Update to v6.18.38

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 18
-SUBLEVEL = 37
+SUBLEVEL = 38
 EXTRAVERSION =
 NAME = Baby Opossum Posse
 
@@ -806,12 +806,6 @@ endif # KBUILD_EXTMOD
 # Defaults to vmlinux, but the arch makefile usually adds further targets
 all: vmlinux
 
-CFLAGS_GCOV	:= -fprofile-arcs -ftest-coverage
-ifdef CONFIG_CC_IS_GCC
-CFLAGS_GCOV	+= -fno-tree-loop-im
-endif
-export CFLAGS_GCOV
-
 # The arch Makefiles can override CC_FLAGS_FTRACE. We may also append it later.
 ifdef CONFIG_FUNCTION_TRACER
   CC_FLAGS_FTRACE := -pg
@@ -1082,6 +1076,27 @@ endif
 # Ensure compilers do not transform certain loops into calls to wcslen()
 KBUILD_CFLAGS += -fno-builtin-wcslen
 
+CFLAGS_GCOV	:= -fprofile-arcs -ftest-coverage
+ifdef CONFIG_CC_IS_GCC
+CFLAGS_GCOV	+= -fno-tree-loop-im
+# Use atomic counter updates to avoid concurrent-access crashes in GCOV.
+# Only enable if -fprofile-update=prefer-atomic does not introduce new
+# undefined symbols (e.g. libatomic calls that the kernel cannot link).
+CFLAGS_GCOV	+= $(call try-run,\
+	echo 'long long x; void f(void){x++;}' | \
+	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -w -fprofile-arcs \
+	-ftest-coverage -x c - -c -o "$$TMP.base" && \
+	echo 'long long x; void f(void){x++;}' | \
+	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -w -fprofile-arcs \
+	-ftest-coverage -fprofile-update=prefer-atomic \
+	-x c - -c -o "$$TMP" && \
+	$(NM) "$$TMP.base" | grep ' U ' > "$$TMP.ubase" || true ; \
+	$(NM) "$$TMP" | grep ' U ' > "$$TMP.utest" || true ; \
+	cmp -s "$$TMP.ubase" "$$TMP.utest",\
+	-fprofile-update=prefer-atomic)
+endif
+export CFLAGS_GCOV
+
 # change __FILE__ to the relative path to the source directory
 ifdef building_out_of_srctree
 KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srcroot)/=)

arch/arm64/kvm/mmu.c

@@ -1444,6 +1444,11 @@ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
 	if (!kvm_has_mte(kvm))
 		return;
 
+	if (is_zero_pfn(pfn)) {
+		WARN_ON_ONCE(nr_pages != 1);
+		return;
+	}
+
 	if (folio_test_hugetlb(folio)) {
 		/* Hugetlb has MTE flags set on head page only */
 		if (folio_try_hugetlb_mte_tagging(folio)) {

arch/loongarch/kernel/smp.c

@@ -688,6 +688,7 @@ static void stop_this_cpu(void *dummy)
 	set_cpu_online(smp_processor_id(), false);
 	calculate_cpu_foreign_map();
 	local_irq_disable();
+	rcutree_report_cpu_dead();
 	while (true);
 }
 

arch/mips/dec/prom/console.c

@@ -2,8 +2,9 @@
 /*
  *	DECstation PROM-based early console support.
  *
- *	Copyright (C) 2004, 2007  Maciej W. Rozycki
+ *	Copyright (C) 2004, 2007, 2026  Maciej W. Rozycki
  */
+#include <linux/bug.h>
 #include <linux/console.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -14,9 +15,11 @@
 static void __init prom_console_write(struct console *con, const char *s,
 				      unsigned int c)
 {
-	char buf[81];
+	static char buf[81] __initdata = { 0 };
 	unsigned int chunk = sizeof(buf) - 1;
 
