Skip to contentSkip to conversation

NFS: Add support for the v4.2 READ_PLUS operation

PATCH New [email protected] 1 participant 11 messages Oct 6, 2020

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

v7 cover NFS: Add support for the v4.2 READ_PLUS operation

From: Anna Schumaker <[email protected]>

These patches add client support for the READ_PLUS operation, which breaks read requests into several "data" and "hole" segments when replying to the client.

- Changes since v6:
- Clean up _zero_pages() to remove an unnecessary conditional

Here are the results of some performance tests I ran on some lab machines. I tested by reading various 2G files from a few different underlying filesystems and across several NFS versions. I used the vmtouch utility to make sure files were only cached when we wanted them to be. In addition to 100% data and 100% hole cases, I also tested with files that alternate between data and hole segments. These files have either 4K, 8K, 16K, or 32K segment sizes and start with either data or hole segments. So the file mixed-4d has a 4K segment size beginning with a data segment, but mixed-32h has 32K segments beginning with a hole. The units are in seconds, with the first number for each NFS version being the uncached read time and the second number is for when the file is cached on the server.

I added some extra data collection (client cpu percentage and sys time), but the extra data means I couldn't figure out a way to break this down into a concise table. I cut out v3 and v4.0 performance numbers to get the size down, but I kept v4.1 for comparison because it uses the same code that v4.2 without read plus uses.

Read Plus Results (ext4):
data
:... v4.1 ... Uncached ... 20.540 s, 105 MB/s, 0.65 s kern, 3% cpu
: :....... Cached ..... 18.252 s, 118 MB/s, 0.70 s kern, 3% cpu
:... v4.2 ... Uncached ... 20.605 s, 104 MB/s, 0.65 s kern, 3% cpu

        :....... Cached ..... 18.253 s, 118 MB/s, 0.67 s kern, 3% cpu
  hole
   :... v4.1 ... Uncached ... 18.255 s, 118 MB/s, 0.72 s kern,  3% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.72 s kern,  3% cpu
   :... v4.2 ... Uncached ...  0.847 s, 2.5 GB/s, 0.73 s kern, 86% cpu
        :....... Cached .....  0.845 s, 2.5 GB/s, 0.72 s kern, 85% cpu
  mixed-4d
   :... v4.1 ... Uncached ... 54.691 s,  39 MB/s, 0.75 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.71 s kern, 3% cpu
   :... v4.2 ... Uncached ... 51.587 s,  42 MB/s, 0.75 s kern, 1% cpu
        :....... Cached .....  9.215 s, 233 MB/s, 0.67 s kern, 7% cpu
  mixed-8d
   :... v4.1 ... Uncached ... 37.072 s,  58 MB/s, 0.67 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.71 s kern, 3% cpu
   :... v4.2 ... Uncached ... 33.259 s,  65 MB/s, 0.68 s kern, 2% cpu
        :....... Cached .....  9.172 s, 234 MB/s, 0.67 s kern, 7% cpu
  mixed-16d
   :... v4.1 ... Uncached ... 27.138 s,  79 MB/s, 0.73 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.71 s kern, 3% cpu
   :... v4.2 ... Uncached ... 23.042 s,  93 MB/s, 0.73 s kern, 3% cpu
        :....... Cached .....  9.150 s, 235 MB/s, 0.66 s kern, 7% cpu
  mixed-32d
   :... v4.1 ... Uncached ... 25.326 s,  85 MB/s, 0.68 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.70 s kern, 3% cpu
   :... v4.2 ... Uncached ... 21.125 s, 102 MB/s, 0.69 s kern, 3% cpu
        :....... Cached .....  9.140 s, 235 MB/s, 0.67 s kern, 7% cpu
  mixed-4h
   :... v4.1 ... Uncached ... 58.317 s,  37 MB/s, 0.75 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.70 s kern, 3% cpu
   :... v4.2 ... Uncached ... 51.878 s,  41 MB/s, 0.74 s kern, 1% cpu
        :....... Cached .....  9.215 s, 233 MB/s, 0.68 s kern, 7% cpu
  mixed-8h
   :... v4.1 ... Uncached ... 36.855 s,  58 MB/s, 0.68 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.72 s kern, 3% cpu
   :... v4.2 ... Uncached ... 29.457 s,  73 MB/s, 0.68 s kern, 2% cpu
        :....... Cached .....  9.172 s, 234 MB/s, 0.67 s kern, 7% cpu
  mixed-16h
   :... v4.1 ... Uncached ... 26.460 s,  81 MB/s, 0.74 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.71 s kern, 3% cpu
   :... v4.2 ... Uncached ... 19.587 s, 110 MB/s, 0.74 s kern, 3% cpu
        :....... Cached .....  9.150 s, 235 MB/s, 0.67 s kern, 7% cpu
  mixed-32h
   :... v4.1 ... Uncached ... 25.495 s,  84 MB/s, 0.69 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.65 s kern, 3% cpu
   :... v4.2 ... Uncached ... 17.634 s, 122 MB/s, 0.69 s kern, 3% cpu
        :....... Cached .....  9.140 s, 235 MB/s, 0.68 s kern, 7% cpu

Read Plus Results (xfs):
data
:... v4.1 ... Uncached ... 20.230 s, 106 MB/s, 0.65 s kern, 3% cpu
: :....... Cached ..... 18.252 s, 118 MB/s, 0.68 s kern, 3% cpu
:... v4.2 ... Uncached ... 20.724 s, 104 MB/s, 0.65 s kern, 3% cpu

        :....... Cached ..... 18.253 s, 118 MB/s, 0.67 s kern, 3% cpu
  hole
   :... v4.1 ... Uncached ... 18.255 s, 118 MB/s, 0.68 s kern,  3% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.69 s kern,  3% cpu
   :... v4.2 ... Uncached ...  0.904 s, 2.4 GB/s, 0.72 s kern, 79% cpu
        :....... Cached .....  0.908 s, 2.4 GB/s, 0.73 s kern, 80% cpu
  mixed-4d
   :... v4.1 ... Uncached ... 57.553 s,  37 MB/s, 0.77 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.70 s kern, 3% cpu
   :... v4.2 ... Uncached ... 37.162 s,  58 MB/s, 0.73 s kern, 1% cpu
        :....... Cached .....  9.215 s, 233 MB/s, 0.67 s kern, 7% cpu
  mixed-8d
   :... v4.1 ... Uncached ... 36.754 s,  58 MB/s, 0.69 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.68 s kern, 3% cpu
   :... v4.2 ... Uncached ... 24.454 s,  88 MB/s, 0.69 s kern, 2% cpu
        :....... Cached .....  9.172 s, 234 MB/s, 0.66 s kern, 7% cpu
  mixed-16d
   :... v4.1 ... Uncached ... 27.156 s,  79 MB/s, 0.73 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.71 s kern, 3% cpu
   :... v4.2 ... Uncached ... 22.934 s,  94 MB/s, 0.72 s kern, 3% cpu
        :....... Cached .....  9.150 s, 235 MB/s, 0.68 s kern, 7% cpu
  mixed-32d
   :... v4.1 ... Uncached ... 27.849 s,  77 MB/s, 0.68 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.72 s kern, 3% cpu
   :... v4.2 ... Uncached ... 23.670 s,  91 MB/s, 0.67 s kern, 2% cpu
        :....... Cached .....  9.139 s, 235 MB/s, 0.64 s kern, 7% cpu
  mixed-4h
   :... v4.1 ... Uncached ... 57.639 s,  37 MB/s, 0.72 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.69 s kern, 3% cpu
   :... v4.2 ... Uncached ... 35.503 s,  61 MB/s, 0.72 s kern, 2% cpu
        :....... Cached .....  9.215 s, 233 MB/s, 0.66 s kern, 7% cpu
  mixed-8h
   :... v4.1 ... Uncached ... 37.044 s,  58 MB/s, 0.71 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.68 s kern, 3% cpu
   :... v4.2 ... Uncached ... 23.779 s,  90 MB/s, 0.69 s kern, 2% cpu
        :....... Cached .....  9.172 s, 234 MB/s, 0.65 s kern, 7% cpu
  mixed-16h
   :... v4.1 ... Uncached ... 27.167 s,  79 MB/s, 0.73 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.67 s kern, 3% cpu
   :... v4.2 ... Uncached ... 19.088 s, 113 MB/s, 0.75 s kern, 3% cpu
        :....... Cached .....  9.159 s, 234 MB/s, 0.66 s kern, 7% cpu
  mixed-32h
   :... v4.1 ... Uncached ... 27.592 s,  78 MB/s, 0.71 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.68 s kern, 3% cpu
   :... v4.2 ... Uncached ... 19.682 s, 109 MB/s, 0.67 s kern, 3% cpu
        :....... Cached .....  9.140 s, 235 MB/s, 0.67 s kern, 7% cpu

