linux_dsm_epyc7002/fs/cifs/transport.c

1059 lines
26 KiB
C
Raw Normal View History

/*
* fs/cifs/transport.c
*
* Copyright (C) International Business Machines Corp., 2002,2008
* Author(s): Steve French (sfrench@us.ibm.com)
* Jeremy Allison (jra@samba.org) 2006.
*
* This library is free software; you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as published
* by the Free Software Foundation; either version 2.1 of the License, or
* (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
* the GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/fs.h>
#include <linux/list.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/gfp.h>
#include <linux/wait.h>
#include <linux/net.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/tcp.h>
#include <linux/highmem.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
#include <linux/mempool.h>
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "cifs_debug.h"
void
cifs_wake_up_task(struct mid_q_entry *mid)
{
wake_up_process(mid->callback_data);
}
struct mid_q_entry *
AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
{
struct mid_q_entry *temp;
if (server == NULL) {
cifs_dbg(VFS, "Null TCP session in AllocMidQEntry\n");
return NULL;
}
temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
if (temp == NULL)
return temp;
else {
memset(temp, 0, sizeof(struct mid_q_entry));
temp->mid = get_mid(smb_buffer);
temp->pid = current->pid;
temp->command = cpu_to_le16(smb_buffer->Command);
cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command);
/* do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */
/* when mid allocated can be before when sent */
temp->when_alloc = jiffies;
temp->server = server;
/*
* The default is for the mid to be synchronous, so the
* default callback just wakes up the current task.
*/
temp->callback = cifs_wake_up_task;
temp->callback_data = current;
}
atomic_inc(&midCount);
temp->mid_state = MID_REQUEST_ALLOCATED;
return temp;
}
void
DeleteMidQEntry(struct mid_q_entry *midEntry)
{
#ifdef CONFIG_CIFS_STATS2
__le16 command = midEntry->server->vals->lock_cmd;
unsigned long now;
#endif
midEntry->mid_state = MID_FREE;
atomic_dec(&midCount);
if (midEntry->large_buf)
cifs_buf_release(midEntry->resp_buf);
else
cifs_small_buf_release(midEntry->resp_buf);
#ifdef CONFIG_CIFS_STATS2
now = jiffies;
/* commands taking longer than one second are indications that
something is wrong, unless it is quite a slow link or server */
if ((now - midEntry->when_alloc) > HZ) {
if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) {
pr_debug(" CIFS slow rsp: cmd %d mid %llu",
midEntry->command, midEntry->mid);
pr_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n",
now - midEntry->when_alloc,
now - midEntry->when_sent,
now - midEntry->when_received);
}
}
#endif
mempool_free(midEntry, cifs_mid_poolp);
}
void
cifs_delete_mid(struct mid_q_entry *mid)
{
spin_lock(&GlobalMid_Lock);
list_del(&mid->qhead);
spin_unlock(&GlobalMid_Lock);
DeleteMidQEntry(mid);
}
/*
* smb_send_kvec - send an array of kvecs to the server
* @server: Server to send the data to
* @smb_msg: Message to send
* @sent: amount of data sent on socket is stored here
*
* Our basic "send data to server" function. Should be called with srv_mutex
* held. The caller is responsible for handling the results.
*/
static int
smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg,
size_t *sent)
{
int rc = 0;
int retries = 0;
struct socket *ssocket = server->ssocket;
*sent = 0;
smb_msg->msg_name = (struct sockaddr *) &server->dstaddr;
smb_msg->msg_namelen = sizeof(struct sockaddr);
smb_msg->msg_control = NULL;
smb_msg->msg_controllen = 0;
if (server->noblocksnd)
smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
else
smb_msg->msg_flags = MSG_NOSIGNAL;
while (msg_data_left(smb_msg)) {
/*
* If blocking send, we try 3 times, since each can block
* for 5 seconds. For nonblocking we have to try more
* but wait increasing amounts of time allowing time for
* socket to clear. The overall time we wait in either
* case to send on the socket is about 15 seconds.
* Similarly we wait for 15 seconds for a response from
* the server in SendReceive[2] for the server to send
* a response back for most types of requests (except
* SMB Write past end of file which can be slow, and
* blocking lock operations). NFS waits slightly longer
* than CIFS, but this can make it take longer for
* nonresponsive servers to be detected and 15 seconds
* is more than enough time for modern networks to
* send a packet. In most cases if we fail to send
* after the retries we will kill the socket and
* reconnect which may clear the network problem.
*/
rc = sock_sendmsg(ssocket, smb_msg);
if (rc == -EAGAIN) {
retries++;
if (retries >= 14 ||
(!server->noblocksnd && (retries > 2))) {
cifs_dbg(VFS, "sends on sock %p stuck for 15 seconds\n",
ssocket);
return -EAGAIN;
}
msleep(1 << retries);
continue;
}
if (rc < 0)
return rc;
if (rc == 0) {
/* should never happen, letting socket clear before
retrying is our only obvious option here */
cifs_dbg(VFS, "tcp sent no data\n");
msleep(500);
continue;
}
/* send was at least partially successful */
*sent += rc;
retries = 0; /* in case we get ENOSPC on the next send */
}
return 0;
}
static unsigned long
rqst_len(struct smb_rqst *rqst)
{
unsigned int i;
struct kvec *iov = rqst->rq_iov;
unsigned long buflen = 0;
/* total up iov array first */
for (i = 0; i < rqst->rq_nvec; i++)
buflen += iov[i].iov_len;
/* add in the page array if there is one */
if (rqst->rq_npages) {
buflen += rqst->rq_pagesz * (rqst->rq_npages - 1);
buflen += rqst->rq_tailsz;
}
return buflen;
}
static int
smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
{
int rc;
struct kvec *iov = rqst->rq_iov;
int n_vec = rqst->rq_nvec;
unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
unsigned long send_length;
unsigned int i;
size_t total_len = 0, sent, size;
struct socket *ssocket = server->ssocket;
struct msghdr smb_msg;
int val = 1;
cifs: move check for NULL socket into smb_send_rqst Cai reported this oops: [90701.616664] BUG: unable to handle kernel NULL pointer dereference at 0000000000000028 [90701.625438] IP: [<ffffffff814a343e>] kernel_setsockopt+0x2e/0x60 [90701.632167] PGD fea319067 PUD 103fda4067 PMD 0 [90701.637255] Oops: 0000 [#1] SMP [90701.640878] Modules linked in: des_generic md4 nls_utf8 cifs dns_resolver binfmt_misc tun sg igb iTCO_wdt iTCO_vendor_support lpc_ich pcspkr i2c_i801 i2c_core i7core_edac edac_core ioatdma dca mfd_core coretemp kvm_intel kvm crc32c_intel microcode sr_mod cdrom ata_generic sd_mod pata_acpi crc_t10dif ata_piix libata megaraid_sas dm_mirror dm_region_hash dm_log dm_mod [90701.677655] CPU 10 [90701.679808] Pid: 9627, comm: ls Tainted: G W 3.7.1+ #10 QCI QSSC-S4R/QSSC-S4R [90701.688950] RIP: 0010:[<ffffffff814a343e>] [<ffffffff814a343e>] kernel_setsockopt+0x2e/0x60 [90701.698383] RSP: 0018:ffff88177b431bb8 EFLAGS: 00010206 [90701.704309] RAX: ffff88177b431fd8 RBX: 00007ffffffff000 RCX: ffff88177b431bec [90701.712271] RDX: 0000000000000003 RSI: 0000000000000006 RDI: 0000000000000000 [90701.720223] RBP: ffff88177b431bc8 R08: 0000000000000004 R09: 0000000000000000 [90701.728185] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000001 [90701.736147] R13: ffff88184ef92000 R14: 0000000000000023 R15: ffff88177b431c88 [90701.744109] FS: 00007fd56a1a47c0(0000) GS:ffff88105fc40000(0000) knlGS:0000000000000000 [90701.753137] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [90701.759550] CR2: 0000000000000028 CR3: 000000104f15f000 CR4: 00000000000007e0 [90701.767512] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [90701.775465] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [90701.783428] Process ls (pid: 9627, threadinfo ffff88177b430000, task ffff88185ca4cb60) [90701.792261] Stack: [90701.794505] 0000000000000023 ffff88177b431c50 ffff88177b431c38 ffffffffa014fcb1 [90701.802809] ffff88184ef921bc 0000000000000000 00000001ffffffff ffff88184ef921c0 [90701.811123] ffff88177b431c08 ffffffff815ca3d9 ffff88177b431c18 ffff880857758000 [90701.819433] Call Trace: [90701.822183] [<ffffffffa014fcb1>] smb_send_rqst+0x71/0x1f0 [cifs] [90701.828991] [<ffffffff815ca3d9>] ? schedule+0x29/0x70 [90701.834736] [<ffffffffa014fe6d>] smb_sendv+0x3d/0x40 [cifs] [90701.841062] [<ffffffffa014fe96>] smb_send+0x26/0x30 [cifs] [90701.847291] [<ffffffffa015801f>] send_nt_cancel+0x6f/0xd0 [cifs] [90701.854102] [<ffffffffa015075e>] SendReceive+0x18e/0x360 [cifs] [90701.860814] [<ffffffffa0134a78>] CIFSFindFirst+0x1a8/0x3f0 [cifs] [90701.867724] [<ffffffffa013f731>] ? build_path_from_dentry+0xf1/0x260 [cifs] [90701.875601] [<ffffffffa013f731>] ? build_path_from_dentry+0xf1/0x260 [cifs] [90701.883477] [<ffffffffa01578e6>] cifs_query_dir_first+0x26/0x30 [cifs] [90701.890869] [<ffffffffa015480d>] initiate_cifs_search+0xed/0x250 [cifs] [90701.898354] [<ffffffff81195970>] ? fillonedir+0x100/0x100 [90701.904486] [<ffffffffa01554cb>] cifs_readdir+0x45b/0x8f0 [cifs] [90701.911288] [<ffffffff81195970>] ? fillonedir+0x100/0x100 [90701.917410] [<ffffffff81195970>] ? fillonedir+0x100/0x100 [90701.923533] [<ffffffff81195970>] ? fillonedir+0x100/0x100 [90701.929657] [<ffffffff81195848>] vfs_readdir+0xb8/0xe0 [90701.935490] [<ffffffff81195b9f>] sys_getdents+0x8f/0x110 [90701.941521] [<ffffffff815d3b99>] system_call_fastpath+0x16/0x1b [90701.948222] Code: 66 90 55 65 48 8b 04 25 f0 c6 00 00 48 89 e5 53 48 83 ec 08 83 fe 01 48 8b 98 48 e0 ff ff 48 c7 80 48 e0 ff ff ff ff ff ff 74 22 <48> 8b 47 28 ff 50 68 65 48 8b 14 25 f0 c6 00 00 48 89 9a 48 e0 [90701.970313] RIP [<ffffffff814a343e>] kernel_setsockopt+0x2e/0x60 [90701.977125] RSP <ffff88177b431bb8> [90701.981018] CR2: 0000000000000028 [90701.984809] ---[ end trace 24bd602971110a43 ]--- This is likely due to a race vs. a reconnection event. The current code checks for a NULL socket in smb_send_kvec, but that's too late. By the time that check is done, the socket will already have been passed to kernel_setsockopt. Move the check into smb_send_rqst, so that it's checked earlier. In truth, this is a bit of a half-assed fix. The -ENOTSOCK error return here looks like it could bubble back up to userspace. The locking rules around the ssocket pointer are really unclear as well. There are cases where the ssocket pointer is changed without holding the srv_mutex, but I'm not clear whether there's a potential race here yet or not. This code seems like it could benefit from some fundamental re-think of how the socket handling should behave. Until then though, this patch should at least fix the above oops in most cases. Cc: <stable@vger.kernel.org> # 3.7+ Reported-and-Tested-by: CAI Qian <caiqian@redhat.com> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Steve French <smfrench@gmail.com>
2012-12-27 19:28:55 +07:00
if (ssocket == NULL)
return -ENOTSOCK;
/* sanity check send length */
send_length = rqst_len(rqst);
if (send_length != smb_buf_length + 4) {
WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n",
send_length, smb_buf_length);
return -EIO;
}
cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
dump_smb(iov[0].iov_base, iov[0].iov_len);
/* cork the socket */
kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
(char *)&val, sizeof(val));
size = 0;
for (i = 0; i < n_vec; i++)
size += iov[i].iov_len;
iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, iov, n_vec, size);
rc = smb_send_kvec(server, &smb_msg, &sent);
if (rc < 0)
goto uncork;
total_len += sent;
/* now walk the page array and send each page in it */
for (i = 0; i < rqst->rq_npages; i++) {
size_t len = i == rqst->rq_npages - 1
? rqst->rq_tailsz
: rqst->rq_pagesz;
struct bio_vec bvec = {
.bv_page = rqst->rq_pages[i],
.bv_len = len
};
iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC,
&bvec, 1, len);
rc = smb_send_kvec(server, &smb_msg, &sent);
if (rc < 0)
break;
total_len += sent;
}
uncork:
/* uncork it */
val = 0;
kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
(char *)&val, sizeof(val));
if ((total_len > 0) && (total_len != smb_buf_length + 4)) {
cifs_dbg(FYI, "partial send (wanted=%u sent=%zu): terminating session\n",
smb_buf_length + 4, total_len);
/*
* If we have only sent part of an SMB then the next SMB could
