Merge branch 'linus' into timers/core

To update with the latest fixes.

38 files changed, 315 insertions, 165 deletions

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/blkdev.h b/include/linux/blkdev.h
index e85ec73a07d5..b7664d593486 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1296,12 +1296,7 @@ bdev_max_secure_erase_sectors(struct block_device *bdev)
 
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return q->limits.max_write_zeroes_sectors;
-
-	return 0;
+	return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors;
 }
 
 static inline bool bdev_nonrot(struct block_device *bdev)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index fb3c3e7181e6..ce91d9b2acb9 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -390,14 +390,6 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 	__ret;								       \
 })
 
-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen)			       \
-({									       \
-	int __ret = 0;							       \
-	if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT))			       \
-		copy_from_sockptr(&__ret, optlen, sizeof(int));		       \
-	__ret;								       \
-})
-
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen,   \
 				       max_optlen, retval)		       \
 ({									       \
@@ -518,7 +510,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })
-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
 				       optlen, max_optlen, retval) ({ retval; })
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6503c85b10a3..7b776dae36e5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -856,8 +856,8 @@ 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/context_tracking.h b/include/linux/context_tracking.h
index 6e76b9dba00e..8a78fabeafc3 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -80,10 +80,12 @@ static __always_inline bool context_tracking_guest_enter(void)
 	return context_tracking_enabled_this_cpu();
 }
 
-static __always_inline void context_tracking_guest_exit(void)
+static __always_inline bool context_tracking_guest_exit(void)
 {
 	if (context_tracking_enabled())
 		__ct_user_exit(CONTEXT_GUEST);
+
+	return context_tracking_enabled_this_cpu();
 }
 
 #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
@@ -98,7 +100,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline int ct_state(void) { return -1; }
 static inline int __ct_state(void) { return -1; }
 static __always_inline bool context_tracking_guest_enter(void) { return false; }
-static __always_inline void context_tracking_guest_exit(void) { }
+static __always_inline bool context_tracking_guest_exit(void) { return false; }
 #define CT_WARN_ON(cond) do { } while (0)
 #endif /* !CONFIG_CONTEXT_TRACKING_USER */
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 51ba681b915a..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,
@@ -148,6 +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 801a7e524113..53158de44b83 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -1037,7 +1037,7 @@ void init_cpu_online(const struct cpumask *src);
 	assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
 #define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
-#define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_possible_mask, (enabled))
+#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))
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index dca2969015d8..6fbfbde68a37 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -5,6 +5,8 @@
 #ifndef _NET_DSA_TAG_OCELOT_H
 #define _NET_DSA_TAG_OCELOT_H
 
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/kthread.h>
 #include <linux/packing.h>
 #include <linux/skbuff.h>
@@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb)
 	return rew_op;
 }
 
+/**
+ * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame
+ * @skb: Pointer to socket buffer
+ * @br: Pointer to bridge device that the port is under, if any
+ * @vlan_tci:
+ * @tag_type:
+ *
+ * If the port is under a VLAN-aware bridge, remove the VLAN header from the
+ * payload and move it into the DSA tag, which will make the switch classify
+ * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
+ * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not
+ * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()).
+ * Anyway, VID 0 is fine because it is stripped on egress for these port modes,
+ * and source address learning is not performed for packets injected from the
+ * CPU anyway, so it doesn't matter that the VID is "wrong".
+ */
+static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb,
+					     struct net_device *br,
+					     u64 *vlan_tci, u64 *tag_type)
+{
+	struct vlan_ethhdr *hdr;
+	u16 proto, tci;
+
+	if (!br || !br_vlan_enabled(br)) {
+		*vlan_tci = 0;
+		*tag_type = IFH_TAG_TYPE_C;
+		return;
+	}
+
+	hdr = (struct vlan_ethhdr *)skb_mac_header(skb);
+	br_vlan_get_proto(br, &proto);
+
+	if (ntohs(hdr->h_vlan_proto) == proto) {
+		vlan_remove_tag(skb, &tci);
+		*vlan_tci = tci;
+	} else {
+		rcu_read_lock();
+		br_vlan_get_pvid_rcu(br, &tci);
+		rcu_read_unlock();
+		*vlan_tci = tci;
+	}
+
+	*tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
+}
+
 #endif
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/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h
index 1dc5b3b50aa9..3387897bf368 100644
--- a/include/linux/firmware/qcom/qcom_qseecom.h
+++ b/include/linux/firmware/qcom/qcom_qseecom.h
@@ -26,51 +26,6 @@ struct qseecom_client {
 };
 