+	BUG_ON((long)buf != (int)(long)buf);
+
 	while (c > 0) {
 		if (chunk > c)
 			chunk = c;

arch/mips/kernel/smp.c

@@ -20,6 +20,7 @@
 #include <linux/sched/mm.h>
 #include <linux/cpumask.h>
 #include <linux/cpu.h>
+#include <linux/rcupdate.h>
 #include <linux/err.h>
 #include <linux/ftrace.h>
 #include <linux/irqdomain.h>
@@ -422,6 +423,7 @@ static void stop_this_cpu(void *dummy)
 	set_cpu_online(smp_processor_id(), false);
 	calculate_cpu_foreign_map();
 	local_irq_disable();
+	rcutree_report_cpu_dead();
 	while (1);
 }
 

arch/riscv/include/asm/cacheflush.h

@@ -43,20 +43,23 @@ do {							\
 #ifdef CONFIG_64BIT
 extern u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1];
 extern char _end[];
+static inline void mark_new_valid_map(void)
+{
+	int i;
+
+	/*
+	 * We don't care if concurrently a cpu resets this value since
+	 * the only place this can happen is in handle_exception() where
+	 * an sfence.vma is emitted.
+	 */
+	for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i)
+		new_vmalloc[i] = -1ULL;
+}
 #define flush_cache_vmap flush_cache_vmap
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	if (is_vmalloc_or_module_addr((void *)start)) {
-		int i;
-
-		/*
-		 * We don't care if concurrently a cpu resets this value since
-		 * the only place this can happen is in handle_exception() where
-		 * an sfence.vma is emitted.
-		 */
-		for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i)
-			new_vmalloc[i] = -1ULL;
-	}
+	if (is_vmalloc_or_module_addr((void *)start))
+		mark_new_valid_map();
 }
 #define flush_cache_vmap_early(start, end)	local_flush_tlb_kernel_range(start, end)
 #endif

arch/riscv/include/asm/kfence.h

@@ -6,6 +6,7 @@
 #include <linux/kfence.h>
 #include <linux/pfn.h>
 #include <asm-generic/pgalloc.h>
+#include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 
 static inline bool arch_kfence_init_pool(void)
@@ -17,10 +18,12 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	pte_t *pte = virt_to_kpte(addr);
 
-	if (protect)
+	if (protect) {
 		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT));
-	else
+	} else {
 		set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
+		mark_new_valid_map();
+	}
 
 	preempt_disable();
 	local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE);

arch/riscv/kernel/entry.S

@@ -107,8 +107,10 @@ SYM_CODE_START(handle_exception)
 
 #ifdef CONFIG_64BIT
 	/*
-	 * The RISC-V kernel does not eagerly emit a sfence.vma after each
-	 * new vmalloc mapping, which may result in exceptions:
+	 * The RISC-V kernel does not flush TLBs on all CPUS after each new
+	 * vmalloc mapping or kfence_unprotect(), which may result in
+	 * exceptions:
+	 *
 	 * - if the uarch caches invalid entries, the new mapping would not be
 	 *   observed by the page table walker and an invalidation is needed.
 	 * - if the uarch does not cache invalid entries, a reordered access

arch/x86/kvm/hyperv.c

@@ -1839,6 +1839,11 @@ static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_ba
 	int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK;
 	unsigned long sbank;
 
+	BUILD_BUG_ON(BITS_PER_TYPE(valid_bank_mask) != HV_MAX_SPARSE_VCPU_BANKS);
+
+	if (valid_bit_nr >= HV_MAX_SPARSE_VCPU_BANKS)
+		return false;
+
 	if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask))
 		return false;
 

arch/x86/kvm/mmu/mmu.c

@@ -2453,13 +2453,15 @@ static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu,
 						 u64 *sptep, gfn_t gfn,
 						 bool direct, unsigned int access)
 {
-	union kvm_mmu_page_role role;
+	union kvm_mmu_page_role role = kvm_mmu_child_role(sptep, direct, access);
 
-	if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep) &&
-	    spte_to_child_sp(*sptep) && spte_to_child_sp(*sptep)->gfn == gfn)
+	if (is_shadow_present_pte(*sptep) &&
+	    !is_large_pte(*sptep) &&
+	    spte_to_child_sp(*sptep) &&
+	    spte_to_child_sp(*sptep)->gfn == gfn &&
+	    spte_to_child_sp(*sptep)->role.word == role.word)
 		return ERR_PTR(-EEXIST);
 