* be taken as the remainder of this one. We need to kill the
* socket so the server throws away the partial SMB
*/
server->tcpStatus = CifsNeedReconnect;
}
if (rc < 0 && rc != -EINTR)
cifs_dbg(VFS, "Error %d sending data on socket to server\n",
rc);
else
rc = 0;
return rc;
}
static int
smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
{
struct smb_rqst rqst = { .rq_iov = iov,
.rq_nvec = n_vec };
return smb_send_rqst(server, &rqst);
}
int
smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer,
unsigned int smb_buf_length)
{
struct kvec iov;
iov.iov_base = smb_buffer;
iov.iov_len = smb_buf_length + 4;
return smb_sendv(server, &iov, 1);
}
static int
wait_for_free_credits(struct TCP_Server_Info *server, const int timeout,
int *credits)
{
int rc;
spin_lock(&server->req_lock);
if (timeout == CIFS_ASYNC_OP) {
/* oplock breaks must not be held up */
server->in_flight++;
*credits -= 1;
spin_unlock(&server->req_lock);
return 0;
}
while (1) {
if (*credits <= 0) {
spin_unlock(&server->req_lock);
cifs_num_waiters_inc(server);
rc = wait_event_killable(server->request_q,
has_credits(server, credits));
cifs_num_waiters_dec(server);
if (rc)
return rc;
spin_lock(&server->req_lock);
} else {
if (server->tcpStatus == CifsExiting) {
spin_unlock(&server->req_lock);
return -ENOENT;
}
/*
* Can not count locking commands against total
* as they are allowed to block on server.
*/
/* update # of requests on the wire to server */
if (timeout != CIFS_BLOCKING_OP) {
*credits -= 1;
server->in_flight++;
}
spin_unlock(&server->req_lock);
break;
}
}
return 0;
}
static int
wait_for_free_request(struct TCP_Server_Info *server, const int timeout,
const int optype)
{
int *val;
val = server->ops->get_credits_field(server, optype);
/* Since an echo is already inflight, no need to wait to send another */
if (*val <= 0 && optype == CIFS_ECHO_OP)
return -EAGAIN;
return wait_for_free_credits(server, timeout, val);
}
int
cifs_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size,
unsigned int *num, unsigned int *credits)
{
*num = size;
*credits = 0;
return 0;
}
static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf,
struct mid_q_entry **ppmidQ)
{
if (ses->server->tcpStatus == CifsExiting) {
return -ENOENT;
}
if (ses->server->tcpStatus == CifsNeedReconnect) {
cifs_dbg(FYI, "tcp session dead - return to caller to retry\n");
return -EAGAIN;
}
if (ses->status == CifsNew) {
if ((in_buf->Command != SMB_COM_SESSION_SETUP_ANDX) &&
(in_buf->Command != SMB_COM_NEGOTIATE))
return -EAGAIN;
/* else ok - we are setting up session */
}
if (ses->status == CifsExiting) {
/* check if SMB session is bad because we are setting it up */
if (in_buf->Command != SMB_COM_LOGOFF_ANDX)
return -EAGAIN;
/* else ok - we are shutting down session */
}
*ppmidQ = AllocMidQEntry(in_buf, ses->server);
if (*ppmidQ == NULL)
return -ENOMEM;
spin_lock(&GlobalMid_Lock);
list_add_tail(&(*ppmidQ)->qhead, &ses->server->pending_mid_q);
spin_unlock(&GlobalMid_Lock);
return 0;
}
static int
wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ)
{
int error;
error = wait_event_freezekillable_unsafe(server->response_q,
midQ->mid_state != MID_REQUEST_SUBMITTED);
if (error < 0)
return -ERESTARTSYS;
return 0;
}
struct mid_q_entry *
cifs_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
{
int rc;
struct smb_hdr *hdr = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
/* enable signing if server requires it */
if (server->sign)
hdr->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
mid = AllocMidQEntry(hdr, server);
if (mid == NULL)
return ERR_PTR(-ENOMEM);
rc = cifs_sign_rqst(rqst, server, &mid->sequence_number);
if (rc) {
DeleteMidQEntry(mid);
return ERR_PTR(rc);
}
return mid;
}
/*
* Send a SMB request and set the callback function in the mid to handle
* the result. Caller is responsible for dealing with timeouts.
