[PATCH v2 bpf-next 3/3] mm: Introduce VM_SPARSE kind and vm_area_[un]map_pages().

[Alexei Starovoitov <alexei.starovoitov@xxxxxxxxx>]

From: Alexei Starovoitov <ast@xxxxxxxxxx>

vmap/vmalloc APIs are used to map a set of pages into contiguous kernel virtual 
space.

get_vm_area() with appropriate flag is used to request an area of kernel 
address range.
It'se used for vmalloc, vmap, ioremap, xen use cases.
- vmalloc use case dominates the usage. Such vm areas have VM_ALLOC flag.
- the areas created by vmap() function should be tagged with VM_MAP.
- ioremap areas are tagged with VM_IOREMAP.
- xen use cases are VM_XEN.

BPF would like to extend the vmap API to implement a lazily-populated
sparse, yet contiguous kernel virtual space.
Introduce VM_SPARSE vm_area flag and
vm_area_map_pages(area, start_addr, count, pages) API to map a set
of pages within a given area.
It has the same sanity checks as vmap() does.
It also checks that get_vm_area() was created with VM_SPARSE flag
which identifies such areas in /proc/vmallocinfo
and returns zero pages on read through /proc/kcore.

The next commits will introduce bpf_arena which is a sparsely populated shared
memory region between bpf program and user space process. It will map
privately-managed pages into a sparse vm area with the following steps:

  area = get_vm_area(area_size, VM_SPARSE);  // at bpf prog verification time
  vm_area_map_pages(area, kaddr, 1, page);   // on demand
                    // it will return an error if kaddr is out of range
  vm_area_unmap_pages(area, kaddr, 1);
  free_vm_area(area);                        // after bpf prog is unloaded

Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx>
---
 include/linux/vmalloc.h |  4 +++
 mm/vmalloc.c            | 55 +++++++++++++++++++++++++++++++++++++++--
 2 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 223e51c243bc..416bc7b0b4db 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -29,6 +29,7 @@ struct iov_iter;              /* in uio.h */
 #define VM_MAP_PUT_PAGES       0x00000200      /* put pages and free array in 
vfree */
 #define VM_ALLOW_HUGE_VMAP     0x00000400      /* Allow for huge pages on 
archs with HAVE_ARCH_HUGE_VMALLOC */
 #define VM_XEN                 0x00000800      /* xen use cases */
+#define VM_SPARSE              0x00001000      /* sparse vm_area. not all 
pages are present. */
 
 #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
        !defined(CONFIG_KASAN_VMALLOC)
@@ -233,6 +234,9 @@ static inline bool is_vm_area_hugepages(const void *addr)
 }
 
 #ifdef CONFIG_MMU
+int vm_area_map_pages(struct vm_struct *area, unsigned long addr, unsigned int 
count,
+                     struct page **pages);
+int vm_area_unmap_pages(struct vm_struct *area, unsigned long addr, unsigned 
int count);
 void vunmap_range(unsigned long addr, unsigned long end);
 static inline void set_vm_flush_reset_perms(void *addr)
 {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d769a65bddad..a05dfbbacb78 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -648,6 +648,54 @@ static int vmap_pages_range(unsigned long addr, unsigned 
long end,
        return err;
 }
 
+/**
+ * vm_area_map_pages - map pages inside given vm_area
+ * @area: vm_area
+ * @addr: start address inside vm_area
+ * @count: number of pages
+ * @pages: pages to map (always PAGE_SIZE pages)
+ */
+int vm_area_map_pages(struct vm_struct *area, unsigned long addr, unsigned int 
count,
+                     struct page **pages)
+{
+       unsigned long size = ((unsigned long)count) * PAGE_SIZE;
+       unsigned long end = addr + size;
+
+       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 (count > totalram_pages())
+               return -E2BIG;
+       if (addr < (unsigned long)area->addr || (void *)end > area->addr + 
area->size)
+               return -ERANGE;
+
+       return vmap_pages_range(addr, end, PAGE_KERNEL, pages, PAGE_SHIFT);
+}
+
+/**
+ * vm_area_unmap_pages - unmap pages inside given vm_area
+ * @area: vm_area
+ * @addr: start address inside vm_area
+ * @count: number of pages to unmap
+ */
+int vm_area_unmap_pages(struct vm_struct *area, unsigned long addr, unsigned 
int count)
+{
+       unsigned long size = ((unsigned long)count) * PAGE_SIZE;
+       unsigned long end = addr + size;
+
+       if (WARN_ON_ONCE(!(area->flags & VM_SPARSE)))
+               return -EINVAL;
+       if (addr < (unsigned long)area->addr || (void *)end > area->addr + 
area->size)
+               return -ERANGE;
+
+       vunmap_range(addr, end);
+       return 0;
+}
+
 int is_vmalloc_or_module_addr(const void *x)
 {
        /*
@@ -3822,9 +3870,9 @@ 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 | VM_XEN))))
+               else if (!(vm && (vm->flags & (VM_IOREMAP | VM_XEN | 
VM_SPARSE))))
                        copied = aligned_vread_iter(iter, addr, n);
-               else /* IOREMAP|XEN area is treated as memory hole */
+               else /* IOREMAP|XEN|SPARSE area is treated as memory hole */
                        copied = zero_iter(iter, n);
 
                addr += copied;
@@ -4418,6 +4466,9 @@ static int s_show(struct seq_file *m, void *p)
        if (v->flags & VM_XEN)
                seq_puts(m, " xen");
 
+       if (v->flags & VM_SPARSE)
+               seq_puts(m, " sparse");
+
        if (v->flags & VM_ALLOC)
                seq_puts(m, " vmalloc");
 
-- 
2.34.1