Merge tag 'v5.15.167' into 5.15-main

This is the 5.15.167 stable release

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmbir24ACgkQONu9yGCS
# aT5AMxAAyTz/ceQCNrwgw9vmwbe+H5JM9etKhuCtlHyxotP1A7/x6yIZ6QYyua5P
# xizu9mvFg7XhEQsvXshppzaK7TuxjYSIkBi0S2XGqAJpI/Tqf+FVHLFVSnxVjE7N
# BZrVc9RqkA+Fo7mEQvLy4+1MuS3zJZ+vsYJ2t+MPmYl5SokDYX0h7CuYD4wBya22
# thlxJX/SRsWfUC5sGG81s7dIMp+fLsgTkJi3Gn/3B/gOILL1Uk+q3PY3RtoQwTyE
# idvHoU4N3pdKZscpwVgs29MkpL96O6Cf/spfn/C3Dm765HZcq366tD015Y4TPYq/
# viJvyEhAB0bURJltq78vB87T9zFPEJ3KJj0p75p7wQBOUE8MtHmBRDzo07bXmBYL
# /208vpgVz+yKNoFV9qm5F87gVWDS1S1Bt7E1VGXFuJY2IlsTMa2zNgLt5d03wlEJ
# LNjPI/t0eUaE0DjVV8c88zyRQm6k7oTutbP3OG8n5whn5+L9aYg4Jz9Xi0gkqP9h
# 0AwGd4618HuskNZCpnwyTB+ytU+XkQ+75BrNNkKvS2Y1NDmsfahMt+PwumuA7Hyc
# d9ZaZNUyFcPV7GZYwi6WmCL0HHWtZuXsm9TByKlLz1G2MWTsiQfmXc0RerCTSTs6
# Xso3nFzQeVyexQNlnyA13miNHAAYdIRToxGOSa4zbxKuVhZuM+o=
# =yA3D
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu Sep 12 11:07:58 2024 CEST
# gpg:                using RSA key 647F28654894E3BD457199BE38DBBDC86092693E
# gpg: Can't check signature: No public key

Documentation/locking/hwspinlock.rst

@@ -85,6 +85,17 @@ is already free).
 
 Should be called from a process context (might sleep).
 
+::
+
+  int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id);
+
+After verifying the owner of the hwspinlock, release a previously acquired
+hwspinlock; returns 0 on success, or an appropriate error code on failure
+(e.g. -EOPNOTSUPP if the bust operation is not defined for the specific
+hwspinlock).
+
+Should be called from a process context (might sleep).
+
 ::
 
   int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout);

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 166
+SUBLEVEL = 167
 EXTRAVERSION =
 NAME = Trick or Treat
 

arch/arm64/include/asm/acpi.h

@@ -97,6 +97,18 @@ static inline u32 get_acpi_id_for_cpu(unsigned int cpu)
 	return	acpi_cpu_get_madt_gicc(cpu)->uid;
 }
 
+static inline int get_cpu_for_acpi_id(u32 uid)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (acpi_cpu_get_madt_gicc(cpu) &&
+		    uid == get_acpi_id_for_cpu(cpu))
+			return cpu;
+
+	return -EINVAL;
+}
+
 static inline void arch_fix_phys_package_id(int num, u32 slot) { }
 void __init acpi_init_cpus(void);
 int apei_claim_sea(struct pt_regs *regs);

arch/arm64/kernel/acpi_numa.c

@@ -34,17 +34,6 @@ int __init acpi_numa_get_nid(unsigned int cpu)
 	return acpi_early_node_map[cpu];
 }
 
-static inline int get_cpu_for_acpi_id(u32 uid)
-{
-	int cpu;
-
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
-		if (uid == get_acpi_id_for_cpu(cpu))
-			return cpu;
-
-	return -EINVAL;
-}
-
 static int __init acpi_parse_gicc_pxm(union acpi_subtable_headers *header,
 				      const unsigned long end)
 {

arch/mips/kernel/cevt-r4k.c

@@ -303,13 +303,6 @@ int r4k_clockevent_init(void)
 	if (!c0_compare_int_usable())
 		return -ENXIO;
 
-	/*
-	 * With vectored interrupts things are getting platform specific.
-	 * get_c0_compare_int is a hook to allow a platform to return the
-	 * interrupt number of its liking.
-	 */
-	irq = get_c0_compare_int();
-
 	cd = &per_cpu(mips_clockevent_device, cpu);
 
 	cd->name		= "MIPS";
@@ -320,7 +313,6 @@ int r4k_clockevent_init(void)
 	min_delta		= calculate_min_delta();
 
 	cd->rating		= 300;
-	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= mips_next_event;
 	cd->event_handler	= mips_event_handler;
@@ -332,6 +324,13 @@ int r4k_clockevent_init(void)
 
 	cp0_timer_irq_installed = 1;
 
+	/*
+	 * With vectored interrupts things are getting platform specific.
+	 * get_c0_compare_int is a hook to allow a platform to return the
+	 * interrupt number of its liking.
+	 */
+	irq = get_c0_compare_int();
+
 	if (request_irq(irq, c0_compare_interrupt, flags, "timer",
 			c0_compare_interrupt))
 		pr_err("Failed to request irq %d (timer)\n", irq);

arch/riscv/kernel/head.S

@@ -309,6 +309,9 @@ clear_bss_done:
 #else
 	mv a0, s1
 #endif /* CONFIG_BUILTIN_DTB */
+	/* Set trap vector to spin forever to help debug */
+	la a3, .Lsecondary_park
+	csrw CSR_TVEC, a3
 	call setup_vm
 #ifdef CONFIG_MMU
 	la a0, early_pg_dir

arch/s390/kernel/vmlinux.lds.S

@@ -72,6 +72,15 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	__end_ro_after_init = .;
 
+	.data.rel.ro : {
+		*(.data.rel.ro .data.rel.ro.*)
+	}
+	.got : {
+		__got_start = .;
+		*(.got)
+		__got_end = .;
+	}
+
 	RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE)
 	BOOT_DATA_PRESERVED
 

arch/um/drivers/line.c

@@ -383,6 +383,7 @@ int setup_one_line(struct line *lines, int n, char *init,
 			parse_chan_pair(NULL, line, n, opts, error_out);
 			err = 0;
 		}
+		*error_out = "configured as 'none'";
 	} else {
 		char *new = kstrdup(init, GFP_KERNEL);
 		if (!new) {
@@ -406,6 +407,7 @@ int setup_one_line(struct line *lines, int n, char *init,
 			}
 		}
 		if (err) {
+			*error_out = "failed to parse channel pair";
 			line->init_str = NULL;
 			line->valid = 0;
 			kfree(new);

arch/x86/kvm/svm/svm.c

@@ -958,6 +958,9 @@ static __init void svm_set_cpu_caps(void)
 
 	/* CPUID 0x8000001F (SME/SEV features) */
 	sev_set_cpu_caps();
+
+	/* Don't advertise Bus Lock Detect to guest if SVM support is absent */
+	kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT);
 }
 
 static __init int svm_hardware_setup(void)
@@ -2712,6 +2715,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CSTAR:
 		msr_info->data = svm->vmcb01.ptr->save.cstar;
 		break;
+	case MSR_GS_BASE:
+		msr_info->data = svm->vmcb01.ptr->save.gs.base;
+		break;
+	case MSR_FS_BASE:
+		msr_info->data = svm->vmcb01.ptr->save.fs.base;
+		break;
 	case MSR_KERNEL_GS_BASE:
 		msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base;
 		break;
@@ -2923,6 +2932,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_CSTAR:
 		svm->vmcb01.ptr->save.cstar = data;
 		break;
+	case MSR_GS_BASE:
+		svm->vmcb01.ptr->save.gs.base = data;
+		break;
+	case MSR_FS_BASE:
+		svm->vmcb01.ptr->save.fs.base = data;
+		break;
 	case MSR_KERNEL_GS_BASE:
 		svm->vmcb01.ptr->save.kernel_gs_base = data;
 		break;

arch/x86/mm/pti.c

@@ -241,7 +241,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
  *
  * Returns a pointer to a PTE on success, or NULL on failure.
  */
-static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	pmd_t *pmd;
@@ -251,10 +251,15 @@ static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 	if (!pmd)
 		return NULL;
 
-	/* We can't do anything sensible if we hit a large mapping. */
+	/* Large PMD mapping found */
 	if (pmd_large(*pmd)) {
-		WARN_ON(1);
-		return NULL;
+		/* Clear the PMD if we hit a large mapping from the first round */
+		if (late_text) {
+			set_pmd(pmd, __pmd(0));
+		} else {
+			WARN_ON_ONCE(1);
+			return NULL;
+		}
 	}
 
 	if (pmd_none(*pmd)) {
@@ -283,7 +288,7 @@ static void __init pti_setup_vsyscall(void)
 	if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
 		return;
 
-	target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
+	target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false);
 	if (WARN_ON(!target_pte))
 		return;
 
@@ -301,7 +306,7 @@ enum pti_clone_level {
 
 static void
 pti_clone_pgtable(unsigned long start, unsigned long end,
-		  enum pti_clone_level level)
+		  enum pti_clone_level level, bool late_text)
 {
 	unsigned long addr;
 
@@ -390,7 +395,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 				return;
 
 			/* Allocate PTE in the user page-table */
-			target_pte = pti_user_pagetable_walk_pte(addr);
+			target_pte = pti_user_pagetable_walk_pte(addr, late_text);
 			if (WARN_ON(!target_pte))
 				return;
 
@@ -452,7 +457,7 @@ static void __init pti_clone_user_shared(void)
 		phys_addr_t pa = per_cpu_ptr_to_phys((void *)va);
 		pte_t *target_pte;
 
-		target_pte = pti_user_pagetable_walk_pte(va);
+		target_pte = pti_user_pagetable_walk_pte(va, false);
 		if (WARN_ON(!target_pte))
 			return;
 
@@ -475,7 +480,7 @@ static void __init pti_clone_user_shared(void)
 	start = CPU_ENTRY_AREA_BASE;
 	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
 
