[rocky9_5] History rebuild to kernel-5.14.0-503.35.1.el9_5

Makefile.rhelver

@@ -12,7 +12,7 @@ RHEL_MINOR = 5
 #
 # Use this spot to avoid future merge conflicts.
 # Do not trim this comment.
-RHEL_RELEASE = 503.29.1
+RHEL_RELEASE = 503.35.1
 
 #
 # ZSTREAM

arch/arm64/kernel/cacheinfo.c

@@ -101,16 +101,18 @@ int populate_cache_leaves(unsigned int cpu)
 	unsigned int level, idx;
 	enum cache_type type;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	struct cacheinfo *infos = this_cpu_ci->info_list;
 
 	for (idx = 0, level = 1; level <= this_cpu_ci->num_levels &&
-	     idx < this_cpu_ci->num_leaves; idx++, level++) {
+	     idx < this_cpu_ci->num_leaves; level++) {
 		type = get_cache_type(level);
 		if (type == CACHE_TYPE_SEPARATE) {
-			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
-			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
+			if (idx + 1 >= this_cpu_ci->num_leaves)
+				break;
+			ci_leaf_init(&infos[idx++], CACHE_TYPE_DATA, level);
+			ci_leaf_init(&infos[idx++], CACHE_TYPE_INST, level);
 		} else {
-			ci_leaf_init(this_leaf++, type, level);
+			ci_leaf_init(&infos[idx++], type, level);
 		}
 	}
 	return 0;

arch/x86/include/asm/page_64.h

@@ -17,6 +17,7 @@ extern unsigned long phys_base;
 extern unsigned long page_offset_base;
 extern unsigned long vmalloc_base;
 extern unsigned long vmemmap_base;
+extern unsigned long physmem_end;
 
 static __always_inline unsigned long __phys_addr_nodebug(unsigned long x)
 {

arch/x86/include/asm/pgtable_64_types.h

@@ -140,6 +140,10 @@ extern unsigned int ptrs_per_p4d;
 # define VMEMMAP_START		__VMEMMAP_BASE_L4
 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
 
+#ifdef CONFIG_RANDOMIZE_MEMORY
+# define PHYSMEM_END		physmem_end
+#endif
+
 /*
  * End of the region for which vmalloc page tables are pre-allocated.
  * For non-KMSAN builds, this is the same as VMALLOC_END.

arch/x86/kernel/machine_kexec_64.c

@@ -28,6 +28,7 @@
 #include <asm/setup.h>
 #include <asm/set_memory.h>
 #include <asm/cpu.h>
+#include <asm/efi.h>
 
 #ifdef CONFIG_ACPI
 /*
@@ -90,6 +91,8 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
 {
 #ifdef CONFIG_EFI
 	unsigned long mstart, mend;
+	void *kaddr;
+	int ret;
 
 	if (!efi_enabled(EFI_BOOT))
 		return 0;
@@ -105,6 +108,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
 	if (!mstart)
 		return 0;
 
+	ret = kernel_ident_mapping_init(info, level4p, mstart, mend);
+	if (ret)
+		return ret;
+
+	kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB);
+	if (!kaddr) {
+		pr_err("Could not map UEFI system table\n");
+		return -ENOMEM;
+	}
+
+	mstart = efi_config_table;
+
+	if (efi_enabled(EFI_64BIT)) {
+		efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr;
+
+		mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables;
+	} else {
+		efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr;
+
+		mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables;
+	}
+
+	memunmap(kaddr);
+
 	return kernel_ident_mapping_init(info, level4p, mstart, mend);
 #endif
 	return 0;

arch/x86/mm/ident_map.c

@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		if (info->direct_gbpages) {
-			pud_t pudval;
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_leaf(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
 
-			if (pud_present(*pud))
-				continue;
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the begining: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
+			pud_t pudval;
 
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;

arch/x86/mm/init_64.c

@@ -950,8 +950,12 @@ static void update_end_of_memory_vars(u64 start, u64 size)
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	      struct mhp_params *params)
 {
+	unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1;
 	int ret;
 