-	role = kvm_mmu_child_role(sptep, direct, access);
 	return kvm_mmu_get_shadow_page(vcpu, gfn, role);
 }
 
@@ -7179,13 +7181,19 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 		sp = sptep_to_sp(sptep);
 
 		/*
-		 * We cannot do huge page mapping for indirect shadow pages,
-		 * which are found on the last rmap (level = 1) when not using
-		 * tdp; such shadow pages are synced with the page table in
-		 * the guest, and the guest page table is using 4K page size
-		 * mapping if the indirect sp has level = 1.
+		 * Direct shadow page can be replaced by a hugepage if the host
+		 * mapping level allows it and the memslot maps all of the host
+		 * hugepage.  Note!  If the memslot maps only part of the
+		 * hugepage, sp->gfn may be below slot->base_gfn, and querying
+		 * the max mapping level would cause an out-of-bounds lpage_info
+		 * access.  So the gfn bounds check *must* be done first.
+		 *
+		 * Indirect shadow pages are created when the guest page tables
+		 * are using 4K pages.  Since the host mapping is always
+		 * constrained by the page size in the guest, indirect shadow
+		 * pages are never collapsible.
 		 */
-		if (sp->role.direct &&
+		if (sp->role.direct && is_gfn_in_memslot(slot, sp->gfn) &&
 		    sp->role.level < kvm_mmu_max_mapping_level(kvm, NULL, slot, sp->gfn)) {
 			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
 

arch/x86/kvm/svm/sev.c

@@ -1340,6 +1340,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 		s_off = vaddr & ~PAGE_MASK;
 		d_off = dst_vaddr & ~PAGE_MASK;
 		len = min_t(size_t, (PAGE_SIZE - s_off), size);
+		len = min_t(size_t, len, PAGE_SIZE - d_off);
 
 		if (dec)
 			ret = __sev_dbg_decrypt_user(kvm,

block/bdev.c

@@ -438,15 +438,10 @@ EXPORT_SYMBOL_GPL(blockdev_superblock);
 
 void __init bdev_cache_init(void)
 {
-	int err;
-
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
 				SLAB_ACCOUNT|SLAB_PANIC),
 			init_once);
-	err = register_filesystem(&bd_type);
-	if (err)
-		panic("Cannot register bdev pseudo-fs");
 	blockdev_mnt = kern_mount(&bd_type);
 	if (IS_ERR(blockdev_mnt))
 		panic("Cannot create bdev pseudo-fs");

block/blk-cgroup.c

@@ -164,20 +164,10 @@ static void blkg_free(struct blkcg_gq *blkg)
 static void __blkg_release(struct rcu_head *rcu)
 {
 	struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);
-	struct blkcg *blkcg = blkg->blkcg;
-	int cpu;
 
 #ifdef CONFIG_BLK_CGROUP_PUNT_BIO
 	WARN_ON(!bio_list_empty(&blkg->async_bios));
 #endif
-	/*
-	 * Flush all the non-empty percpu lockless lists before releasing
-	 * us, given these stat belongs to us.
-	 *
-	 * blkg_stat_lock is for serializing blkg stat update
-	 */
-	for_each_possible_cpu(cpu)
-		__blkcg_rstat_flush(blkcg, cpu);
 
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
@@ -195,6 +185,17 @@ static void __blkg_release(struct rcu_head *rcu)
 static void blkg_release(struct percpu_ref *ref)
 {
 	struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt);
+	struct blkcg *blkcg = blkg->blkcg;
+	int cpu;
+
+	/*
+	 * Flush all the non-empty percpu lockless lists before releasing
+	 * us, given these stat belongs to us.
+	 *
+	 * blkg_stat_lock is for serializing blkg stat update
+	 */
+	for_each_possible_cpu(cpu)
+		__blkcg_rstat_flush(blkcg, cpu);
 
