Merge tag 'v6.18.39' into qcom-6.18.y

Documentation/crypto/userspace-if.rst

@@ -328,33 +328,10 @@ CRYPTO_USER_API_RNG_CAVP option:
 Zero-Copy Interface
 -------------------
 
-In addition to the send/write/read/recv system call family, the AF_ALG
-interface can be accessed with the zero-copy interface of
-splice/vmsplice. As the name indicates, the kernel tries to avoid a copy
-operation into kernel space.
-
-The zero-copy operation requires data to be aligned at the page
-boundary. Non-aligned data can be used as well, but may require more
-operations of the kernel which would defeat the speed gains obtained
-from the zero-copy interface.
-
-The system-inherent limit for the size of one zero-copy operation is 16
-pages. If more data is to be sent to AF_ALG, user space must slice the
-input into segments with a maximum size of 16 pages.
-
-Zero-copy can be used with the following code example (a complete
-working example is provided with libkcapi):
-
-::
-
-    int pipes[2];
-
-    pipe(pipes);
-    /* input data in iov */
-    vmsplice(pipes[1], iov, iovlen, SPLICE_F_GIFT);
-    /* opfd is the file descriptor returned from accept() system call */
-    splice(pipes[0], NULL, opfd, NULL, ret, 0);
-    read(opfd, out, outlen);
+AF_ALG used to have zero-copy support, but it was removed due to it being a
+frequent source of vulnerabilities.  For backwards compatibility the splice()
+and sendfile() system calls are still supported, but the kernel will make an
+internal copy of the data before passing it to the crypto code.
 
 
 Setsockopt Interface

Documentation/process/deprecated.rst

@@ -387,6 +387,7 @@ allocations. For example, these open coded assignments::
 	ptr = kzalloc(sizeof(*ptr), gfp);
 	ptr = kmalloc_array(count, sizeof(*ptr), gfp);
 	ptr = kcalloc(count, sizeof(*ptr), gfp);
+	ptr = kmalloc(struct_size(ptr, flex_member, count), gfp);
 	ptr = kmalloc(sizeof(struct foo, gfp);
 
 become, respectively::
@@ -395,4 +396,10 @@ become, respectively::
 	ptr = kzalloc_obj(*ptr, gfp);
 	ptr = kmalloc_objs(*ptr, count, gfp);
 	ptr = kzalloc_objs(*ptr, count, gfp);
+	ptr = kmalloc_flex(*ptr, flex_member, count, gfp);
 	__auto_type ptr = kmalloc_obj(struct foo, gfp);
+
+If `ptr->flex_member` is annotated with __counted_by(), the allocation
+will automatically fail if `count` is larger than the maximum
+representable value that can be stored in the counter member associated
+with `flex_member`.

MAINTAINERS

@@ -14637,7 +14637,6 @@ M:	Qunqin Zhao <zhaoqunqin@loongson.cn>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
 F:	drivers/char/tpm/tpm_loongson.c
-F:	drivers/crypto/loongson/
 F:	drivers/mfd/loongson-se.c
 F:	include/linux/mfd/loongson-se.h
 

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 18
-SUBLEVEL = 37
+SUBLEVEL = 39
 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
@@ -911,6 +905,9 @@ KBUILD_CFLAGS += $(stackp-flags-y)
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 KBUILD_RUSTFLAGS += -Cforce-frame-pointers=y
+# Work around rustc bug on compilers without
+# https://github.com/rust-lang/rust/pull/156980.
+KBUILD_RUSTFLAGS += $(if $(call rustc-min-version,109800),,-Zllvm_module_flag=frame-pointer:u32:2:max)
 else
 # Some targets (ARM with Thumb2, for example), can't be built with frame
 # pointers.  For those, we don't have FUNCTION_TRACER automatically
@@ -1082,6 +1079,27 @@ 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/kernel/entry-fpsimd.S

@@ -103,13 +103,13 @@ SYM_FUNC_END(sme_set_vq)
  * Save the ZA and ZT state
  *
  * x0 - pointer to buffer for state
- * x1 - number of ZT registers to save
+ * w1 - number of ZT registers to save
  */
 SYM_FUNC_START(sme_save_state)
 	_sme_rdsvl	2, 1		// x2 = VL/8
 	sme_save_za 0, x2, 12		// Leaves x0 pointing to the end of ZA
 
