summaryrefslogtreecommitdiff
path: root/include/linux/sunrpc
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/sunrpc')
-rw-r--r--include/linux/sunrpc/bc_xprt.h7
-rw-r--r--include/linux/sunrpc/cache.h7
-rw-r--r--include/linux/sunrpc/clnt.h5
-rw-r--r--include/linux/sunrpc/debug.h42
-rw-r--r--include/linux/sunrpc/msg_prot.h18
-rw-r--r--include/linux/sunrpc/rpc_pipe_fs.h6
-rw-r--r--include/linux/sunrpc/sched.h7
-rw-r--r--include/linux/sunrpc/svc.h137
-rw-r--r--include/linux/sunrpc/svc_rdma.h31
-rw-r--r--include/linux/sunrpc/svc_xprt.h7
-rw-r--r--include/linux/sunrpc/svcauth.h1
-rw-r--r--include/linux/sunrpc/svcsock.h9
-rw-r--r--include/linux/sunrpc/xdr.h72
-rw-r--r--include/linux/sunrpc/xdrgen/_builtins.h80
-rw-r--r--include/linux/sunrpc/xdrgen/nfs4_1.h112
-rw-r--r--include/linux/sunrpc/xdrgen/nlm4.h233
-rw-r--r--include/linux/sunrpc/xprt.h19
-rw-r--r--include/linux/sunrpc/xprtmultipath.h1
18 files changed, 638 insertions, 156 deletions
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index f22bf915dcf6..98939cb664cf 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -25,12 +25,14 @@ void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task,
void xprt_free_bc_request(struct rpc_rqst *req);
int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
+void xprt_enqueue_bc_request(struct rpc_rqst *req);
/* Socket backchannel transport methods */
int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs);
void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs);
void xprt_free_bc_rqst(struct rpc_rqst *req);
unsigned int xprt_bc_max_slots(struct rpc_xprt *xprt);
+void xprt_svc_destroy_nullify_bc(struct rpc_xprt *xprt, struct svc_serv **serv);
/*
* Determine if a shared backchannel is in use
@@ -68,5 +70,10 @@ static inline void set_bc_enabled(struct svc_serv *serv)
static inline void xprt_free_bc_request(struct rpc_rqst *req)
{
}
+
+static inline void xprt_svc_destroy_nullify_bc(struct rpc_xprt *xprt, struct svc_serv **serv)
+{
+ svc_destroy(serv);
+}
#endif /* CONFIG_SUNRPC_BACKCHANNEL */
#endif /* _LINUX_SUNRPC_BC_XPRT_H */
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index e783132e481f..b1e595c2615b 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -16,6 +16,7 @@
#include <linux/atomic.h>
#include <linux/kstrtox.h>
#include <linux/proc_fs.h>
+#include <linux/wait.h>
/*
* Each cache requires:
@@ -112,7 +113,11 @@ struct cache_detail {
int entries;
/* fields for communication over channel */
- struct list_head queue;
+ struct list_head requests;
+ struct list_head readers;
+ spinlock_t queue_lock;
+ wait_queue_head_t queue_wait;
+ u64 next_seqno;
atomic_t writers; /* how many time is /channel open */
time64_t last_close; /* if no writers, when did last close */
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index fec976e58174..f8b406b0a1af 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -64,7 +64,9 @@ struct rpc_clnt {
cl_noretranstimeo: 1,/* No retransmit timeouts */
cl_autobind : 1,/* use getport() */
cl_chatty : 1,/* be verbose */
- cl_shutdown : 1;/* rpc immediate -EIO */
+ cl_shutdown : 1,/* rpc immediate -EIO */
+ cl_netunreach_fatal : 1;
+ /* Treat ENETUNREACH errors as fatal */
struct xprtsec_parms cl_xprtsec; /* transport security policy */
struct rpc_rtt * cl_rtt; /* RTO estimator data */
@@ -175,6 +177,7 @@ struct rpc_add_xprt_test {
#define RPC_CLNT_CREATE_SOFTERR (1UL << 10)
#define RPC_CLNT_CREATE_REUSEPORT (1UL << 11)
#define RPC_CLNT_CREATE_CONNECTED (1UL << 12)
+#define RPC_CLNT_CREATE_NETUNREACH_FATAL (1UL << 13)
struct rpc_clnt *rpc_create(struct rpc_create_args *args);
struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *,
diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h
index f6aeed07fe04..ab61bed2f7af 100644
--- a/include/linux/sunrpc/debug.h
+++ b/include/linux/sunrpc/debug.h
@@ -14,63 +14,49 @@
/*
* Debugging macros etc
*/
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
extern unsigned int rpc_debug;
extern unsigned int nfs_debug;
extern unsigned int nfsd_debug;
extern unsigned int nlm_debug;
-#endif
#define dprintk(fmt, ...) \
dfprintk(FACILITY, fmt, ##__VA_ARGS__)
-#define dprintk_cont(fmt, ...) \
- dfprintk_cont(FACILITY, fmt, ##__VA_ARGS__)
#define dprintk_rcu(fmt, ...) \
dfprintk_rcu(FACILITY, fmt, ##__VA_ARGS__)
-#define dprintk_rcu_cont(fmt, ...) \
- dfprintk_rcu_cont(FACILITY, fmt, ##__VA_ARGS__)
#undef ifdebug
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
# define ifdebug(fac) if (unlikely(rpc_debug & RPCDBG_##fac))
-# define dfprintk(fac, fmt, ...) \
-do { \
- ifdebug(fac) \
- printk(KERN_DEFAULT fmt, ##__VA_ARGS__); \
-} while (0)
+# if IS_ENABLED(CONFIG_SUNRPC_DEBUG_TRACE)
+# define __sunrpc_printk(fmt, ...) trace_printk(fmt, ##__VA_ARGS__)
+# else
+# define __sunrpc_printk(fmt, ...) printk(KERN_DEFAULT fmt, ##__VA_ARGS__)
+# endif
-# define dfprintk_cont(fac, fmt, ...) \
+# define dfprintk(fac, fmt, ...) \
do { \
ifdebug(fac) \
- printk(KERN_CONT fmt, ##__VA_ARGS__); \
+ __sunrpc_printk(fmt, ##__VA_ARGS__); \
+ else \
+ no_printk(fmt, ##__VA_ARGS__); \
} while (0)
# define dfprintk_rcu(fac, fmt, ...) \
do { \
ifdebug(fac) { \
rcu_read_lock(); \
- printk(KERN_DEFAULT fmt, ##__VA_ARGS__); \
- rcu_read_unlock(); \
- } \
-} while (0)
-
-# define dfprintk_rcu_cont(fac, fmt, ...) \
-do { \
- ifdebug(fac) { \
- rcu_read_lock(); \
- printk(KERN_CONT fmt, ##__VA_ARGS__); \
+ __sunrpc_printk(fmt, ##__VA_ARGS__); \
rcu_read_unlock(); \
+ } else { \
+ no_printk(fmt, ##__VA_ARGS__); \
} \
} while (0)
-# define RPC_IFDEBUG(x) x
#else
# define ifdebug(fac) if (0)
-# define dfprintk(fac, fmt, ...) do {} while (0)
-# define dfprintk_cont(fac, fmt, ...) do {} while (0)
-# define dfprintk_rcu(fac, fmt, ...) do {} while (0)
-# define RPC_IFDEBUG(x)
+# define dfprintk(fac, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
+# define dfprintk_rcu(fac, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
/*
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index c4b0eb2b2f04..ada17b57ca44 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -69,15 +69,17 @@ enum rpc_reject_stat {
};
enum rpc_auth_stat {
- RPC_AUTH_OK = 0,
- RPC_AUTH_BADCRED = 1,
- RPC_AUTH_REJECTEDCRED = 2,
- RPC_AUTH_BADVERF = 3,
- RPC_AUTH_REJECTEDVERF = 4,
- RPC_AUTH_TOOWEAK = 5,
+ RPC_AUTH_OK = 0, /* success */
+ RPC_AUTH_BADCRED = 1, /* bad credential (seal broken) */
+ RPC_AUTH_REJECTEDCRED = 2, /* client must begin new session */
+ RPC_AUTH_BADVERF = 3, /* bad verifier (seal broken) */
