeof(ret))
+				return 13;
+			break;
+		case CMD_QUIT:
+			return 0;
+		default:
+			return 14;
+		}
+	}
+}
+
+FIXTURE(mount_cover) {
+	char base[DIR_LEN];
+	pid_t child;
+	int to_child;
+	int from_child;
+	int dfd;	/* P, unmounted, held */
+	int cfd;	/* C, unmounted, held */
+	int fd;		/* what a lookup on P finds at C's mountpoint */
+	int tfd;	/* T, unmounted, held */
+	int ufd;	/* U, a bind of T, unmounted, held */
+	int fan;	/* fanotify group from before the user namespace, or -1 */
+	struct readdir_hold hold;	/* likewise from before, uffd -1 without */
+};
+
+/*
+ * Everything the setup has made. The harness does not run the teardown
+ * when an assertion of the setup fails, so the setup calls this itself.
+ */
+static void cover_cleanup(FIXTURE_DATA(mount_cover) *self)
+{
+	char cmd = CMD_QUIT;
+	int status;
+
+	if (self->fd >= 0)
+		close(self->fd);
+	if (self->cfd >= 0)
+		close(self->cfd);
+	if (self->dfd >= 0)
+		close(self->dfd);
+	if (self->tfd >= 0)
+		close(self->tfd);
+	if (self->ufd >= 0)
+		close(self->ufd);
+	if (self->fan >= 0)
+		close(self->fan);
+	readdir_hold_destroy(&self->hold);
+	if (self->child > 0) {
+		if (write(self->to_child, &cmd, 1) != 1)
+			kill(self->child, SIGKILL);
+		waitpid(self->child, &status, 0);
+	}
+	if (self->to_child >= 0)
+		close(self->to_child);
+	if (self->from_child >= 0)
+		close(self->from_child);
+	umount2(self->base, MNT_DETACH);
+	rmdir(self->base);
+}
+
+static int same_file(int fd1, int fd2)
+{
+	struct stat st1, st2;
+
+	if (fstat(fd1, &st1) || fstat(fd2, &st2))
+		return 0;
+	return st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino;
+}
+
+FIXTURE_SETUP(mount_cover)
+{
+	int to_parent[2], to_child[2], fds[4], pidfd, status;
+	char dir[PATH_LEN];
+	struct statfs sf;
+
+	self->child = 0;
+	self->to_child = self->from_child = -1;
+	self->dfd = self->cfd = self->fd = self->tfd = self->ufd = -1;
+
+	/*
+	 * A group for plain events takes CAP_SYS_ADMIN in the initial user
+	 * namespace, so get one before that is gone. An inode mark can be
+	 * added to it from anywhere.
+	 */
+	self->fan = fanotify_init(FAN_CLASS_NOTIF | FAN_CLOEXEC, O_RDONLY);
+	/* same for the userfaultfd that holds a readdir in its fault */
+	readdir_hold_init(&self->hold);
+
+	snprintf(self->base, sizeof(self->base), "/tmp/mount_cover.XXXXXX");
+	ASSERT_NE(mkdtemp(self->base), NULL);
+	if (enter_userns()) {
+		cover_cleanup(self);
+		SKIP(return, "test requires user namespaces");
+	}
+	ASSERT_EQ(mount("tmpfs", self->base, "tmpfs", 0, NULL), 0)
+		cover_cleanup(self);
+
+	snprintf(dir, sizeof(dir), "%s/p", self->base);
+	ASSERT_EQ(pipe(to_parent), 0)
+		cover_cleanup(self);
+	ASSERT_EQ(pipe(to_child), 0)
+		cover_cleanup(self);
+	self->child = fork();
+	ASSERT_GE(self->child, 0)
+		cover_cleanup(self);
+	if (self->child == 0) {
+		close(to_parent[0]);
+		close(to_child[1]);
+		_exit(cover_child(self->base, to_parent[1], to_child[0]));
+	}
+	close(to_parent[1]);
+	close(to_child[0]);
+	self->to_child = to_child[1];
+	self->from_child = to_parent[0];
+	if (read(self->from_child, fds, sizeof(fds)) != sizeof(fds)) {
+		pid_t pid = self->child;
+
+		waitpid(pid, &status, 0);
+		self->child = 0;
+		cover_cleanup(self);
+		ASSERT_TRUE(false)
+			TH_LOG("child failed to set up: %s %d",
+			       WIFEXITED(status) ? "step" : "signal",
+			       WIFEXITED(status) ? WEXITSTATUS(status) : WTERMSIG(status));
+	}
+
+	pidfd = syscall(__NR_pidfd_open, self->child, 0);
+	ASSERT_GE(pidfd, 0)
+		cover_cleanup(self);
+	self->dfd = syscall(__NR_pidfd_getfd, pidfd, fds[0], 0);
+	self->cfd = syscall(__NR_pidfd_getfd, pidfd, fds[1], 0);
+	self->tfd = syscall(__NR_pidfd_getfd, pidfd, fds[2], 0);
+	self->ufd = syscall(__NR_pidfd_getfd, pidfd, fds[3], 0);
+	close(pidfd);
+	ASSERT_GE(self->dfd, 0)
+		cover_cleanup(self);
+	ASSERT_GE(self->cfd, 0)
+		cover_cleanup(self);
+	ASSERT_GE(self->tfd, 0)
+		cover_cleanup(self);
+	ASSERT_GE(self->ufd, 0)
+		cover_cleanup(self);
+
+	/* unmounts P and C, C leaves its cover behind */
+	ASSERT_EQ(rmdir(dir), 0)
+		cover_cleanup(self);
+	/* unmounts T and U with their children, two covers on one mountpoint */
+	snprintf(dir, sizeof(dir), "%s/t", self->base);
+	ASSERT_EQ(rmdir(dir), 0)
+		cover_cleanup(self);
+	snprintf(dir, sizeof(dir), "%s/u", self->base);
+	ASSERT_EQ(rmdir(dir), 0)
+		cover_cleanup(self);
+
+	self->fd = openat(self->dfd, "covered", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(self->fd, 0)
+		cover_cleanup(self);
+	ASSERT_EQ(fstatfs(self->fd, &sf), 0)
+		cover_cleanup(self);
+	ASSERT_EQ(sf.f_type, NULL_FS_MAGIC)
+		cover_cleanup(self);
+}
+
+FIXTURE_TEARDOWN(mount_cover)
+{
+	cover_cleanup(self);
+}
+
+TEST_F(mount_cover, not_watchable)
+{
+	char p[PATH_LEN];
+	int ifd;
+
+	snprintf(p, sizeof(p), "/proc/self/fd/%d", self->fd);
+
+	ifd = inotify_init1(IN_CLOEXEC);
+	if (ifd < 0 && errno == ENOSYS) {
+		TH_LOG("no inotify in this kernel, skipping that part");
+	} else {
+		ASSERT_GE(ifd, 0);
+		EXPECT_EQ(inotify_add_watch(ifd, p, IN_OPEN), -1);
+		EXPECT_EQ(errno, EINVAL);
+		close(ifd);
+	}
+
+	/* dnotify ends up at the same place */
+	EXPECT_EQ(fcntl(self->fd, F_NOTIFY, DN_ACCESS), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	if (self->fan < 0) {
+		TH_LOG("no fanotify group without CAP_SYS_ADMIN in the initial user namespace, skipping the fanotify part");
+		return;
+	}
+	EXPECT_EQ(fanotify_mark(self->fan, FAN_MARK_ADD, FAN_OPEN, self->fd, NULL), -1);
+	EXPECT_EQ(errno, EINVAL);
+}
+
+TEST_F(mount_cover, not_lockable)
+{
+	struct flock fl = {
+		.l_type = F_RDLCK,
+		.l_whence = SEEK_SET,
+	};
+
+	EXPECT_EQ(flock(self->fd, LOCK_EX | LOCK_NB), -1);
+	EXPECT_EQ(errno, ENOLCK);
+	EXPECT_EQ(fcntl(self->fd, F_SETLK, &fl), -1);
+	EXPECT_EQ(errno, ENOLCK);
+	EXPECT_EQ(fcntl(self->fd, F_GETLK, &fl), -1);
+	EXPECT_EQ(errno, ENOLCK);
+}
+
+/* a lease is refused for the owner and for everybody else alike */
+TEST_F(mount_cover, not_leasable)
+{
+	struct delegation_req deleg = {
+		.d_type = F_RDLCK,
+	};
+
+	EXPECT_EQ(fcntl(self->fd, F_SETLEASE, F_RDLCK), -1);
+	EXPECT_TRUE(errno == EINVAL || errno == EACCES);
+	EXPECT_EQ(fcntl(self->fd, F_SETDELEG, &deleg), -1);
+	EXPECT_TRUE(errno == EINVAL || errno == EACCES);
+}
+
+TEST_F(mount_cover, not_mountable)
+{
+	char p[PATH_LEN];
+
+	snprintf(p, sizeof(p), "/proc/self/fd/%d", self->fd);
+	EXPECT_EQ(mount("tmpfs", p, "tmpfs", 0, NULL), -1);
+	EXPECT_EQ(errno, ENOENT);
+}
+
+TEST_F(mount_cover, read_only)
+{
+	struct statvfs sv;
+
+	EXPECT_EQ(mkdirat(self->fd, "x", 0755), -1);
+	EXPECT_EQ(errno, ENOENT);
+	EXPECT_EQ(fchmod(self->fd, 0777), -1);
+	EXPECT_EQ(errno, EROFS);
+	/* the immutable inode is checked before the read-only mount */
+	EXPECT_EQ(faccessat(self->fd, ".", W_OK, 0), -1);
+	EXPECT_EQ(errno, EPERM);
+	ASSERT_EQ(fstatvfs(self->fd, &sv), 0);
+	EXPECT_TRUE(sv.f_flag & ST_RDONLY);
+}
+
+/* the stand-in is a root of its own, ".." stays put */
+TEST_F(mount_cover, island)
+{
+	int fd;
+
+	fd = openat(self->fd, "..", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	EXPECT_TRUE(same_file(fd, self->fd));
+	close(fd);
+}
+
+/*
+ * C is alive for as long as the child holds it, but it can't be reached
+ * through P anymore and it's a root of its own as well.
+ */
+TEST_F(mount_cover, held_child_detached)
+{
+	struct statfs sf;
+	int fd;
+
+	ASSERT_EQ(fstatfs(self->cfd, &sf), 0);
+	EXPECT_EQ(sf.f_type, TMPFS_MAGIC);
+
+	fd = openat(self->cfd, "..", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	EXPECT_TRUE(same_file(fd, self->cfd));
+	close(fd);
+
+	fd = openat(self->dfd, "covered", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(fstatfs(fd, &sf), 0);
+	EXPECT_EQ(sf.f_type, NULL_FS_MAGIC);
+	close(fd);
+}
+
+/*
+ * The cover goes with its mountpoint: once the child has removed C's
+ * mountpoint through the bind of P, the name is gone from P as well.
+ * What was opened through the cover before stays open.
+ */
+TEST_F(mount_cover, cover_goes_with_mountpoint)
+{
+	char cmd = CMD_RMDIR;
+	struct statfs sf;
+	int ret;
+
+	ASSERT_EQ(write(self->to_child, &cmd, 1), 1);
+	ASSERT_EQ(read(self->from_child, &ret, sizeof(ret)), sizeof(ret));
+	ASSERT_EQ(ret, 0);
+
+	EXPECT_EQ(openat(self->dfd, "covered", O_RDONLY | O_DIRECTORY | O_CLOEXEC), -1);
+	EXPECT_EQ(errno, ENOENT);
+	ASSERT_EQ(fstatfs(self->fd, &sf), 0);
+	EXPECT_EQ(sf.f_type, NULL_FS_MAGIC);
+}
+
+/*
+ * A readdir of the stand-in holds nothing that others wait for: one holder
+ * sticks in the page fault of its buffer, and a create and a lookup of
+ * another come back meanwhile.
+ */
+TEST_F(mount_cover, readdir_blocks_nobody)
+{
+	bool stalled;
+
+	if (self->hold.uffd < 0)
+		SKIP(return, "test requires userfaultfd");
+	ASSERT_EQ(readdir_hold_check(&self->hold, self->fd, &stalled), 0);
+	EXPECT_FALSE(stalled);
+}
+
+/* where a file was mounted, the stand-in is an empty regular file */
+TEST_F(mount_cover, file_stand_in)
+{
+	char src[PATH_LEN], p[PATH_LEN];
+	struct statfs sf;
+	struct stat st;
+	char c;
+	int fd;
+
+	fd = openat(self->dfd, "file", O_RDONLY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(fstat(fd, &st), 0);
+	EXPECT_TRUE(S_ISREG(st.st_mode));
+	ASSERT_EQ(fstatfs(fd, &sf), 0);
+	EXPECT_EQ(sf.f_type, NULL_FS_MAGIC);
+	/* the two stand-ins are two inodes */
+	EXPECT_FALSE(same_file(fd, self->fd));
+	EXPECT_EQ(read(fd, &c, 1), 0);
+	EXPECT_EQ(flock(fd, LOCK_EX | LOCK_NB), -1);
+	EXPECT_EQ(errno, ENOLCK);
+
+	snprintf(src, sizeof(src), "%s/src", self->base);
+	ASSERT_EQ(touch(src), 0);
+	snprintf(p, sizeof(p), "/proc/self/fd/%d", fd);
+	EXPECT_EQ(mount(src, p, NULL, MS_BIND, NULL), -1);
+	EXPECT_EQ(errno, ENOENT);
+	close(fd);
+
+	/* writes and truncates go nowhere, like /dev/null */
+	fd = openat(self->dfd, "file", O_WRONLY | O_TRUNC | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	EXPECT_EQ(write(fd, "xy", 2), 2);
+	EXPECT_EQ(ftruncate(fd, 4), 0);
+	ASSERT_EQ(fstat(fd, &st), 0);
+	EXPECT_EQ(st.st_size, 0);
+	/* the shared inode keeps its identity */
+	EXPECT_EQ(fchmod(fd, 0600), -1);
+	EXPECT_EQ(errno, EPERM);
+	close(fd);
+	fd = openat(self->dfd, "file", O_RDONLY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	EXPECT_EQ(read(fd, &c, 1), 0);
+	close(fd);
+
+	EXPECT_EQ(openat(self->dfd, "file", O_RDONLY | O_DIRECTORY | O_CLOEXEC), -1);
+	EXPECT_EQ(errno, ENOTDIR);
+}
+
+/*
+ * Two unmounted parents left covers on the same dentry. A lookup on
+ * either finds a stand-in, and U's cover stays when T goes.