+	if (WARN_ON_ONCE(end > PHYSMEM_END))
+		return -ERANGE;
+
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	WARN_ON_ONCE(ret);
 

arch/x86/mm/kaslr.c

@@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
  */
 static __initdata struct kaslr_memory_region {
 	unsigned long *base;
+	unsigned long *end;
 	unsigned long size_tb;
 } kaslr_regions[] = {
-	{ &page_offset_base, 0 },
-	{ &vmalloc_base, 0 },
-	{ &vmemmap_base, 0 },
+	{
+		.base	= &page_offset_base,
+		.end	= &physmem_end,
+	},
+	{
+		.base	= &vmalloc_base,
+	},
+	{
+		.base	= &vmemmap_base,
+	},
 };
 
+/* The end of the possible address space for physical memory */
+unsigned long physmem_end __ro_after_init;
+
 /* Get size in bytes used by the memory region */
 static inline unsigned long get_padding(struct kaslr_memory_region *region)
 {
@@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void)
 	BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
 	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
 
+	/* Preset the end of the possible address space for physical memory */
+	physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1);
 	if (!kaslr_memory_enabled())
 		return;
 
@@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void)
 		vaddr += entropy;
 		*kaslr_regions[i].base = vaddr;
 
+		/* Calculate the end of the region */
+		vaddr += get_padding(&kaslr_regions[i]);
 		/*
-		 * Jump the region and add a minimum padding based on
-		 * randomization alignment.
+		 * KASLR trims the maximum possible size of the
+		 * direct-map. Update the physmem_end boundary.
+		 * No rounding required as the region starts
+		 * PUD aligned and size is in units of TB.
 		 */
-		vaddr += get_padding(&kaslr_regions[i]);
+		if (kaslr_regions[i].end)
+			*kaslr_regions[i].end = __pa_nodebug(vaddr - 1);
+
+		/* Add a minimum padding based on randomization alignment. */
 		vaddr = round_up(vaddr + 1, PUD_SIZE);
 		remain_entropy -= entropy;
 	}

arch/x86/pci/mmconfig-shared.c

@@ -518,7 +518,34 @@ static bool __ref pci_mmcfg_reserved(struct device *dev,
 {
 	struct resource *conflict;
 
-	if (!early && !acpi_disabled) {
+	if (early) {
+
+		/*
+		 * Don't try to do this check unless configuration type 1
+		 * is available.  How about type 2?
+		 */
+
+		/*
+		 * 946f2ee5c731 ("Check that MCFG points to an e820
+		 * reserved area") added this E820 check in 2006 to work
+		 * around BIOS defects.
+		 *
+		 * Per PCI Firmware r3.3, sec 4.1.2, ECAM space must be
+		 * reserved by a PNP0C02 resource, but it need not be
+		 * mentioned in E820.  Before the ACPI interpreter is
+		 * available, we can't check for PNP0C02 resources, so
+		 * there's no reliable way to verify the region in this
+		 * early check.  Keep it only for the old machines that
+		 * motivated 946f2ee5c731.
+		 */
+		if (dmi_get_bios_year() < 2016 && raw_pci_ops)
+			return is_mmconf_reserved(e820__mapped_all, cfg, dev,
+						  "E820 entry");
+
+		return true;
+	}
+
+	if (!acpi_disabled) {
 		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
 				       "ACPI motherboard resource"))
 			return true;
@@ -551,16 +578,7 @@ static bool __ref pci_mmcfg_reserved(struct device *dev,
 	 * For MCFG information constructed from hotpluggable host bridge's
 	 * _CBA method, just assume it's reserved.
 	 */
-	if (pci_mmcfg_running_state)
-		return true;
-
-	/* Don't try to do this check unless configuration
-	   type 1 is available. how about type 2 ?*/
-	if (raw_pci_ops)
-		return is_mmconf_reserved(e820__mapped_all, cfg, dev,
-					  "E820 entry");
-
-	return false;
+	return pci_mmcfg_running_state;
 }
 
 static void __init pci_mmcfg_reject_broken(int early)

block/blk-mq-tag.c

@@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,
 void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
 	unsigned int users;
+	unsigned long flags;
 	struct blk_mq_tags *tags = hctx->tags;
 
 	/*
@@ -56,11 +57,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 			return;
 	}
 
-	spin_lock_irq(&tags->lock);
+	spin_lock_irqsave(&tags->lock, flags);
 	users = tags->active_queues + 1;
 	WRITE_ONCE(tags->active_queues, users);
 	blk_mq_update_wake_batch(tags, users);
-	spin_unlock_irq(&tags->lock);
+	spin_unlock_irqrestore(&tags->lock, flags);
 }
 
