* [net-next PATCH v3 3/5] net: Enable Tx queue selection based on Rx queues
From: Amritha Nambiar @ 2018-06-05 8:38 UTC (permalink / raw)
To: netdev, davem
Cc: alexander.h.duyck, willemdebruijn.kernel, amritha.nambiar,
sridhar.samudrala, edumazet, hannes, tom
In-Reply-To: <152818727065.20862.10108275498797168689.stgit@anamdev.jf.intel.com>
This patch adds support to pick Tx queue based on the Rx queue(s) map
configuration set by the admin through the sysfs attribute
for each Tx queue. If the user configuration for receive queue(s) map
does not apply, then the Tx queue selection falls back to CPU(s) map
based selection and finally to hashing.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
include/net/busy_poll.h | 3 ++
include/net/sock.h | 14 +++++++++++
net/core/dev.c | 60 ++++++++++++++++++++++++++++++++---------------
net/core/sock.c | 4 +++
net/ipv4/tcp_input.c | 3 ++
5 files changed, 65 insertions(+), 19 deletions(-)
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 71c72a9..fc4fb68 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -136,6 +136,9 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = skb->napi_id;
#endif
+#ifdef CONFIG_XPS
+ sk->sk_rx_queue_mapping = skb_get_rx_queue(skb);
+#endif
}
/* variant used for unconnected sockets */
diff --git a/include/net/sock.h b/include/net/sock.h
index 4f7c584..12313653 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -139,6 +139,7 @@ typedef __u64 __bitwise __addrpair;
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
* @skc_tx_queue_mapping: tx queue number for this connection
+ * @skc_rx_queue_mapping: rx queue number for this connection
* @skc_flags: place holder for sk_flags
* %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
@@ -215,6 +216,9 @@ struct sock_common {
struct hlist_nulls_node skc_nulls_node;
};
int skc_tx_queue_mapping;
+#ifdef CONFIG_XPS
+ int skc_rx_queue_mapping;
+#endif
union {
int skc_incoming_cpu;
u32 skc_rcv_wnd;
@@ -326,6 +330,9 @@ struct sock {
#define sk_nulls_node __sk_common.skc_nulls_node
#define sk_refcnt __sk_common.skc_refcnt
#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping
+#ifdef CONFIG_XPS
+#define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping
+#endif
#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin
#define sk_dontcopy_end __sk_common.skc_dontcopy_end
@@ -1696,6 +1703,13 @@ static inline int sk_tx_queue_get(const struct sock *sk)
return sk ? sk->sk_tx_queue_mapping : -1;
}
+static inline void sk_mark_rx_queue(struct sock *sk, struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+ sk->sk_rx_queue_mapping = skb_get_rx_queue(skb);
+#endif
+}
+
static inline void sk_set_socket(struct sock *sk, struct socket *sock)
{
sk_tx_queue_clear(sk);
diff --git a/net/core/dev.c b/net/core/dev.c
index bba755f..1880e6c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3479,36 +3479,58 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
}
#endif /* CONFIG_NET_EGRESS */
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+#ifdef CONFIG_XPS
+static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
+ struct xps_dev_maps *dev_maps, unsigned int tci)
+{
+ struct xps_map *map;
+ int queue_index = -1;
+
+ if (dev->num_tc) {
+ tci *= dev->num_tc;
+ tci += netdev_get_prio_tc_map(dev, skb->priority);
+ }
+
+ map = rcu_dereference(dev_maps->attr_map[tci]);
+ if (map) {
+ if (map->len == 1)
+ queue_index = map->queues[0];
+ else
+ queue_index = map->queues[reciprocal_scale(
+ skb_get_hash(skb), map->len)];
+ if (unlikely(queue_index >= dev->real_num_tx_queues))
+ queue_index = -1;
+ }
+ return queue_index;
+}
+#endif
+
+static int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_XPS
struct xps_dev_maps *dev_maps;
- struct xps_map *map;
+ struct sock *sk = skb->sk;
int queue_index = -1;
+ unsigned int tci = 0;
if (!static_key_false(&xps_needed))
return -1;
+ if (sk && sk->sk_rx_queue_mapping <= dev->num_rx_queues)
+ tci = sk->sk_rx_queue_mapping;
+
rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_cpus_map);
- if (dev_maps) {
- unsigned int tci = skb->sender_cpu - 1;
+ dev_maps = rcu_dereference(dev->xps_rxqs_map);
+ if (dev_maps)
+ queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci);
- if (dev->num_tc) {
- tci *= dev->num_tc;
- tci += netdev_get_prio_tc_map(dev, skb->priority);
- }
- map = rcu_dereference(dev_maps->attr_map[tci]);
- if (map) {
- if (map->len == 1)
- queue_index = map->queues[0];
- else
- queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
- map->len)];
- if (unlikely(queue_index >= dev->real_num_tx_queues))
- queue_index = -1;
- }
+ if (queue_index < 0) {
+ tci = skb->sender_cpu - 1;
+ dev_maps = rcu_dereference(dev->xps_cpus_map);
+ if (dev_maps)
+ queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
+ tci);
}
rcu_read_unlock();
diff --git a/net/core/sock.c b/net/core/sock.c
index 435a0ba..3c10d31 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2824,6 +2824,10 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_pacing_rate = ~0U;
sk->sk_pacing_shift = 10;
sk->sk_incoming_cpu = -1;
+
+#ifdef CONFIG_XPS
+ sk->sk_rx_queue_mapping = -1;
+#endif
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d5ffb57..cc69f75 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -78,6 +78,7 @@
#include <linux/errqueue.h>
#include <trace/events/tcp.h>
#include <linux/static_key.h>
+#include <net/busy_poll.h>
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
@@ -5574,6 +5575,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
if (skb) {
icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
security_inet_conn_established(sk, skb);
+ sk_mark_napi_id(sk, skb);
}
tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
@@ -6402,6 +6404,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->snt_isn = isn;
tcp_rsk(req)->txhash = net_tx_rndhash();
tcp_openreq_init_rwin(req, sk, dst);
+ sk_mark_rx_queue(req_to_sk(req), skb);
if (!want_cookie) {
tcp_reqsk_record_syn(sk, req, skb);
fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
^ permalink raw reply related
* [net-next PATCH v3 2/5] net: Use static_key for XPS maps
From: Amritha Nambiar @ 2018-06-05 8:37 UTC (permalink / raw)
To: netdev, davem
Cc: alexander.h.duyck, willemdebruijn.kernel, amritha.nambiar,
sridhar.samudrala, edumazet, hannes, tom
In-Reply-To: <152818727065.20862.10108275498797168689.stgit@anamdev.jf.intel.com>
Use static_key for XPS maps to reduce the cost of extra map checks,
similar to how it is used for RPS and RFS.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
---
net/core/dev.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/net/core/dev.c b/net/core/dev.c
index 156acbe..bba755f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2081,6 +2081,8 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
EXPORT_SYMBOL(netdev_txq_to_tc);
#ifdef CONFIG_XPS
+struct static_key xps_needed __read_mostly;
+EXPORT_SYMBOL(xps_needed);
static DEFINE_MUTEX(xps_map_mutex);
#define xmap_dereference(P) \
rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
@@ -2189,6 +2191,7 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
out_no_maps:
type++;
}
+ static_key_slow_dec(&xps_needed);
mutex_unlock(&xps_map_mutex);
}
@@ -2309,6 +2312,8 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
if (!new_dev_maps)
goto out_no_new_maps;
+ static_key_slow_inc(&xps_needed);
+
for (j = -1; j = attrmask_next(j, possible_mask, nr_ids),
j < nr_ids;) {
/* copy maps belonging to foreign traffic classes */
@@ -3481,6 +3486,9 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
struct xps_map *map;
int queue_index = -1;
+ if (!static_key_false(&xps_needed))
+ return -1;
+
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_cpus_map);
if (dev_maps) {
^ permalink raw reply related
* [net-next PATCH v3 1/5] net: Refactor XPS for CPUs and Rx queues
From: Amritha Nambiar @ 2018-06-05 8:37 UTC (permalink / raw)
To: netdev, davem
Cc: alexander.h.duyck, willemdebruijn.kernel, amritha.nambiar,
sridhar.samudrala, edumazet, hannes, tom
In-Reply-To: <152818727065.20862.10108275498797168689.stgit@anamdev.jf.intel.com>
Refactor XPS code to support Tx queue selection based on
CPU(s) map or Rx queue(s) map.
Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
---
include/linux/cpumask.h | 11 ++
include/linux/netdevice.h | 73 ++++++++++++++
net/core/dev.c | 228 ++++++++++++++++++++++++++++++---------------
net/core/net-sysfs.c | 4 -
4 files changed, 234 insertions(+), 82 deletions(-)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index bf53d89..57f20a0 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -115,12 +115,17 @@ extern struct cpumask __cpu_active_mask;
#define cpu_active(cpu) ((cpu) == 0)
#endif
-/* verify cpu argument to cpumask_* operators */
-static inline unsigned int cpumask_check(unsigned int cpu)
+static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
{
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
- WARN_ON_ONCE(cpu >= nr_cpumask_bits);
+ WARN_ON_ONCE(cpu >= bits);
#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
+}
+
+/* verify cpu argument to cpumask_* operators */
+static inline unsigned int cpumask_check(unsigned int cpu)
+{
+ cpu_max_bits_warn(cpu, nr_cpumask_bits);
return cpu;
}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6b863ed..354c866 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -730,10 +730,21 @@ struct xps_map {
*/
struct xps_dev_maps {
struct rcu_head rcu;
- struct xps_map __rcu *cpu_map[0];
+ struct xps_map __rcu *attr_map[0];
};
-#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
+
+#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
(nr_cpu_ids * (_tcs) * sizeof(struct xps_map *)))
+
+#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\
+ (_rxqs * (_tcs) * sizeof(struct xps_map *)))
+
+enum xps_map_type {
+ XPS_MAP_RXQS,
+ XPS_MAP_CPUS,
+ __XPS_MAP_MAX
+};
+
#endif /* CONFIG_XPS */
#define TC_MAX_QUEUE 16
@@ -1902,7 +1913,8 @@ struct net_device {
int watchdog_timeo;
#ifdef CONFIG_XPS
- struct xps_dev_maps __rcu *xps_maps;
+ struct xps_dev_maps __rcu *xps_cpus_map;
+ struct xps_dev_maps __rcu *xps_rxqs_map;
#endif
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc __rcu *miniq_egress;
@@ -3251,6 +3263,61 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
#ifdef CONFIG_XPS
int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
u16 index);
+int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
+ u16 index, enum xps_map_type type);
+
+static inline bool attr_test_mask(unsigned long j, const unsigned long *mask,
+ unsigned int nr_bits)
+{
+ cpu_max_bits_warn(j, nr_bits);
+ return test_bit(j, mask);
+}
+
+static inline bool attr_test_online(unsigned long j,
+ const unsigned long *online_mask,
+ unsigned int nr_bits)
+{
+ cpu_max_bits_warn(j, nr_bits);
+
+ if (online_mask)
+ return test_bit(j, online_mask);
+
+ if (j >= 0 && j < nr_bits)
+ return true;
+
+ return false;
+}
+
+static inline unsigned int attrmask_next(int n, const unsigned long *srcp,
+ unsigned int nr_bits)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpu_max_bits_warn(n, nr_bits);
+
+ if (srcp)
+ return find_next_bit(srcp, nr_bits, n + 1);
+
+ return n + 1;
+}
+
+static inline int attrmask_next_and(int n, const unsigned long *src1p,
+ const unsigned long *src2p,
+ unsigned int nr_bits)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpu_max_bits_warn(n, nr_bits);
+
+ if (src1p && src2p)
+ return find_next_and_bit(src1p, src2p, nr_bits, n + 1);
+ else if (src1p)
+ return find_next_bit(src1p, nr_bits, n + 1);
+ else if (src2p)
+ return find_next_bit(src2p, nr_bits, n + 1);
+
+ return n + 1;
+}
#else
static inline int netif_set_xps_queue(struct net_device *dev,
const struct cpumask *mask,
diff --git a/net/core/dev.c b/net/core/dev.c
index 1844d9b..156acbe 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2092,7 +2092,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
int pos;
if (dev_maps)
- map = xmap_dereference(dev_maps->cpu_map[tci]);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
if (!map)
return false;
@@ -2105,7 +2105,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
break;
}
- RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL);
+ RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
kfree_rcu(map, rcu);
return false;
}
@@ -2138,30 +2138,57 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
u16 count)
{
+ const unsigned long *possible_mask = NULL;
+ enum xps_map_type type = XPS_MAP_RXQS;
struct xps_dev_maps *dev_maps;
- int cpu, i;
bool active = false;
+ unsigned int nr_ids;
+ int i, j;
mutex_lock(&xps_map_mutex);
- dev_maps = xmap_dereference(dev->xps_maps);
-
- if (!dev_maps)
- goto out_no_maps;
-
- for_each_possible_cpu(cpu)
- active |= remove_xps_queue_cpu(dev, dev_maps, cpu,
- offset, count);
-
- if (!active) {
- RCU_INIT_POINTER(dev->xps_maps, NULL);
- kfree_rcu(dev_maps, rcu);
- }
+ while (type < __XPS_MAP_MAX) {
+ switch (type) {
+ case XPS_MAP_RXQS:
+ dev_maps = xmap_dereference(dev->xps_rxqs_map);
+ if (!dev_maps)
+ goto out_no_maps;
+ nr_ids = dev->num_rx_queues;
+ break;
+ case XPS_MAP_CPUS:
+ dev_maps = xmap_dereference(dev->xps_cpus_map);
+ if (!dev_maps)
+ goto out_no_maps;
+
+ if (num_possible_cpus() > 1)
+ possible_mask = cpumask_bits(cpu_possible_mask);
+ nr_ids = nr_cpu_ids;
+ break;
+ default:
+ goto out_no_maps;
+ }
- for (i = offset + (count - 1); count--; i--)
- netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i),
- NUMA_NO_NODE);
+ for (j = -1; j = attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;)
+ active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
+ count);
+ if (!active) {
+ if (type == XPS_MAP_RXQS)
+ RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+
+ if (type == XPS_MAP_CPUS) {
+ RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
+
+ for (i = offset + (count - 1); count--; i--)
+ netdev_queue_numa_node_write(
+ netdev_get_tx_queue(dev, i),
+ NUMA_NO_NODE);
+ }
+ kfree_rcu(dev_maps, rcu);
+ }
out_no_maps:
+ type++;
+ }
mutex_unlock(&xps_map_mutex);
}
@@ -2170,8 +2197,8 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
netif_reset_xps_queues(dev, index, dev->num_tx_queues - index);
}
-static struct xps_map *expand_xps_map(struct xps_map *map,
- int cpu, u16 index)
+static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index,
+ u16 index, enum xps_map_type type)
{
struct xps_map *new_map;
int alloc_len = XPS_MIN_MAP_ALLOC;
@@ -2183,7 +2210,7 @@ static struct xps_map *expand_xps_map(struct xps_map *map,
return map;
}
- /* Need to add queue to this CPU's existing map */
+ /* Need to add tx-queue to this CPU's/rx-queue's existing map */
if (map) {
if (pos < map->alloc_len)
return map;
@@ -2191,9 +2218,20 @@ static struct xps_map *expand_xps_map(struct xps_map *map,
alloc_len = map->alloc_len * 2;
}
- /* Need to allocate new map to store queue on this CPU's map */
- new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
- cpu_to_node(cpu));
+ /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's
+ * map
+ */
+ switch (type) {
+ case XPS_MAP_RXQS:
+ new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL);
+ break;
+ case XPS_MAP_CPUS:
+ new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
+ cpu_to_node(attr_index));
+ break;
+ default:
+ return NULL;
+ }
if (!new_map)
return NULL;
@@ -2205,14 +2243,16 @@ static struct xps_map *expand_xps_map(struct xps_map *map,
return new_map;
}
-int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
- u16 index)
+int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
+ u16 index, enum xps_map_type type)
{
+ const unsigned long *online_mask = NULL, *possible_mask = NULL;
struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
- int i, cpu, tci, numa_node_id = -2;
+ int i, j, tci, numa_node_id = -2;
int maps_sz, num_tc = 1, tc = 0;
struct xps_map *map, *new_map;
bool active = false;
+ unsigned int nr_ids;
if (dev->num_tc) {
num_tc = dev->num_tc;
@@ -2221,16 +2261,33 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
return -EINVAL;
}
- maps_sz = XPS_DEV_MAPS_SIZE(num_tc);
- if (maps_sz < L1_CACHE_BYTES)
- maps_sz = L1_CACHE_BYTES;
-
mutex_lock(&xps_map_mutex);
+ switch (type) {
+ case XPS_MAP_RXQS:
+ maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues);
+ dev_maps = xmap_dereference(dev->xps_rxqs_map);
+ nr_ids = dev->num_rx_queues;
+ break;
+ case XPS_MAP_CPUS:
+ maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc);
+ if (num_possible_cpus() > 1) {
+ online_mask = cpumask_bits(cpu_online_mask);
+ possible_mask = cpumask_bits(cpu_possible_mask);
+ }
+ dev_maps = xmap_dereference(dev->xps_cpus_map);
+ nr_ids = nr_cpu_ids;
+ break;
+ default:
+ mutex_unlock(&xps_map_mutex);
+ return -EINVAL;
+ }
- dev_maps = xmap_dereference(dev->xps_maps);
+ if (maps_sz < L1_CACHE_BYTES)
+ maps_sz = L1_CACHE_BYTES;
/* allocate memory for queue storage */
- for_each_cpu_and(cpu, cpu_online_mask, mask) {
+ for (j = -1; j = attrmask_next_and(j, online_mask, mask, nr_ids),
+ j < nr_ids;) {
if (!new_dev_maps)
new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
if (!new_dev_maps) {
@@ -2238,73 +2295,81 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
return -ENOMEM;
}
- tci = cpu * num_tc + tc;
- map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) :
+ tci = j * num_tc + tc;
+ map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) :
NULL;
- map = expand_xps_map(map, cpu, index);
+ map = expand_xps_map(map, j, index, type);
if (!map)
goto error;
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
if (!new_dev_maps)
goto out_no_new_maps;
- for_each_possible_cpu(cpu) {
+ for (j = -1; j = attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
/* copy maps belonging to foreign traffic classes */
- for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) {
+ for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) {
/* fill in the new device map from the old device map */
- map = xmap_dereference(dev_maps->cpu_map[tci]);
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
/* We need to explicitly update tci as prevous loop
* could break out early if dev_maps is NULL.
*/
- tci = cpu * num_tc + tc;
+ tci = j * num_tc + tc;
- if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) {
- /* add queue to CPU maps */
+ if (attr_test_mask(j, mask, nr_ids) &&
+ attr_test_online(j, online_mask, nr_ids)) {
+ /* add tx-queue to CPU/rx-queue maps */
int pos = 0;
- map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+ map = xmap_dereference(new_dev_maps->attr_map[tci]);
while ((pos < map->len) && (map->queues[pos] != index))
pos++;
if (pos == map->len)
map->queues[map->len++] = index;
#ifdef CONFIG_NUMA
- if (numa_node_id == -2)
- numa_node_id = cpu_to_node(cpu);
- else if (numa_node_id != cpu_to_node(cpu))
- numa_node_id = -1;
+ if (type == XPS_MAP_CPUS) {
+ if (numa_node_id == -2)
+ numa_node_id = cpu_to_node(j);
+ else if (numa_node_id != cpu_to_node(j))
+ numa_node_id = -1;
+ }
#endif
} else if (dev_maps) {
/* fill in the new device map from the old device map */
- map = xmap_dereference(dev_maps->cpu_map[tci]);
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
/* copy maps belonging to foreign traffic classes */
for (i = num_tc - tc, tci++; dev_maps && --i; tci++) {
/* fill in the new device map from the old device map */
- map = xmap_dereference(dev_maps->cpu_map[tci]);
- RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
}
}
- rcu_assign_pointer(dev->xps_maps, new_dev_maps);
+ if (type == XPS_MAP_RXQS)
+ rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps);
+ else if (type == XPS_MAP_CPUS)
+ rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps);
/* Cleanup old maps */
if (!dev_maps)
goto out_no_old_maps;
- for_each_possible_cpu(cpu) {
- for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
- new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
- map = xmap_dereference(dev_maps->cpu_map[tci]);
+ for (j = -1; j = attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
+ for (i = num_tc, tci = j * num_tc; i--; tci++) {
+ new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
+ map = xmap_dereference(dev_maps->attr_map[tci]);
if (map && map != new_map)
kfree_rcu(map, rcu);
}
@@ -2317,19 +2382,23 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
active = true;
out_no_new_maps:
- /* update Tx queue numa node */
- netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
- (numa_node_id >= 0) ? numa_node_id :
- NUMA_NO_NODE);
+ if (type == XPS_MAP_CPUS) {
+ /* update Tx queue numa node */
+ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
+ (numa_node_id >= 0) ?
+ numa_node_id : NUMA_NO_NODE);
+ }
if (!dev_maps)
goto out_no_maps;
- /* removes queue from unused CPUs */
- for_each_possible_cpu(cpu) {
- for (i = tc, tci = cpu * num_tc; i--; tci++)
+ /* removes tx-queue from unused CPUs/rx-queues */
+ for (j = -1; j = attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
+ for (i = tc, tci = j * num_tc; i--; tci++)
active |= remove_xps_queue(dev_maps, tci, index);
- if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu))
+ if (!attr_test_mask(j, mask, nr_ids) ||
+ !attr_test_online(j, online_mask, nr_ids))
active |= remove_xps_queue(dev_maps, tci, index);
for (i = num_tc - tc, tci++; --i; tci++)
active |= remove_xps_queue(dev_maps, tci, index);
@@ -2337,7 +2406,10 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
/* free map if not active */
if (!active) {
- RCU_INIT_POINTER(dev->xps_maps, NULL);
+ if (type == XPS_MAP_RXQS)
+ RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+ else if (type == XPS_MAP_CPUS)
+ RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
kfree_rcu(dev_maps, rcu);
}
@@ -2347,11 +2419,12 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
return 0;
error:
/* remove any maps that we added */
- for_each_possible_cpu(cpu) {
- for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
- new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+ for (j = -1; j = attrmask_next(j, possible_mask, nr_ids),
+ j < nr_ids;) {
+ for (i = num_tc, tci = j * num_tc; i--; tci++) {
+ new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
map = dev_maps ?
