In order to support multipathing/trunking we will need the ability to track multiple transports. This patch sets up a basic structure for doing so. Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx> --- include/linux/sunrpc/xprt.h | 5 + include/linux/sunrpc/xprtmultipath.h | 69 +++++ net/sunrpc/Makefile | 3 +- net/sunrpc/xprt.c | 1 + net/sunrpc/xprtmultipath.c | 473 +++++++++++++++++++++++++++++++++++ 5 files changed, 550 insertions(+), 1 deletion(-) create mode 100644 include/linux/sunrpc/xprtmultipath.h create mode 100644 net/sunrpc/xprtmultipath.c diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 83218129ff28..fb0d212e0d3a 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -198,6 +198,11 @@ struct rpc_xprt { unsigned int bind_index; /* bind function index */ /* + * Multipath + */ + struct list_head xprt_switch; + + /* * Connection of transports */ unsigned long bind_timeout, diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h new file mode 100644 index 000000000000..5a9acffa41be --- /dev/null +++ b/include/linux/sunrpc/xprtmultipath.h @@ -0,0 +1,69 @@ +/* + * RPC client multipathing definitions + * + * Copyright (c) 2015, 2016, Primary Data, Inc. All rights reserved. + * + * Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx> + */ +#ifndef _NET_SUNRPC_XPRTMULTIPATH_H +#define _NET_SUNRPC_XPRTMULTIPATH_H + +struct rpc_xprt_iter_ops; +struct rpc_xprt_switch { + spinlock_t xps_lock; + struct kref xps_kref; + + unsigned int xps_nxprts; + struct list_head xps_xprt_list; + + struct net * xps_net; + + const struct rpc_xprt_iter_ops *xps_iter_ops; + + struct rcu_head xps_rcu; +}; + +struct rpc_xprt_iter { + struct rpc_xprt_switch __rcu *xpi_xpswitch; + struct rpc_xprt * xpi_cursor; + + const struct rpc_xprt_iter_ops *xpi_ops; +}; + + +struct rpc_xprt_iter_ops { + void (*xpi_rewind)(struct rpc_xprt_iter *); + struct rpc_xprt *(*xpi_xprt)(struct rpc_xprt_iter *); + struct rpc_xprt *(*xpi_next)(struct rpc_xprt_iter *); +}; + +extern struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, + gfp_t gfp_flags); + +extern struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps); +extern void xprt_switch_put(struct rpc_xprt_switch *xps); + +extern void rpc_xprt_switch_set_roundrobin(struct rpc_xprt_switch *xps); + +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); + +extern void xprt_iter_init(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps); + +extern void xprt_iter_init_listall(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps); + +extern void xprt_iter_destroy(struct rpc_xprt_iter *xpi); + +extern struct rpc_xprt_switch *xprt_iter_xchg_switch( + struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *newswitch); + +extern struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi); +extern struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi); +extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); + +#endif diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index b512fbd9d79a..ea7ffa12e0f9 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -12,7 +12,8 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ - svc_xprt.o + svc_xprt.o \ + xprtmultipath.o sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o sunrpc-$(CONFIG_PROC_FS) += stats.o diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 605858699f6c..323b332f8f7c 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1319,6 +1319,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) spin_lock_init(&xprt->bc_pa_lock); INIT_LIST_HEAD(&xprt->bc_pa_list); #endif /* CONFIG_SUNRPC_BACKCHANNEL */ + INIT_LIST_HEAD(&xprt->xprt_switch); xprt->last_used = jiffies; xprt->cwnd = RPC_INITCWND; diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c new file mode 100644 index 000000000000..0924b3b39e43 --- /dev/null +++ b/net/sunrpc/xprtmultipath.c @@ -0,0 +1,473 @@ +/* + * Multipath support for RPC + * + * Copyright (c) 2015, 2016, Primary Data, Inc. All rights reserved. + * + * Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx> + * + */ +#include <linux/types.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/rcupdate.h> +#include <linux/rculist.h> +#include <linux/slab.h> +#include <asm/cmpxchg.h> +#include <linux/spinlock.h> +#include <linux/sunrpc/xprt.h> +#include <linux/sunrpc/xprtmultipath.h> + +typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct list_head *head, + const struct rpc_xprt *cur); + +static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular; +static const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin; +static const struct rpc_xprt_iter_ops rpc_xprt_iter_listall; + +static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, + struct rpc_xprt *xprt) +{ + if (unlikely(xprt_get(xprt) == NULL)) + return; + list_add_tail_rcu(&xprt->xprt_switch, &xps->xps_xprt_list); + smp_wmb(); + if (xps->xps_nxprts == 0) + xps->xps_net = xprt->xprt_net; + xps->xps_nxprts++; +} + +/** + * rpc_xprt_switch_add_xprt - Add a new rpc_xprt to an rpc_xprt_switch + * @xps - pointer to struct rpc_xprt_switch + * @xprt - pointer to struct rpc_xprt + * + * Adds xprt to the end of the list of struct rpc_xprt in xps. + */ +void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps, + struct rpc_xprt *xprt) +{ + if (xprt == NULL) + return; + spin_lock(&xps->xps_lock); + if (xps->xps_net != xprt->xprt_net || xps->xps_net == NULL) + xprt_switch_add_xprt_locked(xps, xprt); + spin_unlock(&xps->xps_lock); +} + +static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps, + struct rpc_xprt *xprt) +{ + if (unlikely(xprt == NULL)) + return; + xps->xps_nxprts--; + if (xps->xps_nxprts == 0) + xps->xps_net = NULL; + smp_wmb(); + list_del_rcu(&xprt->xprt_switch); +} + +/** + * rpc_xprt_switch_remove_xprt - Removes an rpc_xprt from a rpc_xprt_switch + * @xps - pointer to struct rpc_xprt_switch + * @xprt - pointer to struct rpc_xprt + * + * Removes xprt from the list of struct rpc_xprt in xps. + */ +void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, + struct rpc_xprt *xprt) +{ + spin_lock(&xps->xps_lock); + xprt_switch_remove_xprt_locked(xps, xprt); + spin_unlock(&xps->xps_lock); + xprt_put(xprt); +} + +/** + * xprt_switch_alloc - Allocate a new struct rpc_xprt_switch + * @xprt - pointer to struct rpc_xprt + * @gfp_flags - allocation flags + * + * On success, returns an initialised struct rpc_xprt_switch, containing + * the entry xprt. Returns NULL on failure. + */ +struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, + gfp_t gfp_flags) +{ + struct rpc_xprt_switch *xps; + + xps = kmalloc(sizeof(*xps), gfp_flags); + if (xps != NULL) { + spin_lock_init(&xps->xps_lock); + kref_init(&xps->xps_kref); + xps->xps_nxprts = 0; + INIT_LIST_HEAD(&xps->xps_xprt_list); + xps->xps_iter_ops = &rpc_xprt_iter_singular; + xprt_switch_add_xprt_locked(xps, xprt); + } + + return xps; +} + +static void xprt_switch_free_entries(struct rpc_xprt_switch *xps) +{ + spin_lock(&xps->xps_lock); + while (!list_empty(&xps->xps_xprt_list)) { + struct rpc_xprt *xprt; + + xprt = list_first_entry(&xps->xps_xprt_list, + struct rpc_xprt, xprt_switch); + xprt_switch_remove_xprt_locked(xps, xprt); + spin_unlock(&xps->xps_lock); + xprt_put(xprt); + spin_lock(&xps->xps_lock); + } + spin_unlock(&xps->xps_lock); +} + +static void xprt_switch_free(struct kref *kref) +{ + struct rpc_xprt_switch *xps = container_of(kref, + struct rpc_xprt_switch, xps_kref); + + xprt_switch_free_entries(xps); + kfree_rcu(xps, xps_rcu); +} + +/** + * xprt_switch_get - Return a reference to a rpc_xprt_switch + * @xps - pointer to struct rpc_xprt_switch + * + * Returns a reference to xps unless the refcount is already zero. + */ +struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps) +{ + if (xps != NULL && kref_get_unless_zero(&xps->xps_kref)) + return xps; + return NULL; +} + +/** + * xprt_switch_put - Release a reference to a rpc_xprt_switch + * @xps - pointer to struct rpc_xprt_switch + * + * Release the reference to xps, and free it once the refcount is zero. + */ +void xprt_switch_put(struct rpc_xprt_switch *xps) +{ + if (xps != NULL) + kref_put(&xps->xps_kref, xprt_switch_free); +} + +/** + * rpc_xprt_switch_set_roundrobin - Set a round-robin policy on rpc_xprt_switch + * @xps - pointer to struct rpc_xprt_switch + * + * Sets a round-robin default policy for iterators acting on xps. + */ +void rpc_xprt_switch_set_roundrobin(struct rpc_xprt_switch *xps) +{ + if (READ_ONCE(xps->xps_iter_ops) != &rpc_xprt_iter_roundrobin) + WRITE_ONCE(xps->xps_iter_ops, &rpc_xprt_iter_roundrobin); +} + +static +const struct rpc_xprt_iter_ops *xprt_iter_ops(const struct rpc_xprt_iter *xpi) +{ + if (xpi->xpi_ops != NULL) + return xpi->xpi_ops; + return rcu_dereference(xpi->xpi_xpswitch)->xps_iter_ops; +} + +static +void xprt_iter_no_rewind(struct rpc_xprt_iter *xpi) +{ +} + +static +void xprt_iter_default_rewind(struct rpc_xprt_iter *xpi) +{ + xchg_relaxed(&xpi->xpi_cursor, NULL); +} + +static +struct rpc_xprt *xprt_switch_find_first_entry(struct list_head *head) +{ + return list_first_or_null_rcu(head, struct rpc_xprt, xprt_switch); +} + +static +struct rpc_xprt *xprt_iter_first_entry(struct rpc_xprt_iter *xpi) +{ + struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); + + if (xps == NULL) + return NULL; + return xprt_switch_find_first_entry(&xps->xps_xprt_list); +} + +static +struct rpc_xprt *xprt_switch_find_current_entry(struct list_head *head, + const struct rpc_xprt *cur) +{ + struct rpc_xprt *pos; + + list_for_each_entry_rcu(pos, head, xprt_switch) { + if (cur == pos) + return pos; + } + return NULL; +} + +static +struct rpc_xprt *xprt_iter_current_entry(struct rpc_xprt_iter *xpi) +{ + struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); + struct list_head *head; + + if (xps == NULL) + return NULL; + head = &xps->xps_xprt_list; + if (xpi->xpi_cursor == NULL || xps->xps_nxprts < 2) + return xprt_switch_find_first_entry(head); + return xprt_switch_find_current_entry(head, xpi->xpi_cursor); +} + +static +struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head, + const struct rpc_xprt *cur) +{ + struct rpc_xprt *pos, *prev = NULL; + + list_for_each_entry_rcu(pos, head, xprt_switch) { + if (cur == prev) + return pos; + prev = pos; + } + return NULL; +} + +static +struct rpc_xprt *xprt_switch_set_next_cursor(struct list_head *head, + struct rpc_xprt **cursor, + xprt_switch_find_xprt_t find_next) +{ + struct rpc_xprt *cur, *pos, *old; + + cur = READ_ONCE(*cursor); + for (;;) { + old = cur; + pos = find_next(head, old); + cur = cmpxchg_relaxed(cursor, old, pos); + if (cur == old) + break; + } + return pos; +} + +static +struct rpc_xprt *xprt_iter_next_entry_multiple(struct rpc_xprt_iter *xpi, + xprt_switch_find_xprt_t find_next) +{ + struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); + struct list_head *head; + + if (xps == NULL) + return NULL; + head = &xps->xps_xprt_list; + if (xps->xps_nxprts < 2) + return xprt_switch_find_first_entry(head); + return xprt_switch_set_next_cursor(head, &xpi->xpi_cursor, find_next); +} + +static +struct rpc_xprt *xprt_switch_find_next_entry_roundrobin(struct list_head *head, + const struct rpc_xprt *cur) +{ + struct rpc_xprt *ret; + + ret = xprt_switch_find_next_entry(head, cur); + if (ret != NULL) + return ret; + return xprt_switch_find_first_entry(head); +} + +static +struct rpc_xprt *xprt_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi) +{ + return xprt_iter_next_entry_multiple(xpi, + xprt_switch_find_next_entry_roundrobin); +} + +static +struct rpc_xprt *xprt_iter_next_entry_all(struct rpc_xprt_iter *xpi) +{ + return xprt_iter_next_entry_multiple(xpi, xprt_switch_find_next_entry); +} + +/* + * xprt_iter_rewind - Resets the xprt iterator + * @xpi - pointer to rpc_xprt_iter + * + * Resets xpi to ensure that it points to the first entry in the list + * of transports. + */ +static +void xprt_iter_rewind(struct rpc_xprt_iter *xpi) +{ + rcu_read_lock(); + xprt_iter_ops(xpi)->xpi_rewind(xpi); + rcu_read_unlock(); +} + +static void __xprt_iter_init(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps, + const struct rpc_xprt_iter_ops *ops) +{ + rcu_assign_pointer(xpi->xpi_xpswitch, xprt_switch_get(xps)); + xpi->xpi_cursor = NULL; + xpi->xpi_ops = ops; +} + +/** + * xprt_iter_init - Initialise an xprt iterator + * @xpi - pointer to rpc_xprt_iter + * @xps - pointer to rpc_xprt_switch + * + * Initialises the iterator to use the default iterator ops + * as set in xps. This function is mainly intended for internal + * use in the rpc_client. + */ +void xprt_iter_init(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps) +{ + __xprt_iter_init(xpi, xps, NULL); +} + +/** + * xprt_iter_init_listall - Initialise an xprt iterator + * @xpi - pointer to rpc_xprt_iter + * @xps - pointer to rpc_xprt_switch + * + * Initialises the iterator to iterate once through the entire list + * of entries in xps. + */ +void xprt_iter_init_listall(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *xps) +{ + __xprt_iter_init(xpi, xps, &rpc_xprt_iter_listall); +} + +/** + * xprt_iter_xchg_switch - Atomically swap out the rpc_xprt_switch + * @xpi - pointer to rpc_xprt_iter + * @xps - pointer to a new rpc_xprt_switch or NULL + * + * Swaps out the existing xpi->xpi_xpswitch with a new value. + */ +struct rpc_xprt_switch *xprt_iter_xchg_switch(struct rpc_xprt_iter *xpi, + struct rpc_xprt_switch *newswitch) +{ + struct rpc_xprt_switch __rcu *oldswitch; + + /* Atomically swap out the old xpswitch */ + oldswitch = xchg(&xpi->xpi_xpswitch, RCU_INITIALIZER(newswitch)); + if (newswitch != NULL) + xprt_iter_rewind(xpi); + return rcu_dereference_protected(oldswitch, true); +} + +/** + * xprt_iter_destroy - Destroys the xprt iterator + * @xpi pointer to rpc_xprt_iter + */ +void xprt_iter_destroy(struct rpc_xprt_iter *xpi) +{ + xprt_switch_put(xprt_iter_xchg_switch(xpi, NULL)); +} + +/** + * xprt_iter_xprt - Returns the rpc_xprt pointed to by the cursor + * @xpi - pointer to rpc_xprt_iter + * + * Returns a pointer to the struct rpc_xprt that is currently + * pointed to by the cursor. + * Caller must be holding rcu_read_lock(). + */ +struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return xprt_iter_ops(xpi)->xpi_xprt(xpi); +} + +static +struct rpc_xprt *xprt_iter_get_helper(struct rpc_xprt_iter *xpi, + struct rpc_xprt *(*fn)(struct rpc_xprt_iter *)) +{ + struct rpc_xprt *ret; + + do { + ret = fn(xpi); + if (ret == NULL) + break; + ret = xprt_get(ret); + } while (ret == NULL); + return ret; +} + +/** + * xprt_iter_get_xprt - Returns the rpc_xprt pointed to by the cursor + * @xpi - pointer to rpc_xprt_iter + * + * Returns a reference to the struct rpc_xprt that is currently + * pointed to by the cursor. + */ +struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi) +{ + struct rpc_xprt *xprt; + + rcu_read_lock(); + xprt = xprt_iter_get_helper(xpi, xprt_iter_ops(xpi)->xpi_xprt); + rcu_read_unlock(); + return xprt; +} + +/** + * xprt_iter_get_next - Returns the next rpc_xprt following the cursor + * @xpi - pointer to rpc_xprt_iter + * + * Returns a reference to the struct rpc_xprt that immediately follows the + * entry pointed to by the cursor. + */ +struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi) +{ + struct rpc_xprt *xprt; + + rcu_read_lock(); + xprt = xprt_iter_get_helper(xpi, xprt_iter_ops(xpi)->xpi_next); + rcu_read_unlock(); + return xprt; +} + +/* Policy for always returning the first entry in the rpc_xprt_switch */ +static +const struct rpc_xprt_iter_ops rpc_xprt_iter_singular = { + .xpi_rewind = xprt_iter_no_rewind, + .xpi_xprt = xprt_iter_first_entry, + .xpi_next = xprt_iter_first_entry, +}; + +/* Policy for round-robin iteration of entries in the rpc_xprt_switch */ +static +const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin = { + .xpi_rewind = xprt_iter_default_rewind, + .xpi_xprt = xprt_iter_current_entry, + .xpi_next = xprt_iter_next_entry_roundrobin, +}; + +/* Policy for once-through iteration of entries in the rpc_xprt_switch */ +static +const struct rpc_xprt_iter_ops rpc_xprt_iter_listall = { + .xpi_rewind = xprt_iter_default_rewind, + .xpi_xprt = xprt_iter_current_entry, + .xpi_next = xprt_iter_next_entry_all, +}; -- 2.5.0 -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html