Read Plus Results (btrfs):
data
:... v4.1 ... Uncached ... 21.317 s, 101 MB/s, 0.63 s kern, 2% cpu
: :....... Cached ..... 18.252 s, 118 MB/s, 0.67 s kern, 3% cpu
:... v4.2 ... Uncached ... 28.665 s, 75 MB/s, 0.65 s kern, 2% cpu

        :....... Cached ..... 18.253 s, 118 MB/s, 0.66 s kern, 3% cpu
  hole
   :... v4.1 ... Uncached ... 18.256 s, 118 MB/s, 0.70 s kern,  3% cpu
   :    :....... Cached ..... 18.254 s, 118 MB/s, 0.73 s kern,  4% cpu
   :... v4.2 ... Uncached ...  0.851 s, 2.5 GB/s, 0.72 s kern, 84% cpu
        :....... Cached .....  0.847 s, 2.5 GB/s, 0.73 s kern, 86% cpu
  mixed-4d
   :... v4.1 ... Uncached ... 56.857 s,  38 MB/s, 0.76 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.72 s kern, 3% cpu
   :... v4.2 ... Uncached ... 54.455 s,  39 MB/s, 0.73 s kern, 1% cpu
        :....... Cached .....  9.215 s, 233 MB/s, 0.68 s kern, 7% cpu
  mixed-8d
   :... v4.1 ... Uncached ... 36.641 s,  59 MB/s, 0.68 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.70 s kern, 3% cpu
   :... v4.2 ... Uncached ... 33.205 s,  65 MB/s, 0.67 s kern, 2% cpu
        :....... Cached .....  9.172 s, 234 MB/s, 0.65 s kern, 7% cpu
  mixed-16d
   :... v4.1 ... Uncached ... 28.653 s,  75 MB/s, 0.72 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.70 s kern, 3% cpu
   :... v4.2 ... Uncached ... 25.748 s,  83 MB/s, 0.71 s kern, 2% cpu
        :....... Cached .....  9.150 s, 235 MB/s, 0.64 s kern, 7% cpu
  mixed-32d
   :... v4.1 ... Uncached ... 28.886 s,  74 MB/s, 0.67 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.71 s kern, 3% cpu
   :... v4.2 ... Uncached ... 24.724 s,  87 MB/s, 0.74 s kern, 2% cpu
        :....... Cached .....  9.140 s, 235 MB/s, 0.63 s kern, 6% cpu
  mixed-4h
   :... v4.1 ... Uncached ...  52.181 s,  41 MB/s, 0.73 s kern, 1% cpu
   :    :....... Cached .....  18.252 s, 118 MB/s, 0.66 s kern, 3% cpu
   :... v4.2 ... Uncached ... 150.341 s,  14 MB/s, 0.72 s kern, 0% cpu
        :....... Cached .....   9.216 s, 233 MB/s, 0.63 s kern, 6% cpu
  mixed-8h
   :... v4.1 ... Uncached ... 36.945 s,  58 MB/s, 0.68 s kern, 1% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.65 s kern, 3% cpu
   :... v4.2 ... Uncached ... 79.781 s,  27 MB/s, 0.68 s kern, 0% cpu
        :....... Cached .....  9.172 s, 234 MB/s, 0.66 s kern, 7% cpu
  mixed-16h
   :... v4.1 ... Uncached ... 28.651 s,  75 MB/s, 0.73 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.66 s kern, 3% cpu
   :... v4.2 ... Uncached ... 47.428 s,  45 MB/s, 0.71 s kern, 1% cpu
        :....... Cached .....  9.150 s, 235 MB/s, 0.67 s kern, 7% cpu
  mixed-32h
   :... v4.1 ... Uncached ... 28.618 s,  75 MB/s, 0.69 s kern, 2% cpu
   :    :....... Cached ..... 18.252 s, 118 MB/s, 0.70 s kern, 3% cpu
   :... v4.2 ... Uncached ... 38.813 s,  55 MB/s, 0.67 s kern, 1% cpu
        :....... Cached .....  9.140 s, 235 MB/s, 0.61 s kern, 6% cpu