*/
int
cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
mid_receive_t *receive, mid_callback_t *callback,
void *cbdata, const int flags)
{
int rc, timeout, optype;
struct mid_q_entry *mid;
unsigned int credits = 0;
timeout = flags & CIFS_TIMEOUT_MASK;
optype = flags & CIFS_OP_MASK;
if ((flags & CIFS_HAS_CREDITS) == 0) {
rc = wait_for_free_request(server, timeout, optype);
if (rc)
return rc;
credits = 1;
}
mutex_lock(&server->srv_mutex);
mid = server->ops->setup_async_request(server, rqst);
if (IS_ERR(mid)) {
mutex_unlock(&server->srv_mutex);
add_credits_and_wake_if(server, credits, optype);
return PTR_ERR(mid);
}
mid->receive = receive;
mid->callback = callback;
mid->callback_data = cbdata;
mid->mid_state = MID_REQUEST_SUBMITTED;
/* put it on the pending_mid_q */
spin_lock(&GlobalMid_Lock);
list_add_tail(&mid->qhead, &server->pending_mid_q);
spin_unlock(&GlobalMid_Lock);
cifs_in_send_inc(server);
rc = smb_send_rqst(server, rqst);
cifs_in_send_dec(server);
cifs_save_when_sent(mid);
if (rc < 0) {
server->sequence_number -= 2;
cifs_delete_mid(mid);
}
mutex_unlock(&server->srv_mutex);
if (rc == 0)
return 0;
add_credits_and_wake_if(server, credits, optype);
return rc;
}
/*
*
* Send an SMB Request. No response info (other than return code)
* needs to be parsed.
*
* flags indicate the type of request buffer and how long to wait
* and whether to log NT STATUS code (error) before mapping it to POSIX error
*
*/
int
SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
char *in_buf, int flags)
{
int rc;
struct kvec iov[1];
int resp_buf_type;
iov[0].iov_base = in_buf;
iov[0].iov_len = get_rfc1002_length(in_buf) + 4;
flags |= CIFS_NO_RESP;
rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags);
cifs_dbg(NOISY, "SendRcvNoRsp flags %d rc %d\n", flags, rc);
return rc;
}
static int
cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
{
int rc = 0;
cifs_dbg(FYI, "%s: cmd=%d mid=%llu state=%d\n",
__func__, le16_to_cpu(mid->command), mid->mid, mid->mid_state);
spin_lock(&GlobalMid_Lock);
switch (mid->mid_state) {
case MID_RESPONSE_RECEIVED:
spin_unlock(&GlobalMid_Lock);
return rc;
case MID_RETRY_NEEDED:
rc = -EAGAIN;
break;
case MID_RESPONSE_MALFORMED:
rc = -EIO;
break;
case MID_SHUTDOWN:
rc = -EHOSTDOWN;
break;
default:
list_del_init(&mid->qhead);
cifs_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n",
__func__, mid->mid, mid->mid_state);
rc = -EIO;
}
spin_unlock(&GlobalMid_Lock);
mutex_lock(&server->srv_mutex);
DeleteMidQEntry(mid);
mutex_unlock(&server->srv_mutex);
return rc;
}
static inline int
send_cancel(struct TCP_Server_Info *server, void *buf, struct mid_q_entry *mid)
{
return server->ops->send_cancel ?
