summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/verity/fsverity_private.h5
-rw-r--r--fs/verity/open.c80
-rw-r--r--fs/verity/verify.c309
3 files changed, 296 insertions, 98 deletions
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index 23ded939d649..d34dcc033d72 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -42,9 +42,11 @@ struct merkle_tree_params {
unsigned int digest_size; /* same as hash_alg->digest_size */
unsigned int block_size; /* size of data and tree blocks */
unsigned int hashes_per_block; /* number of hashes per tree block */
+ unsigned int blocks_per_page; /* PAGE_SIZE / block_size */
u8 log_digestsize; /* log2(digest_size) */
u8 log_blocksize; /* log2(block_size) */
u8 log_arity; /* log2(hashes_per_block) */
+ u8 log_blocks_per_page; /* log2(blocks_per_page) */
unsigned int num_levels; /* number of levels in Merkle tree */
u64 tree_size; /* Merkle tree size in bytes */
unsigned long tree_pages; /* Merkle tree size in pages */
@@ -70,9 +72,10 @@ struct fsverity_info {
u8 root_hash[FS_VERITY_MAX_DIGEST_SIZE];
u8 file_digest[FS_VERITY_MAX_DIGEST_SIZE];
const struct inode *inode;
+ unsigned long *hash_block_verified;
+ spinlock_t hash_page_init_lock;
};
-
#define FS_VERITY_MAX_SIGNATURE_SIZE (FS_VERITY_MAX_DESCRIPTOR_SIZE - \
sizeof(struct fsverity_descriptor))
diff --git a/fs/verity/open.c b/fs/verity/open.c
index 09512daa22db..9366b441d01c 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -56,7 +56,23 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
goto out_err;
}
- if (log_blocksize != PAGE_SHIFT) {
+ /*
+ * fs/verity/ directly assumes that the Merkle tree block size is a
+ * power of 2 less than or equal to PAGE_SIZE. Another restriction
+ * arises from the interaction between fs/verity/ and the filesystems
+ * themselves: filesystems expect to be able to verify a single
+ * filesystem block of data at a time. Therefore, the Merkle tree block
+ * size must also be less than or equal to the filesystem block size.
+ *
+ * The above are the only hard limitations, so in theory the Merkle tree
+ * block size could be as small as twice the digest size. However,
+ * that's not useful, and it would result in some unusually deep and
+ * large Merkle trees. So we currently require that the Merkle tree
+ * block size be at least 1024 bytes. That's small enough to test the
+ * sub-page block case on systems with 4K pages, but not too small.
+ */
+ if (log_blocksize < 10 || log_blocksize > PAGE_SHIFT ||
+ log_blocksize > inode->i_blkbits) {
fsverity_warn(inode, "Unsupported log_blocksize: %u",
log_blocksize);
err = -EINVAL;
@@ -64,6 +80,8 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
}
params->log_blocksize = log_blocksize;
params->block_size = 1 << log_blocksize;
+ params->log_blocks_per_page = PAGE_SHIFT - log_blocksize;
+ params->blocks_per_page = 1 << params->log_blocks_per_page;
if (WARN_ON(!is_power_of_2(params->digest_size))) {
err = -EINVAL;
@@ -108,11 +126,19 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
}
/*
- * Since the data, and thus also the Merkle tree, cannot have more than
- * ULONG_MAX pages, hash block indices can always fit in an
- * 'unsigned long'. To be safe, explicitly check for it too.
+ * With block_size != PAGE_SIZE, an in-memory bitmap will need to be
+ * allocated to track the "verified" status of hash blocks. Don't allow
+ * this bitmap to get too large. For now, limit it to 1 MiB, which
+ * limits the file size to about 4.4 TB with SHA-256 and 4K blocks.
+ *
+ * Together with the fact that the data, and thus also the Merkle tree,
+ * cannot have more than ULONG_MAX pages, this implies that hash block
+ * indices can always fit in an 'unsigned long'. But to be safe, we
+ * explicitly check for that too. Note, this is only for hash block
+ * indices; data block indices might not fit in an 'unsigned long'.
