Merge tag 'v6.1.119' into 6.1-main

This is the 6.1.119 stable release

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmdAlzgACgkQONu9yGCS
# aT42uQ//dtRiaR95GtZ741kjEp3bGCYbSvhQsnCF2O5Ft1ajd7zenog2oZ83Xvnk
# JGZwtRvLrBvYekBFHiftF0i0vCxmLPQVx+GUIqCFU/ZZdITw+n99DH/zfl9soXmh
# 0DpZqNos0TkBdPmw0vYB+mIibAjG5brMwfdrXy5U0T1lrw1EeaUxat05fMBiF5XO
# vSK450RgzGa7h+8jUyK4eR7P+aUjNoUl3XZstFK1YzbVznXomvmXGFB0Xt3KIFEZ
# 5waNFJnYkkB/W9IgrcXNtskPUwh3wJ0RltavQcwnCIeRUCousW+tFPn9OGHbOC9V
# VJGiIuzGIQYEY71Ds7O6CD/3EXWs3fn1qJUU40IvJJvhh5z8G3zJWGXolaIJqLzW
# EkfzXF+mtMzjPm+IR2UrGtVMvDEOi7CdBVGDUrxqRiSrZvBKgu4zbF1ZiDI49hcP
# GuYgcPbEF28W4DoABhbzDMvIkyuyFvBInFHnI04KFlHsGMx14Y6FaMtoOz8g8z+0
# NX43nyL2JiWsSSmiViRJlP2cIdqjZb+c0CdunTo6w/Ho4rnRbaiL3Mggt70CBMCM
# /yUCLNcx0c/sEwb0YF+JNAjqGmhVm+aUZ3CRqjPSN44k4wu6TaokhWnaB9g83KP8
# BvpGK0LWnS2whCHS0SkM96Pp5QYXDoQnRJmw/xo+oYwu4/+dK2s=
# =No10
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri Nov 22 15:37:44 2024 CET
# gpg:                using RSA key 647F28654894E3BD457199BE38DBBDC86092693E
# gpg: Can't check signature: No public key

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 1
-SUBLEVEL = 118
+SUBLEVEL = 119
 EXTRAVERSION =
 NAME = Curry Ramen
 

arch/arm/kernel/head.S

@@ -252,27 +252,31 @@ __create_page_tables:
 	 */
 	add	r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ENTRY_ORDER)
 	ldr	r6, =(_end - 1)
+
+	/* For XIP, kernel_sec_start/kernel_sec_end are currently in RO memory */
+#ifndef CONFIG_XIP_KERNEL
 	adr_l	r5, kernel_sec_start		@ _pa(kernel_sec_start)
 #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
 	str	r8, [r5, #4]			@ Save physical start of kernel (BE)
 #else
 	str	r8, [r5]			@ Save physical start of kernel (LE)
+#endif
 #endif
 	orr	r3, r8, r7			@ Add the MMU flags
 	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER)
 1:	str	r3, [r0], #1 << PMD_ENTRY_ORDER
 	add	r3, r3, #1 << SECTION_SHIFT
 	cmp	r0, r6
 	bls	1b
+#ifndef CONFIG_XIP_KERNEL
 	eor	r3, r3, r7			@ Remove the MMU flags
 	adr_l	r5, kernel_sec_end		@ _pa(kernel_sec_end)
 #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
 	str	r3, [r5, #4]			@ Save physical end of kernel (BE)
 #else
 	str	r3, [r5]			@ Save physical end of kernel (LE)
 #endif
-
-#ifdef CONFIG_XIP_KERNEL
+#else
 	/*
 	 * Map the kernel image separately as it is not located in RAM.
 	 */

arch/arm/mm/mmu.c

@@ -1401,18 +1401,6 @@ static void __init devicemaps_init(const struct machine_desc *mdesc)
 		create_mapping(&map);
 	}
 
-	/*
-	 * Map the kernel if it is XIP.
-	 * It is always first in the modulearea.
-	 */
-#ifdef CONFIG_XIP_KERNEL
-	map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK);
-	map.virtual = MODULES_VADDR;
-	map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK;
-	map.type = MT_ROM;
-	create_mapping(&map);
-#endif
-
 	/*
 	 * Map the cache flushing regions.
 	 */
@@ -1602,12 +1590,27 @@ static void __init map_kernel(void)
 	 * This will only persist until we turn on proper memory management later on
 	 * and we remap the whole kernel with page granularity.
 	 */
+#ifdef CONFIG_XIP_KERNEL
+	phys_addr_t kernel_nx_start = kernel_sec_start;
+#else
 	phys_addr_t kernel_x_start = kernel_sec_start;
 	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
 	phys_addr_t kernel_nx_start = kernel_x_end;
+#endif
 	phys_addr_t kernel_nx_end = kernel_sec_end;
 	struct map_desc map;
 