-	pti_clone_pgtable(start, end, PTI_CLONE_PMD);
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD, false);
 }
 #endif /* CONFIG_X86_64 */
 
@@ -492,11 +497,11 @@ static void __init pti_setup_espfix64(void)
 /*
  * Clone the populated PMDs of the entry text and force it RO.
  */
-static void pti_clone_entry_text(void)
+static void pti_clone_entry_text(bool late)
 {
 	pti_clone_pgtable((unsigned long) __entry_text_start,
 			  (unsigned long) __entry_text_end,
-			  PTI_LEVEL_KERNEL_IMAGE);
+			  PTI_LEVEL_KERNEL_IMAGE, late);
 }
 
 /*
@@ -571,7 +576,7 @@ static void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false);
 
 	/*
 	 * pti_clone_pgtable() will set the global bit in any PMDs
@@ -638,8 +643,15 @@ void __init pti_init(void)
 
 	/* Undo all global bits from the init pagetables in head_64.S: */
 	pti_set_kernel_image_nonglobal();
+
 	/* Replace some of the global bits just for shared entry text: */
-	pti_clone_entry_text();
+	/*
+	 * This is very early in boot. Device and Late initcalls can do
+	 * modprobe before free_initmem() and mark_readonly(). This
+	 * pti_clone_entry_text() allows those user-mode-helpers to function,
+	 * but notably the text is still RW.
+	 */
+	pti_clone_entry_text(false);
 	pti_setup_espfix64();
 	pti_setup_vsyscall();
 }
@@ -656,10 +668,11 @@ void pti_finalize(void)
 	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 	/*
-	 * We need to clone everything (again) that maps parts of the
-	 * kernel image.
+	 * This is after free_initmem() (all initcalls are done) and we've done
+	 * mark_readonly(). Text is now NX which might've split some PMDs
+	 * relative to the early clone.
 	 */
-	pti_clone_entry_text();
+	pti_clone_entry_text(true);
 	pti_clone_kernel_text();
 
 	debug_checkwx_user();

block/blk-integrity.c

@@ -431,8 +431,6 @@ void blk_integrity_unregister(struct gendisk *disk)
 	if (!bi->profile)
 		return;
 
-	/* ensure all bios are off the integrity workqueue */
-	blk_flush_integrity();
 	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 	memset(bi, 0, sizeof(*bi));
 }

drivers/acpi/acpi_processor.c

@@ -373,7 +373,7 @@ static int acpi_processor_add(struct acpi_device *device,
 
 	result = acpi_processor_get_info(device);
 	if (result) /* Processor is not physically present or unavailable */
-		return 0;
+		goto err_clear_driver_data;
 
 	BUG_ON(pr->id >= nr_cpu_ids);
 
@@ -388,7 +388,7 @@ static int acpi_processor_add(struct acpi_device *device,
 			"BIOS reported wrong ACPI id %d for the processor\n",
 			pr->id);
 		/* Give up, but do not abort the namespace scan. */
-		goto err;
+		goto err_clear_driver_data;
 	}
 	/*
 	 * processor_device_array is not cleared on errors to allow buggy BIOS
@@ -400,12 +400,12 @@ static int acpi_processor_add(struct acpi_device *device,
 	dev = get_cpu_device(pr->id);
 	if (!dev) {
 		result = -ENODEV;
-		goto err;
+		goto err_clear_per_cpu;
 	}
 
 	result = acpi_bind_one(dev, device);
 	if (result)
-		goto err;
+		goto err_clear_per_cpu;
 
 	pr->dev = dev;
 
@@ -416,10 +416,11 @@ static int acpi_processor_add(struct acpi_device *device,
 	dev_err(dev, "Processor driver could not be attached\n");
 	acpi_unbind_one(dev);
 
- err:
-	free_cpumask_var(pr->throttling.shared_cpu_map);
-	device->driver_data = NULL;
+ err_clear_per_cpu:
 	per_cpu(processors, pr->id) = NULL;
+ err_clear_driver_data:
+	device->driver_data = NULL;
+	free_cpumask_var(pr->throttling.shared_cpu_map);
  err_free_pr:
 	kfree(pr);
 	return result;

drivers/android/binder.c

@@ -3173,6 +3173,7 @@ static void binder_transaction(struct binder_proc *proc,
 		 */
 		copy_size = object_offset - user_offset;
 		if (copy_size && (user_offset > object_offset ||
+				object_offset > tr->data_size ||
 				binder_alloc_copy_user_to_buffer(
 					&target_proc->alloc,
 					t->buffer, user_offset,

drivers/ata/libata-core.c

@@ -5454,8 +5454,10 @@ struct ata_host *ata_host_alloc(struct device *dev, int max_ports)
 	}
 
 	dr = devres_alloc(ata_devres_release, 0, GFP_KERNEL);
-	if (!dr)
+	if (!dr) {
+		kfree(host);
 		goto err_out;
+	}
 
 	devres_add(dev, dr);
 	dev_set_drvdata(dev, host);