 /**
- * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client.
- * @client: The QSEECOM client device.
- *
- * Returns the SCM device under which the provided QSEECOM client device
- * operates. This function is intended to be used for DMA allocations.
- */
-static inline struct device *qseecom_scm_dev(struct qseecom_client *client)
-{
-	return client->aux_dev.dev.parent->parent;
-}
-
-/**
- * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client.
- * @client:     The QSEECOM client to allocate the memory for.
- * @size:       The number of bytes to allocate.
- * @dma_handle: Pointer to where the DMA address should be stored.
- * @gfp:        Allocation flags.
- *
- * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for
- * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details.
- */
-static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size,
-				      dma_addr_t *dma_handle, gfp_t gfp)
-{
-	return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp);
-}
-
-/**
- * dma_free_coherent() - Free QSEECOM DMA memory.
- * @client:     The QSEECOM client for which the memory has been allocated.
- * @size:       The number of bytes allocated.
- * @cpu_addr:   Virtual memory address to free.
- * @dma_handle: DMA memory address to free.
- *
- * Wrapper function for dma_free_coherent(), freeing memory previously
- * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for
- * details.
- */
-static inline void qseecom_dma_free(struct qseecom_client *client, size_t size,
-				    void *cpu_addr, dma_addr_t dma_handle)
-{
-	return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle);
-}
-
-/**
  * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app.
  * @client:   The QSEECOM client associated with the target app.
  * @req:      Request buffer sent to the app (must be TZ memory).
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fd34b5755c0b..6ca11e241a24 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -210,6 +210,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
 #define ATTR_TIMES_SET	(1 << 16)
 #define ATTR_TOUCH	(1 << 17)
+#define ATTR_DELEG	(1 << 18) /* Delegated attrs. Don't break write delegations */
 
 /*
  * Whiteout is represented by a char device.  The following constants define the
@@ -2392,6 +2393,9 @@ 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 +2419,8 @@ 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/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/iommu.h b/include/linux/iommu.h
index 4d47f2c33311..bd722f473635 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,
@@ -1565,7 +1563,7 @@ struct iopf_queue *iopf_queue_alloc(const char *name);
 void iopf_queue_free(struct iopf_queue *queue);
 int iopf_queue_discard_partial(struct iopf_queue *queue);
 void iopf_free_group(struct iopf_group *group);
-void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt);
+int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt);
 void iopf_group_response(struct iopf_group *group,
 			 enum iommu_page_response_code status);
 #else
@@ -1603,9 +1601,10 @@ static inline void iopf_free_group(struct iopf_group *group)
 {
 }
 
-static inline void
+static inline int
 iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
 {
+	return -ENODEV;
 }
 
 static inline void iopf_group_response(struct iopf_group *group,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 689e8be873a7..0d5125a3e31a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -485,7 +485,15 @@ static __always_inline void guest_state_enter_irqoff(void)
  */
 static __always_inline void guest_context_exit_irqoff(void)
 {
-	context_tracking_guest_exit();
+	/*
+	 * Guest mode is treated as a quiescent state, see
+	 * guest_context_enter_irqoff() for more details.
+	 */
+	if (!context_tracking_guest_exit()) {
+		instrumentation_begin();
+		rcu_virt_note_context_switch();
+		instrumentation_end();
+	}
 }
 
 /*
@@ -715,6 +723,13 @@ 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 +2429,7 @@ 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 +2460,11 @@ 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 +2491,9 @@ 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/minmax.h b/include/linux/minmax.h
index 9c2848abc804..98008dd92153 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -26,19 +26,63 @@
 #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 >
@@ -51,34 +95,31 @@
 #define __cmp_once(op, type, x, y) \
 	__cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
 
-#define __careful_cmp_once(op, x, y) ({			\
-	static_assert(__types_ok(x, y),			\
-		#op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \
-	__cmp_once(op, __auto_type, x, y); })
+#define __careful_cmp_once(op, x, y, ux, uy) ({		\
+	__auto_type ux = (x); __auto_type uy = (y);	\
+	BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy),	\
+		#op"("#x", "#y") signedness error");	\
+	__cmp(op, ux, uy); })
 
-#define __careful_cmp(op, x, y)					\
-	__builtin_choose_expr(__is_constexpr((x) - (y)),	\
-		__cmp(op, x, y), __careful_cmp_once(op, x, y))
+#define __careful_cmp(op, x, y) \
+	__careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
 
 #define __clamp(val, lo, hi)	\
 	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
 
-#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({		\
-	typeof(val) unique_val = (val);						\
-	typeof(lo) unique_lo = (lo);						\
-	typeof(hi) unique_hi = (hi);						\
+#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({				\
+	__auto_type uval = (val);						\
+	__auto_type ulo = (lo);							\
+	__auto_type uhi = (hi);							\
 	static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), 	\
 			(lo) <= (hi), true),					\
 		"clamp() low limit " #lo " greater than high limit " #hi);	\
-	static_assert(__types_ok(val, lo), "clamp() 'lo' signedness error");	\
-	static_assert(__types_ok(val, hi), "clamp() 'hi' signedness error");	\