+ */
+TEST_F(mount_cover, shared_mountpoint)
+{
+	char cmd = CMD_CLOSE_T;
+	struct statfs sf;
+	int fd, ret;
+
+	fd = openat(self->tfd, "covered", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(fstatfs(fd, &sf), 0);
+	EXPECT_EQ(sf.f_type, NULL_FS_MAGIC);
+	close(fd);
+
+	fd = openat(self->ufd, "covered", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(fstatfs(fd, &sf), 0);
+	EXPECT_EQ(sf.f_type, NULL_FS_MAGIC);
+	close(fd);
+
+	/* the last references to T go, with T its cover */
+	ASSERT_EQ(write(self->to_child, &cmd, 1), 1);
+	ASSERT_EQ(read(self->from_child, &ret, sizeof(ret)), sizeof(ret));
+	ASSERT_EQ(ret, 0);
+	close(self->tfd);
+	self->tfd = -1;
+
+	fd = openat(self->ufd, "covered", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(fstatfs(fd, &sf), 0);
+	EXPECT_EQ(sf.f_type, NULL_FS_MAGIC);
+	close(fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount_cycle/nsfs_rbind_loop_test.c b/tools/testing/selftests/filesystems/mount_cycle/nsfs_rbind_loop_test.c
new file mode 100644
index 000000000000..0928a584eddc
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/nsfs_rbind_loop_test.c
@@ -0,0 +1,193 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A recursive bind mount of a namespace file that lives in another mount
+ * namespace copies whatever is stacked on top of it there. If that includes
+ * the file of the caller's own mount namespace, or of an older one, the copy
+ * would pin the namespace it is put in forever. The bind mount has to be
+ * refused, a plain bind mount of the file itself still works.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+#include "../../kselftest_harness.h"
+
+#define DIR_LEN 64
+#define PATH_LEN 128
+
+/* Child exit codes. */
+enum {
+	CHILD_OK,
+	CHILD_UNSHARE,		/* could not create the newer mount namespace */
+	CHILD_PIPE,		/* the parent went away */
+	CHILD_TMPFS,		/* could not mount the tmpfs in the new namespace */
+	CHILD_REC_ALLOWED,	/* the recursive bind mount was not refused */
+	CHILD_REC_ERRNO,	/* it was refused with the wrong error */
+	CHILD_PLAIN_REFUSED,	/* the plain bind mount of the file was refused */
+};
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+static int create_file(const char *path)
+{
+	int fd = open(path, O_WRONLY | O_CREAT | O_CLOEXEC, 0644);
+
+	if (fd < 0)
+		return -1;
+	close(fd);
+	return 0;
+}
+
+/* Become root in a new user namespace with a private mount namespace. */
+static int enter_userns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[32];
+
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	if (setgid(0) || setuid(0))
+		return -1;
+	return mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL);
+}
+
+static int send_msg(int fd, char msg)
+{
+	return write(fd, &msg, 1) == 1 ? 0 : -1;
+}
+
+static char recv_msg(int fd)
+{
+	char msg;
+
+	if (read(fd, &msg, 1) != 1)
+		return 0;
+	return msg;
+}
+
+FIXTURE(nsfs_rbind_loop) {
+	char dir[DIR_LEN];
+	char x[PATH_LEN];
+};
+
+FIXTURE_SETUP(nsfs_rbind_loop)
+{
+	snprintf(self->dir, sizeof(self->dir), "/tmp/nsfs_rbind_loop.XXXXXX");
+	ASSERT_NE(mkdtemp(self->dir), NULL);
+	if (enter_userns()) {
+		rmdir(self->dir);
+		SKIP(return, "test requires user namespaces");
+	}
+	ASSERT_EQ(mount("tmpfs", self->dir, "tmpfs", 0, NULL), 0);
+	snprintf(self->x, sizeof(self->x), "%s/x", self->dir);
+	ASSERT_EQ(create_file(self->x), 0);
+}
+
+FIXTURE_TEARDOWN(nsfs_rbind_loop)
+{
+	umount2(self->dir, MNT_DETACH);
+	rmdir(self->dir);
+}
+
+/*
+ * The child in the newer mount namespace binds the network namespace file
+ * mount of the parent through @fd. Recursively that would copy the mount of
+ * its own mount namespace file that the parent stacked on top.
+ */
+static int newer_ns_child(const char *dir, int fd, int to_parent, int from_parent)
+{
+	char src[32], y[PATH_LEN];
+
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	if (send_msg(to_parent, 'r') || recv_msg(from_parent) != 'g')
+		return CHILD_PIPE;
+
+	snprintf(y, sizeof(y), "%s/y", dir);
+	if (mount("tmpfs", y, "tmpfs", 0, NULL))
+		return CHILD_TMPFS;
+	snprintf(src, sizeof(src), "/proc/self/fd/%d", fd);
+	snprintf(y, sizeof(y), "%s/y/f", dir);
+	if (create_file(y))
+		return CHILD_TMPFS;
+
+	if (!mount(src, y, NULL, MS_BIND | MS_REC, NULL))
+		return CHILD_REC_ALLOWED;
+	if (errno != EINVAL)
+		return CHILD_REC_ERRNO;
+	if (mount(src, y, NULL, MS_BIND, NULL))
+		return CHILD_PLAIN_REFUSED;
+	umount2(y, MNT_DETACH);
+	return CHILD_OK;
+}
+
+TEST_F(nsfs_rbind_loop, own_ns_file_below_foreign_source)
+{
+	int to_child[2], to_parent[2], fd, status;
+	char p[PATH_LEN];
+	pid_t pid;
+
+	snprintf(p, sizeof(p), "%s/y", self->dir);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+
+	/* M, a mount of our network namespace file, held by a descriptor */
+	ASSERT_EQ(mount("/proc/self/ns/net", self->x, NULL, MS_BIND, NULL), 0);
+	fd = open(self->x, O_PATH | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+
+	ASSERT_EQ(pipe(to_child), 0);
+	ASSERT_EQ(pipe(to_parent), 0);
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		close(to_child[1]);
+		close(to_parent[0]);
+		_exit(newer_ns_child(self->dir, fd, to_parent[1], to_child[0]));
+	}
+	close(to_child[0]);
+	close(to_parent[1]);
+	ASSERT_EQ(recv_msg(to_parent[0]), 'r');
+
+	/* the child's mount namespace file on top of M */
+	snprintf(p, sizeof(p), "/proc/%d/ns/mnt", pid);
+	ASSERT_EQ(mount(p, self->x, NULL, MS_BIND, NULL), 0);
+
+	ASSERT_EQ(send_msg(to_child[1], 'g'), 0);
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), CHILD_OK);
+
+	close(fd);
+	ASSERT_EQ(umount2(self->x, MNT_DETACH), 0);
+	ASSERT_EQ(umount2(self->x, MNT_DETACH), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount_cycle/overmount_ns_file_test.c b/tools/testing/selftests/filesystems/mount_cycle/overmount_ns_file_test.c
new file mode 100644
index 000000000000..ea1b33fa0bf8
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/overmount_ns_file_test.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A mount namespace file bind-mounted on top of the mount that is moved
+ * onto a shared mount isn't copied to the peers and slaves. The mount that
+ * already sits at the destination in a slave has to end up on top of the
+ * propagated copy, not below the root of the mount namespace file where no
+ * path walk ever finds it.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+
+#include "../wrappers.h"
+#include "../../kselftest_harness.h"
+
+#define DIR_LEN 64
+#define PATH_LEN 128
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+static int create_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+/* the first bytes of the file at @path, "" if it can't be read */
+static const char *read_file(const char *path, char *buf, size_t len)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = read(fd, buf, len - 1);
+		close(fd);
+	}
+	buf[n > 0 ? n : 0] = '\0';
+	return buf;
+}
+
+/* Become root in a new user namespace with a private mount namespace. */
+static int enter_userns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[32];
+
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	if (setgid(0) || setuid(0))
+		return -1;
+	return mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL);
+}
+
+FIXTURE(overmount_ns_file) {
+	char dir[DIR_LEN];
+	pid_t child;
+};
+
+FIXTURE_SETUP(overmount_ns_file)
+{
+	self->child = -1;
+	snprintf(self->dir, sizeof(self->dir), "/tmp/overmount_ns_file.XXXXXX");
+	ASSERT_NE(mkdtemp(self->dir), NULL);
+	if (enter_userns()) {
+		rmdir(self->dir);
+		SKIP(return, "test requires user namespaces");
+	}
+	ASSERT_EQ(mount("tmpfs", self->dir, "tmpfs", 0, NULL), 0);
+}
+
+FIXTURE_TEARDOWN(overmount_ns_file)
+{
+	if (self->child > 0) {
+		kill(self->child, SIGKILL);
+		waitpid(self->child, NULL, 0);
+	}
+	umount2(self->dir, MNT_DETACH);
+	rmdir(self->dir);
+}
+
+/*
+ * A is a shared tmpfs and B its slave with Q, a bind mount of a file, on
+ * B/file. S is a bind mount of a file with N, a bind mount of a newer mount
+ * namespace's file, on top of it. S is moved onto A/file. Its copy S' lands
+ * on B/file below Q, without N. B/file keeps reading Q and once Q is
+ * unmounted it reads S'.
+ */
+TEST_F(overmount_ns_file, existing_mount_stays_on_top)
+{
+	char a[PATH_LEN], b[PATH_LEN], s[PATH_LEN], p[PATH_LEN], buf[16];
+	int fd, pfd[2];
+	char c;
+
+	snprintf(a, sizeof(a), "%s/A", self->dir);
+	snprintf(b, sizeof(b), "%s/B", self->dir);
+	snprintf(s, sizeof(s), "%s/s", self->dir);
+	ASSERT_EQ(mkdir(a, 0755), 0);
+	ASSERT_EQ(mkdir(b, 0755), 0);
+	ASSERT_EQ(mkdir(s, 0755), 0);
+
+	/* A shared, B its slave, Q on B/file */
+	ASSERT_EQ(mount("tmpfs", a, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(mount(NULL, a, NULL, MS_SHARED, NULL), 0);
+	snprintf(p, sizeof(p), "%s/A/file", self->dir);
+	ASSERT_EQ(create_file(p, "A"), 0);
+	ASSERT_EQ(mount(a, b, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(NULL, b, NULL, MS_SLAVE, NULL), 0);
+	snprintf(p, sizeof(p), "%s/Q", self->dir);
+	ASSERT_EQ(create_file(p, "Q"), 0);
+	snprintf(b, sizeof(b), "%s/B/file", self->dir);
+	ASSERT_EQ(mount(p, b, NULL, MS_BIND, NULL), 0);
+
+	/* S on s/f, pinned by a file descriptor before N goes on top */
+	ASSERT_EQ(mount("tmpfs", s, "tmpfs", 0, NULL), 0);
+	snprintf(p, sizeof(p), "%s/s/f", self->dir);
+	ASSERT_EQ(create_file(p, "f"), 0);
+	snprintf(s, sizeof(s), "%s/s/S", self->dir);
+	ASSERT_EQ(create_file(s, "S"), 0);
+	ASSERT_EQ(mount(s, p, NULL, MS_BIND, NULL), 0);
+	fd = open(p, O_PATH | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+
+	/* a newer mount namespace whose file can be bound */
+	ASSERT_EQ(pipe(pfd), 0);
+	self->child = fork();
+	ASSERT_GE(self->child, 0);
+	if (self->child == 0) {
+		close(pfd[0]);
+		if (unshare(CLONE_NEWNS) || write(pfd[1], "r", 1) != 1)
+			_exit(1);
+		pause();
+		_exit(0);
+	}
+	close(pfd[1]);
+	ASSERT_EQ(read(pfd[0], &c, 1), 1);
+	close(pfd[0]);
+	snprintf(s, sizeof(s), "/proc/%d/ns/mnt", self->child);
+	ASSERT_EQ(mount(s, p, NULL, MS_BIND, NULL), 0);
+
+	ASSERT_STREQ(read_file(b, buf, sizeof(buf)), "Q");
+
+	snprintf(a, sizeof(a), "%s/A/file", self->dir);
+	ASSERT_EQ(sys_move_mount(fd, "", AT_FDCWD, a, MOVE_MOUNT_F_EMPTY_PATH), 0);
+	close(fd);
+
+	/* Q is still on top of the copy in B and can be unmounted */
+	EXPECT_STREQ(read_file(b, buf, sizeof(buf)), "Q");
+	EXPECT_EQ(umount2(b, 0), 0);
+	EXPECT_STREQ(read_file(b, buf, sizeof(buf)), "S");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount_cycle/overmount_reparent_test.c b/tools/testing/selftests/filesystems/mount_cycle/overmount_reparent_test.c
new file mode 100644
index 000000000000..46a56b722f3e
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/overmount_reparent_test.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * propagate_umount() slides a surviving overmount off a mount that is being
+ * unmounted and unmounts that mount right after. If a file descriptor keeps
+ * the unmounted mount alive its ->overmount is left pointing at the moved
+ * mount, which is freed on its own schedule. move_mount(MOVE_MOUNT_BENEATH)
+ * with such a file descriptor as the target walks ->overmount in
+ * topmost_overmount() before it checks that the target is still mounted and
+ * must not step into the freed mount.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+
+#include "../wrappers.h"
+#include "../../kselftest_harness.h"
+
+#ifndef MOVE_MOUNT_BENEATH
+#define MOVE_MOUNT_BENEATH 0x00000200
+#endif
+
+#ifndef FSCONFIG_CMD_CREATE
+#define FSCONFIG_CMD_CREATE 6
+#endif
+
+#define DIR_LEN 64
+#define PATH_LEN 128
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+/* Become root in a new user namespace with a private mount namespace. */
+static int enter_userns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[32];
+
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	if (setgid(0) || setuid(0))
+		return -1;
+	return mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL);
+}
+
+/* A detached tmpfs mount to serve as the source of a move. */
+static int detached_tmpfs(void)
+{
+	int sfd, mfd;
+
+	sfd = sys_fsopen("tmpfs", 0);
+	if (sfd < 0)
+		return -1;
+	if (sys_fsconfig(sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0)) {
+		close(sfd);
+		return -1;
+	}
+	mfd = sys_fsmount(sfd, 0, 0);
+	close(sfd);
+	return mfd;
+}
+
+FIXTURE(overmount_reparent) {
+	char dir[DIR_LEN];
+};
+
+FIXTURE_SETUP(overmount_reparent)
+{
+	snprintf(self->dir, sizeof(self->dir), "/tmp/overmount_reparent.XXXXXX");
+	ASSERT_NE(mkdtemp(self->dir), NULL);
+	if (enter_userns()) {
+		rmdir(self->dir);
+		SKIP(return, "test requires user namespaces");
+	}
+}
+
+FIXTURE_TEARDOWN(overmount_reparent)
+{
+	char p[PATH_LEN];
+
+	snprintf(p, sizeof(p), "%s/b", self->dir);
+	umount2(p, MNT_DETACH);
+	snprintf(p, sizeof(p), "%s/a", self->dir);
+	umount2(p, MNT_DETACH);
+}
+
+/*
+ * A shared mount base_a is bind-mounted to base_b as its peer. A mount X on
+ * base_a/mp propagates a copy X_b onto base_b/mp. A file descriptor pins X_b,
+ * then X_b is made private and an overmount is stacked on its root.
