Merge 34e1a5d43c ("Merge tag 'random-6.12-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random") into android-mainline

Steps on the way to 6.12-rc1

Bug: 367265496
Change-Id: I3233ffc3cac200a93cc7c94857d2accad78fa535
Signed-off-by: Matthias Maennich <maennich@google.com>

Documentation/admin-guide/device-mapper/delay.rst

@@ -3,29 +3,52 @@ dm-delay
 ========
 
 Device-Mapper's "delay" target delays reads and/or writes
-and maps them to different devices.
+and/or flushs and optionally maps them to different devices.
 
-Parameters::
+Arguments::
 
     <device> <offset> <delay> [<write_device> <write_offset> <write_delay>
 			       [<flush_device> <flush_offset> <flush_delay>]]
 
-With separate write parameters, the first set is only used for reads.
+Table line has to either have 3, 6 or 9 arguments:
+
+3: apply offset and delay to read, write and flush operations on device
+
+6: apply offset and delay to device, also apply write_offset and write_delay
+   to write and flush operations on optionally different write_device with
+   optionally different sector offset
+
+9: same as 6 arguments plus define flush_offset and flush_delay explicitely
+   on/with optionally different flush_device/flush_offset.
+
 Offsets are specified in sectors.
+
 Delays are specified in milliseconds.
 
+
 Example scripts
 ===============
 
 ::
-
 	#!/bin/sh
-	# Create device delaying rw operation for 500ms
-	echo "0 `blockdev --getsz $1` delay $1 0 500" | dmsetup create delayed
+	#
+	# Create mapped device named "delayed" delaying read, write and flush operations for 500ms.
+	#
+	dmsetup create delayed --table  "0 `blockdev --getsz $1` delay $1 0 500"
 
 ::
-
 	#!/bin/sh
-	# Create device delaying only write operation for 500ms and
-	# splitting reads and writes to different devices $1 $2
-	echo "0 `blockdev --getsz $1` delay $1 0 0 $2 0 500" | dmsetup create delayed
+	#
+	# Create mapped device delaying write and flush operations for 400ms and
+	# splitting reads to device $1 but writes and flushs to different device $2
+	# to different offsets of 2048 and 4096 sectors respectively.
+	#
+	dmsetup create delayed --table "0 `blockdev --getsz $1` delay $1 2048 0 $2 4096 400"
+
+::
+	#!/bin/sh
+	#
+	# Create mapped device delaying reads for 50ms, writes for 100ms and flushs for 333ms
+	# onto the same backing device at offset 0 sectors.
+	#
+	dmsetup create delayed --table "0 `blockdev --getsz $1` delay $1 0 50 $2 0 100 $1 0 333"

Documentation/admin-guide/device-mapper/dm-crypt.rst

@@ -160,6 +160,10 @@ iv_large_sectors
    The <iv_offset> must be multiple of <sector_size> (in 512 bytes units)
    if this flag is specified.
 
+integrity_key_size:<bytes>
+   Use an integrity key of <bytes> size instead of using an integrity key size
+   of the digest size of the used HMAC algorithm.
+
 
 Module parameters::
    max_read_size

Documentation/admin-guide/device-mapper/vdo.rst

@@ -251,7 +251,12 @@ The messages are:
 		by the vdostats userspace program to interpret the output
 		buffer.
 
-        dump:
+	config:
+		Outputs useful vdo configuration information. Mostly used
+		by users who want to recreate a similar VDO volume and
+		want to know the creation configuration used.
+
+	dump:
 		Dumps many internal structures to the system log. This is
 		not always safe to run, so it should only be used to debug
 		a hung vdo. Optional parameters to specify structures to

Documentation/arch/loongarch/irq-chip-model.rst

@@ -85,6 +85,38 @@ to CPUINTC directly::
     | Devices |
     +---------+
 
+Advanced Extended IRQ model
+===========================
+
+In this model, IPI (Inter-Processor Interrupt) and CPU Local Timer interrupt go
+to CPUINTC directly, CPU UARTS interrupts go to LIOINTC, PCH-MSI interrupts go
+to AVECINTC, and then go to CPUINTC directly, while all other devices interrupts
+go to PCH-PIC/PCH-LPC and gathered by EIOINTC, and then go to CPUINTC directly::
+
+ +-----+     +-----------------------+     +-------+
+ | IPI | --> |        CPUINTC        | <-- | Timer |
+ +-----+     +-----------------------+     +-------+
+              ^          ^          ^
+              |          |          |
+       +---------+ +----------+ +---------+     +-------+
+       | EIOINTC | | AVECINTC | | LIOINTC | <-- | UARTs |
+       +---------+ +----------+ +---------+     +-------+
+            ^            ^
+            |            |
+       +---------+  +---------+
+       | PCH-PIC |  | PCH-MSI |
+       +---------+  +---------+
+         ^     ^           ^
+         |     |           |
+ +---------+ +---------+ +---------+
+ | Devices | | PCH-LPC | | Devices |
+ +---------+ +---------+ +---------+
+                  ^
+                  |
+             +---------+
+             | Devices |
+             +---------+
+
 ACPI-related definitions
 ========================
 

Documentation/driver-api/cxl/access-coordinates.rst

@@ -0,0 +1,91 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+==================================
+CXL Access Coordinates Computation
+==================================
+
+Shared Upstream Link Calculation
+================================
+For certain CXL region construction with endpoints behind CXL switches (SW) or
+Root Ports (RP), there is the possibility of the total bandwidth for all
+the endpoints behind a switch being more than the switch upstream link.
+A similar situation can occur within the host, upstream of the root ports.
+The CXL driver performs an additional pass after all the targets have
+arrived for a region in order to recalculate the bandwidths with possible
+upstream link being a limiting factor in mind.
+
+The algorithm assumes the configuration is a symmetric topology as that
+maximizes performance. When asymmetric topology is detected, the calculation
+is aborted. An asymmetric topology is detected during topology walk where the
+number of RPs detected as a grandparent is not equal to the number of devices
+iterated in the same iteration loop. The assumption is made that subtle
+asymmetry in properties does not happen and all paths to EPs are equal.
+
+There can be multiple switches under an RP. There can be multiple RPs under
+a CXL Host Bridge (HB). There can be multiple HBs under a CXL Fixed Memory
+Window Structure (CFMWS).
+
+An example hierarchy:
+
+>                CFMWS 0
+>                  |
+>         _________|_________
+>        |                   |
+>    ACPI0017-0          ACPI0017-1
+> GP0/HB0/ACPI0016-0   GP1/HB1/ACPI0016-1
+>    |          |        |           |
+>   RP0        RP1      RP2         RP3
+>    |          |        |           |
+>  SW 0       SW 1     SW 2        SW 3
+>  |   |      |   |    |   |       |   |
+> EP0 EP1    EP2 EP3  EP4  EP5    EP6 EP7
+
+Computation for the example hierarchy:
+
+Min (GP0 to CPU BW,
+     Min(SW 0 Upstream Link to RP0 BW,
+         Min(SW0SSLBIS for SW0DSP0 (EP0), EP0 DSLBIS, EP0 Upstream Link) +
+         Min(SW0SSLBIS for SW0DSP1 (EP1), EP1 DSLBIS, EP1 Upstream link)) +
+     Min(SW 1 Upstream Link to RP1 BW,
+         Min(SW1SSLBIS for SW1DSP0 (EP2), EP2 DSLBIS, EP2 Upstream Link) +
+         Min(SW1SSLBIS for SW1DSP1 (EP3), EP3 DSLBIS, EP3 Upstream link))) +
+Min (GP1 to CPU BW,
+     Min(SW 2 Upstream Link to RP2 BW,
+         Min(SW2SSLBIS for SW2DSP0 (EP4), EP4 DSLBIS, EP4 Upstream Link) +
+         Min(SW2SSLBIS for SW2DSP1 (EP5), EP5 DSLBIS, EP5 Upstream link)) +
+     Min(SW 3 Upstream Link to RP3 BW,
+         Min(SW3SSLBIS for SW3DSP0 (EP6), EP6 DSLBIS, EP6 Upstream Link) +
+         Min(SW3SSLBIS for SW3DSP1 (EP7), EP7 DSLBIS, EP7 Upstream link))))
+
+The calculation starts at cxl_region_shared_upstream_perf_update(). A xarray
+is created to collect all the endpoint bandwidths via the
+cxl_endpoint_gather_bandwidth() function. The min() of bandwidth from the
+endpoint CDAT and the upstream link bandwidth is calculated. If the endpoint
+has a CXL switch as a parent, then min() of calculated bandwidth and the
+bandwidth from the SSLBIS for the switch downstream port that is associated
+with the endpoint is calculated. The final bandwidth is stored in a
+'struct cxl_perf_ctx' in the xarray indexed by a device pointer. If the
+endpoint is direct attached to a root port (RP), the device pointer would be an
+RP device. If the endpoint is behind a switch, the device pointer would be the
+upstream device of the parent switch.
+
+At the next stage, the code walks through one or more switches if they exist
+in the topology. For endpoints directly attached to RPs, this step is skipped.
+If there is another switch upstream, the code takes the min() of the current
+gathered bandwidth and the upstream link bandwidth. If there's a switch
+upstream, then the SSLBIS of the upstream switch.
+
+Once the topology walk reaches the RP, whether it's direct attached endpoints
+or walking through the switch(es), cxl_rp_gather_bandwidth() is called. At
+this point all the bandwidths are aggregated per each host bridge, which is
+also the index for the resulting xarray.
+
+The next step is to take the min() of the per host bridge bandwidth and the
+bandwidth from the Generic Port (GP). The bandwidths for the GP is retrieved
+via ACPI tables SRAT/HMAT. The min bandwidth are aggregated under the same
+ACPI0017 device to form a new xarray.
+
+Finally, the cxl_region_update_bandwidth() is called and the aggregated
+bandwidth from all the members of the last xarray is updated for the
+access coordinates residing in the cxl region (cxlr) context.

Documentation/driver-api/cxl/index.rst

@@ -8,6 +8,7 @@ Compute Express Link
    :maxdepth: 1
 
    memory-devices
+   access-coordinates
 
    maturity-map
 

Documentation/translations/zh_CN/arch/loongarch/irq-chip-model.rst

@@ -87,6 +87,38 @@ PCH-LPC/PCH-MSI，然后被EIOINTC统一收集，再直接到达CPUINTC::
     | Devices |
     +---------+
 
+高级扩展IRQ模型
+===============
+
+在这种模型里面，IPI（Inter-Processor Interrupt）和CPU本地时钟中断直接发送到CPUINTC，
+CPU串口（UARTs）中断发送到LIOINTC，PCH-MSI中断发送到AVECINTC，而后通过AVECINTC直接
+送达CPUINTC，而其他所有设备的中断则分别发送到所连接的PCH-PIC/PCH-LPC，然后由EIOINTC
+统一收集，再直接到达CPUINTC::
+
+ +-----+     +-----------------------+     +-------+
+ | IPI | --> |        CPUINTC        | <-- | Timer |
+ +-----+     +-----------------------+     +-------+
+              ^          ^          ^
+              |          |          |
+       +---------+ +----------+ +---------+     +-------+
+       | EIOINTC | | AVECINTC | | LIOINTC | <-- | UARTs |
+       +---------+ +----------+ +---------+     +-------+
+            ^            ^
+            |            |
+       +---------+  +---------+
+       | PCH-PIC |  | PCH-MSI |
+       +---------+  +---------+
+         ^     ^           ^
+         |     |           |
+ +---------+ +---------+ +---------+
+ | Devices | | PCH-LPC | | Devices |
+ +---------+ +---------+ +---------+
+                  ^
+                  |
+             +---------+
+             | Devices |
+             +---------+
+
 ACPI相关的定义
 ==============
 

MAINTAINERS

@@ -5728,8 +5728,7 @@ L:	linux-cxl@vger.kernel.org
 S:	Maintained
 F:	Documentation/driver-api/cxl
 F:	drivers/cxl/
-F:	include/linux/einj-cxl.h
-F:	include/linux/cxl-event.h
+F:	include/cxl/
 F:	include/uapi/linux/cxl_mem.h
 F:	tools/testing/cxl/
 
@@ -19352,10 +19351,7 @@ F:	drivers/char/random.c
 F:	include/linux/random.h
 F:	include/uapi/linux/random.h
 F:	drivers/virt/vmgenid.c
-F:	include/vdso/getrandom.h
-F:	lib/vdso/getrandom.c
-F:	arch/x86/entry/vdso/vgetrandom*
-F:	arch/x86/include/asm/vdso/getrandom*
+N:	^.*/vdso/[^/]*getrandom[^/]+$
 
 RAPIDIO SUBSYSTEM
 M:	Matt Porter <mporter@kernel.crashing.org>

arch/loongarch/Kconfig

@@ -25,6 +25,8 @@ config LOONGARCH
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
@@ -82,6 +84,7 @@ config LOONGARCH
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_DEVICES
+	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY
 	select GENERIC_IOREMAP if !ARCH_IOREMAP
@@ -147,7 +150,7 @@ config LOONGARCH
 	select HAVE_LIVEPATCH
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
-	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB && !CC_IS_CLANG
+	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -267,7 +270,7 @@ config AS_HAS_FCSR_CLASS
 	def_bool $(as-instr,movfcsr2gr \$t0$(comma)\$fcsr0)
 
 config AS_HAS_THIN_ADD_SUB
-	def_bool $(cc-option,-Wa$(comma)-mthin-add-sub)
+	def_bool $(cc-option,-Wa$(comma)-mthin-add-sub) || AS_IS_LLVM
 
 config AS_HAS_LSX_EXTENSION
 	def_bool $(as-instr,vld \$vr0$(comma)\$a0$(comma)0)

arch/loongarch/include/asm/atomic.h

@@ -15,6 +15,7 @@
 #define __LL		"ll.w	"
 #define __SC		"sc.w	"
 #define __AMADD		"amadd.w	"
+#define __AMOR		"amor.w		"
 #define __AMAND_DB	"amand_db.w	"
 #define __AMOR_DB	"amor_db.w	"
 #define __AMXOR_DB	"amxor_db.w	"
@@ -22,6 +23,7 @@
 #define __LL		"ll.d	"
 #define __SC		"sc.d	"
 #define __AMADD		"amadd.d	"
+#define __AMOR		"amor.d		"
 #define __AMAND_DB	"amand_db.d	"
 #define __AMOR_DB	"amor_db.d	"
 #define __AMXOR_DB	"amxor_db.d	"

arch/loongarch/include/asm/cpu-features.h

@@ -51,6 +51,7 @@
 #define cpu_has_lbt_mips	cpu_opt(LOONGARCH_CPU_LBT_MIPS)
 #define cpu_has_lbt		(cpu_has_lbt_x86|cpu_has_lbt_arm|cpu_has_lbt_mips)
 #define cpu_has_csr		cpu_opt(LOONGARCH_CPU_CSR)
+#define cpu_has_iocsr		cpu_opt(LOONGARCH_CPU_IOCSR)
 #define cpu_has_tlb		cpu_opt(LOONGARCH_CPU_TLB)
 #define cpu_has_watch		cpu_opt(LOONGARCH_CPU_WATCH)
 #define cpu_has_vint		cpu_opt(LOONGARCH_CPU_VINT)
@@ -65,6 +66,7 @@
 #define cpu_has_guestid		cpu_opt(LOONGARCH_CPU_GUESTID)
 #define cpu_has_hypervisor	cpu_opt(LOONGARCH_CPU_HYPERVISOR)
 #define cpu_has_ptw		cpu_opt(LOONGARCH_CPU_PTW)
+#define cpu_has_lspw		cpu_opt(LOONGARCH_CPU_LSPW)
 #define cpu_has_avecint		cpu_opt(LOONGARCH_CPU_AVECINT)
 
 #endif /* __ASM_CPU_FEATURES_H */

arch/loongarch/include/asm/cpu.h

@@ -87,19 +87,21 @@ enum cpu_type_enum {
 #define CPU_FEATURE_LBT_MIPS		12	/* CPU has MIPS Binary Translation */
 #define CPU_FEATURE_TLB			13	/* CPU has TLB */
 #define CPU_FEATURE_CSR			14	/* CPU has CSR */
-#define CPU_FEATURE_WATCH		15	/* CPU has watchpoint registers */
-#define CPU_FEATURE_VINT		16	/* CPU has vectored interrupts */
-#define CPU_FEATURE_CSRIPI		17	/* CPU has CSR-IPI */
-#define CPU_FEATURE_EXTIOI		18	/* CPU has EXT-IOI */
-#define CPU_FEATURE_PREFETCH		19	/* CPU has prefetch instructions */
-#define CPU_FEATURE_PMP			20	/* CPU has perfermance counter */
-#define CPU_FEATURE_SCALEFREQ		21	/* CPU supports cpufreq scaling */
-#define CPU_FEATURE_FLATMODE		22	/* CPU has flat mode */
-#define CPU_FEATURE_EIODECODE		23	/* CPU has EXTIOI interrupt pin decode mode */
-#define CPU_FEATURE_GUESTID		24	/* CPU has GuestID feature */
-#define CPU_FEATURE_HYPERVISOR		25	/* CPU has hypervisor (running in VM) */
-#define CPU_FEATURE_PTW			26	/* CPU has hardware page table walker */
-#define CPU_FEATURE_AVECINT		27	/* CPU has avec interrupt */
+#define CPU_FEATURE_IOCSR		15	/* CPU has IOCSR */
+#define CPU_FEATURE_WATCH		16	/* CPU has watchpoint registers */
+#define CPU_FEATURE_VINT		17	/* CPU has vectored interrupts */
+#define CPU_FEATURE_CSRIPI		18	/* CPU has CSR-IPI */
+#define CPU_FEATURE_EXTIOI		19	/* CPU has EXT-IOI */
+#define CPU_FEATURE_PREFETCH		20	/* CPU has prefetch instructions */
+#define CPU_FEATURE_PMP			21	/* CPU has perfermance counter */
+#define CPU_FEATURE_SCALEFREQ		22	/* CPU supports cpufreq scaling */
+#define CPU_FEATURE_FLATMODE		23	/* CPU has flat mode */
+#define CPU_FEATURE_EIODECODE		24	/* CPU has EXTIOI interrupt pin decode mode */
+#define CPU_FEATURE_GUESTID		25	/* CPU has GuestID feature */
+#define CPU_FEATURE_HYPERVISOR		26	/* CPU has hypervisor (running in VM) */
+#define CPU_FEATURE_PTW			27	/* CPU has hardware page table walker */
+#define CPU_FEATURE_LSPW		28	/* CPU has LSPW (lddir/ldpte instructions) */
+#define CPU_FEATURE_AVECINT		29	/* CPU has AVEC interrupt */
 
 #define LOONGARCH_CPU_CPUCFG		BIT_ULL(CPU_FEATURE_CPUCFG)
 #define LOONGARCH_CPU_LAM		BIT_ULL(CPU_FEATURE_LAM)
@@ -115,6 +117,7 @@ enum cpu_type_enum {
 #define LOONGARCH_CPU_LBT_ARM		BIT_ULL(CPU_FEATURE_LBT_ARM)
 #define LOONGARCH_CPU_LBT_MIPS		BIT_ULL(CPU_FEATURE_LBT_MIPS)
 #define LOONGARCH_CPU_TLB		BIT_ULL(CPU_FEATURE_TLB)
+#define LOONGARCH_CPU_IOCSR		BIT_ULL(CPU_FEATURE_IOCSR)
 #define LOONGARCH_CPU_CSR		BIT_ULL(CPU_FEATURE_CSR)
 #define LOONGARCH_CPU_WATCH		BIT_ULL(CPU_FEATURE_WATCH)
 #define LOONGARCH_CPU_VINT		BIT_ULL(CPU_FEATURE_VINT)
@@ -128,6 +131,7 @@ enum cpu_type_enum {
 #define LOONGARCH_CPU_GUESTID		BIT_ULL(CPU_FEATURE_GUESTID)
 #define LOONGARCH_CPU_HYPERVISOR	BIT_ULL(CPU_FEATURE_HYPERVISOR)
 #define LOONGARCH_CPU_PTW		BIT_ULL(CPU_FEATURE_PTW)
+#define LOONGARCH_CPU_LSPW		BIT_ULL(CPU_FEATURE_LSPW)
 #define LOONGARCH_CPU_AVECINT		BIT_ULL(CPU_FEATURE_AVECINT)
 
 #endif /* _ASM_CPU_H */

arch/loongarch/include/asm/loongarch.h

@@ -62,6 +62,7 @@
 #define LOONGARCH_CPUCFG1		0x1
 #define  CPUCFG1_ISGR32			BIT(0)
 #define  CPUCFG1_ISGR64			BIT(1)
+#define  CPUCFG1_ISA			GENMASK(1, 0)
 #define  CPUCFG1_PAGING			BIT(2)
 #define  CPUCFG1_IOCSR			BIT(3)
 #define  CPUCFG1_PABITS			GENMASK(11, 4)

arch/loongarch/include/asm/mmu_context.h

@@ -49,12 +49,12 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 
 /* Normal, classic get_new_mmu_context */
 static inline void
-get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
+get_new_mmu_context(struct mm_struct *mm, unsigned long cpu, bool *need_flush)
 {
 	u64 asid = asid_cache(cpu);
 
 	if (!((++asid) & cpu_asid_mask(&cpu_data[cpu])))
-		local_flush_tlb_user();	/* start new asid cycle */
+		*need_flush = true;	/* start new asid cycle */
 
 	cpu_context(cpu, mm) = asid_cache(cpu) = asid;
 }
@@ -74,21 +74,34 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	return 0;
 }
 
+static inline void atomic_update_pgd_asid(unsigned long asid, unsigned long pgdl)
+{
+	__asm__ __volatile__(
+	"csrwr %[pgdl_val], %[pgdl_reg] \n\t"
+	"csrwr %[asid_val], %[asid_reg] \n\t"
+	: [asid_val] "+r" (asid), [pgdl_val] "+r" (pgdl)
+	: [asid_reg] "i" (LOONGARCH_CSR_ASID), [pgdl_reg] "i" (LOONGARCH_CSR_PGDL)
+	: "memory"
+	);
+}
+
 static inline void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 				      struct task_struct *tsk)
 {
+	bool need_flush = false;
 	unsigned int cpu = smp_processor_id();
 
 	/* Check if our ASID is of an older version and thus invalid */
 	if (!asid_valid(next, cpu))
-		get_new_mmu_context(next, cpu);
-
-	write_csr_asid(cpu_asid(cpu, next));
+		get_new_mmu_context(next, cpu, &need_flush);
 
 	if (next != &init_mm)
-		csr_write64((unsigned long)next->pgd, LOONGARCH_CSR_PGDL);
+		atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)next->pgd);
 	else
-		csr_write64((unsigned long)invalid_pg_dir, LOONGARCH_CSR_PGDL);
+		atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)invalid_pg_dir);
+
+	if (need_flush)
+		local_flush_tlb_user(); /* Flush tlb after update ASID */
 
 	/*
 	 * Mark current->active_mm as not "active" anymore.
@@ -135,9 +148,15 @@ drop_mmu_context(struct mm_struct *mm, unsigned int cpu)
 	asid = read_csr_asid() & cpu_asid_mask(&current_cpu_data);
 
 	if (asid == cpu_asid(cpu, mm)) {
+		bool need_flush = false;
+
 		if (!current->mm || (current->mm == mm)) {
-			get_new_mmu_context(mm, cpu);
+			get_new_mmu_context(mm, cpu, &need_flush);
+
 			write_csr_asid(cpu_asid(cpu, mm));
+			if (need_flush)
+				local_flush_tlb_user(); /* Flush tlb after update ASID */
+
 			goto out;
 		}
 	}

arch/loongarch/include/asm/percpu.h

@@ -68,75 +68,6 @@ PERCPU_OP(and, and, &)
 PERCPU_OP(or, or, |)
 #undef PERCPU_OP
 
-static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size)
-{
-	unsigned long ret;
-
-	switch (size) {
-	case 1:
-		__asm__ __volatile__ ("ldx.b %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	case 2:
-		__asm__ __volatile__ ("ldx.h %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	case 4:
-		__asm__ __volatile__ ("ldx.w %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	case 8:
-		__asm__ __volatile__ ("ldx.d %[ret], $r21, %[ptr]	\n"
-		: [ret] "=&r"(ret)
-		: [ptr] "r"(ptr)
-		: "memory");
-		break;
-	default:
-		ret = 0;
-		BUILD_BUG();
-	}
-
-	return ret;
-}
-
-static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size)
-{
-	switch (size) {
-	case 1:
-		__asm__ __volatile__("stx.b %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	case 2:
-		__asm__ __volatile__("stx.h %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	case 4:
-		__asm__ __volatile__("stx.w %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	case 8:
-		__asm__ __volatile__("stx.d %[val], $r21, %[ptr]	\n"
-		:
-		: [val] "r" (val), [ptr] "r" (ptr)
-		: "memory");
-		break;
-	default:
-		BUILD_BUG();
-	}
-}
-
 static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
@@ -157,6 +88,33 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 	return 0;
 }
 
+#define __pcpu_op_1(op)		op ".b "
+#define __pcpu_op_2(op)		op ".h "
+#define __pcpu_op_4(op)		op ".w "
+#define __pcpu_op_8(op)		op ".d "
+
+#define _percpu_read(size, _pcp)					\
+({									\
+	typeof(_pcp) __pcp_ret;						\
+									\
+	__asm__ __volatile__(						\
+		__pcpu_op_##size("ldx") "%[ret], $r21, %[ptr]	\n"	\
+		: [ret] "=&r"(__pcp_ret)				\
+		: [ptr] "r"(&(_pcp))					\
+		: "memory");						\
+									\
+	__pcp_ret;							\
+})
+
+#define _percpu_write(size, _pcp, _val)					\
+do {									\
+	__asm__ __volatile__(						\
+		__pcpu_op_##size("stx") "%[val], $r21, %[ptr]	\n"	\
+		:							\
+		: [val] "r"(_val), [ptr] "r"(&(_pcp))			\
+		: "memory");						\
+} while (0)
+
 /* this_cpu_cmpxchg */
 #define _protect_cmpxchg_local(pcp, o, n)			\
 ({								\
@@ -167,18 +125,6 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 	__ret;							\
 })
 
-#define _percpu_read(pcp)						\
-({									\
-	typeof(pcp) __retval;						\
-	__retval = (typeof(pcp))__percpu_read(&(pcp), sizeof(pcp));	\
-	__retval;							\
-})
-
-#define _percpu_write(pcp, val)						\
-do {									\
-	__percpu_write(&(pcp), (unsigned long)(val), sizeof(pcp));	\
-} while (0)								\
-
 #define _pcp_protect(operation, pcp, val)			\
 ({								\
 	typeof(pcp) __retval;					\
@@ -215,15 +161,15 @@ do {									\
 #define this_cpu_or_4(pcp, val) _percpu_or(pcp, val)
 #define this_cpu_or_8(pcp, val) _percpu_or(pcp, val)
 
-#define this_cpu_read_1(pcp) _percpu_read(pcp)
-#define this_cpu_read_2(pcp) _percpu_read(pcp)
-#define this_cpu_read_4(pcp) _percpu_read(pcp)
-#define this_cpu_read_8(pcp) _percpu_read(pcp)
+#define this_cpu_read_1(pcp) _percpu_read(1, pcp)
+#define this_cpu_read_2(pcp) _percpu_read(2, pcp)
+#define this_cpu_read_4(pcp) _percpu_read(4, pcp)
+#define this_cpu_read_8(pcp) _percpu_read(8, pcp)
 
-#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val)
-#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val)
-#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val)
-#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_1(pcp, val) _percpu_write(1, pcp, val)
+#define this_cpu_write_2(pcp, val) _percpu_write(2, pcp, val)
+#define this_cpu_write_4(pcp, val) _percpu_write(4, pcp, val)
+#define this_cpu_write_8(pcp, val) _percpu_write(8, pcp, val)
 
 #define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val)
 #define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val)

arch/loongarch/include/asm/pgtable.h

@@ -331,29 +331,23 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+		if (pte_none(ptep_get(buddy))) {
 #ifdef CONFIG_SMP
-		/*
-		 * For SMP, multiple CPUs can race, so we need to do
-		 * this atomically.
-		 */
-		unsigned long page_global = _PAGE_GLOBAL;
-		unsigned long tmp;
+			/*
+			 * For SMP, multiple CPUs can race, so we need
+			 * to do this atomically.
+			 */
+			__asm__ __volatile__(
+			__AMOR "$zero, %[global], %[buddy] \n"
+			: [buddy] "+ZB" (buddy->pte)
+			: [global] "r" (_PAGE_GLOBAL)
+			: "memory");
 
-		__asm__ __volatile__ (
-		"1:"	__LL	"%[tmp], %[buddy]		\n"
-		"	bnez	%[tmp], 2f			\n"
-		"	 or	%[tmp], %[tmp], %[global]	\n"
-			__SC	"%[tmp], %[buddy]		\n"
-		"	beqz	%[tmp], 1b			\n"
-		"	nop					\n"
-		"2:						\n"
-		__WEAK_LLSC_MB
-		: [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
-		: [global] "r" (page_global));
+			DBAR(0b11000); /* o_wrw = 0b11000 */
 #else /* !CONFIG_SMP */
-		if (pte_none(ptep_get(buddy)))
 			WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL));
 #endif /* CONFIG_SMP */
+		}
 	}
 }
 

arch/loongarch/include/asm/set_memory.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2024 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_LOONGARCH_SET_MEMORY_H
+#define _ASM_LOONGARCH_SET_MEMORY_H
+
+/*
+ * Functions to change memory attributes.
+ */
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+
+bool kernel_page_present(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+int set_direct_map_invalid_noflush(struct page *page);
+
+#endif /* _ASM_LOONGARCH_SET_MEMORY_H */

arch/loongarch/include/uapi/asm/hwcap.h

@@ -17,5 +17,6 @@
 #define HWCAP_LOONGARCH_LBT_ARM		(1 << 11)
 #define HWCAP_LOONGARCH_LBT_MIPS	(1 << 12)
 #define HWCAP_LOONGARCH_PTW		(1 << 13)
+#define HWCAP_LOONGARCH_LSPW		(1 << 14)
 
 #endif /* _UAPI_ASM_HWCAP_H */

arch/loongarch/include/uapi/asm/sigcontext.h

@@ -9,7 +9,6 @@
 #define _UAPI_ASM_SIGCONTEXT_H
 
 #include <linux/types.h>
-#include <linux/posix_types.h>
 
 /* FP context was used */
 #define SC_USED_FP		(1 << 0)

arch/loongarch/kernel/acpi.c

@@ -9,6 +9,7 @@
 
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/efi-bgrt.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/memblock.h>
@@ -212,6 +213,9 @@ void __init acpi_boot_table_init(void)
 	/* Do not enable ACPI SPCR console by default */
 	acpi_parse_spcr(earlycon_acpi_spcr_enable, false);
 
+	if (IS_ENABLED(CONFIG_ACPI_BGRT))
+		acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
+
 	return;
 
 fdt_earlycon:

arch/loongarch/kernel/cpu-probe.c

@@ -91,12 +91,30 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 	unsigned int config;
 	unsigned long asid_mask;
 