+ RPC_AUTH_REJECTEDVERF = 4, /* verifier expired or replayed */
+ RPC_AUTH_TOOWEAK = 5, /* rejected for security reasons */
+ RPC_AUTH_INVALIDRESP = 6, /* bogus response verifier */
+ RPC_AUTH_FAILED = 7, /* reason unknown */
/* RPCSEC_GSS errors */
- RPCSEC_GSS_CREDPROBLEM = 13,
- RPCSEC_GSS_CTXPROBLEM = 14
+ RPCSEC_GSS_CREDPROBLEM = 13, /* no credentials for user */
+ RPCSEC_GSS_CTXPROBLEM = 14 /* problem with context */
};
#define RPC_MAXNETNAMELEN 256
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index 3b35b6f6533a..2cb406f8ff4e 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -98,7 +98,7 @@ static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) {
}
struct rpc_clnt;
-extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
+extern int rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
extern int rpc_remove_client_dir(struct rpc_clnt *);
extern void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh);
@@ -127,9 +127,9 @@ extern void rpc_remove_cache_dir(struct dentry *);
struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags);
void rpc_destroy_pipe_data(struct rpc_pipe *pipe);
-extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *,
+extern int rpc_mkpipe_dentry(struct dentry *, const char *, void *,
struct rpc_pipe *);
-extern int rpc_unlink(struct dentry *);
+extern void rpc_unlink(struct rpc_pipe *);
extern int register_rpc_pipefs(void);
extern void unregister_rpc_pipefs(void);
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index fec1e8a1570c..0dbdf3722537 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -95,10 +95,7 @@ struct rpc_task {
int tk_rpc_status; /* Result of last RPC operation */
unsigned short tk_flags; /* misc flags */
unsigned short tk_timeouts; /* maj timeouts */
-
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
unsigned short tk_pid; /* debugging aid */
-#endif
unsigned char tk_priority : 2,/* Task priority */
tk_garb_retry : 2,
tk_cred_retry : 2;
@@ -134,6 +131,7 @@ struct rpc_task_setup {
#define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */
#define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */
#define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */
+#define RPC_TASK_NETUNREACH_FATAL 0x0040 /* ENETUNREACH is fatal */
#define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */
#define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */
#define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */
@@ -158,7 +156,6 @@ enum {
RPC_TASK_NEED_XMIT,
RPC_TASK_NEED_RECV,
RPC_TASK_MSG_PIN_WAIT,
- RPC_TASK_SIGNALLED,
};
#define rpc_test_and_set_running(t) \
@@ -171,7 +168,7 @@ enum {
#define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
-#define RPC_SIGNALLED(t) test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate)
+#define RPC_SIGNALLED(t) (READ_ONCE(task->tk_rpc_status) == -ERESTARTSYS)
/*
* Task priorities.
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 74658cca0f38..4be6204f6630 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -20,7 +20,7 @@
#include <linux/lwq.h>
#include <linux/wait.h>
#include <linux/mm.h>
-#include <linux/pagevec.h>
+#include <linux/folio_batch.h>
#include <linux/kthread.h>
/*
@@ -35,8 +35,10 @@
*/
struct svc_pool {
unsigned int sp_id; /* pool id; also node id on NUMA */
+ unsigned int sp_nrthreads; /* # of threads currently running in pool */
+ unsigned int sp_nrthrmin; /* Min number of threads to run per pool */
+ unsigned int sp_nrthrmax; /* Max requested number of threads in pool */
struct lwq sp_xprts; /* pending transports */
- unsigned int sp_nrthreads; /* # of threads in pool */
struct list_head sp_all_threads; /* all server threads */
struct llist_head sp_idle_threads; /* idle server threads */
@@ -53,6 +55,7 @@ enum {
SP_TASK_PENDING, /* still work to do even if no xprt is queued */
SP_NEED_VICTIM, /* One thread needs to agree to exit */
SP_VICTIM_REMAINS, /* One thread needs to actually exit */
+ SP_TASK_STARTING, /* Task has started but not added to idle yet */
};
@@ -71,7 +74,7 @@ struct svc_serv {
struct svc_stat * sv_stats; /* RPC statistics */
spinlock_t sv_lock;
unsigned int sv_nprogs; /* Number of sv_programs */
- unsigned int sv_nrthreads; /* # of server threads */
+ unsigned int sv_nrthreads; /* # of running server threads */
unsigned int sv_max_payload; /* datagram payload size */
unsigned int sv_max_mesg; /* max_payload + 1 page for overheads */
unsigned int sv_xdrsize; /* XDR buffer size */
@@ -119,49 +122,74 @@ void svc_destroy(struct svc_serv **svcp);
* Linux limit; someone who cares more about NFS/UDP performance
* can test a larger number.
*
- * For TCP transports we have more freedom. A size of 1MB is
- * chosen to match the client limit. Other OSes are known to
- * have larger limits, but those numbers are probably beyond
- * the point of diminishing returns.
+ * For non-UDP transports we have more freedom. A size of 4MB is
+ * chosen to accommodate clients that support larger I/O sizes.
*/
-#define RPCSVC_MAXPAYLOAD (1*1024*1024u)
-#define RPCSVC_MAXPAYLOAD_TCP RPCSVC_MAXPAYLOAD
-#define RPCSVC_MAXPAYLOAD_UDP (32*1024u)
+enum {
+ RPCSVC_MAXPAYLOAD = 4 * 1024 * 1024,
+ RPCSVC_MAXPAYLOAD_TCP = RPCSVC_MAXPAYLOAD,
+ RPCSVC_MAXPAYLOAD_UDP = 32 * 1024,
+};
extern u32 svc_max_payload(const struct svc_rqst *rqstp);
/*
- * RPC Requests and replies are stored in one or more pages.
- * We maintain an array of pages for each server thread.
- * Requests are copied into these pages as they arrive. Remaining
- * pages are available to write the reply into.
+ * RPC Call and Reply messages each have their own page array.
+ * rq_pages holds the incoming Call message; rq_respages holds
+ * the outgoing Reply message. Both arrays are sized to
+ * svc_serv_maxpages() entries and are allocated dynamically.
+ *
+ * Pages are sent using ->sendmsg with MSG_SPLICE_PAGES so each
+ * server thread needs to allocate more to replace those used in
+ * sending.
*
- * Pages are sent using ->sendmsg with MSG_SPLICE_PAGES so each server thread
- * needs to allocate more to replace those used in sending. To help keep track
- * of these pages we have a receive list where all pages initialy live, and a
- * send list where pages are moved to when there are to be part of a reply.
+ * rq_pages request page contract:
*
- * We use xdr_buf for holding responses as it fits well with NFS
- * read responses (that have a header, and some data pages, and possibly
- * a tail) and means we can share some client side routines.