+ *
+ * A lazy unmount of X propagates to X_b: X_b is committed to the unmount while
+ * its overmount survives, so propagate_umount() reparents the overmount onto
+ * base_b and unmounts X_b, which the file descriptor keeps alive. Unmounting
+ * the reparented overmount frees it. X_b->overmount now dangles unless
+ * mnt_change_mountpoint() reset it.
+ *
+ * move_mount(MOVE_MOUNT_BENEATH) through the file descriptor makes
+ * do_lock_mount() follow X_b->overmount in topmost_overmount() before it
+ * notices that X_b is no longer mounted. With the pointer reset the move fails
+ * cleanly with ENOENT; otherwise it reads the freed overmount.
+ */
+TEST_F(overmount_reparent, dead_overmount_holder_not_followed)
+{
+	char a[PATH_LEN], b[PATH_LEN], amp[PATH_LEN], bmp[PATH_LEN];
+	int fd, mfd, ret;
+
+	snprintf(a, sizeof(a), "%s/a", self->dir);
+	snprintf(b, sizeof(b), "%s/b", self->dir);
+	ASSERT_EQ(mkdir(a, 0755), 0);
+	ASSERT_EQ(mkdir(b, 0755), 0);
+
+	ASSERT_EQ(mount("tmpfs", a, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(mount(NULL, a, NULL, MS_SHARED, NULL), 0);
+	ASSERT_EQ(mount(a, b, NULL, MS_BIND, NULL), 0);
+
+	snprintf(amp, sizeof(amp), "%s/a/mp", self->dir);
+	snprintf(bmp, sizeof(bmp), "%s/b/mp", self->dir);
+	/* base_a and base_b share one superblock, so this dir is in both. */
+	ASSERT_EQ(mkdir(amp, 0755), 0);
+
+	/* X on base_a/mp propagates a copy X_b onto base_b/mp. */
+	ASSERT_EQ(mount("tmpfs", amp, "tmpfs", 0, NULL), 0);
+
+	/* Pin X_b before anything is stacked on top of it. */
+	fd = open(bmp, O_PATH | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+
+	/* Keep the overmount local to X_b. */
+	ASSERT_EQ(mount(NULL, bmp, NULL, MS_PRIVATE, NULL), 0);
+
+	/* The overmount on X_b's root: X_b->overmount points at it. */
+	ASSERT_EQ(mount("tmpfs", bmp, "tmpfs", 0, NULL), 0);
+
+	/* Reparents the overmount onto base_b and unmounts X_b. */
+	ASSERT_EQ(umount2(amp, MNT_DETACH), 0);
+
+	/* Free the reparented overmount. */
+	ASSERT_EQ(umount2(bmp, MNT_DETACH), 0);
+	usleep(100000);
+
+	mfd = detached_tmpfs();
+	ASSERT_GE(mfd, 0);
+
+	ret = sys_move_mount(mfd, "", fd, "",
+			     MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH |
+			     MOVE_MOUNT_BENEATH);
+	EXPECT_EQ(ret, -1);
+	EXPECT_EQ(errno, ENOENT);
+
+	close(mfd);
+	close(fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/mount_cycle/settings b/tools/testing/selftests/filesystems/mount_cycle/settings
new file mode 100644
index 000000000000..694d70710ff0
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/settings
@@ -0,0 +1 @@
+timeout=300
diff --git a/tools/testing/selftests/filesystems/mount_cycle/unmounted_tree_test.c b/tools/testing/selftests/filesystems/mount_cycle/unmounted_tree_test.c
new file mode 100644
index 000000000000..233f8ea92efc
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount_cycle/unmounted_tree_test.c
@@ -0,0 +1,484 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * An unmounted mount tree that a file descriptor keeps alive is put and
+ * vacated behind the root's back, so nothing may walk it under
+ * namespace_sem: it can't be copied recursively and its propagation can't
+ * be changed. The mount at its root alone can still be copied and that copy
+ * is an ordinary mount.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/mount.h>
+
+#include "../wrappers.h"
+#include "../../kselftest_harness.h"
+
+#ifndef __NR_mount_setattr
+#define __NR_mount_setattr 442
+#endif
+
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open 434
+#endif
+
+#define PATH_LEN	64
+
+static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flags,
+				    struct mount_attr *attr, size_t size)
+{
+	return syscall(__NR_mount_setattr, dfd, path, flags, attr, size);
+}
+
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+	return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+static int touch(const char *path)
+{
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CREAT | O_EXCL | O_CLOEXEC, 0644);
+	if (fd < 0)
+		return -1;
+	close(fd);
+	return 0;
+}
+
+/* Become root in a new user namespace with a private mount namespace. */
+static int enter_userns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[32];
+
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	if (setgid(0) || setuid(0))
+		return -1;
+	return mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL);
+}
+
+/* A private mount namespace of our own, all mounts private. */
+static int own_mntns(void)
+{
+	if (unshare(CLONE_NEWNS))
+		return -1;
+	return mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL);
+}
+
+FIXTURE(unmounted_tree) {
+	char dir[PATH_LEN];
+};
+
+FIXTURE_SETUP(unmounted_tree)
+{
+	snprintf(self->dir, sizeof(self->dir), "/tmp/unmounted_tree.XXXXXX");
+	ASSERT_NE(mkdtemp(self->dir), NULL);
+	if (enter_userns()) {
+		rmdir(self->dir);
+		SKIP(return, "test requires user namespaces");
+	}
+	ASSERT_EQ(mount("tmpfs", self->dir, "tmpfs", 0, NULL), 0);
+}
+
+FIXTURE_TEARDOWN(unmounted_tree)
+{
+	umount2(self->dir, MNT_DETACH);
+	rmdir(self->dir);
+}
+
+/* A recursive copy of the mount @fd refers to must fail with EINVAL. */
+static void assert_not_walked(struct __test_metadata *_metadata, int fd,
+			      const char *target)
+{
+	char link[PATH_LEN];
+	int tfd;
+
+	snprintf(link, sizeof(link), "/proc/self/fd/%d", fd);
+	EXPECT_EQ(mount(link, target, NULL, MS_BIND | MS_REC, NULL), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	tfd = sys_open_tree(fd, "", AT_EMPTY_PATH | AT_RECURSIVE | OPEN_TREE_CLONE |
+			    OPEN_TREE_CLOEXEC);
+	EXPECT_LT(tfd, 0);
+	EXPECT_EQ(errno, EINVAL);
+	if (tfd >= 0)
+		close(tfd);
+}
+
+/* The mount @fd refers to can be copied on its own and mounted on @target. */
+static void assert_root_copied(struct __test_metadata *_metadata, int fd,
+			       const char *target)
+{
+	int tfd;
+
+	tfd = sys_open_tree(fd, "", AT_EMPTY_PATH | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(tfd, 0);
+	ASSERT_EQ(sys_move_mount(tfd, "", AT_FDCWD, target, MOVE_MOUNT_F_EMPTY_PATH), 0);
+	close(tfd);
+	ASSERT_EQ(umount2(target, MNT_DETACH), 0);
+}
+
+/*
+ * A lazily unmounted bind mount of an nsfs file, kept alive by an fd, can't
+ * be copied recursively anymore. Copying the mount itself still works and
+ * so does copying a mounted bind mount of the same file.
+ */
+TEST_F(unmounted_tree, detached_nsfs_bind_not_walked)
+{
+	char x[PATH_LEN], y[PATH_LEN], z[PATH_LEN], link[PATH_LEN];
+	int fd, tfd;
+
+	snprintf(x, sizeof(x), "%s/x", self->dir);
+	snprintf(y, sizeof(y), "%s/y", self->dir);
+	snprintf(z, sizeof(z), "%s/z", self->dir);
+	ASSERT_EQ(touch(x), 0);
+	ASSERT_EQ(touch(y), 0);
+	ASSERT_EQ(touch(z), 0);
+
+	ASSERT_EQ(mount("/proc/self/ns/net", x, NULL, MS_BIND, NULL), 0);
+	fd = open(x, O_PATH | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(umount2(x, MNT_DETACH), 0);
+
+	assert_not_walked(_metadata, fd, y);
+
+	snprintf(link, sizeof(link), "/proc/self/fd/%d", fd);
+	ASSERT_EQ(mount(link, y, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(umount2(y, MNT_DETACH), 0);
+	assert_root_copied(_metadata, fd, y);
+	/* opening it is fine too */
+	tfd = sys_open_tree(fd, "", AT_EMPTY_PATH | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(tfd, 0);
+	close(tfd);
+	close(fd);
+
+	ASSERT_EQ(mount("/proc/self/ns/net", y, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(y, z, NULL, MS_BIND | MS_REC, NULL), 0);
+	tfd = sys_open_tree(AT_FDCWD, y, AT_RECURSIVE | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(tfd, 0);
+	close(tfd);
+}
+
+/* Bind-mount the pidfd @pidfd on @target the way pidfd_bind_mount does. */
+static int bind_pidfd(int pidfd, const char *target)
+{
+	int tfd, ret;
+
+	tfd = sys_open_tree(pidfd, "", AT_EMPTY_PATH | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	if (tfd < 0)
+		return -1;
+	ret = sys_move_mount(tfd, "", AT_FDCWD, target, MOVE_MOUNT_F_EMPTY_PATH);
+	close(tfd);
+	return ret;
+}
+
+/* The same for a bind mount of a pidfd. */
+TEST_F(unmounted_tree, detached_pidfs_bind_not_walked)
+{
+	char x[PATH_LEN], y[PATH_LEN];
+	int pidfd, fd, tfd;
+
+	snprintf(x, sizeof(x), "%s/x", self->dir);
+	snprintf(y, sizeof(y), "%s/y", self->dir);
+	ASSERT_EQ(touch(x), 0);
+	ASSERT_EQ(touch(y), 0);
+
+	pidfd = sys_pidfd_open(getpid(), 0);
+	ASSERT_GE(pidfd, 0);
+	ASSERT_EQ(bind_pidfd(pidfd, x), 0);
+	fd = open(x, O_PATH | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(umount2(x, MNT_DETACH), 0);
+
+	assert_not_walked(_metadata, fd, y);
+	assert_root_copied(_metadata, fd, y);
+	close(fd);
+
+	ASSERT_EQ(bind_pidfd(pidfd, y), 0);
+	tfd = sys_open_tree(AT_FDCWD, y, AT_RECURSIVE | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(tfd, 0);
+	close(tfd);
+	close(pidfd);
+}
+
+/* What a child in its own mount namespace reports back. */
+enum {
+	CHILD_OK,
+	CHILD_NS,		/* could not set up the mount namespace */
+	CHILD_MOUNT,		/* could not set up the mounts */
+	CHILD_PIPE,		/* the parent went away */
+	CHILD_WALKED,		/* the detached tree was copied recursively */
+	CHILD_ROOT_REFUSED,	/* the mount at its root wasn't copied */
+	CHILD_STILL_MOUNTED,	/* the copy survived the unlink of its mountpoint */
+	CHILD_ERRNO,		/* refused, but not with EINVAL */
+};
+
+static const char *child_reason(int code)
+{
+	static const char *const reasons[] = {
+		[CHILD_OK]		= "ok",
+		[CHILD_NS]		= "could not set up the mount namespace",
+		[CHILD_MOUNT]		= "could not set up the mounts",
+		[CHILD_PIPE]		= "the parent went away",
+		[CHILD_WALKED]		= "the detached tree was copied recursively",
+		[CHILD_ROOT_REFUSED]	= "the mount at its root wasn't copied",
+		[CHILD_STILL_MOUNTED]	= "the copy survived the unlink of its mountpoint",
+		[CHILD_ERRNO]		= "refused, but not with EINVAL",
+	};
+
+	if (code < 0 || code >= (int)(sizeof(reasons) / sizeof(reasons[0])))
+		return "child died";
+	return reasons[code];
+}
+
+struct child_args {
+	const char *x;		/* the nsfs bind mount goes here */
+	const char *s;		/* a file to bind on top of it */
+	const char *y;		/* a target to copy to */
+};
+
+/*
+ * Run @fn in a child in a mount namespace of its own. Once the child
+ * reports that its mounts are in place, unlink @victim here, where it is a
+ * plain file, and let the child carry on. Returns what the child reported.