-	c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR |
-		     LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH;
+	c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | LOONGARCH_CPU_VINT;
 
 	elf_hwcap = HWCAP_LOONGARCH_CPUCFG;
 
 	config = read_cpucfg(LOONGARCH_CPUCFG1);
+
+	switch (config & CPUCFG1_ISA) {
+	case 0:
+		set_isa(c, LOONGARCH_CPU_ISA_LA32R);
+		break;
+	case 1:
+		set_isa(c, LOONGARCH_CPU_ISA_LA32S);
+		break;
+	case 2:
+		set_isa(c, LOONGARCH_CPU_ISA_LA64);
+		break;
+	default:
+		pr_warn("Warning: unknown ISA level\n");
+	}
+
+	if (config & CPUCFG1_PAGING)
+		c->options |= LOONGARCH_CPU_TLB;
+	if (config & CPUCFG1_IOCSR)
+		c->options |= LOONGARCH_CPU_IOCSR;
 	if (config & CPUCFG1_UAL) {
 		c->options |= LOONGARCH_CPU_UAL;
 		elf_hwcap |= HWCAP_LOONGARCH_UAL;
@@ -139,6 +157,10 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 		c->options |= LOONGARCH_CPU_PTW;
 		elf_hwcap |= HWCAP_LOONGARCH_PTW;
 	}
+	if (config & CPUCFG2_LSPW) {
+		c->options |= LOONGARCH_CPU_LSPW;
+		elf_hwcap |= HWCAP_LOONGARCH_LSPW;
+	}
 	if (config & CPUCFG2_LVZP) {
 		c->options |= LOONGARCH_CPU_LVZ;
 		elf_hwcap |= HWCAP_LOONGARCH_LVZ;
@@ -162,22 +184,6 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 	if (config & CPUCFG6_PMP)
 		c->options |= LOONGARCH_CPU_PMP;
 
-	config = iocsr_read32(LOONGARCH_IOCSR_FEATURES);
-	if (config & IOCSRF_CSRIPI)
-		c->options |= LOONGARCH_CPU_CSRIPI;
-	if (config & IOCSRF_EXTIOI)
-		c->options |= LOONGARCH_CPU_EXTIOI;
-	if (config & IOCSRF_FREQSCALE)
-		c->options |= LOONGARCH_CPU_SCALEFREQ;
-	if (config & IOCSRF_FLATMODE)
-		c->options |= LOONGARCH_CPU_FLATMODE;
-	if (config & IOCSRF_EIODECODE)
-		c->options |= LOONGARCH_CPU_EIODECODE;
-	if (config & IOCSRF_AVEC)
-		c->options |= LOONGARCH_CPU_AVECINT;
-	if (config & IOCSRF_VM)
-		c->options |= LOONGARCH_CPU_HYPERVISOR;
-
 	config = csr_read32(LOONGARCH_CSR_ASID);
 	config = (config & CSR_ASID_BIT) >> CSR_ASID_BIT_SHIFT;
 	asid_mask = GENMASK(config - 1, 0);
@@ -210,6 +216,9 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 	default:
 		pr_warn("Warning: unknown TLB type\n");
 	}
+
+	if (get_num_brps() + get_num_wrps())
+		c->options |= LOONGARCH_CPU_WATCH;
 }
 
 #define MAX_NAME_LEN	32
@@ -220,8 +229,45 @@ static char cpu_full_name[MAX_NAME_LEN] = "        -        ";
 
 static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int cpu)
 {
+	uint32_t config;
 	uint64_t *vendor = (void *)(&cpu_full_name[VENDOR_OFFSET]);
 	uint64_t *cpuname = (void *)(&cpu_full_name[CPUNAME_OFFSET]);
+	const char *core_name = "Unknown";
+
+	switch (BIT(fls(c->isa_level) - 1)) {
+	case LOONGARCH_CPU_ISA_LA32R:
+	case LOONGARCH_CPU_ISA_LA32S:
+		c->cputype = CPU_LOONGSON32;
+		__cpu_family[cpu] = "Loongson-32bit";
+		break;
+	case LOONGARCH_CPU_ISA_LA64:
+		c->cputype = CPU_LOONGSON64;
+		__cpu_family[cpu] = "Loongson-64bit";
+		break;
+	}
+
+	switch (c->processor_id & PRID_SERIES_MASK) {
+	case PRID_SERIES_LA132:
+		core_name = "LA132";
+		break;
+	case PRID_SERIES_LA264:
+		core_name = "LA264";
+		break;
+	case PRID_SERIES_LA364:
+		core_name = "LA364";
+		break;
+	case PRID_SERIES_LA464:
+		core_name = "LA464";
+		break;
+	case PRID_SERIES_LA664:
+		core_name = "LA664";
+		break;
+	}
+
+	pr_info("%s Processor probed (%s Core)\n", __cpu_family[cpu], core_name);
+
+	if (!cpu_has_iocsr)
+		return;
 
 	if (!__cpu_full_name[cpu])
 		__cpu_full_name[cpu] = cpu_full_name;
@@ -229,43 +275,21 @@ static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int
 	*vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR);
 	*cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME);
 
-	switch (c->processor_id & PRID_SERIES_MASK) {
-	case PRID_SERIES_LA132:
-		c->cputype = CPU_LOONGSON32;
-		set_isa(c, LOONGARCH_CPU_ISA_LA32S);
-		__cpu_family[cpu] = "Loongson-32bit";
-		pr_info("32-bit Loongson Processor probed (LA132 Core)\n");
-		break;
-	case PRID_SERIES_LA264:
-		c->cputype = CPU_LOONGSON64;
-		set_isa(c, LOONGARCH_CPU_ISA_LA64);
-		__cpu_family[cpu] = "Loongson-64bit";
-		pr_info("64-bit Loongson Processor probed (LA264 Core)\n");
-		break;
-	case PRID_SERIES_LA364:
-		c->cputype = CPU_LOONGSON64;
-		set_isa(c, LOONGARCH_CPU_ISA_LA64);
-		__cpu_family[cpu] = "Loongson-64bit";
-		pr_info("64-bit Loongson Processor probed (LA364 Core)\n");
-		break;
-	case PRID_SERIES_LA464:
-		c->cputype = CPU_LOONGSON64;
-		set_isa(c, LOONGARCH_CPU_ISA_LA64);
-		__cpu_family[cpu] = "Loongson-64bit";
-		pr_info("64-bit Loongson Processor probed (LA464 Core)\n");
-		break;
-	case PRID_SERIES_LA664:
-		c->cputype = CPU_LOONGSON64;
-		set_isa(c, LOONGARCH_CPU_ISA_LA64);
-		__cpu_family[cpu] = "Loongson-64bit";
-		pr_info("64-bit Loongson Processor probed (LA664 Core)\n");
-		break;
-	default: /* Default to 64 bit */
-		c->cputype = CPU_LOONGSON64;
-		set_isa(c, LOONGARCH_CPU_ISA_LA64);
-		__cpu_family[cpu] = "Loongson-64bit";
-		pr_info("64-bit Loongson Processor probed (Unknown Core)\n");
-	}
+	config = iocsr_read32(LOONGARCH_IOCSR_FEATURES);
+	if (config & IOCSRF_CSRIPI)
+		c->options |= LOONGARCH_CPU_CSRIPI;
+	if (config & IOCSRF_EXTIOI)
+		c->options |= LOONGARCH_CPU_EXTIOI;
+	if (config & IOCSRF_FREQSCALE)
+		c->options |= LOONGARCH_CPU_SCALEFREQ;
+	if (config & IOCSRF_FLATMODE)
+		c->options |= LOONGARCH_CPU_FLATMODE;
+	if (config & IOCSRF_EIODECODE)
+		c->options |= LOONGARCH_CPU_EIODECODE;
+	if (config & IOCSRF_AVEC)
+		c->options |= LOONGARCH_CPU_AVECINT;
+	if (config & IOCSRF_VM)
+		c->options |= LOONGARCH_CPU_HYPERVISOR;
 }
 
 #ifdef CONFIG_64BIT

arch/loongarch/kernel/proc.c

@@ -31,6 +31,7 @@ int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v)
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	unsigned long n = (unsigned long) v - 1;
+	unsigned int isa = cpu_data[n].isa_level;
 	unsigned int version = cpu_data[n].processor_id & 0xff;
 	unsigned int fp_version = cpu_data[n].fpu_vers;
 	struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args;
@@ -64,9 +65,11 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		      cpu_pabits + 1, cpu_vabits + 1);
 
 	seq_printf(m, "ISA\t\t\t:");
-	if (cpu_has_loongarch32)
-		seq_printf(m, " loongarch32");
-	if (cpu_has_loongarch64)
+	if (isa & LOONGARCH_CPU_ISA_LA32R)
+		seq_printf(m, " loongarch32r");
+	if (isa & LOONGARCH_CPU_ISA_LA32S)
+		seq_printf(m, " loongarch32s");
+	if (isa & LOONGARCH_CPU_ISA_LA64)
 		seq_printf(m, " loongarch64");
 	seq_printf(m, "\n");
 
@@ -81,6 +84,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (cpu_has_complex)	seq_printf(m, " complex");
 	if (cpu_has_crypto)	seq_printf(m, " crypto");
 	if (cpu_has_ptw)	seq_printf(m, " ptw");
+	if (cpu_has_lspw)	seq_printf(m, " lspw");
 	if (cpu_has_lvz)	seq_printf(m, " lvz");
 	if (cpu_has_lbt_x86)	seq_printf(m, " lbt_x86");
 	if (cpu_has_lbt_arm)	seq_printf(m, " lbt_arm");

arch/loongarch/kernel/syscall.c

@@ -79,7 +79,3 @@ void noinstr __no_stack_protector do_syscall(struct pt_regs *regs)
 
 	syscall_exit_to_user_mode(regs);
 }
-
-#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
-STACK_FRAME_NON_STANDARD(do_syscall);
-#endif

arch/loongarch/mm/Makefile

@@ -4,7 +4,8 @@
 #
 
 obj-y				+= init.o cache.o tlb.o tlbex.o extable.o \
-				   fault.o ioremap.o maccess.o mmap.o pgtable.o page.o
+				   fault.o ioremap.o maccess.o mmap.o pgtable.o \
+				   page.o pageattr.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_KASAN)		+= kasan_init.o

arch/loongarch/mm/fault.c

@@ -31,11 +31,52 @@
 
 int show_unhandled_signals = 1;
 
+static int __kprobes spurious_fault(unsigned long write, unsigned long address)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if (!(address & __UA_LIMIT))
+		return 0;
+
+	pgd = pgd_offset_k(address);
+	if (!pgd_present(pgdp_get(pgd)))
+		return 0;
+
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(p4dp_get(p4d)))
+		return 0;
+
+	pud = pud_offset(p4d, address);
+	if (!pud_present(pudp_get(pud)))
+		return 0;
+
+	pmd = pmd_offset(pud, address);
+	if (!pmd_present(pmdp_get(pmd)))
+		return 0;
+
+	if (pmd_leaf(*pmd)) {
+		return write ? pmd_write(pmdp_get(pmd)) : 1;
+	} else {
+		pte = pte_offset_kernel(pmd, address);
+		if (!pte_present(ptep_get(pte)))
+			return 0;
+
+		return write ? pte_write(ptep_get(pte)) : 1;
+	}
+}
+
 static void __kprobes no_context(struct pt_regs *regs,
 			unsigned long write, unsigned long address)
 {
 	const int field = sizeof(unsigned long) * 2;
 
+	if (spurious_fault(write, address))
+		return;
+
 	/* Are we prepared to handle this kernel fault?	 */
 	if (fixup_exception(regs))
 		return;

arch/loongarch/mm/pageattr.c

@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Loongson Technology Corporation Limited
+ */
+
+#include <linux/pagewalk.h>
+#include <linux/pgtable.h>
+#include <asm/set_memory.h>
+#include <asm/tlbflush.h>
+
+struct pageattr_masks {
+	pgprot_t set_mask;
+	pgprot_t clear_mask;
+};
+
+static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
+{
+	unsigned long new_val = val;
+	struct pageattr_masks *masks = walk->private;
+
+	new_val &= ~(pgprot_val(masks->clear_mask));
+	new_val |= (pgprot_val(masks->set_mask));
+
+	return new_val;
+}
+
+static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pgd_t val = pgdp_get(pgd);
+
+	if (pgd_leaf(val)) {
+		val = __pgd(set_pageattr_masks(pgd_val(val), walk));
+		set_pgd(pgd, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	p4d_t val = p4dp_get(p4d);
+
+	if (p4d_leaf(val)) {
+		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
+		set_p4d(p4d, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pud_t val = pudp_get(pud);
+
+	if (pud_leaf(val)) {
+		val = __pud(set_pageattr_masks(pud_val(val), walk));
+		set_pud(pud, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pmd_t val = pmdp_get(pmd);
+
+	if (pmd_leaf(val)) {
+		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
+		set_pmd(pmd, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pte_t val = ptep_get(pte);
+
+	val = __pte(set_pageattr_masks(pte_val(val), walk));
+	set_pte(pte, val);
+
+	return 0;
+}
+
+static int pageattr_pte_hole(unsigned long addr, unsigned long next,
+			     int depth, struct mm_walk *walk)
+{
+	return 0;
+}
+
+static const struct mm_walk_ops pageattr_ops = {
+	.pgd_entry = pageattr_pgd_entry,
+	.p4d_entry = pageattr_p4d_entry,
+	.pud_entry = pageattr_pud_entry,
+	.pmd_entry = pageattr_pmd_entry,
+	.pte_entry = pageattr_pte_entry,
+	.pte_hole = pageattr_pte_hole,
+	.walk_lock = PGWALK_RDLOCK,
+};
+
+static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask)
+{
+	int ret;
+	unsigned long start = addr;
+	unsigned long end = start + PAGE_SIZE * numpages;
+	struct pageattr_masks masks = {
+		.set_mask = set_mask,
+		.clear_mask = clear_mask
+	};
+
+	if (!numpages)
+		return 0;
+
+	mmap_write_lock(&init_mm);
+	ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, &masks);
+	mmap_write_unlock(&init_mm);
+
+	flush_tlb_kernel_range(start, end);
+
+	return ret;
+}
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+	if (addr < vm_map_base)
+		return 0;
+
+	return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_NO_EXEC));
+}
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+	if (addr < vm_map_base)
+		return 0;
+
+	return __set_memory(addr, numpages, __pgprot(_PAGE_NO_EXEC), __pgprot(0));
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+	if (addr < vm_map_base)
+		return 0;
+
+	return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_WRITE | _PAGE_DIRTY));
+}
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+	if (addr < vm_map_base)
+		return 0;
+
+	return __set_memory(addr, numpages, __pgprot(_PAGE_WRITE | _PAGE_DIRTY), __pgprot(0));
+}
+
+bool kernel_page_present(struct page *page)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long addr = (unsigned long)page_address(page);
+
+	if (addr < vm_map_base)
+		return true;
+
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(pgdp_get(pgd)))
+		return false;
+	if (pgd_leaf(pgdp_get(pgd)))
+		return true;
+
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(p4dp_get(p4d)))
+		return false;
+	if (p4d_leaf(p4dp_get(p4d)))
+		return true;
+
+	pud = pud_offset(p4d, addr);
+	if (pud_none(pudp_get(pud)))
+		return false;
+	if (pud_leaf(pudp_get(pud)))
+		return true;
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(pmdp_get(pmd)))
+		return false;
+	if (pmd_leaf(pmdp_get(pmd)))
+		return true;
+
+	pte = pte_offset_kernel(pmd, addr);
+	return pte_present(ptep_get(pte));
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+
+	if (addr < vm_map_base)
+		return 0;
+
+	return __set_memory(addr, 1, PAGE_KERNEL, __pgprot(0));
+}
+
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+
+	if (addr < vm_map_base)
+		return 0;
+
+	return __set_memory(addr, 1, __pgprot(0), __pgprot(_PAGE_PRESENT | _PAGE_VALID));
+}

arch/loongarch/pci/acpi.c

@@ -225,6 +225,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 	if (bus) {
 		memcpy(bus->sysdata, info->cfg, sizeof(struct pci_config_window));
 		kfree(info);
+		kfree(root_ops);
 	} else {
 		struct pci_bus *child;
 

arch/loongarch/vdso/vgetrandom-chacha.S

@@ -9,23 +9,11 @@
 
 .text
 
-/* Salsa20 quarter-round */
-.macro	QR	a b c d
-	add.w		\a, \a, \b
-	xor		\d, \d, \a
-	rotri.w		\d, \d, 16
-
-	add.w		\c, \c, \d
-	xor		\b, \b, \c
-	rotri.w		\b, \b, 20
-
-	add.w		\a, \a, \b
-	xor		\d, \d, \a
-	rotri.w		\d, \d, 24
-
-	add.w		\c, \c, \d
-	xor		\b, \b, \c
-	rotri.w		\b, \b, 25
+.macro	OP_4REG	op d0 d1 d2 d3 s0 s1 s2 s3
+	\op	\d0, \d0, \s0
+	\op	\d1, \d1, \s1
+	\op	\d2, \d2, \s2
+	\op	\d3, \d3, \s3
 .endm
 
 /*
@@ -74,6 +62,23 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 /* Reuse i as copy3 */
 #define copy3		i
 
+/* Packs to be used with OP_4REG */
+#define line0		state0, state1, state2, state3
+#define line1		state4, state5, state6, state7
+#define line2		state8, state9, state10, state11
+#define line3		state12, state13, state14, state15
+
+#define line1_perm	state5, state6, state7, state4
+#define line2_perm	state10, state11, state8, state9
+#define line3_perm	state15, state12, state13, state14
+
+#define copy		copy0, copy1, copy2, copy3
+
+#define _16		16, 16, 16, 16
+#define _20		20, 20, 20, 20
+#define _24		24, 24, 24, 24
+#define _25		25, 25, 25, 25
+
 	/*
 	 * The ABI requires s0-s9 saved, and sp aligned to 16-byte.
 	 * This does not violate the stack-less requirement: no sensitive data
@@ -126,16 +131,38 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	li.w		i, 10
 .Lpermute:
 	/* odd round */
-	QR		state0, state4, state8, state12
-	QR		state1, state5, state9, state13
-	QR		state2, state6, state10, state14
-	QR		state3, state7, state11, state15
+	OP_4REG	add.w	line0, line1
+	OP_4REG	xor	line3, line0
+	OP_4REG	rotri.w	line3, _16
+
+	OP_4REG	add.w	line2, line3
+	OP_4REG	xor	line1, line2
+	OP_4REG	rotri.w	line1, _20
+
+	OP_4REG	add.w	line0, line1
+	OP_4REG	xor	line3, line0
+	OP_4REG	rotri.w	line3, _24
+
+	OP_4REG	add.w	line2, line3
+	OP_4REG	xor	line1, line2
+	OP_4REG	rotri.w	line1, _25
 
 	/* even round */
-	QR		state0, state5, state10, state15
-	QR		state1, state6, state11, state12
-	QR		state2, state7, state8, state13
-	QR		state3, state4, state9, state14
+	OP_4REG	add.w	line0, line1_perm
+	OP_4REG	xor	line3_perm, line0
+	OP_4REG	rotri.w	line3_perm, _16
+
+	OP_4REG	add.w	line2_perm, line3_perm
+	OP_4REG	xor	line1_perm, line2_perm
+	OP_4REG	rotri.w	line1_perm, _20
+
+	OP_4REG	add.w	line0, line1_perm
+	OP_4REG	xor	line3_perm, line0
+	OP_4REG	rotri.w	line3_perm, _24
+
+	OP_4REG	add.w	line2_perm, line3_perm
+	OP_4REG	xor	line1_perm, line2_perm
+	OP_4REG	rotri.w	line1_perm, _25
 
 	addi.w		i, i, -1
 	bnez		i, .Lpermute
@@ -147,10 +174,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	li.w		copy3, 0x6b206574
 
 	/* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */
-	add.w		state0, state0, copy0
-	add.w		state1, state1, copy1
-	add.w		state2, state2, copy2
-	add.w		state3, state3, copy3
+	OP_4REG	add.w	line0, copy
 	st.w		state0, output, 0
 	st.w		state1, output, 4
 	st.w		state2, output, 8
@@ -165,10 +189,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	ld.w		state3, key, 12
 
 	/* output[4,5,6,7] = state[0,1,2,3] + state[4,5,6,7] */
-	add.w		state4, state4, state0
-	add.w		state5, state5, state1
-	add.w		state6, state6, state2
-	add.w		state7, state7, state3
+	OP_4REG	add.w	line1, line0
 	st.w		state4, output, 16
 	st.w		state5, output, 20
 	st.w		state6, output, 24
@@ -181,10 +202,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	ld.w		state3, key, 28
 
 	/* output[8,9,10,11] = state[0,1,2,3] + state[8,9,10,11] */
-	add.w		state8, state8, state0
-	add.w		state9, state9, state1
-	add.w		state10, state10, state2
-	add.w		state11, state11, state3
+	OP_4REG	add.w	line2, line0
 	st.w		state8, output, 32
 	st.w		state9, output, 36
 	st.w		state10, output, 40

arch/sh/include/asm/irq.h

@@ -13,12 +13,6 @@
  */
 #define NO_IRQ_IGNORE		((unsigned int)-1)
 
-/*
- * Simple Mask Register Support
- */
-extern void make_maskreg_irq(unsigned int irq);
-extern unsigned short *irq_mask_register;
-
 /*
  * PINT IRQs
  */

arch/x86/include/asm/pgtable_64.h

@@ -270,5 +270,26 @@ static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
 
 #include <asm/pgtable-invert.h>
 
-#endif /* !__ASSEMBLY__ */
+#else /* __ASSEMBLY__ */
+
+#define l4_index(x)	(((x) >> 39) & 511)
+#define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+
+L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4)
+L4_START_KERNEL = l4_index(__START_KERNEL_map)
+
+L3_START_KERNEL = pud_index(__START_KERNEL_map)
+
+#define SYM_DATA_START_PAGE_ALIGNED(name)			\
+	SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE)
+
+/* Automate the creation of 1 to 1 mapping pmd entries */
+#define PMDS(START, PERM, COUNT)			\
+	i = 0 ;						\
+	.rept (COUNT) ;					\
+	.quad	(START) + (i << PMD_SHIFT) + (PERM) ;	\
+	i = i + 1 ;					\
+	.endr
+
+#endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */

arch/x86/kernel/head_64.S

@@ -32,13 +32,6 @@
  * We are not able to switch in one step to the final KERNEL ADDRESS SPACE
  * because we need identity-mapped pages.
  */
-#define l4_index(x)	(((x) >> 39) & 511)
-#define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
-
-L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4)
-L4_START_KERNEL = l4_index(__START_KERNEL_map)
-
-L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
 	__HEAD
 	.code64
@@ -577,9 +570,6 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb)
 SYM_CODE_END(vc_no_ghcb)
 #endif
 
-#define SYM_DATA_START_PAGE_ALIGNED(name)			\
-	SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE)
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Each PGD needs to be 8k long and 8k aligned.  We do not
@@ -601,14 +591,6 @@ SYM_CODE_END(vc_no_ghcb)
 #define PTI_USER_PGD_FILL	0
 #endif
 
-/* Automate the creation of 1 to 1 mapping pmd entries */
-#define PMDS(START, PERM, COUNT)			\
-	i = 0 ;						\
-	.rept (COUNT) ;					\
-	.quad	(START) + (i << PMD_SHIFT) + (PERM) ;	\
-	i = i + 1 ;					\
-	.endr
-
 	__INITDATA
 	.balign 4
 
@@ -708,8 +690,6 @@ SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt)
 	.endr
 SYM_DATA_END(level1_fixmap_pgt)
 
-#undef PMDS
-
 	.data
 	.align 16
 

arch/x86/platform/pvh/head.S

@@ -7,6 +7,7 @@
 	.code32
 	.text
 #define _pa(x)          ((x) - __START_KERNEL_map)
+#define rva(x)          ((x) - pvh_start_xen)
 
 #include <linux/elfnote.h>
 #include <linux/init.h>
@@ -15,6 +16,7 @@
 #include <asm/segment.h>
 #include <asm/asm.h>
 #include <asm/boot.h>
+#include <asm/pgtable.h>
 #include <asm/processor-flags.h>
 #include <asm/msr.h>
 #include <asm/nospec-branch.h>
@@ -54,7 +56,25 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	UNWIND_HINT_END_OF_STACK
 	cld
 
-	lgdt (_pa(gdt))
+	/*
+	 * See the comment for startup_32 for more details.  We need to
+	 * execute a call to get the execution address to be position
+	 * independent, but we don't have a stack.  Save and restore the
+	 * magic field of start_info in ebx, and use that as the stack.
+	 */
+	mov  (%ebx), %eax
+	leal 4(%ebx), %esp
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call 1f
+1:	popl %ebp
+	mov  %eax, (%ebx)
+	subl $rva(1b), %ebp
+	movl $0, %esp
+
+	leal rva(gdt)(%ebp), %eax
+	leal rva(gdt_start)(%ebp), %ecx
+	movl %ecx, 2(%eax)
+	lgdt (%eax)
 
 	mov $PVH_DS_SEL,%eax
 	mov %eax,%ds
@@ -62,14 +82,14 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	mov %eax,%ss
 
 	/* Stash hvm_start_info. */
-	mov $_pa(pvh_start_info), %edi
+	leal rva(pvh_start_info)(%ebp), %edi
 	mov %ebx, %esi
-	mov _pa(pvh_start_info_sz), %ecx
+	movl rva(pvh_start_info_sz)(%ebp), %ecx
 	shr $2,%ecx
 	rep
 	movsl
 
-	mov $_pa(early_stack_end), %esp
+	leal rva(early_stack_end)(%ebp), %esp
 
 	/* Enable PAE mode. */
 	mov %cr4, %eax
@@ -83,31 +103,86 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	btsl $_EFER_LME, %eax
 	wrmsr
 
+	mov %ebp, %ebx
+	subl $_pa(pvh_start_xen), %ebx /* offset */
+	jz .Lpagetable_done
+
+	/* Fixup page-tables for relocation. */
+	leal rva(pvh_init_top_pgt)(%ebp), %edi
+	movl $PTRS_PER_PGD, %ecx
+2:
+	testl $_PAGE_PRESENT, 0x00(%edi)
+	jz 1f
+	addl %ebx, 0x00(%edi)
+1:
+	addl $8, %edi
+	decl %ecx
+	jnz 2b
+
+	/* L3 ident has a single entry. */
+	leal rva(pvh_level3_ident_pgt)(%ebp), %edi
+	addl %ebx, 0x00(%edi)
+
+	leal rva(pvh_level3_kernel_pgt)(%ebp), %edi
+	addl %ebx, (PAGE_SIZE - 16)(%edi)
+	addl %ebx, (PAGE_SIZE - 8)(%edi)
+
+	/* pvh_level2_ident_pgt is fine - large pages */
+
+	/* pvh_level2_kernel_pgt needs adjustment - large pages */
+	leal rva(pvh_level2_kernel_pgt)(%ebp), %edi
+	movl $PTRS_PER_PMD, %ecx
+2:
+	testl $_PAGE_PRESENT, 0x00(%edi)
+	jz 1f
+	addl %ebx, 0x00(%edi)
+1:
+	addl $8, %edi
+	decl %ecx
+	jnz 2b
+
+.Lpagetable_done:
 	/* Enable pre-constructed page tables. */
-	mov $_pa(init_top_pgt), %eax
+	leal rva(pvh_init_top_pgt)(%ebp), %eax
 	mov %eax, %cr3
 	mov $(X86_CR0_PG | X86_CR0_PE), %eax
 	mov %eax, %cr0
 
 	/* Jump to 64-bit mode. */
-	ljmp $PVH_CS_SEL, $_pa(1f)
+	pushl $PVH_CS_SEL
+	leal  rva(1f)(%ebp), %eax
+	pushl %eax
+	lretl
 
 	/* 64-bit entry point. */
 	.code64
 1:
+	UNWIND_HINT_END_OF_STACK
+
 	/* Set base address in stack canary descriptor. */
 	mov $MSR_GS_BASE,%ecx
-	mov $_pa(canary), %eax
+	leal canary(%rip), %eax
 	xor %edx, %edx
 	wrmsr
 
+	/*
+	 * Calculate load offset and store in phys_base.  __pa() needs
+	 * phys_base set to calculate the hypercall page in xen_pvh_init().
+	 */
+	movq %rbp, %rbx
+	subq $_pa(pvh_start_xen), %rbx
+	movq %rbx, phys_base(%rip)
 	call xen_prepare_pvh
+	/*
+	 * Clear phys_base.  __startup_64 will *add* to its value,
+	 * so reset to 0.
+	 */
+	xor  %rbx, %rbx
+	movq %rbx, phys_base(%rip)
 
 	/* startup_64 expects boot_params in %rsi. */
-	mov $_pa(pvh_bootparams), %rsi
-	mov $_pa(startup_64), %rax
-	ANNOTATE_RETPOLINE_SAFE
-	jmp *%rax
+	lea pvh_bootparams(%rip), %rsi
+	jmp startup_64
 
 #else /* CONFIG_X86_64 */
 
@@ -143,7 +218,7 @@ SYM_CODE_END(pvh_start_xen)
 	.balign 8
 SYM_DATA_START_LOCAL(gdt)
 	.word gdt_end - gdt_start
-	.long _pa(gdt_start)
+	.long _pa(gdt_start) /* x86-64 will overwrite if relocated. */
 	.word 0
 SYM_DATA_END(gdt)
 SYM_DATA_START_LOCAL(gdt_start)
@@ -163,5 +238,67 @@ SYM_DATA_START_LOCAL(early_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
 
+#ifdef CONFIG_X86_64
+/*
+ * Xen PVH needs a set of identity mapped and kernel high mapping
+ * page tables.  pvh_start_xen starts running on the identity mapped
+ * page tables, but xen_prepare_pvh calls into the high mapping.
+ * These page tables need to be relocatable and are only used until
+ * startup_64 transitions to init_top_pgt.
+ */
+SYM_DATA_START_PAGE_ALIGNED(pvh_init_top_pgt)
+	.quad   pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.org    pvh_init_top_pgt + L4_PAGE_OFFSET * 8, 0
+	.quad   pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.org    pvh_init_top_pgt + L4_START_KERNEL * 8, 0
+	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
+	.quad   pvh_level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+SYM_DATA_END(pvh_init_top_pgt)
+
+SYM_DATA_START_PAGE_ALIGNED(pvh_level3_ident_pgt)
+	.quad	pvh_level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.fill	511, 8, 0
+SYM_DATA_END(pvh_level3_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(pvh_level2_ident_pgt)
+	/*
+	 * Since I easily can, map the first 1G.
+	 * Don't set NX because code runs from these pages.
+	 *
+	 * Note: This sets _PAGE_GLOBAL despite whether
+	 * the CPU supports it or it is enabled.  But,
+	 * the CPU should ignore the bit.
+	 */
+	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
+SYM_DATA_END(pvh_level2_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(pvh_level3_kernel_pgt)
+	.fill	L3_START_KERNEL, 8, 0
+	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
+	.quad	pvh_level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.quad	0 /* no fixmap */
+SYM_DATA_END(pvh_level3_kernel_pgt)
+
+SYM_DATA_START_PAGE_ALIGNED(pvh_level2_kernel_pgt)
+	/*
+	 * Kernel high mapping.
+	 *
+	 * The kernel code+data+bss must be located below KERNEL_IMAGE_SIZE in
+	 * virtual address space, which is 1 GiB if RANDOMIZE_BASE is enabled,
+	 * 512 MiB otherwise.
+	 *
+	 * (NOTE: after that starts the module area, see MODULES_VADDR.)
+	 *
+	 * This table is eventually used by the kernel during normal runtime.
+	 * Care must be taken to clear out undesired bits later, like _PAGE_RW
+	 * or _PAGE_GLOBAL in some cases.
+	 */
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE / PMD_SIZE)
+SYM_DATA_END(pvh_level2_kernel_pgt)
+
+	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_RELOC,
+		     .long CONFIG_PHYSICAL_ALIGN;
+		     .long LOAD_PHYSICAL_ADDR;
+		     .long KERNEL_IMAGE_SIZE - 1)
+#endif
+
 	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,
 	             _ASM_PTR (pvh_start_xen - __START_KERNEL_map))

arch/x86/xen/enlighten_pvh.c

@@ -4,6 +4,7 @@
 #include <linux/mm.h>
 
 #include <xen/hvc-console.h>
+#include <xen/acpi.h>
 
 #include <asm/bootparam.h>
 #include <asm/io_apic.h>
@@ -28,6 +29,28 @@
 bool __ro_after_init xen_pvh;
 EXPORT_SYMBOL_GPL(xen_pvh);
 