server->ops->send_cancel(server, buf, mid) : 0;
}
int
cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
bool log_error)
{
unsigned int len = get_rfc1002_length(mid->resp_buf) + 4;
dump_smb(mid->resp_buf, min_t(u32, 92, len));
/* convert the length into a more usable form */
if (server->sign) {
struct kvec iov;
int rc = 0;
struct smb_rqst rqst = { .rq_iov = &iov,
.rq_nvec = 1 };
iov.iov_base = mid->resp_buf;
iov.iov_len = len;
/* FIXME: add code to kill session */
rc = cifs_verify_signature(&rqst, server,
mid->sequence_number);
if (rc)
cifs_dbg(VFS, "SMB signature verification returned error = %d\n",
rc);
}
/* BB special case reconnect tid and uid here? */
return map_smb_to_linux_error(mid->resp_buf, log_error);
}
struct mid_q_entry *
cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
{
int rc;
struct smb_hdr *hdr = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
struct mid_q_entry *mid;
rc = allocate_mid(ses, hdr, &mid);
if (rc)
return ERR_PTR(rc);
rc = cifs_sign_rqst(rqst, ses->server, &mid->sequence_number);
if (rc) {
cifs_delete_mid(mid);
return ERR_PTR(rc);
}
return mid;
}
int
SendReceive2(const unsigned int xid, struct cifs_ses *ses,
struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
const int flags)
{
int rc = 0;
int timeout, optype;
struct mid_q_entry *midQ;
char *buf = iov[0].iov_base;
unsigned int credits = 1;
struct smb_rqst rqst = { .rq_iov = iov,
.rq_nvec = n_vec };
timeout = flags & CIFS_TIMEOUT_MASK;
optype = flags & CIFS_OP_MASK;
*resp_buf_type = CIFS_NO_BUFFER; /* no response buf yet */
if ((ses == NULL) || (ses->server == NULL)) {
cifs_small_buf_release(buf);
cifs_dbg(VFS, "Null session\n");
return -EIO;
}
if (ses->server->tcpStatus == CifsExiting) {
cifs_small_buf_release(buf);
return -ENOENT;
}
/*
* Ensure that we do not send more than 50 overlapping requests
* to the same server. We may make this configurable later or
* use ses->maxReq.
*/
rc = wait_for_free_request(ses->server, timeout, optype);
if (rc) {
cifs_small_buf_release(buf);
return rc;
}
/*
* Make sure that we sign in the same order that we send on this socket
* and avoid races inside tcp sendmsg code that could cause corruption
* of smb data.
*/
mutex_lock(&ses->server->srv_mutex);
midQ = ses->server->ops->setup_request(ses, &rqst);
if (IS_ERR(midQ)) {
mutex_unlock(&ses->server->srv_mutex);
cifs_small_buf_release(buf);
/* Update # of requests on wire to server */
add_credits(ses->server, 1, optype);
return PTR_ERR(midQ);
}
midQ->mid_state = MID_REQUEST_SUBMITTED;
cifs_in_send_inc(ses->server);
rc = smb_sendv(ses->server, iov, n_vec);
cifs_in_send_dec(ses->server);
cifs_save_when_sent(midQ);
if (rc < 0)
ses->server->sequence_number -= 2;
mutex_unlock(&ses->server->srv_mutex);
if (rc < 0) {
cifs_small_buf_release(buf);
goto out;
}
if (timeout == CIFS_ASYNC_OP) {
cifs_small_buf_release(buf);
goto out;
}
rc = wait_for_response(ses->server, midQ);
if (rc != 0) {
send_cancel(ses->server, buf, midQ);
spin_lock(&GlobalMid_Lock);
if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
cifs_small_buf_release(buf);
add_credits(ses->server, 1, optype);
return rc;
}
spin_unlock(&GlobalMid_Lock);
}
cifs_small_buf_release(buf);
rc = cifs_sync_mid_result(midQ, ses->server);
if (rc != 0) {
add_credits(ses->server, 1, optype);
return rc;
}
if (!midQ->resp_buf || midQ->mid_state != MID_RESPONSE_RECEIVED) {
rc = -EIO;
cifs_dbg(FYI, "Bad MID state?\n");
goto out;
}
buf = (char *)midQ->resp_buf;
iov[0].iov_base = buf;
iov[0].iov_len = get_rfc1002_length(buf) + 4;