+ */
+static int run_child(struct __test_metadata *_metadata,
+		     int (*fn)(const struct child_args *, int, int),
+		     const struct child_args *a, const char *victim)
+{
+	int to_parent[2], to_child[2], status;
+	pid_t pid;
+	char c;
+
+	if (pipe(to_parent) || pipe(to_child))
+		return -1;
+	pid = fork();
+	if (pid < 0)
+		return -1;
+	if (pid == 0) {
+		close(to_parent[0]);
+		close(to_child[1]);
+		_exit(fn(a, to_parent[1], to_child[0]));
+	}
+	close(to_parent[1]);
+	close(to_child[0]);
+	if (read(to_parent[0], &c, 1) == 1) {
+		/* not a mountpoint in this namespace, so the file can go */
+		EXPECT_EQ(unlink(victim), 0);
+		EXPECT_EQ(write(to_child[1], "", 1), 1);
+	}
+	close(to_parent[0]);
+	close(to_child[1]);
+	if (waitpid(pid, &status, 0) != pid || !WIFEXITED(status))
+		return -1;
+	return WEXITSTATUS(status);
+}
+
+/*
+ * An nsfs bind mount on @x, an fd on it and a bind mount of @s on top. Once
+ * the parent has unlinked @x underneath, the first mount is detached and the
+ * second one, which stayed attached to it, has been vacated. The tree may
+ * not be walked, the mount at its root may still be copied.
+ */
+static int vacant_child(const struct child_args *a, int to_parent, int from_parent)
+{
+	char link[PATH_LEN];
+	int fd, tfd;
+	char c;
+
+	if (own_mntns())
+		return CHILD_NS;
+	if (mount("/proc/self/ns/net", a->x, NULL, MS_BIND, NULL))
+		return CHILD_MOUNT;
+	fd = open(a->x, O_PATH | O_CLOEXEC);
+	if (fd < 0 || mount(a->s, a->x, NULL, MS_BIND, NULL))
+		return CHILD_MOUNT;
+
+	if (write(to_parent, "", 1) != 1 || read(from_parent, &c, 1) != 1)
+		return CHILD_PIPE;
+
+	tfd = sys_open_tree(fd, "", AT_EMPTY_PATH | AT_RECURSIVE | OPEN_TREE_CLONE |
+			    OPEN_TREE_CLOEXEC);
+	if (tfd >= 0) {
+		close(tfd);
+		return CHILD_WALKED;
+	}
+	if (errno != EINVAL)
+		return CHILD_ERRNO;
+	snprintf(link, sizeof(link), "/proc/self/fd/%d", fd);
+	if (!mount(link, a->y, NULL, MS_BIND | MS_REC, NULL))
+		return CHILD_WALKED;
+	if (errno != EINVAL)
+		return CHILD_ERRNO;
+
+	tfd = sys_open_tree(fd, "", AT_EMPTY_PATH | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	if (tfd < 0)
+		return CHILD_ROOT_REFUSED;
+	close(tfd);
+	/* the last reference on the detached mount collects the vacant one */
+	close(fd);
+	return CHILD_OK;
+}
+
+/*
+ * unlink() of the child's mountpoint from here, where it is a plain file,
+ * detaches the child's nsfs bind mount with the mount on top left attached
+ * to it. The mount on top loses its last reference right there and is
+ * vacated. The child must not be able to walk that tree.
+ */
+TEST_F(unmounted_tree, vacant_child_not_copied)
+{
+	char x[PATH_LEN], s[PATH_LEN], y[PATH_LEN];
+	struct child_args a = { .x = x, .s = s, .y = y };
+	int ret;
+
+	snprintf(x, sizeof(x), "%s/x", self->dir);
+	snprintf(s, sizeof(s), "%s/s", self->dir);
+	snprintf(y, sizeof(y), "%s/y", self->dir);
+	ASSERT_EQ(touch(x), 0);
+	ASSERT_EQ(touch(s), 0);
+	ASSERT_EQ(touch(y), 0);
+
+	ret = run_child(_metadata, vacant_child, &a, x);
+	ASSERT_EQ(ret, CHILD_OK)
+		TH_LOG("child: %s", child_reason(ret));
+}
+
+/*
+ * An nsfs bind mount on @x, lazily unmounted but kept alive by an fd, and a
+ * copy of it on @y. That copy is a mount like any other: once the parent has
+ * unlinked @y underneath, it is unmounted and its attributes can't be changed
+ * anymore. A copy that took the flag along is only unhooked, stays in the
+ * namespace and still takes the change.
+ */
+static int ordinary_copy(const struct child_args *a, int to_parent, int from_parent)
+{
+	struct mount_attr attr = {
+		.attr_set = MOUNT_ATTR_NOSUID,
+	};
+	char link[PATH_LEN];
+	int fd, fdy;
+	char c;
+
+	if (own_mntns())
+		return CHILD_NS;
+	if (mount("/proc/self/ns/net", a->x, NULL, MS_BIND, NULL))
+		return CHILD_MOUNT;
+	fd = open(a->x, O_PATH | O_CLOEXEC);
+	if (fd < 0 || umount2(a->x, MNT_DETACH))
+		return CHILD_MOUNT;
+	snprintf(link, sizeof(link), "/proc/self/fd/%d", fd);
+	if (mount(link, a->y, NULL, MS_BIND, NULL))
+		return CHILD_MOUNT;
+	fdy = open(a->y, O_PATH | O_CLOEXEC);
+	if (fdy < 0)
+		return CHILD_MOUNT;
+
+	if (write(to_parent, "", 1) != 1 || read(from_parent, &c, 1) != 1)
+		return CHILD_PIPE;
+
+	if (!sys_mount_setattr(fdy, "", AT_EMPTY_PATH, &attr, sizeof(attr)))
+		return CHILD_STILL_MOUNTED;
+	if (errno != EINVAL)
+		return CHILD_ERRNO;
+	close(fdy);
+	close(fd);
+	return CHILD_OK;
+}
+
+/*
+ * A copy of a detached nsfs bind mount must not take after its source and
+ * read as unmounted. unlink() of its mountpoint from here unmounts it like
+ * any other mount, so the child can't change its attributes anymore.
+ */
+TEST_F(unmounted_tree, copy_of_detached_bind_is_ordinary)
+{
+	char x[PATH_LEN], y[PATH_LEN];
+	struct child_args a = { .x = x, .y = y };
+	int ret;
+
+	snprintf(x, sizeof(x), "%s/x", self->dir);
+	snprintf(y, sizeof(y), "%s/y", self->dir);
+	ASSERT_EQ(touch(x), 0);
+	ASSERT_EQ(touch(y), 0);
+
+	ret = run_child(_metadata, ordinary_copy, &a, y);
+	ASSERT_EQ(ret, CHILD_OK)
+		TH_LOG("child: %s", child_reason(ret));
+}
+
+/*
+ * mount_setattr() may change the propagation of a detached tree while that
+ * tree is still the root of an anonymous mount namespace, but not once the
+ * tree has been dissolved and only a second fd keeps its root alive.
+ */
+TEST_F(unmounted_tree, detached_tree_setattr_refused)
+{
+	struct mount_attr attr = {
+		.propagation = MS_SHARED,
+	};
+	char a[PATH_LEN], b[PATH_LEN];
+	int tfd, fd;
+
+	snprintf(a, sizeof(a), "%s/a", self->dir);
+	snprintf(b, sizeof(b), "%s/a/b", self->dir);
+	ASSERT_EQ(mkdir(a, 0755), 0);
+	ASSERT_EQ(mount("tmpfs", a, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(mkdir(b, 0755), 0);
+	ASSERT_EQ(mount("tmpfs", b, "tmpfs", 0, NULL), 0);
+
+	tfd = sys_open_tree(AT_FDCWD, self->dir, AT_RECURSIVE | OPEN_TREE_CLONE |
+			    OPEN_TREE_CLOEXEC);
+	ASSERT_GE(tfd, 0);
+	ASSERT_EQ(sys_mount_setattr(tfd, "", AT_EMPTY_PATH | AT_RECURSIVE, &attr, sizeof(attr)), 0);
+	attr.propagation = MS_PRIVATE;
+	ASSERT_EQ(sys_mount_setattr(tfd, "", AT_EMPTY_PATH | AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+	/* a second reference on the root, then dissolve the tree */
+	fd = sys_open_tree(tfd, "", AT_EMPTY_PATH | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	close(tfd);
+
+	attr.propagation = MS_SHARED;
+	ASSERT_EQ(sys_mount_setattr(fd, "", AT_EMPTY_PATH | AT_RECURSIVE, &attr, sizeof(attr)), -1);
+	ASSERT_EQ(errno, EINVAL);
+	attr.propagation = MS_PRIVATE;
+	ASSERT_EQ(sys_mount_setattr(fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), -1);
+	ASSERT_EQ(errno, EINVAL);
+	close(fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/open_tree_ns/.gitignore b/tools/testing/selftests/filesystems/open_tree_ns/.gitignore
index fb12b93fbcaa..76f95c0ae5ef 100644
--- a/tools/testing/selftests/filesystems/open_tree_ns/.gitignore
+++ b/tools/testing/selftests/filesystems/open_tree_ns/.gitignore
@@ -1 +1,2 @@
 open_tree_ns_test
+open_tree_ns_covered_test
diff --git a/tools/testing/selftests/filesystems/open_tree_ns/Makefile b/tools/testing/selftests/filesystems/open_tree_ns/Makefile
index 4976ed1d7d4a..fb2aa77b6edb 100644
--- a/tools/testing/selftests/filesystems/open_tree_ns/Makefile
+++ b/tools/testing/selftests/filesystems/open_tree_ns/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_GEN_PROGS := open_tree_ns_test
+TEST_GEN_PROGS := open_tree_ns_test open_tree_ns_covered_test
 
 CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 LDLIBS := -lcap
diff --git a/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_covered_test.c b/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_covered_test.c
new file mode 100644
index 000000000000..27f5cddfb9ef
--- /dev/null
+++ b/tools/testing/selftests/filesystems/open_tree_ns/open_tree_ns_covered_test.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * open_tree(OPEN_TREE_NAMESPACE) by a caller that isn't privileged over the
+ * mount namespace it copies from must not reveal what the mounts below the
+ * copied mount cover. Without AT_RECURSIVE the copy is refused when there's
+ * anything mounted below the requested directory. With AT_RECURSIVE
+ * unbindable mounts are copied as well.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+#include "../wrappers.h"
+#include "../../kselftest_harness.h"
+
+#ifndef OPEN_TREE_NAMESPACE
+#define OPEN_TREE_NAMESPACE	(1 << 1)
+#endif
+
+#define DIR_LEN 64
+#define PATH_LEN 128
+
+/* Child exit codes. */
+enum {
+	CHILD_OK,
+	CHILD_USERNS,		/* could not create the child user namespace */
+	CHILD_NONREC_ALLOWED,	/* the non-recursive copy was not refused */
+	CHILD_NONREC_ERRNO,	/* it was refused with the wrong error */
+	CHILD_REC_REFUSED,	/* the recursive copy failed */
+	CHILD_SETNS,		/* could not enter the new mount namespace */
+	CHILD_NO_COVER,		/* the covering mount is missing in the copy */
+	CHILD_REVEALED,		/* the covered file is visible in the copy */
+};
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+static int create_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+/* Become root in a new user namespace, the uid @uid is mapped to 0. */
+static int enter_userns(uid_t uid, gid_t gid)
+{
+	char map[32];
+
+	if (unshare(CLONE_NEWUSER))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	return setgid(0) || setuid(0) ? -1 : 0;
+}
+
+FIXTURE(open_tree_ns_covered) {
+	char dir[DIR_LEN];
+	char cover[PATH_LEN];
+};
+
+FIXTURE_VARIANT(open_tree_ns_covered) {
+	int propagation;
+};
+
+FIXTURE_VARIANT_ADD(open_tree_ns_covered, private_cover) {
+	.propagation = MS_PRIVATE,
+};
+
+FIXTURE_VARIANT_ADD(open_tree_ns_covered, unbindable_cover) {
+	.propagation = MS_UNBINDABLE,
+};
+
+/*
+ * Root in a user namespace owns a private mount namespace with a tmpfs
+ * on @dir and a second tmpfs covering @dir/covered/under.txt.
