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

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/intel/iavf/iavf_ethtool.c
  3a0b5a2929fd ("iavf: Introduce new state machines for flow director")
  95260816b489 ("iavf: use iavf_schedule_aq_request() helper")
https://lore.kernel.org/all/84e12519-04dc-bd80-bc34-8cf50d7898ce@intel.com/

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  c13e268c0768 ("bnxt_en: Fix HWTSTAMP_FILTER_ALL packet timestamp logic")
  c2f8063309da ("bnxt_en: Refactor RX VLAN acceleration logic.")
  a7445d69809f ("bnxt_en: Add support for new RX and TPA_START completion types for P7")
  1c7fd6ee2fe4 ("bnxt_en: Rename some macros for the P5 chips")
https://lore.kernel.org/all/20231211110022.27926ad9@canb.auug.org.au/

drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
  bd6781c18cb5 ("bnxt_en: Fix wrong return value check in bnxt_close_nic()")
  84793a499578 ("bnxt_en: Skip nic close/open when configuring tstamp filters")
https://lore.kernel.org/all/20231214113041.3a0c003c@canb.auug.org.au/

drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
  3d7a3f2612d7 ("net/mlx5: Nack sync reset request when HotPlug is enabled")
  cecf44ea1a1f ("net/mlx5: Allow sync reset flow when BF MGT interface device is present")
https://lore.kernel.org/all/20231211110328.76c925af@canb.auug.org.au/

No adjacent changes.

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

10 files changed, 103 insertions, 41 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 89971a894b60..57cd378c73d6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1201,13 +1201,6 @@ config ANON_VMA_NAME
 	  area from being merged with adjacent virtual memory areas due to the
 	  difference in their name.
 
-config USERFAULTFD
-	bool "Enable userfaultfd() system call"
-	depends on MMU
-	help
-	  Enable the userfaultfd() system call that allows to intercept and
-	  handle page faults in userland.
-
 config HAVE_ARCH_USERFAULTFD_WP
 	bool
 	help
@@ -1218,6 +1211,14 @@ config HAVE_ARCH_USERFAULTFD_MINOR
 	help
 	  Arch has userfaultfd minor fault support
 
+menuconfig USERFAULTFD
+	bool "Enable userfaultfd() system call"
+	depends on MMU
+	help
+	  Enable the userfaultfd() system call that allows to intercept and
+	  handle page faults in userland.
+
+if USERFAULTFD
 config PTE_MARKER_UFFD_WP
 	bool "Userfaultfd write protection support for shmem/hugetlbfs"
 	default y
@@ -1227,6 +1228,7 @@ config PTE_MARKER_UFFD_WP
 	  Allows to create marker PTEs for userfaultfd write protection
 	  purposes.  It is required to enable userfaultfd write protection on
 	  file-backed memory types like shmem and hugetlbfs.
+endif # USERFAULTFD
 
 # multi-gen LRU {
 config LRU_GEN
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 6262d55904e7..ce1562783e7e 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1225,6 +1225,7 @@ static void damon_split_region_at(struct damon_target *t,
 	new->age = r->age;
 	new->last_nr_accesses = r->last_nr_accesses;
 	new->nr_accesses_bp = r->nr_accesses_bp;
+	new->nr_accesses = r->nr_accesses;
 
 	damon_insert_region(new, r, damon_next_region(r), t);
 }
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index be667236b8e6..fe0fe2562000 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -139,6 +139,13 @@ static const struct kobj_type damon_sysfs_scheme_region_ktype = {
  * damon_sysfs_before_damos_apply() understands the situation by showing the
  * 'finished' status and do nothing.
  *
+ * If DAMOS is not applied to any region due to any reasons including the
+ * access pattern, the watermarks, the quotas, and the filters,
+ * ->before_damos_apply() will not be called back.  Until the situation is
+ * changed, the update will not be finished.  To avoid this,
+ * damon_sysfs_after_sampling() set the status as 'finished' if more than two
+ * apply intervals of the scheme is passed while the state is 'idle'.
+ *
  *  Finally, the tried regions request handling finisher function
  *  (damon_sysfs_schemes_update_regions_stop()) unregisters the callbacks.
  */
@@ -154,6 +161,7 @@ struct damon_sysfs_scheme_regions {
 	int nr_regions;
 	unsigned long total_bytes;
 	enum damos_sysfs_regions_upd_status upd_status;
+	unsigned long upd_timeout_jiffies;
 };
 
 static struct damon_sysfs_scheme_regions *
@@ -1854,7 +1862,9 @@ static int damon_sysfs_after_sampling(struct damon_ctx *ctx)
 	for (i = 0; i < sysfs_schemes->nr; i++) {
 		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
 		if (sysfs_regions->upd_status ==
-				DAMOS_TRIED_REGIONS_UPD_STARTED)
+				DAMOS_TRIED_REGIONS_UPD_STARTED ||
+				time_after(jiffies,
+					sysfs_regions->upd_timeout_jiffies))
 			sysfs_regions->upd_status =
 				DAMOS_TRIED_REGIONS_UPD_FINISHED;
 	}
@@ -1885,14 +1895,41 @@ int damon_sysfs_schemes_clear_regions(
 	return 0;
 }
 