+#ifdef CONFIG_XEN_DOM0
+int xen_pvh_setup_gsi(int gsi, int trigger, int polarity)
+{
+	int ret;
+	struct physdev_setup_gsi setup_gsi;
+
+	setup_gsi.gsi = gsi;
+	setup_gsi.triggering = (trigger == ACPI_EDGE_SENSITIVE ? 0 : 1);
+	setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+
+	ret = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi);
+	if (ret == -EEXIST) {
+		xen_raw_printk("Already setup the GSI :%d\n", gsi);
+		ret = 0;
+	} else if (ret)
+		xen_raw_printk("Fail to setup GSI (%d)!\n", gsi);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_pvh_setup_gsi);
+#endif
+
 /*
  * Reserve e820 UNUSABLE regions to inflate the memory balloon.
  *

drivers/acpi/Kconfig

@@ -451,7 +451,7 @@ config ACPI_HED
 
 config ACPI_BGRT
 	bool "Boottime Graphics Resource Table support"
-	depends on EFI && (X86 || ARM64)
+	depends on EFI && (X86 || ARM64 || LOONGARCH)
 	help
 	  This driver adds support for exposing the ACPI Boottime Graphics
 	  Resource Table, which allows the operating system to obtain

drivers/acpi/apei/einj-cxl.c

@@ -7,9 +7,9 @@
  *
  * Author: Ben Cheatham <benjamin.cheatham@amd.com>
  */
-#include <linux/einj-cxl.h>
 #include <linux/seq_file.h>
 #include <linux/pci.h>
+#include <cxl/einj.h>
 
 #include "apei-internal.h"
 

drivers/acpi/apei/ghes.c

@@ -27,7 +27,6 @@
 #include <linux/timer.h>
 #include <linux/cper.h>
 #include <linux/cleanup.h>
-#include <linux/cxl-event.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -50,6 +49,7 @@
 #include <acpi/apei.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
+#include <cxl/event.h>
 #include <ras/ras_event.h>
 
 #include "apei-internal.h"

drivers/acpi/pci_irq.c

@@ -288,7 +288,7 @@ static int acpi_reroute_boot_interrupt(struct pci_dev *dev,
 }
 #endif /* CONFIG_X86_IO_APIC */
 
-static struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin)
+struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin)
 {
 	struct acpi_prt_entry *entry = NULL;
 	struct pci_dev *bridge;

drivers/ata/libata-scsi.c

@@ -2256,10 +2256,15 @@ static inline u16 ata_xlat_cdl_limit(u8 *buf)
 static unsigned int ata_msense_control_spgt2(struct ata_device *dev, u8 *buf,
 					     u8 spg)
 {
-	u8 *b, *cdl = dev->cdl->desc_log_buf, *desc;
+	u8 *b, *cdl, *desc;
 	u32 policy;
 	int i;
 
+	if (!(dev->flags & ATA_DFLAG_CDL) || !dev->cdl)
+		return 0;
+
+	cdl = dev->cdl->desc_log_buf;
+
 	/*
 	 * Fill the subpage. The first four bytes of the T2A/T2B mode pages
 	 * are a header. The PAGE LENGTH field is the size of the page
@@ -2356,7 +2361,7 @@ static unsigned int ata_msense_control(struct ata_device *dev, u8 *buf,
 	case ALL_SUB_MPAGES:
 		n = ata_msense_control_spg0(dev, buf, changeable);
 		n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE);
-		n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE);
+		n += ata_msense_control_spgt2(dev, buf + n, CDL_T2B_SUB_MPAGE);
 		n += ata_msense_control_ata_feature(dev, buf + n);
 		return n;
 	default:

drivers/block/zram/zram_drv.c

@@ -2115,8 +2115,10 @@ static void zram_destroy_comps(struct zram *zram)
 		zram->num_active_comps--;
 	}
 
-	for (prio = ZRAM_SECONDARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {
-		kfree(zram->comp_algs[prio]);
+	for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {
+		/* Do not free statically defined compression algorithms */
+		if (zram->comp_algs[prio] != default_compressor)
+			kfree(zram->comp_algs[prio]);
 		zram->comp_algs[prio] = NULL;
 	}
 

drivers/cxl/core/cdat.c

@@ -9,13 +9,12 @@
 #include "cxlmem.h"
 #include "core.h"
 #include "cxl.h"
-#include "core.h"
 
 struct dsmas_entry {
 	struct range dpa_range;
 	u8 handle;
 	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
-
+	struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX];
 	int entries;
 	int qos_class;
 };
@@ -163,7 +162,7 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
 	val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base),
 			     dslbis->data_type);
 
-	cxl_access_coordinate_set(dent->coord, dslbis->data_type, val);
+	cxl_access_coordinate_set(dent->cdat_coord, dslbis->data_type, val);
 
 	return 0;
 }
@@ -220,7 +219,7 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 	xa_for_each(dsmas_xa, index, dent) {
 		int qos_class;
 
-		cxl_coordinates_combine(dent->coord, dent->coord, ep_c);
+		cxl_coordinates_combine(dent->coord, dent->cdat_coord, ep_c);
 		dent->entries = 1;
 		rc = cxl_root->ops->qos_class(cxl_root,
 					      &dent->coord[ACCESS_COORDINATE_CPU],
@@ -241,8 +240,10 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
 			      struct cxl_dpa_perf *dpa_perf)
 {
-	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
 		dpa_perf->coord[i] = dent->coord[i];
+		dpa_perf->cdat_coord[i] = dent->cdat_coord[i];
+	}
 	dpa_perf->dpa_range = dent->dpa_range;
 	dpa_perf->qos_class = dent->qos_class;
 	dev_dbg(dev,
@@ -546,19 +547,37 @@ void cxl_coordinates_combine(struct access_coordinate *out,
 
 MODULE_IMPORT_NS(CXL);
 
-void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
-				    struct cxl_endpoint_decoder *cxled)
+static void cxl_bandwidth_add(struct access_coordinate *coord,
+			      struct access_coordinate *c1,
+			      struct access_coordinate *c2)
+{
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		coord[i].read_bandwidth = c1[i].read_bandwidth +
+					  c2[i].read_bandwidth;
+		coord[i].write_bandwidth = c1[i].write_bandwidth +
+					   c2[i].write_bandwidth;
+	}
+}
+
+static bool dpa_perf_contains(struct cxl_dpa_perf *perf,
+			      struct resource *dpa_res)
+{
+	struct range dpa = {
+		.start = dpa_res->start,
+		.end = dpa_res->end,
+	};
+
+	return range_contains(&perf->dpa_range, &dpa);
+}
+
+static struct cxl_dpa_perf *cxled_get_dpa_perf(struct cxl_endpoint_decoder *cxled,
+					       enum cxl_decoder_mode mode)
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
-	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
-	struct range dpa = {
-			.start = cxled->dpa_res->start,
-			.end = cxled->dpa_res->end,
-	};
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
 	struct cxl_dpa_perf *perf;
 
-	switch (cxlr->mode) {
+	switch (mode) {
 	case CXL_DECODER_RAM:
 		perf = &mds->ram_perf;
 		break;
@@ -566,12 +585,473 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
 		perf = &mds->pmem_perf;
 		break;
 	default:
-		return;
+		return ERR_PTR(-EINVAL);
 	}
 
+	if (!dpa_perf_contains(perf, cxled->dpa_res))
+		return ERR_PTR(-EINVAL);
+
+	return perf;
+}
+
+/*
+ * Transient context for containing the current calculation of bandwidth when
+ * doing walking the port hierarchy to deal with shared upstream link.
+ */
+struct cxl_perf_ctx {
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	struct cxl_port *port;
+};
+
+/**
+ * cxl_endpoint_gather_bandwidth - collect all the endpoint bandwidth in an xarray
+ * @cxlr: CXL region for the bandwidth calculation
+ * @cxled: endpoint decoder to start on
+ * @usp_xa: (output) the xarray that collects all the bandwidth coordinates
+ *          indexed by the upstream device with data of 'struct cxl_perf_ctx'.
+ * @gp_is_root: (output) bool of whether the grandparent is cxl root.
+ *
+ * Return: 0 for success or -errno
+ *
+ * Collects aggregated endpoint bandwidth and store the bandwidth in
+ * an xarray indexed by the upstream device of the switch or the RP
+ * device. Each endpoint consists the minimum of the bandwidth from DSLBIS
+ * from the endpoint CDAT, the endpoint upstream link bandwidth, and the
+ * bandwidth from the SSLBIS of the switch CDAT for the switch upstream port to
+ * the downstream port that's associated with the endpoint. If the
+ * device is directly connected to a RP, then no SSLBIS is involved.
+ */
+static int cxl_endpoint_gather_bandwidth(struct cxl_region *cxlr,
+					 struct cxl_endpoint_decoder *cxled,
+					 struct xarray *usp_xa,
+					 bool *gp_is_root)
+{
+	struct cxl_port *endpoint = to_cxl_port(cxled->cxld.dev.parent);
+	struct cxl_port *parent_port = to_cxl_port(endpoint->dev.parent);
+	struct cxl_port *gp_port = to_cxl_port(parent_port->dev.parent);
+	struct access_coordinate pci_coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate sw_coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate ep_coord[ACCESS_COORDINATE_MAX];
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	struct cxl_perf_ctx *perf_ctx;
+	struct cxl_dpa_perf *perf;
+	unsigned long index;
+	void *ptr;
+	int rc;
+
+	if (cxlds->rcd)
+		return -ENODEV;
+
+	perf = cxled_get_dpa_perf(cxled, cxlr->mode);
+	if (IS_ERR(perf))
+		return PTR_ERR(perf);
+
+	gp_port = to_cxl_port(parent_port->dev.parent);
+	*gp_is_root = is_cxl_root(gp_port);
+
+	/*
+	 * If the grandparent is cxl root, then index is the root port,
+	 * otherwise it's the parent switch upstream device.
+	 */
+	if (*gp_is_root)
+		index = (unsigned long)endpoint->parent_dport->dport_dev;
+	else
+		index = (unsigned long)parent_port->uport_dev;
+
+	perf_ctx = xa_load(usp_xa, index);
+	if (!perf_ctx) {
+		struct cxl_perf_ctx *c __free(kfree) =
+			kzalloc(sizeof(*perf_ctx), GFP_KERNEL);
+
+		if (!c)
+			return -ENOMEM;
+		ptr = xa_store(usp_xa, index, c, GFP_KERNEL);
+		if (xa_is_err(ptr))
+			return xa_err(ptr);
+		perf_ctx = no_free_ptr(c);
+		perf_ctx->port = parent_port;
+	}
+
+	/* Direct upstream link from EP bandwidth */
+	rc = cxl_pci_get_bandwidth(pdev, pci_coord);
+	if (rc < 0)
+		return rc;
+
+	/*
+	 * Min of upstream link bandwidth and Endpoint CDAT bandwidth from
+	 * DSLBIS.
+	 */
+	cxl_coordinates_combine(ep_coord, pci_coord, perf->cdat_coord);
+
+	/*
+	 * If grandparent port is root, then there's no switch involved and
+	 * the endpoint is connected to a root port.
+	 */
+	if (!*gp_is_root) {
+		/*
+		 * Retrieve the switch SSLBIS for switch downstream port
+		 * associated with the endpoint bandwidth.
+		 */
+		rc = cxl_port_get_switch_dport_bandwidth(endpoint, sw_coord);
+		if (rc)
+			return rc;
+
+		/*
+		 * Min of the earlier coordinates with the switch SSLBIS
+		 * bandwidth
+		 */
+		cxl_coordinates_combine(ep_coord, ep_coord, sw_coord);
+	}
+
+	/*
+	 * Aggregate the computed bandwidth with the current aggregated bandwidth
+	 * of the endpoints with the same switch upstream device or RP.
+	 */
+	cxl_bandwidth_add(perf_ctx->coord, perf_ctx->coord, ep_coord);
+
+	return 0;
+}
+
+static void free_perf_xa(struct xarray *xa)
+{
+	struct cxl_perf_ctx *ctx;
+	unsigned long index;
+
+	if (!xa)
+		return;
+
+	xa_for_each(xa, index, ctx)
+		kfree(ctx);
+	xa_destroy(xa);
+	kfree(xa);
+}
+DEFINE_FREE(free_perf_xa, struct xarray *, if (_T) free_perf_xa(_T))
+
+/**
+ * cxl_switch_gather_bandwidth - collect all the bandwidth at switch level in an xarray
+ * @cxlr: The region being operated on
+ * @input_xa: xarray indexed by upstream device of a switch with data of 'struct
+ *	      cxl_perf_ctx'
+ * @gp_is_root: (output) bool of whether the grandparent is cxl root.
+ *
+ * Return: a xarray of resulting cxl_perf_ctx per parent switch or root port
+ *         or ERR_PTR(-errno)
+ *
+ * Iterate through the xarray. Take the minimum of the downstream calculated
+ * bandwidth, the upstream link bandwidth, and the SSLBIS of the upstream
+ * switch if exists. Sum the resulting bandwidth under the switch upstream
+ * device or a RP device. The function can be iterated over multiple switches
+ * if the switches are present.
+ */
+static struct xarray *cxl_switch_gather_bandwidth(struct cxl_region *cxlr,
+						  struct xarray *input_xa,
+						  bool *gp_is_root)
+{
+	struct xarray *res_xa __free(free_perf_xa) =
+		kzalloc(sizeof(*res_xa), GFP_KERNEL);
+	struct access_coordinate coords[ACCESS_COORDINATE_MAX];
+	struct cxl_perf_ctx *ctx, *us_ctx;
+	unsigned long index, us_index;
+	int dev_count = 0;
+	int gp_count = 0;
+	void *ptr;
+	int rc;
+
+	if (!res_xa)
+		return ERR_PTR(-ENOMEM);
+	xa_init(res_xa);
+
+	xa_for_each(input_xa, index, ctx) {
+		struct device *dev = (struct device *)index;
+		struct cxl_port *port = ctx->port;
+		struct cxl_port *parent_port = to_cxl_port(port->dev.parent);
+		struct cxl_port *gp_port = to_cxl_port(parent_port->dev.parent);
+		struct cxl_dport *dport = port->parent_dport;
+		bool is_root = false;
+
+		dev_count++;
+		if (is_cxl_root(gp_port)) {
+			is_root = true;
+			gp_count++;
+		}
+
+		/*
+		 * If the grandparent is cxl root, then index is the root port,
+		 * otherwise it's the parent switch upstream device.
+		 */
+		if (is_root)
+			us_index = (unsigned long)port->parent_dport->dport_dev;
+		else
+			us_index = (unsigned long)parent_port->uport_dev;
+
+		us_ctx = xa_load(res_xa, us_index);
+		if (!us_ctx) {
+			struct cxl_perf_ctx *n __free(kfree) =
+				kzalloc(sizeof(*n), GFP_KERNEL);
+
+			if (!n)
+				return ERR_PTR(-ENOMEM);
+
+			ptr = xa_store(res_xa, us_index, n, GFP_KERNEL);
+			if (xa_is_err(ptr))
+				return ERR_PTR(xa_err(ptr));
+			us_ctx = no_free_ptr(n);
+			us_ctx->port = parent_port;
+		}
+
+		/*
+		 * If the device isn't an upstream PCIe port, there's something
+		 * wrong with the topology.
+		 */
+		if (!dev_is_pci(dev))
+			return ERR_PTR(-EINVAL);
+
+		/* Retrieve the upstream link bandwidth */
+		rc = cxl_pci_get_bandwidth(to_pci_dev(dev), coords);
+		if (rc)
+			return ERR_PTR(-ENXIO);
+
+		/*
+		 * Take the min of downstream bandwidth and the upstream link
+		 * bandwidth.
+		 */
+		cxl_coordinates_combine(coords, coords, ctx->coord);
+
+		/*
+		 * Take the min of the calculated bandwdith and the upstream
+		 * switch SSLBIS bandwidth if there's a parent switch
+		 */
+		if (!is_root)
+			cxl_coordinates_combine(coords, coords, dport->coord);
+
+		/*
+		 * Aggregate the calculated bandwidth common to an upstream
+		 * switch.
+		 */
+		cxl_bandwidth_add(us_ctx->coord, us_ctx->coord, coords);
+	}
+
+	/* Asymmetric topology detected. */
+	if (gp_count) {
+		if (gp_count != dev_count) {
+			dev_dbg(&cxlr->dev,
+				"Asymmetric hierarchy detected, bandwidth not updated\n");
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+		*gp_is_root = true;
+	}
+
+	return no_free_ptr(res_xa);
+}
+
+/**
+ * cxl_rp_gather_bandwidth - handle the root port level bandwidth collection
+ * @xa: the xarray that holds the cxl_perf_ctx that has the bandwidth calculated
+ *      below each root port device.
+ *
+ * Return: xarray that holds cxl_perf_ctx per host bridge or ERR_PTR(-errno)
+ */
+static struct xarray *cxl_rp_gather_bandwidth(struct xarray *xa)
+{
+	struct xarray *hb_xa __free(free_perf_xa) =
+		kzalloc(sizeof(*hb_xa), GFP_KERNEL);
+	struct cxl_perf_ctx *ctx;
+	unsigned long index;
+
+	if (!hb_xa)
+		return ERR_PTR(-ENOMEM);
+	xa_init(hb_xa);
+
+	xa_for_each(xa, index, ctx) {
+		struct cxl_port *port = ctx->port;
+		unsigned long hb_index = (unsigned long)port->uport_dev;
+		struct cxl_perf_ctx *hb_ctx;
+		void *ptr;
+
+		hb_ctx = xa_load(hb_xa, hb_index);
+		if (!hb_ctx) {
+			struct cxl_perf_ctx *n __free(kfree) =
+				kzalloc(sizeof(*n), GFP_KERNEL);
+
+			if (!n)
+				return ERR_PTR(-ENOMEM);
+			ptr = xa_store(hb_xa, hb_index, n, GFP_KERNEL);
+			if (xa_is_err(ptr))
+				return ERR_PTR(xa_err(ptr));
+			hb_ctx = no_free_ptr(n);
+			hb_ctx->port = port;
+		}
+
+		cxl_bandwidth_add(hb_ctx->coord, hb_ctx->coord, ctx->coord);
+	}
+
+	return no_free_ptr(hb_xa);
+}
+
+/**
+ * cxl_hb_gather_bandwidth - handle the host bridge level bandwidth collection
+ * @xa: the xarray that holds the cxl_perf_ctx that has the bandwidth calculated
+ *      below each host bridge.
+ *
+ * Return: xarray that holds cxl_perf_ctx per ACPI0017 device or ERR_PTR(-errno)
+ */
+static struct xarray *cxl_hb_gather_bandwidth(struct xarray *xa)
+{
+	struct xarray *mw_xa __free(free_perf_xa) =
+		kzalloc(sizeof(*mw_xa), GFP_KERNEL);
+	struct cxl_perf_ctx *ctx;
+	unsigned long index;
+
+	if (!mw_xa)
+		return ERR_PTR(-ENOMEM);
+	xa_init(mw_xa);
+
+	xa_for_each(xa, index, ctx) {
+		struct cxl_port *port = ctx->port;
+		struct cxl_port *parent_port;
+		struct cxl_perf_ctx *mw_ctx;
+		struct cxl_dport *dport;
+		unsigned long mw_index;
+		void *ptr;
+
+		parent_port = to_cxl_port(port->dev.parent);
+		mw_index = (unsigned long)parent_port->uport_dev;
+
+		mw_ctx = xa_load(mw_xa, mw_index);
+		if (!mw_ctx) {
+			struct cxl_perf_ctx *n __free(kfree) =
+				kzalloc(sizeof(*n), GFP_KERNEL);
+
+			if (!n)
+				return ERR_PTR(-ENOMEM);
+			ptr = xa_store(mw_xa, mw_index, n, GFP_KERNEL);
+			if (xa_is_err(ptr))
+				return ERR_PTR(xa_err(ptr));
+			mw_ctx = no_free_ptr(n);
+		}
+
+		dport = port->parent_dport;
+		cxl_coordinates_combine(ctx->coord, ctx->coord, dport->coord);
+		cxl_bandwidth_add(mw_ctx->coord, mw_ctx->coord, ctx->coord);
+	}
+
+	return no_free_ptr(mw_xa);
+}
+
+/**
+ * cxl_region_update_bandwidth - Update the bandwidth access coordinates of a region
+ * @cxlr: The region being operated on
+ * @input_xa: xarray holds cxl_perf_ctx wht calculated bandwidth per ACPI0017 instance
+ */
+static void cxl_region_update_bandwidth(struct cxl_region *cxlr,
+					struct xarray *input_xa)
+{
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	struct cxl_perf_ctx *ctx;
+	unsigned long index;
+
+	memset(coord, 0, sizeof(coord));
+	xa_for_each(input_xa, index, ctx)
+		cxl_bandwidth_add(coord, coord, ctx->coord);
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		cxlr->coord[i].read_bandwidth = coord[i].read_bandwidth;
+		cxlr->coord[i].write_bandwidth = coord[i].write_bandwidth;
+	}
+}
+
+/**
+ * cxl_region_shared_upstream_bandwidth_update - Recalculate the bandwidth for
+ *						 the region
+ * @cxlr: the cxl region to recalculate
+ *
+ * The function walks the topology from bottom up and calculates the bandwidth. It
+ * starts at the endpoints, processes at the switches if any, processes at the rootport
+ * level, at the host bridge level, and finally aggregates at the region.
+ */
+void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr)
+{
+	struct xarray *working_xa;
+	int root_count = 0;
+	bool is_root;
+	int rc;
+
 	lockdep_assert_held(&cxl_dpa_rwsem);
 
-	if (!range_contains(&perf->dpa_range, &dpa))
+	struct xarray *usp_xa __free(free_perf_xa) =
+		kzalloc(sizeof(*usp_xa), GFP_KERNEL);
+
+	if (!usp_xa)
+		return;
+
+	xa_init(usp_xa);
+
+	/* Collect bandwidth data from all the endpoints. */
+	for (int i = 0; i < cxlr->params.nr_targets; i++) {
+		struct cxl_endpoint_decoder *cxled = cxlr->params.targets[i];
+
+		is_root = false;
+		rc = cxl_endpoint_gather_bandwidth(cxlr, cxled, usp_xa, &is_root);
+		if (rc)
+			return;
+		root_count += is_root;
+	}
+
+	/* Detect asymmetric hierarchy with some direct attached endpoints. */
+	if (root_count && root_count != cxlr->params.nr_targets) {
+		dev_dbg(&cxlr->dev,
+			"Asymmetric hierarchy detected, bandwidth not updated\n");
+		return;
+	}
+
+	/*
+	 * Walk up one or more switches to deal with the bandwidth of the
+	 * switches if they exist. Endpoints directly attached to RPs skip
+	 * over this part.
+	 */
+	if (!root_count) {
+		do {
+			working_xa = cxl_switch_gather_bandwidth(cxlr, usp_xa,
+								 &is_root);
+			if (IS_ERR(working_xa))
+				return;
+			free_perf_xa(usp_xa);
+			usp_xa = working_xa;
+		} while (!is_root);
+	}
+
+	/* Handle the bandwidth at the root port of the hierarchy */
+	working_xa = cxl_rp_gather_bandwidth(usp_xa);
+	if (IS_ERR(working_xa))
+		return;
+	free_perf_xa(usp_xa);
+	usp_xa = working_xa;
+
+	/* Handle the bandwidth at the host bridge of the hierarchy */
+	working_xa = cxl_hb_gather_bandwidth(usp_xa);
+	if (IS_ERR(working_xa))
+		return;
+	free_perf_xa(usp_xa);
+	usp_xa = working_xa;
+
+	/*
+	 * Aggregate all the bandwidth collected per CFMWS (ACPI0017) and
+	 * update the region bandwidth with the final calculated values.
+	 */
+	cxl_region_update_bandwidth(cxlr, usp_xa);
+}
+
+void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
+				    struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_dpa_perf *perf;
+
+	lockdep_assert_held(&cxl_dpa_rwsem);
+
+	perf = cxled_get_dpa_perf(cxled, cxlr->mode);
+	if (IS_ERR(perf))
 		return;
 
 	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {

drivers/cxl/core/core.h

@@ -103,9 +103,11 @@ enum cxl_poison_trace_type {
 };
 
 long cxl_pci_get_latency(struct pci_dev *pdev);
-
+int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c);
 int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr,
 				       enum access_coordinate_class access);
 bool cxl_need_node_perf_attrs_update(int nid);
+int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
+					struct access_coordinate *c);
 
 #endif /* __CXL_CORE_H__ */

drivers/cxl/core/mbox.c

@@ -225,7 +225,7 @@ static const char *cxl_mem_opcode_to_name(u16 opcode)
 
 /**
  * cxl_internal_send_cmd() - Kernel internal interface to send a mailbox command
- * @mds: The driver data for the operation
+ * @cxl_mbox: CXL mailbox context
  * @mbox_cmd: initialized command to execute
  *
  * Context: Any context.
@@ -241,19 +241,19 @@ static const char *cxl_mem_opcode_to_name(u16 opcode)
  * error. While this distinction can be useful for commands from userspace, the
  * kernel will only be able to use results when both are successful.
  */
-int cxl_internal_send_cmd(struct cxl_memdev_state *mds,
+int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox,
 			  struct cxl_mbox_cmd *mbox_cmd)
 {
 	size_t out_size, min_out;
 	int rc;
 
-	if (mbox_cmd->size_in > mds->payload_size ||
-	    mbox_cmd->size_out > mds->payload_size)
+	if (mbox_cmd->size_in > cxl_mbox->payload_size ||
+	    mbox_cmd->size_out > cxl_mbox->payload_size)
 		return -E2BIG;
 
 	out_size = mbox_cmd->size_out;
 	min_out = mbox_cmd->min_out;
-	rc = mds->mbox_send(mds, mbox_cmd);
+	rc = cxl_mbox->mbox_send(cxl_mbox, mbox_cmd);
 	/*
 	 * EIO is reserved for a payload size mismatch and mbox_send()
 	 * may not return this error.
@@ -353,6 +353,7 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox,
 			     struct cxl_memdev_state *mds, u16 opcode,
 			     size_t in_size, size_t out_size, u64 in_payload)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	*mbox = (struct cxl_mbox_cmd) {
 		.opcode = opcode,
 		.size_in = in_size,
@@ -374,7 +375,7 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox,
 
 	/* Prepare to handle a full payload for variable sized output */
 	if (out_size == CXL_VARIABLE_PAYLOAD)
-		mbox->size_out = mds->payload_size;
+		mbox->size_out = cxl_mbox->payload_size;
 	else
 		mbox->size_out = out_size;
 
@@ -398,6 +399,8 @@ static int cxl_to_mem_cmd_raw(struct cxl_mem_command *mem_cmd,
 			      const struct cxl_send_command *send_cmd,
 			      struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
+
 	if (send_cmd->raw.rsvd)
 		return -EINVAL;
 
@@ -406,7 +409,7 @@ static int cxl_to_mem_cmd_raw(struct cxl_mem_command *mem_cmd,
 	 * gets passed along without further checking, so it must be
 	 * validated here.
 	 */
-	if (send_cmd->out.size > mds->payload_size)
+	if (send_cmd->out.size > cxl_mbox->payload_size)
 		return -EINVAL;
 
 	if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode))
@@ -494,6 +497,7 @@ static int cxl_validate_cmd_from_user(struct cxl_mbox_cmd *mbox_cmd,
 				      struct cxl_memdev_state *mds,
 				      const struct cxl_send_command *send_cmd)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mem_command mem_cmd;
 	int rc;
 
@@ -505,7 +509,7 @@ static int cxl_validate_cmd_from_user(struct cxl_mbox_cmd *mbox_cmd,
 	 * supports, but output can be arbitrarily large (simply write out as
 	 * much data as the hardware provides).
 	 */
-	if (send_cmd->in.size > mds->payload_size)
+	if (send_cmd->in.size > cxl_mbox->payload_size)
 		return -EINVAL;
 
 	/* Sanitize and construct a cxl_mem_command */
@@ -542,7 +546,7 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd,
 		return put_user(ARRAY_SIZE(cxl_mem_commands), &q->n_commands);
 
 	/*
-	 * otherwise, return max(n_commands, total commands) cxl_command_info
+	 * otherwise, return min(n_commands, total commands) cxl_command_info
 	 * structures.
 	 */
 	cxl_for_each_cmd(cmd) {
@@ -591,6 +595,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_memdev_state *mds,
 					u64 out_payload, s32 *size_out,
 					u32 *retval)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct device *dev = mds->cxlds.dev;
 	int rc;
 
@@ -601,7 +606,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_memdev_state *mds,
 		cxl_mem_opcode_to_name(mbox_cmd->opcode),
 		mbox_cmd->opcode, mbox_cmd->size_in);
 
-	rc = mds->mbox_send(mds, mbox_cmd);
+	rc = cxl_mbox->mbox_send(cxl_mbox, mbox_cmd);
 	if (rc)
 		goto out;
 
@@ -659,11 +664,12 @@ int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s)
 static int cxl_xfer_log(struct cxl_memdev_state *mds, uuid_t *uuid,
 			u32 *size, u8 *out)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	u32 remaining = *size;
 	u32 offset = 0;
 
 	while (remaining) {
-		u32 xfer_size = min_t(u32, remaining, mds->payload_size);
+		u32 xfer_size = min_t(u32, remaining, cxl_mbox->payload_size);
 		struct cxl_mbox_cmd mbox_cmd;
 		struct cxl_mbox_get_log log;
 		int rc;
@@ -682,7 +688,7 @@ static int cxl_xfer_log(struct cxl_memdev_state *mds, uuid_t *uuid,
 			.payload_out = out,
 		};
 
-		rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+		rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 
 		/*
 		 * The output payload length that indicates the number
@@ -752,22 +758,23 @@ static void cxl_walk_cel(struct cxl_memdev_state *mds, size_t size, u8 *cel)
 
 static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_get_supported_logs *ret;
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
 
-	ret = kvmalloc(mds->payload_size, GFP_KERNEL);
+	ret = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL);
 	if (!ret)
 		return ERR_PTR(-ENOMEM);
 
 	mbox_cmd = (struct cxl_mbox_cmd) {
 		.opcode = CXL_MBOX_OP_GET_SUPPORTED_LOGS,
-		.size_out = mds->payload_size,
+		.size_out = cxl_mbox->payload_size,
 		.payload_out = ret,
 		/* At least the record number field must be valid */
 		.min_out = 2,
 	};
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0) {
 		kvfree(ret);
 		return ERR_PTR(rc);
@@ -910,6 +917,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 				  enum cxl_event_log_type log,
 				  struct cxl_get_event_payload *get_pl)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_clear_event_payload *payload;
 	u16 total = le16_to_cpu(get_pl->record_count);
 	u8 max_handles = CXL_CLEAR_EVENT_MAX_HANDLES;
@@ -920,8 +928,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 	int i;
 
 	/* Payload size may limit the max handles */
-	if (pl_size > mds->payload_size) {
-		max_handles = (mds->payload_size - sizeof(*payload)) /
+	if (pl_size > cxl_mbox->payload_size) {
+		max_handles = (cxl_mbox->payload_size - sizeof(*payload)) /
 			      sizeof(__le16);
 		pl_size = struct_size(payload, handles, max_handles);
 	}
@@ -955,7 +963,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 
 		if (i == max_handles) {
 			payload->nr_recs = i;
-			rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+			rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 			if (rc)
 				goto free_pl;
 			i = 0;
@@ -966,7 +974,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 	if (i) {
 		payload->nr_recs = i;
 		mbox_cmd.size_in = struct_size(payload, handles, i);
-		rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+		rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 		if (rc)
 			goto free_pl;
 	}
@@ -979,6 +987,7 @@ free_pl:
 static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
 				    enum cxl_event_log_type type)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_memdev *cxlmd = mds->cxlds.cxlmd;
 	struct device *dev = mds->cxlds.dev;
 	struct cxl_get_event_payload *payload;
@@ -995,11 +1004,11 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
 			.payload_in = &log_type,
 			.size_in = sizeof(log_type),
 			.payload_out = payload,
-			.size_out = mds->payload_size,
+			.size_out = cxl_mbox->payload_size,
 			.min_out = struct_size(payload, records, 0),
 		};
 