+ */
+FIXTURE_SETUP(open_tree_ns_covered)
+{
+	char p[PATH_LEN];
+	int fd;
+
+	snprintf(self->dir, sizeof(self->dir), "/tmp/open_tree_ns_covered.XXXXXX");
+	ASSERT_NE(mkdtemp(self->dir), NULL);
+	if (enter_userns(getuid(), getgid()) || unshare(CLONE_NEWNS)) {
+		rmdir(self->dir);
+		SKIP(return, "test requires user namespaces");
+	}
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+	ASSERT_EQ(mount("tmpfs", self->dir, "tmpfs", 0, NULL), 0);
+
+	/* the flag has to exist before its rules can be checked */
+	fd = sys_open_tree(AT_FDCWD, self->dir,
+			   OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC);
+	if (fd < 0 && (errno == EINVAL || errno == ENOSYS)) {
+		umount2(self->dir, MNT_DETACH);
+		rmdir(self->dir);
+		SKIP(return, "OPEN_TREE_NAMESPACE not supported");
+	}
+	ASSERT_GE(fd, 0);
+	close(fd);
+
+	snprintf(self->cover, sizeof(self->cover), "%s/covered", self->dir);
+	ASSERT_EQ(mkdir(self->cover, 0755), 0);
+	snprintf(p, sizeof(p), "%s/covered/under.txt", self->dir);
+	ASSERT_EQ(create_file(p, "hidden"), 0);
+	ASSERT_EQ(mount("tmpfs", self->cover, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(mount(NULL, self->cover, NULL, variant->propagation, NULL), 0);
+}
+
+FIXTURE_TEARDOWN(open_tree_ns_covered)
+{
+	umount2(self->dir, MNT_DETACH);
+	rmdir(self->dir);
+}
+
+/* A caller in a new user namespace that doesn't own the mount namespace. */
+static int foreign_child(const char *dir)
+{
+	struct stat st;
+	int fd;
+
+	if (enter_userns(0, 0))
+		return CHILD_USERNS;
+
+	fd = sys_open_tree(AT_FDCWD, dir, OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC);
+	if (fd >= 0)
+		return CHILD_NONREC_ALLOWED;
+	if (errno != EINVAL)
+		return CHILD_NONREC_ERRNO;
+
+	fd = sys_open_tree(AT_FDCWD, dir,
+			   OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC | AT_RECURSIVE);
+	if (fd < 0)
+		return CHILD_REC_REFUSED;
+	if (setns(fd, CLONE_NEWNS))
+		return CHILD_SETNS;
+	if (stat("/covered", &st))
+		return CHILD_NO_COVER;
+	if (!access("/covered/under.txt", F_OK) || errno != ENOENT)
+		return CHILD_REVEALED;
+	return CHILD_OK;
+}
+
+TEST_F(open_tree_ns_covered, foreign_user_namespace)
+{
+	int status, fd;
+	pid_t pid;
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(foreign_child(self->dir));
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), CHILD_OK);
+
+	/* the owner of the mount namespace keeps bind mount semantics */
+	fd = sys_open_tree(AT_FDCWD, self->dir,
+			   OPEN_TREE_NAMESPACE | OPEN_TREE_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	close(fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/overlayfs/.gitignore b/tools/testing/selftests/filesystems/overlayfs/.gitignore
index 077f7a128168..b343cc430051 100644
--- a/tools/testing/selftests/filesystems/overlayfs/.gitignore
+++ b/tools/testing/selftests/filesystems/overlayfs/.gitignore
@@ -2,3 +2,4 @@
 dev_in_maps
 set_layers_via_fds
 idmapped_mounts
+automount_in_layer
diff --git a/tools/testing/selftests/filesystems/overlayfs/Makefile b/tools/testing/selftests/filesystems/overlayfs/Makefile
index b3185f684add..382a59bda5e7 100644
--- a/tools/testing/selftests/filesystems/overlayfs/Makefile
+++ b/tools/testing/selftests/filesystems/overlayfs/Makefile
@@ -9,6 +9,7 @@ LOCAL_HDRS += ../wrappers.h log.h
 TEST_GEN_PROGS := dev_in_maps
 TEST_GEN_PROGS += set_layers_via_fds
 TEST_GEN_PROGS += idmapped_mounts
+TEST_GEN_PROGS += automount_in_layer
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/filesystems/overlayfs/automount_in_layer.c b/tools/testing/selftests/filesystems/overlayfs/automount_in_layer.c
new file mode 100644
index 000000000000..0476c4582bdf
--- /dev/null
+++ b/tools/testing/selftests/filesystems/overlayfs/automount_in_layer.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A layer of an overlay is a private clone of the mount it was given and
+ * belongs to no mount namespace. fanotify hands out descriptors on it. An
+ * automount triggered through one has no namespace to go into: the open has
+ * to fail, not oops with namespace_sem held.
+ */
+#define _GNU_SOURCE
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/magic.h>
+#include <sys/fanotify.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/vfs.h>
+
+#include "../../kselftest_harness.h"
+
+#define DIR_LEN		64
+#define PATH_LEN	192
+
+static bool have_fs(const char *name)
+{
+	char line[128];
+	bool found = false;
+	FILE *f;
+
+	f = fopen("/proc/filesystems", "re");
+	if (!f)
+		return false;
+	while (fgets(line, sizeof(line), f)) {
+		char *nl = strchr(line, '\n');
+		char *tab = strchr(line, '\t');
+
+		if (nl)
+			*nl = 0;
+		if (tab && !strcmp(tab + 1, name))
+			found = true;
+	}
+	fclose(f);
+	return found;
+}
+
+static int mnt_id_of(int fd)
+{
+	char path[64], buf[4096], *p;
+	ssize_t n;
+	int info;
+
+	snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd);
+	info = open(path, O_RDONLY | O_CLOEXEC);
+	if (info < 0)
+		return -1;
+	n = read(info, buf, sizeof(buf) - 1);
+	close(info);
+	if (n <= 0)
+		return -1;
+	buf[n] = 0;
+	p = strstr(buf, "mnt_id:");
+	return p ? atoi(p + strlen("mnt_id:")) : -1;
+}
+
+static bool on_debugfs(int fd)
+{
+	struct statfs sf;
+
+	return !fstatfs(fd, &sf) && sf.f_type == DEBUGFS_MAGIC;
+}
+
+FIXTURE(layer) {
+	char base[DIR_LEN];
+	int fan;
+	int evfd;	/* on the layer clone of the lower debugfs */
+};
+
+FIXTURE_SETUP(layer)
+{
+	char lower[PATH_LEN], other[PATH_LEN], ovl[PATH_LEN], opts[2 * PATH_LEN + 16];
+	struct fanotify_event_metadata *ev;
+	struct pollfd pfd;
+	char buf[4096];
+	int lfd, lower_id;
+	ssize_t n;
+	DIR *d;
+
+	self->fan = -1;
+	self->evfd = -1;
+	if (geteuid())
+		SKIP(return, "test requires root");
+	if (!have_fs("debugfs") || !have_fs("tracefs"))
+		SKIP(return, "test requires debugfs with the tracefs automount");
+	if (!have_fs("overlay"))
+		SKIP(return, "test requires overlayfs");
+
+	snprintf(self->base, sizeof(self->base), "/tmp/layer.XXXXXX");
+	ASSERT_NE(mkdtemp(self->base), NULL);
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+	ASSERT_EQ(mount("tmpfs", self->base, "tmpfs", 0, "mode=0755"), 0);
+	snprintf(lower, sizeof(lower), "%s/lower", self->base);
+	snprintf(other, sizeof(other), "%s/other", self->base);
+	snprintf(ovl, sizeof(ovl), "%s/ovl", self->base);
+	ASSERT_EQ(mkdir(lower, 0755), 0);
+	ASSERT_EQ(mkdir(other, 0755), 0);
+	ASSERT_EQ(mkdir(ovl, 0755), 0);
+	ASSERT_EQ(mount("debugfs", lower, "debugfs", 0, NULL), 0);
+	snprintf(opts, sizeof(opts), "lowerdir=%s:%s", lower, other);
+	ASSERT_EQ(mount("overlay", ovl, "overlay", MS_RDONLY, opts), 0);
+
+	self->fan = fanotify_init(FAN_CLASS_NOTIF | FAN_NONBLOCK | FAN_CLOEXEC,
+				  O_RDONLY | O_CLOEXEC);
+	ASSERT_GE(self->fan, 0);
+	ASSERT_EQ(fanotify_mark(self->fan, FAN_MARK_ADD | FAN_MARK_FILESYSTEM,
+				FAN_OPEN | FAN_ONDIR, AT_FDCWD, lower), 0);
+	lfd = open(lower, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(lfd, 0);
+	lower_id = mnt_id_of(lfd);
+	close(lfd);
+
+	/* the overlay opens its lower directory through the layer clone */
+	d = opendir(ovl);
+	ASSERT_NE(d, NULL);
+	closedir(d);
+	pfd.fd = self->fan;
+	pfd.events = POLLIN;
+	ASSERT_EQ(poll(&pfd, 1, 5000), 1);
+	n = read(self->fan, buf, sizeof(buf));
+	ASSERT_GT(n, 0);
+	for (ev = (void *)buf; FAN_EVENT_OK(ev, n); ev = FAN_EVENT_NEXT(ev, n)) {
+		if (ev->fd < 0)
+			continue;
+		if (self->evfd < 0 && on_debugfs(ev->fd) &&
+		    mnt_id_of(ev->fd) != lower_id)
+			self->evfd = ev->fd;
+		else
+			close(ev->fd);
+	}
+	ASSERT_GE(self->evfd, 0)
+		TH_LOG("no event on the layer clone");
+}
+
+FIXTURE_TEARDOWN(layer)
+{
+	if (self->evfd >= 0)
+		close(self->evfd);
+	if (self->fan >= 0)
+		close(self->fan);
+	umount2(self->base, MNT_DETACH);
+	rmdir(self->base);
+}
+
+TEST_F(layer, automount_below_the_clone_is_refused)
+{
+	struct stat st;
+	int fd;
+
+	/* the automount point is there */
+	ASSERT_EQ(fstatat(self->evfd, "tracing", &st, AT_NO_AUTOMOUNT), 0);
+	/* the clone is in no namespace, so the automount has nowhere to go */
+	fd = openat(self->evfd, "tracing", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	EXPECT_LT(fd, 0);
+	EXPECT_EQ(errno, EINVAL);
+	if (fd >= 0)
+		close(fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/readdir_hold.h b/tools/testing/selftests/filesystems/readdir_hold.h
new file mode 100644
index 000000000000..57eee1bef470
--- /dev/null
+++ b/tools/testing/selftests/filesystems/readdir_hold.h
@@ -0,0 +1,224 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Hold a readdir of a directory in the page fault of its buffer and see
+ * whether a create and a lookup in that directory wait for it. For a
+ * directory that is permanently empty they must not.
+ */
+#ifndef __SELFTESTS_READDIR_HOLD_H
+#define __SELFTESTS_READDIR_HOLD_H
+
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/userfaultfd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+
+#define HOLD_FAULT_MS	5000	/* for the reader to reach the fault */
+#define HOLD_QUEUE_MS	2000	/* for the create to queue up behind it */
+#define HOLD_LOOKUP_MS	5000	/* for the lookup to come back */
+
+struct readdir_hold {
+	int uffd;
+	int taskdir;		/* /proc/self/task, from before any namespace change */
+	long page_size;
+	char *page;		/* faults until released */
+	int dfd;
+	pid_t creator_tid;
+	int created;
+	int done[2];		/* the finder writes a byte when it is back */
+};
+
+/*
+ * The fault happens in the kernel, so the userfaultfd needs CAP_SYS_PTRACE
+ * in the initial user namespace or vm.unprivileged_userfaultfd. Call this
+ * before entering a user namespace.
+ */
+static inline int readdir_hold_init(struct readdir_hold *h)
+{
+	struct uffdio_api api = { .api = UFFD_API };
+
+	h->page = MAP_FAILED;
+	h->page_size = sysconf(_SC_PAGESIZE);
+	h->taskdir = open("/proc/self/task", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	h->uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+	if (h->uffd < 0 || h->taskdir < 0 || ioctl(h->uffd, UFFDIO_API, &api)) {
+		if (h->uffd >= 0)
+			close(h->uffd);
+		if (h->taskdir >= 0)
+			close(h->taskdir);
+		h->uffd = h->taskdir = -1;
+		return -1;
+	}
+	return 0;
+}
+
+static inline void readdir_hold_destroy(struct readdir_hold *h)
+{
+	if (h->uffd >= 0)
+		close(h->uffd);
+	if (h->taskdir >= 0)
+		close(h->taskdir);
+	h->uffd = h->taskdir = -1;
+}
+
+static inline void *readdir_hold_reader(void *arg)
+{
+	struct readdir_hold *h = arg;
+
+	/* the first byte written to the buffer faults until released */
+	syscall(__NR_getdents64, h->dfd, h->page, h->page_size);
+	return NULL;
+}
+
+static inline void *readdir_hold_creator(void *arg)
+{
+	struct readdir_hold *h = arg;
+
+	h->creator_tid = syscall(__NR_gettid);
+	/* takes the directory lock exclusive before it fails */
+	mkdirat(h->dfd, "x", 0755);
+	__atomic_store_n(&h->created, 1, __ATOMIC_RELEASE);
+	return NULL;
+}
+
+static inline void *readdir_hold_finder(void *arg)
+{
+	struct readdir_hold *h = arg;
+	int fd;
+
+	/* a lookup that misses the dcache takes the lock shared */
+	fd = openat(h->dfd, "no_such_name", O_RDONLY | O_CLOEXEC);
+	if (fd >= 0)
+		close(fd);
+	if (write(h->done[1], "x", 1) != 1)
+		perror("readdir_hold: finder");
+	return NULL;
+}
+
+/* the creator is back, or waits in the kernel for the lock */
+static inline bool readdir_hold_creator_settled(struct readdir_hold *h)
+{
+	char path[32], buf[256], *p;
+	ssize_t n;
+	int fd;
+
+	if (__atomic_load_n(&h->created, __ATOMIC_ACQUIRE))
+		return true;
+	if (!h->creator_tid)
+		return false;
+	snprintf(path, sizeof(path), "%d/stat", h->creator_tid);
+	fd = openat(h->taskdir, path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0)
+		return false;
+	n = read(fd, buf, sizeof(buf) - 1);
+	close(fd);
+	if (n <= 0)
+		return false;
+	buf[n] = 0;
+	/* "pid (comm) state ..." */
+	p = strrchr(buf, ')');
+	return p && p[1] == ' ' && p[2] == 'D';
+}
+
+static inline bool readdir_hold_faulted(struct readdir_hold *h)
+{
+	struct pollfd pfd = { .fd = h->uffd, .events = POLLIN };
+	struct uffd_msg msg;
+
+	if (poll(&pfd, 1, HOLD_FAULT_MS) != 1)
+		return false;
+	if (read(h->uffd, &msg, sizeof(msg)) != sizeof(msg))
+		return false;
+	return msg.event == UFFD_EVENT_PAGEFAULT;
+}
+
+/* let the reader go on */
+static inline void readdir_hold_release(struct readdir_hold *h)
+{
+	struct uffdio_copy cp = {
+		.dst = (unsigned long)h->page,
+		.len = h->page_size,
+	};
+	void *zero;
+
+	zero = calloc(1, h->page_size);
+	if (!zero)
+		return;
+	cp.src = (unsigned long)zero;
+	if (ioctl(h->uffd, UFFDIO_COPY, &cp) && errno != EEXIST)
+		perror("readdir_hold: UFFDIO_COPY");
+	free(zero);
+}
+
+/*
+ * A readdir of @dfd that sticks in the fault of its buffer, then a create
+ * and a lookup in @dfd. Whether the lookup came back while the readdir was
+ * still stuck goes to @stalled. Returns -1 when that could not be found
+ * out.