Thoughts?
Anna

Anna Schumaker (10):
SUNRPC: Split out a function for setting current page
SUNRPC: Implement a xdr_page_pos() function
NFS: Use xdr_page_pos() in NFSv4 decode_getacl()
NFS: Add READ_PLUS data segment support
SUNRPC: Split out xdr_realign_pages() from xdr_align_pages()
SUNRPC: Split out _shift_data_right_tail()
SUNRPC: Add the ability to expand holes in data pages
NFS: Add READ_PLUS hole segment decoding
SUNRPC: Add an xdr_align_data() function
NFS: Decode a full READ_PLUS reply

 fs/nfs/nfs42xdr.c          | 167 ++++++++++++++++++++
 fs/nfs/nfs4client.c        |   2 +
 fs/nfs/nfs4proc.c          |  43 +++++-
 fs/nfs/nfs4xdr.c           |   7 +-
 include/linux/nfs4.h       |   2 +-
 include/linux/nfs_fs_sb.h  |   1 +
 include/linux/nfs_xdr.h    |   2 +-
 include/linux/sunrpc/xdr.h |   3 +
 net/sunrpc/xdr.c           | 305 ++++++++++++++++++++++++++++++++-----
 9 files changed, 484 insertions(+), 48 deletions(-)
Signature · 1 line
2.28.0
#1 lore raw

PATCH v7 1/10 SUNRPC: Split out a function for setting current page

From: Anna Schumaker <[email protected]>

I'm going to need this bit of code in a few places for READ_PLUS decoding, so let's make it a helper function.

---
 net/sunrpc/xdr.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)
net/sunrpc/xdr.c +9 -4
index 6dfe5dc8b35f..c62b0882c0d8 100644
@@ -870,6 +870,13 @@ static int xdr_set_page_base(struct xdr_stream *xdr,
 	return 0;
 }
 
+static void xdr_set_page(struct xdr_stream *xdr, unsigned int base,
+			 unsigned int len)
+{
+	if (xdr_set_page_base(xdr, base, len) < 0)
+		xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2);
+}
+
 static void xdr_set_next_page(struct xdr_stream *xdr)
 {
 	unsigned int newbase;
@@ -877,8 +884,7 @@ static void xdr_set_next_page(struct xdr_stream *xdr)
 	newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT;
 	newbase -= xdr->buf->page_base;
 
-	if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0)
-		xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2);
+	xdr_set_page(xdr, newbase, PAGE_SIZE);
 }
 
 static bool xdr_set_next_buffer(struct xdr_stream *xdr)
@@ -886,8 +892,7 @@ static bool xdr_set_next_buffer(struct xdr_stream *xdr)
 	if (xdr->page_ptr != NULL)
 		xdr_set_next_page(xdr);
 	else if (xdr->iov == xdr->buf->head) {
-		if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0)
-			xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2);
+		xdr_set_page(xdr, 0, PAGE_SIZE);
 	}
 	return xdr->p != xdr->end;
 }
Signature · 1 line
2.28.0
#2 lore raw

PATCH v7 2/10 SUNRPC: Implement a xdr_page_pos() function

In reply to [email protected]

From: Anna Schumaker <[email protected]>

I'll need this for READ_PLUS to help figure out the offset where page data is stored at, but it might also be useful for other things.

---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 13 +++++++++++++
 2 files changed, 14 insertions(+)
include/linux/sunrpc/xdr.h +1 -0
index 6613d96a3029..026edbd041d5 100644
@@ -242,6 +242,7 @@ extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr);
+extern unsigned int xdr_page_pos(const struct xdr_stream *xdr);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
net/sunrpc/xdr.c +13 -0
index c62b0882c0d8..8d29450fdce5 100644
@@ -505,6 +505,19 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
 }
 EXPORT_SYMBOL_GPL(xdr_stream_pos);
 
+/**
+ * xdr_page_pos - Return the current offset from the start of the xdr pages
+ * @xdr: pointer to struct xdr_stream
+ */
+unsigned int xdr_page_pos(const struct xdr_stream *xdr)
+{
+	unsigned int pos = xdr_stream_pos(xdr);
+
+	WARN_ON(pos < xdr->buf->head[0].iov_len);
+	return pos - xdr->buf->head[0].iov_len;
+}
+EXPORT_SYMBOL_GPL(xdr_page_pos);
+
 /**
  * xdr_init_encode - Initialize a struct xdr_stream for sending data.
  * @xdr: pointer to xdr_stream struct
Signature · 1 line
2.28.0
#3 lore raw