 	call_rcu(&blkg->rcu_head, __blkg_release);
 }

drivers/crypto/nx/nx.c

@@ -714,15 +714,13 @@ int nx_crypto_ctx_aes_xcbc_init(struct crypto_shash *tfm)
 /**
  * nx_crypto_ctx_exit - destroy a crypto api context
  *
- * @tfm: the crypto transform pointer for the context
+ * @nx_ctx: the crypto api context
  *
  * As crypto API contexts are destroyed, this exit hook is called to free the
  * memory associated with it.
  */
-void nx_crypto_ctx_exit(struct crypto_tfm *tfm)
+void nx_crypto_ctx_exit(struct nx_crypto_ctx *nx_ctx)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
-
 	kfree_sensitive(nx_ctx->kmem);
 	nx_ctx->csbcpb = NULL;
 	nx_ctx->csbcpb_aead = NULL;

drivers/crypto/nx/nx.h

@@ -153,7 +153,7 @@ int nx_crypto_ctx_aes_ctr_init(struct crypto_skcipher *tfm);
 int nx_crypto_ctx_aes_cbc_init(struct crypto_skcipher *tfm);
 int nx_crypto_ctx_aes_ecb_init(struct crypto_skcipher *tfm);
 int nx_crypto_ctx_sha_init(struct crypto_shash *tfm);
-void nx_crypto_ctx_exit(struct crypto_tfm *tfm);
+void nx_crypto_ctx_exit(struct nx_crypto_ctx *nx_ctx);
 void nx_crypto_ctx_skcipher_exit(struct crypto_skcipher *tfm);
 void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm);
 void nx_crypto_ctx_shash_exit(struct crypto_shash *tfm);

drivers/fpga/of-fpga-region.c

@@ -168,11 +168,10 @@ static int child_regions_with_firmware(struct device_node *overlay)
 						     fpga_region_of_match);
 	}
 
-	of_node_put(child_region);
-
 	if (ret)
 		pr_err("firmware-name not allowed in child FPGA region: %pOF",
 		       child_region);
+	of_node_put(child_region);
 
 	return ret;
 }

drivers/i2c/i2c-core-base.c

@@ -1570,6 +1570,10 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 	pm_suspend_ignore_children(&adap->dev, true);
 	pm_runtime_enable(&adap->dev);
 
+	mutex_lock(&core_lock);
+	idr_replace(&i2c_adapter_idr, adap, adap->nr);
+	mutex_unlock(&core_lock);
+
 	res = device_add(&adap->dev);
 	if (res) {
 		pr_err("adapter '%s': can't register device (%d)\n", adap->name, res);
@@ -1628,7 +1632,7 @@ static int __i2c_add_numbered_adapter(struct i2c_adapter *adap)
 	int id;
 
 	mutex_lock(&core_lock);
-	id = idr_alloc(&i2c_adapter_idr, adap, adap->nr, adap->nr + 1, GFP_KERNEL);
+	id = idr_alloc(&i2c_adapter_idr, NULL, adap->nr, adap->nr + 1, GFP_KERNEL);
 	mutex_unlock(&core_lock);
 	if (WARN(id < 0, "couldn't get idr"))
 		return id == -ENOSPC ? -EBUSY : id;
@@ -1662,7 +1666,7 @@ int i2c_add_adapter(struct i2c_adapter *adapter)
 	}
 
 	mutex_lock(&core_lock);
-	id = idr_alloc(&i2c_adapter_idr, adapter,
+	id = idr_alloc(&i2c_adapter_idr, NULL,
 		       __i2c_first_dynamic_bus_num, 0, GFP_KERNEL);
 	mutex_unlock(&core_lock);
 	if (WARN(id < 0, "couldn't get idr"))

drivers/irqchip/irq-imgpdc.c

@@ -378,6 +378,7 @@ static int pdc_intc_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "cannot add IRQ domain\n");
 		return -ENOMEM;
 	}
+	priv->domain->flags |= IRQ_DOMAIN_FLAG_DESTROY_GC;
 
 	/*
 	 * Set up 2 generic irq chips with 2 chip types.
@@ -465,6 +466,11 @@ static void pdc_intc_remove(struct platform_device *pdev)
 {
 	struct pdc_intc_priv *priv = platform_get_drvdata(pdev);
 
+	for (unsigned int i = 0; i < priv->nr_perips; ++i)
+		irq_set_chained_handler_and_data(priv->perip_irqs[i], NULL, NULL);
+
+	irq_set_chained_handler_and_data(priv->syswake_irq, NULL, NULL);
+
 	irq_domain_remove(priv->domain);
 }