*/
- if (offset > ULONG_MAX) {
+ if ((params->block_size != PAGE_SIZE && offset > 1 << 23) ||
+ offset > ULONG_MAX) {
fsverity_err(inode, "Too many blocks in Merkle tree");
err = -EFBIG;
goto out_err;
@@ -170,7 +196,7 @@ struct fsverity_info *fsverity_create_info(const struct inode *inode,
fsverity_err(inode,
"Error %d initializing Merkle tree parameters",
err);
- goto out;
+ goto fail;
}
memcpy(vi->root_hash, desc->root_hash, vi->tree_params.digest_size);
@@ -179,17 +205,48 @@ struct fsverity_info *fsverity_create_info(const struct inode *inode,
vi->file_digest);
if (err) {
fsverity_err(inode, "Error %d computing file digest", err);
- goto out;
+ goto fail;
}
err = fsverity_verify_signature(vi, desc->signature,
le32_to_cpu(desc->sig_size));
-out:
- if (err) {
- fsverity_free_info(vi);
- vi = ERR_PTR(err);
+ if (err)
+ goto fail;
+
+ if (vi->tree_params.block_size != PAGE_SIZE) {
+ /*
+ * When the Merkle tree block size and page size differ, we use
+ * a bitmap to keep track of which hash blocks have been
+ * verified. This bitmap must contain one bit per hash block,
+ * including alignment to a page boundary at the end.
+ *
+ * Eventually, to support extremely large files in an efficient
+ * way, it might be necessary to make pages of this bitmap
+ * reclaimable. But for now, simply allocating the whole bitmap
+ * is a simple solution that works well on the files on which
+ * fsverity is realistically used. E.g., with SHA-256 and 4K
+ * blocks, a 100MB file only needs a 24-byte bitmap, and the
+ * bitmap for any file under 17GB fits in a 4K page.
+ */
+ unsigned long num_bits =
+ vi->tree_params.tree_pages <<
+ vi->tree_params.log_blocks_per_page;
+
+ vi->hash_block_verified = kvcalloc(BITS_TO_LONGS(num_bits),
+ sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!vi->hash_block_verified) {
+ err = -ENOMEM;
+ goto fail;
+ }
+ spin_lock_init(&vi->hash_page_init_lock);
}
+
return vi;
+
+fail:
+ fsverity_free_info(vi);
+ return ERR_PTR(err);
}
void fsverity_set_info(struct inode *inode, struct fsverity_info *vi)
@@ -216,6 +273,7 @@ void fsverity_free_info(struct fsverity_info *vi)
if (!vi)
return;
kfree(vi->tree_params.hashstate);
+ kvfree(vi->hash_block_verified);
kmem_cache_free(fsverity_info_cachep, vi);
}
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
index 44df06ddcc60..e59ef9d0e21c 100644
--- a/fs/verity/verify.c
+++ b/fs/verity/verify.c
@@ -12,35 +12,9 @@
static struct workqueue_struct *fsverity_read_workqueue;
-/**
- * hash_at_level() - compute the location of the block's hash at the given level
- *
- * @params: (in) the Merkle tree parameters
- * @dindex: (in) the index of the data block being verified
- * @level: (in) the level of hash we want (0 is leaf level)
- * @hindex: (out) the index of the hash block containing the wanted hash
- * @hoffset: (out) the byte offset to the wanted hash within the hash block
- */
-static void hash_at_level(const struct merkle_tree_params *params,
- pgoff_t dindex, unsigned int level, pgoff_t *hindex,
- unsigned int *hoffset)
-{
- pgoff_t position;
-
- /* Offset of the hash within the level's region, in hashes */
- position = dindex >> (level * params->log_arity);
-
- /* Index of the hash block in the tree overall */
- *hindex = params->level_start[level] + (position >> params->log_arity);
-
- /* Offset of the wanted hash (in bytes) within the hash block */
- *hoffset = (position & ((1 << params->log_arity) - 1)) <<