PATCH v7 3/10 NFS: Use xdr_page_pos() in NFSv4 decode_getacl()

In reply to [email protected]

From: Anna Schumaker <[email protected]>

---
 fs/nfs/nfs4xdr.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)
fs/nfs/nfs4xdr.c +1 -5
index 0b3510f62623..3336ea3407a0 100644
@@ -5308,7 +5308,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	int status;
-	unsigned int pg_offset;
 
 	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -5316,9 +5315,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 
 	xdr_enter_page(xdr, xdr->buf->page_len);
 
-	/* Calculate the offset of the page data */
-	pg_offset = xdr->buf->head[0].iov_len;
-
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
@@ -5331,7 +5327,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
 		 * are stored with the acl data to handle the problem of
 		 * variable length bitmaps.*/
-		res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset;
+		res->acl_data_offset = xdr_page_pos(xdr);
 		res->acl_len = attrlen;
 
 		/* Check for receive buffer overflow */
Signature · 1 line
2.28.0
#4 lore raw

PATCH v7 4/10 NFS: Add READ_PLUS data segment support

In reply to [email protected]

From: Anna Schumaker <[email protected]>

This patch adds client support for decoding a single NFS4_CONTENT_DATA segment returned by the server. This is the simplest implementation possible, since it does not account for any hole segments in the reply.

---
v6: Disable READ_PLUS on RDMA
v5: Fix up for the xattr patches

---
 fs/nfs/nfs42xdr.c         | 141 ++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4client.c       |   2 +
 fs/nfs/nfs4proc.c         |  43 +++++++++++-
 fs/nfs/nfs4xdr.c          |   1 +
 include/linux/nfs4.h      |   2 +-
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |   2 +-
 7 files changed, 187 insertions(+), 5 deletions(-)
fs/nfs/nfs42xdr.c +141 -0
index cc50085e151c..930b4ca212c1 100644
@@ -45,6 +45,15 @@
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_read_plus_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + 3)
+#define NFS42_READ_PLUS_SEGMENT_SIZE	(1 /* data_content4 */ + \
+					 2 /* data_info4.di_offset */ + \
+					 2 /* data_info4.di_length */)
+#define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* rpr_eof */ + \
+					 1 /* rpr_contents count */ + \
+					 NFS42_READ_PLUS_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -128,6 +137,14 @@
 					 decode_putfh_maxsz + \
 					 decode_deallocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_read_plus_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_read_plus_maxsz)
+#define NFS4_dec_read_plus_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_read_plus_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -324,6 +341,16 @@ static void encode_deallocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_read_plus(struct xdr_stream *xdr,
+			     const struct nfs_pgio_args *args,
+			     struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_READ_PLUS, decode_read_plus_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->stateid);
+	encode_uint64(xdr, args->offset);
+	encode_uint32(xdr, args->count);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			const struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -722,6 +749,28 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode READ_PLUS request
+ */
+static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const void *data)
+{
+	const struct nfs_pgio_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_read_plus(xdr, args, &hdr);
+
+	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+				args->count, hdr.replen);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode SEEK request
  */
@@ -970,6 +1019,71 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
 }
 
+static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint32_t count, recvd;
+	uint64_t offset;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	count = be32_to_cpup(p);
+	recvd = xdr_read_pages(xdr, count);
+	res->count += recvd;
+
+	if (count > recvd) {
+		dprintk("NFS: server cheating in read reply: "
+				"count %u > recvd %u\n", count, recvd);
+		*eof = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
+{
+	uint32_t eof, segments, type;
+	int status;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_READ_PLUS);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	eof = be32_to_cpup(p++);
+	segments = be32_to_cpup(p++);
+	if (segments == 0)
+		goto out;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	type = be32_to_cpup(p++);
+	if (type == NFS4_CONTENT_DATA)
+		status = decode_read_plus_data(xdr, res, &eof);
+	else
+		return -EINVAL;
+
+	if (status)
+		return status;
+	if (segments > 1)
+		eof = 0;
+
+out:
+	res->eof = eof;
+	return 0;
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -1146,6 +1260,33 @@ static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
 	return status;
 }
 