+ * Transport receive paths that move request data pages out of
+ * rq_pages -- TCP multi-fragment reassembly (svc_tcp_save_pages)
+ * and RDMA Read I/O (svc_rdma_clear_rqst_pages) -- NULL those
+ * entries to prevent svc_rqst_release_pages() from freeing pages
+ * still in transport use, and set rq_pages_nfree to the count.
+ * svc_alloc_arg() refills only that many rq_pages entries.
*
- * The xdr_buf.head kvec always points to the first page in the rq_*pages
- * list. The xdr_buf.pages pointer points to the second page on that
- * list. xdr_buf.tail points to the end of the first page.
- * This assumes that the non-page part of an rpc reply will fit
- * in a page - NFSd ensures this. lockd also has no trouble.
+ * For rq_respages, svc_rqst_release_pages() NULLs entries in
+ * [rq_respages, rq_next_page) after each RPC. svc_alloc_arg()
+ * refills only that range.
*
- * Each request/reply pair can have at most one "payload", plus two pages,
- * one for the request, and one for the reply.
- * We using ->sendfile to return read data, we might need one extra page
- * if the request is not page-aligned. So add another '1'.
+ * xdr_buf holds responses; the structure fits NFS read responses
+ * (header, data pages, optional tail) and enables sharing of
+ * client-side routines.
+ *
+ * The xdr_buf.head kvec always points to the first page in the
+ * rq_*pages list. The xdr_buf.pages pointer points to the second
+ * page on that list. xdr_buf.tail points to the end of the first
+ * page. This assumes that the non-page part of an rpc reply will
+ * fit in a page - NFSd ensures this. lockd also has no trouble.
*/
-#define RPCSVC_MAXPAGES ((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE \
- + 2 + 1)
+
+/**
+ * svc_serv_maxpages - maximum count of pages needed for one RPC message
+ * @serv: RPC service context
+ *
+ * Returns a count of pages or vectors that can hold the maximum
+ * size RPC message for @serv.
+ *
+ * Each page array can hold at most one payload plus two
+ * overhead pages (one for the RPC header, one for tail data).
+ * nfsd_splice_actor() might need an extra page when a READ
+ * payload is not page-aligned.
+ */
+static inline unsigned long svc_serv_maxpages(const struct svc_serv *serv)
+{
+ return DIV_ROUND_UP(serv->sv_max_mesg, PAGE_SIZE) + 2 + 1;
+}
/*
* The context of a single thread, including the request currently being
* processed.
+ *
+ * RPC programs are free to use rq_private to stash thread-local information.
+ * The sunrpc layer will not access it.
*/
struct svc_rqst {
struct list_head rq_all; /* all threads list */
@@ -186,23 +214,23 @@ struct svc_rqst {
struct xdr_buf rq_arg;
struct xdr_stream rq_arg_stream;
struct xdr_stream rq_res_stream;
- struct page *rq_scratch_page;
+ struct folio *rq_scratch_folio;
struct xdr_buf rq_res;
- struct page *rq_pages[RPCSVC_MAXPAGES + 1];
- struct page * *rq_respages; /* points into rq_pages */
+ unsigned long rq_maxpages; /* entries per page array */
+ unsigned long rq_pages_nfree; /* rq_pages entries NULLed by transport */
+ struct page * *rq_pages; /* Call buffer pages */
+ struct page * *rq_respages; /* Reply buffer pages */
struct page * *rq_next_page; /* next reply page to use */
- struct page * *rq_page_end; /* one past the last page */
+ struct page * *rq_page_end; /* one past the last reply page */
struct folio_batch rq_fbatch;
- struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */
- struct bio_vec rq_bvec[RPCSVC_MAXPAGES];
+ struct bio_vec *rq_bvec;
__be32 rq_xid; /* transmission id */
u32 rq_prog; /* program number */
u32 rq_vers; /* program version */
u32 rq_proc; /* procedure number */
u32 rq_prot; /* IP protocol */
- int rq_cachetype; /* catering to nfsd */
unsigned long rq_flags; /* flags field */
ktime_t rq_qtime; /* enqueue time */
@@ -235,10 +263,10 @@ struct svc_rqst {
* initialisation success.
*/
- unsigned long bc_to_initval;
- unsigned int bc_to_retries;
- void ** rq_lease_breaker; /* The v4 client breaking a lease */
+ unsigned long bc_to_initval;
+ unsigned int bc_to_retries;
unsigned int rq_status_counter; /* RPC processing counter */
+ void *rq_private; /* For use by the service thread */
};
/* bits for rq_flags */
@@ -430,13 +458,17 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int,
bool svc_rqst_replace_page(struct svc_rqst *rqstp,
struct page *page);
void svc_rqst_release_pages(struct svc_rqst *rqstp);
+int svc_new_thread(struct svc_serv *serv, struct svc_pool *pool);
void svc_exit_thread(struct svc_rqst *);
struct svc_serv * svc_create_pooled(struct svc_program *prog,
unsigned int nprog,
struct svc_stat *stats,
unsigned int bufsize,
int (*threadfn)(void *data));
-int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
+int svc_set_pool_threads(struct svc_serv *serv, struct svc_pool *pool,
+ unsigned int min_threads, unsigned int max_threads);
+int svc_set_num_threads(struct svc_serv *serv, unsigned int min_threads,
+ unsigned int nrservs);
int svc_pool_stats_open(struct svc_info *si, struct file *file);
void svc_process(struct svc_rqst *rqstp);
void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp);
@@ -452,8 +484,6 @@ const char * svc_proc_name(const struct svc_rqst *rqstp);
int svc_encode_result_payload(struct svc_rqst *rqstp,
unsigned int offset,
unsigned int length);
-unsigned int svc_fill_write_vector(struct svc_rqst *rqstp,
- struct xdr_buf *payload);
char *svc_fill_symlink_pathname(struct svc_rqst *rqstp,
struct kvec *first, void *p,
size_t total);
@@ -468,6 +498,21 @@ int svc_generic_rpcbind_set(struct net *net,
#define RPC_MAX_ADDRBUFLEN (63U)
+/**
+ * svc_rqst_page_release - release a page associated with an RPC transaction
+ * @rqstp: RPC transaction context
+ * @page: page to release
+ *
+ * Released pages are batched and freed together, reducing
+ * allocator pressure under heavy RPC workloads.