if (midQ->large_buf)
*resp_buf_type = CIFS_LARGE_BUFFER;
else
*resp_buf_type = CIFS_SMALL_BUFFER;
credits = ses->server->ops->get_credits(midQ);
rc = ses->server->ops->check_receive(midQ, ses->server,
flags & CIFS_LOG_ERROR);
/* mark it so buf will not be freed by cifs_delete_mid */
if ((flags & CIFS_NO_RESP) == 0)
midQ->resp_buf = NULL;
out:
cifs_delete_mid(midQ);
add_credits(ses->server, credits, optype);
return rc;
}
int
SendReceive(const unsigned int xid, struct cifs_ses *ses,
struct smb_hdr *in_buf, struct smb_hdr *out_buf,
int *pbytes_returned, const int timeout)
{
int rc = 0;
struct mid_q_entry *midQ;
if (ses == NULL) {
cifs_dbg(VFS, "Null smb session\n");
return -EIO;
}
if (ses->server == NULL) {
cifs_dbg(VFS, "Null tcp session\n");
return -EIO;
}
if (ses->server->tcpStatus == CifsExiting)
return -ENOENT;
/* Ensure that we do not send more than 50 overlapping requests
to the same server. We may make this configurable later or
use ses->maxReq */
if (be32_to_cpu(in_buf->smb_buf_length) > CIFSMaxBufSize +
MAX_CIFS_HDR_SIZE - 4) {
cifs_dbg(VFS, "Illegal length, greater than maximum frame, %d\n",
be32_to_cpu(in_buf->smb_buf_length));
return -EIO;
}
rc = wait_for_free_request(ses->server, timeout, 0);
if (rc)
return rc;
/* make sure that we sign in the same order that we send on this socket
and avoid races inside tcp sendmsg code that could cause corruption
of smb data */
mutex_lock(&ses->server->srv_mutex);
rc = allocate_mid(ses, in_buf, &midQ);
if (rc) {
mutex_unlock(&ses->server->srv_mutex);
/* Update # of requests on wire to server */
add_credits(ses->server, 1, 0);
return rc;
}
rc = cifs_sign_smb(in_buf, ses->server, &midQ->sequence_number);
if (rc) {
mutex_unlock(&ses->server->srv_mutex);
goto out;
}
midQ->mid_state = MID_REQUEST_SUBMITTED;
cifs_in_send_inc(ses->server);
rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
cifs_in_send_dec(ses->server);
cifs_save_when_sent(midQ);
if (rc < 0)
ses->server->sequence_number -= 2;
mutex_unlock(&ses->server->srv_mutex);
if (rc < 0)
goto out;
if (timeout == CIFS_ASYNC_OP)
goto out;
rc = wait_for_response(ses->server, midQ);
if (rc != 0) {
send_cancel(ses->server, in_buf, midQ);
spin_lock(&GlobalMid_Lock);
if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
/* no longer considered to be "in-flight" */
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
add_credits(ses->server, 1, 0);
return rc;
}
spin_unlock(&GlobalMid_Lock);
}
rc = cifs_sync_mid_result(midQ, ses->server);
if (rc != 0) {
add_credits(ses->server, 1, 0);
return rc;
}
if (!midQ->resp_buf || !out_buf ||
midQ->mid_state != MID_RESPONSE_RECEIVED) {
rc = -EIO;
cifs_dbg(VFS, "Bad MID state?\n");
goto out;
}
*pbytes_returned = get_rfc1002_length(midQ->resp_buf);
memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4);
rc = cifs_check_receive(midQ, ses->server, 0);
out:
cifs_delete_mid(midQ);
add_credits(ses->server, 1, 0);
return rc;
}
/* We send a LOCKINGX_CANCEL_LOCK to cause the Windows
blocking lock to return. */
static int
send_lock_cancel(const unsigned int xid, struct cifs_tcon *tcon,
struct smb_hdr *in_buf,
struct smb_hdr *out_buf)
{
int bytes_returned;
struct cifs_ses *ses = tcon->ses;
LOCK_REQ *pSMB = (LOCK_REQ *)in_buf;
/* We just modify the current in_buf to change
the type of lock from LOCKING_ANDX_SHARED_LOCK
or LOCKING_ANDX_EXCLUSIVE_LOCK to
LOCKING_ANDX_CANCEL_LOCK. */
pSMB->LockType = LOCKING_ANDX_CANCEL_LOCK|LOCKING_ANDX_LARGE_FILES;
pSMB->Timeout = 0;
pSMB->hdr.Mid = get_next_mid(ses->server);