+/*
+ * Decode READ_PLUS request
+ */
+static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfs_pgio_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_read_plus(xdr, res);
+	if (!status)
+		status = res->count;
+out:
+	return status;
+}
+
 /*
  * Decode SEEK request
  */
fs/nfs/nfs4client.c +2 -0
index daacc78a3d48..be7915c861ce 100644
@@ -1045,6 +1045,8 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	server->caps |= server->nfs_client->cl_mvops->init_caps;
 	if (server->flags & NFS_MOUNT_NORDIRPLUS)
 			server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
 	/*
 	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
 	 * authentication.
fs/nfs/nfs4proc.c +40 -3

81 lines not on this page · raw message

fs/nfs/nfs4xdr.c +1 -0
index 3336ea3407a0..c6dbfcae7517 100644
@@ -7615,6 +7615,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(SETXATTR,	enc_setxattr,		dec_setxattr),
 	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
 	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
+	PROC42(READ_PLUS,	enc_read_plus,		dec_read_plus),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
include/linux/nfs4.h +1 -1
index b8360be141da..9dc7eeac924f 100644
@@ -551,13 +551,13 @@ enum {
 
 	NFSPROC4_CLNT_LOOKUPP,
 	NFSPROC4_CLNT_LAYOUTERROR,
-
 	NFSPROC4_CLNT_COPY_NOTIFY,
 
 	NFSPROC4_CLNT_GETXATTR,
 	NFSPROC4_CLNT_SETXATTR,
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
+	NFSPROC4_CLNT_READ_PLUS,
 };
 
 /* nfs41 types */
include/linux/nfs_fs_sb.h +1 -0
index 7eae72a8762e..38e60ec742df 100644
@@ -287,5 +287,6 @@ struct nfs_server {
 #define NFS_CAP_LAYOUTERROR	(1U << 26)
 #define NFS_CAP_COPY_NOTIFY	(1U << 27)
 #define NFS_CAP_XATTR		(1U << 28)
+#define NFS_CAP_READ_PLUS	(1U << 29)
 
 #endif
include/linux/nfs_xdr.h +1 -1
index 0599efd57eb9..d63cb862d58e 100644
@@ -657,7 +657,7 @@ struct nfs_pgio_args {
 struct nfs_pgio_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
-	__u32			count;
+	__u64			count;
 	__u32			op_status;
 	union {
 		struct {
Signature · 1 line
2.28.0
#5 lore raw

PATCH v7 5/10 SUNRPC: Split out xdr_realign_pages() from xdr_align_pages()

In reply to [email protected]

From: Anna Schumaker <[email protected]>

I don't need the entire align pages code for READ_PLUS, so split out the part I do need so I don't need to reimplement anything.

---
 net/sunrpc/xdr.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)
net/sunrpc/xdr.c +14 -7
index 8d29450fdce5..70efb35c119e 100644
@@ -1042,26 +1042,33 @@ __be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
 }
 EXPORT_SYMBOL_GPL(xdr_inline_decode);
 
-static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
+static void xdr_realign_pages(struct xdr_stream *xdr)
 {
 	struct xdr_buf *buf = xdr->buf;
-	struct kvec *iov;
-	unsigned int nwords = XDR_QUADLEN(len);
+	struct kvec *iov = buf->head;
 	unsigned int cur = xdr_stream_pos(xdr);
 	unsigned int copied, offset;
 
-	if (xdr->nwords == 0)
-		return 0;
-
 	/* Realign pages to current pointer position */
-	iov = buf->head;
 	if (iov->iov_len > cur) {
 		offset = iov->iov_len - cur;
 		copied = xdr_shrink_bufhead(buf, offset);
 		trace_rpc_xdr_alignment(xdr, offset, copied);
 		xdr->nwords = XDR_QUADLEN(buf->len - cur);
 	}
+}
 
+static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int nwords = XDR_QUADLEN(len);
+	unsigned int cur = xdr_stream_pos(xdr);
+	unsigned int copied, offset;
+
+	if (xdr->nwords == 0)
+		return 0;
+
+	xdr_realign_pages(xdr);
 	if (nwords > xdr->nwords) {
 		nwords = xdr->nwords;
 		len = nwords << 2;
Signature · 1 line
2.28.0
#6 lore raw

PATCH v7 6/10 SUNRPC: Split out _shift_data_right_tail()

In reply to [email protected]

From: Anna Schumaker <[email protected]>

xdr_shrink_pagelen() is very similar to what we need for hole expansion, so split out the common code into its own function that can be used by both functions.