+ */
+static inline void svc_rqst_page_release(struct svc_rqst *rqstp,
+ struct page *page)
+{
+ if (!folio_batch_add(&rqstp->rq_fbatch, page_folio(page)))
+ __folio_batch_release(&rqstp->rq_fbatch);
+}
+
/*
* When we want to reduce the size of the reserved space in the response
* buffer, we need to take into account the size of any checksum data that
@@ -495,7 +540,7 @@ static inline void svcxdr_init_decode(struct svc_rqst *rqstp)
buf->len = buf->head->iov_len + buf->page_len + buf->tail->iov_len;
xdr_init_decode(xdr, buf, argv->iov_base, NULL);
- xdr_set_scratch_page(xdr, rqstp->rq_scratch_page);
+ xdr_set_scratch_folio(xdr, rqstp->rq_scratch_folio);
}
/**
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 619fc0bd837a..df6e08aaad57 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -84,6 +84,9 @@ struct svcxprt_rdma {
atomic_t sc_sq_avail; /* SQEs ready to be consumed */
unsigned int sc_sq_depth; /* Depth of SQ */
+ atomic_t sc_sq_ticket_head; /* Next ticket to issue */
+ atomic_t sc_sq_ticket_tail; /* Ticket currently serving */
+ wait_queue_head_t sc_sq_ticket_wait; /* Ticket ordering waitlist */
__be32 sc_fc_credits; /* Forward credits */
u32 sc_max_requests; /* Max requests */
u32 sc_max_bc_requests;/* Backward credits */
@@ -131,7 +134,7 @@ static inline struct svcxprt_rdma *svc_rdma_rqst_rdma(struct svc_rqst *rqstp)
*/
enum {
RPCRDMA_LISTEN_BACKLOG = 10,
- RPCRDMA_MAX_REQUESTS = 64,
+ RPCRDMA_MAX_REQUESTS = 128,
RPCRDMA_MAX_BC_REQUESTS = 2,
};
@@ -202,7 +205,8 @@ struct svc_rdma_recv_ctxt {
struct svc_rdma_pcl rc_reply_pcl;
unsigned int rc_page_count;
- struct page *rc_pages[RPCSVC_MAXPAGES];
+ unsigned long rc_maxpages;
+ struct page *rc_pages[] __counted_by(rc_maxpages);
};
/*
@@ -212,6 +216,7 @@ struct svc_rdma_recv_ctxt {
*/
struct svc_rdma_write_info {
struct svcxprt_rdma *wi_rdma;
+ struct list_head wi_list;
const struct svc_rdma_chunk *wi_chunk;
@@ -240,11 +245,15 @@ struct svc_rdma_send_ctxt {
struct ib_cqe sc_cqe;
struct xdr_buf sc_hdrbuf;
struct xdr_stream sc_stream;
+
+ struct list_head sc_write_info_list;
struct svc_rdma_write_info sc_reply_info;
+
void *sc_xprt_buf;
int sc_page_count;
int sc_cur_sge_no;
- struct page *sc_pages[RPCSVC_MAXPAGES];
+ unsigned long sc_maxpages;
+ struct page **sc_pages;
struct ib_sge sc_sges[];
};
@@ -272,11 +281,14 @@ extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
struct svc_rdma_chunk_ctxt *cc,
enum dma_data_direction dir);
+extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma,
+ struct svc_rdma_send_ctxt *ctxt);
extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *ctxt);
-extern int svc_rdma_send_write_list(struct svcxprt_rdma *rdma,
- const struct svc_rdma_recv_ctxt *rctxt,
- const struct xdr_buf *xdr);
+extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma,
+ const struct svc_rdma_recv_ctxt *rctxt,
+ struct svc_rdma_send_ctxt *sctxt,
+ const struct xdr_buf *xdr);
extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma,
const struct svc_rdma_pcl *write_pcl,
const struct svc_rdma_pcl *reply_pcl,
@@ -304,6 +316,13 @@ extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
struct svc_rdma_recv_ctxt *rctxt,
int status);
extern void svc_rdma_wake_send_waiters(struct svcxprt_rdma *rdma, int avail);
+extern int svc_rdma_sq_wait(struct svcxprt_rdma *rdma,
+ const struct rpc_rdma_cid *cid, int sqecount);
+extern int svc_rdma_post_send_err(struct svcxprt_rdma *rdma,
+ const struct rpc_rdma_cid *cid,
+ const struct ib_send_wr *bad_wr,
+ const struct ib_send_wr *first_wr,
+ int sqecount, int ret);
extern int svc_rdma_sendto(struct svc_rqst *);
extern int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
unsigned int length);
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 72be60952579..da2a2531e110 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -53,6 +53,7 @@ struct svc_xprt {
struct svc_xprt_class *xpt_class;
const struct svc_xprt_ops *xpt_ops;
struct kref xpt_ref;
+ ktime_t xpt_qtime;
struct list_head xpt_list;
struct lwq_node xpt_ready;
unsigned long xpt_flags;
@@ -103,6 +104,9 @@ enum {
* it has access to. It is NOT counted
* in ->sv_tmpcnt.
*/
+ XPT_RPCB_UNREG, /* transport that needs unregistering
+ * with rpcbind (TCP, UDP) on destroy
+ */
};
/*
@@ -164,7 +168,8 @@ int svc_xprt_create(struct svc_serv *serv, const char *xprt_name,
struct net *net, const int family,
const unsigned short port, int flags,
const struct cred *cred);
-void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net);
+void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net,
+ bool unregister);
void svc_xprt_received(struct svc_xprt *xprt);
void svc_xprt_enqueue(struct svc_xprt *xprt);
void svc_xprt_put(struct svc_xprt *xprt);
diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index 2e111153f7cd..4b92fec23a49 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -86,7 +86,6 @@ struct auth_domain {
enum svc_auth_status {
SVC_GARBAGE = 1,
- SVC_SYSERR,
SVC_VALID,
SVC_NEGATIVE,
SVC_OK,
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index bf45d9e8492a..372a00882ca6 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -26,6 +26,9 @@ struct svc_sock {
void (*sk_odata)(struct sock *);
void (*sk_owspace)(struct sock *);
+ /* For sends (protected by xpt_mutex) */
+ struct bio_vec *sk_bvec;
+
/* private TCP part */
/* On-the-wire fragment header: */
__be32 sk_marker;
@@ -40,7 +43,9 @@ struct svc_sock {
struct completion sk_handshake_done;
- struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */
+ /* received data */
+ unsigned long sk_maxpages;
+ struct page * sk_pages[] __counted_by(sk_maxpages);
};
static inline u32 svc_sock_reclen(struct svc_sock *svsk)
@@ -56,7 +61,7 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk)
/*
* Function prototypes.
*/
-void svc_recv(struct svc_rqst *rqstp);
+int svc_recv(struct svc_rqst *rqstp, long timeo);
void svc_send(struct svc_rqst *rqstp);
int svc_addsock(struct svc_serv *serv, struct net *net,
const int fd, char *name_return, const size_t len,
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index a2ab813a9800..b639a6fafcbc 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -119,6 +119,8 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
#define rpc_autherr_badverf cpu_to_be32(RPC_AUTH_BADVERF)
#define rpc_autherr_rejectedverf cpu_to_be32(RPC_AUTH_REJECTEDVERF)
#define rpc_autherr_tooweak cpu_to_be32(RPC_AUTH_TOOWEAK)
+#define rpc_autherr_invalidresp cpu_to_be32(RPC_AUTH_INVALIDRESP)
+#define rpc_autherr_failed cpu_to_be32(RPC_AUTH_FAILED)
#define rpcsec_gsserr_credproblem cpu_to_be32(RPCSEC_GSS_CREDPROBLEM)
#define rpcsec_gsserr_ctxproblem cpu_to_be32(RPCSEC_GSS_CTXPROBLEM)
@@ -128,10 +130,7 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
__be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int len);
__be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int len);
__be32 *xdr_encode_string(__be32 *p, const char *s);
-__be32 *xdr_decode_string_inplace(__be32 *p, char **sp, unsigned int *lenp,
- unsigned int maxlen);
__be32 *xdr_encode_netobj(__be32 *p, const struct xdr_netobj *);
-__be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *);
void xdr_inline_pages(struct xdr_buf *, unsigned int,
struct page **, unsigned int, unsigned int);
@@ -242,8 +241,7 @@ typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
__be32 *p, struct rpc_rqst *rqst);
-extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
- struct page **pages, struct rpc_rqst *rqst);
+void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf);
extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
extern int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes);
extern void __xdr_commit_encode(struct xdr_stream *xdr);
@@ -290,16 +288,16 @@ xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
}
/**
- * xdr_set_scratch_page - Attach a scratch buffer for decoding data
+ * xdr_set_scratch_folio - Attach a scratch buffer for decoding data
* @xdr: pointer to xdr_stream struct
- * @page: an anonymous page
+ * @folio: an anonymous folio
*
* See xdr_set_scratch_buffer().