+ */
+static inline int readdir_hold_check(struct readdir_hold *h, int dfd,
+				     bool *stalled)
+{
+	pthread_t reader, creator, finder;
+	struct uffdio_register reg = {};
+	struct pollfd pfd;
+	int ret = -1, i;
+
+	h->dfd = dfd;
+	h->created = 0;
+	h->creator_tid = 0;
+	h->page = mmap(NULL, h->page_size, PROT_READ | PROT_WRITE,
+		       MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (h->page == MAP_FAILED)
+		return -1;
+	reg.range.start = (unsigned long)h->page;
+	reg.range.len = h->page_size;
+	reg.mode = UFFDIO_REGISTER_MODE_MISSING;
+	if (ioctl(h->uffd, UFFDIO_REGISTER, &reg) || pipe2(h->done, O_CLOEXEC))
+		goto out_page;
+
+	if (pthread_create(&reader, NULL, readdir_hold_reader, h))
+		goto out_pipe;
+	if (!readdir_hold_faulted(h))
+		goto out_reader;
+	if (pthread_create(&creator, NULL, readdir_hold_creator, h))
+		goto out_reader;
+	for (i = 0; i < HOLD_QUEUE_MS / 10 && !readdir_hold_creator_settled(h); i++)
+		usleep(10000);
+	if (pthread_create(&finder, NULL, readdir_hold_finder, h))
+		goto out_creator;
+
+	pfd.fd = h->done[0];
+	pfd.events = POLLIN;
+	*stalled = poll(&pfd, 1, HOLD_LOOKUP_MS) != 1;
+	ret = 0;
+
+	readdir_hold_release(h);
+	pthread_join(finder, NULL);
+out_creator:
+	if (ret)
+		readdir_hold_release(h);
+	pthread_join(creator, NULL);
+out_reader:
+	if (ret)
+		readdir_hold_release(h);
+	pthread_join(reader, NULL);
+out_pipe:
+	close(h->done[0]);
+	close(h->done[1]);
+out_page:
+	munmap(h->page, h->page_size);
+	h->page = MAP_FAILED;
+	return ret;
+}
+
+#endif /* __SELFTESTS_READDIR_HOLD_H */
diff --git a/tools/testing/selftests/filesystems/rw_hint_test.c b/tools/testing/selftests/filesystems/rw_hint_test.c
new file mode 100644
index 000000000000..d1930f82f63b
--- /dev/null
+++ b/tools/testing/selftests/filesystems/rw_hint_test.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * F_SET_RW_HINT is refused on an immutable inode. Nothing is ever written
+ * to it and it may be shared with everybody, like a namespace file or the
+ * root of an empty mount namespace.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+#include "../kselftest_harness.h"
+
+/* <linux/fs.h> and <linux/fcntl.h> don't mix with the libc headers */
+#ifndef FS_IOC_GETFLAGS
+#define FS_IOC_GETFLAGS		_IOR('f', 1, long)
+#define FS_IOC_SETFLAGS		_IOW('f', 2, long)
+#endif
+#ifndef FS_IMMUTABLE_FL
+#define FS_IMMUTABLE_FL		0x00000010
+#endif
+#ifndef F_LINUX_SPECIFIC_BASE
+#define F_LINUX_SPECIFIC_BASE	1024
+#endif
+#ifndef F_GET_RW_HINT
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#endif
+#ifndef RWH_WRITE_LIFE_SHORT
+#define RWH_WRITE_LIFE_SHORT	2
+#endif
+#ifndef UNSHARE_EMPTY_MNTNS
+#define UNSHARE_EMPTY_MNTNS	0x00100000
+#endif
+
+static int set_hint(int fd, uint64_t hint)
+{
+	return fcntl(fd, F_SET_RW_HINT, &hint);
+}
+
+static long get_hint(int fd)
+{
+	uint64_t hint;
+
+	if (fcntl(fd, F_GET_RW_HINT, &hint))
+		return -1;
+	return hint;
+}
+
+TEST(immutable_file)
+{
+	char path[] = "/tmp/rw_hint.XXXXXX";
+	int fd, flags;
+
+	if (geteuid())
+		SKIP(return, "test requires root");
+
+	fd = mkstemp(path);
+	ASSERT_GE(fd, 0);
+	unlink(path);
+	ASSERT_EQ(set_hint(fd, RWH_WRITE_LIFE_SHORT), 0);
+	EXPECT_EQ(get_hint(fd), RWH_WRITE_LIFE_SHORT);
+
+	if (ioctl(fd, FS_IOC_GETFLAGS, &flags)) {
+		close(fd);
+		SKIP(return, "no file attributes on this filesystem");
+	}
+	flags |= FS_IMMUTABLE_FL;
+	ASSERT_EQ(ioctl(fd, FS_IOC_SETFLAGS, &flags), 0);
+	EXPECT_EQ(set_hint(fd, RWH_WRITE_LIFE_SHORT), -1);
+	EXPECT_EQ(errno, EPERM);
+	flags &= ~FS_IMMUTABLE_FL;
+	ASSERT_EQ(ioctl(fd, FS_IOC_SETFLAGS, &flags), 0);
+	EXPECT_EQ(set_hint(fd, RWH_WRITE_LIFE_SHORT), 0);
+	close(fd);
+}
+
+TEST(namespace_file)
+{
+	int fd;
+
+	if (geteuid())
+		SKIP(return, "test requires root");
+
+	fd = open("/proc/self/ns/mnt", O_RDONLY | O_CLOEXEC);
+	ASSERT_GE(fd, 0);
+	EXPECT_EQ(set_hint(fd, RWH_WRITE_LIFE_SHORT), -1);
+	EXPECT_EQ(errno, EPERM);
+	close(fd);
+}
+
+TEST(empty_mntns_root)
+{
+	int status;
+	pid_t pid;
+
+	if (geteuid())
+		SKIP(return, "test requires root");
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		int fd;
+
+		if (unshare(UNSHARE_EMPTY_MNTNS))
+			_exit(errno == EINVAL ? 100 : 1);
+		fd = open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+		if (fd < 0)
+			_exit(2);
+		if (set_hint(fd, RWH_WRITE_LIFE_SHORT) == 0)
+			_exit(3);
+		_exit(errno == EPERM ? 0 : 4);
+	}
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	if (WEXITSTATUS(status) == 100)
+		SKIP(return, "UNSHARE_EMPTY_MNTNS not supported");
+	EXPECT_EQ(WEXITSTATUS(status), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/umount_propagation/Makefile b/tools/testing/selftests/filesystems/umount_propagation/Makefile
new file mode 100644
index 000000000000..31f783a92b23
--- /dev/null
+++ b/tools/testing/selftests/filesystems/umount_propagation/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_GEN_PROGS := umount_propagation_test shrink_submounts_test locked_mount_test
+
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/umount_propagation/locked_mount_test.c b/tools/testing/selftests/filesystems/umount_propagation/locked_mount_test.c
new file mode 100644
index 000000000000..0799b2ba545d
--- /dev/null
+++ b/tools/testing/selftests/filesystems/umount_propagation/locked_mount_test.c
@@ -0,0 +1,432 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MNT_LOCKED keeps the owner of a user namespace from revealing what a
+ * mount covers. The lock has to be set on the copy in that namespace and
+ * only there, it has to survive the expiry of a mount placed beneath the
+ * locked one, and it has to survive the propagated umount of such a copy.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+
+#include "../../kselftest_harness.h"
+
+#ifndef MOVE_MOUNT_F_EMPTY_PATH
+#define MOVE_MOUNT_F_EMPTY_PATH	0x00000004
+#endif
+#ifndef MOVE_MOUNT_BENEATH
+#define MOVE_MOUNT_BENEATH	0x00000200
+#endif
+
+#define DIR_LEN		64
+#define PATH_LEN	192
+#define FLAGS		(MS_NOSUID | MS_NODEV | MS_NOEXEC)
+
+/* exit codes of the children, each test says what they mean */
+enum {
+	CHILD_OK,
+	CHILD_SETUP,
+	CHILD_STEP1,
+	CHILD_STEP2,
+	CHILD_STEP3,
+	CHILD_STEP4,
+};
+
+static int write_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+static int create_file(const char *path, const char *s)
+{
+	ssize_t n = -1;
+	int fd;
+
+	fd = open(path, O_WRONLY | O_CREAT | O_EXCL | O_CLOEXEC, 0644);
+	if (fd >= 0) {
+		n = write(fd, s, strlen(s));
+		close(fd);
+	}
+	return n == (ssize_t)strlen(s) ? 0 : -1;
+}
+
+/* Root in a new user namespace with a copy of the mount namespace. */
+static int enter_userns(void)
+{
+	uid_t uid = getuid();
+	gid_t gid = getgid();
+	char map[32];
+
+	prctl(PR_SET_DUMPABLE, 1);
+	if (unshare(CLONE_NEWUSER | CLONE_NEWNS))
+		return -1;
+	if (write_file("/proc/self/setgroups", "deny") && errno != ENOENT)
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map))
+		return -1;
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map))
+		return -1;
+	return setgid(0) || setuid(0) ? -1 : 0;
+}
+
+static int wait_child(pid_t pid)
+{
+	int status;
+
+	if (waitpid(pid, &status, 0) != pid || !WIFEXITED(status))
+		return -1;
+	return WEXITSTATUS(status);
+}
+
+static int wait_byte(int fd)
+{
+	char c;
+
+	return read(fd, &c, 1) == 1 ? 0 : -1;
+}
+
+static int send_byte(int fd)
+{
+	return write(fd, "x", 1) == 1 ? 0 : -1;
+}
+
+/* A read of @path fails: the file is covered. */
+static bool covered(const char *path)
+{
+	int fd = open(path, O_RDONLY | O_CLOEXEC);
+
+	if (fd >= 0)
+		close(fd);
+	return fd < 0;
+}
+
+FIXTURE(locked_mount) {
+	char base[DIR_LEN];
+	bool tracing;		/* debugfs with the tracefs automount is there */
+};
+
+FIXTURE_SETUP(locked_mount)
+{
+	char p[PATH_LEN];
+	struct stat st;
+
+	if (geteuid())
+		SKIP(return, "test requires root");
+
+	snprintf(self->base, sizeof(self->base), "/tmp/locked_mount.XXXXXX");
+	ASSERT_NE(mkdtemp(self->base), NULL);
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+	ASSERT_EQ(mount("tmpfs", self->base, "tmpfs", 0, "mode=0755"), 0);
+
+	/* an automount that a user can name: the tracefs below debugfs */
+	snprintf(p, sizeof(p), "%s/dbg", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	self->tracing = !mount("debugfs", p, "debugfs", FLAGS, NULL);
+	if (self->tracing) {
+		/* the cases trigger it themselves */
+		snprintf(p, sizeof(p), "%s/dbg/tracing", self->base);
+		self->tracing = !fstatat(AT_FDCWD, p, &st, AT_NO_AUTOMOUNT) &&
+				S_ISDIR(st.st_mode);
+	}
+}
+
+FIXTURE_TEARDOWN(locked_mount)
+{
+	umount2(self->base, MNT_DETACH);
+	rmdir(self->base);
+}
+
+/*
+ * The child keeps a directory descriptor on the host's debugfs mount, moves
+ * to a user namespace of its own and triggers the automount through the
+ * descriptor. The mount goes below the host's mount and propagates into the
+ * child's copy. The child's copy has to be locked, the host's not.
+ */
+static int automount_child(const char *base, int dfd, int to_host, int from_host)
+{
+	char p[PATH_LEN];
+	struct stat st;
+
+	if (enter_userns())
+		return CHILD_SETUP;
+	if (fstatat(dfd, "tracing/.", &st, 0))
+		return CHILD_STEP1;
+	if (send_byte(to_host) || wait_byte(from_host))
+		return CHILD_SETUP;
+	/* the flags of the copy are locked: EPERM */
+	snprintf(p, sizeof(p), "%s/dbg/tracing", base);
+	if (!mount(NULL, p, NULL, MS_REMOUNT | MS_BIND, NULL) || errno != EPERM)
+		return CHILD_STEP2;
+	return CHILD_OK;
+}
+
+TEST_F(locked_mount, automount_locked_in_the_triggering_namespace)
+{
+	int to_host[2], from_host[2], dfd, ret;
+	char p[PATH_LEN];
+	pid_t pid;
+
+	if (!self->tracing)
+		SKIP(return, "test requires debugfs with the tracefs automount");
+
+	snprintf(p, sizeof(p), "%s/dbg", self->base);
+	ASSERT_EQ(mount(NULL, p, NULL, MS_SHARED, NULL), 0);
+	dfd = open(p, O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+	ASSERT_GE(dfd, 0);
+	ASSERT_EQ(pipe(to_host), 0);
+	ASSERT_EQ(pipe(from_host), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(automount_child(self->base, dfd, to_host[1], from_host[0]));
+	close(dfd);
+	ASSERT_EQ(wait_byte(to_host[0]), 0);
+
+	/* the host's own mount isn't locked: the flags can go */
+	snprintf(p, sizeof(p), "%s/dbg/tracing", self->base);
+	EXPECT_EQ(mount(NULL, p, NULL, MS_REMOUNT | MS_BIND, NULL), 0);
+
+	ASSERT_EQ(send_byte(from_host[1]), 0);
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
+/*
+ * A copy of a tree with a locked cover. The child puts a shrinkable mount
+ * beneath the cover, which hands the lock down, unmounts the cover and then
+ * asks for the umount of an unlocked ancestor. That expires the shrinkable
+ * mount on a kernel that doesn't look at the lock, and the covered
+ * directory is bare.