-		rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+		rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 		if (rc) {
 			dev_err_ratelimited(dev,
 				"Event log '%d': Failed to query event records : %d",
@@ -1070,6 +1079,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, CXL);
  */
 static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_get_partition_info pi;
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
@@ -1079,7 +1089,7 @@ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds)
 		.size_out = sizeof(pi),
 		.payload_out = &pi,
 	};
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc)
 		return rc;
 
@@ -1106,6 +1116,7 @@ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds)
  */
 int cxl_dev_state_identify(struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	/* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
 	struct cxl_mbox_identify id;
 	struct cxl_mbox_cmd mbox_cmd;
@@ -1120,7 +1131,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds)
 		.size_out = sizeof(id),
 		.payload_out = &id,
 	};
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0)
 		return rc;
 
@@ -1148,6 +1159,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL);
 
 static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	int rc;
 	u32 sec_out = 0;
 	struct cxl_get_security_output {
@@ -1159,14 +1171,13 @@ static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd)
 		.size_out = sizeof(out),
 	};
 	struct cxl_mbox_cmd mbox_cmd = { .opcode = cmd };
-	struct cxl_dev_state *cxlds = &mds->cxlds;
 
 	if (cmd != CXL_MBOX_OP_SANITIZE && cmd != CXL_MBOX_OP_SECURE_ERASE)
 		return -EINVAL;
 
-	rc = cxl_internal_send_cmd(mds, &sec_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &sec_cmd);
 	if (rc < 0) {
-		dev_err(cxlds->dev, "Failed to get security state : %d", rc);
+		dev_err(cxl_mbox->host, "Failed to get security state : %d", rc);
 		return rc;
 	}
 
@@ -1183,9 +1194,9 @@ static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd)
 	    sec_out & CXL_PMEM_SEC_STATE_LOCKED)
 		return -EINVAL;
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0) {
-		dev_err(cxlds->dev, "Failed to sanitize device : %d", rc);
+		dev_err(cxl_mbox->host, "Failed to sanitize device : %d", rc);
 		return rc;
 	}
 
@@ -1214,7 +1225,7 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd)
 	int rc;
 
 	/* synchronize with cxl_mem_probe() and decoder write operations */
-	device_lock(&cxlmd->dev);
+	guard(device)(&cxlmd->dev);
 	endpoint = cxlmd->endpoint;
 	down_read(&cxl_region_rwsem);
 	/*
@@ -1226,7 +1237,6 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd)
 	else
 		rc = -EBUSY;
 	up_read(&cxl_region_rwsem);
-	device_unlock(&cxlmd->dev);
 
 	return rc;
 }
@@ -1300,6 +1310,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_create_range_info, CXL);
 
 int cxl_set_timestamp(struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_cmd mbox_cmd;
 	struct cxl_mbox_set_timestamp_in pi;
 	int rc;
@@ -1311,7 +1322,7 @@ int cxl_set_timestamp(struct cxl_memdev_state *mds)
 		.payload_in = &pi,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	/*
 	 * Command is optional. Devices may have another way of providing
 	 * a timestamp, or may return all 0s in timestamp fields.
@@ -1328,6 +1339,7 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
 		       struct cxl_region *cxlr)
 {
 	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_mbox_poison_out *po;
 	struct cxl_mbox_poison_in pi;
 	int nr_records = 0;
@@ -1346,12 +1358,12 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
 			.opcode = CXL_MBOX_OP_GET_POISON,
 			.size_in = sizeof(pi),
 			.payload_in = &pi,
-			.size_out = mds->payload_size,
+			.size_out = cxl_mbox->payload_size,
 			.payload_out = po,
 			.min_out = struct_size(po, record, 0),
 		};
 
-		rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+		rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 		if (rc)
 			break;
 
@@ -1382,7 +1394,9 @@ static void free_poison_buf(void *buf)
 /* Get Poison List output buffer is protected by mds->poison.lock */
 static int cxl_poison_alloc_buf(struct cxl_memdev_state *mds)
 {
-	mds->poison.list_out = kvmalloc(mds->payload_size, GFP_KERNEL);
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
+
+	mds->poison.list_out = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL);
 	if (!mds->poison.list_out)
 		return -ENOMEM;
 
@@ -1408,6 +1422,19 @@ int cxl_poison_state_init(struct cxl_memdev_state *mds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_poison_state_init, CXL);
 
+int cxl_mailbox_init(struct cxl_mailbox *cxl_mbox, struct device *host)
+{
+	if (!cxl_mbox || !host)
+		return -EINVAL;
+
+	cxl_mbox->host = host;
+	mutex_init(&cxl_mbox->mbox_mutex);
+	rcuwait_init(&cxl_mbox->mbox_wait);
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mailbox_init, CXL);
+
 struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
 {
 	struct cxl_memdev_state *mds;
@@ -1418,7 +1445,6 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	mutex_init(&mds->mbox_mutex);
 	mutex_init(&mds->event.log_lock);
 	mds->cxlds.dev = dev;
 	mds->cxlds.reg_map.host = dev;

drivers/cxl/core/memdev.c

@@ -58,7 +58,7 @@ static ssize_t payload_max_show(struct device *dev,
 
 	if (!mds)
 		return sysfs_emit(buf, "\n");
-	return sysfs_emit(buf, "%zu\n", mds->payload_size);
+	return sysfs_emit(buf, "%zu\n", cxlds->cxl_mbox.payload_size);
 }
 static DEVICE_ATTR_RO(payload_max);
 
@@ -124,15 +124,16 @@ static ssize_t security_state_show(struct device *dev,
 {
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox;
 	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
 	unsigned long state = mds->security.state;
 	int rc = 0;
 
 	/* sync with latest submission state */
-	mutex_lock(&mds->mbox_mutex);
+	mutex_lock(&cxl_mbox->mbox_mutex);
 	if (mds->security.sanitize_active)
 		rc = sysfs_emit(buf, "sanitize\n");
-	mutex_unlock(&mds->mbox_mutex);
+	mutex_unlock(&cxl_mbox->mbox_mutex);
 	if (rc)
 		return rc;
 
@@ -277,7 +278,7 @@ static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa)
 
 int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 {
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_mbox_inject_poison inject;
 	struct cxl_poison_record record;
 	struct cxl_mbox_cmd mbox_cmd;
@@ -307,13 +308,13 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 		.size_in = sizeof(inject),
 		.payload_in = &inject,
 	};
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc)
 		goto out;
 
 	cxlr = cxl_dpa_to_region(cxlmd, dpa);
 	if (cxlr)
-		dev_warn_once(mds->cxlds.dev,
+		dev_warn_once(cxl_mbox->host,
 			      "poison inject dpa:%#llx region: %s\n", dpa,
 			      dev_name(&cxlr->dev));
 
@@ -332,7 +333,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL);
 
 int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 {
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_mbox_clear_poison clear;
 	struct cxl_poison_record record;
 	struct cxl_mbox_cmd mbox_cmd;
@@ -371,13 +372,13 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 		.payload_in = &clear,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc)
 		goto out;
 
 	cxlr = cxl_dpa_to_region(cxlmd, dpa);
 	if (cxlr)
-		dev_warn_once(mds->cxlds.dev,
+		dev_warn_once(cxl_mbox->host,
 			      "poison clear dpa:%#llx region: %s\n", dpa,
 			      dev_name(&cxlr->dev));
 
@@ -714,6 +715,7 @@ static int cxl_memdev_release_file(struct inode *inode, struct file *file)
  */
 static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_get_fw_info info;
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
@@ -724,7 +726,7 @@ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds)
 		.payload_out = &info,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0)
 		return rc;
 
@@ -748,6 +750,7 @@ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds)
  */
 static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_activate_fw activate;
 	struct cxl_mbox_cmd mbox_cmd;
 
@@ -764,7 +767,7 @@ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot)
 	activate.action = CXL_FW_ACTIVATE_OFFLINE;
 	activate.slot = slot;
 
-	return cxl_internal_send_cmd(mds, &mbox_cmd);
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 }
 
 /**
@@ -779,6 +782,7 @@ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot)
  */
 static int cxl_mem_abort_fw_xfer(struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_transfer_fw *transfer;
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
@@ -798,7 +802,7 @@ static int cxl_mem_abort_fw_xfer(struct cxl_memdev_state *mds)
 
 	transfer->action = CXL_FW_TRANSFER_ACTION_ABORT;
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	kfree(transfer);
 	return rc;
 }
@@ -829,12 +833,13 @@ static enum fw_upload_err cxl_fw_prepare(struct fw_upload *fwl, const u8 *data,
 {
 	struct cxl_memdev_state *mds = fwl->dd_handle;
 	struct cxl_mbox_transfer_fw *transfer;
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 
 	if (!size)
 		return FW_UPLOAD_ERR_INVALID_SIZE;
 
 	mds->fw.oneshot = struct_size(transfer, data, size) <
-			    mds->payload_size;
+			    cxl_mbox->payload_size;
 
 	if (cxl_mem_get_fw_info(mds))
 		return FW_UPLOAD_ERR_HW_ERROR;
@@ -854,6 +859,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data,
 {
 	struct cxl_memdev_state *mds = fwl->dd_handle;
 	struct cxl_dev_state *cxlds = &mds->cxlds;
+	struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox;
 	struct cxl_memdev *cxlmd = cxlds->cxlmd;
 	struct cxl_mbox_transfer_fw *transfer;
 	struct cxl_mbox_cmd mbox_cmd;
@@ -877,7 +883,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data,
 	 * sizeof(*transfer) is 128.  These constraints imply that @cur_size
 	 * will always be 128b aligned.
 	 */
-	cur_size = min_t(size_t, size, mds->payload_size - sizeof(*transfer));
+	cur_size = min_t(size_t, size, cxl_mbox->payload_size - sizeof(*transfer));
 
 	remaining = size - cur_size;
 	size_in = struct_size(transfer, data, cur_size);
@@ -921,7 +927,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data,
 		.poll_count = 30,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0) {
 		rc = FW_UPLOAD_ERR_RW_ERROR;
 		goto out_free;
@@ -1059,16 +1065,17 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_add_memdev, CXL);
 static void sanitize_teardown_notifier(void *data)
 {
 	struct cxl_memdev_state *mds = data;
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct kernfs_node *state;
 
 	/*
 	 * Prevent new irq triggered invocations of the workqueue and
 	 * flush inflight invocations.
 	 */
-	mutex_lock(&mds->mbox_mutex);
+	mutex_lock(&cxl_mbox->mbox_mutex);
 	state = mds->security.sanitize_node;
 	mds->security.sanitize_node = NULL;
-	mutex_unlock(&mds->mbox_mutex);
+	mutex_unlock(&cxl_mbox->mbox_mutex);
 
 	cancel_delayed_work_sync(&mds->security.poll_dwork);
 	sysfs_put(state);

drivers/cxl/core/pci.c

@@ -211,37 +211,6 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, CXL);
 
-static int wait_for_valid(struct pci_dev *pdev, int d)
-{
-	u32 val;
-	int rc;
-
-	/*
-	 * Memory_Info_Valid: When set, indicates that the CXL Range 1 Size high
-	 * and Size Low registers are valid. Must be set within 1 second of
-	 * deassertion of reset to CXL device. Likely it is already set by the
-	 * time this runs, but otherwise give a 1.5 second timeout in case of
-	 * clock skew.
-	 */
-	rc = pci_read_config_dword(pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &val);
-	if (rc)
-		return rc;
-
-	if (val & CXL_DVSEC_MEM_INFO_VALID)
-		return 0;
-
-	msleep(1500);
-
-	rc = pci_read_config_dword(pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &val);
-	if (rc)
-		return rc;
-
-	if (val & CXL_DVSEC_MEM_INFO_VALID)
-		return 0;
-
-	return -ETIMEDOUT;
-}
-
 static int cxl_set_mem_enable(struct cxl_dev_state *cxlds, u16 val)
 {
 	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
@@ -322,11 +291,13 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm)
 	return devm_add_action_or_reset(host, disable_hdm, cxlhdm);
 }
 
-int cxl_dvsec_rr_decode(struct device *dev, int d,
+int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port,
 			struct cxl_endpoint_dvsec_info *info)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
 	int hdm_count, rc, i, ranges = 0;
+	int d = cxlds->cxl_dvsec;
 	u16 cap, ctrl;
 
 	if (!d) {
@@ -353,12 +324,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 	if (!hdm_count || hdm_count > 2)
 		return -EINVAL;
 
-	rc = wait_for_valid(pdev, d);
-	if (rc) {
-		dev_dbg(dev, "Failure awaiting MEM_INFO_VALID (%d)\n", rc);
-		return rc;
-	}
-
 	/*
 	 * The current DVSEC values are moot if the memory capability is
 	 * disabled, and they will remain moot after the HDM Decoder
@@ -376,6 +341,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 		u64 base, size;
 		u32 temp;
 
+		rc = cxl_dvsec_mem_range_valid(cxlds, i);
+		if (rc)
+			return rc;
+
 		rc = pci_read_config_dword(
 			pdev, d + CXL_DVSEC_RANGE_SIZE_HIGH(i), &temp);
 		if (rc)
@@ -390,10 +359,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 
 		size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK;
 		if (!size) {
-			info->dvsec_range[i] = (struct range) {
-				.start = 0,
-				.end = CXL_RESOURCE_NONE,
-			};
 			continue;
 		}
 
@@ -411,12 +376,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 
 		base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK;
 
-		info->dvsec_range[i] = (struct range) {
+		info->dvsec_range[ranges++] = (struct range) {
 			.start = base,
 			.end = base + size - 1
 		};
-
-		ranges++;
 	}
 
 	info->ranges = ranges;
@@ -463,7 +426,15 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 		return -ENODEV;
 	}
 
-	for (i = 0, allowed = 0; info->mem_enabled && i < info->ranges; i++) {
+	if (!info->mem_enabled) {
+		rc = devm_cxl_enable_hdm(&port->dev, cxlhdm);
+		if (rc)
+			return rc;
+
+		return devm_cxl_enable_mem(&port->dev, cxlds);
+	}
+
+	for (i = 0, allowed = 0; i < info->ranges; i++) {
 		struct device *cxld_dev;
 
 		cxld_dev = device_find_child(&root->dev, &info->dvsec_range[i],
@@ -477,7 +448,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 		allowed++;
 	}
 
-	if (!allowed && info->mem_enabled) {
+	if (!allowed) {
 		dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n");
 		return -ENXIO;
 	}
@@ -491,14 +462,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 	 * match. If at least one DVSEC range is enabled and allowed, skip HDM
 	 * Decoder Capability Enable.
 	 */
-	if (info->mem_enabled)
-		return 0;
-
-	rc = devm_cxl_enable_hdm(&port->dev, cxlhdm);
-	if (rc)
-		return rc;
-
-	return devm_cxl_enable_mem(&port->dev, cxlds);
+	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL);
 
@@ -772,22 +736,20 @@ static bool cxl_handle_endpoint_ras(struct cxl_dev_state *cxlds)
 
 static void cxl_dport_map_rch_aer(struct cxl_dport *dport)
 {
-	struct cxl_rcrb_info *ri = &dport->rcrb;
-	void __iomem *dport_aer = NULL;
 	resource_size_t aer_phys;
 	struct device *host;
+	u16 aer_cap;
 
-	if (dport->rch && ri->aer_cap) {
+	aer_cap = cxl_rcrb_to_aer(dport->dport_dev, dport->rcrb.base);
+	if (aer_cap) {
 		host = dport->reg_map.host;
-		aer_phys = ri->aer_cap + ri->base;
-		dport_aer = devm_cxl_iomap_block(host, aer_phys,
-				sizeof(struct aer_capability_regs));
+		aer_phys = aer_cap + dport->rcrb.base;
+		dport->regs.dport_aer = devm_cxl_iomap_block(host, aer_phys,
+						sizeof(struct aer_capability_regs));
 	}
-
-	dport->regs.dport_aer = dport_aer;
 }
 
-static void cxl_dport_map_regs(struct cxl_dport *dport)
+static void cxl_dport_map_ras(struct cxl_dport *dport)
 {
 	struct cxl_register_map *map = &dport->reg_map;
 	struct device *dev = dport->dport_dev;
@@ -797,22 +759,16 @@ static void cxl_dport_map_regs(struct cxl_dport *dport)
 	else if (cxl_map_component_regs(map, &dport->regs.component,
 					BIT(CXL_CM_CAP_CAP_ID_RAS)))
 		dev_dbg(dev, "Failed to map RAS capability.\n");
-
-	if (dport->rch)
-		cxl_dport_map_rch_aer(dport);
 }
 
 static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 {
 	void __iomem *aer_base = dport->regs.dport_aer;
-	struct pci_host_bridge *bridge;
 	u32 aer_cmd_mask, aer_cmd;
 
 	if (!aer_base)
 		return;
 
-	bridge = to_pci_host_bridge(dport->dport_dev);
-
 	/*
 	 * Disable RCH root port command interrupts.
 	 * CXL 3.0 12.2.1.1 - RCH Downstream Port-detected Errors
@@ -821,34 +777,35 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 	 * the root cmd register's interrupts is required. But, PCI spec
 	 * shows these are disabled by default on reset.
 	 */
-	if (bridge->native_aer) {
-		aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN |
-				PCI_ERR_ROOT_CMD_NONFATAL_EN |
-				PCI_ERR_ROOT_CMD_FATAL_EN);
-		aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND);
-		aer_cmd &= ~aer_cmd_mask;
-		writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND);
-	}
+	aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN |
+			PCI_ERR_ROOT_CMD_NONFATAL_EN |
+			PCI_ERR_ROOT_CMD_FATAL_EN);
+	aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND);
+	aer_cmd &= ~aer_cmd_mask;
+	writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND);
 }
 
-void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport)
+/**
+ * cxl_dport_init_ras_reporting - Setup CXL RAS report on this dport
+ * @dport: the cxl_dport that needs to be initialized
+ * @host: host device for devm operations
+ */
+void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
 {
-	struct device *dport_dev = dport->dport_dev;
+	dport->reg_map.host = host;
+	cxl_dport_map_ras(dport);
 
 	if (dport->rch) {
-		struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport_dev);
+		struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport->dport_dev);
 
-		if (host_bridge->native_aer)
-			dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base);
-	}
+		if (!host_bridge->native_aer)
+			return;
 
-	dport->reg_map.host = host;
-	cxl_dport_map_regs(dport);
-
-	if (dport->rch)
+		cxl_dport_map_rch_aer(dport);
 		cxl_disable_rch_root_ints(dport);
+	}
 }
-EXPORT_SYMBOL_NS_GPL(cxl_setup_parent_dport, CXL);
+EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, CXL);
 
 static void cxl_handle_rdport_cor_ras(struct cxl_dev_state *cxlds,
 					  struct cxl_dport *dport)
@@ -915,15 +872,13 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
 	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
 	struct aer_capability_regs aer_regs;
 	struct cxl_dport *dport;
-	struct cxl_port *port;
 	int severity;
 
-	port = cxl_pci_find_port(pdev, &dport);
+	struct cxl_port *port __free(put_cxl_port) =
+		cxl_pci_find_port(pdev, &dport);
 	if (!port)
 		return;
 
-	put_device(&port->dev);
-
 	if (!cxl_rch_get_aer_info(dport->regs.dport_aer, &aer_regs))
 		return;
 
@@ -1076,3 +1031,26 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port)
 				     __cxl_endpoint_decoder_reset_detected);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_reset_detected, CXL);
+
+int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c)
+{
+	int speed, bw;
+	u16 lnksta;
+	u32 width;
+
+	speed = pcie_link_speed_mbps(pdev);
+	if (speed < 0)
+		return speed;
+	speed /= BITS_PER_BYTE;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
+	width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta);
+	bw = speed * width;
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		c[i].read_bandwidth = bw;
+		c[i].write_bandwidth = bw;
+	}
+
+	return 0;
+}

drivers/cxl/core/port.c

@@ -3,7 +3,6 @@
 #include <linux/platform_device.h>
 #include <linux/memregion.h>
 #include <linux/workqueue.h>
-#include <linux/einj-cxl.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/module.h>
@@ -11,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/node.h>
+#include <cxl/einj.h>
 #include <cxlmem.h>
 #include <cxlpci.h>
 #include <cxl.h>
@@ -828,27 +828,20 @@ static void cxl_debugfs_create_dport_dir(struct cxl_dport *dport)
 			    &cxl_einj_inject_fops);
 }
 
-static struct cxl_port *__devm_cxl_add_port(struct device *host,
-					    struct device *uport_dev,
-					    resource_size_t component_reg_phys,
-					    struct cxl_dport *parent_dport)
+static int cxl_port_add(struct cxl_port *port,
+			resource_size_t component_reg_phys,
+			struct cxl_dport *parent_dport)
 {
-	struct cxl_port *port;
-	struct device *dev;
+	struct device *dev __free(put_device) = &port->dev;
 	int rc;
 
-	port = cxl_port_alloc(uport_dev, parent_dport);
-	if (IS_ERR(port))
-		return port;
-
-	dev = &port->dev;
-	if (is_cxl_memdev(uport_dev)) {
-		struct cxl_memdev *cxlmd = to_cxl_memdev(uport_dev);
+	if (is_cxl_memdev(port->uport_dev)) {
+		struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
 		struct cxl_dev_state *cxlds = cxlmd->cxlds;
 
 		rc = dev_set_name(dev, "endpoint%d", port->id);
 		if (rc)
-			goto err;
+			return rc;
 
 		/*
 		 * The endpoint driver already enumerated the component and RAS
@@ -861,19 +854,41 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 	} else if (parent_dport) {
 		rc = dev_set_name(dev, "port%d", port->id);
 		if (rc)
-			goto err;
+			return rc;
 
 		rc = cxl_port_setup_regs(port, component_reg_phys);
 		if (rc)
-			goto err;
-	} else
+			return rc;
+	} else {
 		rc = dev_set_name(dev, "root%d", port->id);
-	if (rc)
-		goto err;
+		if (rc)
+			return rc;
+	}
 
 	rc = device_add(dev);
 	if (rc)
-		goto err;
+		return rc;
+
+	/* Inhibit the cleanup function invoked */
+	dev = NULL;
+	return 0;
+}
+
+static struct cxl_port *__devm_cxl_add_port(struct device *host,
+					    struct device *uport_dev,
+					    resource_size_t component_reg_phys,
+					    struct cxl_dport *parent_dport)
+{
+	struct cxl_port *port;
+	int rc;
+
+	port = cxl_port_alloc(uport_dev, parent_dport);
+	if (IS_ERR(port))
+		return port;
+
+	rc = cxl_port_add(port, component_reg_phys, parent_dport);
+	if (rc)
+		return ERR_PTR(rc);
 
 	rc = devm_add_action_or_reset(host, unregister_port, port);
 	if (rc)
@@ -891,10 +906,6 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 		port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev));
 
 	return port;
-
-err:
-	put_device(dev);
-	return ERR_PTR(rc);
 }
 
 /**
@@ -941,7 +952,7 @@ struct cxl_root *devm_cxl_add_root(struct device *host,
 
 	port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL);
 	if (IS_ERR(port))
-		return (struct cxl_root *)port;
+		return ERR_CAST(port);
 
 	cxl_root = to_cxl_root(port);
 	cxl_root->ops = ops;
@@ -1258,18 +1269,13 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_add_rch_dport, CXL);
 static int add_ep(struct cxl_ep *new)
 {
 	struct cxl_port *port = new->dport->port;
-	int rc;
 
-	device_lock(&port->dev);
-	if (port->dead) {
-		device_unlock(&port->dev);
+	guard(device)(&port->dev);
+	if (port->dead)
 		return -ENXIO;
-	}
-	rc = xa_insert(&port->endpoints, (unsigned long)new->ep, new,
-		       GFP_KERNEL);
-	device_unlock(&port->dev);
 
-	return rc;
+	return xa_insert(&port->endpoints, (unsigned long)new->ep,
+			 new, GFP_KERNEL);
 }
 
 /**
@@ -1393,14 +1399,14 @@ static void delete_endpoint(void *data)
 	struct cxl_port *endpoint = cxlmd->endpoint;
 	struct device *host = endpoint_host(endpoint);
 
-	device_lock(host);
-	if (host->driver && !endpoint->dead) {
-		devm_release_action(host, cxl_unlink_parent_dport, endpoint);
-		devm_release_action(host, cxl_unlink_uport, endpoint);
-		devm_release_action(host, unregister_port, endpoint);
+	scoped_guard(device, host) {
+		if (host->driver && !endpoint->dead) {
+			devm_release_action(host, cxl_unlink_parent_dport, endpoint);
+			devm_release_action(host, cxl_unlink_uport, endpoint);
+			devm_release_action(host, unregister_port, endpoint);
+		}
+		cxlmd->endpoint = NULL;
 	}
-	cxlmd->endpoint = NULL;
-	device_unlock(host);
 	put_device(&endpoint->dev);
 	put_device(host);
 }
@@ -1477,12 +1483,11 @@ static void cxl_detach_ep(void *data)
 			.cxlmd = cxlmd,
 			.depth = i,
 		};
-		struct device *dev;
 		struct cxl_ep *ep;
 		bool died = false;
 
-		dev = bus_find_device(&cxl_bus_type, NULL, &ctx,
-				      port_has_memdev);
+		struct device *dev __free(put_device) =
+			bus_find_device(&cxl_bus_type, NULL, &ctx, port_has_memdev);
 		if (!dev)
 			continue;
 		port = to_cxl_port(dev);
@@ -1512,7 +1517,6 @@ static void cxl_detach_ep(void *data)
 				dev_name(&port->dev));
 			delete_switch_port(port);
 		}
-		put_device(&port->dev);
 		device_unlock(&parent_port->dev);
 	}
 }
@@ -1540,7 +1544,6 @@ static int add_port_attach_ep(struct cxl_memdev *cxlmd,
 			      struct device *dport_dev)
 {
 	struct device *dparent = grandparent(dport_dev);
-	struct cxl_port *port, *parent_port = NULL;
 	struct cxl_dport *dport, *parent_dport;
 	resource_size_t component_reg_phys;
 	int rc;
@@ -1556,50 +1559,52 @@ static int add_port_attach_ep(struct cxl_memdev *cxlmd,
 		return -ENXIO;
 	}
 
-	parent_port = find_cxl_port(dparent, &parent_dport);
+	struct cxl_port *parent_port __free(put_cxl_port) =
+		find_cxl_port(dparent, &parent_dport);
 	if (!parent_port) {
 		/* iterate to create this parent_port */
 		return -EAGAIN;
 	}
 
-	device_lock(&parent_port->dev);
-	if (!parent_port->dev.driver) {
-		dev_warn(&cxlmd->dev,
-			 "port %s:%s disabled, failed to enumerate CXL.mem\n",
-			 dev_name(&parent_port->dev), dev_name(uport_dev));
-		port = ERR_PTR(-ENXIO);
-		goto out;
-	}
-
-	port = find_cxl_port_at(parent_port, dport_dev, &dport);
-	if (!port) {
-		component_reg_phys = find_component_registers(uport_dev);
-		port = devm_cxl_add_port(&parent_port->dev, uport_dev,
-					 component_reg_phys, parent_dport);
-		/* retry find to pick up the new dport information */
-		if (!IS_ERR(port))
-			port = find_cxl_port_at(parent_port, dport_dev, &dport);
-	}
-out:
-	device_unlock(&parent_port->dev);
-
-	if (IS_ERR(port))
-		rc = PTR_ERR(port);
-	else {
-		dev_dbg(&cxlmd->dev, "add to new port %s:%s\n",
-			dev_name(&port->dev), dev_name(port->uport_dev));
-		rc = cxl_add_ep(dport, &cxlmd->dev);
-		if (rc == -EBUSY) {
-			/*
-			 * "can't" happen, but this error code means
-			 * something to the caller, so translate it.
-			 */
-			rc = -ENXIO;
+	/*
+	 * Definition with __free() here to keep the sequence of
+	 * dereferencing the device of the port before the parent_port releasing.
+	 */
+	struct cxl_port *port __free(put_cxl_port) = NULL;
+	scoped_guard(device, &parent_port->dev) {
+		if (!parent_port->dev.driver) {
+			dev_warn(&cxlmd->dev,
+				 "port %s:%s disabled, failed to enumerate CXL.mem\n",
+				 dev_name(&parent_port->dev), dev_name(uport_dev));
+			return -ENXIO;
+		}
+
+		port = find_cxl_port_at(parent_port, dport_dev, &dport);
+		if (!port) {
+			component_reg_phys = find_component_registers(uport_dev);
+			port = devm_cxl_add_port(&parent_port->dev, uport_dev,
+						 component_reg_phys, parent_dport);
+			if (IS_ERR(port))
+				return PTR_ERR(port);
+
+			/* retry find to pick up the new dport information */
+			port = find_cxl_port_at(parent_port, dport_dev, &dport);
+			if (!port)
+				return -ENXIO;
 		}
-		put_device(&port->dev);
 	}
 
-	put_device(&parent_port->dev);
+	dev_dbg(&cxlmd->dev, "add to new port %s:%s\n",
+		dev_name(&port->dev), dev_name(port->uport_dev));
+	rc = cxl_add_ep(dport, &cxlmd->dev);
+	if (rc == -EBUSY) {
+		/*
+		 * "can't" happen, but this error code means
+		 * something to the caller, so translate it.
+		 */
+		rc = -ENXIO;
+	}
+
 	return rc;
 }
 
@@ -1630,7 +1635,6 @@ retry:
 		struct device *dport_dev = grandparent(iter);
 		struct device *uport_dev;
 		struct cxl_dport *dport;
-		struct cxl_port *port;
 
 		/*
 		 * The terminal "grandparent" in PCI is NULL and @platform_bus
@@ -1649,7 +1653,8 @@ retry:
 		dev_dbg(dev, "scan: iter: %s dport_dev: %s parent: %s\n",
 			dev_name(iter), dev_name(dport_dev),
 			dev_name(uport_dev));
-		port = find_cxl_port(dport_dev, &dport);
+		struct cxl_port *port __free(put_cxl_port) =
+			find_cxl_port(dport_dev, &dport);
 		if (port) {
 			dev_dbg(&cxlmd->dev,
 				"found already registered port %s:%s\n",
@@ -1664,18 +1669,13 @@ retry:
 			 * the parent_port lock as the current port may be being
 			 * reaped.
 			 */
-			if (rc && rc != -EBUSY) {
-				put_device(&port->dev);
+			if (rc && rc != -EBUSY)
 				return rc;
-			}
 
 			/* Any more ports to add between this one and the root? */
-			if (!dev_is_cxl_root_child(&port->dev)) {
-				put_device(&port->dev);
+			if (!dev_is_cxl_root_child(&port->dev))
 				continue;
-			}
 
-			put_device(&port->dev);
 			return 0;
 		}
 
@@ -1983,7 +1983,6 @@ EXPORT_SYMBOL_NS_GPL(cxl_decoder_add_locked, CXL);
 int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
 {
 	struct cxl_port *port;
-	int rc;
 
 	if (WARN_ON_ONCE(!cxld))
 		return -EINVAL;
@@ -1993,11 +1992,8 @@ int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
 
 	port = to_cxl_port(cxld->dev.parent);
 
-	device_lock(&port->dev);
-	rc = cxl_decoder_add_locked(cxld, target_map);
-	device_unlock(&port->dev);
-
-	return rc;
+	guard(device)(&port->dev);
+	return cxl_decoder_add_locked(cxld, target_map);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_decoder_add, CXL);
 
@@ -2241,6 +2237,26 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_get_perf_coordinates, CXL);
 