---
 net/sunrpc/xdr.c | 68 +++++++++++++++++++++++++++++-------------------
 1 file changed, 41 insertions(+), 27 deletions(-)
net/sunrpc/xdr.c +41 -27
index 70efb35c119e..d8c9555c6f2b 100644
@@ -266,6 +266,46 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base,
 	} while ((len -= copy) != 0);
 }
 
+static unsigned int
+_shift_data_right_tail(struct xdr_buf *buf, unsigned int pgfrom, size_t len)
+{
+	struct kvec *tail = buf->tail;
+	unsigned int tailbuf_len;
+	unsigned int result = 0;
+	size_t copy;
+
+	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;
+
+	/* Shift the tail first */
+	if (tailbuf_len != 0) {
+		unsigned int free_space = tailbuf_len - tail->iov_len;
+
+		if (len < free_space)
+			free_space = len;
+		if (len > free_space)
+			len = free_space;
+
+		tail->iov_len += free_space;
+		copy = len;
+
+		if (tail->iov_len > len) {
+			char *p = (char *)tail->iov_base + len;
+			memmove(p, tail->iov_base, tail->iov_len - free_space);
+			result += tail->iov_len - free_space;
+		} else
+			copy = tail->iov_len;
+
+		/* Copy from the inlined pages into the tail */
+		_copy_from_pages((char *)tail->iov_base,
+					 buf->pages,
+					 buf->page_base + pgfrom,
+					 copy);
+		result += copy;
+	}
+
+	return result;
+}
+
 /**
  * _copy_to_pages
  * @pages: array of pages
@@ -446,39 +486,13 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len)
 static unsigned int
 xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
 {
-	struct kvec *tail;
-	size_t copy;
 	unsigned int pglen = buf->page_len;
-	unsigned int tailbuf_len;
 	unsigned int result;
 
-	result = 0;
-	tail = buf->tail;
 	if (len > buf->page_len)
 		len = buf-> page_len;
-	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;
 
-	/* Shift the tail first */
-	if (tailbuf_len != 0) {
-		unsigned int free_space = tailbuf_len - tail->iov_len;
-
-		if (len < free_space)
-			free_space = len;
-		tail->iov_len += free_space;
-
-		copy = len;
-		if (tail->iov_len > len) {
-			char *p = (char *)tail->iov_base + len;
-			memmove(p, tail->iov_base, tail->iov_len - len);
-			result += tail->iov_len - len;
-		} else
-			copy = tail->iov_len;
-		/* Copy from the inlined pages into the tail */
-		_copy_from_pages((char *)tail->iov_base,
-				buf->pages, buf->page_base + pglen - len,
-				copy);
-		result += copy;
-	}
+	result = _shift_data_right_tail(buf, pglen - len, len);
 	buf->page_len -= len;
 	buf->buflen -= len;
 	/* Have we truncated the message? */
Signature · 1 line
2.28.0
#7 lore raw

PATCH v7 7/10 SUNRPC: Add the ability to expand holes in data pages

In reply to [email protected]

From: Anna Schumaker <[email protected]>

This patch adds the ability to "read a hole" into a set of XDR data pages by taking the following steps:

1) Shift all data after the current xdr->p to the right, possibly into the tail,
2) Zero the specified range, and
3) Update xdr->p to point beyond the hole.

---
- v7: Clean up _zero_pages() to remove an unnecessary conditional

---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 69 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)
include/linux/sunrpc/xdr.h +1 -0
index 026edbd041d5..36a81c29542e 100644
@@ -252,6 +252,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
net/sunrpc/xdr.c +69 -0

81 lines not on this page · raw message

Signature · 1 line
2.28.0
#8 lore raw

PATCH v7 8/10 NFS: Add READ_PLUS hole segment decoding

In reply to [email protected]

From: Anna Schumaker <[email protected]>

We keep things simple for now by only decoding a single hole or data segment returned by the server, even if they returned more to us.