+	/*
+	 * Map the kernel if it is XIP.
+	 * It is always first in the modulearea.
+	 */
+#ifdef CONFIG_XIP_KERNEL
+	map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK);
+	map.virtual = MODULES_VADDR;
+	map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK;
+	map.type = MT_ROM;
+	create_mapping(&map);
+#else
 	map.pfn = __phys_to_pfn(kernel_x_start);
 	map.virtual = __phys_to_virt(kernel_x_start);
 	map.length = kernel_x_end - kernel_x_start;
@@ -1617,7 +1620,7 @@ static void __init map_kernel(void)
 	/* If the nx part is small it may end up covered by the tail of the RWX section */
 	if (kernel_x_end == kernel_nx_end)
 		return;
-
+#endif
 	map.pfn = __phys_to_pfn(kernel_nx_start);
 	map.virtual = __phys_to_virt(kernel_nx_start);
 	map.length = kernel_nx_end - kernel_nx_start;
@@ -1762,6 +1765,11 @@ void __init paging_init(const struct machine_desc *mdesc)
 {
 	void *zero_page;
 
+#ifdef CONFIG_XIP_KERNEL
+	/* Store the kernel RW RAM region start/end in these variables */
+	kernel_sec_start = CONFIG_PHYS_OFFSET & SECTION_MASK;
+	kernel_sec_end = round_up(__pa(_end), SECTION_SIZE);
+#endif
 	pr_debug("physical kernel sections: 0x%08llx-0x%08llx\n",
 		 kernel_sec_start, kernel_sec_end);
 

arch/arm64/include/asm/mman.h

@@ -3,6 +3,8 @@
 #define __ASM_MMAN_H__
 
 #include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/shmem_fs.h>
 #include <linux/types.h>
 #include <uapi/asm/mman.h>
 
@@ -21,19 +23,21 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
+						   unsigned long flags)
 {
 	/*
 	 * Only allow MTE on anonymous mappings as these are guaranteed to be
 	 * backed by tags-capable memory. The vm_flags may be overridden by a
 	 * filesystem supporting MTE (RAM-based).
 	 */
-	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+	if (system_supports_mte() &&
+	    ((flags & MAP_ANONYMOUS) || shmem_file(file)))
 		return VM_MTE_ALLOWED;
 
 	return 0;
 }
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
 
 static inline bool arch_validate_prot(unsigned long prot,
 	unsigned long addr __always_unused)

arch/parisc/Kconfig

@@ -18,6 +18,7 @@ config PARISC
 	select ARCH_SUPPORTS_HUGETLBFS if PA20
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_STACKWALK
+	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select HAVE_RELIABLE_STACKTRACE
 	select DMA_OPS

arch/parisc/include/asm/cache.h

@@ -20,7 +20,16 @@
 
 #define SMP_CACHE_BYTES L1_CACHE_BYTES
 
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+#ifdef CONFIG_PA20
+#define ARCH_DMA_MINALIGN	128
+#else
+#define ARCH_DMA_MINALIGN	32
+#endif
+#define ARCH_KMALLOC_MINALIGN	16	/* ldcw requires 16-byte alignment */
+
+#define arch_slab_minalign()	((unsigned)dcache_stride)
+#define cache_line_size()	dcache_stride
+#define dma_get_cache_alignment cache_line_size
 
 #define __read_mostly __section(".data..read_mostly")
 

arch/x86/kvm/lapic.c

@@ -2453,19 +2453,26 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic->apicv_active) {
-		/* irr_pending is always true when apicv is activated. */
-		apic->irr_pending = true;
+	/*
+	 * When APICv is enabled, KVM must always search the IRR for a pending
+	 * IRQ, as other vCPUs and devices can set IRR bits even if the vCPU
+	 * isn't running.  If APICv is disabled, KVM _should_ search the IRR
+	 * for a pending IRQ.  But KVM currently doesn't ensure *all* hardware,
+	 * e.g. CPUs and IOMMUs, has seen the change in state, i.e. searching
+	 * the IRR at this time could race with IRQ delivery from hardware that
+	 * still sees APICv as being enabled.
+	 *
+	 * FIXME: Ensure other vCPUs and devices observe the change in APICv
+	 *        state prior to updating KVM's metadata caches, so that KVM
+	 *        can safely search the IRR and set irr_pending accordingly.
+	 */
+	apic->irr_pending = true;
+
+	if (apic->apicv_active)
 		apic->isr_count = 1;
-	} else {
-		/*
-		 * Don't clear irr_pending, searching the IRR can race with
-		 * updates from the CPU as APICv is still active from hardware's
-		 * perspective.  The flag will be cleared as appropriate when
-		 * KVM injects the interrupt.
-		 */
+	else
 		apic->isr_count = count_vectors(apic->regs + APIC_ISR);
-	}
+
 	apic->highest_isr_cache = -1;
 }
 EXPORT_SYMBOL_GPL(kvm_apic_update_apicv);

arch/x86/kvm/vmx/nested.c

@@ -1126,11 +1126,14 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	/*
-	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
-	 * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
-	 * full TLB flush from the guest's perspective.  This is required even
-	 * if VPID is disabled in the host as KVM may need to synchronize the
-	 * MMU in response to the guest TLB flush.
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host, and so architecturally, linear and combined
+	 * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit.  KVM
+	 * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2,
+	 * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01.  This
+	 * is required if VPID is disabled in KVM, as a TLB flush (there are no
+	 * VPIDs) still occurs from L1's perspective, and KVM may need to
+	 * synchronize the MMU in response to the guest TLB flush.
 	 *
 	 * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use.
 	 * EPT is a special snowflake, as guest-physical mappings aren't
@@ -2196,6 +2199,17 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
 
 	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA);
 
+	/*
+	 * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the
+	 * same VPID as the host.  Emulate this behavior by using vpid01 for L2
+	 * if VPID is disabled in vmcs12.  Note, if VPID is disabled, VM-Enter
+	 * and VM-Exit are architecturally required to flush VPID=0, but *only*
+	 * VPID=0.  I.e. using vpid02 would be ok (so long as KVM emulates the
+	 * required flushes), but doing so would cause KVM to over-flush.  E.g.
+	 * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled,
+	 * and then runs L2 X again, then KVM can and should retain TLB entries
+	 * for VPID12=1.
+	 */
 	if (enable_vpid) {
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
 			vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
@@ -5758,6 +5772,12 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return nested_vmx_fail(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 
+	/*
+	 * Always flush the effective vpid02, i.e. never flush the current VPID
+	 * and never explicitly flush vpid01.  INVVPID targets a VPID, not a
+	 * VMCS, and so whether or not the current vmcs12 has VPID enabled is
+	 * irrelevant (and there may not be a loaded vmcs12).
+	 */
 	vpid02 = nested_get_vpid02(vcpu);
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:

arch/x86/kvm/vmx/vmx.c

@@ -209,9 +209,11 @@ module_param(ple_window_shrink, uint, 0444);
 static unsigned int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
 module_param(ple_window_max, uint, 0444);
 
-/* Default is SYSTEM mode, 1 for host-guest mode */
+/* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */
 int __read_mostly pt_mode = PT_MODE_SYSTEM;
+#ifdef CONFIG_BROKEN
 module_param(pt_mode, int, S_IRUGO);
+#endif
 
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
@@ -3098,7 +3100,7 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 
 static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu))
+	if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu)))
 		return nested_get_vpid02(vcpu);
 	return to_vmx(vcpu)->vpid;
 }

arch/x86/mm/ioremap.c

@@ -650,7 +650,8 @@ static bool memremap_is_setup_data(resource_size_t phys_addr,
 		paddr_next = data->next;
 		len = data->len;
 
-		if ((phys_addr > paddr) && (phys_addr < (paddr + len))) {
+		if ((phys_addr > paddr) &&
+		    (phys_addr < (paddr + sizeof(struct setup_data) + len))) {
 			memunmap(data);
 			return true;
 		}
@@ -712,7 +713,8 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
 		paddr_next = data->next;
 		len = data->len;
 
-		if ((phys_addr > paddr) && (phys_addr < (paddr + len))) {
+		if ((phys_addr > paddr) &&
+		    (phys_addr < (paddr + sizeof(struct setup_data) + len))) {
 			early_memunmap(data, sizeof(*data));
 			return true;
 		}