btrfs: detect fast implementation of crc32c on all architectures

Currently, there's only check for fast crc32c implementation on X86,
based on the CPU flags. This is used to decide if checksumming should be
offloaded to worker threads or can be calculated by the caller.

As there are more architectures that implement a faster version of
crc32c (ARM, SPARC, s390, MIPS, PowerPC), also there are specialized hw
cards.

The detection is based on driver name, all generic C implementations
contain 'generic', while the specialized versions do not. Alternatively
the priority could be used, but this is not currently provided by the
crypto API.

The flag is set per-filesystem at mount time and used for the offloading
decisions.
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/ctree.h

@@ -791,6 +791,12 @@ enum {
 
 	/* Indicate that the cleaner thread is awake and doing something. */
 	BTRFS_FS_CLEANER_RUNNING,
+
+	/*
+	 * The checksumming has an optimized version and is considered fast,
+	 * so we don't need to offload checksums to workqueues.
+	 */
+	BTRFS_FS_CSUM_IMPL_FAST,
 };
 
 struct btrfs_fs_info {

fs/btrfs/disk-io.c

@@ -40,10 +40,6 @@
 #include "tree-checker.h"
 #include "ref-verify.h"
 
-#ifdef CONFIG_X86
-#include <asm/cpufeature.h>
-#endif
-
 #define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
 				 BTRFS_HEADER_FLAG_RELOC |\
 				 BTRFS_SUPER_FLAG_ERROR |\
@@ -873,14 +869,13 @@ static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio,
 	return btree_csum_one_bio(bio);
 }
 
-static int check_async_write(struct btrfs_inode *bi)
+static int check_async_write(struct btrfs_fs_info *fs_info,
+			     struct btrfs_inode *bi)
 {
 	if (atomic_read(&bi->sync_writers))
 		return 0;
-#ifdef CONFIG_X86
-	if (static_cpu_has(X86_FEATURE_XMM4_2))
+	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
 		return 0;
-#endif
 	return 1;
 }
 
@@ -889,7 +884,7 @@ static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio,
 					  unsigned long bio_flags)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	int async = check_async_write(BTRFS_I(inode));
+	int async = check_async_write(fs_info, BTRFS_I(inode));
 	blk_status_t ret;
 
 	if (bio_op(bio) != REQ_OP_WRITE) {

fs/btrfs/super.c

@@ -1553,6 +1553,8 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	} else {
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		btrfs_sb(s)->bdev_holder = fs_type;
+		if (!strstr(crc32c_impl(), "generic"))
+			set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags);
 		error = btrfs_fill_super(s, fs_devices, data);
 	}
 	if (!error)