* [PATCH nf-next 1/7] xtables: add xt_match, xt_target and data copy_to_user functions
From: Willem de Bruijn @ 2017-01-02 22:19 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, davem, fw, dborkman, pablo, Willem de Bruijn
In-Reply-To: <1483395586-105774-1-git-send-email-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
xt_entry_target, xt_entry_match and their private data may contain
kernel data.
Introduce helper functions xt_match_to_user, xt_target_to_user and
xt_data_to_user that copy only the expected fields. These replace
existing logic that calls copy_to_user on entire structs, then
overwrites select fields.
Private data is defined in xt_match and xt_target. All matches and
targets that maintain kernel data store this at the tail of their
private structure. Extend xt_match and xt_target with .usersize to
limit how many bytes of data are copied. The remainder is cleared.
If compatsize is specified, usersize can only safely be used if all
fields up to usersize use platform-independent types. Otherwise, the
compat_to_user callback must be defined.
This patch does not yet enable the support logic.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
include/linux/netfilter/x_tables.h | 9 +++++++
net/netfilter/x_tables.c | 54 ++++++++++++++++++++++++++++++++++++++
2 files changed, 63 insertions(+)
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 5117e4d..be378cf 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -167,6 +167,7 @@ struct xt_match {
const char *table;
unsigned int matchsize;
+ unsigned int usersize;
#ifdef CONFIG_COMPAT
unsigned int compatsize;
#endif
@@ -207,6 +208,7 @@ struct xt_target {
const char *table;
unsigned int targetsize;
+ unsigned int usersize;
#ifdef CONFIG_COMPAT
unsigned int compatsize;
#endif
@@ -287,6 +289,13 @@ int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
bool inv_proto);
+int xt_match_to_user(const struct xt_entry_match *m,
+ struct xt_entry_match __user *u);
+int xt_target_to_user(const struct xt_entry_target *t,
+ struct xt_entry_target __user *u);
+int xt_data_to_user(void __user *dst, const void *src,
+ int usersize, int size);
+
void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
struct xt_counters_info *info, bool compat);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 2ff4996..feccf52 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -262,6 +262,60 @@ struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision)
}
EXPORT_SYMBOL_GPL(xt_request_find_target);
+
+static int xt_obj_to_user(u16 __user *psize, u16 size,
+ void __user *pname, const char *name,
+ u8 __user *prev, u8 rev)
+{
+ if (put_user(size, psize))
+ return -EFAULT;
+ if (copy_to_user(pname, name, strlen(name) + 1))
+ return -EFAULT;
+ if (put_user(rev, prev))
+ return -EFAULT;
+
+ return 0;
+}
+
+#define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE) \
+ xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size, \
+ U->u.user.name, K->u.kernel.TYPE->name, \
+ &U->u.user.revision, K->u.kernel.TYPE->revision)
+
+int xt_data_to_user(void __user *dst, const void *src,
+ int usersize, int size)
+{
+ usersize = usersize ? : size;
+ if (copy_to_user(dst, src, usersize))
+ return -EFAULT;
+ if (usersize != size && clear_user(dst + usersize, size - usersize))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xt_data_to_user);
+
+#define XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \
+ xt_data_to_user(U->data, K->data, \
+ K->u.kernel.TYPE->usersize, \
+ C_SIZE ? : K->u.kernel.TYPE->TYPE##size)
+
+int xt_match_to_user(const struct xt_entry_match *m,
+ struct xt_entry_match __user *u)
+{
+ return XT_OBJ_TO_USER(u, m, match, 0) ||
+ XT_DATA_TO_USER(u, m, match, 0);
+}
+EXPORT_SYMBOL_GPL(xt_match_to_user);
+
+int xt_target_to_user(const struct xt_entry_target *t,
+ struct xt_entry_target __user *u)
+{
+ return XT_OBJ_TO_USER(u, t, target, 0) ||
+ XT_DATA_TO_USER(u, t, target, 0);
+}
+EXPORT_SYMBOL_GPL(xt_target_to_user);
+
static int match_revfn(u8 af, const char *name, u8 revision, int *bestp)
{
const struct xt_match *m;
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH nf-next 2/7] iptables: use match, target and data copy_to_user helpers
From: Willem de Bruijn @ 2017-01-02 22:19 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, davem, fw, dborkman, pablo, Willem de Bruijn
In-Reply-To: <1483395586-105774-1-git-send-email-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Convert iptables to copying entries, matches and targets one by one,
using the xt_match_to_user and xt_target_to_user helper functions.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/ipv4/netfilter/ip_tables.c | 21 ++++++---------------
1 file changed, 6 insertions(+), 15 deletions(-)
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 91656a1..384b857 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -826,10 +826,6 @@ copy_entries_to_user(unsigned int total_size,
return PTR_ERR(counters);
loc_cpu_entry = private->entries;
- if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
- ret = -EFAULT;
- goto free_counters;
- }
/* FIXME: use iterator macros --RR */
/* ... then go back and fix counters and names */
@@ -839,6 +835,10 @@ copy_entries_to_user(unsigned int total_size,
const struct xt_entry_target *t;
e = (struct ipt_entry *)(loc_cpu_entry + off);
+ if (copy_to_user(userptr + off, e, sizeof(*e))) {
+ ret = -EFAULT;
+ goto free_counters;
+ }
if (copy_to_user(userptr + off
+ offsetof(struct ipt_entry, counters),
&counters[num],
@@ -852,23 +852,14 @@ copy_entries_to_user(unsigned int total_size,
i += m->u.match_size) {
m = (void *)e + i;
- if (copy_to_user(userptr + off + i
- + offsetof(struct xt_entry_match,
- u.user.name),
- m->u.kernel.match->name,
- strlen(m->u.kernel.match->name)+1)
- != 0) {
+ if (xt_match_to_user(m, userptr + off + i)) {
ret = -EFAULT;
goto free_counters;
}
}
t = ipt_get_target_c(e);
- if (copy_to_user(userptr + off + e->target_offset
- + offsetof(struct xt_entry_target,
- u.user.name),
- t->u.kernel.target->name,
- strlen(t->u.kernel.target->name)+1) != 0) {
+ if (xt_target_to_user(t, userptr + off + e->target_offset)) {
ret = -EFAULT;
goto free_counters;
}
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH nf-next 3/7] ip6tables: use match, target and data copy_to_user helpers
From: Willem de Bruijn @ 2017-01-02 22:19 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, davem, fw, dborkman, pablo, Willem de Bruijn
In-Reply-To: <1483395586-105774-1-git-send-email-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Convert ip6tables to copying entries, matches and targets one by one,
using the xt_match_to_user and xt_target_to_user helper functions.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/ipv6/netfilter/ip6_tables.c | 21 ++++++---------------
1 file changed, 6 insertions(+), 15 deletions(-)
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 25a022d..1e15c54 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -855,10 +855,6 @@ copy_entries_to_user(unsigned int total_size,
return PTR_ERR(counters);
loc_cpu_entry = private->entries;
- if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
- ret = -EFAULT;
- goto free_counters;
- }
/* FIXME: use iterator macros --RR */
/* ... then go back and fix counters and names */
@@ -868,6 +864,10 @@ copy_entries_to_user(unsigned int total_size,
const struct xt_entry_target *t;
e = (struct ip6t_entry *)(loc_cpu_entry + off);
+ if (copy_to_user(userptr + off, e, sizeof(*e))) {
+ ret = -EFAULT;
+ goto free_counters;
+ }
if (copy_to_user(userptr + off
+ offsetof(struct ip6t_entry, counters),
&counters[num],
@@ -881,23 +881,14 @@ copy_entries_to_user(unsigned int total_size,
i += m->u.match_size) {
m = (void *)e + i;
- if (copy_to_user(userptr + off + i
- + offsetof(struct xt_entry_match,
- u.user.name),
- m->u.kernel.match->name,
- strlen(m->u.kernel.match->name)+1)
- != 0) {
+ if (xt_match_to_user(m, userptr + off + i)) {
ret = -EFAULT;
goto free_counters;
}
}
t = ip6t_get_target_c(e);
- if (copy_to_user(userptr + off + e->target_offset
- + offsetof(struct xt_entry_target,
- u.user.name),
- t->u.kernel.target->name,
- strlen(t->u.kernel.target->name)+1) != 0) {
+ if (xt_target_to_user(t, userptr + off + e->target_offset)) {
ret = -EFAULT;
goto free_counters;
}
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH nf-next 4/7] arptables: use match, target and data copy_to_user helpers
From: Willem de Bruijn @ 2017-01-02 22:19 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, davem, fw, dborkman, pablo, Willem de Bruijn
In-Reply-To: <1483395586-105774-1-git-send-email-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Convert arptables to copying entries, matches and targets one by one,
using the xt_match_to_user and xt_target_to_user helper functions.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/ipv4/netfilter/arp_tables.c | 15 +++++----------
1 file changed, 5 insertions(+), 10 deletions(-)
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index a467e12..6241a81 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -677,11 +677,6 @@ static int copy_entries_to_user(unsigned int total_size,
return PTR_ERR(counters);
loc_cpu_entry = private->entries;
- /* ... then copy entire thing ... */
- if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
- ret = -EFAULT;
- goto free_counters;
- }
/* FIXME: use iterator macros --RR */
/* ... then go back and fix counters and names */
@@ -689,6 +684,10 @@ static int copy_entries_to_user(unsigned int total_size,
const struct xt_entry_target *t;
e = (struct arpt_entry *)(loc_cpu_entry + off);
+ if (copy_to_user(userptr + off, e, sizeof(*e))) {
+ ret = -EFAULT;
+ goto free_counters;
+ }
if (copy_to_user(userptr + off
+ offsetof(struct arpt_entry, counters),
&counters[num],
@@ -698,11 +697,7 @@ static int copy_entries_to_user(unsigned int total_size,
}
t = arpt_get_target_c(e);
- if (copy_to_user(userptr + off + e->target_offset
- + offsetof(struct xt_entry_target,
- u.user.name),
- t->u.kernel.target->name,
- strlen(t->u.kernel.target->name)+1) != 0) {
+ if (xt_target_to_user(t, userptr + off + e->target_offset)) {
ret = -EFAULT;
goto free_counters;
}
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH nf-next 5/7] ebtables: use match, target and data copy_to_user helpers
From: Willem de Bruijn @ 2017-01-02 22:19 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, davem, fw, dborkman, pablo, Willem de Bruijn
In-Reply-To: <1483395586-105774-1-git-send-email-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Convert ebtables to copying entries, matches and targets one by one.
