Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 13efc29..fc48298 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -157,10 +157,9 @@
 static unsigned long long kvm_createvm_count;
 static unsigned long long kvm_active_vms;
 
-__weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end, bool blockable)
+__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+						   unsigned long start, unsigned long end)
 {
-	return 0;
 }
 
 bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
@@ -186,6 +185,7 @@
 	 */
 	if (pfn_valid(pfn))
 		return PageReserved(pfn_to_page(pfn)) &&
+		       !is_zero_pfn(pfn) &&
 		       !kvm_is_zone_device_pfn(pfn);
 
 	return true;
@@ -381,6 +381,18 @@
 	return container_of(mn, struct kvm, mmu_notifier);
 }
 
+static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
+					      struct mm_struct *mm,
+					      unsigned long start, unsigned long end)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	kvm_arch_mmu_notifier_invalidate_range(kvm, start, end);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					struct mm_struct *mm,
 					unsigned long address,
@@ -405,7 +417,6 @@
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
 	int need_tlb_flush = 0, idx;
-	int ret;
 
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
@@ -415,21 +426,16 @@
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_notifier_count++;
-	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end);
-	need_tlb_flush |= kvm->tlbs_dirty;
+	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
+					     range->flags);
 	/* we've to flush the tlb before the pages can be freed */
-	if (need_tlb_flush)
+	if (need_tlb_flush || kvm->tlbs_dirty)
 		kvm_flush_remote_tlbs(kvm);
 
 	spin_unlock(&kvm->mmu_lock);
-
-	ret = kvm_arch_mmu_notifier_invalidate_range(kvm, range->start,
-					range->end,
-					mmu_notifier_range_blockable(range));
-
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	return ret;
+	return 0;
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -535,6 +541,7 @@
 }
 
 static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
+	.invalidate_range	= kvm_mmu_notifier_invalidate_range,
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
@@ -628,6 +635,8 @@
 
 static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 {
+	static DEFINE_MUTEX(kvm_debugfs_lock);
+	struct dentry *dent;
 	char dir_name[ITOA_MAX_LEN * 2];
 	struct kvm_stat_data *stat_data;
 	struct kvm_stats_debugfs_item *p;
@@ -636,8 +645,20 @@
 		return 0;
 
 	snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
-	kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir);
+	mutex_lock(&kvm_debugfs_lock);
+	dent = debugfs_lookup(dir_name, kvm_debugfs_dir);
+	if (dent) {
+		pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name);
+		dput(dent);
+		mutex_unlock(&kvm_debugfs_lock);
+		return 0;
+	}
+	dent = debugfs_create_dir(dir_name, kvm_debugfs_dir);
+	mutex_unlock(&kvm_debugfs_lock);
+	if (IS_ERR(dent))
+		return 0;
 
+	kvm->debugfs_dentry = dent;
 	kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
 					 sizeof(*kvm->debugfs_stat_data),
 					 GFP_KERNEL_ACCOUNT);
@@ -1010,6 +1031,7 @@
 	/* We can read the guest memory with __xxx_user() later on. */
 	if ((id < KVM_USER_MEM_SLOTS) &&
 	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
+	     (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size)))
 		goto out;
@@ -1394,14 +1416,14 @@
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, size;
 
 	size = PAGE_SIZE;
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return PAGE_SIZE;
 
@@ -1585,15 +1607,24 @@
 	return true;
 }
 
+static int kvm_try_get_pfn(kvm_pfn_t pfn)
+{
+	if (kvm_is_reserved_pfn(pfn))
+		return 1;
+	return get_page_unless_zero(pfn_to_page(pfn));
+}
+
 static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 			       unsigned long addr, bool *async,
 			       bool write_fault, bool *writable,
 			       kvm_pfn_t *p_pfn)
 {
-	unsigned long pfn;
+	kvm_pfn_t pfn;
+	pte_t *ptep;
+	spinlock_t *ptl;
 	int r;
 
-	r = follow_pfn(vma, addr, &pfn);
+	r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
 	if (r) {
 		/*
 		 * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
@@ -1608,14 +1639,19 @@
 		if (r)
 			return r;
 
-		r = follow_pfn(vma, addr, &pfn);
+		r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
 		if (r)
 			return r;
+	}
 