*/
static inline void
-xdr_set_scratch_page(struct xdr_stream *xdr, struct page *page)
+xdr_set_scratch_folio(struct xdr_stream *xdr, struct folio *folio)
{
- xdr_set_scratch_buffer(xdr, page_address(page), PAGE_SIZE);
+ xdr_set_scratch_buffer(xdr, folio_address(folio), folio_size(folio));
}
/**
@@ -332,7 +330,7 @@ static inline void xdr_commit_encode(struct xdr_stream *xdr)
* xdr_stream_remaining - Return the number of bytes remaining in the stream
* @xdr: pointer to struct xdr_stream
*
- * Return value:
+ * Returns:
* Number of bytes remaining in @xdr before xdr->end
*/
static inline size_t
@@ -341,12 +339,6 @@ xdr_stream_remaining(const struct xdr_stream *xdr)
return xdr->nwords << 2;
}
-ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr,
- size_t size);
-ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr,
- size_t maxlen, gfp_t gfp_flags);
-ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str,
- size_t size);
ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str,
size_t maxlen, gfp_t gfp_flags);
ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor,
@@ -358,7 +350,7 @@ ssize_t xdr_stream_encode_opaque_auth(struct xdr_stream *xdr, u32 flavor,
* xdr_align_size - Calculate padded size of an object
* @n: Size of an object being XDR encoded (in bytes)
*
- * Return value:
+ * Returns:
* Size (in bytes) of the object including xdr padding
*/
static inline size_t
@@ -376,7 +368,7 @@ xdr_align_size(size_t n)
* This implementation avoids the need for conditional
* branches or modulo division.
*
- * Return value:
+ * Returns:
* Size (in bytes) of the needed XDR pad
*/
static inline size_t xdr_pad_size(size_t n)
@@ -388,7 +380,7 @@ static inline size_t xdr_pad_size(size_t n)
* xdr_stream_encode_item_present - Encode a "present" list item
* @xdr: pointer to xdr_stream
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -407,7 +399,7 @@ static inline ssize_t xdr_stream_encode_item_present(struct xdr_stream *xdr)
* xdr_stream_encode_item_absent - Encode a "not present" list item
* @xdr: pointer to xdr_stream
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -427,7 +419,7 @@ static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr)
* @p: address in a buffer into which to encode
* @n: boolean value to encode
*
- * Return value:
+ * Returns:
* Address of item following the encoded boolean
*/
static inline __be32 *xdr_encode_bool(__be32 *p, u32 n)
@@ -441,7 +433,7 @@ static inline __be32 *xdr_encode_bool(__be32 *p, u32 n)
* @xdr: pointer to xdr_stream
* @n: boolean value to encode
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -461,7 +453,7 @@ static inline int xdr_stream_encode_bool(struct xdr_stream *xdr, __u32 n)
* @xdr: pointer to xdr_stream
* @n: integer to encode
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -482,7 +474,7 @@ xdr_stream_encode_u32(struct xdr_stream *xdr, __u32 n)
* @xdr: pointer to xdr_stream
* @n: integer to encode
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -503,7 +495,7 @@ xdr_stream_encode_be32(struct xdr_stream *xdr, __be32 n)
* @xdr: pointer to xdr_stream
* @n: 64-bit integer to encode
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -525,7 +517,7 @@ xdr_stream_encode_u64(struct xdr_stream *xdr, __u64 n)
* @ptr: pointer to void pointer
* @len: size of object
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -550,7 +542,7 @@ xdr_stream_encode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t len)
* @ptr: pointer to opaque data object
* @len: size of object pointed to by @ptr
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -571,7 +563,7 @@ xdr_stream_encode_opaque_fixed(struct xdr_stream *xdr, const void *ptr, size_t l
* @ptr: pointer to opaque data object
* @len: size of object pointed to by @ptr
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -593,7 +585,7 @@ xdr_stream_encode_opaque(struct xdr_stream *xdr, const void *ptr, size_t len)
* @array: array of integers
* @array_size: number of elements in @array
*
- * Return values:
+ * Returns:
* On success, returns length in bytes of XDR buffer consumed
* %-EMSGSIZE on XDR buffer overflow
*/
@@ -616,7 +608,7 @@ xdr_stream_encode_uint32_array(struct xdr_stream *xdr,
* xdr_item_is_absent - symbolically handle XDR discriminators
* @p: pointer to undecoded discriminator
*
- * Return values:
+ * Returns:
* %true if the following XDR item is absent
* %false if the following XDR item is present
*/
@@ -629,7 +621,7 @@ static inline bool xdr_item_is_absent(const __be32 *p)
* xdr_item_is_present - symbolically handle XDR discriminators
* @p: pointer to undecoded discriminator
*
- * Return values:
+ * Returns:
* %true if the following XDR item is present
* %false if the following XDR item is absent
*/
@@ -643,7 +635,7 @@ static inline bool xdr_item_is_present(const __be32 *p)
* @xdr: pointer to xdr_stream
* @ptr: pointer to a u32 in which to store the result
*
- * Return values:
+ * Returns:
* %0 on success
* %-EBADMSG on XDR buffer overflow
*/
@@ -664,7 +656,7 @@ xdr_stream_decode_bool(struct xdr_stream *xdr, __u32 *ptr)
* @xdr: pointer to xdr_stream
* @ptr: location to store integer
*
- * Return values:
+ * Returns:
* %0 on success
* %-EBADMSG on XDR buffer overflow
*/
@@ -685,7 +677,7 @@ xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr)
* @xdr: pointer to xdr_stream
* @ptr: location to store integer
*
- * Return values:
+ * Returns:
* %0 on success
* %-EBADMSG on XDR buffer overflow
*/
@@ -706,7 +698,7 @@ xdr_stream_decode_be32(struct xdr_stream *xdr, __be32 *ptr)
* @xdr: pointer to xdr_stream
* @ptr: location to store 64-bit integer
*
- * Return values:
+ * Returns:
* %0 on success
* %-EBADMSG on XDR buffer overflow
*/
@@ -728,8 +720,8 @@ xdr_stream_decode_u64(struct xdr_stream *xdr, __u64 *ptr)
* @ptr: location to store data
* @len: size of buffer pointed to by @ptr
*
- * Return values:
- * On success, returns size of object stored in @ptr
+ * Returns:
+ * %0 on success
* %-EBADMSG on XDR buffer overflow
*/
static inline ssize_t
@@ -740,7 +732,7 @@ xdr_stream_decode_opaque_fixed(struct xdr_stream *xdr, void *ptr, size_t len)
if (unlikely(!p))
return -EBADMSG;
xdr_decode_opaque_fixed(p, ptr, len);
- return len;
+ return 0;
}
/**
@@ -754,7 +746,7 @@ xdr_stream_decode_opaque_fixed(struct xdr_stream *xdr, void *ptr, size_t len)
* on @xdr. It is therefore expected that the object it points to should
* be processed immediately.