The solution is analogous to that of generic xt_(match|target)_to_user
helpers, but is applied to different structs.
Convert existing helpers ebt_make_XXXname helpers that overwrite
fields of an already copy_to_user'd struct with ebt_XXX_to_user
helpers that copy all relevant fields of the struct from scratch.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/bridge/netfilter/ebtables.c | 78 +++++++++++++++++++++++++----------------
1 file changed, 47 insertions(+), 31 deletions(-)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 537e3d5..79b6991 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1346,56 +1346,72 @@ static int update_counters(struct net *net, const void __user *user,
hlp.num_counters, user, len);
}
-static inline int ebt_make_matchname(const struct ebt_entry_match *m,
- const char *base, char __user *ubase)
+static inline int ebt_obj_to_user(char __user *um, const char *_name,
+ const char *data, int entrysize,
+ int usersize, int datasize)
{
- char __user *hlp = ubase + ((char *)m - base);
- char name[EBT_FUNCTION_MAXNAMELEN] = {};
+ char name[EBT_FUNCTION_MAXNAMELEN] = {0};
/* ebtables expects 32 bytes long names but xt_match names are 29 bytes
* long. Copy 29 bytes and fill remaining bytes with zeroes.
*/
- strlcpy(name, m->u.match->name, sizeof(name));
- if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
+ strlcpy(name, _name, sizeof(name));
+ if (copy_to_user(um, name, EBT_FUNCTION_MAXNAMELEN) ||
+ put_user(datasize, (int __user *)(um + EBT_FUNCTION_MAXNAMELEN)) ||
+ xt_data_to_user(um + entrysize, data, usersize, datasize))
return -EFAULT;
+
return 0;
}
-static inline int ebt_make_watchername(const struct ebt_entry_watcher *w,
- const char *base, char __user *ubase)
+static inline int ebt_match_to_user(const struct ebt_entry_match *m,
+ const char *base, char __user *ubase)
{
- char __user *hlp = ubase + ((char *)w - base);
- char name[EBT_FUNCTION_MAXNAMELEN] = {};
+ return ebt_obj_to_user(ubase + ((char *)m - base),
+ m->u.match->name, m->data, sizeof(*m),
+ m->u.match->usersize, m->match_size);
+}
- strlcpy(name, w->u.watcher->name, sizeof(name));
- if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
- return -EFAULT;
- return 0;
+static inline int ebt_watcher_to_user(const struct ebt_entry_watcher *w,
+ const char *base, char __user *ubase)
+{
+ return ebt_obj_to_user(ubase + ((char *)w - base),
+ w->u.watcher->name, w->data, sizeof(*w),
+ w->u.watcher->usersize, w->watcher_size);
}
-static inline int ebt_make_names(struct ebt_entry *e, const char *base,
- char __user *ubase)
+static inline int ebt_entry_to_user(struct ebt_entry *e, const char *base,
+ char __user *ubase)
{
int ret;
char __user *hlp;
const struct ebt_entry_target *t;
- char name[EBT_FUNCTION_MAXNAMELEN] = {};
- if (e->bitmask == 0)
+ if (e->bitmask == 0) {
+ /* special case !EBT_ENTRY_OR_ENTRIES */
+ if (copy_to_user(ubase + ((char *)e - base), e,
+ sizeof(struct ebt_entries)))
+ return -EFAULT;
return 0;
+ }
+
+ if (copy_to_user(ubase + ((char *)e - base), e, sizeof(*e)))
+ return -EFAULT;
hlp = ubase + (((char *)e + e->target_offset) - base);
t = (struct ebt_entry_target *)(((char *)e) + e->target_offset);
- ret = EBT_MATCH_ITERATE(e, ebt_make_matchname, base, ubase);
+ ret = EBT_MATCH_ITERATE(e, ebt_match_to_user, base, ubase);
if (ret != 0)
return ret;
- ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase);
+ ret = EBT_WATCHER_ITERATE(e, ebt_watcher_to_user, base, ubase);
if (ret != 0)
return ret;
- strlcpy(name, t->u.target->name, sizeof(name));
- if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN))
- return -EFAULT;
+ ret = ebt_obj_to_user(hlp, t->u.target->name, t->data, sizeof(*t),
+ t->u.target->usersize, t->target_size);
+ if (ret != 0)
+ return ret;
+
return 0;
}
@@ -1475,13 +1491,9 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user,
if (ret)
return ret;
- if (copy_to_user(tmp.entries, entries, entries_size)) {
- BUGPRINT("Couldn't copy entries to userspace\n");
- return -EFAULT;
- }
/* set the match/watcher/target names right */
return EBT_ENTRY_ITERATE(entries, entries_size,
- ebt_make_names, entries, tmp.entries);
+ ebt_entry_to_user, entries, tmp.entries);
}
static int do_ebt_set_ctl(struct sock *sk,
@@ -1630,8 +1642,10 @@ static int compat_match_to_user(struct ebt_entry_match *m, void __user **dstptr,
if (match->compat_to_user) {
if (match->compat_to_user(cm->data, m->data))
return -EFAULT;
- } else if (copy_to_user(cm->data, m->data, msize))
+ } else {
+ if (xt_data_to_user(cm->data, m->data, match->usersize, msize))
return -EFAULT;
+ }
*size -= ebt_compat_entry_padsize() + off;
*dstptr = cm->data;
@@ -1657,8 +1671,10 @@ static int compat_target_to_user(struct ebt_entry_target *t,
if (target->compat_to_user) {
if (target->compat_to_user(cm->data, t->data))
return -EFAULT;
- } else if (copy_to_user(cm->data, t->data, tsize))
- return -EFAULT;
+ } else {
+ if (xt_data_to_user(cm->data, t->data, target->usersize, tsize))
+ return -EFAULT;
+ }
*size -= ebt_compat_entry_padsize() + off;
*dstptr = cm->data;
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH nf-next 6/7] xtables: use match, target and data copy_to_user helpers in compat
From: Willem de Bruijn @ 2017-01-02 22:19 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, davem, fw, dborkman, pablo, Willem de Bruijn
In-Reply-To: <1483395586-105774-1-git-send-email-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Convert compat to copying entries, matches and targets one by one,
using the xt_match_to_user and xt_target_to_user helper functions.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/netfilter/x_tables.c | 14 ++++----------
1 file changed, 4 insertions(+), 10 deletions(-)
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index feccf52..016db6b 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -619,17 +619,14 @@ int xt_compat_match_to_user(const struct xt_entry_match *m,
int off = xt_compat_match_offset(match);
u_int16_t msize = m->u.user.match_size - off;
- if (copy_to_user(cm, m, sizeof(*cm)) ||
- put_user(msize, &cm->u.user.match_size) ||
- copy_to_user(cm->u.user.name, m->u.kernel.match->name,
- strlen(m->u.kernel.match->name) + 1))
+ if (XT_OBJ_TO_USER(cm, m, match, msize))
return -EFAULT;
if (match->compat_to_user) {
if (match->compat_to_user((void __user *)cm->data, m->data))
return -EFAULT;
} else {
- if (copy_to_user(cm->data, m->data, msize - sizeof(*cm)))
+ if (XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm)))
return -EFAULT;
}
@@ -977,17 +974,14 @@ int xt_compat_target_to_user(const struct xt_entry_target *t,
int off = xt_compat_target_offset(target);
u_int16_t tsize = t->u.user.target_size - off;
- if (copy_to_user(ct, t, sizeof(*ct)) ||
- put_user(tsize, &ct->u.user.target_size) ||
- copy_to_user(ct->u.user.name, t->u.kernel.target->name,
- strlen(t->u.kernel.target->name) + 1))
+ if (XT_OBJ_TO_USER(ct, t, target, tsize))
return -EFAULT;
if (target->compat_to_user) {
if (target->compat_to_user((void __user *)ct->data, t->data))
return -EFAULT;
} else {
- if (copy_to_user(ct->data, t->data, tsize - sizeof(*ct)))
+ if (XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct)))
return -EFAULT;
}
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH nf-next 7/7] xtables: extend matches and targets with .usersize
From: Willem de Bruijn @ 2017-01-02 22:19 UTC (permalink / raw)
To: netfilter-devel; +Cc: netdev, davem, fw, dborkman, pablo, Willem de Bruijn
In-Reply-To: <1483395586-105774-1-git-send-email-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
In matches and targets that define a kernel-only tail to their
xt_match and xt_target data structs, add a field .usersize that
specifies up to where data is to be shared with userspace.
Performed a search for comment "Used internally by the kernel" to find
relevant matches and targets. Manually inspected the structs to derive
a valid offsetof.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/bridge/netfilter/ebt_limit.c | 1 +
net/ipv4/netfilter/ipt_CLUSTERIP.c | 1 +
net/ipv6/netfilter/ip6t_NPT.c | 2 ++
net/netfilter/xt_CT.c | 3 +++
net/netfilter/xt_RATEEST.c | 1 +
net/netfilter/xt_TEE.c | 2 ++
net/netfilter/xt_bpf.c | 2 ++
net/netfilter/xt_cgroup.c | 1 +
net/netfilter/xt_connlimit.c | 1 +
net/netfilter/xt_hashlimit.c | 4 ++++
net/netfilter/xt_limit.c | 2 ++
net/netfilter/xt_quota.c | 1 +
net/netfilter/xt_rateest.c | 1 +
net/netfilter/xt_string.c | 1 +
14 files changed, 23 insertions(+)
diff --git a/net/bridge/netfilter/ebt_limit.c b/net/bridge/netfilter/ebt_limit.c
index 517e78b..61a9f1b 100644
--- a/net/bridge/netfilter/ebt_limit.c
+++ b/net/bridge/netfilter/ebt_limit.c
@@ -105,6 +105,7 @@ static struct xt_match ebt_limit_mt_reg __read_mostly = {
.match = ebt_limit_mt,
.checkentry = ebt_limit_mt_check,
.matchsize = sizeof(struct ebt_limit_info),
+ .usersize = offsetof(struct ebt_limit_info, prev),
#ifdef CONFIG_COMPAT
.compatsize = sizeof(struct ebt_compat_limit_info),
#endif
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 21db00d..8a3d20e 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -468,6 +468,7 @@ static struct xt_target clusterip_tg_reg __read_mostly = {
.checkentry = clusterip_tg_check,
.destroy = clusterip_tg_destroy,
.targetsize = sizeof(struct ipt_clusterip_tgt_info),
+ .usersize = offsetof(struct ipt_clusterip_tgt_info, config),
#ifdef CONFIG_COMPAT
.compatsize = sizeof(struct compat_ipt_clusterip_tgt_info),
#endif /* CONFIG_COMPAT */
diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c
index 590f767..a379d2f 100644
--- a/net/ipv6/netfilter/ip6t_NPT.c
+++ b/net/ipv6/netfilter/ip6t_NPT.c
@@ -112,6 +112,7 @@ static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
.table = "mangle",
.target = ip6t_snpt_tg,
.targetsize = sizeof(struct ip6t_npt_tginfo),
+ .usersize = offsetof(struct ip6t_npt_tginfo, adjustment),
.checkentry = ip6t_npt_checkentry,
.family = NFPROTO_IPV6,
.hooks = (1 << NF_INET_LOCAL_IN) |
@@ -123,6 +124,7 @@ static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
.table = "mangle",
.target = ip6t_dnpt_tg,
.targetsize = sizeof(struct ip6t_npt_tginfo),
+ .usersize = offsetof(struct ip6t_npt_tginfo, adjustment),
.checkentry = ip6t_npt_checkentry,
.family = NFPROTO_IPV6,
.hooks = (1 << NF_INET_PRE_ROUTING) |
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 95c7503..26b0bccfa 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -373,6 +373,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = {
.name = "CT",
.family = NFPROTO_UNSPEC,
.targetsize = sizeof(struct xt_ct_target_info),
+ .usersize = offsetof(struct xt_ct_target_info, ct),
.checkentry = xt_ct_tg_check_v0,
.destroy = xt_ct_tg_destroy_v0,
.target = xt_ct_target_v0,
@@ -384,6 +385,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision = 1,
.targetsize = sizeof(struct xt_ct_target_info_v1),
+ .usersize = offsetof(struct xt_ct_target_info, ct),
.checkentry = xt_ct_tg_check_v1,
.destroy = xt_ct_tg_destroy_v1,
.target = xt_ct_target_v1,
@@ -395,6 +397,7 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision = 2,
.targetsize = sizeof(struct xt_ct_target_info_v1),
+ .usersize = offsetof(struct xt_ct_target_info, ct),
.checkentry = xt_ct_tg_check_v2,
.destroy = xt_ct_tg_destroy_v1,
.target = xt_ct_target_v1,
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 91a373a..498b54f 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -162,6 +162,7 @@ static struct xt_target xt_rateest_tg_reg __read_mostly = {
.checkentry = xt_rateest_tg_checkentry,
.destroy = xt_rateest_tg_destroy,
.targetsize = sizeof(struct xt_rateest_target_info),
+ .usersize = offsetof(struct xt_rateest_target_info, est),
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 1c57ace..86b0580 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -133,6 +133,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
.family = NFPROTO_IPV4,
.target = tee_tg4,
.targetsize = sizeof(struct xt_tee_tginfo),
+ .usersize = offsetof(struct xt_tee_tginfo, priv),
.checkentry = tee_tg_check,
.destroy = tee_tg_destroy,
.me = THIS_MODULE,
@@ -144,6 +145,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
.family = NFPROTO_IPV6,
.target = tee_tg6,
.targetsize = sizeof(struct xt_tee_tginfo),
+ .usersize = offsetof(struct xt_tee_tginfo, priv),
.checkentry = tee_tg_check,
.destroy = tee_tg_destroy,
.me = THIS_MODULE,
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 2dedaa2..38986a9 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -110,6 +110,7 @@ static struct xt_match bpf_mt_reg[] __read_mostly = {
.match = bpf_mt,
.destroy = bpf_mt_destroy,
.matchsize = sizeof(struct xt_bpf_info),
+ .usersize = offsetof(struct xt_bpf_info, filter),
.me = THIS_MODULE,
},
{
@@ -120,6 +121,7 @@ static struct xt_match bpf_mt_reg[] __read_mostly = {
.match = bpf_mt_v1,
.destroy = bpf_mt_destroy_v1,
.matchsize = sizeof(struct xt_bpf_info_v1),
+ .usersize = offsetof(struct xt_bpf_info_v1, filter),
.me = THIS_MODULE,
},
};
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index a086a91..1db1ce5 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -122,6 +122,7 @@ static struct xt_match cgroup_mt_reg[] __read_mostly = {
.checkentry = cgroup_mt_check_v1,
.match = cgroup_mt_v1,
.matchsize = sizeof(struct xt_cgroup_info_v1),
+ .usersize = offsetof(struct xt_cgroup_info_v1, priv),
.destroy = cgroup_mt_destroy_v1,
.me = THIS_MODULE,
.hooks = (1 << NF_INET_LOCAL_OUT) |
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 2aff2b7..6d16f46 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -431,6 +431,7 @@ static struct xt_match connlimit_mt_reg __read_mostly = {
.checkentry = connlimit_mt_check,
.match = connlimit_mt,
.matchsize = sizeof(struct xt_connlimit_info),
+ .usersize = offsetof(struct xt_connlimit_info, data),
.destroy = connlimit_mt_destroy,
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 1006340..26ef70c 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -838,6 +838,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV4,
.match = hashlimit_mt_v1,
.matchsize = sizeof(struct xt_hashlimit_mtinfo1),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo),
.checkentry = hashlimit_mt_check_v1,
.destroy = hashlimit_mt_destroy_v1,
.me = THIS_MODULE,
@@ -848,6 +849,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV4,
.match = hashlimit_mt,
.matchsize = sizeof(struct xt_hashlimit_mtinfo2),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo),
.checkentry = hashlimit_mt_check,
.destroy = hashlimit_mt_destroy,
.me = THIS_MODULE,
@@ -859,6 +861,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV6,
.match = hashlimit_mt_v1,
.matchsize = sizeof(struct xt_hashlimit_mtinfo1),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo),
.checkentry = hashlimit_mt_check_v1,
.destroy = hashlimit_mt_destroy_v1,
.me = THIS_MODULE,
@@ -869,6 +872,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
.family = NFPROTO_IPV6,
.match = hashlimit_mt,
.matchsize = sizeof(struct xt_hashlimit_mtinfo2),
+ .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo),
.checkentry = hashlimit_mt_check,
.destroy = hashlimit_mt_destroy,
.me = THIS_MODULE,
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index bef8505..dab962d 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -192,6 +192,8 @@ static struct xt_match limit_mt_reg __read_mostly = {
.compatsize = sizeof(struct compat_xt_rateinfo),
.compat_from_user = limit_mt_compat_from_user,
.compat_to_user = limit_mt_compat_to_user,
+#else
+ .usersize = offsetof(struct xt_rateinfo, prev),
#endif
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c
index 44c8eb4..10d61a6 100644
--- a/net/netfilter/xt_quota.c
+++ b/net/netfilter/xt_quota.c
@@ -73,6 +73,7 @@ static struct xt_match quota_mt_reg __read_mostly = {
.checkentry = quota_mt_check,
.destroy = quota_mt_destroy,
.matchsize = sizeof(struct xt_quota_info),
+ .usersize = offsetof(struct xt_quota_info, master),
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c
index 1db02f6..755d2f6 100644
--- a/net/netfilter/xt_rateest.c
+++ b/net/netfilter/xt_rateest.c
@@ -133,6 +133,7 @@ static struct xt_match xt_rateest_mt_reg __read_mostly = {
.checkentry = xt_rateest_mt_checkentry,
.destroy = xt_rateest_mt_destroy,
.matchsize = sizeof(struct xt_rateest_match_info),
+ .usersize = offsetof(struct xt_rateest_match_info, est1),
.me = THIS_MODULE,
};
diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c
index 0bc3460..423293e 100644
--- a/net/netfilter/xt_string.c
+++ b/net/netfilter/xt_string.c
@@ -77,6 +77,7 @@ static struct xt_match xt_string_mt_reg __read_mostly = {
.match = string_mt,
.destroy = string_mt_destroy,
.matchsize = sizeof(struct xt_string_info),
+ .usersize = offsetof(struct xt_string_info, config),
.me = THIS_MODULE,
};
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* Re: [PATCH net-next] net/sched: cls_flower: Add user specified data
From: Jamal Hadi Salim @ 2017-01-02 22:21 UTC (permalink / raw)
To: John Fastabend, Paul Blakey, David S. Miller, netdev
Cc: Jiri Pirko, Hadar Hen Zion, Or Gerlitz, Roi Dayan, Roman Mashak,
Simon Horman
In-Reply-To: <586A9A9F.4030002@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 2833 bytes --]
On 17-01-02 01:23 PM, John Fastabend wrote:
>
> Additionally I would like to point out this is an arbitrary length binary
> blob (for undefined use, without even a specified encoding) that gets pushed
> between user space and hardware ;) This seemed to get folks fairly excited in
> the past.