+int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
+					struct access_coordinate *c)
+{
+	struct cxl_dport *dport = port->parent_dport;
+
+	/* Check this port is connected to a switch DSP and not an RP */
+	if (parent_port_is_cxl_root(to_cxl_port(port->dev.parent)))
+		return -ENODEV;
+
+	if (!coordinates_valid(dport->coord))
+		return -EINVAL;
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		c[i].read_bandwidth = dport->coord[i].read_bandwidth;
+		c[i].write_bandwidth = dport->coord[i].write_bandwidth;
+	}
+
+	return 0;
+}
+
 /* for user tooling to ensure port disable work has completed */
 static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count)
 {

drivers/cxl/core/region.c

@@ -1983,6 +1983,7 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		 * then the region is already committed.
 		 */
 		p->state = CXL_CONFIG_COMMIT;
+		cxl_region_shared_upstream_bandwidth_update(cxlr);
 
 		return 0;
 	}
@@ -2004,6 +2005,7 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		if (rc)
 			return rc;
 		p->state = CXL_CONFIG_ACTIVE;
+		cxl_region_shared_upstream_bandwidth_update(cxlr);
 	}
 
 	cxled->cxld.interleave_ways = p->interleave_ways;
@@ -2313,8 +2315,6 @@ static void unregister_region(void *_cxlr)
 	struct cxl_region_params *p = &cxlr->params;
 	int i;
 
-	unregister_memory_notifier(&cxlr->memory_notifier);
-	unregister_mt_adistance_algorithm(&cxlr->adist_notifier);
 	device_del(&cxlr->dev);
 
 	/*
@@ -2391,18 +2391,6 @@ static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid)
 	return true;
 }
 
-static int cxl_region_nid(struct cxl_region *cxlr)
-{
-	struct cxl_region_params *p = &cxlr->params;
-	struct resource *res;
-
-	guard(rwsem_read)(&cxl_region_rwsem);
-	res = p->res;
-	if (!res)
-		return NUMA_NO_NODE;
-	return phys_to_target_node(res->start);
-}
-
 static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
 					  unsigned long action, void *arg)
 {
@@ -2415,7 +2403,11 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
 	if (nid == NUMA_NO_NODE || action != MEM_ONLINE)
 		return NOTIFY_DONE;
 
-	region_nid = cxl_region_nid(cxlr);
+	/*
+	 * No need to hold cxl_region_rwsem; region parameters are stable
+	 * within the cxl_region driver.
+	 */
+	region_nid = phys_to_target_node(cxlr->params.res->start);
 	if (nid != region_nid)
 		return NOTIFY_DONE;
 
@@ -2434,7 +2426,11 @@ static int cxl_region_calculate_adistance(struct notifier_block *nb,
 	int *adist = data;
 	int region_nid;
 
-	region_nid = cxl_region_nid(cxlr);
+	/*
+	 * No need to hold cxl_region_rwsem; region parameters are stable
+	 * within the cxl_region driver.
+	 */
+	region_nid = phys_to_target_node(cxlr->params.res->start);
 	if (nid != region_nid)
 		return NOTIFY_OK;
 
@@ -2484,14 +2480,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 	if (rc)
 		goto err;
 
-	cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback;
-	cxlr->memory_notifier.priority = CXL_CALLBACK_PRI;
-	register_memory_notifier(&cxlr->memory_notifier);
-
-	cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance;
-	cxlr->adist_notifier.priority = 100;
-	register_mt_adistance_algorithm(&cxlr->adist_notifier);
-
 	rc = devm_add_action_or_reset(port->uport_dev, unregister_region, cxlr);
 	if (rc)
 		return ERR_PTR(rc);
@@ -3094,11 +3082,11 @@ static void cxlr_release_nvdimm(void *_cxlr)
 	struct cxl_region *cxlr = _cxlr;
 	struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb;
 
-	device_lock(&cxl_nvb->dev);
-	if (cxlr->cxlr_pmem)
-		devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister,
-				    cxlr->cxlr_pmem);
-	device_unlock(&cxl_nvb->dev);
+	scoped_guard(device, &cxl_nvb->dev) {
+		if (cxlr->cxlr_pmem)
+			devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister,
+					    cxlr->cxlr_pmem);
+	}
 	cxlr->cxl_nvb = NULL;
 	put_device(&cxl_nvb->dev);
 }
@@ -3134,13 +3122,14 @@ static int devm_cxl_add_pmem_region(struct cxl_region *cxlr)
 	dev_dbg(&cxlr->dev, "%s: register %s\n", dev_name(dev->parent),
 		dev_name(dev));
 
-	device_lock(&cxl_nvb->dev);
-	if (cxl_nvb->dev.driver)
-		rc = devm_add_action_or_reset(&cxl_nvb->dev,
-					      cxlr_pmem_unregister, cxlr_pmem);
-	else
-		rc = -ENXIO;
-	device_unlock(&cxl_nvb->dev);
+	scoped_guard(device, &cxl_nvb->dev) {
+		if (cxl_nvb->dev.driver)
+			rc = devm_add_action_or_reset(&cxl_nvb->dev,
+						      cxlr_pmem_unregister,
+						      cxlr_pmem);
+		else
+			rc = -ENXIO;
+	}
 
 	if (rc)
 		goto err_bridge;
@@ -3386,6 +3375,14 @@ static int is_system_ram(struct resource *res, void *arg)
 	return 1;
 }
 
+static void shutdown_notifiers(void *_cxlr)
+{
+	struct cxl_region *cxlr = _cxlr;
+
+	unregister_memory_notifier(&cxlr->memory_notifier);
+	unregister_mt_adistance_algorithm(&cxlr->adist_notifier);
+}
+
 static int cxl_region_probe(struct device *dev)
 {
 	struct cxl_region *cxlr = to_cxl_region(dev);
@@ -3418,6 +3415,18 @@ static int cxl_region_probe(struct device *dev)
 out:
 	up_read(&cxl_region_rwsem);
 
+	if (rc)
+		return rc;
+
+	cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback;
+	cxlr->memory_notifier.priority = CXL_CALLBACK_PRI;
+	register_memory_notifier(&cxlr->memory_notifier);
+
+	cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance;
+	cxlr->adist_notifier.priority = 100;
+	register_mt_adistance_algorithm(&cxlr->adist_notifier);
+
+	rc = devm_add_action_or_reset(&cxlr->dev, shutdown_notifiers, cxlr);
 	if (rc)
 		return rc;
 

drivers/cxl/cxl.h

@@ -744,6 +744,7 @@ struct cxl_root *find_cxl_root(struct cxl_port *port);
 void put_cxl_root(struct cxl_root *cxl_root);
 DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T))
 
+DEFINE_FREE(put_cxl_port, struct cxl_port *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
 int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd);
 void cxl_bus_rescan(void);
 void cxl_bus_drain(void);
@@ -762,9 +763,10 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
 
 #ifdef CONFIG_PCIEAER_CXL
 void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport);
+void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host);
 #else
-static inline void cxl_setup_parent_dport(struct device *host,
-					  struct cxl_dport *dport) { }
+static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
+						struct device *host) { }
 #endif
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
@@ -809,7 +811,7 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port,
 int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 				struct cxl_endpoint_dvsec_info *info);
 int devm_cxl_add_passthrough_decoder(struct cxl_port *port);
-int cxl_dvsec_rr_decode(struct device *dev, int dvsec,
+int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port,
 			struct cxl_endpoint_dvsec_info *info);
 
 bool is_cxl_region(struct device *dev);
@@ -889,6 +891,7 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 				      struct access_coordinate *coord);
 void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
 				    struct cxl_endpoint_decoder *cxled);
+void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr);
 
 void cxl_memdev_update_perf(struct cxl_memdev *cxlmd);
 

drivers/cxl/cxlmem.h

@@ -3,11 +3,12 @@
 #ifndef __CXL_MEM_H__
 #define __CXL_MEM_H__
 #include <uapi/linux/cxl_mem.h>
+#include <linux/pci.h>
 #include <linux/cdev.h>
 #include <linux/uuid.h>
-#include <linux/rcuwait.h>
-#include <linux/cxl-event.h>
 #include <linux/node.h>
+#include <cxl/event.h>
+#include <cxl/mailbox.h>
 #include "cxl.h"
 
 /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
@@ -397,11 +398,13 @@ enum cxl_devtype {
  * struct cxl_dpa_perf - DPA performance property entry
  * @dpa_range: range for DPA address
  * @coord: QoS performance data (i.e. latency, bandwidth)
+ * @cdat_coord: raw QoS performance data from CDAT
  * @qos_class: QoS Class cookies
  */
 struct cxl_dpa_perf {
 	struct range dpa_range;
 	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX];
 	int qos_class;
 };
 
@@ -424,6 +427,7 @@ struct cxl_dpa_perf {
  * @ram_res: Active Volatile memory capacity configuration
  * @serial: PCIe Device Serial Number
  * @type: Generic Memory Class device or Vendor Specific Memory device
+ * @cxl_mbox: CXL mailbox context
  */
 struct cxl_dev_state {
 	struct device *dev;
@@ -438,8 +442,14 @@ struct cxl_dev_state {
 	struct resource ram_res;
 	u64 serial;
 	enum cxl_devtype type;
+	struct cxl_mailbox cxl_mbox;
 };
 
+static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox)
+{
+	return dev_get_drvdata(cxl_mbox->host);
+}
+
 /**
  * struct cxl_memdev_state - Generic Type-3 Memory Device Class driver data
  *
@@ -448,11 +458,8 @@ struct cxl_dev_state {
  * the functionality related to that like Identify Memory Device and Get
  * Partition Info
  * @cxlds: Core driver state common across Type-2 and Type-3 devices
- * @payload_size: Size of space for payload
- *                (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register)
  * @lsa_size: Size of Label Storage Area
  *                (CXL 2.0 8.2.9.5.1.1 Identify Memory Device)
- * @mbox_mutex: Mutex to synchronize mailbox access.
  * @firmware_version: Firmware version for the memory device.
  * @enabled_cmds: Hardware commands found enabled in CEL.
  * @exclusive_cmds: Commands that are kernel-internal only
@@ -470,17 +477,13 @@ struct cxl_dev_state {
  * @poison: poison driver state info
  * @security: security driver state info
  * @fw: firmware upload / activation state
- * @mbox_wait: RCU wait for mbox send completely
- * @mbox_send: @dev specific transport for transmitting mailbox commands
  *
  * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for
  * details on capacity parameters.
  */
 struct cxl_memdev_state {
 	struct cxl_dev_state cxlds;
-	size_t payload_size;
 	size_t lsa_size;
-	struct mutex mbox_mutex; /* Protects device mailbox and firmware */
 	char firmware_version[0x10];
 	DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX);
 	DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
@@ -500,10 +503,6 @@ struct cxl_memdev_state {
 	struct cxl_poison_state poison;
 	struct cxl_security_state security;
 	struct cxl_fw_state fw;
-
-	struct rcuwait mbox_wait;
-	int (*mbox_send)(struct cxl_memdev_state *mds,
-			 struct cxl_mbox_cmd *cmd);
 };
 
 static inline struct cxl_memdev_state *
@@ -814,7 +813,7 @@ enum {
 	CXL_PMEM_SEC_PASS_USER,
 };
 
-int cxl_internal_send_cmd(struct cxl_memdev_state *mds,
+int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox,
 			  struct cxl_mbox_cmd *cmd);
 int cxl_dev_state_identify(struct cxl_memdev_state *mds);
 int cxl_await_media_ready(struct cxl_dev_state *cxlds);

drivers/cxl/mem.c

@@ -109,7 +109,6 @@ static int cxl_mem_probe(struct device *dev)
 	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct device *endpoint_parent;
-	struct cxl_port *parent_port;
 	struct cxl_dport *dport;
 	struct dentry *dentry;
 	int rc;
@@ -146,7 +145,8 @@ static int cxl_mem_probe(struct device *dev)
 	if (rc)
 		return rc;
 
-	parent_port = cxl_mem_find_port(cxlmd, &dport);
+	struct cxl_port *parent_port __free(put_cxl_port) =
+		cxl_mem_find_port(cxlmd, &dport);
 	if (!parent_port) {
 		dev_err(dev, "CXL port topology not found\n");
 		return -ENXIO;
@@ -166,23 +166,20 @@ static int cxl_mem_probe(struct device *dev)
 	else
 		endpoint_parent = &parent_port->dev;
 
-	cxl_setup_parent_dport(dev, dport);
+	cxl_dport_init_ras_reporting(dport, dev);
 
-	device_lock(endpoint_parent);
-	if (!endpoint_parent->driver) {
-		dev_err(dev, "CXL port topology %s not enabled\n",
-			dev_name(endpoint_parent));
-		rc = -ENXIO;
-		goto unlock;
+	scoped_guard(device, endpoint_parent) {
+		if (!endpoint_parent->driver) {
+			dev_err(dev, "CXL port topology %s not enabled\n",
+				dev_name(endpoint_parent));
+			return -ENXIO;
+		}
+
+		rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport);
+		if (rc)
+			return rc;
 	}
 
-	rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport);
-unlock:
-	device_unlock(endpoint_parent);
-	put_device(&parent_port->dev);
-	if (rc)
-		return rc;
-
 	/*
 	 * The kernel may be operating out of CXL memory on this device,
 	 * there is no spec defined way to determine whether this device

drivers/cxl/pci.c

@@ -11,6 +11,7 @@
 #include <linux/pci.h>
 #include <linux/aer.h>
 #include <linux/io.h>
+#include <cxl/mailbox.h>
 #include "cxlmem.h"
 #include "cxlpci.h"
 #include "cxl.h"
@@ -124,6 +125,7 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id)
 	u16 opcode;
 	struct cxl_dev_id *dev_id = id;
 	struct cxl_dev_state *cxlds = dev_id->cxlds;
+	struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox;
 	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
 
 	if (!cxl_mbox_background_complete(cxlds))
@@ -132,13 +134,13 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id)
 	reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET);
 	opcode = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg);
 	if (opcode == CXL_MBOX_OP_SANITIZE) {
-		mutex_lock(&mds->mbox_mutex);
+		mutex_lock(&cxl_mbox->mbox_mutex);
 		if (mds->security.sanitize_node)
 			mod_delayed_work(system_wq, &mds->security.poll_dwork, 0);
-		mutex_unlock(&mds->mbox_mutex);
+		mutex_unlock(&cxl_mbox->mbox_mutex);
 	} else {
 		/* short-circuit the wait in __cxl_pci_mbox_send_cmd() */
-		rcuwait_wake_up(&mds->mbox_wait);
+		rcuwait_wake_up(&cxl_mbox->mbox_wait);
 	}
 
 	return IRQ_HANDLED;
@@ -152,8 +154,9 @@ static void cxl_mbox_sanitize_work(struct work_struct *work)
 	struct cxl_memdev_state *mds =
 		container_of(work, typeof(*mds), security.poll_dwork.work);
 	struct cxl_dev_state *cxlds = &mds->cxlds;
+	struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox;
 
-	mutex_lock(&mds->mbox_mutex);
+	mutex_lock(&cxl_mbox->mbox_mutex);
 	if (cxl_mbox_background_complete(cxlds)) {
 		mds->security.poll_tmo_secs = 0;
 		if (mds->security.sanitize_node)
@@ -167,12 +170,12 @@ static void cxl_mbox_sanitize_work(struct work_struct *work)
 		mds->security.poll_tmo_secs = min(15 * 60, timeout);
 		schedule_delayed_work(&mds->security.poll_dwork, timeout * HZ);
 	}
-	mutex_unlock(&mds->mbox_mutex);
+	mutex_unlock(&cxl_mbox->mbox_mutex);
 }
 
 /**
  * __cxl_pci_mbox_send_cmd() - Execute a mailbox command
- * @mds: The memory device driver data
+ * @cxl_mbox: CXL mailbox context
  * @mbox_cmd: Command to send to the memory device.
  *
  * Context: Any context. Expects mbox_mutex to be held.
@@ -192,17 +195,18 @@ static void cxl_mbox_sanitize_work(struct work_struct *work)
  * not need to coordinate with each other. The driver only uses the primary
  * mailbox.
  */
-static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds,
+static int __cxl_pci_mbox_send_cmd(struct cxl_mailbox *cxl_mbox,
 				   struct cxl_mbox_cmd *mbox_cmd)
 {
-	struct cxl_dev_state *cxlds = &mds->cxlds;
+	struct cxl_dev_state *cxlds = mbox_to_cxlds(cxl_mbox);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
 	void __iomem *payload = cxlds->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET;
 	struct device *dev = cxlds->dev;
 	u64 cmd_reg, status_reg;
 	size_t out_len;
 	int rc;
 
-	lockdep_assert_held(&mds->mbox_mutex);
+	lockdep_assert_held(&cxl_mbox->mbox_mutex);
 
 	/*
 	 * Here are the steps from 8.2.8.4 of the CXL 2.0 spec.
@@ -315,10 +319,10 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds,
 
 		timeout = mbox_cmd->poll_interval_ms;
 		for (i = 0; i < mbox_cmd->poll_count; i++) {
-			if (rcuwait_wait_event_timeout(&mds->mbox_wait,
-				       cxl_mbox_background_complete(cxlds),
-				       TASK_UNINTERRUPTIBLE,
-				       msecs_to_jiffies(timeout)) > 0)
+			if (rcuwait_wait_event_timeout(&cxl_mbox->mbox_wait,
+						       cxl_mbox_background_complete(cxlds),
+						       TASK_UNINTERRUPTIBLE,
+						       msecs_to_jiffies(timeout)) > 0)
 				break;
 		}
 
@@ -360,7 +364,7 @@ success:
 		 */
 		size_t n;
 
-		n = min3(mbox_cmd->size_out, mds->payload_size, out_len);
+		n = min3(mbox_cmd->size_out, cxl_mbox->payload_size, out_len);
 		memcpy_fromio(mbox_cmd->payload_out, payload, n);
 		mbox_cmd->size_out = n;
 	} else {
@@ -370,14 +374,14 @@ success:
 	return 0;
 }
 
-static int cxl_pci_mbox_send(struct cxl_memdev_state *mds,
+static int cxl_pci_mbox_send(struct cxl_mailbox *cxl_mbox,
 			     struct cxl_mbox_cmd *cmd)
 {
 	int rc;
 
-	mutex_lock_io(&mds->mbox_mutex);
-	rc = __cxl_pci_mbox_send_cmd(mds, cmd);
-	mutex_unlock(&mds->mbox_mutex);
+	mutex_lock_io(&cxl_mbox->mbox_mutex);
+	rc = __cxl_pci_mbox_send_cmd(cxl_mbox, cmd);
+	mutex_unlock(&cxl_mbox->mbox_mutex);
 
 	return rc;
 }
@@ -385,6 +389,7 @@ static int cxl_pci_mbox_send(struct cxl_memdev_state *mds,
 static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail)
 {
 	struct cxl_dev_state *cxlds = &mds->cxlds;
+	struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox;
 	const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET);
 	struct device *dev = cxlds->dev;
 	unsigned long timeout;
@@ -417,8 +422,8 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail)
 		return -ETIMEDOUT;
 	}
 
-	mds->mbox_send = cxl_pci_mbox_send;
-	mds->payload_size =
+	cxl_mbox->mbox_send = cxl_pci_mbox_send;
+	cxl_mbox->payload_size =
 		1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap);
 
 	/*
@@ -428,16 +433,15 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail)
 	 * there's no point in going forward. If the size is too large, there's
 	 * no harm is soft limiting it.
 	 */
-	mds->payload_size = min_t(size_t, mds->payload_size, SZ_1M);
-	if (mds->payload_size < 256) {
+	cxl_mbox->payload_size = min_t(size_t, cxl_mbox->payload_size, SZ_1M);
+	if (cxl_mbox->payload_size < 256) {
 		dev_err(dev, "Mailbox is too small (%zub)",
-			mds->payload_size);
+			cxl_mbox->payload_size);
 		return -ENXIO;
 	}
 
-	dev_dbg(dev, "Mailbox payload sized %zu", mds->payload_size);
+	dev_dbg(dev, "Mailbox payload sized %zu", cxl_mbox->payload_size);
 
-	rcuwait_init(&mds->mbox_wait);
 	INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work);
 
 	/* background command interrupts are optional */
@@ -473,7 +477,6 @@ static bool is_cxl_restricted(struct pci_dev *pdev)
 static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev,
 				  struct cxl_register_map *map)
 {
-	struct cxl_port *port;
 	struct cxl_dport *dport;
 	resource_size_t component_reg_phys;
 
@@ -482,14 +485,12 @@ static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev,
 		.resource = CXL_RESOURCE_NONE,
 	};
 
-	port = cxl_pci_find_port(pdev, &dport);
+	struct cxl_port *port __free(put_cxl_port) =
+		cxl_pci_find_port(pdev, &dport);
 	if (!port)
 		return -EPROBE_DEFER;
 
 	component_reg_phys = cxl_rcd_component_reg_phys(&pdev->dev, dport);
-
-	put_device(&port->dev);
-
 	if (component_reg_phys == CXL_RESOURCE_NONE)
 		return -ENXIO;
 
@@ -578,9 +579,10 @@ static void free_event_buf(void *buf)
  */
 static int cxl_mem_alloc_event_buf(struct cxl_memdev_state *mds)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_get_event_payload *buf;
 
-	buf = kvmalloc(mds->payload_size, GFP_KERNEL);
+	buf = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 	mds->event.buf = buf;
@@ -653,6 +655,7 @@ static int cxl_event_req_irq(struct cxl_dev_state *cxlds, u8 setting)
 static int cxl_event_get_int_policy(struct cxl_memdev_state *mds,
 				    struct cxl_event_interrupt_policy *policy)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_cmd mbox_cmd = {
 		.opcode = CXL_MBOX_OP_GET_EVT_INT_POLICY,
 		.payload_out = policy,
@@ -660,7 +663,7 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds,
 	};
 	int rc;
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0)
 		dev_err(mds->cxlds.dev,
 			"Failed to get event interrupt policy : %d", rc);
@@ -671,6 +674,7 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds,
 static int cxl_event_config_msgnums(struct cxl_memdev_state *mds,
 				    struct cxl_event_interrupt_policy *policy)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
 
@@ -687,7 +691,7 @@ static int cxl_event_config_msgnums(struct cxl_memdev_state *mds,
 		.size_in = sizeof(*policy),
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0) {
 		dev_err(mds->cxlds.dev, "Failed to set event interrupt policy : %d",
 			rc);
@@ -786,6 +790,23 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge,
 	return 0;
 }
 
+static int cxl_pci_type3_init_mailbox(struct cxl_dev_state *cxlds)
+{
+	int rc;
+
+	/*
+	 * Fail the init if there's no mailbox. For a type3 this is out of spec.
+	 */
+	if (!cxlds->reg_map.device_map.mbox.valid)
+		return -ENODEV;
+
+	rc = cxl_mailbox_init(&cxlds->cxl_mbox, cxlds->dev);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
 static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus);
@@ -846,6 +867,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		dev_dbg(&pdev->dev, "Failed to map RAS capability.\n");
 
+	rc = cxl_pci_type3_init_mailbox(cxlds);
+	if (rc)
+		return rc;
+
 	rc = cxl_await_media_ready(cxlds);
 	if (rc == 0)
 		cxlds->media_ready = true;

drivers/cxl/pmem.c

@@ -102,13 +102,15 @@ static int cxl_pmem_get_config_size(struct cxl_memdev_state *mds,
 				    struct nd_cmd_get_config_size *cmd,
 				    unsigned int buf_len)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
+
 	if (sizeof(*cmd) > buf_len)
 		return -EINVAL;
 
 	*cmd = (struct nd_cmd_get_config_size){
 		.config_size = mds->lsa_size,
 		.max_xfer =
-			mds->payload_size - sizeof(struct cxl_mbox_set_lsa),
+			cxl_mbox->payload_size - sizeof(struct cxl_mbox_set_lsa),
 	};
 
 	return 0;
@@ -118,6 +120,7 @@ static int cxl_pmem_get_config_data(struct cxl_memdev_state *mds,
 				    struct nd_cmd_get_config_data_hdr *cmd,
 				    unsigned int buf_len)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_get_lsa get_lsa;
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
@@ -139,7 +142,7 @@ static int cxl_pmem_get_config_data(struct cxl_memdev_state *mds,
 		.payload_out = cmd->out_buf,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	cmd->status = 0;
 
 	return rc;
@@ -149,6 +152,7 @@ static int cxl_pmem_set_config_data(struct cxl_memdev_state *mds,
 				    struct nd_cmd_set_config_hdr *cmd,
 				    unsigned int buf_len)
 {
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
 	struct cxl_mbox_set_lsa *set_lsa;
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
@@ -175,7 +179,7 @@ static int cxl_pmem_set_config_data(struct cxl_memdev_state *mds,
 		.size_in = struct_size(set_lsa, data, cmd->in_length),
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 
 	/*
 	 * Set "firmware" status (4-packed bytes at the end of the input
@@ -233,15 +237,13 @@ static int detach_nvdimm(struct device *dev, void *data)
 	if (!is_cxl_nvdimm(dev))
 		return 0;
 
-	device_lock(dev);
-	if (!dev->driver)
-		goto out;
-
-	cxl_nvd = to_cxl_nvdimm(dev);
-	if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data)
-		release = true;
-out:
-	device_unlock(dev);
+	scoped_guard(device, dev) {
+		if (dev->driver) {
+			cxl_nvd = to_cxl_nvdimm(dev);
+			if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data)
+				release = true;
+		}
+	}
 	if (release)
 		device_release_driver(dev);
 	return 0;

drivers/cxl/port.c

@@ -98,7 +98,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	struct cxl_port *root;
 	int rc;
 
-	rc = cxl_dvsec_rr_decode(cxlds->dev, cxlds->cxl_dvsec, &info);
+	rc = cxl_dvsec_rr_decode(cxlds->dev, port, &info);
 	if (rc < 0)
 		return rc;
 

drivers/cxl/security.c

@@ -14,6 +14,7 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm,
 {
 	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
 	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
 	unsigned long security_flags = 0;
 	struct cxl_get_security_output {
@@ -29,7 +30,7 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm,
 		.payload_out = &out,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0)
 		return 0;
 
@@ -70,7 +71,7 @@ static int cxl_pmem_security_change_key(struct nvdimm *nvdimm,
 {
 	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
 	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_mbox_cmd mbox_cmd;
 	struct cxl_set_pass set_pass;
 
@@ -87,7 +88,7 @@ static int cxl_pmem_security_change_key(struct nvdimm *nvdimm,
 		.payload_in = &set_pass,
 	};
 
-	return cxl_internal_send_cmd(mds, &mbox_cmd);
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 }
 
 static int __cxl_pmem_security_disable(struct nvdimm *nvdimm,
@@ -96,7 +97,7 @@ static int __cxl_pmem_security_disable(struct nvdimm *nvdimm,
 {
 	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
 	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_disable_pass dis_pass;
 	struct cxl_mbox_cmd mbox_cmd;
 
@@ -112,7 +113,7 @@ static int __cxl_pmem_security_disable(struct nvdimm *nvdimm,
 		.payload_in = &dis_pass,
 	};
 
-	return cxl_internal_send_cmd(mds, &mbox_cmd);
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 }
 
 static int cxl_pmem_security_disable(struct nvdimm *nvdimm,
@@ -131,12 +132,12 @@ static int cxl_pmem_security_freeze(struct nvdimm *nvdimm)
 {
 	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
 	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_mbox_cmd mbox_cmd = {
 		.opcode = CXL_MBOX_OP_FREEZE_SECURITY,
 	};
 
-	return cxl_internal_send_cmd(mds, &mbox_cmd);
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 }
 
 static int cxl_pmem_security_unlock(struct nvdimm *nvdimm,
@@ -144,7 +145,7 @@ static int cxl_pmem_security_unlock(struct nvdimm *nvdimm,
 {
 	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
 	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	u8 pass[NVDIMM_PASSPHRASE_LEN];
 	struct cxl_mbox_cmd mbox_cmd;
 	int rc;
@@ -156,7 +157,7 @@ static int cxl_pmem_security_unlock(struct nvdimm *nvdimm,
 		.payload_in = pass,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0)
 		return rc;
 
@@ -169,7 +170,7 @@ static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm,
 {
 	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
 	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
 	struct cxl_mbox_cmd mbox_cmd;
 	struct cxl_pass_erase erase;
 	int rc;
@@ -185,7 +186,7 @@ static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm,
 		.payload_in = &erase,
 	};
 
-	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc < 0)
 		return rc;
 

drivers/md/dm-bufio.c

@@ -529,9 +529,6 @@ static struct dm_buffer *list_to_buffer(struct list_head *l)
 {
 	struct lru_entry *le = list_entry(l, struct lru_entry, list);
 
-	if (!le)
-		return NULL;
-
 	return le_to_buffer(le);
 }
 

drivers/md/dm-cache-target.c

@@ -1368,7 +1368,7 @@ static void mg_copy(struct work_struct *ws)
 			 */
 			bool rb = bio_detain_shared(mg->cache, mg->op->oblock, mg->overwrite_bio);
 
-			BUG_ON(rb); /* An exclussive lock must _not_ be held for this block */
+			BUG_ON(rb); /* An exclusive lock must _not_ be held for this block */
 			mg->overwrite_bio = NULL;
 			inc_io_migrations(mg->cache);
 			mg_full_copy(ws);
@@ -3200,8 +3200,6 @@ static int parse_cblock_range(struct cache *cache, const char *str,
 	 * Try and parse form (ii) first.
 	 */
 	r = sscanf(str, "%llu-%llu%c", &b, &e, &dummy);
-	if (r < 0)
-		return r;
 
 	if (r == 2) {
 		result->begin = to_cblock(b);
@@ -3213,8 +3211,6 @@ static int parse_cblock_range(struct cache *cache, const char *str,
 	 * That didn't work, try form (i).
 	 */
 	r = sscanf(str, "%llu%c", &b, &dummy);
-	if (r < 0)
-		return r;
 
 	if (r == 1) {
 		result->begin = to_cblock(b);

drivers/md/dm-clone-metadata.c

@@ -530,10 +530,7 @@ static int __load_bitset_in_core(struct dm_clone_metadata *cmd)
 		return r;
 
 	for (i = 0; ; i++) {
-		if (dm_bitset_cursor_get_value(&c))
-			__set_bit(i, cmd->region_map);
-		else
-			__clear_bit(i, cmd->region_map);
+		__assign_bit(i, cmd->region_map, dm_bitset_cursor_get_value(&c));
 
 		if (i >= (cmd->nr_regions - 1))
 			break;

drivers/md/dm-crypt.c

@@ -147,6 +147,7 @@ enum cipher_flags {
 	CRYPT_MODE_INTEGRITY_AEAD,	/* Use authenticated mode for cipher */
 	CRYPT_IV_LARGE_SECTORS,		/* Calculate IV from sector_size, not 512B sectors */
 	CRYPT_ENCRYPT_PREPROCESS,	/* Must preprocess data for encryption (elephant) */
+	CRYPT_KEY_MAC_SIZE_SET,		/* The integrity_key_size option was used */
 };
 
 /*
@@ -2613,35 +2614,31 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	key = request_key(type, key_desc + 1, NULL);
 	if (IS_ERR(key)) {
-		kfree_sensitive(new_key_string);
-		return PTR_ERR(key);
+		ret = PTR_ERR(key);
+		goto free_new_key_string;
 	}
 
 	down_read(&key->sem);
-
 	ret = set_key(cc, key);
-	if (ret < 0) {
-		up_read(&key->sem);
-		key_put(key);
-		kfree_sensitive(new_key_string);
-		return ret;
-	}
-
 	up_read(&key->sem);
 	key_put(key);
+	if (ret < 0)
+		goto free_new_key_string;
 
 	/* clear the flag since following operations may invalidate previously valid key */
 	clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 
 	ret = crypt_setkey(cc);
+	if (ret)
+		goto free_new_key_string;
 
-	if (!ret) {
-		set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
-		kfree_sensitive(cc->key_string);
-		cc->key_string = new_key_string;
-	} else
-		kfree_sensitive(new_key_string);
+	set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
+	kfree_sensitive(cc->key_string);
+	cc->key_string = new_key_string;
+	return 0;
 