-	cbz	x1, 1f
+	cbz	w1, 1f
 	_str_zt 0
 1:
 	ret
@@ -119,13 +119,13 @@ SYM_FUNC_END(sme_save_state)
  * Load the ZA and ZT state
  *
  * x0 - pointer to buffer for state
- * x1 - number of ZT registers to save
+ * w1 - number of ZT registers to save
  */
 SYM_FUNC_START(sme_load_state)
 	_sme_rdsvl	2, 1		// x2 = VL/8
 	sme_load_za 0, x2, 12		// Leaves x0 pointing to the end of ZA
 
-	cbz	x1, 1f
+	cbz	w1, 1f
 	_ldr_zt 0
 1:
 	ret

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -126,6 +126,9 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
 
+	/* __hyp_running_vcpu must be NULL in a guest context. */
+	hyp_vcpu->vcpu.arch.ctxt.__hyp_running_vcpu = NULL;
+
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
 	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
 	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &

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/arm64/kvm/nested.c

@@ -824,34 +824,31 @@ static void invalidate_vncr(struct vncr_tlb *vt)
 		clear_fixmap(vncr_fixmap(vt->cpu));
 }
 
+/*
+ * VNCR TLB invalidation occurs from MMU notifiers or TLBI instructions, and
+ * either can race against a vcpu not being onlined yet (no pseudo-TLB
+ * allocated). Similarly, the TLB might be invalid.  Skip those, as they
+ * obviously don't participate in the invalidation at this stage.
+ */
+#define kvm_for_each_vncr_tlb(idx, vcpup, tlbp, kvm)	\
+	kvm_for_each_vcpu(idx, vcpup, kvm)		\
+		if (((tlbp) = vcpup->arch.vncr_tlb) &&	\
+		    (tlbp)->valid)
+
 static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end)
 {
 	struct kvm_vcpu *vcpu;
+	struct vncr_tlb *vt;
 	unsigned long i;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
 		return;
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+	kvm_for_each_vncr_tlb(i, vcpu, vt, kvm) {
 		u64 ipa_start, ipa_end, ipa_size;
 
-		/*
-		 * Careful here: We end-up here from an MMU notifier,
-		 * and this can race against a vcpu not being onlined
-		 * yet, without the pseudo-TLB being allocated.
-		 *
-		 * Skip those, as they obviously don't participate in
-		 * the invalidation at this stage.
-		 */
-		if (!vt)
-			continue;
-
-		if (!vt->valid)
-			continue;
-
 		ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
 							    vt->wr.level));
 		ipa_start = vt->wr.pa & ~(ipa_size - 1);
@@ -881,17 +878,14 @@ static void invalidate_vncr_va(struct kvm *kvm,
 			       struct s1e2_tlbi_scope *scope)
 {
 	struct kvm_vcpu *vcpu;
+	struct vncr_tlb *vt;
 	unsigned long i;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+	kvm_for_each_vncr_tlb(i, vcpu, vt, kvm) {
 		u64 va_start, va_end, va_size;
 
-		if (!vt->valid)
-			continue;
-
 		va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
 							   vt->wr.level));
 		va_start = vt->gva & ~(va_size - 1);
@@ -1244,8 +1238,10 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 	}
 
 	scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
-		if (mmu_invalidate_retry(vcpu->kvm, mmu_seq))
+		if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) {
+			kvm_release_faultin_page(vcpu->kvm, page, true, false);
 			return -EAGAIN;
+		}
 
 		vt->gva = va;
 		vt->hpa = pfn << PAGE_SHIFT;

arch/arm64/lib/insn.c

@@ -338,6 +338,8 @@ u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
 	long offset;
 
 	offset = label_imm_common(pc, addr, SZ_1M);
+	if (offset >= SZ_1M)
+		return AARCH64_BREAK_FAULT;
 
 	insn = aarch64_insn_get_bcond_value();
 

arch/arm64/net/bpf_jit_comp.c

@@ -2117,7 +2117,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	image_size = extable_offset + extable_size;
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
 					      sizeof(u64), &header, &image_ptr,
-					      jit_fill_hole);
+					      jit_fill_hole, was_classic);
 	if (!ro_header) {
 		prog = orig_prog;
 		goto out_off;
@@ -2754,7 +2754,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
-	return bpf_prog_pack_alloc(size, jit_fill_hole);
+	return bpf_prog_pack_alloc(size, jit_fill_hole, false);
 }
 
 void arch_free_bpf_trampoline(void *image, unsigned int size)

arch/loongarch/include/asm/acpi.h

@@ -38,6 +38,8 @@ static inline bool acpi_has_cpu_in_madt(void)
 extern struct list_head acpi_wakeup_device_list;
 extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
+extern void acpi_add_early_pio(void);
+extern void acpi_remove_early_pio(void);
 extern int __init parse_acpi_topology(void);
 
 static inline u32 get_acpi_id_for_cpu(unsigned int cpu)

arch/loongarch/kernel/acpi.c

@@ -16,6 +16,7 @@
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/serial_core.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 #include <asm/numa.h>
 #include <asm/loongson.h>
@@ -59,6 +60,33 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 		return ioremap_cache(phys, size);
 }
 
+#define PIO_BASE (unsigned long)PCI_IOBASE
+#define PIO_SIZE ALIGN(ISA_IOSIZE, PAGE_SIZE)
+
+static bool acpi_pio;
+
+/* Add PIO for early access */
+void acpi_add_early_pio(void)
+{
+	if (!acpi_disabled) {
+		acpi_pio = true;
+		vmap_page_range(PIO_BASE, PIO_BASE + PIO_SIZE,
+				LOONGSON_LIO_BASE, pgprot_device(PAGE_KERNEL));
+	}
+}
+
+/* Remove PIO for PCI register */
+void acpi_remove_early_pio(void)
+{
+	if (!acpi_pio)
+		return;
+
+	if (!acpi_disabled) {
+		acpi_pio = false;
+		vunmap_range(PIO_BASE, PIO_BASE + PIO_SIZE);
+	}
+}
+
 #ifdef CONFIG_SMP
 static int set_processor_mask(u32 id, u32 pass)
 {

arch/loongarch/kernel/setup.c

@@ -510,6 +510,8 @@ static __init int arch_reserve_pio_range(void)
 {
 	struct device_node *np;
 
+	acpi_add_early_pio();
+
 	for_each_node_by_name(np, "isa") {
 		struct of_range range;
 		struct of_range_parser parser;

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/loongarch/kvm/intc/eiointc.c

@@ -654,10 +654,14 @@ static int kvm_eiointc_create(struct kvm_device *dev, u32 type)
 
 	device = &s->device_vext;
 	kvm_iodevice_init(device, &kvm_eiointc_virt_ops);
+	mutex_lock(&kvm->slots_lock);
 	ret = kvm_io_bus_register_dev(kvm, KVM_IOCSR_BUS,
 			EIOINTC_VIRT_BASE, EIOINTC_VIRT_SIZE, device);
+	mutex_unlock(&kvm->slots_lock);
 	if (ret < 0) {
+		mutex_lock(&kvm->slots_lock);
 		kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &s->device);
+		mutex_unlock(&kvm->slots_lock);
 		kfree(s);
 		return ret;
 	}
@@ -676,8 +680,10 @@ static void kvm_eiointc_destroy(struct kvm_device *dev)
 
 	kvm = dev->kvm;
 	eiointc = kvm->arch.eiointc;
+	mutex_lock(&kvm->slots_lock);
 	kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device);
 	kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device_vext);
+	mutex_unlock(&kvm->slots_lock);
 	kfree(eiointc);
 	kfree(dev);
 }

arch/loongarch/kvm/intc/ipi.c

@@ -457,7 +457,9 @@ static void kvm_ipi_destroy(struct kvm_device *dev)
 
 	kvm = dev->kvm;
 	ipi = kvm->arch.ipi;
+	mutex_lock(&kvm->slots_lock);
 	kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &ipi->device);
+	mutex_unlock(&kvm->slots_lock);
 	kfree(ipi);
 	kfree(dev);
 }

arch/loongarch/kvm/intc/pch_pic.c

@@ -473,7 +473,9 @@ static void kvm_pch_pic_destroy(struct kvm_device *dev)
 	kvm = dev->kvm;
 	s = kvm->arch.pch_pic;
 	/* unregister pch pic device and free it's memory */
+	mutex_lock(&kvm->slots_lock);
 	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &s->device);
+	mutex_unlock(&kvm->slots_lock);
 	kfree(s);
 	kfree(dev);
 }