*
- * Return values:
+ * Returns:
* On success, returns size of object stored in *@ptr
* %-EBADMSG on XDR buffer overflow
* %-EMSGSIZE if the size of the object would exceed @maxlen
@@ -785,7 +777,7 @@ xdr_stream_decode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t maxle
* @array: location to store the integer array or NULL
* @array_size: number of elements to store
*
- * Return values:
+ * Returns:
* On success, returns number of elements stored in @array
* %-EBADMSG on XDR buffer overflow
* %-EMSGSIZE if the size of the array exceeds @array_size
diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h
index 66ca3ece951a..a723fb1da9c8 100644
--- a/include/linux/sunrpc/xdrgen/_builtins.h
+++ b/include/linux/sunrpc/xdrgen/_builtins.h
@@ -46,6 +46,66 @@ xdrgen_encode_bool(struct xdr_stream *xdr, bool val)
return true;
}
+/*
+ * De facto (non-standard but commonly implemented) signed short type:
+ * - Wire sends sign-extended 32-bit value (e.g., 0xFFFFFFFF)
+ * - be32_to_cpup() returns u32 (0xFFFFFFFF)
+ * - Explicit (s16) cast truncates to 16 bits (0xFFFF = -1)
+ */
+static inline bool
+xdrgen_decode_short(struct xdr_stream *xdr, s16 *ptr)
+{
+ __be32 *p = xdr_inline_decode(xdr, XDR_UNIT);
+
+ if (unlikely(!p))
+ return false;
+ *ptr = (s16)be32_to_cpup(p);
+ return true;
+}
+
+/*
+ * De facto (non-standard but commonly implemented) signed short type:
+ * - C integer promotion sign-extends s16 val to int before passing to
+ * cpu_to_be32()
+ * - This is well-defined: -1 as s16 -1 as int 0xFFFFFFFF on wire
+ */
+static inline bool
+xdrgen_encode_short(struct xdr_stream *xdr, s16 val)
+{
+ __be32 *p = xdr_reserve_space(xdr, XDR_UNIT);
+
+ if (unlikely(!p))
+ return false;
+ *p = cpu_to_be32(val);
+ return true;
+}
+
+/*
+ * De facto (non-standard but commonly implemented) unsigned short type:
+ * 16-bit integer zero-extended to fill one XDR_UNIT.
+ */
+static inline bool
+xdrgen_decode_unsigned_short(struct xdr_stream *xdr, u16 *ptr)
+{
+ __be32 *p = xdr_inline_decode(xdr, XDR_UNIT);
+
+ if (unlikely(!p))
+ return false;
+ *ptr = (u16)be32_to_cpup(p);
+ return true;
+}
+
+static inline bool
+xdrgen_encode_unsigned_short(struct xdr_stream *xdr, u16 val)
+{
+ __be32 *p = xdr_reserve_space(xdr, XDR_UNIT);
+
+ if (unlikely(!p))
+ return false;
+ *p = cpu_to_be32(val);
+ return true;
+}
+
static inline bool
xdrgen_decode_int(struct xdr_stream *xdr, s32 *ptr)
{
@@ -188,12 +248,10 @@ xdrgen_decode_string(struct xdr_stream *xdr, string *ptr, u32 maxlen)
return false;
if (unlikely(maxlen && len > maxlen))
return false;
- if (len != 0) {
- p = xdr_inline_decode(xdr, len);
- if (unlikely(!p))
- return false;
- ptr->data = (unsigned char *)p;
- }
+ p = xdr_inline_decode(xdr, len);
+ if (unlikely(!p))
+ return false;
+ ptr->data = (unsigned char *)p;
ptr->len = len;
return true;
}
@@ -219,12 +277,10 @@ xdrgen_decode_opaque(struct xdr_stream *xdr, opaque *ptr, u32 maxlen)
return false;
if (unlikely(maxlen && len > maxlen))
return false;
- if (len != 0) {
- p = xdr_inline_decode(xdr, len);
- if (unlikely(!p))
- return false;
- ptr->data = (u8 *)p;
- }
+ p = xdr_inline_decode(xdr, len);
+ if (unlikely(!p))
+ return false;
+ ptr->data = (u8 *)p;
ptr->len = len;
return true;
}
diff --git a/include/linux/sunrpc/xdrgen/nfs4_1.h b/include/linux/sunrpc/xdrgen/nfs4_1.h
index cf21a14aa885..4ac54bdbd335 100644
--- a/include/linux/sunrpc/xdrgen/nfs4_1.h
+++ b/include/linux/sunrpc/xdrgen/nfs4_1.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Generated by xdrgen. Manual edits will be lost. */
/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
-/* XDR specification modification time: Mon Oct 14 09:10:13 2024 */
+/* XDR specification modification time: Thu Jan 8 23:12:07 2026 */
#ifndef _LINUX_XDRGEN_NFS4_1_DEF_H
#define _LINUX_XDRGEN_NFS4_1_DEF_H
@@ -18,6 +18,14 @@ typedef struct {
uint32_t *element;
} bitmap4;
+typedef opaque utf8string;
+
+typedef utf8string utf8str_cis;
+
+typedef utf8string utf8str_cs;
+
+typedef utf8string utf8str_mixed;
+
struct nfstime4 {
int64_t seconds;
uint32_t nseconds;
@@ -40,6 +48,7 @@ enum open_args_share_access4 {
OPEN_ARGS_SHARE_ACCESS_WRITE = 2,
OPEN_ARGS_SHARE_ACCESS_BOTH = 3,
};
+
typedef enum open_args_share_access4 open_args_share_access4;
enum open_args_share_deny4 {
@@ -48,6 +57,7 @@ enum open_args_share_deny4 {
OPEN_ARGS_SHARE_DENY_WRITE = 2,
OPEN_ARGS_SHARE_DENY_BOTH = 3,
};
+
typedef enum open_args_share_deny4 open_args_share_deny4;
enum open_args_share_access_want4 {
@@ -59,6 +69,7 @@ enum open_args_share_access_want4 {
OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 20,
OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 21,
};
+
typedef enum open_args_share_access_want4 open_args_share_access_want4;
enum open_args_open_claim4 {
@@ -70,6 +81,7 @@ enum open_args_open_claim4 {
OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH = 5,
OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH = 6,
};
+
typedef enum open_args_open_claim4 open_args_open_claim4;
enum open_args_createmode4 {
@@ -78,10 +90,15 @@ enum open_args_createmode4 {
OPEN_ARGS_CREATEMODE_EXCLUSIVE4 = 2,
OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1 = 3,
};
+
typedef enum open_args_createmode4 open_args_createmode4;
typedef struct open_arguments4 fattr4_open_arguments;
+/*
+ * Determine what OPEN supports.
+ */
+
enum { FATTR4_OPEN_ARGUMENTS = 86 };
enum { OPEN4_RESULT_NO_OPEN_STATEID = 0x00000010 };
@@ -90,6 +107,11 @@ typedef struct nfstime4 fattr4_time_deleg_access;
typedef struct nfstime4 fattr4_time_deleg_modify;
+/*
+ * New RECOMMENDED Attribute for
+ * delegation caching of times
+ */
+
enum { FATTR4_TIME_DELEG_ACCESS = 84 };
enum { FATTR4_TIME_DELEG_MODIFY = 85 };
@@ -124,13 +146,88 @@ enum open_delegation_type4 {
OPEN_DELEGATE_READ_ATTRS_DELEG = 4,
OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5,
};
+
typedef enum open_delegation_type4 open_delegation_type4;
+enum aclmodel4 {
+ ACL_MODEL_NFS4 = 1,
+ ACL_MODEL_POSIX_DRAFT = 2,
+ ACL_MODEL_NONE = 3,
+};
+
+typedef enum aclmodel4 aclmodel4;
+
+enum aclscope4 {
+ ACL_SCOPE_FILE_OBJECT = 1,
+ ACL_SCOPE_FILE_SYSTEM = 2,
+ ACL_SCOPE_SERVER = 3,
+};
+
+typedef enum aclscope4 aclscope4;
+
+enum posixacetag4 {
+ POSIXACE4_TAG_USER_OBJ = 1,
+ POSIXACE4_TAG_USER = 2,
+ POSIXACE4_TAG_GROUP_OBJ = 3,
+ POSIXACE4_TAG_GROUP = 4,
+ POSIXACE4_TAG_MASK = 5,
+ POSIXACE4_TAG_OTHER = 6,
+};
+
+typedef enum posixacetag4 posixacetag4;
+
+typedef uint32_t posixaceperm4;
+
+enum { POSIXACE4_PERM_EXECUTE = 0x00000001 };
+
+enum { POSIXACE4_PERM_WRITE = 0x00000002 };
+
+enum { POSIXACE4_PERM_READ = 0x00000004 };
+
+struct posixace4 {
+ posixacetag4 tag;
+ posixaceperm4 perm;
+ utf8str_mixed who;
+};
+
+typedef aclmodel4 fattr4_acl_trueform;
+
+typedef aclscope4 fattr4_acl_trueform_scope;
+
+typedef struct {
+ u32 count;
+ struct posixace4 *element;
+} fattr4_posix_default_acl;
+
+typedef struct {
+ u32 count;
+ struct posixace4 *element;
+} fattr4_posix_access_acl;
+
+/*
+ * New for POSIX ACL extension
+ */
+
+enum { FATTR4_ACL_TRUEFORM = 89 };
+
+enum { FATTR4_ACL_TRUEFORM_SCOPE = 90 };
+
+enum { FATTR4_POSIX_DEFAULT_ACL = 91 };
+
+enum { FATTR4_POSIX_ACCESS_ACL = 92 };
+
#define NFS4_int64_t_sz \
(XDR_hyper)
#define NFS4_uint32_t_sz \
(XDR_unsigned_int)
#define NFS4_bitmap4_sz (XDR_unsigned_int)
+#define NFS4_utf8string_sz (XDR_unsigned_int)
+#define NFS4_utf8str_cis_sz \
+ (NFS4_utf8string_sz)
+#define NFS4_utf8str_cs_sz \
+ (NFS4_utf8string_sz)
+#define NFS4_utf8str_mixed_sz \
+ (NFS4_utf8string_sz)
#define NFS4_nfstime4_sz \
(NFS4_int64_t_sz + NFS4_uint32_t_sz)
#define NFS4_fattr4_offline_sz \
@@ -149,5 +246,18 @@ typedef enum open_delegation_type4 open_delegation_type4;
#define NFS4_fattr4_time_deleg_modify_sz \
(NFS4_nfstime4_sz)
#define NFS4_open_delegation_type4_sz (XDR_int)
+#define NFS4_aclmodel4_sz (XDR_int)
+#define NFS4_aclscope4_sz (XDR_int)
+#define NFS4_posixacetag4_sz (XDR_int)
+#define NFS4_posixaceperm4_sz \
+ (NFS4_uint32_t_sz)
+#define NFS4_posixace4_sz \
+ (NFS4_posixacetag4_sz + NFS4_posixaceperm4_sz + NFS4_utf8str_mixed_sz)
+#define NFS4_fattr4_acl_trueform_sz \
+ (NFS4_aclmodel4_sz)
+#define NFS4_fattr4_acl_trueform_scope_sz \
+ (NFS4_aclscope4_sz)
+#define NFS4_fattr4_posix_default_acl_sz (XDR_unsigned_int)
+#define NFS4_fattr4_posix_access_acl_sz (XDR_unsigned_int)
#endif /* _LINUX_XDRGEN_NFS4_1_DEF_H */
diff --git a/include/linux/sunrpc/xdrgen/nlm4.h b/include/linux/sunrpc/xdrgen/nlm4.h
new file mode 100644
index 000000000000..e95e8f105624
--- /dev/null
+++ b/include/linux/sunrpc/xdrgen/nlm4.h
@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Generated by xdrgen. Manual edits will be lost. */
+/* XDR specification file: ../../Documentation/sunrpc/xdr/nlm4.x */
+/* XDR specification modification time: Thu Dec 25 13:10:19 2025 */
+
+#ifndef _LINUX_XDRGEN_NLM4_DEF_H
+#define _LINUX_XDRGEN_NLM4_DEF_H
+
+#include <linux/types.h>
+#include <linux/sunrpc/xdrgen/_defs.h>
+
+enum { LM_MAXSTRLEN = 1024 };
+
+enum { LM_MAXNAMELEN = 1025 };
+
+enum { MAXNETOBJ_SZ = 1024 };
+
+typedef opaque netobj;
+
+enum fsh4_mode {
+ fsm_DN = 0,
+ fsm_DR = 1,
+ fsm_DW = 2,
+ fsm_DRW = 3,
+};
+
+typedef enum fsh4_mode fsh4_mode;
+
+enum fsh4_access {
+ fsa_NONE = 0,
+ fsa_R = 1,
+ fsa_W = 2,
+ fsa_RW = 3,
+};
+
+typedef enum fsh4_access fsh4_access;
+
+enum { SM_MAXSTRLEN = 1024 };
+
+typedef u64 uint64;
+
+typedef s64 int64;
+
+typedef u32 uint32;
+
+typedef s32 int32;
+
+enum nlm4_stats {
+ NLM4_GRANTED = 0,
+ NLM4_DENIED = 1,
+ NLM4_DENIED_NOLOCKS = 2,
+ NLM4_BLOCKED = 3,
+ NLM4_DENIED_GRACE_PERIOD = 4,
+ NLM4_DEADLCK = 5,
+ NLM4_ROFS = 6,
+ NLM4_STALE_FH = 7,
+ NLM4_FBIG = 8,
+ NLM4_FAILED = 9,
+};
+
+typedef __be32 nlm4_stats;
+
+struct nlm4_holder {
+ bool exclusive;
+ int32 svid;
+ netobj oh;
+ uint64 l_offset;
+ uint64 l_len;
+};
+
+struct nlm4_testrply {
+ nlm4_stats stat;
+ union {
+ struct nlm4_holder holder;
+ } u;
+};
+
+struct nlm4_stat {
+ nlm4_stats stat;
+};
+
+struct nlm4_res {
+ netobj cookie;
+ struct nlm4_stat stat;
+};
+
+struct nlm4_testres {
+ netobj cookie;
+ struct nlm4_testrply stat;
+};
+
+struct nlm4_lock {
+ string caller_name;
+ netobj fh;
+ netobj oh;
+ int32 svid;
+ uint64 l_offset;
+ uint64 l_len;
+};
+
+struct nlm4_lockargs {
+ netobj cookie;
+ bool block;
+ bool exclusive;
+ struct nlm4_lock alock;
+ bool reclaim;
+ int32 state;
+};
+
+struct nlm4_cancargs {
+ netobj cookie;
+ bool block;
+ bool exclusive;
+ struct nlm4_lock alock;
+};
+
+struct nlm4_testargs {
+ netobj cookie;
+ bool exclusive;
+ struct nlm4_lock alock;
+};
+
+struct nlm4_unlockargs {
+ netobj cookie;
+ struct nlm4_lock alock;
+};
+
+struct nlm4_share {