---
 fs/nfs/nfs42xdr.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)
fs/nfs/nfs42xdr.c +25 -1
index 930b4ca212c1..9720fedd2e57 100644
@@ -53,7 +53,7 @@
 #define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
 					 1 /* rpr_eof */ + \
 					 1 /* rpr_contents count */ + \
-					 NFS42_READ_PLUS_SEGMENT_SIZE)
+					 2 * NFS42_READ_PLUS_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -1045,6 +1045,28 @@ static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *re
 	return 0;
 }
 
+static int decode_read_plus_hole(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint64_t offset, length, recvd;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 8);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	p = xdr_decode_hyper(p, &length);
+	recvd = xdr_expand_hole(xdr, 0, length);
+	res->count += recvd;
+
+	if (recvd < length) {
+		*eof = 0;
+		return 1;
+	}
+	return 0;
+}
+
 static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
 {
 	uint32_t eof, segments, type;
@@ -1071,6 +1093,8 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
 	type = be32_to_cpup(p++);
 	if (type == NFS4_CONTENT_DATA)
 		status = decode_read_plus_data(xdr, res, &eof);
+	else if (type == NFS4_CONTENT_HOLE)
+		status = decode_read_plus_hole(xdr, res, &eof);
 	else
 		return -EINVAL;
 
Signature · 1 line
2.28.0
#9 lore raw

PATCH v7 9/10 SUNRPC: Add an xdr_align_data() function

In reply to [email protected]

From: Anna Schumaker <[email protected]>

For now, this function simply aligns the data at the beginning of the pages. This can eventually be expanded to shift data to the correct offsets when we're ready.

---
 include/linux/sunrpc/xdr.h |   1 +
 net/sunrpc/xdr.c           | 121 +++++++++++++++++++++++++++++++++++++
 2 files changed, 122 insertions(+)
include/linux/sunrpc/xdr.h +1 -0
index 36a81c29542e..9548d075e06d 100644
@@ -252,6 +252,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
net/sunrpc/xdr.c +121 -0

139 lines not on this page · raw message

Signature · 1 line
2.28.0
#10 lore raw

PATCH v7 10/10 NFS: Decode a full READ_PLUS reply

In reply to [email protected]

From: Anna Schumaker <[email protected]>

Decode multiple hole and data segments sent by the server, placing everything directly where they need to go in the xdr pages.

---
 fs/nfs/nfs42xdr.c | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)
fs/nfs/nfs42xdr.c +19 -17
index 9720fedd2e57..0dc31ad2362e 100644
@@ -1032,7 +1032,7 @@ static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *re
 
 	p = xdr_decode_hyper(p, &offset);
 	count = be32_to_cpup(p);
-	recvd = xdr_read_pages(xdr, count);
+	recvd = xdr_align_data(xdr, res->count, count);
 	res->count += recvd;
 
 	if (count > recvd) {
@@ -1057,7 +1057,7 @@ static int decode_read_plus_hole(struct xdr_stream *xdr, struct nfs_pgio_res *re
 
 	p = xdr_decode_hyper(p, &offset);
 	p = xdr_decode_hyper(p, &length);
-	recvd = xdr_expand_hole(xdr, 0, length);
+	recvd = xdr_expand_hole(xdr, res->count, length);
 	res->count += recvd;
 
 	if (recvd < length) {
@@ -1070,7 +1070,7 @@ static int decode_read_plus_hole(struct xdr_stream *xdr, struct nfs_pgio_res *re
 static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
 {
 	uint32_t eof, segments, type;
-	int status;
+	int status, i;
 	__be32 *p;
 
 	status = decode_op_hdr(xdr, OP_READ_PLUS);
@@ -1086,22 +1086,24 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
 	if (segments == 0)
 		goto out;
 
-	p = xdr_inline_decode(xdr, 4);
-	if (unlikely(!p))
-		return -EIO;
+	for (i = 0; i < segments; i++) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			return -EIO;
 
-	type = be32_to_cpup(p++);
-	if (type == NFS4_CONTENT_DATA)
-		status = decode_read_plus_data(xdr, res, &eof);
-	else if (type == NFS4_CONTENT_HOLE)
-		status = decode_read_plus_hole(xdr, res, &eof);
-	else
-		return -EINVAL;
+		type = be32_to_cpup(p++);
+		if (type == NFS4_CONTENT_DATA)
+			status = decode_read_plus_data(xdr, res, &eof);
+		else if (type == NFS4_CONTENT_HOLE)
+			status = decode_read_plus_hole(xdr, res, &eof);
+		else
+			return -EINVAL;
 
-	if (status)
-		return status;
-	if (segments > 1)
-		eof = 0;
+		if (status < 0)
+			return status;
+		if (status > 0)
+			break;
+	}
 
 out:
 	res->eof = eof;
Signature · 1 line
2.28.0