+static struct damos *damos_sysfs_nth_scheme(int n, struct damon_ctx *ctx)
+{
+	struct damos *scheme;
+	int i = 0;
+
+	damon_for_each_scheme(scheme, ctx) {
+		if (i == n)
+			return scheme;
+		i++;
+	}
+	return NULL;
+}
+
 static void damos_tried_regions_init_upd_status(
-		struct damon_sysfs_schemes *sysfs_schemes)
+		struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx)
 {
 	int i;
+	struct damos *scheme;
+	struct damon_sysfs_scheme_regions *sysfs_regions;
 
-	for (i = 0; i < sysfs_schemes->nr; i++)
-		sysfs_schemes->schemes_arr[i]->tried_regions->upd_status =
-			DAMOS_TRIED_REGIONS_UPD_IDLE;
+	for (i = 0; i < sysfs_schemes->nr; i++) {
+		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
+		scheme = damos_sysfs_nth_scheme(i, ctx);
+		if (!scheme) {
+			sysfs_regions->upd_status =
+				DAMOS_TRIED_REGIONS_UPD_FINISHED;
+			continue;
+		}
+		sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE;
+		sysfs_regions->upd_timeout_jiffies = jiffies +
+			2 * usecs_to_jiffies(scheme->apply_interval_us ?
+					scheme->apply_interval_us :
+					ctx->attrs.sample_interval);
+	}
 }
 
 /* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */
@@ -1902,7 +1939,7 @@ int damon_sysfs_schemes_update_regions_start(
 {
 	damon_sysfs_schemes_clear_regions(sysfs_schemes, ctx);
 	damon_sysfs_schemes_for_damos_callback = sysfs_schemes;
-	damos_tried_regions_init_upd_status(sysfs_schemes);
+	damos_tried_regions_init_upd_status(sysfs_schemes, ctx);
 	damos_regions_upd_total_bytes_only = total_bytes_only;
 	ctx->callback.before_damos_apply = damon_sysfs_before_damos_apply;
 	ctx->callback.after_sampling = damon_sysfs_after_sampling;
diff --git a/mm/filemap.c b/mm/filemap.c
index 32eedf3afd45..f1c8c278310f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3371,7 +3371,7 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
 		}
 	}
 
-	if (pmd_none(*vmf->pmd))
+	if (pmd_none(*vmf->pmd) && vmf->prealloc_pte)
 		pmd_install(mm, vmf->pmd, &vmf->prealloc_pte);
 
 	return false;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1169ef2f2176..6feb3e0630d1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1182,6 +1182,13 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 	return (get_vma_private_data(vma) & flag) != 0;
 }
 
+bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return !(vma->vm_flags & VM_MAYSHARE) &&
+		get_vma_private_data(vma) & ~HPAGE_RESV_MASK &&
+		is_vma_resv_set(vma, HPAGE_RESV_OWNER);
+}
+
 void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 1eacca03bedd..5501363d6b31 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -642,32 +642,16 @@ static struct kmemleak_object *__alloc_object(gfp_t gfp)
 	if (!object) {
 		pr_warn("Cannot allocate a kmemleak_object structure\n");
 		kmemleak_disable();
+		return NULL;
 	}
 
-	return object;
-}
-
-static int __link_object(struct kmemleak_object *object, unsigned long ptr,
-			 size_t size, int min_count, bool is_phys)
-{
-
-	struct kmemleak_object *parent;
-	struct rb_node **link, *rb_parent;
-	unsigned long untagged_ptr;
-	unsigned long untagged_objp;
-
 	INIT_LIST_HEAD(&object->object_list);
 	INIT_LIST_HEAD(&object->gray_list);
 	INIT_HLIST_HEAD(&object->area_list);
 	raw_spin_lock_init(&object->lock);
 	atomic_set(&object->use_count, 1);
-	object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0);
-	object->pointer = ptr;
-	object->size = kfence_ksize((void *)ptr) ?: size;
 	object->excess_ref = 0;
-	object->min_count = min_count;
 	object->count = 0;			/* white color initially */
-	object->jiffies = jiffies;
 	object->checksum = 0;
 	object->del_state = 0;
 
@@ -692,6 +676,24 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
 	/* kernel backtrace */
 	object->trace_handle = set_track_prepare();
 