+free_new_key_string:
+	kfree_sensitive(new_key_string);
 	return ret;
 }
 
@@ -2937,7 +2934,8 @@ static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api)
 	if (IS_ERR(mac))
 		return PTR_ERR(mac);
 
-	cc->key_mac_size = crypto_ahash_digestsize(mac);
+	if (!test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags))
+		cc->key_mac_size = crypto_ahash_digestsize(mac);
 	crypto_free_ahash(mac);
 
 	cc->authenc_key = kmalloc(crypt_authenckey_size(cc), GFP_KERNEL);
@@ -3219,6 +3217,13 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 			cc->cipher_auth = kstrdup(sval, GFP_KERNEL);
 			if (!cc->cipher_auth)
 				return -ENOMEM;
+		} else if (sscanf(opt_string, "integrity_key_size:%u%c", &val, &dummy) == 1) {
+			if (!val) {
+				ti->error = "Invalid integrity_key_size argument";
+				return -EINVAL;
+			}
+			cc->key_mac_size = val;
+			set_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags);
 		} else if (sscanf(opt_string, "sector_size:%hu%c", &cc->sector_size, &dummy) == 1) {
 			if (cc->sector_size < (1 << SECTOR_SHIFT) ||
 			    cc->sector_size > 4096 ||
@@ -3607,10 +3612,10 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 		num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags);
+		num_feature_args += !!cc->used_tag_size;
 		num_feature_args += cc->sector_size != (1 << SECTOR_SHIFT);
 		num_feature_args += test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags);
-		if (cc->used_tag_size)
-			num_feature_args++;
+		num_feature_args += test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags);
 		if (num_feature_args) {
 			DMEMIT(" %d", num_feature_args);
 			if (ti->num_discard_bios)
@@ -3631,6 +3636,8 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 				DMEMIT(" sector_size:%d", cc->sector_size);
 			if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags))
 				DMEMIT(" iv_large_sectors");
+			if (test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags))
+				DMEMIT(" integrity_key_size:%u", cc->key_mac_size);
 		}
 		break;
 
@@ -3758,7 +3765,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 27, 0},
+	.version = {1, 28, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,

drivers/md/dm-integrity.c

@@ -284,6 +284,7 @@ struct dm_integrity_c {
 
 	mempool_t recheck_pool;
 	struct bio_set recheck_bios;
+	struct bio_set recalc_bios;
 
 	struct notifier_block reboot_notifier;
 };
@@ -321,7 +322,9 @@ struct dm_integrity_io {
 	struct dm_bio_details bio_details;
 
 	char *integrity_payload;
+	unsigned payload_len;
 	bool integrity_payload_from_mempool;
+	bool integrity_range_locked;
 };
 
 struct journal_completion {
@@ -359,7 +362,7 @@ static struct kmem_cache *journal_io_cache;
 #endif
 
 static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map);
-static int dm_integrity_map_inline(struct dm_integrity_io *dio);
+static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map);
 static void integrity_bio_wait(struct work_struct *w);
 static void dm_integrity_dtr(struct dm_target *ti);
 
@@ -491,7 +494,8 @@ static int sb_mac(struct dm_integrity_c *ic, bool wr)
 	__u8 *sb = (__u8 *)ic->sb;
 	__u8 *mac = sb + (1 << SECTOR_SHIFT) - mac_size;
 
-	if (sizeof(struct superblock) + mac_size > 1 << SECTOR_SHIFT) {
+	if (sizeof(struct superblock) + mac_size > 1 << SECTOR_SHIFT ||
+	    mac_size > HASH_MAX_DIGESTSIZE) {
 		dm_integrity_io_error(ic, "digest is too long", -EINVAL);
 		return -EINVAL;
 	}
@@ -1500,15 +1504,15 @@ static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_dat
 	if (!ic->meta_dev)
 		flush_data = false;
 	if (flush_data) {
-		fr.io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC,
-		fr.io_req.mem.type = DM_IO_KMEM,
-		fr.io_req.mem.ptr.addr = NULL,
-		fr.io_req.notify.fn = flush_notify,
+		fr.io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
+		fr.io_req.mem.type = DM_IO_KMEM;
+		fr.io_req.mem.ptr.addr = NULL;
+		fr.io_req.notify.fn = flush_notify;
 		fr.io_req.notify.context = &fr;
-		fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
-		fr.io_reg.bdev = ic->dev->bdev,
-		fr.io_reg.sector = 0,
-		fr.io_reg.count = 0,
+		fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio);
+		fr.io_reg.bdev = ic->dev->bdev;
+		fr.io_reg.sector = 0;
+		fr.io_reg.count = 0;
 		fr.ic = ic;
 		init_completion(&fr.comp);
 		r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL, IOPRIO_DEFAULT);
@@ -1946,8 +1950,13 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
 	dio->bi_status = 0;
 	dio->op = bio_op(bio);
 
-	if (ic->mode == 'I')
-		return dm_integrity_map_inline(dio);
+	if (ic->mode == 'I') {
+		bio->bi_iter.bi_sector = dm_target_offset(ic->ti, bio->bi_iter.bi_sector);
+		dio->integrity_payload = NULL;
+		dio->integrity_payload_from_mempool = false;
+		dio->integrity_range_locked = false;
+		return dm_integrity_map_inline(dio, true);
+	}
 
 	if (unlikely(dio->op == REQ_OP_DISCARD)) {
 		if (ti->max_io_len) {
@@ -2397,15 +2406,13 @@ journal_read_write:
 	do_endio_flush(ic, dio);
 }
 
-static int dm_integrity_map_inline(struct dm_integrity_io *dio)
+static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map)
 {
 	struct dm_integrity_c *ic = dio->ic;
 	struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
 	struct bio_integrity_payload *bip;
-	unsigned payload_len, digest_size, extra_size, ret;
-
-	dio->integrity_payload = NULL;
-	dio->integrity_payload_from_mempool = false;
+	unsigned ret;
+	sector_t recalc_sector;
 
 	if (unlikely(bio_integrity(bio))) {
 		bio->bi_status = BLK_STS_NOTSUPP;
@@ -2418,28 +2425,67 @@ static int dm_integrity_map_inline(struct dm_integrity_io *dio)
 		return DM_MAPIO_REMAPPED;
 
 retry:
-	payload_len = ic->tuple_size * (bio_sectors(bio) >> ic->sb->log2_sectors_per_block);
-	digest_size = crypto_shash_digestsize(ic->internal_hash);
-	extra_size = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0;
-	payload_len += extra_size;
-	dio->integrity_payload = kmalloc(payload_len, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
-	if (unlikely(!dio->integrity_payload)) {
-		const unsigned x_size = PAGE_SIZE << 1;
-		if (payload_len > x_size) {
-			unsigned sectors = ((x_size - extra_size) / ic->tuple_size) << ic->sb->log2_sectors_per_block;
-			if (WARN_ON(!sectors || sectors >= bio_sectors(bio))) {
-				bio->bi_status = BLK_STS_NOTSUPP;
-				bio_endio(bio);
-				return DM_MAPIO_SUBMITTED;
+	if (!dio->integrity_payload) {
+		unsigned digest_size, extra_size;
+		dio->payload_len = ic->tuple_size * (bio_sectors(bio) >> ic->sb->log2_sectors_per_block);
+		digest_size = crypto_shash_digestsize(ic->internal_hash);
+		extra_size = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0;
+		dio->payload_len += extra_size;
+		dio->integrity_payload = kmalloc(dio->payload_len, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+		if (unlikely(!dio->integrity_payload)) {
+			const unsigned x_size = PAGE_SIZE << 1;
+			if (dio->payload_len > x_size) {
+				unsigned sectors = ((x_size - extra_size) / ic->tuple_size) << ic->sb->log2_sectors_per_block;
+				if (WARN_ON(!sectors || sectors >= bio_sectors(bio))) {
+					bio->bi_status = BLK_STS_NOTSUPP;
+					bio_endio(bio);
+					return DM_MAPIO_SUBMITTED;
+				}
+				dm_accept_partial_bio(bio, sectors);
+				goto retry;
 			}
-			dm_accept_partial_bio(bio, sectors);
-			goto retry;
 		}
+	}
+
+	dio->range.logical_sector = bio->bi_iter.bi_sector;
+	dio->range.n_sectors = bio_sectors(bio);
+
+	if (!(ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)))
+		goto skip_spinlock;
+#ifdef CONFIG_64BIT
+	/*
+	 * On 64-bit CPUs we can optimize the lock away (so that it won't cause
+	 * cache line bouncing) and use acquire/release barriers instead.
+	 *
+	 * Paired with smp_store_release in integrity_recalc_inline.
+	 */
+	recalc_sector = le64_to_cpu(smp_load_acquire(&ic->sb->recalc_sector));
+	if (likely(dio->range.logical_sector + dio->range.n_sectors <= recalc_sector))
+		goto skip_spinlock;
+#endif
+	spin_lock_irq(&ic->endio_wait.lock);
+	recalc_sector = le64_to_cpu(ic->sb->recalc_sector);
+	if (dio->range.logical_sector + dio->range.n_sectors <= recalc_sector)
+		goto skip_unlock;
+	if (unlikely(!add_new_range(ic, &dio->range, true))) {
+		if (from_map) {
+			spin_unlock_irq(&ic->endio_wait.lock);
+			INIT_WORK(&dio->work, integrity_bio_wait);
+			queue_work(ic->wait_wq, &dio->work);
+			return DM_MAPIO_SUBMITTED;
+		}
+		wait_and_add_new_range(ic, &dio->range);
+	}
+	dio->integrity_range_locked = true;
+skip_unlock:
+	spin_unlock_irq(&ic->endio_wait.lock);
+skip_spinlock:
+
+	if (unlikely(!dio->integrity_payload)) {
 		dio->integrity_payload = page_to_virt((struct page *)mempool_alloc(&ic->recheck_pool, GFP_NOIO));
 		dio->integrity_payload_from_mempool = true;
 	}
 
-	bio->bi_iter.bi_sector = dm_target_offset(ic->ti, bio->bi_iter.bi_sector);
 	dio->bio_details.bi_iter = bio->bi_iter;
 
 	if (unlikely(!dm_integrity_check_limits(ic, bio->bi_iter.bi_sector, bio))) {
@@ -2449,7 +2495,7 @@ retry:
 	bio->bi_iter.bi_sector += ic->start + SB_SECTORS;
 
 	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
-	if (unlikely(IS_ERR(bip))) {
+	if (IS_ERR(bip)) {
 		bio->bi_status = errno_to_blk_status(PTR_ERR(bip));
 		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
@@ -2470,8 +2516,8 @@ retry:
 	}
 
 	ret = bio_integrity_add_page(bio, virt_to_page(dio->integrity_payload),
-					payload_len, offset_in_page(dio->integrity_payload));
-	if (unlikely(ret != payload_len)) {
+					dio->payload_len, offset_in_page(dio->integrity_payload));
+	if (unlikely(ret != dio->payload_len)) {
 		bio->bi_status = BLK_STS_RESOURCE;
 		bio_endio(bio);
 		return DM_MAPIO_SUBMITTED;
@@ -2522,7 +2568,7 @@ static void dm_integrity_inline_recheck(struct work_struct *w)
 		}
 
 		bip = bio_integrity_alloc(outgoing_bio, GFP_NOIO, 1);
-		if (unlikely(IS_ERR(bip))) {
+		if (IS_ERR(bip)) {
 			bio_put(outgoing_bio);
 			bio->bi_status = errno_to_blk_status(PTR_ERR(bip));
 			bio_endio(bio);
@@ -2579,6 +2625,9 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status
 		struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));
 		if (dio->op == REQ_OP_READ && likely(*status == BLK_STS_OK)) {
 			unsigned pos = 0;
+			if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
+			    unlikely(dio->integrity_range_locked))
+				goto skip_check;
 			while (dio->bio_details.bi_iter.bi_size) {
 				char digest[HASH_MAX_DIGESTSIZE];
 				struct bio_vec bv = bio_iter_iovec(bio, dio->bio_details.bi_iter);
@@ -2598,9 +2647,10 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status
 				bio_advance_iter_single(bio, &dio->bio_details.bi_iter, ic->sectors_per_block << SECTOR_SHIFT);
 			}
 		}
-		if (likely(dio->op == REQ_OP_READ) || likely(dio->op == REQ_OP_WRITE)) {
-			dm_integrity_free_payload(dio);
-		}
+skip_check:
+		dm_integrity_free_payload(dio);
+		if (unlikely(dio->integrity_range_locked))
+			remove_range(ic, &dio->range);
 	}
 	return DM_ENDIO_DONE;
 }
@@ -2608,8 +2658,26 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status
 static void integrity_bio_wait(struct work_struct *w)
 {
 	struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work);
+	struct dm_integrity_c *ic = dio->ic;
 
-	dm_integrity_map_continue(dio, false);
+	if (ic->mode == 'I') {
+		struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
+		int r = dm_integrity_map_inline(dio, false);
+		switch (r) {
+			case DM_MAPIO_KILL:
+				bio->bi_status = BLK_STS_IOERR;
+				fallthrough;
+			case DM_MAPIO_REMAPPED:
+				submit_bio_noacct(bio);
+				fallthrough;
+			case DM_MAPIO_SUBMITTED:
+				return;
+			default:
+				BUG();
+		}
+	} else {
+		dm_integrity_map_continue(dio, false);
+	}
 }
 
 static void pad_uncommitted(struct dm_integrity_c *ic)
@@ -3081,6 +3149,133 @@ free_ret:
 	kvfree(recalc_tags);
 }
 
+static void integrity_recalc_inline(struct work_struct *w)
+{
+	struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, recalc_work);
+	size_t recalc_tags_size;
+	u8 *recalc_buffer = NULL;
+	u8 *recalc_tags = NULL;
+	struct dm_integrity_range range;
+	struct bio *bio;
+	struct bio_integrity_payload *bip;
+	__u8 *t;
+	unsigned int i;
+	int r;
+	unsigned ret;
+	unsigned int super_counter = 0;
+	unsigned recalc_sectors = RECALC_SECTORS;
+
+retry:
+	recalc_buffer = kmalloc(recalc_sectors << SECTOR_SHIFT, GFP_NOIO | __GFP_NOWARN);
+	if (!recalc_buffer) {
+oom:
+		recalc_sectors >>= 1;
+		if (recalc_sectors >= 1U << ic->sb->log2_sectors_per_block)
+			goto retry;
+		DMCRIT("out of memory for recalculate buffer - recalculation disabled");
+		goto free_ret;
+	}
+
+	recalc_tags_size = (recalc_sectors >> ic->sb->log2_sectors_per_block) * ic->tuple_size;
+	if (crypto_shash_digestsize(ic->internal_hash) > ic->tuple_size)
+		recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tuple_size;
+	recalc_tags = kmalloc(recalc_tags_size, GFP_NOIO | __GFP_NOWARN);
+	if (!recalc_tags) {
+		kfree(recalc_buffer);
+		recalc_buffer = NULL;
+		goto oom;
+	}
+
+	spin_lock_irq(&ic->endio_wait.lock);
+
+next_chunk:
+	if (unlikely(dm_post_suspending(ic->ti)))
+		goto unlock_ret;
+
+	range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
+	if (unlikely(range.logical_sector >= ic->provided_data_sectors))
+		goto unlock_ret;
+	range.n_sectors = min((sector_t)recalc_sectors, ic->provided_data_sectors - range.logical_sector);
+
+	add_new_range_and_wait(ic, &range);
+	spin_unlock_irq(&ic->endio_wait.lock);
+
+	if (unlikely(++super_counter == RECALC_WRITE_SUPER)) {
+		recalc_write_super(ic);
+		super_counter = 0;
+	}
+
+	if (unlikely(dm_integrity_failed(ic)))
+		goto err;
+
+	DEBUG_print("recalculating: %llx - %llx\n", range.logical_sector, range.n_sectors);
+
+	bio = bio_alloc_bioset(ic->dev->bdev, 1, REQ_OP_READ, GFP_NOIO, &ic->recalc_bios);
+	bio->bi_iter.bi_sector = ic->start + SB_SECTORS + range.logical_sector;
+	__bio_add_page(bio, virt_to_page(recalc_buffer), range.n_sectors << SECTOR_SHIFT, offset_in_page(recalc_buffer));
+	r = submit_bio_wait(bio);
+	bio_put(bio);
+	if (unlikely(r)) {
+		dm_integrity_io_error(ic, "reading data", r);
+		goto err;
+	}
+
+	t = recalc_tags;
+	for (i = 0; i < range.n_sectors; i += ic->sectors_per_block) {
+		memset(t, 0, ic->tuple_size);
+		integrity_sector_checksum(ic, range.logical_sector + i, recalc_buffer + (i << SECTOR_SHIFT), t);
+		t += ic->tuple_size;
+	}
+
+	bio = bio_alloc_bioset(ic->dev->bdev, 1, REQ_OP_WRITE, GFP_NOIO, &ic->recalc_bios);
+	bio->bi_iter.bi_sector = ic->start + SB_SECTORS + range.logical_sector;
+	__bio_add_page(bio, virt_to_page(recalc_buffer), range.n_sectors << SECTOR_SHIFT, offset_in_page(recalc_buffer));
+
+	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
+	if (unlikely(IS_ERR(bip))) {
+		bio_put(bio);
+		DMCRIT("out of memory for bio integrity payload - recalculation disabled");
+		goto err;
+	}
+	ret = bio_integrity_add_page(bio, virt_to_page(recalc_tags), t - recalc_tags, offset_in_page(recalc_tags));
+	if (unlikely(ret != t - recalc_tags)) {
+		bio_put(bio);
+		dm_integrity_io_error(ic, "attaching integrity tags", -ENOMEM);
+		goto err;
+	}
+
+	r = submit_bio_wait(bio);
+	bio_put(bio);
+	if (unlikely(r)) {
+		dm_integrity_io_error(ic, "writing data", r);
+		goto err;
+	}
+
+	cond_resched();
+	spin_lock_irq(&ic->endio_wait.lock);
+	remove_range_unlocked(ic, &range);
+#ifdef CONFIG_64BIT
+	/* Paired with smp_load_acquire in dm_integrity_map_inline. */
+	smp_store_release(&ic->sb->recalc_sector, cpu_to_le64(range.logical_sector + range.n_sectors));
+#else
+	ic->sb->recalc_sector = cpu_to_le64(range.logical_sector + range.n_sectors);
+#endif
+	goto next_chunk;
+
+err:
+	remove_range(ic, &range);
+	goto free_ret;
+
+unlock_ret:
+	spin_unlock_irq(&ic->endio_wait.lock);
+
+	recalc_write_super(ic);
+
+free_ret:
+	kfree(recalc_buffer);
+	kfree(recalc_tags);
+}
+
 static void bitmap_block_work(struct work_struct *w)
 {
 	struct bitmap_block_status *bbs = container_of(w, struct bitmap_block_status, work);
@@ -4619,6 +4814,17 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 			r = -ENOMEM;
 			goto bad;
 		}
+		r = bioset_init(&ic->recalc_bios, 1, 0, BIOSET_NEED_BVECS);
+		if (r) {
+			ti->error = "Cannot allocate bio set";
+			goto bad;
+		}
+		r = bioset_integrity_create(&ic->recalc_bios, 1);
+		if (r) {
+			ti->error = "Cannot allocate bio integrity set";
+			r = -ENOMEM;
+			goto bad;
+		}
 	}
 
 	ic->metadata_wq = alloc_workqueue("dm-integrity-metadata",
@@ -4717,13 +4923,18 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 		ti->error = "Block size doesn't match the information in superblock";
 		goto bad;
 	}
-	if (!le32_to_cpu(ic->sb->journal_sections) != (ic->mode == 'I')) {
-		r = -EINVAL;
-		if (ic->mode != 'I')
+	if (ic->mode != 'I') {
+		if (!le32_to_cpu(ic->sb->journal_sections)) {
+			r = -EINVAL;
 			ti->error = "Corrupted superblock, journal_sections is 0";
-		else
+			goto bad;
+		}
+	} else {
+		if (le32_to_cpu(ic->sb->journal_sections)) {
+			r = -EINVAL;
 			ti->error = "Corrupted superblock, journal_sections is not 0";
-		goto bad;
+			goto bad;
+		}
 	}
 	/* make sure that ti->max_io_len doesn't overflow */
 	if (!ic->meta_dev) {
@@ -4830,7 +5041,7 @@ try_smaller_buffer:
 			r = -ENOMEM;
 			goto bad;
 		}
-		INIT_WORK(&ic->recalc_work, integrity_recalc);
+		INIT_WORK(&ic->recalc_work, ic->mode == 'I' ? integrity_recalc_inline : integrity_recalc);
 	} else {
 		if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
 			ti->error = "Recalculate can only be specified with internal_hash";
@@ -4847,17 +5058,15 @@ try_smaller_buffer:
 		goto bad;
 	}
 
-	if (ic->mode != 'I') {
-		ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev,
-				1U << (SECTOR_SHIFT + ic->log2_buffer_sectors), 1, 0, NULL, NULL, 0);
-		if (IS_ERR(ic->bufio)) {
-			r = PTR_ERR(ic->bufio);
-			ti->error = "Cannot initialize dm-bufio";
-			ic->bufio = NULL;
-			goto bad;
-		}
-		dm_bufio_set_sector_offset(ic->bufio, ic->start + ic->initial_sectors);
+	ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev,
+			1U << (SECTOR_SHIFT + ic->log2_buffer_sectors), 1, 0, NULL, NULL, 0);
+	if (IS_ERR(ic->bufio)) {
+		r = PTR_ERR(ic->bufio);
+		ti->error = "Cannot initialize dm-bufio";
+		ic->bufio = NULL;
+		goto bad;
 	}
+	dm_bufio_set_sector_offset(ic->bufio, ic->start + ic->initial_sectors);
 
 	if (ic->mode != 'R' && ic->mode != 'I') {
 		r = create_journal(ic, &ti->error);
@@ -4979,6 +5188,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 	kvfree(ic->bbs);
 	if (ic->bufio)
 		dm_bufio_client_destroy(ic->bufio);
+	bioset_exit(&ic->recalc_bios);
 	bioset_exit(&ic->recheck_bios);
 	mempool_exit(&ic->recheck_pool);
 	mempool_exit(&ic->journal_io_mempool);
@@ -5033,7 +5243,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 
 static struct target_type integrity_target = {
 	.name			= "integrity",
-	.version		= {1, 12, 0},
+	.version		= {1, 13, 0},
 	.module			= THIS_MODULE,
 	.features		= DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
 	.ctr			= dm_integrity_ctr,

drivers/md/dm-raid.c

@@ -2519,7 +2519,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
 		rdev->saved_raid_disk = rdev->raid_disk;
 	}
 
-	/* Reshape support -> restore repective data offsets */
+	/* Reshape support -> restore respective data offsets */
 	rdev->data_offset = le64_to_cpu(sb->data_offset);
 	rdev->new_data_offset = le64_to_cpu(sb->new_data_offset);
 

drivers/md/dm-rq.c

@@ -496,8 +496,10 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 		map = dm_get_live_table(md, &srcu_idx);
 		if (unlikely(!map)) {
+			DMERR_LIMIT("%s: mapping table unavailable, erroring io",
+				    dm_device_name(md));
 			dm_put_live_table(md, srcu_idx);
-			return BLK_STS_RESOURCE;
+			return BLK_STS_IOERR;
 		}
 		ti = dm_table_find_target(map, 0);
 		dm_put_live_table(md, srcu_idx);

drivers/md/dm-thin.c

@@ -2948,7 +2948,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	pmd = dm_pool_metadata_open(metadata_dev, block_size, format_device);
 	if (IS_ERR(pmd)) {
 		*error = "Error creating metadata object";
-		return (struct pool *)pmd;
+		return ERR_CAST(pmd);
 	}
 
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);

drivers/md/dm-vdo/data-vio.c

@@ -501,6 +501,7 @@ static void launch_data_vio(struct data_vio *data_vio, logical_block_number_t lb
 
 	memset(&data_vio->record_name, 0, sizeof(data_vio->record_name));
 	memset(&data_vio->duplicate, 0, sizeof(data_vio->duplicate));
+	vdo_reset_completion(&data_vio->decrement_completion);
 	vdo_reset_completion(completion);
 	completion->error_handler = handle_data_vio_error;
 	set_data_vio_logical_callback(data_vio, attempt_logical_block_lock);
@@ -1273,12 +1274,14 @@ static void clean_hash_lock(struct vdo_completion *completion)
 static void finish_cleanup(struct data_vio *data_vio)
 {
 	struct vdo_completion *completion = &data_vio->vio.completion;
+	u32 discard_size = min_t(u32, data_vio->remaining_discard,
+				 VDO_BLOCK_SIZE - data_vio->offset);
 
 	VDO_ASSERT_LOG_ONLY(data_vio->allocation.lock == NULL,
 			    "complete data_vio has no allocation lock");
 	VDO_ASSERT_LOG_ONLY(data_vio->hash_lock == NULL,
 			    "complete data_vio has no hash lock");
-	if ((data_vio->remaining_discard <= VDO_BLOCK_SIZE) ||
+	if ((data_vio->remaining_discard <= discard_size) ||
 	    (completion->result != VDO_SUCCESS)) {
 		struct data_vio_pool *pool = completion->vdo->data_vio_pool;
 
@@ -1287,12 +1290,12 @@ static void finish_cleanup(struct data_vio *data_vio)
 		return;
 	}
 
-	data_vio->remaining_discard -= min_t(u32, data_vio->remaining_discard,
-					     VDO_BLOCK_SIZE - data_vio->offset);
+	data_vio->remaining_discard -= discard_size;
 	data_vio->is_partial = (data_vio->remaining_discard < VDO_BLOCK_SIZE);
 	data_vio->read = data_vio->is_partial;
 	data_vio->offset = 0;
 	completion->requeue = true;
+	data_vio->first_reference_operation_complete = false;
 	launch_data_vio(data_vio, data_vio->logical.lbn + 1);
 }
 
@@ -1965,7 +1968,8 @@ static void allocate_block(struct vdo_completion *completion)
 		.state = VDO_MAPPING_STATE_UNCOMPRESSED,
 	};
 
-	if (data_vio->fua) {
+	if (data_vio->fua ||
+	    data_vio->remaining_discard > (u32) (VDO_BLOCK_SIZE - data_vio->offset)) {
 		prepare_for_dedupe(data_vio);
 		return;
 	}
@@ -2042,7 +2046,6 @@ void continue_data_vio_with_block_map_slot(struct vdo_completion *completion)
 		return;
 	}
 
-
 	/*
 	 * We don't need to write any data, so skip allocation and just update the block map and
 	 * reference counts (via the journal).
@@ -2051,7 +2054,7 @@ void continue_data_vio_with_block_map_slot(struct vdo_completion *completion)
 	if (data_vio->is_zero)
 		data_vio->new_mapped.state = VDO_MAPPING_STATE_UNCOMPRESSED;
 
-	if (data_vio->remaining_discard > VDO_BLOCK_SIZE) {
+	if (data_vio->remaining_discard > (u32) (VDO_BLOCK_SIZE - data_vio->offset)) {
 		/* This is not the final block of a discard so we can't acknowledge it yet. */
 		update_metadata_for_data_vio_write(data_vio, NULL);
 		return;

drivers/md/dm-vdo/dedupe.c

@@ -729,6 +729,7 @@ static void process_update_result(struct data_vio *agent)
 	    !change_context_state(context, DEDUPE_CONTEXT_COMPLETE, DEDUPE_CONTEXT_IDLE))
 		return;
 
+	agent->dedupe_context = NULL;
 	release_context(context);
 }
 
@@ -1648,6 +1649,7 @@ static void process_query_result(struct data_vio *agent)
 
 	if (change_context_state(context, DEDUPE_CONTEXT_COMPLETE, DEDUPE_CONTEXT_IDLE)) {
 		agent->is_duplicate = decode_uds_advice(context);
+		agent->dedupe_context = NULL;
 		release_context(context);
 	}
 }
@@ -2321,6 +2323,7 @@ static void timeout_index_operations_callback(struct vdo_completion *completion)
 		 * send its requestor on its way.
 		 */
 		list_del_init(&context->list_entry);
+		context->requestor->dedupe_context = NULL;
 		continue_data_vio(context->requestor);
 		timed_out++;
 	}

drivers/md/dm-vdo/dm-vdo-target.c

@@ -1105,6 +1105,9 @@ static int vdo_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if ((argc == 1) && (strcasecmp(argv[0], "stats") == 0)) {
 		vdo_write_stats(vdo, result_buffer, maxlen);
 		result = 1;
+	} else if ((argc == 1) && (strcasecmp(argv[0], "config") == 0)) {
+		vdo_write_config(vdo, &result_buffer, &maxlen);
+		result = 1;
 	} else {
 		result = vdo_status_to_errno(process_vdo_message(vdo, argc, argv));
 	}
@@ -2293,6 +2296,14 @@ static void handle_load_error(struct vdo_completion *completion)
 		return;
 	}
 
+	if ((completion->result == VDO_UNSUPPORTED_VERSION) &&
+	    (vdo->admin.phase == LOAD_PHASE_MAKE_DIRTY)) {
+		vdo_log_error("Aborting load due to unsupported version");
+		vdo->admin.phase = LOAD_PHASE_FINISHED;
+		load_callback(completion);
+		return;
+	}
+
 	vdo_log_error_strerror(completion->result,
 			       "Entering read-only mode due to load error");
 	vdo->admin.phase = LOAD_PHASE_WAIT_FOR_READ_ONLY;
@@ -2737,6 +2748,19 @@ static int vdo_preresume_registered(struct dm_target *ti, struct vdo *vdo)
 		vdo_log_info("starting device '%s'", device_name);
 		result = perform_admin_operation(vdo, LOAD_PHASE_START, load_callback,
 						 handle_load_error, "load");
+		if (result == VDO_UNSUPPORTED_VERSION) {
+			 /*
+			  * A component version is not supported. This can happen when the
+			  * recovery journal metadata is in an old version format. Abort the
+			  * load without saving the state.
+			  */
+			vdo->suspend_type = VDO_ADMIN_STATE_SUSPENDING;
+			perform_admin_operation(vdo, SUSPEND_PHASE_START,
+						suspend_callback, suspend_callback,
+						"suspend");
+			return result;
+		}
+
 		if ((result != VDO_SUCCESS) && (result != VDO_READ_ONLY)) {
 			/*
 			 * Something has gone very wrong. Make sure everything has drained and
@@ -2808,7 +2832,8 @@ static int vdo_preresume(struct dm_target *ti)
 
 	vdo_register_thread_device_id(&instance_thread, &vdo->instance);
 	result = vdo_preresume_registered(ti, vdo);
-	if ((result == VDO_PARAMETER_MISMATCH) || (result == VDO_INVALID_ADMIN_STATE))
+	if ((result == VDO_PARAMETER_MISMATCH) || (result == VDO_INVALID_ADMIN_STATE) ||
+	    (result == VDO_UNSUPPORTED_VERSION))
 		result = -EINVAL;
 	vdo_unregister_thread_device_id();
 	return vdo_status_to_errno(result);
@@ -2832,7 +2857,7 @@ static void vdo_resume(struct dm_target *ti)
 static struct target_type vdo_target_bio = {
 	.features = DM_TARGET_SINGLETON,
 	.name = "vdo",
-	.version = { 9, 0, 0 },
+	.version = { 9, 1, 0 },
 	.module = THIS_MODULE,
 	.ctr = vdo_ctr,
 	.dtr = vdo_dtr,

drivers/md/dm-vdo/indexer/chapter-index.c

@@ -177,7 +177,7 @@ int uds_pack_open_chapter_index_page(struct open_chapter_index *chapter_index,
 			if (list_number < 0)
 				return UDS_OVERFLOW;
 