- xmap_dereference(dev_maps->cpu_map[tci]) :
+ xmap_dereference(dev_maps->attr_map[tci]) :
NULL;
if (new_map && new_map != map)
kfree(new_map);
@@ -2363,6 +2436,13 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
kfree(new_dev_maps);
return -ENOMEM;
}
+
+int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
+ u16 index)
+{
+ return __netif_set_xps_queue(dev, cpumask_bits(mask), index,
+ XPS_MAP_CPUS);
+}
EXPORT_SYMBOL(netif_set_xps_queue);
#endif
@@ -3402,7 +3482,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
int queue_index = -1;
rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_maps);
+ dev_maps = rcu_dereference(dev->xps_cpus_map);
if (dev_maps) {
unsigned int tci = skb->sender_cpu - 1;
@@ -3411,7 +3491,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
tci += netdev_get_prio_tc_map(dev, skb->priority);
}
- map = rcu_dereference(dev_maps->cpu_map[tci]);
+ map = rcu_dereference(dev_maps->attr_map[tci]);
if (map) {
if (map->len == 1)
queue_index = map->queues[0];
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bb7e80f..b39987c 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1227,13 +1227,13 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
return -ENOMEM;
rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_maps);
+ dev_maps = rcu_dereference(dev->xps_cpus_map);
if (dev_maps) {
for_each_possible_cpu(cpu) {
int i, tci = cpu * num_tc + tc;
struct xps_map *map;
- map = rcu_dereference(dev_maps->cpu_map[tci]);
+ map = rcu_dereference(dev_maps->attr_map[tci]);
if (!map)
continue;
^ permalink raw reply related
* [net-next PATCH v3 0/5] Symmetric queue selection using XPS for Rx queues
From: Amritha Nambiar @ 2018-06-05 8:37 UTC (permalink / raw)
To: netdev, davem
Cc: alexander.h.duyck, willemdebruijn.kernel, amritha.nambiar,
sridhar.samudrala, edumazet, hannes, tom
This patch series implements support for Tx queue selection based on
Rx queue(s) map. This is done by configuring Rx queue(s) map per Tx-queue
using sysfs attribute. If the user configuration for Rx queues does
not apply, then the Tx queue selection falls back to XPS using CPUs and
finally to hashing.
XPS is refactored to support Tx queue selection based on either the
CPUs map or the Rx-queues map. The config option CONFIG_XPS needs to be
enabled. By default no receive queues are configured for the Tx queue.
- /sys/class/net/<dev>/queues/tx-*/xps_rxqs
A set of receive queues can be mapped to a set of transmit queues (many:many),
although the common use case is a 1:1 mapping. This will enable sending
packets on the same Tx-Rx queue pair as this is useful for busy polling
multi-threaded workloads where it is not possible to pin the threads to
a CPU. This is a rework of Sridhar's patch for symmetric queueing via
socket option:
https://www.spinics.net/lists/netdev/msg453106.html
Testing Hints:
Kernel: Linux 4.17.0-rc7+
Interface:
driver: ixgbe
version: 5.1.0-k
firmware-version: 0x00015e0b
Configuration:
ethtool -L $iface combined 16
ethtool -C $iface rx-usecs 1000
sysctl net.core.busy_poll=1000
ATR disabled:
ethtool -K $iface ntuple on
Workload:
Modified memcached that changes the thread selection policy to be based
on the incoming rx-queue of a connection using SO_INCOMING_NAPI_ID socket
option. The default is round-robin.
Default: No rxqs_map configured
Symmetric queues: Enable rxqs_map for all queues 1:1 mapped to Tx queue
System:
Architecture: x86_64
CPU(s): 72
Model name: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz
16 threads 400K requests/sec
=============================
-------------------------------------------------------------------------------
Default Symmetric queues
-------------------------------------------------------------------------------
RTT min/avg/max 4/51/2215 2/30/5163
(usec)
intr/sec 26655 18606
contextswitch/sec 5145 4044
insn per cycle 0.43 0.72
cache-misses 6.919 4.310
(% of all cache refs)
L1-dcache-load- 4.49 3.29
-misses
(% of all L1-dcache hits)
LLC-load-misses 13.26 8.96
(% of all LL-cache hits)
-------------------------------------------------------------------------------
32 threads 400K requests/sec
=============================
-------------------------------------------------------------------------------
Default Symmetric queues
-------------------------------------------------------------------------------
RTT min/avg/max 10/112/5562 9/46/4637
(usec)
intr/sec 30456 27666
contextswitch/sec 7552 5133
insn per cycle 0.41 0.49
cache-misses 9.357 2.769
(% of all cache refs)
L1-dcache-load- 4.09 3.98
-misses
(% of all L1-dcache hits)
LLC-load-misses 12.96 3.96
(% of all LL-cache hits)
-------------------------------------------------------------------------------
16 threads 800K requests/sec
=============================
-------------------------------------------------------------------------------
Default Symmetric queues
-------------------------------------------------------------------------------
RTT min/avg/max 5/151/4989 9/69/2611
(usec)
intr/sec 35686 22907
contextswitch/sec 25522 12281
insn per cycle 0.67 0.74
cache-misses 8.652 6.38
(% of all cache refs)
L1-dcache-load- 3.19 2.86
-misses
(% of all L1-dcache hits)
LLC-load-misses 16.53 11.99
(% of all LL-cache hits)
-------------------------------------------------------------------------------
32 threads 800K requests/sec
=============================
-------------------------------------------------------------------------------
Default Symmetric queues
-------------------------------------------------------------------------------
RTT min/avg/max 6/163/6152 8/88/4209
(usec)
intr/sec 47079 26548
contextswitch/sec 42190 39168
insn per cycle 0.45 0.54
cache-misses 8.798 4.668
(% of all cache refs)
L1-dcache-load- 6.55 6.29
-misses
(% of all L1-dcache hits)
LLC-load-misses 13.91 10.44
(% of all LL-cache hits)
-------------------------------------------------------------------------------
v3:
- Removed xps_maps array and used separate pointers for rxqs_map and cpus_map
- Used static_key for XPS maps
- Removed skc_rx_ifindex from sock_common
- Record rx_queue_mapping as part of sk_mark_napi_id, sk_mark_rx_queue is
retained to be used on request sock which has only struct sock_common and not
a full sock.
- Added documentation in ABI/testing/sysfs-class-net-queues
---
Amritha Nambiar (5):
net: Refactor XPS for CPUs and Rx queues
net: Use static_key for XPS maps
net: Enable Tx queue selection based on Rx queues
net-sysfs: Add interface for Rx queue(s) map per Tx queue
Documentation: Add explanation for XPS using Rx-queue(s) map
Documentation/ABI/testing/sysfs-class-net-queues | 11 +
Documentation/networking/scaling.txt | 58 ++++
include/linux/cpumask.h | 11 +
include/linux/netdevice.h | 73 +++++-
include/net/busy_poll.h | 3
include/net/sock.h | 14 +
net/core/dev.c | 292 +++++++++++++++-------
net/core/net-sysfs.c | 85 ++++++
net/core/sock.c | 4
net/ipv4/tcp_input.c | 3
10 files changed, 445 insertions(+), 109 deletions(-)
^ permalink raw reply
* Re: [PATCH V4] mlx4_core: allocate ICM memory in page size chunks
From: Michal Hocko @ 2018-06-05 8:32 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, qing.huang, tariqt, haakon.bugge, yanjun.zhu,
netdev, linux-rdma, linux-kernel, gi-oh.kim
In-Reply-To: <1908601f-2eda-d739-9c4d-430a002b1a05@gmail.com>
On Mon 04-06-18 06:22:26, Eric Dumazet wrote:
>
>
> On 06/04/2018 06:11 AM, Michal Hocko wrote:
> > On Thu 31-05-18 11:10:22, Michal Hocko wrote:
>
> > Just in case you are interested
> > ---
> > From 5010543ed6f73e4c00367801486dca8d5c63b2ce Mon Sep 17 00:00:00 2001
> > From: Michal Hocko <mhocko@suse.com>
> > Date: Mon, 4 Jun 2018 15:07:37 +0200
> > Subject: [PATCH] net: cleanup gfp mask in alloc_skb_with_frags
> >
> > alloc_skb_with_frags uses __GFP_NORETRY for non-sleeping allocations
> > which is just a noop and a little bit confusing.
> >
> > __GFP_NORETRY was added by ed98df3361f0 ("net: use __GFP_NORETRY for
> > high order allocations") to prevent from the OOM killer. Yet this was
> > not enough because fb05e7a89f50 ("net: don't wait for order-3 page
> > allocation") didn't want an excessive reclaim for non-costly orders
> > so it made it completely NOWAIT while it preserved __GFP_NORETRY in
> > place which is now redundant.
> >
> > Drop the pointless __GFP_NORETRY because this function is used as
> > copy&paste source for other places.
> >
> > Signed-off-by: Michal Hocko <mhocko@suse.com>
> > ---
>
> Reviewed-by: Eric Dumazet <edumazet@google.com>
Thanks! What is the proper process now? Should I resend or somebody can
pick it up from this thread?
--
Michal Hocko
SUSE Labs
^ permalink raw reply
* Re: WARNING in bpf_int_jit_compile
From: Dmitry Vyukov @ 2018-06-05 8:23 UTC (permalink / raw)
To: Daniel Borkmann
Cc: syzbot, Alexei Starovoitov, David Miller, H. Peter Anvin,
Alexey Kuznetsov, LKML, Ingo Molnar, netdev, syzkaller-bugs,
Thomas Gleixner, the arch/x86 maintainers, Hideaki YOSHIFUJI
In-Reply-To: <cc2c87d5-0543-c340-9700-23f8676315f0@iogearbox.net>
On Mon, May 28, 2018 at 1:17 AM, Daniel Borkmann <daniel@iogearbox.net> wrote:
> On 05/26/2018 11:29 AM, syzbot wrote:
>> syzbot has found a reproducer for the following crash on:
>>
>> HEAD commit: 62d18ecfa641 Merge tag 'arm64-fixes' of git://git.kernel.o..
>> git tree: upstream
>> console output: https://syzkaller.appspot.com/x/log.txt?x=14c6bf57800000
>> kernel config: https://syzkaller.appspot.com/x/.config?x=982e2df1b9e60b02
>> dashboard link: https://syzkaller.appspot.com/bug?extid=9e762b52dd17e616a7a5
>> compiler: gcc (GCC) 8.0.1 20180413 (experimental)
>> syzkaller repro:https://syzkaller.appspot.com/x/repro.syz?x=130e42b7800000
>>
>> IMPORTANT: if you fix the bug, please add the following tag to the commit:
>> Reported-by: syzbot+9e762b52dd17e616a7a5@syzkaller.appspotmail.com
>>
>> RAX: ffffffffffffffda RBX: 0000000002542914 RCX: 0000000000455a09
>> RDX: 0000000000000048 RSI: 0000000020000240 RDI: 0000000000000005
>> RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003
>> R13: 0000000000000046 R14: 00000000006f4730 R15: 0000000000000023
>> WARNING: CPU: 0 PID: 4752 at include/linux/filter.h:667 bpf_jit_binary_lock_ro include/linux/filter.h:667 [inline]
>> WARNING: CPU: 0 PID: 4752 at include/linux/filter.h:667 bpf_int_jit_compile+0xbf7/0xef7 arch/x86/net/bpf_jit_comp.c:1271
>> Kernel panic - not syncing: panic_on_warn set ...