return SendReceive(xid, ses, in_buf, out_buf,
&bytes_returned, 0);
}
int
SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
struct smb_hdr *in_buf, struct smb_hdr *out_buf,
int *pbytes_returned)
{
int rc = 0;
int rstart = 0;
struct mid_q_entry *midQ;
struct cifs_ses *ses;
if (tcon == NULL || tcon->ses == NULL) {
cifs_dbg(VFS, "Null smb session\n");
return -EIO;
}
ses = tcon->ses;
if (ses->server == NULL) {
cifs_dbg(VFS, "Null tcp session\n");
return -EIO;
}
if (ses->server->tcpStatus == CifsExiting)
return -ENOENT;
/* Ensure that we do not send more than 50 overlapping requests
to the same server. We may make this configurable later or
use ses->maxReq */
if (be32_to_cpu(in_buf->smb_buf_length) > CIFSMaxBufSize +
MAX_CIFS_HDR_SIZE - 4) {
cifs_dbg(VFS, "Illegal length, greater than maximum frame, %d\n",
be32_to_cpu(in_buf->smb_buf_length));
return -EIO;
}
rc = wait_for_free_request(ses->server, CIFS_BLOCKING_OP, 0);
if (rc)
return rc;
/* make sure that we sign in the same order that we send on this socket
and avoid races inside tcp sendmsg code that could cause corruption
of smb data */
mutex_lock(&ses->server->srv_mutex);
rc = allocate_mid(ses, in_buf, &midQ);
if (rc) {
mutex_unlock(&ses->server->srv_mutex);
return rc;
}
rc = cifs_sign_smb(in_buf, ses->server, &midQ->sequence_number);
if (rc) {
cifs_delete_mid(midQ);
mutex_unlock(&ses->server->srv_mutex);
return rc;
}
midQ->mid_state = MID_REQUEST_SUBMITTED;
cifs_in_send_inc(ses->server);
rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
cifs_in_send_dec(ses->server);
cifs_save_when_sent(midQ);
if (rc < 0)
ses->server->sequence_number -= 2;
mutex_unlock(&ses->server->srv_mutex);
if (rc < 0) {
cifs_delete_mid(midQ);
return rc;
}
/* Wait for a reply - allow signals to interrupt. */
rc = wait_event_interruptible(ses->server->response_q,
(!(midQ->mid_state == MID_REQUEST_SUBMITTED)) ||
((ses->server->tcpStatus != CifsGood) &&
(ses->server->tcpStatus != CifsNew)));
/* Were we interrupted by a signal ? */
if ((rc == -ERESTARTSYS) &&
(midQ->mid_state == MID_REQUEST_SUBMITTED) &&
((ses->server->tcpStatus == CifsGood) ||
(ses->server->tcpStatus == CifsNew))) {
if (in_buf->Command == SMB_COM_TRANSACTION2) {
/* POSIX lock. We send a NT_CANCEL SMB to cause the
blocking lock to return. */
rc = send_cancel(ses->server, in_buf, midQ);
if (rc) {
cifs_delete_mid(midQ);
return rc;
}
} else {
/* Windows lock. We send a LOCKINGX_CANCEL_LOCK
to cause the blocking lock to return. */
rc = send_lock_cancel(xid, tcon, in_buf, out_buf);
/* If we get -ENOLCK back the lock may have
already been removed. Don't exit in this case. */
if (rc && rc != -ENOLCK) {
cifs_delete_mid(midQ);
return rc;
}
}
rc = wait_for_response(ses->server, midQ);
if (rc) {
send_cancel(ses->server, in_buf, midQ);
spin_lock(&GlobalMid_Lock);
if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
/* no longer considered to be "in-flight" */
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
return rc;
}
spin_unlock(&GlobalMid_Lock);
}
/* We got the response - restart system call. */
rstart = 1;
}
rc = cifs_sync_mid_result(midQ, ses->server);
if (rc != 0)
return rc;
/* rcvd frame is ok */
if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_RECEIVED) {
rc = -EIO;
cifs_dbg(VFS, "Bad MID state?\n");
goto out;
}
*pbytes_returned = get_rfc1002_length(midQ->resp_buf);
memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4);
rc = cifs_check_receive(midQ, ses->server, 0);
out:
cifs_delete_mid(midQ);
if (rstart && rc == -EACCES)
return -ERESTARTSYS;
return rc;
}