>
The binary blob size is a little strange - but i think there is value
in storing some "cookie" field. The challenge is whether the kernel
gets to intepret it; in which case encoding must be specified. Or
whether we should leave it up to user space - in which something
like tc could standardize its own encodings.
> Some questions, exactly what do you mean by "port mappings" above? In
> general the 'tc' API uses the netdev the netlink msg is processed on as
> the port mapping. If you mean OVS port to netdev port I think this is
> a OVS problem and nothing to do with 'tc'. For what its worth there is an
> existing problem with 'tc' where rules only apply to a single ingress or
> egress port which is limiting on hardware.
>
In our case the desire is to be able to correlate for a system wide
mostly identity/key mapping.
> The UFID in my ovs code base is defined as best I can tell here,
>
> [OVS_FLOW_ATTR_UFID] = { .type = NL_A_UNSPEC, .optional = true,
> .min_len = sizeof(ovs_u128) },
>
> So you need 128 bits if you want a 1:1 mapping onto 'tc'. So rather
> than an arbitrary blob why not make the case that 'tc' ids need to be
> 128 bits long? Even if its just initially done in flower call it
> flower_flow_id and define it so its not opaque and at least at the code
> level it isn't an arbitrary blob of data.
>
I dont know what this UFID is, but do note:
The idea is not new - the FIB for example has some such cookie
(albeit a tiny one) which will typically be populated to tell
you who/what installed the entry.
I could see f.e use for this cookie to simplify and pretty print in
a human language for the u32 classifier (i.e user space tc sets
some fields in the cookie when updating kernel and when user space
invokes get/dump it uses the cookie to intepret how to pretty print).
I have attached a compile tested version of the cookies on actions
(flat 64 bit; now that we have experienced the use when we have a
large number of counters - I would not mind a 128 bit field).
cheers,
jamal
> And what are the "next" uses of this besides OVS. It would be really
> valuable to see how this generalizes to other usage models. To avoid
> embedding OVS syntax into 'tc'.
>
> Finally if you want to see an example of binary data encodings look at
> how drivers/hardware/users are currently using the user defined bits in
> ethtools ntuple API. Also track down out of tree drivers to see other
> interesting uses. And that was capped at 64bits :/
>
> Thanks,
> John
>
>
>
>
>
[-- Attachment #2: kernel-new-net-next --]
[-- Type: text/plain, Size: 2178 bytes --]
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 1d71644..f299ed3 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -41,6 +41,7 @@ struct tc_action {
struct rcu_head tcfa_rcu;
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
struct gnet_stats_queue __percpu *cpu_qstats;
+ u64 cookie;
};
#define tcf_head common.tcfa_head
#define tcf_index common.tcfa_index
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index cb4bcdc..2e968ee 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -67,6 +67,7 @@ enum {
TCA_ACT_INDEX,
TCA_ACT_STATS,
TCA_ACT_PAD,
+ TCA_ACT_COOKIE,
__TCA_ACT_MAX
};
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2095c83..97eae6b 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -26,6 +26,7 @@
#include <net/sch_generic.h>
#include <net/act_api.h>
#include <net/netlink.h>
+#include <net/tc_act/tc_gact.h>
static void free_tcf(struct rcu_head *head)
{
@@ -467,17 +468,21 @@ int tcf_action_destroy(struct list_head *actions, int bind)
return a->ops->dump(skb, a, bind, ref);
}
-int
-tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind,
+ int ref)
{
int err = -EINVAL;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
+ u64 cookie = a->cookie;
if (nla_put_string(skb, TCA_KIND, a->ops->kind))
goto nla_put_failure;
if (tcf_action_copy_stats(skb, a, 0))
goto nla_put_failure;
+ if (nla_put_u64_64bit(skb, TCA_ACT_COOKIE, cookie, TCA_ACT_PAD))
+ goto nla_put_failure;
+
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
@@ -578,6 +583,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
if (err < 0)
goto err_mod;
+ if (tb[TCA_ACT_COOKIE])
+ a->cookie = nla_get_u64(tb[TCA_ACT_COOKIE]);
+ else
+ a->cookie = 0; /* kernel uses 0 */
+
/* module count goes up only when brand new policy is created
* if it exists and is only bound to in a_o->init() then
* ACT_P_CREATED is not returned (a zero is).
[-- Attachment #3: iprt-ck-patch --]
[-- Type: text/plain, Size: 2425 bytes --]
commit 0a6fd6b024db77e3a460c22ab8a496a714bc71b7
Author: Jamal Hadi Salim <hadi@mojatatu.com>
Date: Fri Aug 12 06:10:46 2016 -0400
actions: add support for cookies
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
diff --git a/tc/m_action.c b/tc/m_action.c
index c416d98..75d1a5a 100644
--- a/tc/m_action.c
+++ b/tc/m_action.c
@@ -137,8 +137,7 @@ noexist:
return a;
}
-static int
-new_cmd(char **argv)
+static int new_cmd(char **argv)
{
if ((matches(*argv, "change") == 0) ||
(matches(*argv, "replace") == 0) ||
@@ -151,8 +150,7 @@ new_cmd(char **argv)
}
-int
-parse_action(int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
+int parse_action(int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
{
int argc = *argc_p;
char **argv = *argv_p;
@@ -160,6 +158,7 @@ parse_action(int *argc_p, char ***argv_p, int tca_id, struct nlmsghdr *n)
char k[16];
int ok = 0;
int eap = 0; /* expect action parameters */
+ __u64 act_ck = 0;
int ret = 0;
int prio = 0;
@@ -215,13 +214,28 @@ done0:
tail = NLMSG_TAIL(n);
addattr_l(n, MAX_MSG, ++prio, NULL, 0);
addattr_l(n, MAX_MSG, TCA_ACT_KIND, k, strlen(k) + 1);
-
- ret = a->parse_aopt(a, &argc, &argv, TCA_ACT_OPTIONS, n);
+ ret = a->parse_aopt(a, &argc, &argv, TCA_ACT_OPTIONS,
+ n);
if (ret < 0) {
- fprintf(stderr, "bad action parsing\n");
+ fprintf(stderr, "bad action option parsing\n");
goto bad_val;
}
+
+ if (*argv && strcmp(*argv, "cookie") == 0) {
+ NEXT_ARG();
+ ret = get_u64(&act_ck, *argv, 0);
+ if (ret) {
+ fprintf(stderr, "bad cookie <%s>\n",
+ *argv);
+ goto bad_val;
+ }
+ argc--;
+ argv++;
+ }
+
+ if (act_ck)
+ addattr64(n, MAX_MSG, TCA_ACT_COOKIE, act_ck);
tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
ok++;
}
@@ -246,8 +260,7 @@ bad_val:
return -1;
}
-static int
-tc_print_one_action(FILE *f, struct rtattr *arg)
+static int tc_print_one_action(FILE *f, struct rtattr *arg)
{
struct rtattr *tb[TCA_ACT_MAX + 1];
@@ -277,6 +290,10 @@ tc_print_one_action(FILE *f, struct rtattr *arg)
if (show_stats && tb[TCA_ACT_STATS]) {
fprintf(f, "\tAction statistics:\n");
print_tcstats2_attr(f, tb[TCA_ACT_STATS], "\t", NULL);
+ if (tb[TCA_ACT_COOKIE]) {
+ __u64 acookie = rta_getattr_u64(tb[TCA_ACT_COOKIE]);
+ fprintf(f, "cookie 0x%llx ", acookie);
+ }
fprintf(f, "\n");
}
^ permalink raw reply related
* [net PATCH] net: virtio: cap mtu when XDP programs are running
From: John Fastabend @ 2017-01-02 22:30 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
XDP programs can not consume multiple pages so we cap the MTU to
avoid this case. Virtio-net however only checks the MTU at XDP
program load and does not block MTU changes after the program
has loaded.
This patch sets/clears the max_mtu value at XDP load/unload time.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/net/virtio_net.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5deeda6..783e842 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1699,6 +1699,9 @@ static void virtnet_init_settings(struct net_device *dev)
.set_settings = virtnet_set_settings,
};
+#define MIN_MTU ETH_MIN_MTU
+#define MAX_MTU ETH_MAX_MTU
+
static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
{
unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr);
@@ -1748,6 +1751,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
virtnet_set_queues(vi, curr_qp);
return PTR_ERR(prog);
}
+ dev->max_mtu = max_sz;
+ } else {
+ dev->max_mtu = ETH_MAX_MTU;
}
vi->xdp_queue_pairs = xdp_qp;
@@ -2133,9 +2139,6 @@ static bool virtnet_validate_features(struct virtio_device *vdev)
return true;
}
-#define MIN_MTU ETH_MIN_MTU
-#define MAX_MTU ETH_MAX_MTU
-
static int virtnet_probe(struct virtio_device *vdev)
{
int i, err;
^ permalink raw reply related
* Re: [PATCH v2 net-next 2/2] tools: test case for TPACKET_V3/TX_RING support
From: Willem de Bruijn @ 2017-01-02 22:31 UTC (permalink / raw)
To: Sowmini Varadhan
Cc: Network Development, Daniel Borkmann, Willem de Bruijn,
David Miller
In-Reply-To: <d26567a7226d392b8105f35be5cf25a17dbdf2ed.1483309545.git.sowmini.varadhan@oracle.com>
On Sun, Jan 1, 2017 at 5:45 PM, Sowmini Varadhan
<sowmini.varadhan@oracle.com> wrote:
> Add a test case and sample code for (TPACKET_V3, PACKET_TX_RING)
Thanks for adding this.
walk_v3_tx is almost identical to walk_v1_v2_tx. That function can
just be extended to add a v3 case where it already multiplexes between
v1 and v2.