+	if (write_fault && !pte_write(*ptep)) {
+		pfn = KVM_PFN_ERR_RO_FAULT;
+		goto out;
 	}
 
 	if (writable)
-		*writable = true;
+		*writable = pte_write(*ptep);
+	pfn = pte_pfn(*ptep);
 
 	/*
 	 * Get a reference here because callers of *hva_to_pfn* and
@@ -1627,11 +1663,21 @@
 	 * Whoever called remap_pfn_range is also going to call e.g.
 	 * unmap_mapping_range before the underlying pages are freed,
 	 * causing a call to our MMU notifier.
+	 *
+	 * Certain IO or PFNMAP mappings can be backed with valid
+	 * struct pages, but be allocated without refcounting e.g.,
+	 * tail pages of non-compound higher order allocations, which
+	 * would then underflow the refcount when the caller does the
+	 * required put_page. Don't allow those pages here.
 	 */ 
-	kvm_get_pfn(pfn);
+	if (!kvm_try_get_pfn(pfn))
+		r = -EFAULT;
 
+out:
+	pte_unmap_unlock(ptep, ptl);
 	*p_pfn = pfn;
-	return 0;
+
+	return r;
 }
 
 /*
@@ -1809,26 +1855,72 @@
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
-static int __kvm_map_gfn(struct kvm_memory_slot *slot, gfn_t gfn,
-			 struct kvm_host_map *map)
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+{
+	if (pfn == 0)
+		return;
+
+	if (cache)
+		cache->pfn = cache->gfn = 0;
+
+	if (dirty)
+		kvm_release_pfn_dirty(pfn);
+	else
+		kvm_release_pfn_clean(pfn);
+}
+
+static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
+				 struct gfn_to_pfn_cache *cache, u64 gen)
+{
+	kvm_release_pfn(cache->pfn, cache->dirty, cache);
+
+	cache->pfn = gfn_to_pfn_memslot(slot, gfn);
+	cache->gfn = gfn;
+	cache->dirty = false;
+	cache->generation = gen;
+}
+
+static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
+			 struct kvm_host_map *map,
+			 struct gfn_to_pfn_cache *cache,
+			 bool atomic)
 {
 	kvm_pfn_t pfn;
 	void *hva = NULL;
 	struct page *page = KVM_UNMAPPED_PAGE;
+	struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
+	u64 gen = slots->generation;
 
 	if (!map)
 		return -EINVAL;
 
-	pfn = gfn_to_pfn_memslot(slot, gfn);
+	if (cache) {
+		if (!cache->pfn || cache->gfn != gfn ||
+			cache->generation != gen) {
+			if (atomic)
+				return -EAGAIN;
+			kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
+		}
+		pfn = cache->pfn;
+	} else {
+		if (atomic)
+			return -EAGAIN;
+		pfn = gfn_to_pfn_memslot(slot, gfn);
+	}
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
 
 	if (pfn_valid(pfn)) {
 		page = pfn_to_page(pfn);
-		hva = kmap(page);
+		if (atomic)
+			hva = kmap_atomic(page);
+		else
+			hva = kmap(page);
 #ifdef CONFIG_HAS_IOMEM
-	} else {
+	} else if (!atomic) {
 		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+	} else {
+		return -EINVAL;
 #endif
 	}
 
@@ -1843,14 +1935,25 @@
 	return 0;
 }
 
+int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
+		struct gfn_to_pfn_cache *cache, bool atomic)
+{
+	return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
+			cache, atomic);
+}
+EXPORT_SYMBOL_GPL(kvm_map_gfn);
+
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 {
-	return __kvm_map_gfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, map);
+	return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
+		NULL, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
-		    bool dirty)
+static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
+			struct kvm_host_map *map,
+			struct gfn_to_pfn_cache *cache,
+			bool dirty, bool atomic)
 {
 	if (!map)
 		return;
@@ -1858,23 +1961,45 @@
 	if (!map->hva)
 		return;
 
-	if (map->page != KVM_UNMAPPED_PAGE)
-		kunmap(map->page);
+	if (map->page != KVM_UNMAPPED_PAGE) {
+		if (atomic)
+			kunmap_atomic(map->hva);
+		else
+			kunmap(map->page);
+	}
 #ifdef CONFIG_HAS_IOMEM
-	else
+	else if (!atomic)
 		memunmap(map->hva);
+	else
+		WARN_ONCE(1, "Unexpected unmapping in atomic context");
 #endif
 