+ */
+static int expiry_child(const char *base)
+{
+	char srv[PATH_LEN], shr[PATH_LEN], x[PATH_LEN], c[PATH_LEN];
+	char hidden[PATH_LEN], secret[PATH_LEN];
+
+	snprintf(srv, sizeof(srv), "%s/srv", base);
+	snprintf(shr, sizeof(shr), "%s/shr", base);
+	snprintf(x, sizeof(x), "%s/x", base);
+	snprintf(c, sizeof(c), "%s/c", base);
+	snprintf(hidden, sizeof(hidden), "%s/x/hidden", base);
+	snprintf(secret, sizeof(secret), "%s/x/hidden/secret", base);
+
+	if (enter_userns())
+		return CHILD_SETUP;
+	if (mount(srv, x, NULL, MS_BIND | MS_REC, NULL) ||
+	    mount(shr, c, NULL, MS_BIND, NULL))
+		return CHILD_SETUP;
+	/* the cover is locked */
+	if (!umount2(hidden, 0) || errno != EINVAL)
+		return CHILD_STEP1;
+	if (syscall(__NR_move_mount, AT_FDCWD, c, AT_FDCWD, hidden, MOVE_MOUNT_BENEATH))
+		return CHILD_STEP2;
+	/* the lock moved down, the cover may go */
+	if (umount2(hidden, 0))
+		return CHILD_STEP3;
+	/* the holder of the lock may not, in any way */
+	if (!umount2(hidden, 0) || errno != EINVAL)
+		return CHILD_STEP4;
+	if (chdir(x))
+		return CHILD_SETUP;
+	umount2(x, 0);
+	return covered(secret) ? CHILD_OK : CHILD_STEP4;
+}
+
+TEST_F(locked_mount, expiry_leaves_a_locked_mount_alone)
+{
+	char p[PATH_LEN], q[PATH_LEN];
+	pid_t pid;
+	int ret;
+
+	if (!self->tracing)
+		SKIP(return, "test requires debugfs with the tracefs automount");
+
+	snprintf(p, sizeof(p), "%s/dbg/tracing", self->base);
+	snprintf(q, sizeof(q), "%s/shr", self->base);
+	ASSERT_EQ(mkdir(q, 0755), 0);
+	/* a bind of an automount is shrinkable as well */
+	ASSERT_EQ(mount(p, q, NULL, MS_BIND, NULL), 0);
+	snprintf(p, sizeof(p), "%s/srv", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	ASSERT_EQ(mount("tmpfs", p, "tmpfs", 0, "mode=0755"), 0);
+	snprintf(p, sizeof(p), "%s/srv/hidden", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	snprintf(p, sizeof(p), "%s/srv/hidden/secret", self->base);
+	ASSERT_EQ(create_file(p, "covered-by-root\n"), 0);
+	snprintf(p, sizeof(p), "%s/srv/hidden", self->base);
+	ASSERT_EQ(mount("tmpfs", p, "tmpfs", 0, "mode=0755"), 0);
+	snprintf(p, sizeof(p), "%s/x", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	snprintf(p, sizeof(p), "%s/c", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(expiry_child(self->base));
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
+/*
+ * The copy of the mount tree that a user namespace gets at its creation has
+ * the automounts in it locked unless they are on an expiry list. A bind of
+ * such a tree inside the namespace copies the lock to the automount but not
+ * to the root of the bind, so the child may ask for the umount of that root.
+ * That must not expire the locked automount below it: the root is busy, the
+ * umount fails and the automount has to be there afterwards.
+ */
+static int copied_tree_child(const char *base)
+{
+	char dbg[PATH_LEN], x[PATH_LEN], tracing[PATH_LEN];
+	struct stat root, st;
+
+	snprintf(dbg, sizeof(dbg), "%s/dbg", base);
+	snprintf(x, sizeof(x), "%s/x", base);
+	snprintf(tracing, sizeof(tracing), "%s/x/tracing", base);
+
+	if (enter_userns())
+		return CHILD_SETUP;
+	if (mount(dbg, x, NULL, MS_BIND | MS_REC, NULL))
+		return CHILD_SETUP;
+	/* the copy of the automount carries the lock */
+	if (!umount2(tracing, 0) || errno != EINVAL)
+		return CHILD_STEP1;
+	/* the root of the bind doesn't; keep it busy */
+	if (chdir(x))
+		return CHILD_SETUP;
+	if (!umount2(x, 0) || errno != EBUSY)
+		return CHILD_STEP2;
+	/* the automount below it must not have gone */
+	if (stat(x, &root) || fstatat(AT_FDCWD, tracing, &st, AT_NO_AUTOMOUNT))
+		return CHILD_SETUP;
+	return st.st_dev != root.st_dev ? CHILD_OK : CHILD_STEP3;
+}
+
+TEST_F(locked_mount, umount_of_a_bind_leaves_a_locked_automount_alone)
+{
+	char p[PATH_LEN];
+	struct stat st;
+	pid_t pid;
+	int ret;
+
+	if (!self->tracing)
+		SKIP(return, "test requires debugfs with the tracefs automount");
+
+	/* the copy the child gets has to contain the automount */
+	snprintf(p, sizeof(p), "%s/dbg/tracing/.", self->base);
+	ASSERT_EQ(stat(p, &st), 0);
+	snprintf(p, sizeof(p), "%s/x", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(copied_tree_child(self->base));
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
+/*
+ * Z is a user namespace with a copy of a tree in which P/d is covered by a
+ * locked mount. The host mounts X on P/d, which propagates beneath Z's
+ * cover, and unmounts it again. Z's cover has to be locked afterwards as
+ * it was before.
+ */
+static int propagation_child(const char *base, int to_host, int from_host)
+{
+	char d[PATH_LEN], secret[PATH_LEN];
+
+	snprintf(d, sizeof(d), "%s/P/d", base);
+	snprintf(secret, sizeof(secret), "%s/P/d/secret", base);
+
+	if (enter_userns())
+		return CHILD_SETUP;
+	/* the cover is locked */
+	if (!umount2(d, 0) || errno != EINVAL)
+		return CHILD_STEP1;
+	if (send_byte(to_host) || wait_byte(from_host))
+		return CHILD_SETUP;
+	/* X came and went beneath it: still locked */
+	if (!umount2(d, 0) || errno != EINVAL)
+		return CHILD_STEP2;
+	return covered(secret) ? CHILD_OK : CHILD_STEP3;
+}
+
+TEST_F(locked_mount, propagated_copy_keeps_the_cover_locked)
+{
+	int to_host[2], from_host[2], ret;
+	char p[PATH_LEN];
+	pid_t pid;
+
+	snprintf(p, sizeof(p), "%s/P", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	ASSERT_EQ(mount("tmpfs", p, "tmpfs", 0, "mode=0755"), 0);
+	ASSERT_EQ(mount(NULL, p, NULL, MS_SHARED, NULL), 0);
+	snprintf(p, sizeof(p), "%s/P/d", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	snprintf(p, sizeof(p), "%s/P/d/secret", self->base);
+	ASSERT_EQ(create_file(p, "covered-by-root\n"), 0);
+	ASSERT_EQ(pipe(to_host), 0);
+	ASSERT_EQ(pipe(from_host), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		/* M: a manager's namespace that covers P/d for Z */
+		pid_t z;
+
+		if (unshare(CLONE_NEWNS))
+			_exit(CHILD_SETUP);
+		snprintf(p, sizeof(p), "%s/P", self->base);
+		if (mount(NULL, p, NULL, MS_SLAVE, NULL))
+			_exit(CHILD_SETUP);
+		snprintf(p, sizeof(p), "%s/P/d", self->base);
+		if (mount("tmpfs", p, "tmpfs", 0, "mode=0755"))
+			_exit(CHILD_SETUP);
+		z = fork();
+		if (z < 0)
+			_exit(CHILD_SETUP);
+		if (z == 0)
+			_exit(propagation_child(self->base, to_host[1], from_host[0]));
+		_exit(wait_child(z));
+	}
+	ASSERT_EQ(wait_byte(to_host[0]), 0);
+
+	/* the host mounts on P/d and unmounts again; both propagate */
+	snprintf(p, sizeof(p), "%s/P/d", self->base);
+	ASSERT_EQ(mount("tmpfs", p, "tmpfs", 0, "mode=0755"), 0);
+	ASSERT_EQ(umount2(p, 0), 0);
+
+	ASSERT_EQ(send_byte(from_host[1]), 0);
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/umount_propagation/shrink_submounts_test.c b/tools/testing/selftests/filesystems/umount_propagation/shrink_submounts_test.c
new file mode 100644
index 000000000000..b024ae3417ce
--- /dev/null
+++ b/tools/testing/selftests/filesystems/umount_propagation/shrink_submounts_test.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A synchronous umount first unmounts the shrinkable submounts of the
+ * victim that aren't busy. Every one of them has to be checked right
+ * before it is unmounted: unmounting one can slide a busy mount to where
+ * the propagated copy of the next one is looked up.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/fanotify.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/statfs.h>
+#include <sys/vfs.h>
+#include <linux/magic.h>
+
+#include "../../kselftest_harness.h"
+
+#ifndef FAN_REPORT_MNT
+#define FAN_REPORT_MNT		0x00004000
+#endif
+#ifndef FAN_MARK_MNTNS
+#define FAN_MARK_MNTNS		0x00000110
+#endif
+#ifndef FAN_MNT_ATTACH
+#define FAN_MNT_ATTACH		0x01000000
+#endif
+#ifndef FAN_MNT_DETACH
+#define FAN_MNT_DETACH		0x02000000
+#endif
+
+#define DIR_LEN 64
+#define PATH_LEN 128
+
+FIXTURE(shrink_submounts) {
+	char base[DIR_LEN];
+	char automount[PATH_LEN];
+	bool mounted;
+	int fan;
+};
+
+/*
+ * Shrinkable mounts come from an automount. The tracefs mount below debugfs
+ * is one and bind mounts inherit the flag.
+ */
+FIXTURE_SETUP(shrink_submounts)
+{
+	struct stat st;
+	char p[PATH_LEN];
+
+	self->mounted = false;
+	self->fan = -1;
+
+	if (geteuid() != 0)
+		SKIP(return, "test requires CAP_SYS_ADMIN");
+
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+
+	snprintf(self->base, sizeof(self->base), "/tmp/shrink_submounts.XXXXXX");
+	ASSERT_NE(mkdtemp(self->base), NULL);
+	ASSERT_EQ(mount("tmpfs", self->base, "tmpfs", 0, NULL), 0);
+	self->mounted = true;
+	ASSERT_EQ(mount(NULL, self->base, NULL, MS_PRIVATE, NULL), 0);
+
+	snprintf(p, sizeof(p), "%s/dbg", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	if (mount("debugfs", p, "debugfs", 0, NULL)) {
+		umount2(self->base, MNT_DETACH);
+		rmdir(self->base);
+		SKIP(return, "test requires debugfs");
+	}
+	snprintf(self->automount, sizeof(self->automount), "%s/dbg/tracing",
+		 self->base);
+	snprintf(p, sizeof(p), "%s/dbg/tracing/.", self->base);
+	if (stat(p, &st)) {
+		umount2(self->base, MNT_DETACH);
+		rmdir(self->base);
+		SKIP(return, "test requires the tracefs automount");
+	}
+}
+
+FIXTURE_TEARDOWN(shrink_submounts)
+{
+	if (self->fan >= 0)
+		close(self->fan);
+	chdir("/");
+	if (self->mounted)
+		umount2(self->base, MNT_DETACH);
+	rmdir(self->base);
+}
+
+static bool mounted_tmpfs(const char *path)
+{
+	struct statfs st;
+
+	return !statfs(path, &st) && st.f_type == TMPFS_MAGIC;
+}
+
+/*
+ * P is a shared bind mount of the automount, P1 a slave of P that is shared
+ * in turn and P2 its peer. B, another bind mount of the automount, goes on
+ * P/options and propagates copies Bc1 and Bc2 onto P1/options and
+ * P2/options. R, a tmpfs and our working directory, sits on top of Bc2 which
+ * is made private first. P, with B on it, is moved to P1/instances.
+ *
+ * A synchronous umount of P1 unmounts the shrinkable submounts Bc1 and B
+ * first. Unmounting Bc1 takes Bc2 along and slides R to P2/options where
+ * the propagated copy of B is looked up next. R is busy, so B has to stay
+ * and the umount fails with EBUSY.
+ */
+TEST_F(shrink_submounts, busy_mount_moved_into_reach)
+{
+	char p[PATH_LEN], p1[PATH_LEN], p2[PATH_LEN], r[PATH_LEN], cwd[PATH_LEN];
+	int nsfd;
+
+	snprintf(p, sizeof(p), "%s/p", self->base);
+	snprintf(p1, sizeof(p1), "%s/p1", self->base);
+	snprintf(p2, sizeof(p2), "%s/p2", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	ASSERT_EQ(mkdir(p1, 0755), 0);
+	ASSERT_EQ(mkdir(p2, 0755), 0);
+
+	/* watch the mount namespace so that the detached mounts get queued */
+	self->fan = fanotify_init(FAN_REPORT_MNT, O_RDONLY);
+	if (self->fan >= 0) {
+		nsfd = open("/proc/self/ns/mnt", O_RDONLY | O_CLOEXEC);
+		ASSERT_GE(nsfd, 0);
+		EXPECT_EQ(fanotify_mark(self->fan, FAN_MARK_ADD | FAN_MARK_MNTNS,
+					FAN_MNT_ATTACH | FAN_MNT_DETACH, nsfd, NULL), 0);
+		close(nsfd);
+	}
+
+	ASSERT_EQ(mount(self->automount, p, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(NULL, p, NULL, MS_SHARED, NULL), 0);
+	ASSERT_EQ(mount(p, p1, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(NULL, p1, NULL, MS_SLAVE, NULL), 0);
+	ASSERT_EQ(mount(NULL, p1, NULL, MS_SHARED, NULL), 0);
+	ASSERT_EQ(mount(p1, p2, NULL, MS_BIND, NULL), 0);
+
+	/* B on P/options, copies on P1/options and P2/options */
+	snprintf(r, sizeof(r), "%s/p/options", self->base);
+	ASSERT_EQ(mount(self->automount, r, NULL, MS_BIND, NULL), 0);
+
+	/* R on top of Bc2 */
+	snprintf(r, sizeof(r), "%s/p2/options", self->base);
+	ASSERT_EQ(mount(NULL, r, NULL, MS_PRIVATE, NULL), 0);
+	ASSERT_EQ(mount("R", r, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(chdir(r), 0);
+
+	/* P, with B on it, below the victim */
+	snprintf(cwd, sizeof(cwd), "%s/p1/instances", self->base);
+	ASSERT_EQ(mount(p, cwd, NULL, MS_MOVE, NULL), 0);
+
+	ASSERT_TRUE(mounted_tmpfs(r));
+	ASSERT_EQ(umount2(p1, 0), -1);
+	EXPECT_EQ(errno, EBUSY);
+
+	/* R is still mounted and still our working directory */
+	EXPECT_TRUE(mounted_tmpfs(r));
+	ASSERT_NE(getcwd(cwd, sizeof(cwd)), NULL);
+	EXPECT_STREQ(cwd, r);
+}
+
+/*
+ * T is shared and Q, a slave of T, has T moved into it, so Q receives
+ * propagation from its own child. M, another bind mount of the automount, is
+ * on T/options and that is the dentry T sits on in Q. Unmounting M makes T
+ * the propagated victim at that dentry in Q and takes T along. The shrink
+ * walk of V has just unmounted M and continues in the children of T.