-			next_list = first_list + list_number--,
+			next_list = first_list + list_number--;
 			result = uds_start_delta_index_search(delta_index, next_list, 0,
 							      &entry);
 			if (result != UDS_SUCCESS)

drivers/md/dm-vdo/io-submitter.c

@@ -346,7 +346,6 @@ void __submit_metadata_vio(struct vio *vio, physical_block_number_t physical,
 
 
 	VDO_ASSERT_LOG_ONLY(!code->quiescent, "I/O not allowed in state %s", code->name);
-	VDO_ASSERT_LOG_ONLY(vio->bio->bi_next == NULL, "metadata bio has no next bio");
 
 	vdo_reset_completion(completion);
 	completion->error_handler = error_handler;

drivers/md/dm-vdo/message-stats.c

@@ -4,6 +4,7 @@
  */
 
 #include "dedupe.h"
+#include "indexer.h"
 #include "logger.h"
 #include "memory-alloc.h"
 #include "message-stats.h"
@@ -430,3 +431,50 @@ int vdo_write_stats(struct vdo *vdo, char *buf, unsigned int maxlen)
 	vdo_free(stats);
 	return VDO_SUCCESS;
 }
+
+static void write_index_memory(u32 mem, char **buf, unsigned int *maxlen)
+{
+	char *prefix = "memorySize : ";
+
+	/* Convert index memory to fractional value */
+	if (mem == (u32)UDS_MEMORY_CONFIG_256MB)
+		write_string(prefix, "0.25, ", NULL, buf, maxlen);
+	else if (mem == (u32)UDS_MEMORY_CONFIG_512MB)
+		write_string(prefix, "0.50, ", NULL, buf, maxlen);
+	else if (mem == (u32)UDS_MEMORY_CONFIG_768MB)
+		write_string(prefix, "0.75, ", NULL, buf, maxlen);
+	else
+		write_u32(prefix, mem, ", ", buf, maxlen);
+}
+
+static void write_index_config(struct index_config *config, char **buf,
+			       unsigned int *maxlen)
+{
+	write_string("index :  ", "{ ", NULL, buf, maxlen);
+	/* index mem size */
+	write_index_memory(config->mem, buf, maxlen);
+	/* whether the index is sparse or not */
+	write_bool("isSparse : ", config->sparse, ", ", buf, maxlen);
+	write_string(NULL, "}", ", ", buf, maxlen);
+}
+
+int vdo_write_config(struct vdo *vdo, char **buf, unsigned int *maxlen)
+{
+	struct vdo_config *config = &vdo->states.vdo.config;
+
+	write_string(NULL, "{ ", NULL, buf, maxlen);
+	/* version */
+	write_u32("version : ", 1, ", ", buf, maxlen);
+	/* physical size */
+	write_block_count_t("physicalSize : ", config->physical_blocks * VDO_BLOCK_SIZE, ", ",
+			    buf, maxlen);
+	/* logical size */
+	write_block_count_t("logicalSize : ", config->logical_blocks * VDO_BLOCK_SIZE, ", ",
+			    buf, maxlen);
+	/* slab size */
+	write_block_count_t("slabSize : ", config->slab_size, ", ", buf, maxlen);
+	/* index config */
+	write_index_config(&vdo->geometry.index_config, buf, maxlen);
+	write_string(NULL, "}", NULL, buf, maxlen);
+	return VDO_SUCCESS;
+}

drivers/md/dm-vdo/message-stats.h

@@ -8,6 +8,7 @@
 
 #include "types.h"
 
+int vdo_write_config(struct vdo *vdo, char **buf, unsigned int *maxlen);
 int vdo_write_stats(struct vdo *vdo, char *buf, unsigned int maxlen);
 
 #endif /* VDO_MESSAGE_STATS_H */

drivers/md/dm-vdo/repair.c

@@ -1202,17 +1202,14 @@ static bool __must_check is_valid_recovery_journal_block(const struct recovery_j
  * @journal: The journal to use.
  * @header: The unpacked block header to check.
  * @sequence: The expected sequence number.
- * @type: The expected metadata type.
  *
  * Return: True if the block matches.
  */
 static bool __must_check is_exact_recovery_journal_block(const struct recovery_journal *journal,
 							 const struct recovery_block_header *header,
-							 sequence_number_t sequence,
-							 enum vdo_metadata_type type)
+							 sequence_number_t sequence)
 {
-	return ((header->metadata_type == type) &&
-		(header->sequence_number == sequence) &&
+	return ((header->sequence_number == sequence) &&
 		(is_valid_recovery_journal_block(journal, header, true)));
 }
 
@@ -1371,7 +1368,8 @@ static void extract_entries_from_block(struct repair_completion *repair,
 		get_recovery_journal_block_header(journal, repair->journal_data,
 						  sequence);
 
-	if (!is_exact_recovery_journal_block(journal, &header, sequence, format)) {
+	if (!is_exact_recovery_journal_block(journal, &header, sequence) ||
+	    (header.metadata_type != format)) {
 		/* This block is invalid, so skip it. */
 		return;
 	}
@@ -1557,10 +1555,13 @@ static int parse_journal_for_recovery(struct repair_completion *repair)
 	sequence_number_t i, head;
 	bool found_entries = false;
 	struct recovery_journal *journal = repair->completion.vdo->recovery_journal;
+	struct recovery_block_header header;
+	enum vdo_metadata_type expected_format;
 
 	head = min(repair->block_map_head, repair->slab_journal_head);
+	header = get_recovery_journal_block_header(journal, repair->journal_data, head);
+	expected_format = header.metadata_type;
 	for (i = head; i <= repair->highest_tail; i++) {
-		struct recovery_block_header header;
 		journal_entry_count_t block_entries;
 		u8 j;
 
@@ -1572,19 +1573,15 @@ static int parse_journal_for_recovery(struct repair_completion *repair)
 		};
 
 		header = get_recovery_journal_block_header(journal, repair->journal_data, i);
-		if (header.metadata_type == VDO_METADATA_RECOVERY_JOURNAL) {
-			/* This is an old format block, so we need to upgrade */
-			vdo_log_error_strerror(VDO_UNSUPPORTED_VERSION,
-					       "Recovery journal is in the old format, a read-only rebuild is required.");
-			vdo_enter_read_only_mode(repair->completion.vdo,
-						 VDO_UNSUPPORTED_VERSION);
-			return VDO_UNSUPPORTED_VERSION;
-		}
-
-		if (!is_exact_recovery_journal_block(journal, &header, i,
-						     VDO_METADATA_RECOVERY_JOURNAL_2)) {
+		if (!is_exact_recovery_journal_block(journal, &header, i)) {
 			/* A bad block header was found so this must be the end of the journal. */
 			break;
+		} else if (header.metadata_type != expected_format) {
+			/* There is a mix of old and new format blocks, so we need to rebuild. */
+			vdo_log_error_strerror(VDO_CORRUPT_JOURNAL,
+					       "Recovery journal is in an invalid format, a read-only rebuild is required.");
+			vdo_enter_read_only_mode(repair->completion.vdo, VDO_CORRUPT_JOURNAL);
+			return VDO_CORRUPT_JOURNAL;
 		}
 
 		block_entries = header.entry_count;
@@ -1620,8 +1617,14 @@ static int parse_journal_for_recovery(struct repair_completion *repair)
 			break;
 	}
 
-	if (!found_entries)
+	if (!found_entries) {
 		return validate_heads(repair);
+	} else if (expected_format == VDO_METADATA_RECOVERY_JOURNAL) {
+		/* All journal blocks have the old format, so we need to upgrade. */
+		vdo_log_error_strerror(VDO_UNSUPPORTED_VERSION,
+				       "Recovery journal is in the old format. Downgrade and complete recovery, then upgrade with a clean volume");
+		return VDO_UNSUPPORTED_VERSION;
+	}
 
 	/* Set the tail to the last valid tail block, if there is one. */
 	if (repair->tail_recovery_point.sector_count == 0)

drivers/md/dm-vdo/status-codes.c

@@ -28,7 +28,7 @@ const struct error_info vdo_status_list[] = {
 	{ "VDO_LOCK_ERROR", "A lock is held incorrectly" },
 	{ "VDO_READ_ONLY", "The device is in read-only mode" },
 	{ "VDO_SHUTTING_DOWN", "The device is shutting down" },
-	{ "VDO_CORRUPT_JOURNAL", "Recovery journal entries corrupted" },
+	{ "VDO_CORRUPT_JOURNAL", "Recovery journal corrupted" },
 	{ "VDO_TOO_MANY_SLABS", "Exceeds maximum number of slabs supported" },
 	{ "VDO_INVALID_FRAGMENT", "Compressed block fragment is invalid" },
 	{ "VDO_RETRY_AFTER_REBUILD", "Retry operation after rebuilding finishes" },

drivers/md/dm-vdo/status-codes.h

@@ -52,7 +52,7 @@ enum vdo_status_codes {
 	VDO_READ_ONLY,
 	/* the VDO is shutting down */
 	VDO_SHUTTING_DOWN,
-	/* the recovery journal has corrupt entries */
+	/* the recovery journal has corrupt entries or corrupt metadata */
 	VDO_CORRUPT_JOURNAL,
 	/* exceeds maximum number of slabs supported */
 	VDO_TOO_MANY_SLABS,

drivers/md/dm-verity-target.c

@@ -273,8 +273,10 @@ out:
 	if (v->mode == DM_VERITY_MODE_LOGGING)
 		return 0;
 
-	if (v->mode == DM_VERITY_MODE_RESTART)
-		kernel_restart("dm-verity device corrupted");
+	if (v->mode == DM_VERITY_MODE_RESTART) {
+		pr_emerg("dm-verity device corrupted\n");
+		emergency_restart();
+	}
 
 	if (v->mode == DM_VERITY_MODE_PANIC)
 		panic("dm-verity device corrupted");
@@ -597,6 +599,23 @@ static void verity_finish_io(struct dm_verity_io *io, blk_status_t status)
 	if (!static_branch_unlikely(&use_bh_wq_enabled) || !io->in_bh)
 		verity_fec_finish_io(io);
 
+	if (unlikely(status != BLK_STS_OK) &&
+	    unlikely(!(bio->bi_opf & REQ_RAHEAD)) &&
+	    !verity_is_system_shutting_down()) {
+		if (v->mode == DM_VERITY_MODE_RESTART ||
+		    v->mode == DM_VERITY_MODE_PANIC)
+			DMERR_LIMIT("%s has error: %s", v->data_dev->name,
+					blk_status_to_str(status));
+
+		if (v->mode == DM_VERITY_MODE_RESTART) {
+			pr_emerg("dm-verity device corrupted\n");
+			emergency_restart();
+		}
+
+		if (v->mode == DM_VERITY_MODE_PANIC)
+			panic("dm-verity device corrupted");
+	}
+
 	bio_endio(bio);
 }
 

drivers/md/dm-verity-verify-sig.c

@@ -127,7 +127,7 @@ int verity_verify_root_hash(const void *root_hash, size_t root_hash_len,
 #endif
 				VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL);
 #ifdef CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG_PLATFORM_KEYRING
-	if (ret == -ENOKEY)
+	if (ret == -ENOKEY || ret == -EKEYREJECTED)
 		ret = verify_pkcs7_signature(root_hash, root_hash_len, sig_data,
 					sig_len,
 					VERIFY_USE_PLATFORM_KEYRING,

drivers/md/dm.c

@@ -2030,10 +2030,15 @@ static void dm_submit_bio(struct bio *bio)
 	struct dm_table *map;
 
 	map = dm_get_live_table(md, &srcu_idx);
+	if (unlikely(!map)) {
+		DMERR_LIMIT("%s: mapping table unavailable, erroring io",
+			    dm_device_name(md));
+		bio_io_error(bio);
+		goto out;
+	}
 
-	/* If suspended, or map not yet available, queue this IO for later */
-	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) ||
-	    unlikely(!map)) {
+	/* If suspended, queue this IO for later */
+	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		else if (bio->bi_opf & REQ_RAHEAD)

drivers/md/dm.h

@@ -109,7 +109,6 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone);
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
 bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
-int dm_zone_map_bio(struct dm_target_io *io);
 int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t,
 			     sector_t sector, unsigned int nr_zones,
 			     unsigned long *need_reset);
@@ -119,10 +118,6 @@ static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 {
 	return false;
 }
-static inline int dm_zone_map_bio(struct dm_target_io *tio)
-{
-	return DM_MAPIO_KILL;
-}
 #endif
 
 /*

drivers/sh/intc/userimask.c

@@ -32,8 +32,11 @@ store_intc_userimask(struct device *dev,
 		     const char *buf, size_t count)
 {
 	unsigned long level;
+	int ret;
 
-	level = simple_strtoul(buf, NULL, 10);
+	ret = kstrtoul(buf, 10, &level);
+	if (ret != 0)
+		return ret;
 
 	/*
 	 * Minimal acceptable IRQ levels are in the 2 - 16 range, but

drivers/xen/Kconfig

@@ -261,6 +261,7 @@ config XEN_SCSI_BACKEND
 config XEN_PRIVCMD
 	tristate "Xen hypercall passthrough driver"
 	depends on XEN
+	imply CONFIG_XEN_PCIDEV_BACKEND
 	default m
 	help
 	  The hypercall passthrough driver allows privileged user programs to

drivers/xen/acpi.c

@@ -30,6 +30,7 @@
  * IN THE SOFTWARE.
  */
 
+#include <linux/pci.h>
 #include <xen/acpi.h>
 #include <xen/interface/platform.h>
 #include <asm/xen/hypercall.h>
@@ -75,3 +76,52 @@ int xen_acpi_notify_hypervisor_extended_sleep(u8 sleep_state,
 	return xen_acpi_notify_hypervisor_state(sleep_state, val_a,
 						val_b, true);
 }
+
+struct acpi_prt_entry {
+	struct acpi_pci_id      id;
+	u8                      pin;
+	acpi_handle             link;
+	u32                     index;
+};
+
+int xen_acpi_get_gsi_info(struct pci_dev *dev,
+						  int *gsi_out,
+						  int *trigger_out,
+						  int *polarity_out)
+{
+	int gsi;
+	u8 pin;
+	struct acpi_prt_entry *entry;
+	int trigger = ACPI_LEVEL_SENSITIVE;
+	int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ?
+				      ACPI_ACTIVE_HIGH : ACPI_ACTIVE_LOW;
+
+	if (!dev || !gsi_out || !trigger_out || !polarity_out)
+		return -EINVAL;
+
+	pin = dev->pin;
+	if (!pin)
+		return -EINVAL;
+
+	entry = acpi_pci_irq_lookup(dev, pin);
+	if (entry) {
+		if (entry->link)
+			gsi = acpi_pci_link_allocate_irq(entry->link,
+							 entry->index,
+							 &trigger, &polarity,
+							 NULL);
+		else
+			gsi = entry->index;
+	} else
+		gsi = -1;
+
+	if (gsi < 0)
+		return -EINVAL;
+
+	*gsi_out = gsi;
+	*trigger_out = trigger;
+	*polarity_out = polarity;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_acpi_get_gsi_info);

drivers/xen/pci.c

@@ -173,6 +173,19 @@ static int xen_remove_device(struct device *dev)
 	return r;
 }
 
+int xen_reset_device(const struct pci_dev *dev)
+{
+	struct pci_device_reset device = {
+		.dev.seg = pci_domain_nr(dev->bus),
+		.dev.bus = dev->bus->number,
+		.dev.devfn = dev->devfn,
+		.flags = PCI_DEVICE_RESET_FLR,
+	};
+
+	return HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_reset, &device);
+}
+EXPORT_SYMBOL_GPL(xen_reset_device);
+
 static int xen_pci_notifier(struct notifier_block *nb,
 			    unsigned long action, void *data)
 {

drivers/xen/privcmd.c

@@ -46,6 +46,9 @@
 #include <xen/page.h>
 #include <xen/xen-ops.h>
 #include <xen/balloon.h>
+#ifdef CONFIG_XEN_ACPI
+#include <xen/acpi.h>
+#endif
 
 #include "privcmd.h"
 
@@ -844,6 +847,31 @@ out:
 	return rc;
 }
 
+static long privcmd_ioctl_pcidev_get_gsi(struct file *file, void __user *udata)
+{
+#if defined(CONFIG_XEN_ACPI)
+	int rc = -EINVAL;
+	struct privcmd_pcidev_get_gsi kdata;
+
+	if (copy_from_user(&kdata, udata, sizeof(kdata)))
+		return -EFAULT;
+
+	if (IS_REACHABLE(CONFIG_XEN_PCIDEV_BACKEND))
+		rc = pcistub_get_gsi_from_sbdf(kdata.sbdf);
+
+	if (rc < 0)
+		return rc;
+
+	kdata.gsi = rc;
+	if (copy_to_user(udata, &kdata, sizeof(kdata)))
+		return -EFAULT;
+
+	return 0;
+#else
+	return -EINVAL;
+#endif
+}
+
 #ifdef CONFIG_XEN_PRIVCMD_EVENTFD
 /* Irqfd support */
 static struct workqueue_struct *irqfd_cleanup_wq;
@@ -1543,6 +1571,10 @@ static long privcmd_ioctl(struct file *file,
 		ret = privcmd_ioctl_ioeventfd(file, udata);
 		break;
 
+	case IOCTL_PRIVCMD_PCIDEV_GET_GSI:
+		ret = privcmd_ioctl_pcidev_get_gsi(file, udata);
+		break;
+
 	default:
 		break;
 	}

drivers/xen/xen-pciback/conf_space_capability.c

@@ -122,7 +122,7 @@ static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value,
 	if (err)
 		goto out;
 
-	new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK);
+	new_state = (__force pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK);
 
 	new_value &= PM_OK_BITS;
 	if ((old_value & PM_OK_BITS) != new_value) {

drivers/xen/xen-pciback/pci_stub.c

@@ -21,6 +21,9 @@
 #include <xen/events.h>
 #include <xen/pci.h>
 #include <xen/xen.h>
+#ifdef CONFIG_XEN_ACPI
+#include <xen/acpi.h>
+#endif
 #include <asm/xen/hypervisor.h>
 #include <xen/interface/physdev.h>
 #include "pciback.h"
@@ -53,6 +56,9 @@ struct pcistub_device {
 
 	struct pci_dev *dev;
 	struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */
+#ifdef CONFIG_XEN_ACPI
+	int gsi;
+#endif
 };
 
 /* Access to pcistub_devices & seized_devices lists and the initialize_devices
@@ -85,10 +91,23 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev)
 
 	kref_init(&psdev->kref);
 	spin_lock_init(&psdev->lock);
+#ifdef CONFIG_XEN_ACPI
+	psdev->gsi = -1;
+#endif
 
 	return psdev;
 }
 
+static int pcistub_reset_device_state(struct pci_dev *dev)
+{
+	__pci_reset_function_locked(dev);
+
+	if (!xen_pv_domain())
+		return xen_reset_device(dev);
+	else
+		return 0;
+}
+
 /* Don't call this directly as it's called by pcistub_device_put */
 static void pcistub_device_release(struct kref *kref)
 {
@@ -107,7 +126,7 @@ static void pcistub_device_release(struct kref *kref)
 	/* Call the reset function which does not take lock as this
 	 * is called from "unbind" which takes a device_lock mutex.
 	 */
-	__pci_reset_function_locked(dev);
+	pcistub_reset_device_state(dev);
 	if (dev_data &&
 	    pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state))
 		dev_info(&dev->dev, "Could not reload PCI state\n");
@@ -207,6 +226,25 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev,
 	return pci_dev;
 }
 
+#ifdef CONFIG_XEN_ACPI
+int pcistub_get_gsi_from_sbdf(unsigned int sbdf)
+{
+	struct pcistub_device *psdev;
+	int domain = (sbdf >> 16) & 0xffff;
+	int bus = PCI_BUS_NUM(sbdf);
+	int slot = PCI_SLOT(sbdf);
+	int func = PCI_FUNC(sbdf);
+
+	psdev = pcistub_device_find(domain, bus, slot, func);
+
+	if (!psdev)
+		return -ENODEV;
+
+	return psdev->gsi;
+}
+EXPORT_SYMBOL_GPL(pcistub_get_gsi_from_sbdf);
+#endif
+
 struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev,
 					    int domain, int bus,
 					    int slot, int func)
@@ -284,7 +322,7 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	 * (so it's ready for the next domain)
 	 */
 	device_lock_assert(&dev->dev);
-	__pci_reset_function_locked(dev);
+	pcistub_reset_device_state(dev);
 
 	dev_data = pci_get_drvdata(dev);
 	ret = pci_load_saved_state(dev, dev_data->pci_saved_state);
@@ -354,11 +392,20 @@ static int pcistub_match(struct pci_dev *dev)
 	return found;
 }
 
-static int pcistub_init_device(struct pci_dev *dev)
+static int pcistub_init_device(struct pcistub_device *psdev)
 {
 	struct xen_pcibk_dev_data *dev_data;
+	struct pci_dev *dev;
+#ifdef CONFIG_XEN_ACPI
+	int gsi, trigger, polarity;
+#endif
 	int err = 0;
 
+	if (!psdev)
+		return -EINVAL;
+
+	dev = psdev->dev;
+
 	dev_dbg(&dev->dev, "initializing...\n");
 
 	/* The PCI backend is not intended to be a module (or to work with
@@ -420,9 +467,26 @@ static int pcistub_init_device(struct pci_dev *dev)
 		dev_err(&dev->dev, "Could not store PCI conf saved state!\n");
 	else {
 		dev_dbg(&dev->dev, "resetting (FLR, D3, etc) the device\n");
-		__pci_reset_function_locked(dev);
+		err = pcistub_reset_device_state(dev);
+		if (err)
+			goto config_release;
 		pci_restore_state(dev);
 	}
+
+#ifdef CONFIG_XEN_ACPI
+	if (xen_initial_domain() && xen_pvh_domain()) {
+		err = xen_acpi_get_gsi_info(dev, &gsi, &trigger, &polarity);
+		if (err) {
+			dev_err(&dev->dev, "Fail to get gsi info!\n");
+			goto config_release;
+		}
+		err = xen_pvh_setup_gsi(gsi, trigger, polarity);
+		if (err)
+			goto config_release;
+		psdev->gsi = gsi;
+	}
+#endif
+
 	/* Now disable the device (this also ensures some private device
 	 * data is setup before we export)
 	 */
@@ -462,7 +526,7 @@ static int __init pcistub_init_devices_late(void)
 
 		spin_unlock_irqrestore(&pcistub_devices_lock, flags);
 
-		err = pcistub_init_device(psdev->dev);
+		err = pcistub_init_device(psdev);
 		if (err) {
 			dev_err(&psdev->dev->dev,
 				"error %d initializing device\n", err);
@@ -532,7 +596,7 @@ static int pcistub_seize(struct pci_dev *dev,
 		spin_unlock_irqrestore(&pcistub_devices_lock, flags);
 
 		/* don't want irqs disabled when calling pcistub_init_device */
-		err = pcistub_init_device(psdev->dev);
+		err = pcistub_init_device(psdev);
 
 		spin_lock_irqsave(&pcistub_devices_lock, flags);
 
@@ -757,7 +821,7 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 	}
 	clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
-	res = (pci_ers_result_t)aer_op->err;
+	res = (__force pci_ers_result_t)aer_op->err;
 	return res;
 }
 

fs/ocfs2/aops.c

@@ -156,9 +156,8 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock,
 	err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
 					  &ext_flags);
 	if (err) {
-		mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
-		     "%llu, NULL)\n", err, inode, (unsigned long long)iblock,
-		     (unsigned long long)p_blkno);
+		mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, "
+		     "block: %llu\n", inode, (unsigned long long)iblock);
 		goto bail;
 	}
 

fs/ocfs2/extent_map.c

@@ -973,7 +973,13 @@ int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr,
 	}
 
 	while (done < nr) {
-		down_read(&OCFS2_I(inode)->ip_alloc_sem);
+		if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
+			rc = -EAGAIN;
+			mlog(ML_ERROR,
+				 "Inode #%llu ip_alloc_sem is temporarily unavailable\n",
+				 (unsigned long long)OCFS2_I(inode)->ip_blkno);
+			break;
+		}
 		rc = ocfs2_extent_map_get_blocks(inode, v_block + done,
 						 &p_block, &p_count, NULL);
 		up_read(&OCFS2_I(inode)->ip_alloc_sem);

fs/ocfs2/refcounttree.c

@@ -25,6 +25,7 @@
 #include "namei.h"
 #include "ocfs2_trace.h"
 #include "file.h"
+#include "symlink.h"
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>
@@ -4148,8 +4149,9 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 	int ret;
 	struct inode *inode = d_inode(old_dentry);
 	struct buffer_head *new_bh = NULL;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
+	if (oi->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
 		ret = -EINVAL;
 		mlog_errno(ret);
 		goto out;
@@ -4175,6 +4177,26 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 		goto out_unlock;
 	}
 
+	if ((oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) &&
+	    (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
+		/*
+		 * Adjust extent record count to reserve space for extended attribute.
+		 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
+		 */
+		struct ocfs2_inode_info *new_oi = OCFS2_I(new_inode);
+
+		if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+		    !(ocfs2_inode_is_fast_symlink(new_inode))) {
+			struct ocfs2_dinode *new_di = (struct ocfs2_dinode *)new_bh->b_data;
+			struct ocfs2_dinode *old_di = (struct ocfs2_dinode *)old_bh->b_data;
+			struct ocfs2_extent_list *el = &new_di->id2.i_list;
+			int inline_size = le16_to_cpu(old_di->i_xattr_inline_size);
+
+			le16_add_cpu(&el->l_count, -(inline_size /
+					sizeof(struct ocfs2_extent_rec)));
+		}
+	}
+
 	ret = ocfs2_create_reflink_node(inode, old_bh,
 					new_inode, new_bh, preserve);
 	if (ret) {
@@ -4182,7 +4204,7 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 		goto inode_unlock;
 	}
 
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
+	if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
 		ret = ocfs2_reflink_xattrs(inode, old_bh,
 					   new_inode, new_bh,
 					   preserve);

fs/ocfs2/xattr.c

@@ -6511,16 +6511,7 @@ static int ocfs2_reflink_xattr_inline(struct ocfs2_xattr_reflink *args)
 	}
 
 	new_oi = OCFS2_I(args->new_inode);
-	/*
-	 * Adjust extent record count to reserve space for extended attribute.
-	 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
-	 */
-	if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
-	    !(ocfs2_inode_is_fast_symlink(args->new_inode))) {
-		struct ocfs2_extent_list *el = &new_di->id2.i_list;
-		le16_add_cpu(&el->l_count, -(inline_size /
-					sizeof(struct ocfs2_extent_rec)));
-	}
+
 	spin_lock(&new_oi->ip_lock);
 	new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL;
 	new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features);

include/cxl/mailbox.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2024 Intel Corporation. */
+#ifndef __CXL_MBOX_H__
+#define __CXL_MBOX_H__
+#include <linux/rcuwait.h>
+
+struct cxl_mbox_cmd;
+
+/**
+ * struct cxl_mailbox - context for CXL mailbox operations
+ * @host: device that hosts the mailbox
+ * @payload_size: Size of space for payload
+ *                (CXL 3.1 8.2.8.4.3 Mailbox Capabilities Register)
+ * @mbox_mutex: mutex protects device mailbox and firmware
+ * @mbox_wait: rcuwait for mailbox
+ * @mbox_send: @dev specific transport for transmitting mailbox commands
+ */
+struct cxl_mailbox {
+	struct device *host;
+	size_t payload_size;
+	struct mutex mbox_mutex; /* lock to protect mailbox context */
+	struct rcuwait mbox_wait;
+	int (*mbox_send)(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd);
+};
+
+int cxl_mailbox_init(struct cxl_mailbox *cxl_mbox, struct device *host);
+
+#endif

include/linux/acpi.h

@@ -363,6 +363,7 @@ void acpi_unregister_gsi (u32 gsi);
 
 struct pci_dev;
 
+struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin);
 int acpi_pci_irq_enable (struct pci_dev *dev);
 void acpi_penalize_isa_irq(int irq, int active);
 bool acpi_isa_irq_available(int irq);

include/linux/bitmap.h

@@ -203,12 +203,12 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
  * the bit offset of all zero areas this function finds is multiples of that
  * power of 2. A @align_mask of 0 means no alignment is required.
  */
-static inline unsigned long
-bitmap_find_next_zero_area(unsigned long *map,
-			   unsigned long size,
-			   unsigned long start,
-			   unsigned int nr,
-			   unsigned long align_mask)
+static __always_inline
+unsigned long bitmap_find_next_zero_area(unsigned long *map,
+					 unsigned long size,
+					 unsigned long start,
+					 unsigned int nr,
+					 unsigned long align_mask)
 {
 	return bitmap_find_next_zero_area_off(map, size, start, nr,
 					      align_mask, 0);
@@ -228,7 +228,7 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 
 #define bitmap_size(nbits)	(ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
 
-static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
+static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = bitmap_size(nbits);
 
@@ -238,7 +238,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 		memset(dst, 0, len);
 }
 
-static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
+static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
 	unsigned int len = bitmap_size(nbits);
 
@@ -248,8 +248,8 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 		memset(dst, 0xff, len);
 }
 
-static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
-			unsigned int nbits)
+static __always_inline
+void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	unsigned int len = bitmap_size(nbits);
 
@@ -262,8 +262,8 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 /*
  * Copy bitmap and clear tail bits in last word.
  */
-static inline void bitmap_copy_clear_tail(unsigned long *dst,
-		const unsigned long *src, unsigned int nbits)
+static __always_inline
+void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	bitmap_copy(dst, src, nbits);
 	if (nbits % BITS_PER_LONG)
@@ -318,16 +318,18 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
 	bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits))
 #endif
 
-static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_and(unsigned long *dst, const unsigned long *src1,
+		const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_and(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+void bitmap_or(unsigned long *dst, const unsigned long *src1,
+	       const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 | *src2;
@@ -335,8 +337,9 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 		__bitmap_or(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+void bitmap_xor(unsigned long *dst, const unsigned long *src1,
+		const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 ^ *src2;
@@ -344,16 +347,17 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 		__bitmap_xor(dst, src1, src2, nbits);
 }
 
-static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+		   const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_andnot(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
-			unsigned int nbits)
+static __always_inline
+void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = ~(*src);
@@ -368,8 +372,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr
 #endif
 #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
 
-static inline bool bitmap_equal(const unsigned long *src1,
-				const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
@@ -388,10 +392,9 @@ static inline bool bitmap_equal(const unsigned long *src1,
  *
  * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
  */
-static inline bool bitmap_or_equal(const unsigned long *src1,
-				   const unsigned long *src2,
-				   const unsigned long *src3,
-				   unsigned int nbits)
+static __always_inline
+bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2,
+		     const unsigned long *src3, unsigned int nbits)
 {
 	if (!small_const_nbits(nbits))
 		return __bitmap_or_equal(src1, src2, src3, nbits);
@@ -399,9 +402,8 @@ static inline bool bitmap_or_equal(const unsigned long *src1,
 	return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits));
 }
 
-static inline bool bitmap_intersects(const unsigned long *src1,
-				     const unsigned long *src2,
-				     unsigned int nbits)
+static __always_inline
+bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
@@ -409,8 +411,8 @@ static inline bool bitmap_intersects(const unsigned long *src1,
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
-static inline bool bitmap_subset(const unsigned long *src1,
-				 const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
@@ -418,7 +420,8 @@ static inline bool bitmap_subset(const unsigned long *src1,
 		return __bitmap_subset(src1, src2, nbits);
 }
 
-static inline bool bitmap_empty(const unsigned long *src, unsigned nbits)
+static __always_inline
+bool bitmap_empty(const unsigned long *src, unsigned nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -426,7 +429,8 @@ static inline bool bitmap_empty(const unsigned long *src, unsigned nbits)
 	return find_first_bit(src, nbits) == nbits;
 }
 
-static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
+static __always_inline
+bool bitmap_full(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
@@ -460,8 +464,8 @@ unsigned long bitmap_weight_andnot(const unsigned long *src1,
 	return __bitmap_weight_andnot(src1, src2, nbits);
 }
 
-static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
-		unsigned int nbits)
+static __always_inline
+void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits)
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__set_bit(start, map);
@@ -476,8 +480,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 		__bitmap_set(map, start, nbits);
 }
 
-static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
-		unsigned int nbits)
+static __always_inline
+void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits)
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__clear_bit(start, map);
@@ -492,8 +496,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
 		__bitmap_clear(map, start, nbits);
 }
 
-static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
-				unsigned int shift, unsigned int nbits)
+static __always_inline
+void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
+			unsigned int shift, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift;
@@ -501,8 +506,9 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s
 		__bitmap_shift_right(dst, src, shift, nbits);
 }
 
-static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
-				unsigned int shift, unsigned int nbits)
+static __always_inline
+void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
+		       unsigned int shift, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits);
@@ -510,11 +516,12 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr
 		__bitmap_shift_left(dst, src, shift, nbits);
 }
 
-static inline void bitmap_replace(unsigned long *dst,
-				  const unsigned long *old,
-				  const unsigned long *new,
-				  const unsigned long *mask,
-				  unsigned int nbits)
+static __always_inline
+void bitmap_replace(unsigned long *dst,
+		    const unsigned long *old,
+		    const unsigned long *new,
+		    const unsigned long *mask,
+		    unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*old & ~(*mask)) | (*new & *mask);
@@ -557,8 +564,9 @@ static inline void bitmap_replace(unsigned long *dst,
  * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation.
  * See bitmap_scatter() for details related to this relationship.
  */
-static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src,
-				  const unsigned long *mask, unsigned int nbits)
+static __always_inline
+void bitmap_scatter(unsigned long *dst, const unsigned long *src,
+		    const unsigned long *mask, unsigned int nbits)
 {
 	unsigned int n = 0;
 	unsigned int bit;
@@ -611,8 +619,9 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src,
  * bitmap_scatter(res, src, mask, n) and a call to
  * bitmap_scatter(res, result, mask, n) will lead to the same res value.
  */
-static inline void bitmap_gather(unsigned long *dst, const unsigned long *src,
-				 const unsigned long *mask, unsigned int nbits)
+static __always_inline
+void bitmap_gather(unsigned long *dst, const unsigned long *src,
+		   const unsigned long *mask, unsigned int nbits)
 {
 	unsigned int n = 0;
 	unsigned int bit;
@@ -623,9 +632,9 @@ static inline void bitmap_gather(unsigned long *dst, const unsigned long *src,
 		__assign_bit(n++, dst, test_bit(bit, src));
 }
 
-static inline void bitmap_next_set_region(unsigned long *bitmap,
-					  unsigned int *rs, unsigned int *re,
-					  unsigned int end)
+static __always_inline
+void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs,
+			    unsigned int *re, unsigned int end)
 {
 	*rs = find_next_bit(bitmap, end, *rs);
 	*re = find_next_zero_bit(bitmap, end, *rs + 1);
@@ -640,7 +649,8 @@ static inline void bitmap_next_set_region(unsigned long *bitmap,
  * This is the complement to __bitmap_find_free_region() and releases
  * the found region (by clearing it in the bitmap).
  */
-static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order)
+static __always_inline
+void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order)
 {
 	bitmap_clear(bitmap, pos, BIT(order));
 }
@@ -656,7 +666,8 @@ static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos
  * Returns: 0 on success, or %-EBUSY if specified region wasn't
  * free (not all bits were zero).
  */
-static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order)
+static __always_inline
+int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order)
 {
 	unsigned int len = BIT(order);
 
@@ -680,7 +691,8 @@ static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos
  * Returns: the bit offset in bitmap of the allocated region,
  * or -errno on failure.
  */
-static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order)
+static __always_inline
+int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order)
 {
 	unsigned int pos, end;		/* scans bitmap by regions of size order */
 
@@ -734,7 +746,7 @@ static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bi
  * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits,
  * but we expect the lower 32-bits of u64.
  */
-static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
+static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask)
 {
 	bitmap_from_arr64(dst, &mask, 64);
 }
@@ -749,9 +761,8 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
  * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return
  * value is undefined.
  */
-static inline unsigned long bitmap_read(const unsigned long *map,
-					unsigned long start,
-					unsigned long nbits)
+static __always_inline
+unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits)
 {
 	size_t index = BIT_WORD(start);
 	unsigned long offset = start % BITS_PER_LONG;
@@ -784,8 +795,9 @@ static inline unsigned long bitmap_read(const unsigned long *map,
  *
  * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed.
  */
-static inline void bitmap_write(unsigned long *map, unsigned long value,
-				unsigned long start, unsigned long nbits)
+static __always_inline
+void bitmap_write(unsigned long *map, unsigned long value,
+		  unsigned long start, unsigned long nbits)
 {
 	size_t index;
 	unsigned long offset;

include/linux/bits.h

@@ -36,4 +36,19 @@
 #define GENMASK_ULL(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __GENMASK_U128() depends on _BIT128() which would not work
+ * in the asm code, as it shifts an 'unsigned __init128' data
+ * type instead of direct representation of 128 bit constants
+ * such as long and unsigned long. The fundamental problem is
+ * that a 128 bit constant will get silently truncated by the
+ * gcc compiler.
+ */
+#define GENMASK_U128(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
+#endif
+
 #endif	/* __LINUX_BITS_H */

include/linux/compiler.h

@@ -133,7 +133,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #define annotate_unreachable() __annotate_unreachable(__COUNTER__)
 
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(".rodata..c_jump_table")
+#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #")
 
 #else /* !CONFIG_OBJTOOL */
 #define annotate_reachable()

include/linux/cpumask.h

@@ -30,7 +30,7 @@
 extern unsigned int nr_cpu_ids;
 #endif
 
-static inline void set_nr_cpu_ids(unsigned int nr)
+static __always_inline void set_nr_cpu_ids(unsigned int nr)
 {
 #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
 	WARN_ON(nr != nr_cpu_ids);
@@ -149,7 +149,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu)
  *
  * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline unsigned int cpumask_first(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first(const struct cpumask *srcp)
 {
 	return find_first_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -160,7 +160,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if all cpus are set.
  */
-static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 {
 	return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -172,7 +172,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
  */
-static inline
+static __always_inline
 unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
 	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
@@ -186,7 +186,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
  *
  * Return: >= nr_cpu_ids if no cpus set in all.
  */
-static inline
+static __always_inline
 unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
 				   const struct cpumask *srcp2,
 				   const struct cpumask *srcp3)
@@ -201,7 +201,7 @@ unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
  *
  * Return:	>= nr_cpumask_bits if no CPUs set.
  */
-static inline unsigned int cpumask_last(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_last(const struct cpumask *srcp)
 {
 	return find_last_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -213,7 +213,7 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no further cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
@@ -229,7 +229,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no further cpus unset.
  */
-static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -239,18 +240,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 
 #if NR_CPUS == 1
 /* Uniprocessor: there is only one valid CPU */
-static inline unsigned int cpumask_local_spread(unsigned int i, int node)
+static __always_inline
+unsigned int cpumask_local_spread(unsigned int i, int node)
 {
 	return 0;
 }
 
-static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
-						      const struct cpumask *src2p)
+static __always_inline
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
+					const struct cpumask *src2p)
 {
 	return cpumask_first_and(src1p, src2p);
 }
 
-static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	return cpumask_first(srcp);
 }
@@ -269,9 +273,9 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp);
  *
  * Return: >= nr_cpu_ids if no further cpus set in both.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
-		     const struct cpumask *src2p)
+			      const struct cpumask *src2p)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -291,7 +295,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
 
 #if NR_CPUS == 1
-static inline
+static __always_inline
 unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
 {
 	cpumask_check(start);
@@ -394,7 +398,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * Often used to find any cpu but smp_processor_id() in a mask.
  * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 {
 	unsigned int i;
@@ -414,7 +418,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  *
  * Returns >= nr_cpu_ids if no cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_any_and_but(const struct cpumask *mask1,
 				 const struct cpumask *mask2,
 				 unsigned int cpu)
@@ -436,7 +440,8 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1,
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
 {
 	return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu));
 }
@@ -449,7 +454,7 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline
+static __always_inline
 unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
@@ -465,7 +470,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline
+static __always_inline
 unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
@@ -508,12 +513,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
@@ -557,7 +564,8 @@ static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp,
  *
  * Return: true if @cpu is set in @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
 {
 	return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
 }
@@ -571,7 +579,8 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum
  *
  * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -585,7 +594,8 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp
  *
  * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -594,7 +604,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *
  * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_setall(struct cpumask *dstp)
+static __always_inline void cpumask_setall(struct cpumask *dstp)
 {
 	if (small_const_nbits(small_cpumask_bits)) {
 		cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits);
@@ -607,7 +617,7 @@ static inline void cpumask_setall(struct cpumask *dstp)
  * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_clear(struct cpumask *dstp)
+static __always_inline void cpumask_clear(struct cpumask *dstp)
 {
 	bitmap_zero(cpumask_bits(dstp), large_cpumask_bits);
 }
@@ -620,9 +630,9 @@ static inline void cpumask_clear(struct cpumask *dstp)
  *
  * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_and(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -634,8 +644,9 @@ static inline bool cpumask_and(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
-			      const struct cpumask *src2p)
+static __always_inline
+void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
+		const struct cpumask *src2p)
 {
 	bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p),
 				      cpumask_bits(src2p), small_cpumask_bits);
@@ -647,9 +658,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_xor(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -663,9 +674,9 @@ static inline void cpumask_xor(struct cpumask *dstp,
  *
  * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_andnot(struct cpumask *dstp,
-				  const struct cpumask *src1p,
-				  const struct cpumask *src2p)
+static __always_inline
+bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p,
+		    const struct cpumask *src2p)
 {
 	return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
 					  cpumask_bits(src2p), small_cpumask_bits);
@@ -678,8 +689,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp,
  *
  * Return: true if the cpumasks are equal, false if not
  */
-static inline bool cpumask_equal(const struct cpumask *src1p,
-				const struct cpumask *src2p)
+static __always_inline
+bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 						 small_cpumask_bits);
@@ -694,9 +705,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p,
  * Return: true if first cpumask ORed with second cpumask == third cpumask,
  *	   otherwise false
  */
-static inline bool cpumask_or_equal(const struct cpumask *src1p,
-				    const struct cpumask *src2p,
-				    const struct cpumask *src3p)
+static __always_inline
+bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p,
+		      const struct cpumask *src3p)
 {
 	return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 			       cpumask_bits(src3p), small_cpumask_bits);
@@ -710,8 +721,8 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p,
  * Return: true if first cpumask ANDed with second cpumask is non-empty,
  *	   otherwise false
  */
-static inline bool cpumask_intersects(const struct cpumask *src1p,
-				     const struct cpumask *src2p)
+static __always_inline
+bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p),
 						      small_cpumask_bits);
@@ -724,8 +735,8 @@ static inline bool cpumask_intersects(const struct cpumask *src1p,
  *
  * Return: true if *@src1p is a subset of *@src2p, else returns false
  */
-static inline bool cpumask_subset(const struct cpumask *src1p,
-				 const struct cpumask *src2p)
+static __always_inline
+bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
 						  small_cpumask_bits);
@@ -737,7 +748,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p,
  *
  * Return: true if srcp is empty (has no bits set), else false
  */
-static inline bool cpumask_empty(const struct cpumask *srcp)
+static __always_inline bool cpumask_empty(const struct cpumask *srcp)
 {
 	return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -748,7 +759,7 @@ static inline bool cpumask_empty(const struct cpumask *srcp)
  *
  * Return: true if srcp is full (has all bits set), else false
  */
-static inline bool cpumask_full(const struct cpumask *srcp)
+static __always_inline bool cpumask_full(const struct cpumask *srcp)
 {
 	return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits);
 }
@@ -759,7 +770,7 @@ static inline bool cpumask_full(const struct cpumask *srcp)
  *
  * Return: count of bits set in *srcp
  */
-static inline unsigned int cpumask_weight(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp)
 {
 	return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -771,8 +782,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
  *
  * Return: count of bits set in both *srcp1 and *srcp2
  */
-static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
-						const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
 	return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
@@ -784,8 +795,9 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
  *
  * Return: count of bits set in both *srcp1 and *srcp2
  */
-static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
-						const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
+				   const struct cpumask *srcp2)
 {
 	return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
@@ -796,8 +808,8 @@ static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_right(struct cpumask *dstp,
-				       const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					       small_cpumask_bits);
@@ -809,8 +821,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp,
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_left(struct cpumask *dstp,
-				      const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					      nr_cpumask_bits);
@@ -821,8 +833,8 @@ static inline void cpumask_shift_left(struct cpumask *dstp,
  * @dstp: the result
  * @srcp: the input cpumask
  */
-static inline void cpumask_copy(struct cpumask *dstp,
-				const struct cpumask *srcp)
+static __always_inline
+void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp)
 {
 	bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits);
 }
@@ -858,8 +870,8 @@ static inline void cpumask_copy(struct cpumask *dstp,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -872,8 +884,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parselist_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
 				     nr_cpumask_bits);
@@ -886,7 +898,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -898,7 +910,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -908,7 +920,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
  *
  * Return: size to allocate for a &struct cpumask in bytes
  */
-static inline unsigned int cpumask_size(void)
+static __always_inline unsigned int cpumask_size(void)
 {
 	return bitmap_size(large_cpumask_bits);
 }
@@ -920,7 +932,7 @@ static inline unsigned int cpumask_size(void)
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 
-static inline
+static __always_inline
 bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 {
 	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
@@ -938,13 +950,13 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
  *
  * Return: %true if allocation succeeded, %false if not
  */
-static inline
+static __always_inline
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
 }
 
-static inline
+static __always_inline
 bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
@@ -954,7 +966,7 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
 void free_bootmem_cpumask_var(cpumask_var_t mask);
 
-static inline bool cpumask_available(cpumask_var_t mask)
+static __always_inline bool cpumask_available(cpumask_var_t mask)
 {
 	return mask != NULL;
 }
@@ -964,43 +976,43 @@ static inline bool cpumask_available(cpumask_var_t mask)
 #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
 #define __cpumask_var_read_mostly
 
-static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return true;
 }
 
-static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
 					  int node)
 {
 	return true;
 }
 
-static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	cpumask_clear(*mask);
 	return true;
 }
 
-static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
 					  int node)
 {
 	cpumask_clear(*mask);
 	return true;
 }
 
-static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
+static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
 }
 
-static inline void free_cpumask_var(cpumask_var_t mask)
+static __always_inline void free_cpumask_var(cpumask_var_t mask)
 {
 }
 
-static inline void free_bootmem_cpumask_var(cpumask_var_t mask)
+static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask)
 {
 }
 
-static inline bool cpumask_available(cpumask_var_t mask)
+static __always_inline bool cpumask_available(cpumask_var_t mask)
 {
 	return true;
 }
@@ -1058,7 +1070,7 @@ void set_cpu_online(unsigned int cpu, bool online);
 	((struct cpumask *)(1 ? (bitmap)				\
 			    : (void *)sizeof(__check_is_bitmap(bitmap))))
 
-static inline int __check_is_bitmap(const unsigned long *bitmap)
+static __always_inline int __check_is_bitmap(const unsigned long *bitmap)
 {
 	return 1;
 }
@@ -1073,7 +1085,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap)
 extern const unsigned long
 	cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)];
 
-static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
+static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 {
 	const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];
 	p -= cpu / BITS_PER_LONG;
@@ -1100,32 +1112,32 @@ static __always_inline unsigned int num_online_cpus(void)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)
 #define num_active_cpus()	cpumask_weight(cpu_active_mask)
 
-static inline bool cpu_online(unsigned int cpu)
+static __always_inline bool cpu_online(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_online_mask);
 }
 
-static inline bool cpu_enabled(unsigned int cpu)
+static __always_inline bool cpu_enabled(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_enabled_mask);
 }
 
-static inline bool cpu_possible(unsigned int cpu)
+static __always_inline bool cpu_possible(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_possible_mask);
 }
 
-static inline bool cpu_present(unsigned int cpu)
+static __always_inline bool cpu_present(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_present_mask);
 }
 
-static inline bool cpu_active(unsigned int cpu)
+static __always_inline bool cpu_active(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_active_mask);
 }
 
-static inline bool cpu_dying(unsigned int cpu)
+static __always_inline bool cpu_dying(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_dying_mask);
 }
@@ -1138,32 +1150,32 @@ static inline bool cpu_dying(unsigned int cpu)
 #define num_present_cpus()	1U
 #define num_active_cpus()	1U
 
-static inline bool cpu_online(unsigned int cpu)
+static __always_inline bool cpu_online(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_possible(unsigned int cpu)
+static __always_inline bool cpu_possible(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_enabled(unsigned int cpu)
+static __always_inline bool cpu_enabled(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_present(unsigned int cpu)
+static __always_inline bool cpu_present(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_active(unsigned int cpu)
+static __always_inline bool cpu_active(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_dying(unsigned int cpu)
+static __always_inline bool cpu_dying(unsigned int cpu)
 {
 	return false;
 }
@@ -1197,7 +1209,7 @@ static inline bool cpu_dying(unsigned int cpu)
  * Return: the length of the (null-terminated) @buf string, zero if
  * nothing is copied.
  */
-static inline ssize_t
+static __always_inline ssize_t
 cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
 {
 	return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask),
@@ -1220,9 +1232,9 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
  * Return: the length of how many bytes have been copied, excluding
  * terminating '\0'.
  */
-static inline ssize_t
-cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
-		loff_t off, size_t count)
+static __always_inline
+ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
+				    loff_t off, size_t count)
 {
 	return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask),
 				   nr_cpu_ids, off, count) - 1;
@@ -1242,9 +1254,9 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
  * Return: the length of how many bytes have been copied, excluding
  * terminating '\0'.
  */
-static inline ssize_t
-cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
-		loff_t off, size_t count)
+static __always_inline
+ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
+				 loff_t off, size_t count)
 {
 	return bitmap_print_list_to_buf(buf, cpumask_bits(mask),
 				   nr_cpu_ids, off, count) - 1;

include/linux/device-mapper.h

@@ -524,7 +524,6 @@ int dm_post_suspending(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors);
 void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone);
-union map_info *dm_get_rq_mapinfo(struct request *rq);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 struct dm_report_zones_args {

include/linux/find.h

@@ -52,7 +52,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 			    unsigned long offset)
 {
@@ -81,7 +81,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -112,7 +112,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_andnot_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -142,7 +142,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_or_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -171,7 +171,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1,
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
@@ -198,7 +198,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
  * Returns the bit number of the first set bit.
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -224,7 +224,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
  * Returns the bit number of the N'th set bit.
  * If no such, returns >= @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
 {
 	if (n >= size)
@@ -249,7 +249,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign
  * Returns the bit number of the N'th set bit.
  * If no such, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
 				unsigned long size, unsigned long n)
 {
@@ -276,7 +276,7 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *
  * Returns the bit number of the N'th set bit.
  * If no such, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
 				unsigned long size, unsigned long n)
 {
@@ -332,7 +332,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_and_bit(const unsigned long *addr1,
 				 const unsigned long *addr2,
 				 unsigned long size)
@@ -357,7 +357,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
  * Returns the bit number for the first set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_and_and_bit(const unsigned long *addr1,
 				     const unsigned long *addr2,
 				     const unsigned long *addr3,
@@ -381,7 +381,7 @@ unsigned long find_first_and_and_bit(const unsigned long *addr1,
  * Returns the bit number of the first cleared bit.
  * If no bits are zero, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -402,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
  *
  * Returns the bit number of the last set bit, or size.
  */
-static inline
+static __always_inline
 unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -425,7 +425,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
  * Returns the bit number for the next set bit, or first set bit up to @offset
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
 					const unsigned long *addr2,
 					unsigned long size, unsigned long offset)
@@ -448,7 +448,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
  * Returns the bit number for the next set bit, or first set bit up to @offset
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_bit_wrap(const unsigned long *addr,
 					unsigned long size, unsigned long offset)
 {
@@ -465,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr,
  * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing
  * before using it alone.
  */
-static inline
+static __always_inline
 unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size,
 				 unsigned long start, unsigned long n)
 {
@@ -506,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump,
 
 #if defined(__LITTLE_ENDIAN)
 
-static inline unsigned long find_next_zero_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
+static __always_inline
+unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset)
 {
 	return find_next_zero_bit(addr, size, offset);
 }
 
-static inline unsigned long find_next_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
+static __always_inline
+unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset)
 {
 	return find_next_bit(addr, size, offset);
 }
 
-static inline unsigned long find_first_zero_bit_le(const void *addr,
-		unsigned long size)
+static __always_inline
+unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 {
 	return find_first_zero_bit(addr, size);
 }
@@ -527,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr,
 #elif defined(__BIG_ENDIAN)
 
 #ifndef find_next_zero_bit_le
-static inline
+static __always_inline
 unsigned long find_next_zero_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
@@ -546,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned
 #endif
 
 #ifndef find_first_zero_bit_le
-static inline
+static __always_inline
 unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -560,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 #endif
 
 #ifndef find_next_bit_le
-static inline
+static __always_inline
 unsigned long find_next_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {

include/linux/hugetlb.h

@@ -692,6 +692,9 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask, gfp_t gfp_mask,
 				bool allow_alloc_fallback);
+struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
+					  nodemask_t *nmask, gfp_t gfp_mask);
+
 int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
 			pgoff_t idx);
 void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
@@ -1059,6 +1062,13 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	return NULL;
 }
 
+static inline struct folio *
+alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
+			    nodemask_t *nmask, gfp_t gfp_mask)
+{
+	return NULL;
+}
+
 static inline struct folio *
 alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 			nodemask_t *nmask, gfp_t gfp_mask,

include/linux/nodemask.h

@@ -107,11 +107,11 @@ extern nodemask_t _unused_nodemask_arg_;
  */
 #define nodemask_pr_args(maskp)	__nodemask_pr_numnodes(maskp), \
 				__nodemask_pr_bits(maskp)
-static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
+static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
 {
 	return m ? MAX_NUMNODES : 0;
 }
-static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
+static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
 {
 	return m ? m->bits : NULL;
 }
@@ -132,19 +132,19 @@ static __always_inline void __node_set(int node, volatile nodemask_t *dstp)
 }
 
 #define node_clear(node, dst) __node_clear((node), &(dst))
-static inline void __node_clear(int node, volatile nodemask_t *dstp)
+static __always_inline void __node_clear(int node, volatile nodemask_t *dstp)
 {
 	clear_bit(node, dstp->bits);
 }
 
 #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
-static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
+static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_fill(dstp->bits, nbits);
 }
 
 #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
-static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
+static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_zero(dstp->bits, nbits);
 }
@@ -154,14 +154,14 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 
 #define node_test_and_set(node, nodemask) \
 			__node_test_and_set((node), &(nodemask))
-static inline bool __node_test_and_set(int node, nodemask_t *addr)
+static __always_inline bool __node_test_and_set(int node, nodemask_t *addr)
 {
 	return test_and_set_bit(node, addr->bits);
 }
 
 #define nodes_and(dst, src1, src2) \
 			__nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
@@ -169,7 +169,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
 
 #define nodes_or(dst, src1, src2) \
 			__nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
@@ -177,7 +177,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
 
 #define nodes_xor(dst, src1, src2) \
 			__nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
@@ -185,7 +185,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
 
 #define nodes_andnot(dst, src1, src2) \
 			__nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
@@ -193,7 +193,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
 
 #define nodes_complement(dst, src) \
 			__nodes_complement(&(dst), &(src), MAX_NUMNODES)
-static inline void __nodes_complement(nodemask_t *dstp,
+static __always_inline void __nodes_complement(nodemask_t *dstp,
 					const nodemask_t *srcp, unsigned int nbits)
 {
 	bitmap_complement(dstp->bits, srcp->bits, nbits);
@@ -201,7 +201,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
 
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
-static inline bool __nodes_equal(const nodemask_t *src1p,
+static __always_inline bool __nodes_equal(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
@@ -209,7 +209,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p,
 
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
-static inline bool __nodes_intersects(const nodemask_t *src1p,
+static __always_inline bool __nodes_intersects(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
@@ -217,33 +217,33 @@ static inline bool __nodes_intersects(const nodemask_t *src1p,
 
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
-static inline bool __nodes_subset(const nodemask_t *src1p,
+static __always_inline bool __nodes_subset(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
+static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
+static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }
 
 #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
+static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_weight(srcp->bits, nbits);
 }
 
 #define nodes_shift_right(dst, src, n) \
 			__nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES)
-static inline void __nodes_shift_right(nodemask_t *dstp,
+static __always_inline void __nodes_shift_right(nodemask_t *dstp,
 					const nodemask_t *srcp, int n, int nbits)
 {
 	bitmap_shift_right(dstp->bits, srcp->bits, n, nbits);
@@ -251,7 +251,7 @@ static inline void __nodes_shift_right(nodemask_t *dstp,
 
 #define nodes_shift_left(dst, src, n) \
 			__nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES)
-static inline void __nodes_shift_left(nodemask_t *dstp,
+static __always_inline void __nodes_shift_left(nodemask_t *dstp,
 					const nodemask_t *srcp, int n, int nbits)
 {
 	bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
@@ -261,13 +261,13 @@ static inline void __nodes_shift_left(nodemask_t *dstp,
           > MAX_NUMNODES, then the silly min_ts could be dropped. */
 
 #define first_node(src) __first_node(&(src))
-static inline unsigned int __first_node(const nodemask_t *srcp)
+static __always_inline unsigned int __first_node(const nodemask_t *srcp)
 {
 	return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
 }
 
 #define next_node(n, src) __next_node((n), &(src))
-static inline unsigned int __next_node(int n, const nodemask_t *srcp)
+static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp)
 {
 	return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
 }
@@ -277,7 +277,7 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp)
  * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
  */
 #define next_node_in(n, src) __next_node_in((n), &(src))
-static inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
+static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
 {
 	unsigned int ret = __next_node(node, srcp);
 
@@ -286,7 +286,7 @@ static inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
 	return ret;
 }
 
-static inline void init_nodemask_of_node(nodemask_t *mask, int node)
+static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node)
 {
 	nodes_clear(*mask);
 	node_set(node, *mask);
@@ -304,7 +304,7 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 })
 
 #define first_unset_node(mask) __first_unset_node(&(mask))
-static inline unsigned int __first_unset_node(const nodemask_t *maskp)
+static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp)
 {
 	return min_t(unsigned int, MAX_NUMNODES,
 			find_first_zero_bit(maskp->bits, MAX_NUMNODES));
@@ -338,21 +338,21 @@ static inline unsigned int __first_unset_node(const nodemask_t *maskp)
 
 #define nodemask_parse_user(ubuf, ulen, dst) \
 		__nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES)
-static inline int __nodemask_parse_user(const char __user *buf, int len,
+static __always_inline int __nodemask_parse_user(const char __user *buf, int len,
 					nodemask_t *dstp, int nbits)
 {
 	return bitmap_parse_user(buf, len, dstp->bits, nbits);
 }
 
 #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES)
-static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits)
+static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits)
 {
 	return bitmap_parselist(buf, dstp->bits, nbits);
 }
 
 #define node_remap(oldbit, old, new) \
 		__node_remap((oldbit), &(old), &(new), MAX_NUMNODES)
-static inline int __node_remap(int oldbit,
+static __always_inline int __node_remap(int oldbit,
 		const nodemask_t *oldp, const nodemask_t *newp, int nbits)
 {
 	return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits);
@@ -360,7 +360,7 @@ static inline int __node_remap(int oldbit,
 
 #define nodes_remap(dst, src, old, new) \
 		__nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES)
-static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
+static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
 		const nodemask_t *oldp, const nodemask_t *newp, int nbits)
 {
 	bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits);
@@ -368,7 +368,7 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
 
 #define nodes_onto(dst, orig, relmap) \
 		__nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES)
-static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
+static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
 		const nodemask_t *relmapp, int nbits)
 {
 	bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits);
@@ -376,7 +376,7 @@ static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
 
 #define nodes_fold(dst, orig, sz) \
 		__nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES)
-static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
+static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
 		int sz, int nbits)
 {
 	bitmap_fold(dstp->bits, origp->bits, sz, nbits);
@@ -418,22 +418,22 @@ enum node_states {
 extern nodemask_t node_states[NR_NODE_STATES];
 
 #if MAX_NUMNODES > 1
-static inline int node_state(int node, enum node_states state)
+static __always_inline int node_state(int node, enum node_states state)
 {
 	return node_isset(node, node_states[state]);
 }
 
-static inline void node_set_state(int node, enum node_states state)
+static __always_inline void node_set_state(int node, enum node_states state)
 {
 	__node_set(node, &node_states[state]);
 }
 
-static inline void node_clear_state(int node, enum node_states state)
+static __always_inline void node_clear_state(int node, enum node_states state)
 {
 	__node_clear(node, &node_states[state]);
 }
 
-static inline int num_node_state(enum node_states state)
+static __always_inline int num_node_state(enum node_states state)
 {
 	return nodes_weight(node_states[state]);
 }
@@ -443,11 +443,11 @@ static inline int num_node_state(enum node_states state)
 
 #define first_online_node	first_node(node_states[N_ONLINE])
 #define first_memory_node	first_node(node_states[N_MEMORY])
-static inline unsigned int next_online_node(int nid)
+static __always_inline unsigned int next_online_node(int nid)
 {
 	return next_node(nid, node_states[N_ONLINE]);
 }
-static inline unsigned int next_memory_node(int nid)
+static __always_inline unsigned int next_memory_node(int nid)
 {
 	return next_node(nid, node_states[N_MEMORY]);
 }
@@ -455,13 +455,13 @@ static inline unsigned int next_memory_node(int nid)
 extern unsigned int nr_node_ids;
 extern unsigned int nr_online_nodes;
 
-static inline void node_set_online(int nid)
+static __always_inline void node_set_online(int nid)
 {
 	node_set_state(nid, N_ONLINE);
 	nr_online_nodes = num_node_state(N_ONLINE);
 }
 
-static inline void node_set_offline(int nid)
+static __always_inline void node_set_offline(int nid)
 {
 	node_clear_state(nid, N_ONLINE);
 	nr_online_nodes = num_node_state(N_ONLINE);
@@ -469,20 +469,20 @@ static inline void node_set_offline(int nid)
 
 #else
 
-static inline int node_state(int node, enum node_states state)
+static __always_inline int node_state(int node, enum node_states state)
 {
 	return node == 0;
 }
 
-static inline void node_set_state(int node, enum node_states state)
+static __always_inline void node_set_state(int node, enum node_states state)
 {
 }
 
-static inline void node_clear_state(int node, enum node_states state)
+static __always_inline void node_clear_state(int node, enum node_states state)
 {
 }
 
-static inline int num_node_state(enum node_states state)
+static __always_inline int num_node_state(enum node_states state)
 {
 	return 1;
 }
@@ -502,7 +502,7 @@ static inline int num_node_state(enum node_states state)
 
 #endif
 
-static inline int node_random(const nodemask_t *maskp)
+static __always_inline int node_random(const nodemask_t *maskp)
 {
 #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1)
 	int w, bit;

include/uapi/linux/bits.h

@@ -12,4 +12,7 @@
         (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
          (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
+#define __GENMASK_U128(h, l) \
+	((_BIT128((h)) << 1) - (_BIT128(l)))
+
 #endif /* _UAPI_LINUX_BITS_H */

include/uapi/linux/const.h

@@ -28,6 +28,23 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __BIT128() would not work in the asm code, as it shifts an
+ * 'unsigned __init128' data type as direct representation of
+ * 128 bit constants is not supported in the gcc compiler, as
+ * they get silently truncated.
+ *
+ * TODO: Please revisit this implementation when gcc compiler
+ * starts representing 128 bit constants directly like long
+ * and unsigned long etc. Subsequently drop the comment for
+ * GENMASK_U128() which would then start supporting asm code.
+ */
+#define _BIT128(x)	((unsigned __int128)(1) << (x))
+#endif
+
 #define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
 #define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))