 /*

ciq/ciq_backports/kernel-5.14.0-503.31.1.el9_5/0840556e.failed

@@ -0,0 +1,86 @@
+net: Protect dev->name by seqlock.
+
+jira LE-2742
+Rebuild_History Non-Buildable kernel-5.14.0-503.31.1.el9_5
+commit-author Kuniyuki Iwashima <kuniyu@amazon.com>
+commit 0840556e5a3a331b6932ef17dd4bc94445df3297
+Empty-Commit: Cherry-Pick Conflicts during history rebuild.
+Will be included in final tarball splat. Ref for failed cherry-pick at:
+ciq/ciq_backports/kernel-5.14.0-503.31.1.el9_5/0840556e.failed
+
+We will convert ioctl(SIOCGARP) to RCU, and then we need to copy
+dev->name which is currently protected by rtnl_lock().
+
+This patch does the following:
+
+  1) Add seqlock netdev_rename_lock to protect dev->name
+
+  2) Add netdev_copy_name() that copies dev->name to buffer
+     under netdev_rename_lock
+
+  3) Use netdev_copy_name() in netdev_get_name() and drop
+     devnet_rename_sem
+
+	Suggested-by: Eric Dumazet <edumazet@google.com>
+Link: https://lore.kernel.org/netdev/CANn89iJEWs7AYSJqGCUABeVqOCTkErponfZdT5kV-iD=-SajnQ@mail.gmail.com/
+	Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
+Link: https://lore.kernel.org/r/20240430015813.71143-7-kuniyu@amazon.com
+	Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+(cherry picked from commit 0840556e5a3a331b6932ef17dd4bc94445df3297)
+	Signed-off-by: Jonathan Maple <jmaple@ciq.com>
+
+# Conflicts:
+#	net/core/dev.c
+diff --cc net/core/dev.c
+index a4af81272b39,e02d2363347e..000000000000
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@@ -1241,9 -1270,11 +1254,11 @@@ rollback
+  		if (err >= 0) {
+  			err = ret;
+  			down_write(&devnet_rename_sem);
++ 			write_seqlock(&netdev_rename_lock);
+  			memcpy(dev->name, oldname, IFNAMSIZ);
++ 			write_sequnlock(&netdev_rename_lock);
+  			memcpy(oldname, newname, IFNAMSIZ);
+ -			WRITE_ONCE(dev->name_assign_type, old_assign_type);
+ +			dev->name_assign_type = old_assign_type;
+  			old_assign_type = NET_NAME_RENAMED;
+  			goto rollback;
+  		} else {
+@@@ -11075,6 -11418,19 +11090,22 @@@ int __dev_change_net_namespace(struct n
+  	dev_net_set(dev, net);
+  	dev->ifindex = new_ifindex;
+
+++<<<<<<< HEAD
+++=======
++ 	if (new_name[0]) {
++ 		/* Rename the netdev to prepared name */
++ 		write_seqlock(&netdev_rename_lock);
++ 		strscpy(dev->name, new_name, IFNAMSIZ);
++ 		write_sequnlock(&netdev_rename_lock);
++ 	}
++ 
++ 	/* Fixup kobjects */
++ 	dev_set_uevent_suppress(&dev->dev, 1);
++ 	err = device_rename(&dev->dev, dev->name);
++ 	dev_set_uevent_suppress(&dev->dev, 0);
++ 	WARN_ON(err);
++ 
+++>>>>>>> 0840556e5a3a (net: Protect dev->name by seqlock.)
+  	/* Send a netdev-add uevent to the new namespace */
+  	kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
+  	netdev_adjacent_add_links(dev);
+diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
+index 46c83f63545d..de505c2ad012 100644
+--- a/include/linux/netdevice.h
++++ b/include/linux/netdevice.h
+@@ -3192,6 +3192,7 @@ struct net_device *netdev_get_by_name(struct net *net, const char *name,
+ 				      netdevice_tracker *tracker, gfp_t gfp);
+ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
+ struct net_device *dev_get_by_napi_id(unsigned int napi_id);
++void netdev_copy_name(struct net_device *dev, char *name);
+
+ static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
+ 				  unsigned short type,
+* Unmerged path net/core/dev.c