mempool: make tailq fully local

Since the data structures such as rings are shared in their entirety,
those TAILQ pointers are shared as well. Meaning that, after a
successful rte_ring creation, the tailq_next pointer of the last
ring in the TAILQ will be updated with a pointer to a ring which may
not be present in the address space of another process (i.e. a ring
that may be host-local or guest-local, and not shared over IVSHMEM).
Any successive ring create/lookup on the other side of IVSHMEM will
result in trying to dereference an invalid pointer.

This patchset fixes this problem by creating a default tailq entry
that may be used by any data structure that chooses to use TAILQs.
This default TAILQ entry will consist of a tailq_next/tailq_prev
pointers, and an opaque pointer to arbitrary data. All TAILQ
pointers from data structures themselves will be removed and
replaced by those generic TAILQ entries, thus fixing the problem
of potentially exposing local address space to shared structures.

Technically, only rte_ring structure require modification, because
IVSHMEM is only using memzones (which aren't in TAILQs) and rings,
but for consistency's sake other TAILQ-based data structures were
adapted as well.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

diff --git a/lib/librte_mempool/Makefile b/lib/librte_mempool/Makefile
index c79b3064f3119e172d569bdb9a2f740727888026..9939e100be88fd220b2ab0219f1a4c429fb6e50c 100644 (file)
--- a/lib/librte_mempool/Makefile
+++ b/lib/librte_mempool/Makefile
@@ -44,7 +44,8 @@ endif
 # install includes
 SYMLINK-$(CONFIG_RTE_LIBRTE_MEMPOOL)-include := rte_mempool.h
 
-# this lib needs eal
+# this lib needs eal, rte_ring and rte_malloc
 DEPDIRS-$(CONFIG_RTE_LIBRTE_MEMPOOL) += lib/librte_eal lib/librte_ring
+DEPDIRS-$(CONFIG_RTE_LIBRTE_MEMPOOL) += lib/librte_malloc
 
 include $(RTE_SDK)/mk/rte.lib.mk

diff --git a/lib/librte_mempool/rte_mempool.c b/lib/librte_mempool/rte_mempool.c
index dbb4104369af12e5871519426fcd5221857d1a26..332f46946f8c5f4a7cd98f2f045cdaa4f6e43d1d 100644 (file)
--- a/lib/librte_mempool/rte_mempool.c
+++ b/lib/librte_mempool/rte_mempool.c
@@ -45,6 +45,7 @@
 #include <rte_debug.h>
 #include <rte_memory.h>
 #include <rte_memzone.h>
+#include <rte_malloc.h>
 #include <rte_atomic.h>
 #include <rte_launch.h>
 #include <rte_tailq.h>
@@ -60,7 +61,7 @@
 
 #include "rte_mempool.h"
 
-TAILQ_HEAD(rte_mempool_list, rte_mempool);
+TAILQ_HEAD(rte_mempool_list, rte_tailq_entry);
 
 #define CACHE_FLUSHTHRESH_MULTIPLIER 1.5
 
@@ -404,6 +405,7 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
        char mz_name[RTE_MEMZONE_NAMESIZE];
        char rg_name[RTE_RING_NAMESIZE];
        struct rte_mempool *mp = NULL;
+       struct rte_tailq_entry *te;
        struct rte_ring *r;
        const struct rte_memzone *mz;
        size_t mempool_size;
@@ -501,6 +503,13 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
                }
        }
 
+       /* try to allocate tailq entry */
+       te = rte_zmalloc("MEMPOOL_TAILQ_ENTRY", sizeof(*te), 0);
+       if (te == NULL) {
+               RTE_LOG(ERR, MEMPOOL, "Cannot allocate tailq entry!\n");
+               goto exit;
+       }
+
        /*
         * If user provided an external memory buffer, then use it to
         * store mempool objects. Otherwise reserve memzone big enough to
@@ -527,8 +536,10 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
         * no more memory: in this case we loose previously reserved
         * space for the as we cannot free it
         */
-       if (mz == NULL)
+       if (mz == NULL) {
+               rte_free(te);
                goto exit;
+       }
 
        if (rte_eal_has_hugepages()) {
                startaddr = (void*)mz->addr;
@@ -587,7 +598,9 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 
        mempool_populate(mp, n, 1, obj_init, obj_init_arg);
 
-       RTE_EAL_TAILQ_INSERT_TAIL(RTE_TAILQ_MEMPOOL, rte_mempool_list, mp);
+       te->data = (void *) mp;
+
+       RTE_EAL_TAILQ_INSERT_TAIL(RTE_TAILQ_MEMPOOL, rte_mempool_list, te);
 
 exit:
        rte_rwlock_write_unlock(RTE_EAL_MEMPOOL_RWLOCK);
@@ -812,6 +825,7 @@ void
 rte_mempool_list_dump(FILE *f)
 {
        const struct rte_mempool *mp = NULL;
+       struct rte_tailq_entry *te;
        struct rte_mempool_list *mempool_list;
 
        if ((mempool_list =
@@ -822,7 +836,8 @@ rte_mempool_list_dump(FILE *f)
 
        rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);
 
-       TAILQ_FOREACH(mp, mempool_list, next) {
+       TAILQ_FOREACH(te, mempool_list, next) {
+               mp = (struct rte_mempool *) te->data;
                rte_mempool_dump(f, mp);
        }
 
@@ -834,6 +849,7 @@ struct rte_mempool *
 rte_mempool_lookup(const char *name)
 {
        struct rte_mempool *mp = NULL;
+       struct rte_tailq_entry *te;
        struct rte_mempool_list *mempool_list;
 
        if ((mempool_list =
@@ -844,15 +860,18 @@ rte_mempool_lookup(const char *name)
 
        rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);
 
-       TAILQ_FOREACH(mp, mempool_list, next) {
+       TAILQ_FOREACH(te, mempool_list, next) {
+               mp = (struct rte_mempool *) te->data;
                if (strncmp(name, mp->name, RTE_MEMPOOL_NAMESIZE) == 0)
                        break;
        }
 
        rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);
 
-       if (mp == NULL)
+       if (te == NULL) {
                rte_errno = ENOENT;
+               return NULL;
+       }
 
        return mp;
 }
@@ -860,7 +879,7 @@ rte_mempool_lookup(const char *name)
 void rte_mempool_walk(void (*func)(const struct rte_mempool *, void *),
                      void *arg)
 {
-       struct rte_mempool *mp = NULL;
+       struct rte_tailq_entry *te = NULL;
        struct rte_mempool_list *mempool_list;
 
        if ((mempool_list =
@@ -871,8 +890,8 @@ void rte_mempool_walk(void (*func)(const struct rte_mempool *, void *),
 
        rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);
 
-       TAILQ_FOREACH(mp, mempool_list, next) {
-               (*func)(mp, arg);
+       TAILQ_FOREACH(te, mempool_list, next) {
+               (*func)((struct rte_mempool *) te->data, arg);
        }
 
        rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);

diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
index e5a0b1334668969b90f7ec187add0e064933e954..95f19f9f73ca40975ced0ba95b9855b417869106 100644 (file)
--- a/lib/librte_mempool/rte_mempool.h
+++ b/lib/librte_mempool/rte_mempool.h
@@ -143,8 +143,6 @@ struct rte_mempool_objsz {
  * The RTE mempool structure.
  */
 struct rte_mempool {
-       TAILQ_ENTRY(rte_mempool) next;   /**< Next in list. */
-
        char name[RTE_MEMPOOL_NAMESIZE]; /**< Name of mempool. */
        struct rte_ring *ring;           /**< Ring to store objects. */
        phys_addr_t phys_addr;           /**< Phys. addr. of mempool struct. */