^ permalink raw reply
* Re: [PATCH net 9/9] virtio-net: XDP support for small buffers
From: John Fastabend @ 2017-01-02 22:43 UTC (permalink / raw)
To: Jason Wang, mst, virtualization, netdev, linux-kernel; +Cc: john.r.fastabend
In-Reply-To: <1482503852-12438-10-git-send-email-jasowang@redhat.com>
On 16-12-23 06:37 AM, Jason Wang wrote:
> Commit f600b6905015 ("virtio_net: Add XDP support") leaves the case of
> small receive buffer untouched. This will confuse the user who want to
> set XDP but use small buffers. Other than forbid XDP in small buffer
> mode, let's make it work. XDP then can only work at skb->data since
> virtio-net create skbs during refill, this is sub optimal which could
> be optimized in the future.
>
> Cc: John Fastabend <john.r.fastabend@intel.com>
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> ---
> drivers/net/virtio_net.c | 112 ++++++++++++++++++++++++++++++++++++-----------
> 1 file changed, 87 insertions(+), 25 deletions(-)
>
Hi Jason,
I was doing some more testing on this what do you think about doing this
so that free_unused_bufs() handles the buffer free with dev_kfree_skb()
instead of put_page in small receive mode. Seems more correct to me.
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 783e842..27ff76c 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1898,6 +1898,10 @@ static void free_receive_page_frags(struct virtnet_info *vi)
static bool is_xdp_queue(struct virtnet_info *vi, int q)
{
+ /* For small receive mode always use kfree_skb variants */
+ if (!vi->mergeable_rx_bufs)
+ return false;
+
if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
return false;
else if (q < vi->curr_queue_pairs)
patch is untested just spotted doing code review.
Thanks,
John
^ permalink raw reply related
* [net-next][PATCH v3 01/17] RDS: log the address on bind failure
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
It's useful to know the IP address when RDS fails to bind a
connection. Thus, adding it to the error message.
Orabug: 21894138
Reviewed-by: Wei Lin Guay <wei.lin.guay@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/bind.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 095f6ce..3a915be 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -176,8 +176,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (!trans) {
ret = -EADDRNOTAVAIL;
rds_remove_bound(rs);
- printk_ratelimited(KERN_INFO "RDS: rds_bind() could not find a transport, "
- "load rds_tcp or rds_rdma?\n");
+ pr_info_ratelimited("RDS: %s could not find a transport for %pI4, load rds_tcp or rds_rdma?\n",
+ __func__, &sin->sin_addr.s_addr);
goto out;
}
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 02/17] RDS: mark few internal functions static to make sparse build happy
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
Fixes below warnings:
warning: symbol 'rds_send_probe' was not declared. Should it be static?
warning: symbol 'rds_send_ping' was not declared. Should it be static?
warning: symbol 'rds_tcp_accept_one_path' was not declared. Should it be static?
warning: symbol 'rds_walk_conn_path_info' was not declared. Should it be static?
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/connection.c | 10 +++++-----
net/rds/send.c | 4 ++--
net/rds/tcp_listen.c | 1 +
3 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/net/rds/connection.c b/net/rds/connection.c
index fe9d31c..0e04dcc 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -545,11 +545,11 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len,
}
EXPORT_SYMBOL_GPL(rds_for_each_conn_info);
-void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
- struct rds_info_iterator *iter,
- struct rds_info_lengths *lens,
- int (*visitor)(struct rds_conn_path *, void *),
- size_t item_len)
+static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
+ struct rds_info_iterator *iter,
+ struct rds_info_lengths *lens,
+ int (*visitor)(struct rds_conn_path *, void *),
+ size_t item_len)
{
u64 buffer[(item_len + 7) / 8];
struct hlist_head *head;
diff --git a/net/rds/send.c b/net/rds/send.c
index 77c8c6e..bb13c56 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1169,7 +1169,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
* or
* RDS_FLAG_HB_PONG|RDS_FLAG_ACK_REQUIRED
*/
-int
+static int
rds_send_probe(struct rds_conn_path *cp, __be16 sport,
__be16 dport, u8 h_flags)
{
@@ -1238,7 +1238,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
return rds_send_probe(cp, 0, dport, 0);
}
-void
+static void
rds_send_ping(struct rds_connection *conn)
{
unsigned long flags;
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index f74bab3..67d0929 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -79,6 +79,7 @@ int rds_tcp_keepalive(struct socket *sock)
* smaller ip address, we recycle conns in RDS_CONN_ERROR on the passive side
* by moving them to CONNECTING in this function.
*/
+static
struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)
{
int i;
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 04/17] RDS: IB: make the transport retry count smallest
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
Transport retry is not much useful since it indicate packet loss
in fabric so its better to failover fast rather than longer retry.
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/ib.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 45ac8e8..f4e8121 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -16,7 +16,7 @@
#define RDS_IB_DEFAULT_SEND_WR 256
#define RDS_IB_DEFAULT_FR_WR 512
-#define RDS_IB_DEFAULT_RETRY_COUNT 2
+#define RDS_IB_DEFAULT_RETRY_COUNT 1
#define RDS_IB_SUPPORTED_PROTOCOLS 0x00000003 /* minor versions supported */
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 07/17] RDS: RDMA: return appropriate error on rdma map failures
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
The first message to a remote node should prompt a new
connection even if it is RDMA operation. For RDMA operation
the MR mapping can fail because connections is not yet up.
Since the connection establishment is asynchronous,
we make sure the map failure because of unavailable
connection reach to the user by appropriate error code.
Before returning to the user, lets trigger the connection
so that its ready for the next retry.
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/send.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/net/rds/send.c b/net/rds/send.c
index bb13c56..0a6f38b 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -945,6 +945,11 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm,
ret = rds_cmsg_rdma_map(rs, rm, cmsg);
if (!ret)
*allocated_mr = 1;
+ else if (ret == -ENODEV)
+ /* Accommodate the get_mr() case which can fail
+ * if connection isn't established yet.
+ */
+ ret = -EAGAIN;
break;
case RDS_CMSG_ATOMIC_CSWP:
case RDS_CMSG_ATOMIC_FADD:
@@ -1082,8 +1087,12 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
/* Parse any control messages the user may have included. */
ret = rds_cmsg_send(rs, rm, msg, &allocated_mr);
- if (ret)
+ if (ret) {
+ /* Trigger connection so that its ready for the next retry */
+ if (ret == -EAGAIN)
+ rds_conn_connect_if_down(conn);
goto out;
+ }
if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) {
printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n",
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 10/17] RDS: IB: track and log active side endpoint in connection
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
Useful to know the active and passive end points in a
RDS IB connection.
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/ib.h | 3 +++
net/rds/ib_cm.c | 11 +++++++----
2 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/net/rds/ib.h b/net/rds/ib.h
index f14c26d..5f02b4d 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -181,6 +181,9 @@ struct rds_ib_connection {
/* Batched completions */
unsigned int i_unsignaled_wrs;
+
+ /* Endpoint role in connection */
+ bool i_active_side;
};
/* This assumes that atomic_t is at least 32 bits */
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 3002acf..4d1bf04 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -120,16 +120,17 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
rds_conn_destroy(conn);
return;
} else {
- pr_notice("RDS/IB: connected <%pI4,%pI4> version %u.%u%s\n",
+ pr_notice("RDS/IB: %s conn connected <%pI4,%pI4> version %u.%u%s\n",
+ ic->i_active_side ? "Active" : "Passive",
&conn->c_laddr, &conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version),
ic->i_flowctl ? ", flow control" : "");
}
- /*
- * Init rings and fill recv. this needs to wait until protocol negotiation
- * is complete, since ring layout is different from 3.0 to 3.1.
+ /* Init rings and fill recv. this needs to wait until protocol
+ * negotiation is complete, since ring layout is different
+ * from 3.1 to 4.1.
*/
rds_ib_send_init_ring(ic);
rds_ib_recv_init_ring(ic);
@@ -685,6 +686,7 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id)
if (ic->i_cm_id == cm_id)
ret = 0;
}
+ ic->i_active_side = true;
return ret;
}
@@ -859,6 +861,7 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
ic->i_sends = NULL;
vfree(ic->i_recvs);
ic->i_recvs = NULL;
+ ic->i_active_side = false;
}
int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 12/17] RDS: IB: Add vector spreading for cqs
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
Based on available device vectors, allocate cqs accordingly to
get better spread of completion vectors which helps performace
great deal..
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/ib.c | 11 +++++++++++
net/rds/ib.h | 5 +++++
net/rds/ib_cm.c | 40 +++++++++++++++++++++++++++++++++++++---
3 files changed, 53 insertions(+), 3 deletions(-)
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 5680d90..8d70884 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -111,6 +111,9 @@ static void rds_ib_dev_free(struct work_struct *work)
kfree(i_ipaddr);
}
+ if (rds_ibdev->vector_load)
+ kfree(rds_ibdev->vector_load);
+
kfree(rds_ibdev);
}
@@ -159,6 +162,14 @@ static void rds_ib_add_one(struct ib_device *device)
rds_ibdev->max_initiator_depth = device->attrs.max_qp_init_rd_atom;
rds_ibdev->max_responder_resources = device->attrs.max_qp_rd_atom;
+ rds_ibdev->vector_load = kzalloc(sizeof(int) * device->num_comp_vectors,
+ GFP_KERNEL);
+ if (!rds_ibdev->vector_load) {
+ pr_err("RDS/IB: %s failed to allocate vector memory\n",
+ __func__);
+ goto put_dev;
+ }
+
rds_ibdev->dev = device;
rds_ibdev->pd = ib_alloc_pd(device, 0);
if (IS_ERR(rds_ibdev->pd)) {
diff --git a/net/rds/ib.h b/net/rds/ib.h
index c62e551..1fe9f79 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -185,6 +185,10 @@ struct rds_ib_connection {
/* Endpoint role in connection */
bool i_active_side;
+
+ /* Send/Recv vectors */
+ int i_scq_vector;
+ int i_rcq_vector;
};
/* This assumes that atomic_t is at least 32 bits */
@@ -227,6 +231,7 @@ struct rds_ib_device {
spinlock_t spinlock; /* protect the above */
atomic_t refcount;
struct work_struct free_work;
+ int *vector_load;
};
#define ibdev_to_node(ibdev) dev_to_node(ibdev->dma_device)
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 4d1bf04..33c8584 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -358,6 +358,28 @@ static void rds_ib_cq_comp_handler_send(struct ib_cq *cq, void *context)
tasklet_schedule(&ic->i_send_tasklet);
}
+static inline int ibdev_get_unused_vector(struct rds_ib_device *rds_ibdev)
+{
+ int min = rds_ibdev->vector_load[rds_ibdev->dev->num_comp_vectors - 1];
+ int index = rds_ibdev->dev->num_comp_vectors - 1;
+ int i;
+
+ for (i = rds_ibdev->dev->num_comp_vectors - 1; i >= 0; i--) {
+ if (rds_ibdev->vector_load[i] < min) {
+ index = i;
+ min = rds_ibdev->vector_load[i];
+ }
+ }
+
+ rds_ibdev->vector_load[index]++;
+ return index;
+}
+
+static inline void ibdev_put_vector(struct rds_ib_device *rds_ibdev, int index)
+{
+ rds_ibdev->vector_load[index]--;
+}
+
/*
* This needs to be very careful to not leave IS_ERR pointers around for
* cleanup to trip over.
@@ -399,25 +421,30 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
/* Protection domain and memory range */
ic->i_pd = rds_ibdev->pd;
+ ic->i_scq_vector = ibdev_get_unused_vector(rds_ibdev);
cq_attr.cqe = ic->i_send_ring.w_nr + fr_queue_space + 1;
-
+ cq_attr.comp_vector = ic->i_scq_vector;
ic->i_send_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_send,
rds_ib_cq_event_handler, conn,
&cq_attr);
if (IS_ERR(ic->i_send_cq)) {
ret = PTR_ERR(ic->i_send_cq);
ic->i_send_cq = NULL;
+ ibdev_put_vector(rds_ibdev, ic->i_scq_vector);
rdsdebug("ib_create_cq send failed: %d\n", ret);
goto out;
}
+ ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev);
cq_attr.cqe = ic->i_recv_ring.w_nr;
+ cq_attr.comp_vector = ic->i_rcq_vector;
ic->i_recv_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_recv,
rds_ib_cq_event_handler, conn,
&cq_attr);
if (IS_ERR(ic->i_recv_cq)) {
ret = PTR_ERR(ic->i_recv_cq);
ic->i_recv_cq = NULL;
+ ibdev_put_vector(rds_ibdev, ic->i_rcq_vector);
rdsdebug("ib_create_cq recv failed: %d\n", ret);
goto out;
}
@@ -780,10 +807,17 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
/* first destroy the ib state that generates callbacks */
if (ic->i_cm_id->qp)
rdma_destroy_qp(ic->i_cm_id);
- if (ic->i_send_cq)
+ if (ic->i_send_cq) {
+ if (ic->rds_ibdev)
+ ibdev_put_vector(ic->rds_ibdev, ic->i_scq_vector);
ib_destroy_cq(ic->i_send_cq);
- if (ic->i_recv_cq)
+ }
+
+ if (ic->i_recv_cq) {
+ if (ic->rds_ibdev)
+ ibdev_put_vector(ic->rds_ibdev, ic->i_rcq_vector);
ib_destroy_cq(ic->i_recv_cq);
+ }
/* then free the resources that ib callbacks use */
if (ic->i_send_hdrs)
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 13/17] RDS: RDMA: Fix the composite message user notification
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
When application sends an RDS RDMA composite message consist of
RDMA transfer to be followed up by non RDMA payload, it expect to
be notified *only* when the full message gets delivered. RDS RDMA
notification doesn't behave this way though.
Thanks to Venkat for debug and root casuing the issue
where only first part of the message(RDMA) was
successfully delivered but remainder payload delivery failed.
In that case, application should not be notified with
a false positive of message delivery success.
Fix this case by making sure the user gets notified only after
the full message delivery.
Reviewed-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/ib_send.c | 25 +++++++++++++++----------
net/rds/rdma.c | 10 ++++++++++
net/rds/rds.h | 1 +
net/rds/send.c | 4 +++-
4 files changed, 29 insertions(+), 11 deletions(-)
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 19eca5c..5e72de1 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -69,16 +69,6 @@ static void rds_ib_send_complete(struct rds_message *rm,
complete(rm, notify_status);
}
-static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
- struct rm_data_op *op,
- int wc_status)
-{
- if (op->op_nents)
- ib_dma_unmap_sg(ic->i_cm_id->device,
- op->op_sg, op->op_nents,
- DMA_TO_DEVICE);
-}
-
static void rds_ib_send_unmap_rdma(struct rds_ib_connection *ic,
struct rm_rdma_op *op,
int wc_status)
@@ -139,6 +129,21 @@ static void rds_ib_send_unmap_atomic(struct rds_ib_connection *ic,
rds_ib_stats_inc(s_ib_atomic_fadd);
}
+static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
+ struct rm_data_op *op,
+ int wc_status)
+{
+ struct rds_message *rm = container_of(op, struct rds_message, data);
+
+ if (op->op_nents)
+ ib_dma_unmap_sg(ic->i_cm_id->device,
+ op->op_sg, op->op_nents,
+ DMA_TO_DEVICE);
+
+ if (rm->rdma.op_active && rm->data.op_notify)
+ rds_ib_send_unmap_rdma(ic, &rm->rdma, wc_status);
+}
+
/*
* Unmap the resources associated with a struct send_work.
*
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 4297f3f..138aef6 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -627,6 +627,16 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
}
op->op_notifier->n_user_token = args->user_token;
op->op_notifier->n_status = RDS_RDMA_SUCCESS;
+
+ /* Enable rmda notification on data operation for composite
+ * rds messages and make sure notification is enabled only
+ * for the data operation which follows it so that application
+ * gets notified only after full message gets delivered.
+ */
+ if (rm->data.op_sg) {
+ rm->rdma.op_notify = 0;
+ rm->data.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME);
+ }
}
/* The cookie contains the R_Key of the remote memory region, and
diff --git a/net/rds/rds.h b/net/rds/rds.h
index ebbf909..0bb8213 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -419,6 +419,7 @@ struct rds_message {
} rdma;
struct rm_data_op {
unsigned int op_active:1;
+ unsigned int op_notify:1;
unsigned int op_nents;
unsigned int op_count;
unsigned int op_dmasg;
diff --git a/net/rds/send.c b/net/rds/send.c
index 0a6f38b..45e025b 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -476,12 +476,14 @@ void rds_rdma_send_complete(struct rds_message *rm, int status)
struct rm_rdma_op *ro;
struct rds_notifier *notifier;
unsigned long flags;
+ unsigned int notify = 0;
spin_lock_irqsave(&rm->m_rs_lock, flags);
+ notify = rm->rdma.op_notify | rm->data.op_notify;
ro = &rm->rdma;
if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) &&
- ro->op_active && ro->op_notify && ro->op_notifier) {
+ ro->op_active && notify && ro->op_notifier) {
notifier = ro->op_notifier;
rs = rm->m_rs;
sock_hold(rds_rs_to_sk(rs));
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 14/17] RDS: IB: fix panic due to handlers running post teardown
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
Shutdown code reaping loop takes care of emptying the
CQ's before they being destroyed. And once tasklets are
killed, the hanlders are not expected to run.
But because of core tasklet code issues, tasklet handler could
still run even after tasklet_kill,
RDS IB shutdown code already reaps the CQs before freeing
cq/qp resources so as such the handlers have nothing left
to do post shutdown.
On other hand any handler running after teardown and trying
to access already freed qp/cq resources causes issues
Patch fixes this race by makes sure that handlers returns
without any action post teardown.
Reviewed-by: Wengang <wen.gang.wang@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/ib.h | 1 +
net/rds/ib_cm.c | 12 ++++++++++++
2 files changed, 13 insertions(+)
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 1fe9f79..5404589 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -185,6 +185,7 @@ struct rds_ib_connection {
/* Endpoint role in connection */
bool i_active_side;
+ atomic_t i_cq_quiesce;
/* Send/Recv vectors */
int i_scq_vector;
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 33c8584..ce3775a 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -128,6 +128,8 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
ic->i_flowctl ? ", flow control" : "");
}
+ atomic_set(&ic->i_cq_quiesce, 0);
+
/* Init rings and fill recv. this needs to wait until protocol
* negotiation is complete, since ring layout is different
* from 3.1 to 4.1.
@@ -267,6 +269,10 @@ static void rds_ib_tasklet_fn_send(unsigned long data)
rds_ib_stats_inc(s_ib_tasklet_call);
+ /* if cq has been already reaped, ignore incoming cq event */
+ if (atomic_read(&ic->i_cq_quiesce))
+ return;
+
poll_scq(ic, ic->i_send_cq, ic->i_send_wc);
ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
poll_scq(ic, ic->i_send_cq, ic->i_send_wc);
@@ -308,6 +314,10 @@ static void rds_ib_tasklet_fn_recv(unsigned long data)
rds_ib_stats_inc(s_ib_tasklet_call);
+ /* if cq has been already reaped, ignore incoming cq event */
+ if (atomic_read(&ic->i_cq_quiesce))
+ return;
+
memset(&state, 0, sizeof(state));
poll_rcq(ic, ic->i_recv_cq, ic->i_recv_wc, &state);
ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
@@ -804,6 +814,8 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
tasklet_kill(&ic->i_send_tasklet);
tasklet_kill(&ic->i_recv_tasklet);
+ atomic_set(&ic->i_cq_quiesce, 1);
+
/* first destroy the ib state that generates callbacks */
if (ic->i_cm_id->qp)
rdma_destroy_qp(ic->i_cm_id);
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 15/17] RDS: add stat for socket recv memory usage
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
From: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Tracks the receive side memory added to scokets and removed from sockets.