>>
>> CPU: 0 PID: 4752 Comm: syz-executor0 Not tainted 4.17.0-rc6+ #67
>> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
>> Call Trace:
>> __dump_stack lib/dump_stack.c:77 [inline]
>> dump_stack+0x1b9/0x294 lib/dump_stack.c:113
>> panic+0x22f/0x4de kernel/panic.c:184
>> __warn.cold.8+0x163/0x1b3 kernel/panic.c:536
>> report_bug+0x252/0x2d0 lib/bug.c:186
>> fixup_bug arch/x86/kernel/traps.c:178 [inline]
>> do_error_trap+0x1de/0x490 arch/x86/kernel/traps.c:296
>> do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315
>> invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:992
>> RIP: 0010:bpf_jit_binary_lock_ro include/linux/filter.h:667 [inline]
>
> Been looking into this last Friday already. What seems to happen here is that
> there's fault injection from inside set_memory_ro(), meaning it will eventually
> return an error there, and we throw a WARN_ON_ONCE() to bark that making the
> memory read-only didn't work out. I'd be in preference to notify the user on
> such issue rather than keeping completely silent about it so that there's
> awareness that read-only protections are not in place / guaranteed.
Hi Daniel,
There is no problem with notifying user, but there is a problem with
making this notification indistinguishable from kernel bugs. Also the
stack trace is pointless for end user, and they may not even
understand what happened and what they were notified about (not
everybody is a kernel developer!). A pr_err/pr_err_once with a
readable error message would be a better fit here.
>> RIP: 0010:bpf_int_jit_compile+0xbf7/0xef7 arch/x86/net/bpf_jit_comp.c:1271
>> RSP: 0018:ffff8801d85ff920 EFLAGS: 00010293
>> RAX: ffff8801d78c40c0 RBX: 0000000000000046 RCX: ffffffff81445d89
>> RDX: 0000000000000000 RSI: ffffffff81445d97 RDI: 0000000000000005
>> RBP: ffff8801d85ffa40 R08: ffff8801d78c40c0 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000000 R12: ffffc9000194e002
>> R13: ffff8801d85ffa18 R14: 00000000fffffff4 R15: 0000000000000003
>> bpf_prog_select_runtime+0x131/0x640 kernel/bpf/core.c:1541
>> bpf_prog_load+0x16c2/0x2070 kernel/bpf/syscall.c:1333
>> __do_sys_bpf kernel/bpf/syscall.c:2073 [inline]
>> __se_sys_bpf kernel/bpf/syscall.c:2035 [inline]
>> __x64_sys_bpf+0x389/0x4c0 kernel/bpf/syscall.c:2035
>> do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
>> entry_SYSCALL_64_after_hwframe+0x49/0xbe
>> RIP: 0033:0x455a09
>> RSP: 002b:00007ffec3da2868 EFLAGS: 00000246 ORIG_RAX: 0000000000000141
>> RAX: ffffffffffffffda RBX: 0000000002542914 RCX: 0000000000455a09
>> RDX: 0000000000000048 RSI: 0000000020000240 RDI: 0000000000000005
>> RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003
>> R13: 0000000000000046 R14: 00000000006f4730 R15: 0000000000000023
>> Dumping ftrace buffer:
>> (ftrace buffer empty)
>> Kernel Offset: disabled
>> Rebooting in 86400 seconds..
>>
>
> --
> You received this message because you are subscribed to the Google Groups "syzkaller-bugs" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to syzkaller-bugs+unsubscribe@googlegroups.com.
> To view this discussion on the web visit https://groups.google.com/d/msgid/syzkaller-bugs/cc2c87d5-0543-c340-9700-23f8676315f0%40iogearbox.net.
> For more options, visit https://groups.google.com/d/optout.
^ permalink raw reply
* Re: [PATCH net-next 3/3] mlxsw: Add extack messages for port_{un,}split failures?
From: Jiri Pirko @ 2018-06-05 8:18 UTC (permalink / raw)
To: Ido Schimmel; +Cc: dsahern, netdev, idosch, jiri, jakub.kicinski, David Ahern
In-Reply-To: <20180605080528.GA2034@splinter.mtl.com>
Tue, Jun 05, 2018 at 10:05:28AM CEST, idosch@idosch.org wrote:
>On Tue, Jun 05, 2018 at 09:52:30AM +0200, Jiri Pirko wrote:
>> Tue, Jun 05, 2018 at 12:15:03AM CEST, dsahern@kernel.org wrote:
>> > if (!mlxsw_sp_port->split) {
>> > netdev_err(mlxsw_sp_port->dev, "Port wasn't split\n");
>> >+ NL_SET_ERR_MSG_MOD(extack, "Port was not split");
>>
>> I wonder if we need the dmesg for these as well. Plus it is not the same
>> (wasn't/was not) which is maybe confusing. Any objection against the
>> original dmesg messages removal?
>
>We had this discussion about three months ago and decided to keep the
>existing messages:
>https://marc.info/?l=linux-netdev&m=151982813309466&w=2
I forgot. Thanks for reminding me. So could we at least have the
messages 100% same? Thanks.
^ permalink raw reply
* Re: [PATCH net-next 3/3] mlxsw: Add extack messages for port_{un,}split failures?
From: Ido Schimmel @ 2018-06-05 8:05 UTC (permalink / raw)
To: Jiri Pirko; +Cc: dsahern, netdev, idosch, jiri, jakub.kicinski, David Ahern
In-Reply-To: <20180605075230.GC2164@nanopsycho>
On Tue, Jun 05, 2018 at 09:52:30AM +0200, Jiri Pirko wrote:
> Tue, Jun 05, 2018 at 12:15:03AM CEST, dsahern@kernel.org wrote:
> > if (!mlxsw_sp_port->split) {
> > netdev_err(mlxsw_sp_port->dev, "Port wasn't split\n");
> >+ NL_SET_ERR_MSG_MOD(extack, "Port was not split");
>
> I wonder if we need the dmesg for these as well. Plus it is not the same
> (wasn't/was not) which is maybe confusing. Any objection against the
> original dmesg messages removal?
We had this discussion about three months ago and decided to keep the
existing messages:
https://marc.info/?l=linux-netdev&m=151982813309466&w=2
^ permalink raw reply
* [PATCH net] net: sched: cls: Fix offloading when ingress dev is vxlan
From: Paul Blakey @ 2018-06-05 8:04 UTC (permalink / raw)
To: Jiri Pirko, Cong Wang, Jamal Hadi Salim, David Miller, netdev
Cc: Yevgeny Kliteynik, Roi Dayan, Shahar Klein, Mark Bloch,
Or Gerlitz, Paul Blakey
When using a vxlan device as the ingress dev, we count it as a
"no offload dev", so when such a rule comes and err stop is true,
we fail early and don't try the egdev route which can offload it
through the egress device.
Fix that by not calling the block offload if one of the devices
attached to it is not offload capable, but make sure egress on such case
is capable instead.
Fixes: caa7260156eb ("net: sched: keep track of offloaded filters [..]")
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Paul Blakey <paulb@mellanox.com>
---
net/sched/cls_api.c | 26 ++++++++++++++++----------
1 file changed, 16 insertions(+), 10 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a57e112..2cd579f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -734,10 +734,6 @@ static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
int ok_count = 0;
int err;
- /* Make sure all netdevs sharing this block are offload-capable. */
- if (block->nooffloaddevcnt && err_stop)
- return -EOPNOTSUPP;
-
list_for_each_entry(block_cb, &block->cb_list, list) {
err = block_cb->cb(type, type_data, block_cb->cb_priv);
if (err) {
@@ -1580,21 +1576,31 @@ static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
enum tc_setup_type type, void *type_data, bool err_stop)
{
- int ok_count;
+ int ok_count = 0;
int ret;
- ret = tcf_block_cb_call(block, type, type_data, err_stop);
- if (ret < 0)
- return ret;
- ok_count = ret;
+ if (!block->nooffloaddevcnt) {
+ ret = tcf_block_cb_call(block, type, type_data, err_stop);
+ if (ret < 0)
+ return ret;
+ ok_count = ret;
+ }
if (!exts || ok_count)
- return ok_count;
+ goto skip_egress;
+
ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
if (ret < 0)
return ret;
ok_count += ret;
+skip_egress:
+ /* if one of the netdevs sharing this block are not offload-capable
+ * make sure we succeeded in egress instead.
+ */
+ if (block->nooffloaddevcnt && !ok_count && err_stop)
+ return -EOPNOTSUPP;
+
return ok_count;
}
EXPORT_SYMBOL(tc_setup_cb_call);
--
2.7.4
^ permalink raw reply related
* Re: [PATCH net-next 3/3] mlxsw: Add extack messages for port_{un,}split failures^[
From: Jiri Pirko @ 2018-06-05 7:52 UTC (permalink / raw)
To: dsahern; +Cc: netdev, idosch, jiri, jakub.kicinski, David Ahern
In-Reply-To: <20180604221503.20329-4-dsahern@kernel.org>
Tue, Jun 05, 2018 at 12:15:03AM CEST, dsahern@kernel.org wrote:
>From: David Ahern <dsahern@gmail.com>
>
>Return messages in extack for port split/unsplit errors. e.g.,
> $ devlink port split swp1s1 count 4
> Error: mlxsw_spectrum: Port cannot be split further.
> devlink answers: Invalid argument
>
> $ devlink port unsplit swp4
> Error: mlxsw_spectrum: Port was not split.
