Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Cross-merge bpf fixes after downstream PR including
important fixes (from bpf-next point of view):
commit 41c24102af7b ("selftests/bpf: Filter out _GNU_SOURCE when compiling test_cpp")
commit fdad456cbcca ("bpf: Fix updating attached freplace prog in prog_array map")

No conflicts.

Adjacent changes in:
include/linux/bpf_verifier.h
kernel/bpf/verifier.c
tools/testing/selftests/bpf/Makefile

Link: https://lore.kernel.org/bpf/20240813234307.82773-1-alexei.starovoitov@gmail.com/
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

40 files changed, 342 insertions, 214 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index f0b95c76c707..0687a442fec7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -259,6 +259,12 @@ static inline void
 acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
 #endif
 
+#ifdef CONFIG_RISCV
+void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa);
+#else
+static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { }
+#endif
+
 #ifndef PHYS_CPUID_INVALID
 typedef u32 phys_cpuid_t;
 #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1)
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 8c4768c44a01..d3b66d77df7a 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst,
 		dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits);
 }
 
+static inline void bitmap_copy_and_extend(unsigned long *to,
+					  const unsigned long *from,
+					  unsigned int count, unsigned int size)
+{
+	unsigned int copy = BITS_TO_LONGS(count);
+
+	memcpy(to, from, copy * sizeof(long));
+	if (count % BITS_PER_LONG)
+		to[copy - 1] &= BITMAP_LAST_WORD_MASK(count);
+	memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long));
+}
+
 /*
  * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
  * machines the order of hi and lo parts of numbers match the bitmap structure.
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 46d4bdc634c0..ba35bbf07798 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -47,12 +47,17 @@ extern unsigned long __sw_hweight64(__u64 w);
 	  __builtin_constant_p(*(const unsigned long *)(addr))) ?	\
 	 const##op(nr, addr) : op(nr, addr))
 
+/*
+ * The following macros are non-atomic versions of their non-underscored
+ * counterparts.
+ */
 #define __set_bit(nr, addr)		bitop(___set_bit, nr, addr)
 #define __clear_bit(nr, addr)		bitop(___clear_bit, nr, addr)
 #define __change_bit(nr, addr)		bitop(___change_bit, nr, addr)
 #define __test_and_set_bit(nr, addr)	bitop(___test_and_set_bit, nr, addr)
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
+
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
 #define test_bit_acquire(nr, addr)	bitop(_test_bit_acquire, nr, addr)
 
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 634a302a39e3..279b4a640644 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -874,8 +874,8 @@ static inline u32 type_flag(u32 type)
 /* only use after check_attach_btf_id() */
 static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
 {
-	return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ?
-		prog->aux->dst_prog->type : prog->type;
+	return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ?
+		prog->aux->saved_dst_prog_type : prog->type;
 }
 
 static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 2594553bb30b..2df665fa2964 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -297,6 +297,15 @@ static inline void *offset_to_ptr(const int *off)
 #define is_unsigned_type(type) (!is_signed_type(type))
 
 /*
+ * Useful shorthand for "is this condition known at compile-time?"
+ *
+ * Note that the condition may involve non-constant values,
+ * but the compiler may know enough about the details of the
+ * values to determine that the condition is statically true.
+ */
+#define statically_true(x) (__builtin_constant_p(x) && (x))
+
+/*
  * This is needed in functions which generate the stack canary, see
  * arch/x86/kernel/smpboot.c::start_secondary() for an example.
  */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 89f5c34ce4df..9316c39260e0 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -100,7 +100,6 @@ enum cpuhp_state {
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-	CPUHP_PROFILE_PREPARE,
 	CPUHP_X2APIC_PREPARE,
 	CPUHP_SMPCFD_PREPARE,
 	CPUHP_RELAY_PREPARE,
@@ -122,6 +121,7 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_PREPARE,
+	CPUHP_TMIGR_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,
@@ -147,6 +147,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_LOONGARCH_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
 	CPUHP_AP_IRQ_RISCV_IMSIC_STARTING,
+	CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 099e8b32dd68..53158de44b83 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -1033,53 +1033,17 @@ void init_cpu_present(const struct cpumask *src);
 void init_cpu_possible(const struct cpumask *src);
 void init_cpu_online(const struct cpumask *src);
 
-static inline void
-set_cpu_possible(unsigned int cpu, bool possible)
-{
-	if (possible)
-		cpumask_set_cpu(cpu, &__cpu_possible_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_possible_mask);
-}
+#define assign_cpu(cpu, mask, val)	\
+	assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
-static inline void
-set_cpu_enabled(unsigned int cpu, bool can_be_onlined)
-{
-	if (can_be_onlined)
-		cpumask_set_cpu(cpu, &__cpu_enabled_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_enabled_mask);
-}
-
-static inline void
-set_cpu_present(unsigned int cpu, bool present)
-{
-	if (present)
-		cpumask_set_cpu(cpu, &__cpu_present_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_present_mask);
-}
+#define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
+#define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
+#define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))
+#define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
+#define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
 
 void set_cpu_online(unsigned int cpu, bool online);
 
-static inline void
-set_cpu_active(unsigned int cpu, bool active)
-{
-	if (active)
-		cpumask_set_cpu(cpu, &__cpu_active_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_active_mask);
-}
-
-static inline void
-set_cpu_dying(unsigned int cpu, bool dying)
-{
-	if (dying)
-		cpumask_set_cpu(cpu, &__cpu_dying_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_dying_mask);
-}
-
 /**
  * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
  * @bitmap: the bitmap
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 60b25020281f..0bea1afbd747 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -21,6 +21,21 @@ struct cxl_event_record_hdr {
 	u8 reserved[15];
 } __packed;
 
+struct cxl_event_media_hdr {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	/*
+	 * The meaning of Validity Flags from bit 2 is
+	 * different across DRAM and General Media records
+	 */
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+} __packed;
+
 #define CXL_EVENT_RECORD_DATA_LENGTH 0x50
 struct cxl_event_generic {
 	struct cxl_event_record_hdr hdr;
@@ -33,14 +48,7 @@ struct cxl_event_generic {
  */
 #define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
 struct cxl_event_gen_media {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
+	struct cxl_event_media_hdr media_hdr;
 	u8 device[3];
 	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
 	u8 reserved[46];
@@ -52,14 +60,7 @@ struct cxl_event_gen_media {
  */
 #define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
 struct cxl_event_dram {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
+	struct cxl_event_media_hdr media_hdr;
 	u8 nibble_mask[3];
 	u8 bank_group;
 	u8 bank;
@@ -95,21 +96,13 @@ struct cxl_event_mem_module {
 	u8 reserved[0x3d];
 } __packed;
 
-/*
- * General Media or DRAM Event Common Fields
- * - provides common access to phys_addr
- */
-struct cxl_event_common {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-} __packed;
-
 union cxl_event {
 	struct cxl_event_generic generic;
 	struct cxl_event_gen_media gen_media;
 	struct cxl_event_dram dram;
 	struct cxl_event_mem_module mem_module;
-	struct cxl_event_common common;
+	/* dram & gen_media event header */
+	struct cxl_event_media_hdr media_hdr;
 } __packed;
 
 /*
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 303fda54ef17..989c94eddb2b 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -736,10 +736,10 @@ struct kernel_ethtool_ts_info {
  * @rxfh_key_space: same as @rxfh_indir_space, but for the key.
  * @rxfh_priv_size: size of the driver private data area the core should
  *	allocate for an RSS context (in &struct ethtool_rxfh_context).
- * @rxfh_max_context_id: maximum (exclusive) supported RSS context ID.  If this
- *	is zero then the core may choose any (nonzero) ID, otherwise the core
- *	will only use IDs strictly less than this value, as the @rss_context
- *	argument to @create_rxfh_context and friends.
+ * @rxfh_max_num_contexts: maximum (exclusive) supported RSS context ID.
+ *	If this is zero then the core may choose any (nonzero) ID, otherwise
+ *	the core will only use IDs strictly less than this value, as the
+ *	@rss_context argument to @create_rxfh_context and friends.
  * @supported_coalesce_params: supported types of interrupt coalescing.
  * @supported_ring_params: supported ring params.
  * @get_drvinfo: Report driver/device information. Modern drivers no
@@ -954,7 +954,7 @@ struct ethtool_ops {
 	u32	rxfh_indir_space;
 	u16	rxfh_key_space;
 	u16	rxfh_priv_size;
-	u32	rxfh_max_context_id;
+	u32	rxfh_max_num_contexts;
 	u32	supported_coalesce_params;
 	u32	supported_ring_params;
 	void	(*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *);
diff --git a/include/linux/file.h b/include/linux/file.h
index 237931f20739..59b146a14dca 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
  *
  * f = dentry_open(&path, O_RDONLY, current_cred());
  * if (IS_ERR(f))
- *         return PTR_ERR(fd);
+ *         return PTR_ERR(f);
  *
  * fd_install(fd, f);
  * return take_fd(fd);
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 00abe0e5d602..1cca14cf5652 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -462,9 +462,8 @@ struct fw_iso_packet {
 				/* rx: Sync bit, wait for matching sy	*/
 	u32 tag:2;		/* tx: Tag in packet header		*/
 	u32 sy:4;		/* tx: Sy in packet header		*/
-	u32 header_length:8;	/* Length of immediate header		*/
-				/* tx: Top of 1394 isoch. data_block    */
-	u32 header[] __counted_by(header_length);
+	u32 header_length:8;	/* Size of immediate header		*/
+	u32 header[];		/* tx: Top of 1394 isoch. data_block	*/
 };
 
 #define FW_ISO_CONTEXT_TRANSMIT			0
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fd34b5755c0b..fb0426f349fc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2392,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
  *
  * I_PINNING_FSCACHE_WB	Inode is pinning an fscache object for writeback.
  *
+ * I_LRU_ISOLATING	Inode is pinned being isolated from LRU without holding
+ *			i_count.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2415,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 #define I_DONTCACHE		(1 << 16)
 #define I_SYNC_QUEUED		(1 << 17)
 #define I_PINNING_NETFS_WB	(1 << 18)
+#define __I_LRU_ISOLATING	19
+#define I_LRU_ISOLATING		(1 << __I_LRU_ISOLATING)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cff002be83eb..e25d9ebfdf89 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -74,14 +74,20 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr;
 #define THP_ORDERS_ALL_ANON	((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
 
 /*
- * Mask of all large folio orders supported for file THP.
+ * Mask of all large folio orders supported for file THP. Folios in a DAX
+ * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to
+ * it.
  */
-#define THP_ORDERS_ALL_FILE	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+#define THP_ORDERS_ALL_FILE_DAX		\
+	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+#define THP_ORDERS_ALL_FILE_DEFAULT	\
+	((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0))
 
 /*
  * Mask of all large folio orders supported for THP.
  */
-#define THP_ORDERS_ALL		(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE)
+#define THP_ORDERS_ALL	\
+	(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT)
 
 #define TVA_SMAPS		(1 << 0)	/* Will be used for procfs */
 #define TVA_IN_PF		(1 << 1)	/* Page fault handler */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index c9bf68c239a0..45bf05ad5c53 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -944,10 +944,37 @@ static inline bool htlb_allow_alloc_fallback(int reason)
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
-	if (huge_page_size(h) == PMD_SIZE)
+	const unsigned long size = huge_page_size(h);
+
+	VM_WARN_ON(size == PAGE_SIZE);
+
+	/*
+	 * hugetlb must use the exact same PT locks as core-mm page table
+	 * walkers would. When modifying a PTE table, hugetlb must take the
+	 * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD
+	 * PT lock etc.
+	 *
+	 * The expectation is that any hugetlb folio smaller than a PMD is
+	 * always mapped into a single PTE table and that any hugetlb folio
+	 * smaller than a PUD (but at least as big as a PMD) is always mapped
+	 * into a single PMD table.
+	 *
+	 * If that does not hold for an architecture, then that architecture
+	 * must disable split PT locks such that all *_lockptr() functions
+	 * will give us the same result: the per-MM PT lock.
+	 *
+	 * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where
+	 * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr()
+	 * and core-mm would use pmd_lockptr(). However, in such configurations
+	 * split PMD locks are disabled -- they don't make sense on a single
+	 * PGDIR page table -- and the end result is the same.
+	 */
+	if (size >= PUD_SIZE)
+		return pud_lockptr(mm, (pud_t *) pte);
+	else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE))
 		return pmd_lockptr(mm, (pmd_t *) pte);
-	VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
-	return &mm->page_table_lock;
+	/* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */
+	return ptep_lockptr(mm, pte);
 }
 
 #ifndef hugepages_supported
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 07e33bbc9256..377def497298 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev,
 struct acpi_resource;
 struct acpi_resource_i2c_serialbus;
 
-#if IS_ENABLED(CONFIG_ACPI)
+#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C)
 bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares,
 			       struct acpi_resource_i2c_serialbus **i2c);
 int i2c_acpi_client_count(struct acpi_device *adev);
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 0ca27dd86956..074f632868d9 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -33,6 +33,7 @@ enum {
 struct i3c_master_controller;
 struct i3c_bus;
 struct i3c_device;
+extern const struct bus_type i3c_bus_type;
 
 /**
  * struct i3c_i2c_dev_desc - Common part of the I3C/I2C device descriptor
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 3bb6198d1523..3315005df117 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -404,7 +404,7 @@ struct io_ring_ctx {
 	spinlock_t		napi_lock;	/* napi_list lock */
 
 	/* napi busy poll default timeout */
-	unsigned int		napi_busy_poll_to;
+	ktime_t			napi_busy_poll_dt;
 	bool			napi_prefer_busy_poll;
 	bool			napi_enabled;
 
@@ -461,7 +461,6 @@ enum {
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
 	REQ_F_POLL_NO_LAZY_BIT,
-	REQ_F_CANCEL_SEQ_BIT,
 	REQ_F_CAN_POLL_BIT,
 	REQ_F_BL_EMPTY_BIT,
 	REQ_F_BL_NO_RECYCLE_BIT,
@@ -536,8 +535,6 @@ enum {
 	REQ_F_HASH_LOCKED	= IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT),
 	/* don't use lazy poll wake for this request */
 	REQ_F_POLL_NO_LAZY	= IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT),
-	/* cancel sequence is set and valid */
-	REQ_F_CANCEL_SEQ	= IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT),
 	/* file is pollable */
 	REQ_F_CAN_POLL		= IO_REQ_FLAG(REQ_F_CAN_POLL_BIT),
 	/* buffer list was empty after selection of buffer */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 4d47f2c33311..04cbdae0052e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -795,8 +795,6 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-				   struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 689e8be873a7..b23c6d48392f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -715,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
 }
 #endif
 
+#ifndef kvm_arch_has_readonly_mem
+static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
+{
+	return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM);
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
@@ -2414,7 +2421,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn
 }
 
 bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
-				     unsigned long attrs);
+				     unsigned long mask, unsigned long attrs);
 bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range);
 bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
@@ -2445,11 +2452,11 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_PRIVATE_MEM */
 
-#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
-bool kvm_arch_gmem_prepare_needed(struct kvm *kvm);
 #endif
 
+#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
 /**
  * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
  *
@@ -2476,8 +2483,9 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 
 long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque);
+#endif
 
-#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
 void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
 #endif
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7e2eb091049a..0e5bf25d324f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -109,6 +109,7 @@ struct mem_cgroup_per_node {
 
 	/* Fields which get updated often at the end. */
 	struct lruvec		lruvec;
+	CACHELINE_PADDING(_pad2_);
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 	struct mem_cgroup_reclaim_iter	iter;
 };
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index 2ec559284a9f..98008dd92153 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -26,56 +26,100 @@
 #define __typecheck(x, y) \
 	(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
 
-/* is_signed_type() isn't a constexpr for pointer types */
-#define __is_signed(x) 								\
-	__builtin_choose_expr(__is_constexpr(is_signed_type(typeof(x))),	\
-		is_signed_type(typeof(x)), 0)
+/*
+ * __sign_use for integer expressions:
+ *   bit #0 set if ok for unsigned comparisons
+ *   bit #1 set if ok for signed comparisons
+ *
+ * In particular, statically non-negative signed integer
+ * expressions are ok for both.
+ *
+ * NOTE! Unsigned types smaller than 'int' are implicitly
+ * converted to 'int' in expressions, and are accepted for
+ * signed conversions for now. This is debatable.
+ *
+ * Note that 'x' is the original expression, and 'ux' is
+ * the unique variable that contains the value.
+ *
+ * We use 'ux' for pure type checking, and 'x' for when
+ * we need to look at the value (but without evaluating
+ * it for side effects! Careful to only ever evaluate it
+ * with sizeof() or __builtin_constant_p() etc).
+ *
+ * Pointers end up being checked by the normal C type
+ * rules at the actual comparison, and these expressions
+ * only need to be careful to not cause warnings for
+ * pointer use.
+ */
+#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux))
+#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4))
+#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \
+	__signed_type_use(x,ux):__unsigned_type_use(x,ux))
 
-/* True for a non-negative signed int constant */
-#define __is_noneg_int(x)	\
-	(__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0)
+/*
+ * To avoid warnings about casting pointers to integers
+ * of different sizes, we need that special sign type.
+ *
+ * On 64-bit we can just always use 'long', since any
+ * integer or pointer type can just be cast to that.
+ *
+ * This does not work for 128-bit signed integers since
+ * the cast would truncate them, but we do not use s128
+ * types in the kernel (we do use 'u128', but they will
+ * be handled by the !is_signed_type() case).
+ *
+ * NOTE! The cast is there only to avoid any warnings
+ * from when values that aren't signed integer types.
+ */
+#ifdef CONFIG_64BIT
+  #define __signed_type(ux) long
+#else
+  #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L))
+#endif
+#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0)
+
+#define __types_ok(x,y,ux,uy) \
+	(__sign_use(x,ux) & __sign_use(y,uy))
 
-#define __types_ok(x, y) 					\
-	(__is_signed(x) == __is_signed(y) ||			\
-		__is_signed((x) + 0) == __is_signed((y) + 0) ||	\
-		__is_noneg_int(x) || __is_noneg_int(y))
+#define __types_ok3(x,y,z,ux,uy,uz) \
+	(__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz))
 
 #define __cmp_op_min <
 #define __cmp_op_max >
 <