mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-17 04:49:33 +07:00
a71e36045e
Trond made a change to the server's tcp logic that allows a fast client to better take advantage of high bandwidth networks, but may increase the risk that a single client could starve other clients; a new sunrpc.svc_rpc_per_connection_limit parameter should help mitigate this in the (hopefully unlikely) event this becomes a problem in practice. Tom Haynes added a minimal flex-layout pnfs server, which is of no use in production for now--don't build it unless you're doing client testing or further server development. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJXo7HNAAoJECebzXlCjuG+zqUP/RxO5jZjBhNI8/ayGdDW/Jnq s0Fu6B+aNRV3GnugmIeI4tWNGnPyERNzFtjLKlnwaasz/oW4qBLqGbNUWC5xKARS erODs0hM/1aCYWwNBEc5qXP2u23HrWVuQ+B5fg42ACyliKFGq5faDRmf6XGU/1kB 8unXGWPAiLiNZD/bWP91fYhThlLgpfHBFZ7M3G2IqmzWZTSELPzwp1bpRWt7yWQQ z1oYtXToycbwz3yPVk3cXtaoqpjDUVZf2Guqgqi1BwEyEtYOSaYo1VHNsKDf4OId QXQh64AqIK4uszpvtNhvsEaAECN7IiB+N4n2laFiQVmAf8Hfl3AnV/gKeD4lKmTj TY6knnjZO/X88wn80MB7JR1H1WXvvzNIHwNR95qfub/lVKX+C+0AORRtYhi5F9ec ixNs/z1ImLpYxAjiP/T5anD5xcX2S+LcSv7kRjhEufqNFtRAIqBZO9ZWbCdXAAyE tcH9Cru4jeIlFO/y6O61EVrn9FFj2+0uu+7urefNRQ2Y9pmKeculJrLF6WO8WHms 4IzXMmjZK+358RVdX2Ji5Hw6rBDvfgP+LjB8Jn8CeIiNRONEjT+2/AYQcfk61aLb INUbk6G6Vfd8iMO4aaRI9tmW+vKCOZa0IbnrNE1oHKp/AKBDr25i5YPSCsnl3r4Q iR7rRe9FIkfqBpbfjVFv =mo54 -----END PGP SIGNATURE----- Merge tag 'nfsd-4.8' of git://linux-nfs.org/~bfields/linux Pull nfsd updates from Bruce Fields: "Highlights: - Trond made a change to the server's tcp logic that allows a fast client to better take advantage of high bandwidth networks, but may increase the risk that a single client could starve other clients; a new sunrpc.svc_rpc_per_connection_limit parameter should help mitigate this in the (hopefully unlikely) event this becomes a problem in practice. - Tom Haynes added a minimal flex-layout pnfs server, which is of no use in production for now--don't build it unless you're doing client testing or further server development" * tag 'nfsd-4.8' of git://linux-nfs.org/~bfields/linux: (32 commits) nfsd: remove some dead code in nfsd_create_locked() nfsd: drop unnecessary MAY_EXEC check from create nfsd: clean up bad-type check in nfsd_create_locked nfsd: remove unnecessary positive-dentry check nfsd: reorganize nfsd_create nfsd: check d_can_lookup in fh_verify of directories nfsd: remove redundant zero-length check from create nfsd: Make creates return EEXIST instead of EACCES SUNRPC: Detect immediate closure of accepted sockets SUNRPC: accept() may return sockets that are still in SYN_RECV nfsd: allow nfsd to advertise multiple layout types nfsd: Close race between nfsd4_release_lockowner and nfsd4_lock nfsd/blocklayout: Make sure calculate signature/designator length aligned xfs: abstract block export operations from nfsd layouts SUNRPC: Remove unused callback xpo_adjust_wspace() SUNRPC: Change TCP socket space reservation SUNRPC: Add a server side per-connection limit SUNRPC: Micro optimisation for svc_data_ready SUNRPC: Call the default socket callbacks instead of open coding SUNRPC: lock the socket while detaching it ...
226 lines
5.1 KiB
C
226 lines
5.1 KiB
C
/*
|
|
* Copyright (c) 2014-2016 Christoph Hellwig.
|
|
*/
|
|
#include <linux/sunrpc/svc.h>
|
|
#include <linux/exportfs.h>
|
|
#include <linux/iomap.h>
|
|
#include <linux/nfs4.h>
|
|
|
|
#include "nfsd.h"
|
|
#include "blocklayoutxdr.h"
|
|
|
|
#define NFSDDBG_FACILITY NFSDDBG_PNFS
|
|
|
|
|
|
__be32
|
|
nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
|
|
struct nfsd4_layoutget *lgp)
|
|
{
|
|
struct pnfs_block_extent *b = lgp->lg_content;
|
|
int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32);
|
|
__be32 *p;
|
|
|
|
p = xdr_reserve_space(xdr, sizeof(__be32) + len);
|
|
if (!p)
|
|
return nfserr_toosmall;
|
|
|
|
*p++ = cpu_to_be32(len);
|
|
*p++ = cpu_to_be32(1); /* we always return a single extent */
|
|
|
|
p = xdr_encode_opaque_fixed(p, &b->vol_id,
|
|
sizeof(struct nfsd4_deviceid));
|
|
p = xdr_encode_hyper(p, b->foff);
|
|
p = xdr_encode_hyper(p, b->len);
|
|
p = xdr_encode_hyper(p, b->soff);
|
|
*p++ = cpu_to_be32(b->es);
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
|
|
{
|
|
__be32 *p;
|
|
int len;
|
|
|
|
switch (b->type) {
|
|
case PNFS_BLOCK_VOLUME_SIMPLE:
|
|
len = 4 + 4 + 8 + 4 + (XDR_QUADLEN(b->simple.sig_len) << 2);
|
|
p = xdr_reserve_space(xdr, len);
|
|
if (!p)
|
|
return -ETOOSMALL;
|
|
|
|
*p++ = cpu_to_be32(b->type);
|
|
*p++ = cpu_to_be32(1); /* single signature */
|
|
p = xdr_encode_hyper(p, b->simple.offset);
|
|
p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
|
|
break;
|
|
case PNFS_BLOCK_VOLUME_SCSI:
|
|
len = 4 + 4 + 4 + 4 + (XDR_QUADLEN(b->scsi.designator_len) << 2) + 8;
|
|
p = xdr_reserve_space(xdr, len);
|
|
if (!p)
|
|
return -ETOOSMALL;
|
|
|
|
*p++ = cpu_to_be32(b->type);
|
|
*p++ = cpu_to_be32(b->scsi.code_set);
|
|
*p++ = cpu_to_be32(b->scsi.designator_type);
|
|
p = xdr_encode_opaque(p, b->scsi.designator, b->scsi.designator_len);
|
|
p = xdr_encode_hyper(p, b->scsi.pr_key);
|
|
break;
|
|
default:
|
|
return -ENOTSUPP;
|
|
}
|
|
|
|
return len;
|
|
}
|
|
|
|
__be32
|
|
nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
|
|
struct nfsd4_getdeviceinfo *gdp)
|
|
{
|
|
struct pnfs_block_deviceaddr *dev = gdp->gd_device;
|
|
int len = sizeof(__be32), ret, i;
|
|
__be32 *p;
|
|
|
|
p = xdr_reserve_space(xdr, len + sizeof(__be32));
|
|
if (!p)
|
|
return nfserr_resource;
|
|
|
|
for (i = 0; i < dev->nr_volumes; i++) {
|
|
ret = nfsd4_block_encode_volume(xdr, &dev->volumes[i]);
|
|
if (ret < 0)
|
|
return nfserrno(ret);
|
|
len += ret;
|
|
}
|
|
|
|
/*
|
|
* Fill in the overall length and number of volumes at the beginning
|
|
* of the layout.
|
|
*/
|
|
*p++ = cpu_to_be32(len);
|
|
*p++ = cpu_to_be32(dev->nr_volumes);
|
|
return 0;
|
|
}
|
|
|
|
int
|
|
nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
|
|
u32 block_size)
|
|
{
|
|
struct iomap *iomaps;
|
|
u32 nr_iomaps, i;
|
|
|
|
if (len < sizeof(u32)) {
|
|
dprintk("%s: extent array too small: %u\n", __func__, len);
|
|
return -EINVAL;
|
|
}
|
|
len -= sizeof(u32);
|
|
if (len % PNFS_BLOCK_EXTENT_SIZE) {
|
|
dprintk("%s: extent array invalid: %u\n", __func__, len);
|
|
return -EINVAL;
|
|
}
|
|
|
|
nr_iomaps = be32_to_cpup(p++);
|
|
if (nr_iomaps != len / PNFS_BLOCK_EXTENT_SIZE) {
|
|
dprintk("%s: extent array size mismatch: %u/%u\n",
|
|
__func__, len, nr_iomaps);
|
|
return -EINVAL;
|
|
}
|
|
|
|
iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL);
|
|
if (!iomaps) {
|
|
dprintk("%s: failed to allocate extent array\n", __func__);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
for (i = 0; i < nr_iomaps; i++) {
|
|
struct pnfs_block_extent bex;
|
|
|
|
memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid));
|
|
p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid));
|
|
|
|
p = xdr_decode_hyper(p, &bex.foff);
|
|
if (bex.foff & (block_size - 1)) {
|
|
dprintk("%s: unaligned offset 0x%llx\n",
|
|
__func__, bex.foff);
|
|
goto fail;
|
|
}
|
|
p = xdr_decode_hyper(p, &bex.len);
|
|
if (bex.len & (block_size - 1)) {
|
|
dprintk("%s: unaligned length 0x%llx\n",
|
|
__func__, bex.foff);
|
|
goto fail;
|
|
}
|
|
p = xdr_decode_hyper(p, &bex.soff);
|
|
if (bex.soff & (block_size - 1)) {
|
|
dprintk("%s: unaligned disk offset 0x%llx\n",
|
|
__func__, bex.soff);
|
|
goto fail;
|
|
}
|
|
bex.es = be32_to_cpup(p++);
|
|
if (bex.es != PNFS_BLOCK_READWRITE_DATA) {
|
|
dprintk("%s: incorrect extent state %d\n",
|
|
__func__, bex.es);
|
|
goto fail;
|
|
}
|
|
|
|
iomaps[i].offset = bex.foff;
|
|
iomaps[i].length = bex.len;
|
|
}
|
|
|
|
*iomapp = iomaps;
|
|
return nr_iomaps;
|
|
fail:
|
|
kfree(iomaps);
|
|
return -EINVAL;
|
|
}
|
|
|
|
int
|
|
nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
|
|
u32 block_size)
|
|
{
|
|
struct iomap *iomaps;
|
|
u32 nr_iomaps, expected, i;
|
|
|
|
if (len < sizeof(u32)) {
|
|
dprintk("%s: extent array too small: %u\n", __func__, len);
|
|
return -EINVAL;
|
|
}
|
|
|
|
nr_iomaps = be32_to_cpup(p++);
|
|
expected = sizeof(__be32) + nr_iomaps * PNFS_SCSI_RANGE_SIZE;
|
|
if (len != expected) {
|
|
dprintk("%s: extent array size mismatch: %u/%u\n",
|
|
__func__, len, expected);
|
|
return -EINVAL;
|
|
}
|
|
|
|
iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL);
|
|
if (!iomaps) {
|
|
dprintk("%s: failed to allocate extent array\n", __func__);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
for (i = 0; i < nr_iomaps; i++) {
|
|
u64 val;
|
|
|
|
p = xdr_decode_hyper(p, &val);
|
|
if (val & (block_size - 1)) {
|
|
dprintk("%s: unaligned offset 0x%llx\n", __func__, val);
|
|
goto fail;
|
|
}
|
|
iomaps[i].offset = val;
|
|
|
|
p = xdr_decode_hyper(p, &val);
|
|
if (val & (block_size - 1)) {
|
|
dprintk("%s: unaligned length 0x%llx\n", __func__, val);
|
|
goto fail;
|
|
}
|
|
iomaps[i].length = val;
|
|
}
|
|
|
|
*iomapp = iomaps;
|
|
return nr_iomaps;
|
|
fail:
|
|
kfree(iomaps);
|
|
return -EINVAL;
|
|
}
|