- params->log_digestsize;
-}
-
static inline int cmp_hashes(const struct fsverity_info *vi,
const u8 *want_hash, const u8 *real_hash,
- pgoff_t index, int level)
+ u64 data_pos, int level)
{
const unsigned int hsize = vi->tree_params.digest_size;
@@ -48,148 +22,310 @@ static inline int cmp_hashes(const struct fsverity_info *vi,
return 0;
fsverity_err(vi->inode,
- "FILE CORRUPTED! index=%lu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN",
- index, level,
+ "FILE CORRUPTED! pos=%llu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN",
+ data_pos, level,
vi->tree_params.hash_alg->name, hsize, want_hash,
vi->tree_params.hash_alg->name, hsize, real_hash);
return -EBADMSG;
}
+static bool data_is_zeroed(struct inode *inode, struct page *page,
+ unsigned int len, unsigned int offset)
+{
+ void *virt = kmap_local_page(page);
+
+ if (memchr_inv(virt + offset, 0, len)) {
+ kunmap_local(virt);
+ fsverity_err(inode,
+ "FILE CORRUPTED! Data past EOF is not zeroed");
+ return false;
+ }
+ kunmap_local(virt);
+ return true;
+}
+
+/*
+ * Returns true if the hash block with index @hblock_idx in the tree, located in
+ * @hpage, has already been verified.
+ */
+static bool is_hash_block_verified(struct fsverity_info *vi, struct page *hpage,
+ unsigned long hblock_idx)
+{
+ bool verified;
+ unsigned int blocks_per_page;
+ unsigned int i;
+
+ /*
+ * When the Merkle tree block size and page size are the same, then the
+ * ->hash_block_verified bitmap isn't allocated, and we use PG_checked
+ * to directly indicate whether the page's block has been verified.
+ *
+ * Using PG_checked also guarantees that we re-verify hash pages that
+ * get evicted and re-instantiated from the backing storage, as new
+ * pages always start out with PG_checked cleared.
+ */
+ if (!vi->hash_block_verified)
+ return PageChecked(hpage);
+
+ /*
+ * When the Merkle tree block size and page size differ, we use a bitmap
+ * to indicate whether each hash block has been verified.
+ *
+ * However, we still need to ensure that hash pages that get evicted and
+ * re-instantiated from the backing storage are re-verified. To do
+ * this, we use PG_checked again, but now it doesn't really mean
+ * "checked". Instead, now it just serves as an indicator for whether
+ * the hash page is newly instantiated or not.
+ *
+ * The first thread that sees PG_checked=0 must clear the corresponding
+ * bitmap bits, then set PG_checked=1. This requires a spinlock. To
+ * avoid having to take this spinlock in the common case of
+ * PG_checked=1, we start with an opportunistic lockless read.
+ */
+ if (PageChecked(hpage)) {
+ /*
+ * A read memory barrier is needed here to give ACQUIRE
+ * semantics to the above PageChecked() test.
+ */
+ smp_rmb();
+ return test_bit(hblock_idx, vi->hash_block_verified);
+ }
+ spin_lock(&vi->hash_page_init_lock);
+ if (PageChecked(hpage)) {
+ verified = test_bit(hblock_idx, vi->hash_block_verified);
+ } else {
+ blocks_per_page = vi->tree_params.blocks_per_page;
+ hblock_idx = round_down(hblock_idx, blocks_per_page);
+ for (i = 0; i < blocks_per_page; i++)
+ clear_bit(hblock_idx + i, vi->hash_block_verified);
+ /*
+ * A write memory barrier is needed here to give RELEASE
+ * semantics to the below SetPageChecked() operation.
+ */
+ smp_wmb();
+ SetPageChecked(hpage);
+ verified = false;
+ }
+ spin_unlock(&vi->hash_page_init_lock);
+ return verified;
+}
+
/*
- * Verify a single data page against the file's Merkle tree.
+ * Verify a single data block against the file's Merkle tree.
*
* In principle, we need to verify the entire path to the root node. However,
- * for efficiency the filesystem may cache the hash pages. Therefore we need
- * only ascend the tree until an already-verified page is seen, as indicated by
- * the PageChecked bit being set; then verify the path to that page.
+ * for efficiency the filesystem may cache the hash blocks. Therefore we need
+ * only ascend the tree until an already-verified hash block is seen, and then
+ * verify the path to that block.
*
- * This code currently only supports the case where the verity block size is
- * equal to PAGE_SIZE. Doing otherwise would be possible but tricky, since we
- * wouldn't be able to use the PageChecked bit.
- *
- * Note that multiple processes may race to verify a hash page and mark it
- * Checked, but it doesn't matter; the result will be the same either way.
- *
- * Return: true if the page is valid, else false.
+ * Return: %true if the data block is valid, else %false.
*/
-static bool verify_page(struct inode *inode, const struct fsverity_info *vi,
- struct ahash_request *req, struct page *data_page,
- unsigned long max_ra_pages)
+static bool
+verify_data_block(struct inode *inode, struct fsverity_info *vi,
+ struct ahash_request *req, struct page *data_page,
+ u64 data_pos, unsigned int dblock_offset_in_page,
+ unsigned long max_ra_pages)
{
const struct merkle_tree_params *params = &vi->tree_params;
const unsigned int hsize = params->digest_size;
- const pgoff_t index = data_page->index;
int level;
u8 _want_hash[FS_VERITY_MAX_DIGEST_SIZE];
const u8 *want_hash;
u8 real_hash[FS_VERITY_MAX_DIGEST_SIZE];
- struct page *hpages[FS_VERITY_MAX_LEVELS];
- unsigned int hoffsets[FS_VERITY_MAX_LEVELS];
+ /* The hash blocks that are traversed, indexed by level */
+ struct {
+ /* Page containing the hash block */
+ struct page *page;
+ /* Index of the hash block in the tree overall */
+ unsigned long index;
+ /* Byte offset of the hash block within @page */
+ unsigned int offset_in_page;
+ /* Byte offset of the wanted hash within @page */
+ unsigned int hoffset;
+ } hblocks[FS_VERITY_MAX_LEVELS];
+ /*
+ * The index of the previous level's block within that level; also the
+ * index of that block's hash within the current level.
+ */
+ u64 hidx = data_pos >> params->log_blocksize;
int err;
- if (WARN_ON_ONCE(!PageLocked(data_page) || PageUptodate(data_page)))
- return false;
+ if (unlikely(data_pos >= inode->i_size)) {
+ /*
+ * This can happen in the data page spanning EOF when the Merkle
+ * tree block size is less than the page size. The Merkle tree
+ * doesn't cover data blocks fully past EOF. But the entire
+ * page spanning EOF can be visible to userspace via a mmap, and
+ * any part past EOF should be all zeroes. Therefore, we need
+ * to verify that any data blocks fully past EOF are all zeroes.
+ */
+ return data_is_zeroed(inode, data_page, params->block_size,
+ dblock_offset_in_page);
+ }
/*
- * Starting at the leaf level, ascend the tree saving hash pages along
- * the way until we find a verified hash page, indicated by PageChecked;
- * or until we reach the root.
+ * Starting at the leaf level, ascend the tree saving hash blocks along
+ * the way until we find a hash block that has already been verified, or
+ * until we reach the root.
*/
for (level = 0; level < params->num_levels; level++) {
- pgoff_t hindex;
+ unsigned long next_hidx;
+ unsigned long hblock_idx;
+ pgoff_t hpage_idx;
+ unsigned int hblock_offset_in_page;
unsigned int hoffset;
struct page *hpage;
- hash_at_level(params, index, level, &hindex, &hoffset);
+ /*
+ * The index of the block in the current level; also the index
+ * of that block's hash within the next level.
+ */
+ next_hidx = hidx >> params->log_arity;
+
+ /* Index of the hash block in the tree overall */
+ hblock_idx = params->level_start[level] + next_hidx;
+
+ /* Index of the hash page in the tree overall */
+ hpage_idx = hblock_idx >> params->log_blocks_per_page;
+
+ /* Byte offset of the hash block within the page */
+ hblock_offset_in_page =
+ (hblock_idx << params->log_blocksize) & ~PAGE_MASK;
+
+ /* Byte offset of the hash within the page */
+ hoffset = hblock_offset_in_page +
+ ((hidx << params->log_digestsize) &
+ (params->block_size - 1));
- hpage = inode->i_sb->s_vop->read_merkle_tree_page(inode, hindex,
- level == 0 ? min(max_ra_pages,
- params->tree_pages - hindex) : 0);
+ hpage = inode->i_sb->s_vop->read_merkle_tree_page(inode,
+ hpage_idx, level == 0 ? min(max_ra_pages,
+ params->tree_pages - hpage_idx) : 0);
if (IS_ERR(hpage)) {
err = PTR_ERR(hpage);
fsverity_err(inode,
"Error %d reading Merkle tree page %lu",
- err, hindex);
+ err, hpage_idx);
goto out;
}
-
- if (PageChecked(hpage)) {
+ if (is_hash_block_verified(vi, hpage, hblock_idx)) {
memcpy_from_page(_want_hash, hpage, hoffset, hsize);
want_hash = _want_hash;
put_page(hpage);
goto descend;
}
- hpages[level] = hpage;
- hoffsets[level] = hoffset;
+ hblocks[level].page = hpage;
+ hblocks[level].index = hblock_idx;
+ hblocks[level].offset_in_page = hblock_offset_in_page;
+ hblocks[level].hoffset = hoffset;
+ hidx = next_hidx;
}
want_hash = vi->root_hash;
descend:
/* Descend the tree verifying hash blocks. */
for (; level > 0; level--) {
- struct page *hpage = hpages[level - 1];
- unsigned int hoffset = hoffsets[level - 1];
-
- err = fsverity_hash_block(params, inode, req, hpage, 0,
- real_hash);
+ struct page *hpage = hblocks[level - 1].page;
+ unsigned long hblock_idx = hblocks[level - 1].index;
+ unsigned int hblock_offset_in_page =
+ hblocks[level - 1].offset_in_page;
+ unsigned int hoffset = hblocks[level - 1].hoffset;
+
+ err = fsverity_hash_block(params, inode, req, hpage,
+ hblock_offset_in_page, real_hash);
if (err)
goto out;
- err = cmp_hashes(vi, want_hash, real_hash, index, level - 1);
+ err = cmp_hashes(vi, want_hash, real_hash, data_pos, level - 1);
if (err)
goto out;
- SetPageChecked(hpage);
+ /*
+ * Mark the hash block as verified. This must be atomic and
+ * idempotent, as the same hash block might be verified by
+ * multiple threads concurrently.
+ */
+ if (vi->hash_block_verified)
+ set_bit(hblock_idx, vi->hash_block_verified);
+ else
+ SetPageChecked(hpage);
memcpy_from_page(_want_hash, hpage, hoffset, hsize);
want_hash = _want_hash;
put_page(hpage);
}
/* Finally, verify the data block. */
- err = fsverity_hash_block(params, inode, req, data_page, 0, real_hash);
+ err = fsverity_hash_block(params, inode, req, data_page,
+ dblock_offset_in_page, real_hash);
if (err)
goto out;
- err = cmp_hashes(vi, want_hash, real_hash, index, -1);
+ err = cmp_hashes(vi, want_hash, real_hash, data_pos, -1);
out:
for (; level > 0; level--)
- put_page(hpages[level - 1]);
+ put_page(hblocks[level - 1].page);
return err == 0;
}
+static bool
+verify_data_blocks(struct inode *inode, struct fsverity_info *vi,
+ struct ahash_request *req, struct page *data_page,
+ unsigned int len, unsigned int offset,
+ unsigned long max_ra_pages)
+{
+ const unsigned int block_size = vi->tree_params.block_size;
+ u64 pos = (u64)data_page->index << PAGE_SHIFT;
+
+ if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offset, block_size)))
+ return false;
+ if (WARN_ON_ONCE(!PageLocked(data_page) || PageUptodate(data_page)))
+ return false;
+ do {
+ if (!verify_data_block(inode, vi, req, data_page,
+ pos + offset, offset, max_ra_pages))
+ return false;
+ offset += block_size;
+ len -= block_size;
+ } while (len);
+ return true;
+}
+
/**
- * fsverity_verify_page() - verify a data page
- * @page: the page to verity
+ * fsverity_verify_blocks() - verify data in a page
+ * @page: the page containing the data to verify
+ * @len: the length of the data to verify in the page
+ * @offset: the offset of the data to verify in the page
*
- * Verify a page that has just been read from a verity file. The page must be a
- * pagecache page that is still locked and not yet uptodate.
+ * Verify data that has just been read from a verity file. The data must be
+ * located in a pagecache page that is still locked and not yet uptodate. The
+ * length and offset of the data must be Merkle tree block size aligned.
*
- * Return: true if the page is valid, else false.
+ * Return: %true if the data is valid, else %false.
*/
-bool fsverity_verify_page(struct page *page)
+bool fsverity_verify_blocks(struct page *page, unsigned int len,
+ unsigned int offset)
{
struct inode *inode = page->mapping->host;
- const struct fsverity_info *vi = inode->i_verity_info;
+ struct fsverity_info *vi = inode->i_verity_info;
struct ahash_request *req;
bool valid;
/* This allocation never fails, since it's mempool-backed. */
req = fsverity_alloc_hash_request(vi->tree_params.hash_alg, GFP_NOFS);
- valid = verify_page(inode, vi, req, page, 0);
+ valid = verify_data_blocks(inode, vi, req, page, len, offset, 0);
fsverity_free_hash_request(vi->tree_params.hash_alg, req);
return valid;
}
-EXPORT_SYMBOL_GPL(fsverity_verify_page);
+EXPORT_SYMBOL_GPL(fsverity_verify_blocks);
#ifdef CONFIG_BLOCK
/**
* fsverity_verify_bio() - verify a 'read' bio that has just completed
* @bio: the bio to verify
*
- * Verify a set of pages that have just been read from a verity file. The pages
- * must be pagecache pages that are still locked and not yet uptodate. If a
- * page fails verification, then bio->bi_status is set to an error status.
+ * Verify the bio's data against the file's Merkle tree. All bio data segments
+ * must be aligned to the file's Merkle tree block size. If any data fails
+ * verification, then bio->bi_status is set to an error status.
*
* This is a helper function for use by the ->readahead() method of filesystems
* that issue bios to read data directly into the page cache. Filesystems that
@@ -200,7 +336,7 @@ EXPORT_SYMBOL_GPL(fsverity_verify_page);
void fsverity_verify_bio(struct bio *bio)
{
struct inode *inode = bio_first_page_all(bio)->mapping->host;
- const struct fsverity_info *vi = inode->i_verity_info;
+ struct fsverity_info *vi = inode->i_verity_info;
struct ahash_request *req;
struct bio_vec *bv;
struct bvec_iter_all iter_all;
@@ -223,7 +359,8 @@ void fsverity_verify_bio(struct bio *bio)
}
bio_for_each_segment_all(bv, bio, iter_all) {
- if (!verify_page(inode, vi, req, bv->bv_page, max_ra_pages)) {
+ if (!verify_data_blocks(inode, vi, req, bv->bv_page, bv->bv_len,
+ bv->bv_offset, max_ra_pages)) {
bio->bi_status = BLK_STS_IOERR;
break;
}