+ string caller_name;
+ netobj fh;
+ netobj oh;
+ fsh4_mode mode;
+ fsh4_access access;
+};
+
+struct nlm4_shareargs {
+ netobj cookie;
+ struct nlm4_share share;
+ bool reclaim;
+};
+
+struct nlm4_shareres {
+ netobj cookie;
+ nlm4_stats stat;
+ int32 sequence;
+};
+
+struct nlm4_notify {
+ string name;
+ int32 state;
+};
+
+enum { SM_PRIV_SIZE = 16 };
+
+struct nlm4_notifyargs {
+ struct nlm4_notify notify;
+ u8 private[SM_PRIV_SIZE];
+};
+
+enum {
+ NLMPROC4_NULL = 0,
+ NLMPROC4_TEST = 1,
+ NLMPROC4_LOCK = 2,
+ NLMPROC4_CANCEL = 3,
+ NLMPROC4_UNLOCK = 4,
+ NLMPROC4_GRANTED = 5,
+ NLMPROC4_TEST_MSG = 6,
+ NLMPROC4_LOCK_MSG = 7,
+ NLMPROC4_CANCEL_MSG = 8,
+ NLMPROC4_UNLOCK_MSG = 9,
+ NLMPROC4_GRANTED_MSG = 10,
+ NLMPROC4_TEST_RES = 11,
+ NLMPROC4_LOCK_RES = 12,
+ NLMPROC4_CANCEL_RES = 13,
+ NLMPROC4_UNLOCK_RES = 14,
+ NLMPROC4_GRANTED_RES = 15,
+ NLMPROC4_SM_NOTIFY = 16,
+ NLMPROC4_SHARE = 20,
+ NLMPROC4_UNSHARE = 21,
+ NLMPROC4_NM_LOCK = 22,
+ NLMPROC4_FREE_ALL = 23,
+};
+
+#ifndef NLM4_PROG
+#define NLM4_PROG (100021)
+#endif
+
+#define NLM4_netobj_sz (XDR_unsigned_int + XDR_QUADLEN(MAXNETOBJ_SZ))
+#define NLM4_fsh4_mode_sz (XDR_int)
+#define NLM4_fsh4_access_sz (XDR_int)
+#define NLM4_uint64_sz \
+ (XDR_unsigned_hyper)
+#define NLM4_int64_sz \
+ (XDR_hyper)
+#define NLM4_uint32_sz \
+ (XDR_unsigned_long)
+#define NLM4_int32_sz \
+ (XDR_long)
+#define NLM4_nlm4_stats_sz (XDR_int)
+#define NLM4_nlm4_holder_sz \
+ (XDR_bool + NLM4_int32_sz + NLM4_netobj_sz + NLM4_uint64_sz + NLM4_uint64_sz)
+#define NLM4_nlm4_testrply_sz \
+ (NLM4_nlm4_stats_sz + NLM4_nlm4_holder_sz)
+#define NLM4_nlm4_stat_sz \
+ (NLM4_nlm4_stats_sz)
+#define NLM4_nlm4_res_sz \
+ (NLM4_netobj_sz + NLM4_nlm4_stat_sz)
+#define NLM4_nlm4_testres_sz \
+ (NLM4_netobj_sz + NLM4_nlm4_testrply_sz)
+#define NLM4_nlm4_lock_sz \
+ (XDR_unsigned_int + XDR_QUADLEN(LM_MAXSTRLEN) + NLM4_netobj_sz + NLM4_netobj_sz + NLM4_int32_sz + NLM4_uint64_sz + NLM4_uint64_sz)
+#define NLM4_nlm4_lockargs_sz \
+ (NLM4_netobj_sz + XDR_bool + XDR_bool + NLM4_nlm4_lock_sz + XDR_bool + NLM4_int32_sz)
+#define NLM4_nlm4_cancargs_sz \
+ (NLM4_netobj_sz + XDR_bool + XDR_bool + NLM4_nlm4_lock_sz)
+#define NLM4_nlm4_testargs_sz \
+ (NLM4_netobj_sz + XDR_bool + NLM4_nlm4_lock_sz)
+#define NLM4_nlm4_unlockargs_sz \
+ (NLM4_netobj_sz + NLM4_nlm4_lock_sz)
+#define NLM4_nlm4_share_sz \
+ (XDR_unsigned_int + XDR_QUADLEN(LM_MAXSTRLEN) + NLM4_netobj_sz + NLM4_netobj_sz + NLM4_fsh4_mode_sz + NLM4_fsh4_access_sz)
+#define NLM4_nlm4_shareargs_sz \
+ (NLM4_netobj_sz + NLM4_nlm4_share_sz + XDR_bool)
+#define NLM4_nlm4_shareres_sz \
+ (NLM4_netobj_sz + NLM4_nlm4_stats_sz + NLM4_int32_sz)
+#define NLM4_nlm4_notify_sz \
+ (XDR_unsigned_int + XDR_QUADLEN(LM_MAXNAMELEN) + NLM4_int32_sz)
+#define NLM4_nlm4_notifyargs_sz \
+ (NLM4_nlm4_notify_sz + XDR_QUADLEN(SM_PRIV_SIZE))
+#define NLM4_MAX_ARGS_SZ \
+ (NLM4_nlm4_lockargs_sz)
+
+#endif /* _LINUX_XDRGEN_NLM4_DEF_H */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 81b952649d35..a82045804d34 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -30,6 +30,8 @@
#define RPC_MAXCWND(xprt) ((xprt)->max_reqs << RPC_CWNDSHIFT)
#define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
+#define RPC_GSS_SEQNO_ARRAY_SIZE 3U
+
enum rpc_display_format_t {
RPC_DISPLAY_ADDR = 0,
RPC_DISPLAY_PORT,
@@ -66,7 +68,8 @@ struct rpc_rqst {
struct rpc_cred * rq_cred; /* Bound cred */
__be32 rq_xid; /* request XID */
int rq_cong; /* has incremented xprt->cong */
- u32 rq_seqno; /* gss seq no. used on req. */
+ u32 rq_seqnos[RPC_GSS_SEQNO_ARRAY_SIZE]; /* past gss req seq nos. */
+ unsigned int rq_seqno_count; /* number of entries in rq_seqnos */
int rq_enc_pages_num;
struct page **rq_enc_pages; /* scratch pages for use by
gss privacy code */
@@ -119,6 +122,18 @@ struct rpc_rqst {
#define rq_svec rq_snd_buf.head
#define rq_slen rq_snd_buf.len
+static inline int xprt_rqst_add_seqno(struct rpc_rqst *req, u32 seqno)
+{
+ if (likely(req->rq_seqno_count < RPC_GSS_SEQNO_ARRAY_SIZE))
+ req->rq_seqno_count++;
+
+ /* Shift array to make room for the newest element at the beginning */
+ memmove(&req->rq_seqnos[1], &req->rq_seqnos[0],
+ (RPC_GSS_SEQNO_ARRAY_SIZE - 1) * sizeof(req->rq_seqnos[0]));
+ req->rq_seqnos[0] = seqno;
+ return 0;
+}
+
/* RPC transport layer security policies */
enum xprtsec_policies {
RPC_XPRTSEC_NONE = 0,
@@ -389,6 +404,8 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size,
unsigned int max_req);
void xprt_free(struct rpc_xprt *);
void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task);
+void xprt_add_backlog_noncongested(struct rpc_xprt *xprt,
+ struct rpc_task *task);
bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req);
void xprt_cleanup_ids(void);
diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h
index e411368cdacf..e4db5022fe92 100644
--- a/include/linux/sunrpc/xprtmultipath.h
+++ b/include/linux/sunrpc/xprtmultipath.h
@@ -56,6 +56,7 @@ extern void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps,
struct rpc_xprt *xprt);
extern void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps,
struct rpc_xprt *xprt, bool offline);
+extern struct rpc_xprt *rpc_xprt_switch_get_main_xprt(struct rpc_xprt_switch *xps);
extern void xprt_iter_init(struct rpc_xprt_iter *xpi,
struct rpc_xprt_switch *xps);