Merge remote-tracking branch 'stable/linux-6.13.y' into v6.13+

Author: xdevs23

Documentation/admin-guide/sysctl/kernel.rst

@@ -212,6 +212,17 @@ pid>/``).
 This value defaults to 0.
 
 
+core_sort_vma
+=============
+
+The default coredump writes VMAs in address order. By setting
+``core_sort_vma`` to 1, VMAs will be written from smallest size
+to largest size. This is known to break at least elfutils, but
+can be handy when dealing with very large (and truncated)
+coredumps where the more useful debugging details are included
+in the smaller VMAs.
+
+
 core_uses_pid
 =============
 

Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml

@@ -146,6 +146,7 @@ properties:
     maxItems: 2
 
   pwm-names:
+    minItems: 1
     items:
       - const: convst1
       - const: convst2

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 13
-SUBLEVEL = 5
+SUBLEVEL = 7
 EXTRAVERSION =
 NAME = Baby Opossum Posse
 
@@ -1121,6 +1121,11 @@ endif
 KBUILD_USERCFLAGS  += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
+# userspace programs are linked via the compiler, use the correct linker
+ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_LD_IS_LLD),yy)
+KBUILD_USERLDFLAGS += --ld-path=$(LD)
+endif
+
 # make the checker run with the right architecture
 CHECKFLAGS += --arch=$(ARCH)
 

arch/arm/mm/fault-armv.c

@@ -62,7 +62,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
@@ -99,12 +99,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
@@ -114,7 +113,7 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
@@ -123,9 +122,10 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
@@ -141,6 +141,14 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	 */
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
+		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
 		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
@@ -151,7 +159,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
@@ -194,7 +207,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}

arch/arm64/include/asm/hugetlb.h

@@ -42,8 +42,8 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);

arch/arm64/include/asm/kvm_host.h

@@ -1262,7 +1262,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 extern unsigned int __ro_after_init kvm_arm_vmid_bits;
 int __init kvm_arm_vmid_alloc_init(void);
 void __init kvm_arm_vmid_alloc_free(void);
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)

arch/arm64/kvm/arm.c

@@ -580,6 +580,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	mmu = vcpu->arch.hw_mmu;
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
+	/*
+	 * Ensure a VMID is allocated for the MMU before programming VTTBR_EL2,
+	 * which happens eagerly in VHE.
+	 *
+	 * Also, the VMID allocator only preserves VMIDs that are active at the
+	 * time of rollover, so KVM might need to grab a new VMID for the MMU if
+	 * this is called from kvm_sched_in().
+	 */
+	kvm_arm_vmid_update(&mmu->vmid);
+
 	/*
 	 * We guarantee that both TLBs and I-cache are private to each
 	 * vcpu. If detecting that a vcpu from the same VM has
@@ -1147,18 +1157,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
-		/*
-		 * The VMID allocator only tracks active VMIDs per
-		 * physical CPU, and therefore the VMID allocated may not be
-		 * preserved on VMID roll-over if the task was preempted,
-		 * making a thread's VMID inactive. So we need to call
-		 * kvm_arm_vmid_update() in non-premptible context.
-		 */
-		if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
-		    has_vhe())
-			__load_stage2(vcpu->arch.hw_mmu,
-				      vcpu->arch.hw_mmu->arch);
-
 		kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();

arch/arm64/kvm/vmid.c

@@ -135,11 +135,10 @@ void kvm_arm_vmid_clear_active(void)
 	atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
 }
 
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 {
 	unsigned long flags;
 	u64 vmid, old_active_vmid;
-	bool updated = false;
 
 	vmid = atomic64_read(&kvm_vmid->id);
 
@@ -157,21 +156,17 @@ bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 	if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
 	    0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
 					  old_active_vmid, vmid))
-		return false;
+		return;
 
 	raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
 
 	/* Check that our VMID belongs to the current generation. */
 	vmid = atomic64_read(&kvm_vmid->id);
-	if (!vmid_gen_match(vmid)) {
+	if (!vmid_gen_match(vmid))
 		vmid = new_vmid(kvm_vmid);
-		updated = true;
-	}
 
 	atomic64_set(this_cpu_ptr(&active_vmids), vmid);
 	raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
-
-	return updated;
 }
 
 /*

arch/arm64/mm/hugetlbpage.c

@@ -100,20 +100,11 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
-	int contig_ptes = 0;
+	int contig_ptes = 1;
 
 	*pgsize = size;
 
 	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		if (pud_sect_supported())
-			contig_ptes = 1;
-		break;
-#endif
-	case PMD_SIZE:
-		contig_ptes = 1;
-		break;
 	case CONT_PMD_SIZE:
 		*pgsize = PMD_SIZE;
 		contig_ptes = CONT_PMDS;
@@ -122,6 +113,8 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 		*pgsize = PAGE_SIZE;
 		contig_ptes = CONT_PTES;
 		break;
+	default:
+		WARN_ON(!__hugetlb_valid_size(size));
 	}
 
 	return contig_ptes;
@@ -163,24 +156,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = __ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
-
-		/*
-		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty or accessed bit for any page in the set,
-		 * so check them all.
-		 */
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = __ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += pgsize;
+		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -396,18 +388,13 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = __ptep_get(ptep);
-
-	if (!pte_cont(orig_pte))
-		return __ptep_get_and_clear(mm, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
+	ncontig = num_contig_ptes(sz, &pgsize);
 	return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 }
 
@@ -549,6 +536,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
@@ -558,7 +547,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,

arch/arm64/mm/init.c

@@ -279,12 +279,7 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-
-		/*
-		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
-		 * map randomization can be enabled by shrinking the IPA space.
-		 */
-		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -