1 files changed, 318 insertions, 43 deletions

diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 5083c68c3a4e..76f0940fb485 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -18,6 +18,7 @@
 #include <linux/memblock.h>
 #include <linux/notifier.h>
 #include <linux/page-isolation.h>
+#include <linux/vmalloc.h>
 
 #include <asm/early_ioremap.h>
 
@@ -107,6 +108,29 @@ struct kho_serialization {
 	struct khoser_mem_chunk *preserved_mem_map;
 };
 
+struct kho_out {
+	struct blocking_notifier_head chain_head;
+
+	struct dentry *dir;
+
+	struct mutex lock; /* protects KHO FDT finalization */
+
+	struct kho_serialization ser;
+	bool finalized;
+};
+
+static struct kho_out kho_out = {
+	.chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
+	.lock = __MUTEX_INITIALIZER(kho_out.lock),
+	.ser = {
+		.fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list),
+		.track = {
+			.orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
+		},
+	},
+	.finalized = false,
+};
+
 static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz)
 {
 	void *elm, *res;
@@ -165,6 +189,9 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
 
 	might_sleep();
 
+	if (kho_out.finalized)
+		return -EBUSY;
+
 	physxa = xa_load(&track->orders, order);
 	if (!physxa) {
 		int err;
@@ -248,6 +275,37 @@ struct folio *kho_restore_folio(phys_addr_t phys)
 }
 EXPORT_SYMBOL_GPL(kho_restore_folio);
 
+/**
+ * kho_restore_pages - restore list of contiguous order 0 pages.
+ * @phys: physical address of the first page.
+ * @nr_pages: number of pages.
+ *
+ * Restore a contiguous list of order 0 pages that was preserved with
+ * kho_preserve_pages().
+ *
+ * Return: 0 on success, error code on failure
+ */
+struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages)
+{
+	const unsigned long start_pfn = PHYS_PFN(phys);
+	const unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long pfn = start_pfn;
+
+	while (pfn < end_pfn) {
+		const unsigned int order =
+			min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn));
+		struct page *page = kho_restore_page(PFN_PHYS(pfn));
+
+		if (!page)
+			return NULL;
+		split_page(page, order);
+		pfn += 1 << order;
+	}
+
+	return pfn_to_page(start_pfn);
+}
+EXPORT_SYMBOL_GPL(kho_restore_pages);
+
 /* Serialize and deserialize struct kho_mem_phys across kexec
  *
  * Record all the bitmaps in a linked list of pages for the next kernel to
@@ -667,29 +725,6 @@ int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt)
 }
 EXPORT_SYMBOL_GPL(kho_add_subtree);
 
-struct kho_out {
-	struct blocking_notifier_head chain_head;
-
-	struct dentry *dir;
-
-	struct mutex lock; /* protects KHO FDT finalization */
-
-	struct kho_serialization ser;
-	bool finalized;
-};
-
-static struct kho_out kho_out = {
-	.chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
-	.lock = __MUTEX_INITIALIZER(kho_out.lock),
-	.ser = {
-		.fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list),
-		.track = {
-			.orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
-		},
-	},
-	.finalized = false,
-};
-
 int register_kho_notifier(struct notifier_block *nb)
 {
 	return blocking_notifier_chain_register(&kho_out.chain_head, nb);
@@ -717,37 +752,28 @@ int kho_preserve_folio(struct folio *folio)
 	const unsigned int order = folio_order(folio);
 	struct kho_mem_track *track = &kho_out.ser.track;
 
-	if (kho_out.finalized)
-		return -EBUSY;
-
 	return __kho_preserve_order(track, pfn, order);
 }
 EXPORT_SYMBOL_GPL(kho_preserve_folio);
 
 /**
- * kho_preserve_phys - preserve a physically contiguous range across kexec.
- * @phys: physical address of the range.
- * @size: size of the range.
+ * kho_preserve_pages - preserve contiguous pages across kexec
+ * @page: first page in the list.
+ * @nr_pages: number of pages.
  *
- * Instructs KHO to preserve the memory range from @phys to @phys + @size
- * across kexec.
+ * Preserve a contiguous list of order 0 pages. Must be restored using
+ * kho_restore_pages() to ensure the pages are restored properly as order 0.
  *
  * Return: 0 on success, error code on failure
  */
-int kho_preserve_phys(phys_addr_t phys, size_t size)
+int kho_preserve_pages(struct page *page, unsigned int nr_pages)
 {
-	unsigned long pfn = PHYS_PFN(phys);
+	struct kho_mem_track *track = &kho_out.ser.track;
+	const unsigned long start_pfn = page_to_pfn(page);
+	const unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long pfn = start_pfn;
 	unsigned long failed_pfn = 0;
-	const unsigned long start_pfn = pfn;
-	const unsigned long end_pfn = PHYS_PFN(phys + size);
 	int err = 0;
-	struct kho_mem_track *track = &kho_out.ser.track;
-
-	if (kho_out.finalized)
-		return -EBUSY;
-
-	if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
-		return -EINVAL;
 
 	while (pfn < end_pfn) {
 		const unsigned int order =
@@ -767,7 +793,256 @@ int kho_preserve_phys(phys_addr_t phys, size_t size)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(kho_preserve_phys);
+EXPORT_SYMBOL_GPL(kho_preserve_pages);
+
+struct kho_vmalloc_hdr {
+	DECLARE_KHOSER_PTR(next, struct kho_vmalloc_chunk *);
+};
+
+#define KHO_VMALLOC_SIZE				\
+	((PAGE_SIZE - sizeof(struct kho_vmalloc_hdr)) / \
+	 sizeof(phys_addr_t))
+
+struct kho_vmalloc_chunk {
+	struct kho_vmalloc_hdr hdr;
+	phys_addr_t phys[KHO_VMALLOC_SIZE];
+};
+
+static_assert(sizeof(struct kho_vmalloc_chunk) == PAGE_SIZE);
+
+/* vmalloc flags KHO supports */
+#define KHO_VMALLOC_SUPPORTED_FLAGS	(VM_ALLOC | VM_ALLOW_HUGE_VMAP)
+
+/* KHO internal flags for vmalloc preservations */
+#define KHO_VMALLOC_ALLOC	0x0001
+#define KHO_VMALLOC_HUGE_VMAP	0x0002
+
+static unsigned short vmalloc_flags_to_kho(unsigned int vm_flags)
+{
+	unsigned short kho_flags = 0;
+
+	if (vm_flags & VM_ALLOC)
+		kho_flags |= KHO_VMALLOC_ALLOC;
+	if (vm_flags & VM_ALLOW_HUGE_VMAP)
+		kho_flags |= KHO_VMALLOC_HUGE_VMAP;
+
+	return kho_flags;
+}
+
+static unsigned int kho_flags_to_vmalloc(unsigned short kho_flags)
+{
+	unsigned int vm_flags = 0;
+
+	if (kho_flags & KHO_VMALLOC_ALLOC)
+		vm_flags |= VM_ALLOC;
+	if (kho_flags & KHO_VMALLOC_HUGE_VMAP)
+		vm_flags |= VM_ALLOW_HUGE_VMAP;
+
+	return vm_flags;
+}
+
+static struct kho_vmalloc_chunk *new_vmalloc_chunk(struct kho_vmalloc_chunk *cur)
+{
+	struct kho_vmalloc_chunk *chunk;
+	int err;
+
+	chunk = (struct kho_vmalloc_chunk *)get_zeroed_page(GFP_KERNEL);
+	if (!chunk)
+		return NULL;
+
+	err = kho_preserve_pages(virt_to_page(chunk), 1);
+	if (err)
+		goto err_free;
+	if (cur)
+		KHOSER_STORE_PTR(cur->hdr.next, chunk);
+	return chunk;
+
+err_free:
+	free_page((unsigned long)chunk);
+	return NULL;
+}
+
+static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk)
+{
+	struct kho_mem_track *track = &kho_out.ser.track;
+	unsigned long pfn = PHYS_PFN(virt_to_phys(chunk));
+
+	__kho_unpreserve(track, pfn, pfn + 1);
+
+	for (int i = 0; chunk->phys[i]; i++) {
+		pfn = PHYS_PFN(chunk->phys[i]);
+		__kho_unpreserve(track, pfn, pfn + 1);
+	}
+}
+
+static void kho_vmalloc_free_chunks(struct kho_vmalloc *kho_vmalloc)
+{
+	struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(kho_vmalloc->first);
+
+	while (chunk) {
+		struct kho_vmalloc_chunk *tmp = chunk;
+
+		kho_vmalloc_unpreserve_chunk(chunk);
+
+		chunk = KHOSER_LOAD_PTR(chunk->hdr.next);
+		free_page((unsigned long)tmp);
+	}
+}
+
+/**
+ * kho_preserve_vmalloc - preserve memory allocated with vmalloc() across kexec
+ * @ptr: pointer to the area in vmalloc address space
+ * @preservation: placeholder for preservation metadata
+ *
+ * Instructs KHO to preserve the area in vmalloc address space at @ptr. The
+ * physical pages mapped at @ptr will be preserved and on successful return
+ * @preservation will hold the physical address of a structure that describes
+ * the preservation.
+ *
+ * NOTE: The memory allocated with vmalloc_node() variants cannot be reliably
+ * restored on the same node
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation)
+{
+	struct kho_vmalloc_chunk *chunk;
+	struct vm_struct *vm = find_vm_area(ptr);
+	unsigned int order, flags, nr_contig_pages;
+	unsigned int idx = 0;
+	int err;
+
+	if (!vm)
+		return -EINVAL;
+
+	if (vm->flags & ~KHO_VMALLOC_SUPPORTED_FLAGS)
+		return -EOPNOTSUPP;
+
+	flags = vmalloc_flags_to_kho(vm->flags);
+	order = get_vm_area_page_order(vm);
+
+	chunk = new_vmalloc_chunk(NULL);
+	if (!chunk)
+		return -ENOMEM;
+	KHOSER_STORE_PTR(preservation->first, chunk);
+
+	nr_contig_pages = (1 << order);
+	for (int i = 0; i < vm->nr_pages; i += nr_contig_pages) {
+		phys_addr_t phys = page_to_phys(vm->pages[i]);
+
+		err = kho_preserve_pages(vm->pages[i], nr_contig_pages);
+		if (err)
+			goto err_free;
+
+		chunk->phys[idx++] = phys;
+		if (idx == ARRAY_SIZE(chunk->phys)) {
+			chunk = new_vmalloc_chunk(chunk);
+			if (!chunk)
+				goto err_free;
+			idx = 0;
+		}
+	}
+
+	preservation->total_pages = vm->nr_pages;
+	preservation->flags = flags;
+	preservation->order = order;
+
+	return 0;
+
+err_free:
+	kho_vmalloc_free_chunks(preservation);
+	return err;
+}
+EXPORT_SYMBOL_GPL(kho_preserve_vmalloc);
+
+/**
+ * kho_restore_vmalloc - recreates and populates an area in vmalloc address
+ * space from the preserved memory.
+ * @preservation: preservation metadata.
+ *
+ * Recreates an area in vmalloc address space and populates it with memory that
+ * was preserved using kho_preserve_vmalloc().
+ *
+ * Return: pointer to the area in the vmalloc address space, NULL on failure.
+ */
+void *kho_restore_vmalloc(const struct kho_vmalloc *preservation)
+{
+	struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(preservation->first);
+	unsigned int align, order, shift, vm_flags;
+	unsigned long total_pages, contig_pages;
+	unsigned long addr, size;
+	struct vm_struct *area;
+	struct page **pages;
+	unsigned int idx = 0;
+	int err;
+
+	vm_flags = kho_flags_to_vmalloc(preservation->flags);
+	if (vm_flags & ~KHO_VMALLOC_SUPPORTED_FLAGS)
+		return NULL;
+
+	total_pages = preservation->total_pages;
+	pages = kvmalloc_array(total_pages, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+	order = preservation->order;
+	contig_pages = (1 << order);
+	shift = PAGE_SHIFT + order;
+	align = 1 << shift;
+
+	while (chunk) {
+		struct page *page;
+
+		for (int i = 0; chunk->phys[i]; i++) {
+			phys_addr_t phys = chunk->phys[i];
+
+			if (idx + contig_pages > total_pages)
+				goto err_free_pages_array;
+
+			page = kho_restore_pages(phys, contig_pages);
+			if (!page)
+				goto err_free_pages_array;
+
+			for (int j = 0; j < contig_pages; j++)
+				pages[idx++] = page;
+
+			phys += contig_pages * PAGE_SIZE;
+		}
+
+		page = kho_restore_pages(virt_to_phys(chunk), 1);
+		if (!page)
+			goto err_free_pages_array;
+		chunk = KHOSER_LOAD_PTR(chunk->hdr.next);
+		__free_page(page);
+	}
+
+	if (idx != total_pages)
+		goto err_free_pages_array;
+
+	area = __get_vm_area_node(total_pages * PAGE_SIZE, align, shift,
+				  vm_flags, VMALLOC_START, VMALLOC_END,
+				  NUMA_NO_NODE, GFP_KERNEL,
+				  __builtin_return_address(0));
+	if (!area)
+		goto err_free_pages_array;
+
+	addr = (unsigned long)area->addr;
+	size = get_vm_area_size(area);
+	err = vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, shift);
+	if (err)
+		goto err_free_vm_area;
+
+	area->nr_pages = total_pages;
+	area->pages = pages;
+
+	return area->addr;
+
+err_free_vm_area:
+	free_vm_area(area);
+err_free_pages_array:
+	kvfree(pages);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(kho_restore_vmalloc);
 
 /* Handling for debug/kho/out */