+ */
+TEST_F(shrink_submounts, parent_goes_with_child)
+{
+	char v[PATH_LEN], t[PATH_LEN], q[PATH_LEN], p[PATH_LEN];
+	struct stat before, after;
+
+	snprintf(v, sizeof(v), "%s/v", self->base);
+	snprintf(t, sizeof(t), "%s/v/t", self->base);
+	snprintf(q, sizeof(q), "%s/v/q", self->base);
+	ASSERT_EQ(mkdir(v, 0755), 0);
+	ASSERT_EQ(mount("V", v, "tmpfs", 0, NULL), 0);
+	ASSERT_EQ(mount(NULL, v, NULL, MS_PRIVATE, NULL), 0);
+	ASSERT_EQ(stat(v, &before), 0);
+	ASSERT_EQ(mkdir(t, 0755), 0);
+	ASSERT_EQ(mkdir(q, 0755), 0);
+
+	/* T shared, M on T/options before anything receives from T */
+	ASSERT_EQ(mount(self->automount, t, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(NULL, t, NULL, MS_SHARED, NULL), 0);
+	snprintf(p, sizeof(p), "%s/v/t/options", self->base);
+	ASSERT_EQ(mount(self->automount, p, NULL, MS_BIND, NULL), 0);
+
+	/* Q, a slave of T, and T moved into Q at the dentry M sits on */
+	ASSERT_EQ(mount(t, q, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(NULL, q, NULL, MS_SLAVE, NULL), 0);
+	snprintf(p, sizeof(p), "%s/v/q/options", self->base);
+	ASSERT_EQ(mount(t, p, NULL, MS_MOVE, NULL), 0);
+
+	/* M, T and then Q go, V is empty and can be unmounted */
+	ASSERT_EQ(umount2(v, 0), 0);
+	ASSERT_EQ(stat(v, &after), 0);
+	EXPECT_NE(before.st_dev, after.st_dev);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/umount_propagation/umount_propagation_test.c b/tools/testing/selftests/filesystems/umount_propagation/umount_propagation_test.c
new file mode 100644
index 000000000000..9e18d54dfb32
--- /dev/null
+++ b/tools/testing/selftests/filesystems/umount_propagation/umount_propagation_test.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A synchronous umount fails with EBUSY when a mount it would pull out by
+ * propagation is still in use.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/mount.h>
+#include <linux/stat.h>
+
+#include "../../kselftest_harness.h"
+
+#ifndef OPEN_TREE_CLONE
+#define OPEN_TREE_CLONE		1
+#endif
+#ifndef OPEN_TREE_CLOEXEC
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC
+#endif
+#ifndef AT_RECURSIVE
+#define AT_RECURSIVE		0x8000
+#endif
+#ifndef MOVE_MOUNT_F_EMPTY_PATH
+#define MOVE_MOUNT_F_EMPTY_PATH	0x00000004
+#endif
+#ifndef MOVE_MOUNT_BENEATH
+#define MOVE_MOUNT_BENEATH	0x00000200
+#endif
+#ifndef STATX_MNT_ID
+#define STATX_MNT_ID		0x00001000U
+#endif
+
+static int sys_open_tree(int dfd, const char *filename, unsigned int flags)
+{
+	return syscall(__NR_open_tree, dfd, filename, flags);
+}
+
+static int sys_move_mount(int from_dfd, const char *from_pathname,
+			  int to_dfd, const char *to_pathname,
+			  unsigned int flags)
+{
+	return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd,
+		       to_pathname, flags);
+}
+
+/* Child exit codes. */
+enum {
+	CHILD_OK,
+	CHILD_UNSHARE,		/* could not set up the slave namespace */
+	CHILD_OPEN_TREE,	/* open_tree() failed */
+	CHILD_MOVE_MOUNT,	/* move_mount() failed */
+	CHILD_STATX,		/* statx() failed */
+	CHILD_PIPE,		/* the parent went away */
+};
+
+/* Messages between parent and child. */
+enum {
+	MSG_READY = 'r',	/* child: the copy is mounted and referenced */
+	MSG_CHECK = 'c',	/* parent: check that the copy is still attached */
+	MSG_ATTACHED = 'a',	/* child: it is */
+	MSG_DETACHED = 'd',	/* child: it is not */
+	MSG_CLOSE = 'x',	/* parent: drop the reference */
+	MSG_CLOSED = 'y',	/* child: dropped */
+	MSG_EXIT = 'e',		/* parent: done */
+};
+
+FIXTURE(umount_propagation)
+{
+	char base[64];
+	char victim[80];
+	bool mounted;
+};
+
+FIXTURE_SETUP(umount_propagation)
+{
+	self->mounted = false;
+
+	if (geteuid() != 0)
+		SKIP(return, "test requires CAP_SYS_ADMIN");
+
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount("", "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+
+	snprintf(self->base, sizeof(self->base), "/tmp/umount_propagation.XXXXXX");
+	ASSERT_NE(mkdtemp(self->base), NULL);
+	ASSERT_EQ(mount("tmpfs", self->base, "tmpfs", 0, NULL), 0);
+	self->mounted = true;
+	ASSERT_EQ(mount(NULL, self->base, NULL, MS_SHARED, NULL), 0);
+
+	snprintf(self->victim, sizeof(self->victim), "%s/victim", self->base);
+	ASSERT_EQ(mkdir(self->victim, 0755), 0);
+	ASSERT_EQ(mount("tmpfs", self->victim, "tmpfs", 0, NULL), 0);
+}
+
+FIXTURE_TEARDOWN(umount_propagation)
+{
+	if (self->mounted)
+		umount2(self->base, MNT_DETACH);
+	rmdir(self->base);
+}
+
+static int send_msg(int fd, char msg)
+{
+	return write(fd, &msg, 1) == 1 ? 0 : -1;
+}
+
+static char recv_msg(int fd)
+{
+	char msg;
+
+	if (read(fd, &msg, 1) != 1)
+		return 0;
+	return msg;
+}
+
+/* Is the mount with id @mnt_id attached in this mount namespace? */
+static bool mount_attached(__u64 mnt_id)
+{
+	char line[4096];
+	bool found = false;
+	FILE *f;
+
+	f = fopen("/proc/self/mountinfo", "re");
+	if (!f)
+		return false;
+
+	while (fgets(line, sizeof(line), f)) {
+		if (strtoull(line, NULL, 10) == mnt_id) {
+			found = true;
+			break;
+		}
+	}
+	fclose(f);
+	return found;
+}
+
+/*
+ * The slave namespace: take a detached copy of the shared tree and move it
+ * beneath the propagated copy of the victim, keeping the open_tree()
+ * descriptor as a reference on it.
+ */
+static int slave_child(const char *base, const char *victim, int to_parent,
+		       int from_parent)
+{
+	struct statx stx;
+	int fd;
+
+	if (unshare(CLONE_NEWNS))
+		return CHILD_UNSHARE;
+	if (mount("", "/", NULL, MS_REC | MS_SLAVE, NULL))
+		return CHILD_UNSHARE;
+
+	fd = sys_open_tree(AT_FDCWD, base,
+			   OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_RECURSIVE);
+	if (fd < 0)
+		return CHILD_OPEN_TREE;
+	if (sys_move_mount(fd, "", AT_FDCWD, victim,
+			   MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_BENEATH))
+		return CHILD_MOVE_MOUNT;
+	if (statx(fd, "", AT_EMPTY_PATH, STATX_MNT_ID, &stx))
+		return CHILD_STATX;
+
+	if (send_msg(to_parent, MSG_READY) || recv_msg(from_parent) != MSG_CHECK)
+		return CHILD_PIPE;
+	if (send_msg(to_parent, mount_attached(stx.stx_mnt_id) ?
+				MSG_ATTACHED : MSG_DETACHED))
+		return CHILD_PIPE;
+
+	if (recv_msg(from_parent) != MSG_CLOSE)
+		return CHILD_PIPE;
+	close(fd);
+	if (send_msg(to_parent, MSG_CLOSED) || recv_msg(from_parent) != MSG_EXIT)
+		return CHILD_PIPE;
+	return CHILD_OK;
+}
+
+TEST_F(umount_propagation, busy_copy_pulled_out)
+{
+	int to_child[2], to_parent[2];
+	int status;
+	pid_t pid;
+
+	ASSERT_EQ(pipe(to_child), 0);
+	ASSERT_EQ(pipe(to_parent), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		close(to_child[1]);
+		close(to_parent[0]);
+		_exit(slave_child(self->base, self->victim, to_parent[1],
+				  to_child[0]));
+	}
+	close(to_child[0]);
+	close(to_parent[1]);
+
+	ASSERT_EQ(recv_msg(to_parent[0]), MSG_READY);
+
+	/* the copy in the slave namespace is in use */
+	ASSERT_EQ(umount2(self->victim, 0), -1);
+	ASSERT_EQ(errno, EBUSY);
+
+	ASSERT_EQ(send_msg(to_child[1], MSG_CHECK), 0);
+	ASSERT_EQ(recv_msg(to_parent[0]), MSG_ATTACHED);
+
+	/* and once it is not, the umount goes through */
+	ASSERT_EQ(send_msg(to_child[1], MSG_CLOSE), 0);
+	ASSERT_EQ(recv_msg(to_parent[0]), MSG_CLOSED);
+	ASSERT_EQ(umount2(self->victim, 0), 0);
+
+	ASSERT_EQ(send_msg(to_child[1], MSG_EXIT), 0);
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), CHILD_OK);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
index 12434415ec36..9c8fc8c7f62c 100644
--- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
+++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
@@ -146,17 +146,19 @@ static void null_endofword(char *word)
 	*word = '\0';
 }
 
-static bool is_shared_mount(const char *path)
+/* Does the mount on @path carry the optional field @field in mountinfo? */
+static bool mount_has_field(const char *path, const char *field)
 {
 	size_t len = 0;
 	char *line = NULL;
 	FILE *f = NULL;
+	bool found = false;
 
 	f = fopen("/proc/self/mountinfo", "re");
 	if (!f)
 		return false;
 
-	while (getline(&line, &len, f) != -1) {
+	while (!found && getline(&line, &len, f) != -1) {
 		char *opts, *target;
 
 		target = get_field(line, 4);
@@ -172,15 +174,29 @@ static bool is_shared_mount(const char *path)
 		if (strcmp(target, path) != 0)
 			continue;
 
-		null_endofword(opts);
-		if (strstr(opts, "shared:"))
-			return true;
+		/* the optional fields end at the "-" separator */
+		while (opts && *opts != '-') {
+			char *next = strchr(opts, ' ');
+
+			if (next)
+				*next++ = '\0';
+			if (!strncmp(opts, field, strlen(field))) {
+				found = true;
+				break;
+			}
+			opts = next;
+		}
 	}
 
 	free(line);
 	fclose(f);
 
-	return false;
+	return found;
+}
+
+static bool is_shared_mount(const char *path)
+{
+	return mount_has_field(path, "shared:");
 }
 
 /* Attempt to de-conflict with the selftests tree. */
@@ -372,4 +388,50 @@ TEST_F(move_mount_set_group, complex_sharing_copying)
 	ASSERT_EQ(is_shared_mount(SET_GROUP_A), 1);
 }
 
+#define SET_GROUP_B "/tmp/B"
+#define SET_GROUP_C "/tmp/C"
+
+/*
+ * An unbindable mount is neither shared nor a slave, so it must not be
+ * accepted as the target: with a slave source it would end up unbindable
+ * and a slave at the same time.
+ */
+TEST_F(move_mount_set_group, unbindable_target)
+{
+	bool ret;
+
+	ret = move_mount_set_group_supported();
+	ASSERT_GE(ret, 0);
+	if (!ret)
+		SKIP(return, "move_mount(MOVE_MOUNT_SET_GROUP) is not supported");
+
+	ASSERT_EQ(mount(NULL, SET_GROUP_A, NULL, MS_SHARED, 0), 0);
+
+	/* B: a slave of A's peer group */
+	ASSERT_EQ(mkdir(SET_GROUP_B, 0777), 0);
+	ASSERT_EQ(mount(SET_GROUP_A, SET_GROUP_B, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(NULL, SET_GROUP_B, NULL, MS_SLAVE, 0), 0);
+	ASSERT_TRUE(mount_has_field(SET_GROUP_B, "master:"));
+
+	/* C: unbindable */
+	ASSERT_EQ(mkdir(SET_GROUP_C, 0777), 0);
+	ASSERT_EQ(mount(SET_GROUP_A, SET_GROUP_C, NULL, MS_BIND, NULL), 0);
+	ASSERT_EQ(mount(NULL, SET_GROUP_C, NULL, MS_UNBINDABLE, 0), 0);
+	ASSERT_TRUE(mount_has_field(SET_GROUP_C, "unbindable"));
+
+	/* from a slave */
+	ASSERT_EQ(syscall(__NR_move_mount, AT_FDCWD, SET_GROUP_B,
+			  AT_FDCWD, SET_GROUP_C, MOVE_MOUNT_SET_GROUP), -1);
+	ASSERT_EQ(errno, EINVAL);
+	ASSERT_FALSE(mount_has_field(SET_GROUP_C, "master:"));
+	ASSERT_TRUE(mount_has_field(SET_GROUP_C, "unbindable"));
+
+	/* from a shared mount */
+	ASSERT_EQ(syscall(__NR_move_mount, AT_FDCWD, SET_GROUP_A,
+			  AT_FDCWD, SET_GROUP_C, MOVE_MOUNT_SET_GROUP), -1);
+	ASSERT_EQ(errno, EINVAL);
+	ASSERT_FALSE(mount_has_field(SET_GROUP_C, "shared:"));
+	ASSERT_TRUE(mount_has_field(SET_GROUP_C, "unbindable"));
+}
+
 TEST_HARNESS_MAIN