Signed-off-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/rds.h | 3 +++
net/rds/recv.c | 4 ++++
2 files changed, 7 insertions(+)
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 0bb8213..8ccd5a9 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -631,6 +631,9 @@ struct rds_statistics {
uint64_t s_cong_update_received;
uint64_t s_cong_send_error;
uint64_t s_cong_send_blocked;
+ uint64_t s_recv_bytes_added_to_socket;
+ uint64_t s_recv_bytes_removed_from_socket;
+
};
/* af_rds.c */
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 9d0666e..ba19eee 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -94,6 +94,10 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk,
return;
rs->rs_rcv_bytes += delta;
+ if (delta > 0)
+ rds_stats_add(s_recv_bytes_added_to_socket, delta);
+ else
+ rds_stats_add(s_recv_bytes_removed_from_socket, -delta);
now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs);
rdsdebug("rs %p (%pI4:%u) recv bytes %d buf %d "
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 16/17] RDS: make message size limit compliant with spec
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
From: Avinash Repaka <avinash.repaka@oracle.com>
RDS support max message size as 1M but the code doesn't check this
in all cases. Patch fixes it for RDMA & non-RDMA and RDS MR size
and its enforced irrespective of underlying transport.
Signed-off-by: Avinash Repaka <avinash.repaka@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/rdma.c | 9 ++++++++-
net/rds/rds.h | 3 +++
net/rds/send.c | 31 +++++++++++++++++++++++++++++++
3 files changed, 42 insertions(+), 1 deletion(-)
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 138aef6..f06fac4 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -40,7 +40,6 @@
/*
* XXX
* - build with sparse
- * - should we limit the size of a mr region? let transport return failure?
* - should we detect duplicate keys on a socket? hmm.
* - an rdma is an mlock, apply rlimit?
*/
@@ -200,6 +199,14 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
goto out;
}
+ /* Restrict the size of mr irrespective of underlying transport
+ * To account for unaligned mr regions, subtract one from nr_pages
+ */
+ if ((nr_pages - 1) > (RDS_MAX_MSG_SIZE >> PAGE_SHIFT)) {
+ ret = -EMSGSIZE;
+ goto out;
+ }
+
rdsdebug("RDS: get_mr addr %llx len %llu nr_pages %u\n",
args->vec.addr, args->vec.bytes, nr_pages);
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 8ccd5a9..f713194 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -50,6 +50,9 @@ void rdsdebug(char *fmt, ...)
#define RDS_FRAG_SHIFT 12
#define RDS_FRAG_SIZE ((unsigned int)(1 << RDS_FRAG_SHIFT))
+/* Used to limit both RDMA and non-RDMA RDS message to 1MB */
+#define RDS_MAX_MSG_SIZE ((unsigned int)(1 << 20))
+
#define RDS_CONG_MAP_BYTES (65536 / 8)
#define RDS_CONG_MAP_PAGES (PAGE_ALIGN(RDS_CONG_MAP_BYTES) / PAGE_SIZE)
#define RDS_CONG_MAP_PAGE_BITS (PAGE_SIZE * 8)
diff --git a/net/rds/send.c b/net/rds/send.c
index 45e025b..5cc6403 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -994,6 +994,26 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn)
return hash;
}
+static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
+{
+ struct rds_rdma_args *args;
+ struct cmsghdr *cmsg;
+
+ for_each_cmsghdr(cmsg, msg) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+
+ if (cmsg->cmsg_level != SOL_RDS)
+ continue;
+
+ if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+ args = CMSG_DATA(cmsg);
+ *rdma_bytes += args->remote_vec.bytes;
+ }
+ }
+ return 0;
+}
+
int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
{
struct sock *sk = sock->sk;
@@ -1008,6 +1028,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
int nonblock = msg->msg_flags & MSG_DONTWAIT;
long timeo = sock_sndtimeo(sk, nonblock);
struct rds_conn_path *cpath;
+ size_t total_payload_len = payload_len, rdma_payload_len = 0;
/* Mirror Linux UDP mirror of BSD error message compatibility */
/* XXX: Perhaps MSG_MORE someday */
@@ -1040,6 +1061,16 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
}
release_sock(sk);
+ ret = rds_rdma_bytes(msg, &rdma_payload_len);
+ if (ret)
+ goto out;
+
+ total_payload_len += rdma_payload_len;
+ if (max_t(size_t, payload_len, rdma_payload_len) > RDS_MAX_MSG_SIZE) {
+ ret = -EMSGSIZE;
+ goto out;
+ }
+
if (payload_len > rds_sk_sndbuf(rs)) {
ret = -EMSGSIZE;
goto out;
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 17/17] RDS: add receive message trace used by application
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
Socket option to tap receive path latency in various stages
in nano seconds. It can be enabled on selective sockets using
using SO_RDS_MSG_RXPATH_LATENCY socket option. RDS will return
the data to application with RDS_CMSG_RXPATH_LATENCY in defined
format. Scope is left to add more trace points for future
without need of change in the interface.
Reviewed-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
include/uapi/linux/rds.h | 33 +++++++++++++++++++++++++++++++++
net/rds/af_rds.c | 28 ++++++++++++++++++++++++++++
net/rds/ib_recv.c | 4 ++++
net/rds/rds.h | 10 ++++++++++
net/rds/recv.c | 32 +++++++++++++++++++++++++++++---
net/rds/tcp_recv.c | 5 +++++
6 files changed, 109 insertions(+), 3 deletions(-)
diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h
index 0f9265c..3833113 100644
--- a/include/uapi/linux/rds.h
+++ b/include/uapi/linux/rds.h
@@ -52,6 +52,13 @@
#define RDS_GET_MR_FOR_DEST 7
#define SO_RDS_TRANSPORT 8
+/* Socket option to tap receive path latency
+ * SO_RDS: SO_RDS_MSG_RXPATH_LATENCY
+ * Format used struct rds_rx_trace_so
+ */
+#define SO_RDS_MSG_RXPATH_LATENCY 10
+
+
/* supported values for SO_RDS_TRANSPORT */
#define RDS_TRANS_IB 0
#define RDS_TRANS_IWARP 1
@@ -77,6 +84,12 @@
* the same as for the GET_MR setsockopt.
* RDS_CMSG_RDMA_STATUS (recvmsg)
* Returns the status of a completed RDMA operation.
+ * RDS_CMSG_RXPATH_LATENCY(recvmsg)
+ * Returns rds message latencies in various stages of receive
+ * path in nS. Its set per socket using SO_RDS_MSG_RXPATH_LATENCY
+ * socket option. Legitimate points are defined in
+ * enum rds_message_rxpath_latency. More points can be added in
+ * future. CSMG format is struct rds_cmsg_rx_trace.
*/
#define RDS_CMSG_RDMA_ARGS 1
#define RDS_CMSG_RDMA_DEST 2
@@ -87,6 +100,7 @@
#define RDS_CMSG_ATOMIC_CSWP 7
#define RDS_CMSG_MASKED_ATOMIC_FADD 8
#define RDS_CMSG_MASKED_ATOMIC_CSWP 9
+#define RDS_CMSG_RXPATH_LATENCY 11
#define RDS_INFO_FIRST 10000
#define RDS_INFO_COUNTERS 10000
@@ -171,6 +185,25 @@ struct rds_info_rdma_connection {
uint32_t rdma_mr_size;
};
+/* RDS message Receive Path Latency points */
+enum rds_message_rxpath_latency {
+ RDS_MSG_RX_HDR_TO_DGRAM_START = 0,
+ RDS_MSG_RX_DGRAM_REASSEMBLE,
+ RDS_MSG_RX_DGRAM_DELIVERED,
+ RDS_MSG_RX_DGRAM_TRACE_MAX
+};
+
+struct rds_rx_trace_so {
+ u8 rx_traces;
+ u8 rx_trace_pos[RDS_MSG_RX_DGRAM_TRACE_MAX];
+};
+
+struct rds_cmsg_rx_trace {
+ u8 rx_traces;
+ u8 rx_trace_pos[RDS_MSG_RX_DGRAM_TRACE_MAX];
+ u64 rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX];
+};
+
/*
* Congestion monitoring.
* Congestion control in RDS happens at the host connection
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 2ac1e61..fd821740 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -298,6 +298,30 @@ static int rds_enable_recvtstamp(struct sock *sk, char __user *optval,
return 0;
}
+static int rds_recv_track_latency(struct rds_sock *rs, char __user *optval,
+ int optlen)
+{
+ struct rds_rx_trace_so trace;
+ int i;
+
+ if (optlen != sizeof(struct rds_rx_trace_so))
+ return -EFAULT;
+
+ if (copy_from_user(&trace, optval, sizeof(trace)))
+ return -EFAULT;
+
+ rs->rs_rx_traces = trace.rx_traces;
+ for (i = 0; i < rs->rs_rx_traces; i++) {
+ if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) {
+ rs->rs_rx_traces = 0;
+ return -EFAULT;
+ }
+ rs->rs_rx_trace[i] = trace.rx_trace_pos[i];
+ }
+
+ return 0;
+}
+
static int rds_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
@@ -338,6 +362,9 @@ static int rds_setsockopt(struct socket *sock, int level, int optname,
ret = rds_enable_recvtstamp(sock->sk, optval, optlen);
release_sock(sock->sk);
break;
+ case SO_RDS_MSG_RXPATH_LATENCY:
+ ret = rds_recv_track_latency(rs, optval, optlen);
+ break;
default:
ret = -ENOPROTOOPT;
}
@@ -484,6 +511,7 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol)
INIT_LIST_HEAD(&rs->rs_cong_list);
spin_lock_init(&rs->rs_rdma_lock);
rs->rs_rdma_keys = RB_ROOT;
+ rs->rs_rx_traces = 0;
spin_lock_bh(&rds_sock_lock);
list_add_tail(&rs->rs_item, &rds_sock_list);
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 4b0f126..e10624a 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -911,8 +911,12 @@ static void rds_ib_process_recv(struct rds_connection *conn,
ic->i_ibinc = ibinc;
hdr = &ibinc->ii_inc.i_hdr;
+ ibinc->ii_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] =
+ local_clock();
memcpy(hdr, ihdr, sizeof(*hdr));
ic->i_recv_data_rem = be32_to_cpu(hdr->h_len);
+ ibinc->ii_inc.i_rx_lat_trace[RDS_MSG_RX_START] =
+ local_clock();
rdsdebug("ic %p ibinc %p rem %u flag 0x%x\n", ic, ibinc,
ic->i_recv_data_rem, hdr->h_flags);
diff --git a/net/rds/rds.h b/net/rds/rds.h
index f713194..07fff73 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -253,6 +253,11 @@ struct rds_ext_header_rdma_dest {
#define RDS_EXTHDR_GEN_NUM 6
#define __RDS_EXTHDR_MAX 16 /* for now */
+#define RDS_RX_MAX_TRACES (RDS_MSG_RX_DGRAM_TRACE_MAX + 1)
+#define RDS_MSG_RX_HDR 0
+#define RDS_MSG_RX_START 1
+#define RDS_MSG_RX_END 2
+#define RDS_MSG_RX_CMSG 3
struct rds_incoming {
atomic_t i_refcount;
@@ -265,6 +270,7 @@ struct rds_incoming {
rds_rdma_cookie_t i_rdma_cookie;
struct timeval i_rx_tstamp;
+ u64 i_rx_lat_trace[RDS_RX_MAX_TRACES];
};
struct rds_mr {
@@ -575,6 +581,10 @@ struct rds_sock {
unsigned char rs_recverr,
rs_cong_monitor;
u32 rs_hash_initval;
+
+ /* Socket receive path trace points*/
+ u8 rs_rx_traces;
+ u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX];
};
static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk)
diff --git a/net/rds/recv.c b/net/rds/recv.c
index ba19eee..8b7e7b7 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -43,6 +43,8 @@
void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
__be32 saddr)
{
+ int i;
+
atomic_set(&inc->i_refcount, 1);
INIT_LIST_HEAD(&inc->i_item);
inc->i_conn = conn;
@@ -50,6 +52,9 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
inc->i_rdma_cookie = 0;
inc->i_rx_tstamp.tv_sec = 0;
inc->i_rx_tstamp.tv_usec = 0;
+
+ for (i = 0; i < RDS_RX_MAX_TRACES; i++)
+ inc->i_rx_lat_trace[i] = 0;
}
EXPORT_SYMBOL_GPL(rds_inc_init);
@@ -373,6 +378,7 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
if (sock_flag(sk, SOCK_RCVTSTAMP))
do_gettimeofday(&inc->i_rx_tstamp);
rds_inc_addref(inc);
+ inc->i_rx_lat_trace[RDS_MSG_RX_END] = local_clock();
list_add_tail(&inc->i_item, &rs->rs_recv_queue);
__rds_wake_sk_sleep(sk);
} else {
@@ -534,7 +540,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg,
ret = put_cmsg(msg, SOL_RDS, RDS_CMSG_RDMA_DEST,
sizeof(inc->i_rdma_cookie), &inc->i_rdma_cookie);
if (ret)
- return ret;
+ goto out;
}
if ((inc->i_rx_tstamp.tv_sec != 0) &&
@@ -543,10 +549,30 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg,
sizeof(struct timeval),
&inc->i_rx_tstamp);
if (ret)
- return ret;
+ goto out;
}
- return 0;
+ if (rs->rs_rx_traces) {
+ struct rds_cmsg_rx_trace t;
+ int i, j;
+
+ inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock();
+ t.rx_traces = rs->rs_rx_traces;
+ for (i = 0; i < rs->rs_rx_traces; i++) {
+ j = rs->rs_rx_trace[i];
+ t.rx_trace_pos[i] = j;
+ t.rx_trace[i] = inc->i_rx_lat_trace[j + 1] -
+ inc->i_rx_lat_trace[j];
+ }
+
+ ret = put_cmsg(msg, SOL_RDS, RDS_CMSG_RXPATH_LATENCY,
+ sizeof(t), &t);
+ if (ret)
+ goto out;
+ }
+
+out:
+ return ret;
}
int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index ad4892e..e006ef8 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -180,6 +180,9 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
rdsdebug("alloced tinc %p\n", tinc);
rds_inc_path_init(&tinc->ti_inc, cp,
cp->cp_conn->c_faddr);
+ tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] =
+ local_clock();
+
/*
* XXX * we might be able to use the __ variants when
* we've already serialized at a higher level.
@@ -204,6 +207,8 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
/* could be 0 for a 0 len message */
tc->t_tinc_data_rem =
be32_to_cpu(tinc->ti_inc.i_hdr.h_len);
+ tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_START] =
+ local_clock();
}
}
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 00/17] net: RDS updates
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
v2->v3:
- Re-based against latest net-next head.
- Dropped a user visible change after discussing with David Miller.
It needs some more work to fully support old/new tools matrix.
- Addressed Dave's comment about bool usage in patch
"RDS: IB: track and log active side..."
v1->v2:
Re-aligned indentation in patch 'RDS: mark few internal functions..."
Series consist of:
- RDMA transport fixes for map failure, listen sequence, handler panic and
composite message notification.
- Couple of sparse fixes.
- Message logging improvements for bind failure, use once mr semantics
and connection remote address, active end point.
- Performance improvement for RDMA transport by reducing the post send
pressure on the queue and spreading the CQ vectors.
- Useful statistics for socket send/recv usage and receive cache usage.
- Additional RDS CMSG used by application to track the RDS message
stages for certain type of traffic to find out latency spots.
Can be enabled/disabled per socket.
Series generated against 'net-next'. Full patchset is also available on
below git tree.
The following changes since commit 525dfa2cdce4f5ab76251b5e57ebabf4f2dfc40c:
Merge branch 'mlx5-odp' (2017-01-02 15:51:21 -0500)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux.git for_4.11/net-next/rds_v3
for you to fetch changes up to 3289025aedc018f8fd9d0e37fb9efa0c6d531ffa:
RDS: add receive message trace used by application (2017-01-02 14:02:59 -0800)
----------------------------------------------------------------
Avinash Repaka (1):
RDS: make message size limit compliant with spec
Qing Huang (1):
RDS: RDMA: start rdma listening after init
Santosh Shilimkar (14):
RDS: log the address on bind failure
RDS: mark few internal functions static to make sparse build happy
RDS: IB: include faddr in connection log
RDS: IB: make the transport retry count smallest
RDS: RDMA: fix the ib_map_mr_sg_zbva() argument
RDS: RDMA: return appropriate error on rdma map failures
RDS: IB: split the mr registration and invalidation path
RDS: RDMA: silence the use_once mr log flood
RDS: IB: track and log active side endpoint in connection
RDS: IB: add few useful cache stasts
RDS: IB: Add vector spreading for cqs
RDS: RDMA: Fix the composite message user notification
RDS: IB: fix panic due to handlers running post teardown
RDS: add receive message trace used by application
Venkat Venkatsubra (1):
RDS: add stat for socket recv memory usage
include/uapi/linux/rds.h | 33 ++++++++++++++++++
net/rds/af_rds.c | 28 +++++++++++++++
net/rds/bind.c | 4 +--
net/rds/connection.c | 10 +++---
net/rds/ib.c | 11 ++++++
net/rds/ib.h | 22 ++++++++++--
net/rds/ib_cm.c | 89 ++++++++++++++++++++++++++++++++++++++----------
net/rds/ib_frmr.c | 16 +++++----
net/rds/ib_recv.c | 14 ++++++--
net/rds/ib_send.c | 29 +++++++++-------
net/rds/ib_stats.c | 2 ++
net/rds/rdma.c | 22 ++++++++++--
net/rds/rdma_transport.c | 11 ++----
net/rds/rds.h | 17 +++++++++
net/rds/recv.c | 36 ++++++++++++++++++--
net/rds/send.c | 50 ++++++++++++++++++++++++---
net/rds/tcp_listen.c | 1 +
net/rds/tcp_recv.c | 5 +++
18 files changed, 335 insertions(+), 65 deletions(-)
--
1.9.1
^ permalink raw reply
* [net-next][PATCH v3 05/17] RDS: RDMA: fix the ib_map_mr_sg_zbva() argument
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
Fixes warning: Using plain integer as NULL pointer
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/ib_frmr.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index d921adc..66b3d62 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -104,14 +104,15 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
struct rds_ib_frmr *frmr = &ibmr->u.frmr;
struct ib_send_wr *failed_wr;
struct ib_reg_wr reg_wr;
- int ret;
+ int ret, off = 0;
while (atomic_dec_return(&ibmr->ic->i_fastreg_wrs) <= 0) {
atomic_inc(&ibmr->ic->i_fastreg_wrs);
cpu_relax();
}
- ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len, 0, PAGE_SIZE);
+ ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len,
+ &off, PAGE_SIZE);
if (unlikely(ret != ibmr->sg_len))
return ret < 0 ? ret : -EINVAL;
--
1.9.1
^ permalink raw reply related
* [net-next][PATCH v3 06/17] RDS: RDMA: start rdma listening after init
From: Santosh Shilimkar @ 2017-01-02 22:45 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-kernel, santosh.shilimkar
In-Reply-To: <1483397152-8307-1-git-send-email-santosh.shilimkar@oracle.com>
From: Qing Huang <qing.huang@oracle.com>
This prevents RDS from handling incoming rdma packets before RDS
completes initializing its recv/send components.
Signed-off-by: Qing Huang <qing.huang@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/rdma_transport.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index d5f3117..fc59821 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -206,18 +206,13 @@ static int rds_rdma_init(void)
{
int ret;
- ret = rds_rdma_listen_init();
+ ret = rds_ib_init();
if (ret)
goto out;
- ret = rds_ib_init();
+ ret = rds_rdma_listen_init();
if (ret)
- goto err_ib_init;
-
- goto out;
-
-err_ib_init:
- rds_rdma_listen_stop();
+ rds_ib_exit();
out:
return ret;
}
--
1.9.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox