Merge branch 'mm-enforce-ioremap-address-space-and-introduce-sparse-vm_area'

Alexei Starovoitov says:

====================
mm: Enforce ioremap address space and introduce sparse vm_area

From: Alexei Starovoitov <ast@kernel.org>

v3 -> v4
- dropped VM_XEN patch for now. It will be in the follow up.
- fixed constant as pointed out by Mike

v2 -> v3
- added Christoph's reviewed-by to patch 1
- cap commit log lines to 75 chars
- factored out common checks in patch 3 into helper
- made vm_area_unmap_pages() return void

There are various users of kernel virtual address space:
vmalloc, vmap, ioremap, xen.

- vmalloc use case dominates the usage. Such vm areas have VM_ALLOC flag
and these areas are treated differently by KASAN.

- the areas created by vmap() function should be tagged with VM_MAP
(as majority of the users do).

- ioremap areas are tagged with VM_IOREMAP and vm area start is aligned
to size of the area unlike vmalloc/vmap.

- there is also xen usage that is marked as VM_IOREMAP, but it doesn't
call ioremap_page_range() unlike all other VM_IOREMAP users.

To clean this up a bit, enforce that ioremap_page_range() checks the range
and VM_IOREMAP flag.

In addition BPF would like to reserve regions of kernel virtual address
space and populate it lazily, similar to xen use cases.
For that reason, introduce VM_SPARSE flag and vm_area_[un]map_pages()
helpers to populate this sparse area.

In the end the /proc/vmallocinfo will show
"vmalloc"
"vmap"
"ioremap"
"sparse"
categories for different kinds of address regions.

ioremap, sparse will return zero when dumped through /proc/kcore
====================

Link: https://lore.kernel.org/r/20240305030516.41519-1-alexei.starovoitov@gmail.comSigned-off-by: Andrii Nakryiko <andrii@kernel.org>

include/linux/vmalloc.h

@@ -35,6 +35,7 @@ struct iov_iter;		/* in uio.h */
 #else
 #define VM_DEFER_KMEMLEAK	0
 #endif
+#define VM_SPARSE		0x00001000	/* sparse vm_area. not all pages are present. */
 
 /* bits [20..32] reserved for arch specific ioremap internals */
 
@@ -232,6 +233,10 @@ static inline bool is_vm_area_hugepages(const void *addr)
 }
 
 #ifdef CONFIG_MMU
+int vm_area_map_pages(struct vm_struct *area, unsigned long start,
+		      unsigned long end, struct page **pages);
+void vm_area_unmap_pages(struct vm_struct *area, unsigned long start,
+			 unsigned long end);
 void vunmap_range(unsigned long addr, unsigned long end);
 static inline void set_vm_flush_reset_perms(void *addr)
 {

mm/vmalloc.c

@@ -307,8 +307,21 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end,
 int ioremap_page_range(unsigned long addr, unsigned long end,
 		phys_addr_t phys_addr, pgprot_t prot)
 {
+	struct vm_struct *area;
 	int err;
 
+	area = find_vm_area((void *)addr);
+	if (!area || !(area->flags & VM_IOREMAP)) {
+		WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr);
+		return -EINVAL;
+	}
+	if (addr != (unsigned long)area->addr ||
+	    (void *)end != area->addr + get_vm_area_size(area)) {
+		WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n",
+			  addr, end, (long)area->addr,
+			  (long)area->addr + get_vm_area_size(area));
+		return -ERANGE;
+	}
 	err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot),
 				 ioremap_max_page_shift);
 	flush_cache_vmap(addr, end);
@@ -635,6 +648,58 @@ static int vmap_pages_range(unsigned long addr, unsigned long end,
 	return err;
 }
 
+static int check_sparse_vm_area(struct vm_struct *area, unsigned long start,
+				unsigned long end)
+{
+	might_sleep();
+	if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS))
+		return -EINVAL;
+	if (WARN_ON_ONCE(area->flags & VM_NO_GUARD))
+		return -EINVAL;
+	if (WARN_ON_ONCE(!(area->flags & VM_SPARSE)))
+		return -EINVAL;
+	if ((end - start) >> PAGE_SHIFT > totalram_pages())
+		return -E2BIG;
+	if (start < (unsigned long)area->addr ||
+	    (void *)end > area->addr + get_vm_area_size(area))
+		return -ERANGE;
+	return 0;
+}
+
+/**
+ * vm_area_map_pages - map pages inside given sparse vm_area
+ * @area: vm_area
+ * @start: start address inside vm_area
+ * @end: end address inside vm_area
+ * @pages: pages to map (always PAGE_SIZE pages)
+ */
+int vm_area_map_pages(struct vm_struct *area, unsigned long start,
+		      unsigned long end, struct page **pages)
+{
+	int err;
+
+	err = check_sparse_vm_area(area, start, end);
+	if (err)
+		return err;
+
+	return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT);
+}
+
+/**
+ * vm_area_unmap_pages - unmap pages inside given sparse vm_area
+ * @area: vm_area
+ * @start: start address inside vm_area
+ * @end: end address inside vm_area
+ */
+void vm_area_unmap_pages(struct vm_struct *area, unsigned long start,
+			 unsigned long end)
+{
+	if (check_sparse_vm_area(area, start, end))
+		return;
+
+	vunmap_range(start, end);
+}
+
 int is_vmalloc_or_module_addr(const void *x)
 {
 	/*
@@ -3809,9 +3874,9 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 
 		if (flags & VMAP_RAM)
 			copied = vmap_ram_vread_iter(iter, addr, n, flags);
-		else if (!(vm && (vm->flags & VM_IOREMAP)))
+		else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE))))
 			copied = aligned_vread_iter(iter, addr, n);
-		else /* IOREMAP area is treated as memory hole */
+		else /* IOREMAP | SPARSE area is treated as memory hole */
 			copied = zero_iter(iter, n);
 
 		addr += copied;
@@ -4402,6 +4467,9 @@ static int s_show(struct seq_file *m, void *p)
 	if (v->flags & VM_IOREMAP)
 		seq_puts(m, " ioremap");
 
+	if (v->flags & VM_SPARSE)
+		seq_puts(m, " sparse");
+
 	if (v->flags & VM_ALLOC)
 		seq_puts(m, " vmalloc");