+	return object;
+}
+
+static int __link_object(struct kmemleak_object *object, unsigned long ptr,
+			 size_t size, int min_count, bool is_phys)
+{
+
+	struct kmemleak_object *parent;
+	struct rb_node **link, *rb_parent;
+	unsigned long untagged_ptr;
+	unsigned long untagged_objp;
+
+	object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0);
+	object->pointer = ptr;
+	object->size = kfence_ksize((void *)ptr) ?: size;
+	object->min_count = min_count;
+	object->jiffies = jiffies;
+
 	untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr);
 	/*
 	 * Only update min_addr and max_addr with object
@@ -1150,6 +1152,7 @@ EXPORT_SYMBOL_GPL(kmemleak_free_percpu);
 void __ref kmemleak_update_trace(const void *ptr)
 {
 	struct kmemleak_object *object;
+	depot_stack_handle_t trace_handle;
 	unsigned long flags;
 
 	pr_debug("%s(0x%px)\n", __func__, ptr);
@@ -1166,8 +1169,9 @@ void __ref kmemleak_update_trace(const void *ptr)
 		return;
 	}
 
+	trace_handle = set_track_prepare();
 	raw_spin_lock_irqsave(&object->lock, flags);
-	object->trace_handle = set_track_prepare();
+	object->trace_handle = trace_handle;
 	raw_spin_unlock_irqrestore(&object->lock, flags);
 
 	put_object(object);
diff --git a/mm/madvise.c b/mm/madvise.c
index cf4d694280e9..6214a1ab5654 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -335,6 +335,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 	struct folio *folio = NULL;
 	LIST_HEAD(folio_list);
 	bool pageout_anon_only_filter;
+	unsigned int batch_count = 0;
 
 	if (fatal_signal_pending(current))
 		return -EINTR;
@@ -416,6 +417,7 @@ huge_unlock:
 regular_folio:
 #endif
 	tlb_change_page_size(tlb, PAGE_SIZE);
+restart:
 	start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (!start_pte)
 		return 0;
@@ -424,6 +426,15 @@ regular_folio:
 	for (; addr < end; pte++, addr += PAGE_SIZE) {
 		ptent = ptep_get(pte);
 
+		if (++batch_count == SWAP_CLUSTER_MAX) {
+			batch_count = 0;
+			if (need_resched()) {
+				pte_unmap_unlock(start_pte, ptl);
+				cond_resched();
+				goto restart;
+			}
+		}
+
 		if (pte_none(ptent))
 			continue;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1c1061df9cd1..b226090fd906 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3166,6 +3166,7 @@ __always_inline struct obj_cgroup *current_obj_cgroup(void)
 	return NULL;
 
 from_memcg:
+	objcg = NULL;
 	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
 		/*
 		 * Memcg pointer is protected by scope (see set_active_memcg())
@@ -3176,7 +3177,6 @@ from_memcg:
 		objcg = rcu_dereference_check(memcg->objcg, 1);
 		if (likely(objcg))
 			break;
-		objcg = NULL;
 	}
 
 	return objcg;
diff --git a/mm/memory.c b/mm/memory.c
index 1f18ed4a5497..5c757fba8858 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1517,6 +1517,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				continue;
 		} else {
 			/* We should have covered all the swap entry types */
+			pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
 			WARN_ON_ONCE(1);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ab41a511e20a..7a5fc89a8652 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1129,6 +1129,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
 	kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
 }
 
+/*
+ * Must be called with mem_hotplug_lock in write mode.
+ */
 int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 		       struct zone *zone, struct memory_group *group)
 {
@@ -1149,7 +1152,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 			 !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION)))
 		return -EINVAL;
 
-	mem_hotplug_begin();
 
 	/* associate pfn range with the zone */
 	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
@@ -1208,7 +1210,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_ONLINE, &arg);
-	mem_hotplug_done();
 	return 0;
 
 failed_addition:
@@ -1217,7 +1218,6 @@ failed_addition:
 		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
 	memory_notify(MEM_CANCEL_ONLINE, &arg);
 	remove_pfn_range_from_zone(zone, pfn, nr_pages);
-	mem_hotplug_done();
 	return ret;
 }
 
@@ -1458,7 +1458,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	/* create memory block devices after memory was added */
 	ret = create_memory_block_devices(start, size, params.altmap, group);
 	if (ret) {
-		arch_remove_memory(start, size, NULL);
+		arch_remove_memory(start, size, params.altmap);
 		goto error_free;
 	}
 
@@ -1863,6 +1863,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn,
 	return 0;
 }
 
+/*
+ * Must be called with mem_hotplug_lock in write mode.
+ */
 int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group)
 {
@@ -1885,8 +1888,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			 !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION)))
 		return -EINVAL;
 
-	mem_hotplug_begin();
-
 	/*
 	 * Don't allow to offline memory blocks that contain holes.
 	 * Consequently, memory blocks with holes can never get onlined
@@ -2031,7 +2032,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 	memory_notify(MEM_OFFLINE, &arg);
 	remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
-	mem_hotplug_done();
 	return 0;
 
 failed_removal_isolated:
@@ -2046,7 +2046,6 @@ failed_removal:
 		 (unsigned long long) start_pfn << PAGE_SHIFT,
 		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1,
 		 reason);
-	mem_hotplug_done();
 	return ret;
 }