-	if (dirty) {
-		kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
-		kvm_release_pfn_dirty(map->pfn);
-	} else {
-		kvm_release_pfn_clean(map->pfn);
-	}
+	if (dirty)
+		mark_page_dirty_in_slot(memslot, map->gfn);
+
+	if (cache)
+		cache->dirty |= dirty;
+	else
+		kvm_release_pfn(map->pfn, dirty, NULL);
 
 	map->hva = NULL;
 	map->page = NULL;
 }
+
+int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
+		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
+{
+	__kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map,
+			cache, dirty, atomic);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
+
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
+{
+	__kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL,
+			dirty, false);
+}
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
@@ -2196,12 +2321,12 @@
 	if (slots->generation != ghc->generation)
 		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
 
-	if (unlikely(!ghc->memslot))
-		return kvm_write_guest(kvm, gpa, data, len);
-
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
+	if (unlikely(!ghc->memslot))
+		return kvm_write_guest(kvm, gpa, data, len);
+
 	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
@@ -2229,12 +2354,12 @@
 	if (slots->generation != ghc->generation)
 		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
 
-	if (unlikely(!ghc->memslot))
-		return kvm_read_guest(kvm, ghc->gpa, data, len);
-
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
+	if (unlikely(!ghc->memslot))
+		return kvm_read_guest(kvm, ghc->gpa, data, len);
+
 	r = __copy_from_user(data, (void __user *)ghc->hva, len);
 	if (r)
 		return -EFAULT;
@@ -3459,6 +3584,16 @@
 	};
 };
 
+struct compat_kvm_clear_dirty_log {
+	__u32 slot;
+	__u32 num_pages;
+	__u64 first_page;
+	union {
+		compat_uptr_t dirty_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
 static long kvm_vm_compat_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -3468,6 +3603,24 @@
 	if (kvm->mm != current->mm)
 		return -EIO;
 	switch (ioctl) {
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+	case KVM_CLEAR_DIRTY_LOG: {
+		struct compat_kvm_clear_dirty_log compat_log;
+		struct kvm_clear_dirty_log log;
+
+		if (copy_from_user(&compat_log, (void __user *)arg,
+				   sizeof(compat_log)))
+			return -EFAULT;
+		log.slot	 = compat_log.slot;
+		log.num_pages	 = compat_log.num_pages;
+		log.first_page	 = compat_log.first_page;
+		log.padding2	 = compat_log.padding2;
+		log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
+
+		r = kvm_vm_ioctl_clear_dirty_log(kvm, &log);
+		break;
+	}
+#endif
 	case KVM_GET_DIRTY_LOG: {
 		struct compat_kvm_dirty_log compat_log;
 		struct kvm_dirty_log log;
@@ -3921,15 +4074,15 @@
 }
 
 /* Caller must hold slots_lock. */
-void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			       struct kvm_io_device *dev)
+int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+			      struct kvm_io_device *dev)
 {
-	int i;
+	int i, j;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
-		return;
+		return 0;
 
 	for (i = 0; i < bus->dev_count; i++)
 		if (bus->range[i].dev == dev) {
@@ -3937,25 +4090,28 @@
 		}
 
 	if (i == bus->dev_count)
-		return;
+		return 0;
 
 	new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
 			  GFP_KERNEL_ACCOUNT);
-	if (!new_bus)  {
+	if (new_bus) {
+		memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+		new_bus->dev_count--;
+		memcpy(new_bus->range + i, bus->range + i + 1,
+		       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
+	} else {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		goto broken;
+		for (j = 0; j < bus->dev_count; j++) {
+			if (j == i)
+				continue;
+			kvm_iodevice_destructor(bus->range[j].dev);
+		}
 	}
 
-	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
-	new_bus->dev_count--;
-	memcpy(new_bus->range + i, bus->range + i + 1,
-	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
-
-broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);
-	return;
+	return new_bus ? 0 : -ENOMEM;
 }
 
 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
@@ -4225,7 +4381,7 @@
 	}
 	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
-	if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) {
+	if (kvm->debugfs_dentry) {
 		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
 
 		if (p) {