> devlink answers: Invalid argument
>
>Signed-off-by: David Ahern <dsahern@gmail.com>
>---
> drivers/net/ethernet/mellanox/mlxsw/core.c | 14 ++++++++++----
> drivers/net/ethernet/mellanox/mlxsw/core.h | 5 +++--
> drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 13 +++++++++++--
> 3 files changed, 24 insertions(+), 8 deletions(-)
>
>diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
>index 7ed38d80bc08..f9c724752a32 100644
>--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
>+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
>@@ -775,11 +775,14 @@ static int mlxsw_devlink_port_split(struct devlink *devlink,
> {
> struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
>
>- if (port_index >= mlxsw_core->max_ports)
>+ if (port_index >= mlxsw_core->max_ports) {
>+ NL_SET_ERR_MSG_MOD(extack, "Port index exceeds maximum number of ports");
> return -EINVAL;
>+ }
> if (!mlxsw_core->driver->port_split)
> return -EOPNOTSUPP;
>- return mlxsw_core->driver->port_split(mlxsw_core, port_index, count);
>+ return mlxsw_core->driver->port_split(mlxsw_core, port_index, count,
>+ extack);
> }
>
> static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
>@@ -788,11 +791,14 @@ static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
> {
> struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
>
>- if (port_index >= mlxsw_core->max_ports)
>+ if (port_index >= mlxsw_core->max_ports) {
>+ NL_SET_ERR_MSG_MOD(extack, "Port index exceeds maximum number of ports");
> return -EINVAL;
>+ }
> if (!mlxsw_core->driver->port_unsplit)
> return -EOPNOTSUPP;
>- return mlxsw_core->driver->port_unsplit(mlxsw_core, port_index);
>+ return mlxsw_core->driver->port_unsplit(mlxsw_core, port_index,
>+ extack);
> }
>
> static int
>diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
>index 4a8d4c7f89d9..552cfa29c2f7 100644
>--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
>+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
>@@ -274,8 +274,9 @@ struct mlxsw_driver {
> int (*port_type_set)(struct mlxsw_core *mlxsw_core, u8 local_port,
> enum devlink_port_type new_type);
> int (*port_split)(struct mlxsw_core *mlxsw_core, u8 local_port,
>- unsigned int count);
>- int (*port_unsplit)(struct mlxsw_core *mlxsw_core, u8 local_port);
>+ unsigned int count, struct netlink_ext_ack *extack);
>+ int (*port_unsplit)(struct mlxsw_core *mlxsw_core, u8 local_port,
>+ struct netlink_ext_ack *extack);
> int (*sb_pool_get)(struct mlxsw_core *mlxsw_core,
> unsigned int sb_index, u16 pool_index,
> struct devlink_sb_pool_info *pool_info);
>diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
>index fc39f22e5c70..1b6d930e452d 100644
>--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
>+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
>@@ -3092,7 +3092,8 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp,
> }
>
> static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
>- unsigned int count)
>+ unsigned int count,
>+ struct netlink_ext_ack *extack)
> {
> struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
> struct mlxsw_sp_port *mlxsw_sp_port;
>@@ -3104,6 +3105,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
> if (!mlxsw_sp_port) {
> dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
> local_port);
>+ NL_SET_ERR_MSG_MOD(extack, "Port number does not exist");
> return -EINVAL;
> }
>
>@@ -3112,11 +3114,13 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
>
> if (count != 2 && count != 4) {
> netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n");
>+ NL_SET_ERR_MSG_MOD(extack, "Port can only be split into 2 or 4 ports");
> return -EINVAL;
> }
>
> if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) {
> netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n");
>+ NL_SET_ERR_MSG_MOD(extack, "Port cannot be split further");
> return -EINVAL;
> }
>
>@@ -3125,6 +3129,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
> base_port = local_port;
> if (mlxsw_sp->ports[base_port + 1]) {
> netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n");
>+ NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration");
> return -EINVAL;
> }
> } else {
>@@ -3132,6 +3137,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
> if (mlxsw_sp->ports[base_port + 1] ||
> mlxsw_sp->ports[base_port + 3]) {
> netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n");
>+ NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration");
> return -EINVAL;
> }
> }
>@@ -3153,7 +3159,8 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
> return err;
> }
>
>-static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
>+static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
>+ struct netlink_ext_ack *extack)
> {
> struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
> struct mlxsw_sp_port *mlxsw_sp_port;
>@@ -3165,11 +3172,13 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
> if (!mlxsw_sp_port) {
> dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
> local_port);
>+ NL_SET_ERR_MSG_MOD(extack, "Port number does not exist");
> return -EINVAL;
> }
>
> if (!mlxsw_sp_port->split) {
> netdev_err(mlxsw_sp_port->dev, "Port wasn't split\n");
>+ NL_SET_ERR_MSG_MOD(extack, "Port was not split");
I wonder if we need the dmesg for these as well. Plus it is not the same
(wasn't/was not) which is maybe confusing. Any objection against the
original dmesg messages removal?
> return -EINVAL;
> }
>
>--
>2.11.0
>
^ permalink raw reply
* Re: [PATCH net-next 1/3] devlink: Add extack to reload and port_{un,}split operations
From: Jiri Pirko @ 2018-06-05 7:50 UTC (permalink / raw)
To: dsahern; +Cc: netdev, idosch, jiri, jakub.kicinski, David Ahern
In-Reply-To: <20180604221503.20329-2-dsahern@kernel.org>
Tue, Jun 05, 2018 at 12:15:01AM CEST, dsahern@kernel.org wrote:
>From: David Ahern <dsahern@gmail.com>
>
>Add extack argument to reload, port_split and port_unsplit operations.
>
>Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
^ permalink raw reply
* Re: [Patch net-next] netdev-FAQ: clarify DaveM's position for stable backports
From: Greg KH @ 2018-06-05 7:46 UTC (permalink / raw)
To: Cong Wang; +Cc: netdev, stable
In-Reply-To: <20180604180719.6053-1-xiyou.wangcong@gmail.com>
On Mon, Jun 04, 2018 at 11:07:19AM -0700, Cong Wang wrote:
> Per discussion with David at netconf 2018, let's clarify
> DaveM's position of handling stable backports in netdev-FAQ.
>
> This is important for people relying on upstream -stable
> releases.
>
> Cc: stable@vger.kernel.org
> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
> ---
> Documentation/networking/netdev-FAQ.txt | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
> index 2a3278d5cf35..6dde6686c870 100644
> --- a/Documentation/networking/netdev-FAQ.txt
> +++ b/Documentation/networking/netdev-FAQ.txt
> @@ -179,6 +179,15 @@ A: No. See above answer. In short, if you think it really belongs in
> dash marker line as described in Documentation/process/submitting-patches.rst to
> temporarily embed that information into the patch that you send.
>
> +Q: Are all networking bug fixes backported to all stable releases?
> +
> +A: Due to capacity, Dave could only take care of the backports for the last
> + 3 stable releases. For earlier stable releases, each stable branch maintainer
s/3/2/
There's no need for Dave to do more work than he currently does :)
thanks,
greg k-h
^ permalink raw reply
* Re: [PATCH net-next V2 1/2] cls_flower: Fix missing free of rhashtable
From: Paul Blakey @ 2018-06-05 7:44 UTC (permalink / raw)
To: David Miller
Cc: paulb, jiri, xiyou.wangcong, jhs, netdev, kliteyn, roid, shahark,
markb, ogerlitz
In-Reply-To: <20180604.170409.1557542563226321470.davem@davemloft.net>
On 05/06/2018 00:04, David Miller wrote:
> From: Paul Blakey <paulb@mellanox.com>
> Date: Sun, 3 Jun 2018 10:06:13 +0300
>
>> When destroying the instance, destroy the head rhashtable.
>>
>> Fixes: 05cd271fd61a ("cls_flower: Support multiple masks per priority")
>> Reported-by: Vlad Buslov <vladbu@mellanox.com>
>> Reviewed-by: Roi Dayan <roid@mellanox.com>
>> Reviewed-by: Jiri Pirko <jiri@mellanox.com>
>> Signed-off-by: Paul Blakey <paulb@mellanox.com>
>
> Applied.
>
thanks.
^ permalink raw reply
* [RFC v6 5/5] virtio_ring: enable packed ring
From: Tiwei Bie @ 2018-06-05 7:40 UTC (permalink / raw)
To: mst, jasowang, virtualization, linux-kernel, netdev
Cc: wexu, jfreimann, tiwei.bie
In-Reply-To: <20180605074046.20709-1-tiwei.bie@intel.com>
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
---
drivers/s390/virtio/virtio_ccw.c | 8 ++++++++
drivers/virtio/virtio_ring.c | 2 ++
2 files changed, 10 insertions(+)
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 8f5c1d7f751a..ff5b85736d8d 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -765,6 +765,11 @@ static u64 virtio_ccw_get_features(struct virtio_device *vdev)
return rc;
}
+static void ccw_transport_features(struct virtio_device *vdev)
+{
+ __virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
+}
+
static int virtio_ccw_finalize_features(struct virtio_device *vdev)
{
struct virtio_ccw_device *vcdev = to_vc_device(vdev);
@@ -791,6 +796,9 @@ static int virtio_ccw_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
+ /* Give virtio_ccw a chance to accept features. */
+ ccw_transport_features(vdev);
+
features->index = 0;
features->features = cpu_to_le32((u32)vdev->features);
/* Write the first half of the feature bits to the host. */
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index aefd7ac40928..fe849fd8733b 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1965,6 +1965,8 @@ void vring_transport_features(struct virtio_device *vdev)
break;
case VIRTIO_F_IOMMU_PLATFORM:
break;
+ case VIRTIO_F_RING_PACKED:
+ break;
default:
/* We don't understand this bit. */
__virtio_clear_bit(vdev, i);
--
2.17.0
^ permalink raw reply related
* [RFC v6 4/5] virtio_ring: add event idx support in packed ring
From: Tiwei Bie @ 2018-06-05 7:40 UTC (permalink / raw)
To: mst, jasowang, virtualization, linux-kernel, netdev
Cc: wexu, jfreimann, tiwei.bie
In-Reply-To: <20180605074046.20709-1-tiwei.bie@intel.com>
This commit introduces the EVENT_IDX support in packed ring.
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
---
drivers/virtio/virtio_ring.c | 74 ++++++++++++++++++++++++++++++++----
1 file changed, 67 insertions(+), 7 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 983ce5ffda1b..aefd7ac40928 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1048,7 +1048,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- u16 flags;
+ u16 new, old, off_wrap, flags, wrap_counter, event_idx;
bool needs_kick;
u32 snapshot;
@@ -1057,9 +1057,19 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
* suppressions. */
virtio_mb(vq->weak_barriers);
+ old = vq->next_avail_idx - vq->num_added;
+ new = vq->next_avail_idx;
+ vq->num_added = 0;
+
snapshot = *(u32 *)vq->vring_packed.device;
+ off_wrap = virtio16_to_cpu(_vq->vdev, (__virtio16)(snapshot & 0xffff));
flags = virtio16_to_cpu(_vq->vdev, (__virtio16)(snapshot >> 16)) & 0x3;
+ wrap_counter = off_wrap >> 15;
+ event_idx = off_wrap & ~(1<<15);
+ if (wrap_counter != vq->avail_wrap_counter)
+ event_idx -= vq->vring_packed.num;
+
#ifdef DEBUG
if (vq->last_add_time_valid) {
WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
@@ -1068,7 +1078,10 @@ static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
vq->last_add_time_valid = false;
#endif
- needs_kick = (flags != VRING_EVENT_F_DISABLE);
+ if (flags == VRING_EVENT_F_DESC)
+ needs_kick = vring_need_event(event_idx, new, old);
+ else
+ needs_kick = (flags != VRING_EVENT_F_DISABLE);
END_USE(vq);
return needs_kick;
}
@@ -1177,6 +1190,15 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
ret = vq->desc_state_packed[id].data;
detach_buf_packed(vq, id, ctx);
+ /* If we expect an interrupt for the next entry, tell host
+ * by writing event index and flush out the write before
+ * the read in the next get_buf call. */
+ if (vq->event_flags_shadow == VRING_EVENT_F_DESC)
+ virtio_store_mb(vq->weak_barriers,
+ &vq->vring_packed.driver->off_wrap,
+ cpu_to_virtio16(_vq->vdev, vq->last_used_idx |
+ ((u16)vq->used_wrap_counter << 15)));
+
#ifdef DEBUG
vq->last_add_time_valid = false;
#endif
@@ -1204,9 +1226,20 @@ static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
/* We optimistically turn back on interrupts, then check if there was
* more to do. */
+ /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+ * either clear the flags bit or point the event index at the next
+ * entry. Always update the event index to keep code simple. */
+
+ vq->vring_packed.driver->off_wrap = cpu_to_virtio16(_vq->vdev,
+ vq->last_used_idx |
+ ((u16)vq->used_wrap_counter << 15));
if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) {
- vq->event_flags_shadow = VRING_EVENT_F_ENABLE;
+ /* We need to update event offset and event wrap
+ * counter first before updating event flags. */
+ virtio_wmb(vq->weak_barriers);
+ vq->event_flags_shadow = vq->event ? VRING_EVENT_F_DESC :
+ VRING_EVENT_F_ENABLE;
vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
vq->event_flags_shadow);
}
@@ -1232,21 +1265,48 @@ static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx)
static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 bufs, used_idx, wrap_counter;
START_USE(vq);
/* We optimistically turn back on interrupts, then check if there was
* more to do. */
+ /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+ * either clear the flags bit or point the event index at the next
+ * entry. Always update the event index to keep code simple. */
+
+ /* TODO: tune this threshold */
+ if (vq->next_avail_idx < vq->last_used_idx)
+ bufs = (vq->vring_packed.num + vq->next_avail_idx -
+ vq->last_used_idx) * 3 / 4;
+ else
+ bufs = (vq->next_avail_idx - vq->last_used_idx) * 3 / 4;
+
+ wrap_counter = vq->used_wrap_counter;
+
+ used_idx = vq->last_used_idx + bufs;
+ if (used_idx >= vq->vring_packed.num) {
+ used_idx -= vq->vring_packed.num;
+ wrap_counter ^= 1;
+ }
+
+ vq->vring_packed.driver->off_wrap = cpu_to_virtio16(_vq->vdev,
+ used_idx | (wrap_counter << 15));
if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) {
- vq->event_flags_shadow = VRING_EVENT_F_ENABLE;
+ /* We need to update event offset and event wrap
+ * counter first before updating event flags. */
+ virtio_wmb(vq->weak_barriers);
+ vq->event_flags_shadow = vq->event ? VRING_EVENT_F_DESC :
+ VRING_EVENT_F_ENABLE;
vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
vq->event_flags_shadow);
- /* We need to enable interrupts first before re-checking
- * for more used buffers. */
- virtio_mb(vq->weak_barriers);
}
+ /* We need to update event suppression structure first
+ * before re-checking for more used buffers. */
+ virtio_mb(vq->weak_barriers);
+
if (more_used_packed(vq)) {
END_USE(vq);
return false;
--
2.17.0
^ permalink raw reply related
* [RFC v6 3/5] virtio_ring: add packed ring support
From: Tiwei Bie @ 2018-06-05 7:40 UTC (permalink / raw)
To: mst, jasowang, virtualization, linux-kernel, netdev
Cc: wexu, jfreimann, tiwei.bie
In-Reply-To: <20180605074046.20709-1-tiwei.bie@intel.com>
This commit introduces the support (without EVENT_IDX) for
packed ring.
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
---
drivers/virtio/virtio_ring.c | 486 ++++++++++++++++++++++++++++++++++-
1 file changed, 479 insertions(+), 7 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 416c33143125..983ce5ffda1b 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -62,6 +62,12 @@ struct vring_desc_state {
};
struct vring_desc_state_packed {
+ void *data; /* Data for callback. */
+ struct vring_packed_desc *indir_desc; /* Indirect descriptor, if any. */
+ int num; /* Descriptor list length. */
+ dma_addr_t addr; /* Buffer DMA addr. */
+ u32 len; /* Buffer length. */
+ u16 flags; /* Descriptor flags. */
int next; /* The next desc state. */
};
@@ -661,7 +667,6 @@ static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- virtio_mb(vq->weak_barriers);
return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
}
@@ -758,6 +763,72 @@ static inline unsigned vring_size_packed(unsigned int num, unsigned long align)
& ~(align - 1)) + sizeof(struct vring_packed_desc_event) * 2;
}
+static void vring_unmap_state_packed(const struct vring_virtqueue *vq,
+ struct vring_desc_state_packed *state)
+{
+ u16 flags;
+
+ if (!vring_use_dma_api(vq->vq.vdev))
+ return;
+
+ flags = state->flags;
+
+ if (flags & VRING_DESC_F_INDIRECT) {
+ dma_unmap_single(vring_dma_dev(vq),
+ state->addr, state->len,
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ } else {
+ dma_unmap_page(vring_dma_dev(vq),
+ state->addr, state->len,
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ }
+}
+
+static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
+ struct vring_packed_desc *desc)
+{
+ u16 flags;
+
+ if (!vring_use_dma_api(vq->vq.vdev))
+ return;
+
+ flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
+
+ if (flags & VRING_DESC_F_INDIRECT) {
+ dma_unmap_single(vring_dma_dev(vq),
+ virtio64_to_cpu(vq->vq.vdev, desc->addr),
+ virtio32_to_cpu(vq->vq.vdev, desc->len),
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ } else {
+ dma_unmap_page(vring_dma_dev(vq),
+ virtio64_to_cpu(vq->vq.vdev, desc->addr),
+ virtio32_to_cpu(vq->vq.vdev, desc->len),
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ }
+}
+
+static struct vring_packed_desc *alloc_indirect_packed(struct virtqueue *_vq,
+ unsigned int total_sg,
+ gfp_t gfp)
+{
+ struct vring_packed_desc *desc;
+
+ /*
+ * We require lowmem mappings for the descriptors because
+ * otherwise virt_to_phys will give us bogus addresses in the
+ * virtqueue.
+ */
+ gfp &= ~__GFP_HIGHMEM;
+
+ desc = kmalloc(total_sg * sizeof(struct vring_packed_desc), gfp);
+
+ return desc;
+}
+
static inline int virtqueue_add_packed(struct virtqueue *_vq,
struct scatterlist *sgs[],
unsigned int total_sg,
@@ -767,47 +838,445 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
void *ctx,
gfp_t gfp)
{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ struct vring_packed_desc *desc;
+ struct scatterlist *sg;
+ unsigned int i, n, descs_used, uninitialized_var(prev), err_idx;
+ __virtio16 uninitialized_var(head_flags), flags;
+ u16 head, avail_wrap_counter, id, curr;
+ bool indirect;
+
+ START_USE(vq);
+
+ BUG_ON(data == NULL);
+ BUG_ON(ctx && vq->indirect);
+
+ if (unlikely(vq->broken)) {
+ END_USE(vq);
+ return -EIO;
+ }
+
+#ifdef DEBUG
+ {
+ ktime_t now = ktime_get();
+
+ /* No kick or get, with .1 second between? Warn. */
+ if (vq->last_add_time_valid)
+ WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
+ > 100);
+ vq->last_add_time = now;
+ vq->last_add_time_valid = true;
+ }
+#endif
+
+ BUG_ON(total_sg == 0);
+
+ head = vq->next_avail_idx;
+ avail_wrap_counter = vq->avail_wrap_counter;
+
+ if (virtqueue_use_indirect(_vq, total_sg))
+ desc = alloc_indirect_packed(_vq, total_sg, gfp);
+ else {
+ desc = NULL;
+ WARN_ON_ONCE(total_sg > vq->vring_packed.num && !vq->indirect);
+ }
+
+ if (desc) {
+ /* Use a single buffer which doesn't continue */
+ indirect = true;
+ /* Set up rest to use this indirect table. */
+ i = 0;
+ descs_used = 1;
+ } else {
+ indirect = false;
+ desc = vq->vring_packed.desc;
+ i = head;
+ descs_used = total_sg;
+ }
+
+ if (vq->vq.num_free < descs_used) {
+ pr_debug("Can't add buf len %i - avail = %i\n",
+ descs_used, vq->vq.num_free);
+ /* FIXME: for historical reasons, we force a notify here if
+ * there are outgoing parts to the buffer. Presumably the
+ * host should service the ring ASAP. */
+ if (out_sgs)
+ vq->notify(&vq->vq);
+ if (indirect)
+ kfree(desc);
+ END_USE(vq);
+ return -ENOSPC;
+ }
+
+ id = vq->free_head;
+ BUG_ON(id == vq->vring_packed.num);
+
+ curr = id;
+ for (n = 0; n < out_sgs + in_sgs; n++) {
+ for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+ dma_addr_t addr = vring_map_one_sg(vq, sg, n < out_sgs ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ if (vring_mapping_error(vq, addr))
+ goto unmap_release;
+
+ flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT |
+ (n < out_sgs ? 0 : VRING_DESC_F_WRITE) |
+ VRING_DESC_F_AVAIL(vq->avail_wrap_counter) |
+ VRING_DESC_F_USED(!vq->avail_wrap_counter));
+ if (!indirect && i == head)
+ head_flags = flags;
+ else
+ desc[i].flags = flags;
+
+ desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
+ desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
+ i++;
+ if (!indirect) {
+ if (vring_use_dma_api(_vq->vdev)) {
+ vq->desc_state_packed[curr].addr = addr;
+ vq->desc_state_packed[curr].len =
+ sg->length;
+ vq->desc_state_packed[curr].flags =
+ virtio16_to_cpu(_vq->vdev,
+ flags);
+ }
+ curr = vq->desc_state_packed[curr].next;
+
+ if (i >= vq->vring_packed.num) {
+ i = 0;
+ vq->avail_wrap_counter ^= 1;
+ }
+ }
+ }
+ }
+
+ prev = (i > 0 ? i : vq->vring_packed.num) - 1;
+ desc[prev].id = cpu_to_virtio16(_vq->vdev, id);
+
+ /* Last one doesn't continue. */
+ if (total_sg == 1)
+ head_flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
+ else
+ desc[prev].flags &= cpu_to_virtio16(_vq->vdev,
+ ~VRING_DESC_F_NEXT);
+
+ if (indirect) {
+ /* Now that the indirect table is filled in, map it. */
+ dma_addr_t addr = vring_map_single(
+ vq, desc, total_sg * sizeof(struct vring_packed_desc),
+ DMA_TO_DEVICE);
+ if (vring_mapping_error(vq, addr))
+ goto unmap_release;
+
+ head_flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT |
+ VRING_DESC_F_AVAIL(avail_wrap_counter) |
+ VRING_DESC_F_USED(!avail_wrap_counter));
+ vq->vring_packed.desc[head].addr = cpu_to_virtio64(_vq->vdev,
+ addr);
+ vq->vring_packed.desc[head].len = cpu_to_virtio32(_vq->vdev,
+ total_sg * sizeof(struct vring_packed_desc));
+ vq->vring_packed.desc[head].id = cpu_to_virtio16(_vq->vdev, id);
+
+ if (vring_use_dma_api(_vq->vdev)) {
+ vq->desc_state_packed[id].addr = addr;
+ vq->desc_state_packed[id].len = total_sg *
+ sizeof(struct vring_packed_desc);
+ vq->desc_state_packed[id].flags =
+ virtio16_to_cpu(_vq->vdev, head_flags);
+ }
+ }
+
+ /* We're using some buffers from the free list. */
+ vq->vq.num_free -= descs_used;
+
+ /* Update free pointer */
+ if (indirect) {
+ n = head + 1;
+ if (n >= vq->vring_packed.num) {
+ n = 0;
+ vq->avail_wrap_counter ^= 1;
+ }
+ vq->next_avail_idx = n;
+ vq->free_head = vq->desc_state_packed[id].next;
+ } else {
+ vq->next_avail_idx = i;
+ vq->free_head = curr;
+ }
+
+ /* Store token and indirect buffer state. */
+ vq->desc_state_packed[id].num = descs_used;
+ vq->desc_state_packed[id].data = data;
+ if (indirect)
+ vq->desc_state_packed[id].indir_desc = desc;
+ else
+ vq->desc_state_packed[id].indir_desc = ctx;
+
+ /* A driver MUST NOT make the first descriptor in the list
+ * available before all subsequent descriptors comprising
+ * the list are made available. */
+ virtio_wmb(vq->weak_barriers);
+ vq->vring_packed.desc[head].flags = head_flags;
+ vq->num_added += descs_used;
+
+ pr_debug("Added buffer head %i to %p\n", head, vq);
+ END_USE(vq);
+
+ return 0;
+
+unmap_release:
+ err_idx = i;
+ i = head;
+
+ for (n = 0; n < total_sg; n++) {
+ if (i == err_idx)
+ break;
+ vring_unmap_desc_packed(vq, &desc[i]);
+ i++;
+ if (!indirect && i >= vq->vring_packed.num)
+ i = 0;
+ }
+
+ vq->avail_wrap_counter = avail_wrap_counter;
+
+ if (indirect)
+ kfree(desc);
+
+ END_USE(vq);
return -EIO;
}
static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
{
- return false;
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 flags;
+ bool needs_kick;
+ u32 snapshot;
+
+ START_USE(vq);
+ /* We need to expose the new flags value before checking notification
+ * suppressions. */
+ virtio_mb(vq->weak_barriers);
+
+ snapshot = *(u32 *)vq->vring_packed.device;
+ flags = virtio16_to_cpu(_vq->vdev, (__virtio16)(snapshot >> 16)) & 0x3;
+
+#ifdef DEBUG
+ if (vq->last_add_time_valid) {
+ WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
+ vq->last_add_time)) > 100);
+ }
+ vq->last_add_time_valid = false;
+#endif
+
+ needs_kick = (flags != VRING_EVENT_F_DISABLE);
+ END_USE(vq);
+ return needs_kick;
+}
+
+static void detach_buf_packed(struct vring_virtqueue *vq,
+ unsigned int id, void **ctx)
+{
+ struct vring_desc_state_packed *state = NULL;
+ struct vring_packed_desc *desc;
+ unsigned int curr, i;
+
+ /* Clear data ptr. */
+ vq->desc_state_packed[id].data = NULL;
+
+ curr = id;
+ for (i = 0; i < vq->desc_state_packed[id].num; i++) {
+ state = &vq->desc_state_packed[curr];
+ vring_unmap_state_packed(vq, state);
+ curr = state->next;
+ }
+
+ BUG_ON(state == NULL);
+ vq->vq.num_free += vq->desc_state_packed[id].num;
+ state->next = vq->free_head;
+ vq->free_head = id;
+
+ if (vq->indirect) {
+ u32 len;
+
+ /* Free the indirect table, if any, now that it's unmapped. */
+ desc = vq->desc_state_packed[id].indir_desc;
+ if (!desc)
+ return;
+
+ if (vring_use_dma_api(vq->vq.vdev)) {
+ len = vq->desc_state_packed[id].len;
+ for (i = 0; i < len / sizeof(struct vring_packed_desc);
+ i++)
+ vring_unmap_desc_packed(vq, &desc[i]);
+ }
+ kfree(desc);
+ vq->desc_state_packed[id].indir_desc = NULL;
+ } else if (ctx) {
+ *ctx = vq->desc_state_packed[id].indir_desc;
+ }
}
static inline bool more_used_packed(const struct vring_virtqueue *vq)
{
- return false;
+ u16 last_used, flags;
+ u8 avail, used;
+
+ last_used = vq->last_used_idx;
+ flags = virtio16_to_cpu(vq->vq.vdev,
+ vq->vring_packed.desc[last_used].flags);
+ avail = !!(flags & VRING_DESC_F_AVAIL(1));
+ used = !!(flags & VRING_DESC_F_USED(1));
+
+ return avail == used && used == vq->used_wrap_counter;
}
static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
unsigned int *len,
void **ctx)
{
- return NULL;
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 last_used, id;
+ void *ret;
+
+ START_USE(vq);
+
+ if (unlikely(vq->broken)) {
+ END_USE(vq);
+ return NULL;
+ }
+
+ if (!more_used_packed(vq)) {
+ pr_debug("No more buffers in queue\n");
+ END_USE(vq);
+ return NULL;
+ }
+
+ /* Only get used elements after they have been exposed by host. */
+ virtio_rmb(vq->weak_barriers);
+
+ last_used = vq->last_used_idx;
+ id = virtio16_to_cpu(_vq->vdev, vq->vring_packed.desc[last_used].id);
+ *len = virtio32_to_cpu(_vq->vdev, vq->vring_packed.desc[last_used].len);
+
+ if (unlikely(id >= vq->vring_packed.num)) {
+ BAD_RING(vq, "id %u out of range\n", id);
+ return NULL;
+ }
+ if (unlikely(!vq->desc_state_packed[id].data)) {
+ BAD_RING(vq, "id %u is not a head!\n", id);
+ return NULL;
+ }
+
+ vq->last_used_idx += vq->desc_state_packed[id].num;
+ if (vq->last_used_idx >= vq->vring_packed.num) {
+ vq->last_used_idx -= vq->vring_packed.num;
+ vq->used_wrap_counter ^= 1;
+ }
+
+ /* detach_buf_packed clears data, so grab it now. */
+ ret = vq->desc_state_packed[id].data;
+ detach_buf_packed(vq, id, ctx);
+
+#ifdef DEBUG
+ vq->last_add_time_valid = false;
+#endif
+
+ END_USE(vq);
+ return ret;
}
static void virtqueue_disable_cb_packed(struct virtqueue *_vq)
{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ if (vq->event_flags_shadow != VRING_EVENT_F_DISABLE) {
+ vq->event_flags_shadow = VRING_EVENT_F_DISABLE;
+ vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
+ vq->event_flags_shadow);
+ }
}
static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
{
- return 0;
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+
+ if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) {
+ vq->event_flags_shadow = VRING_EVENT_F_ENABLE;
+ vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
+ vq->event_flags_shadow);
+ }
+
+ END_USE(vq);
+ return vq->last_used_idx;
}
static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx)
{
- return false;
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u8 avail, used;
+ u16 flags;
+
+ flags = virtio16_to_cpu(vq->vq.vdev,
+ vq->vring_packed.desc[last_used_idx].flags);
+ avail = !!(flags & VRING_DESC_F_AVAIL(1));
+ used = !!(flags & VRING_DESC_F_USED(1));
+
+ return avail == used && used == vq->used_wrap_counter;
}
static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
{
- return false;
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+
+ if (vq->event_flags_shadow == VRING_EVENT_F_DISABLE) {
+ vq->event_flags_shadow = VRING_EVENT_F_ENABLE;
+ vq->vring_packed.driver->flags = cpu_to_virtio16(_vq->vdev,
+ vq->event_flags_shadow);
+ /* We need to enable interrupts first before re-checking
+ * for more used buffers. */
+ virtio_mb(vq->weak_barriers);
+ }
+
+ if (more_used_packed(vq)) {
+ END_USE(vq);
+ return false;
+ }
+
+ END_USE(vq);
+ return true;
}
static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ unsigned int i;
+ void *buf;
+
+ START_USE(vq);
+
+ for (i = 0; i < vq->vring_packed.num; i++) {
+ if (!vq->desc_state_packed[i].data)
+ continue;
+ /* detach_buf clears data, so grab it now. */
+ buf = vq->desc_state_packed[i].data;
+ detach_buf_packed(vq, i, NULL);
+ END_USE(vq);
+ return buf;
+ }
+ /* That should have freed everything. */
+ BUG_ON(vq->vq.num_free != vq->vring_packed.num);
+
+ END_USE(vq);
return NULL;
}
@@ -1084,6 +1553,9 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
{
struct vring_virtqueue *vq = to_vvq(_vq);
+ /* We need to enable interrupts first before re-checking
+ * for more used buffers. */
+ virtio_mb(vq->weak_barriers);
return vq->packed ? virtqueue_poll_packed(_vq, last_used_idx) :
virtqueue_poll_split(_vq, last_used_idx);
}
--
2.17.0
^ permalink raw reply related
* [RFC v6 2/5] virtio_ring: support creating packed ring
From: Tiwei Bie @ 2018-06-05 7:40 UTC (permalink / raw)
To: mst, jasowang, virtualization, linux-kernel, netdev
Cc: wexu, jfreimann, tiwei.bie
In-Reply-To: <20180605074046.20709-1-tiwei.bie@intel.com>
This commit introduces the support for creating packed ring.
All split ring specific functions are added _split suffix.
Some necessary stubs for packed ring are also added.
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
---
drivers/virtio/virtio_ring.c | 801 +++++++++++++++++++++++------------
include/linux/virtio_ring.h | 8 +-
2 files changed, 546 insertions(+), 263 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 71458f493cf8..416c33143125 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -61,11 +61,15 @@ struct vring_desc_state {
struct vring_desc *indir_desc; /* Indirect descriptor, if any. */
};
+struct vring_desc_state_packed {
+ int next; /* The next desc state. */
+};
+
struct vring_virtqueue {
struct virtqueue vq;
- /* Actual memory layout for this queue */
- struct vring vring;
+ /* Is this a packed ring? */
+ bool packed;
/* Can we use weak barriers? */
bool weak_barriers;
@@ -87,11 +91,39 @@ struct vring_virtqueue {
/* Last used index we've seen. */
u16 last_used_idx;
- /* Last written value to avail->flags */
- u16 avail_flags_shadow;
+ union {
+ /* Available for split ring */
+ struct {
+ /* Actual memory layout for this queue. */
+ struct vring vring;
- /* Last written value to avail->idx in guest byte order */
- u16 avail_idx_shadow;
+ /* Last written value to avail->flags */
+ u16 avail_flags_shadow;
+
+ /* Last written value to avail->idx in
+ * guest byte order. */
+ u16 avail_idx_shadow;
+ };
+
+ /* Available for packed ring */
+ struct {
+ /* Actual memory layout for this queue. */
+ struct vring_packed vring_packed;
+
+ /* Driver ring wrap counter. */
+ bool avail_wrap_counter;
+
+ /* Device ring wrap counter. */
+ bool used_wrap_counter;
+
+ /* Index of the next avail descriptor. */
+ u16 next_avail_idx;
+
+ /* Last written value to driver->flags in
+ * guest byte order. */
+ u16 event_flags_shadow;
+ };
+ };
/* How to notify other side. FIXME: commonalize hcalls! */
bool (*notify)(struct virtqueue *vq);
@@ -111,11 +143,24 @@ struct vring_virtqueue {
#endif
/* Per-descriptor state. */
- struct vring_desc_state desc_state[];
+ union {
+ struct vring_desc_state desc_state[1];
+ struct vring_desc_state_packed desc_state_packed[1];
+ };
};
#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
+static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
+ unsigned int total_sg)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ /* If the host supports indirect descriptor tables, and we have multiple
+ * buffers, then go indirect. FIXME: tune this threshold */
+ return (vq->indirect && total_sg > 1 && vq->vq.num_free);
+}
+
/*
* Modern virtio devices have feature bits to specify whether they need a
* quirk and bypass the IOMMU. If not there, just use the DMA API.
@@ -201,8 +246,17 @@ static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
cpu_addr, size, direction);
}
-static void vring_unmap_one(const struct vring_virtqueue *vq,
- struct vring_desc *desc)
+static int vring_mapping_error(const struct vring_virtqueue *vq,
+ dma_addr_t addr)
+{
+ if (!vring_use_dma_api(vq->vq.vdev))
+ return 0;
+
+ return dma_mapping_error(vring_dma_dev(vq), addr);
+}
+
+static void vring_unmap_one_split(const struct vring_virtqueue *vq,
+ struct vring_desc *desc)
{
u16 flags;
@@ -226,17 +280,9 @@ static void vring_unmap_one(const struct vring_virtqueue *vq,
}
}
-static int vring_mapping_error(const struct vring_virtqueue *vq,
- dma_addr_t addr)
-{
- if (!vring_use_dma_api(vq->vq.vdev))
- return 0;
-
- return dma_mapping_error(vring_dma_dev(vq), addr);
-}
-
-static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
- unsigned int total_sg, gfp_t gfp)
+static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
+ unsigned int total_sg,
+ gfp_t gfp)
{
struct vring_desc *desc;
unsigned int i;
@@ -257,14 +303,14 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
return desc;
}
-static inline int virtqueue_add(struct virtqueue *_vq,
- struct scatterlist *sgs[],
- unsigned int total_sg,
- unsigned int out_sgs,
- unsigned int in_sgs,
- void *data,
- void *ctx,
- gfp_t gfp)
+static inline int virtqueue_add_split(struct virtqueue *_vq,
+ struct scatterlist *sgs[],
+ unsigned int total_sg,
+ unsigned int out_sgs,
+ unsigned int in_sgs,
+ void *data,
+ void *ctx,
+ gfp_t gfp)
{
struct vring_virtqueue *vq = to_vvq(_vq);
struct scatterlist *sg;
@@ -300,10 +346,8 @@ static inline int virtqueue_add(struct virtqueue *_vq,
head = vq->free_head;
- /* If the host supports indirect descriptor tables, and we have multiple
- * buffers, then go indirect. FIXME: tune this threshold */
- if (vq->indirect && total_sg > 1 && vq->vq.num_free)
- desc = alloc_indirect(_vq, total_sg, gfp);
+ if (virtqueue_use_indirect(_vq, total_sg))
+ desc = alloc_indirect_split(_vq, total_sg, gfp);
else {
desc = NULL;
WARN_ON_ONCE(total_sg > vq->vring.num && !vq->indirect);
@@ -424,7 +468,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
for (n = 0; n < total_sg; n++) {
if (i == err_idx)
break;
- vring_unmap_one(vq, &desc[i]);
+ vring_unmap_one_split(vq, &desc[i]);
i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next);
}
@@ -435,6 +479,355 @@ static inline int virtqueue_add(struct virtqueue *_vq,
return -EIO;
}
+static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 new, old;
+ bool needs_kick;
+
+ START_USE(vq);
+ /* We need to expose available array entries before checking avail
+ * event. */
+ virtio_mb(vq->weak_barriers);
+
+ old = vq->avail_idx_shadow - vq->num_added;
+ new = vq->avail_idx_shadow;
+ vq->num_added = 0;
+
+#ifdef DEBUG
+ if (vq->last_add_time_valid) {
+ WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
+ vq->last_add_time)) > 100);
+ }
+ vq->last_add_time_valid = false;
+#endif
+
+ if (vq->event) {
+ needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
+ new, old);
+ } else {
+ needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
+ }
+ END_USE(vq);
+ return needs_kick;
+}
+
+static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
+ void **ctx)
+{
+ unsigned int i, j;
+ __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
+
+ /* Clear data ptr. */
+ vq->desc_state[head].data = NULL;
+
+ /* Put back on free list: unmap first-level descriptors and find end */
+ i = head;
+
+ while (vq->vring.desc[i].flags & nextflag) {
+ vring_unmap_one_split(vq, &vq->vring.desc[i]);
+ i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
+ vq->vq.num_free++;
+ }
+
+ vring_unmap_one_split(vq, &vq->vring.desc[i]);
+ vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
+ vq->free_head = head;
+
+ /* Plus final descriptor */
+ vq->vq.num_free++;
+
+ if (vq->indirect) {
+ struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
+ u32 len;
+
+ /* Free the indirect table, if any, now that it's unmapped. */
+ if (!indir_desc)
+ return;
+
+ len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
+
+ BUG_ON(!(vq->vring.desc[head].flags &
+ cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
+ BUG_ON(len == 0 || len % sizeof(struct vring_desc));
+
+ for (j = 0; j < len / sizeof(struct vring_desc); j++)
+ vring_unmap_one_split(vq, &indir_desc[j]);
+
+ kfree(indir_desc);
+ vq->desc_state[head].indir_desc = NULL;
+ } else if (ctx) {
+ *ctx = vq->desc_state[head].indir_desc;
+ }
+}
+
+static inline bool more_used_split(const struct vring_virtqueue *vq)
+{
+ return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
+}
+
+static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
+ unsigned int *len,
+ void **ctx)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ void *ret;
+ unsigned int i;
+ u16 last_used;
+
+ START_USE(vq);
+
+ if (unlikely(vq->broken)) {
+ END_USE(vq);
+ return NULL;
+ }
+
+ if (!more_used_split(vq)) {
+ pr_debug("No more buffers in queue\n");
+ END_USE(vq);
+ return NULL;
+ }
+
+ /* Only get used array entries after they have been exposed by host. */
+ virtio_rmb(vq->weak_barriers);
+
+ last_used = (vq->last_used_idx & (vq->vring.num - 1));
+ i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
+ *len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
+
+ if (unlikely(i >= vq->vring.num)) {
+ BAD_RING(vq, "id %u out of range\n", i);
+ return NULL;
+ }
+ if (unlikely(!vq->desc_state[i].data)) {
+ BAD_RING(vq, "id %u is not a head!\n", i);
+ return NULL;
+ }
+
+ /* detach_buf_split clears data, so grab it now. */
+ ret = vq->desc_state[i].data;
+ detach_buf_split(vq, i, ctx);
+ vq->last_used_idx++;
+ /* If we expect an interrupt for the next entry, tell host
+ * by writing event index and flush out the write before
+ * the read in the next get_buf call. */
+ if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
+ virtio_store_mb(vq->weak_barriers,
+ &vring_used_event(&vq->vring),
+ cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
+
+#ifdef DEBUG
+ vq->last_add_time_valid = false;
+#endif
+
+ END_USE(vq);
+ return ret;
+}
+
+static void virtqueue_disable_cb_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
+ vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ }
+}
+
+static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 last_used_idx;
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+ /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+ * either clear the flags bit or point the event index at the next
+ * entry. Always do both to keep code simple. */
+ if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+ vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ }
+ vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
+ END_USE(vq);
+ return last_used_idx;
+}
+
+static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ virtio_mb(vq->weak_barriers);
+ return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
+}
+
+static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 bufs;
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+ /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+ * either clear the flags bit or point the event index at the next
+ * entry. Always update the event index to keep code simple. */
+ if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+ vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ }
+ /* TODO: tune this threshold */
+ bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
+
+ virtio_store_mb(vq->weak_barriers,
+ &vring_used_event(&vq->vring),
+ cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
+
+ if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
+ END_USE(vq);
+ return false;
+ }
+
+ END_USE(vq);
+ return true;
+}
+
+static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ unsigned int i;
+ void *buf;
+
+ START_USE(vq);
+
+ for (i = 0; i < vq->vring.num; i++) {
+ if (!vq->desc_state[i].data)
+ continue;
+ /* detach_buf clears data, so grab it now. */
+ buf = vq->desc_state[i].data;
+ detach_buf_split(vq, i, NULL);
+ vq->avail_idx_shadow--;
+ vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
+ END_USE(vq);
+ return buf;
+ }
+ /* That should have freed everything. */
+ BUG_ON(vq->vq.num_free != vq->vring.num);
+
+ END_USE(vq);
+ return NULL;
+}
+
+/*
+ * The layout for the packed ring is a continuous chunk of memory
+ * which looks like this.
+ *
+ * struct vring_packed {
+ * // The actual descriptors (16 bytes each)
+ * struct vring_packed_desc desc[num];
+ *
+ * // Padding to the next align boundary.
+ * char pad[];
+ *
+ * // Driver Event Suppression
+ * struct vring_packed_desc_event driver;
+ *
+ * // Device Event Suppression
+ * struct vring_packed_desc_event device;
+ * };
+ */
+static inline void vring_init_packed(struct vring_packed *vr, unsigned int num,
+ void *p, unsigned long align)
+{
+ vr->num = num;
+ vr->desc = p;
+ vr->driver = (void *)ALIGN(((uintptr_t)p +
+ sizeof(struct vring_packed_desc) * num), align);
+ vr->device = vr->driver + 1;
+}
+
+static inline unsigned vring_size_packed(unsigned int num, unsigned long align)
+{
+ return ((sizeof(struct vring_packed_desc) * num + align - 1)
+ & ~(align - 1)) + sizeof(struct vring_packed_desc_event) * 2;
+}
+
+static inline int virtqueue_add_packed(struct virtqueue *_vq,
+ struct scatterlist *sgs[],
+ unsigned int total_sg,
+ unsigned int out_sgs,
+ unsigned int in_sgs,
+ void *data,
+ void *ctx,
+ gfp_t gfp)
+{
+ return -EIO;
+}
+
+static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
+{
+ return false;
+}
+
+static inline bool more_used_packed(const struct vring_virtqueue *vq)
+{
+ return false;
+}
+
+static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
+ unsigned int *len,
+ void **ctx)
+{
+ return NULL;
+}
+
+static void virtqueue_disable_cb_packed(struct virtqueue *_vq)
+{
+}
+
+static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
+{
+ return 0;
+}
+
+static bool virtqueue_poll_packed(struct virtqueue *_vq, unsigned last_used_idx)
+{
+ return false;
+}
+
+static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
+{
+ return false;
+}
+
+static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
+{
+ return NULL;
+}
+
+static inline int virtqueue_add(struct virtqueue *_vq,
+ struct scatterlist *sgs[],
+ unsigned int total_sg,
+ unsigned int out_sgs,
+ unsigned int in_sgs,
+ void *data,
+ void *ctx,
+ gfp_t gfp)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ return vq->packed ? virtqueue_add_packed(_vq, sgs, total_sg, out_sgs,
+ in_sgs, data, ctx, gfp) :
+ virtqueue_add_split(_vq, sgs, total_sg, out_sgs,
+ in_sgs, data, ctx, gfp);
+}
+
/**
* virtqueue_add_sgs - expose buffers to other end
* @vq: the struct virtqueue we're talking about.
@@ -551,34 +944,9 @@ EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
bool virtqueue_kick_prepare(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- u16 new, old;
- bool needs_kick;
- START_USE(vq);
- /* We need to expose available array entries before checking avail
- * event. */
- virtio_mb(vq->weak_barriers);
-
- old = vq->avail_idx_shadow - vq->num_added;
- new = vq->avail_idx_shadow;
- vq->num_added = 0;
-
-#ifdef DEBUG
- if (vq->last_add_time_valid) {
- WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
- vq->last_add_time)) > 100);
- }
- vq->last_add_time_valid = false;
-#endif
-
- if (vq->event) {
- needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
- new, old);
- } else {
- needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
- }
- END_USE(vq);
- return needs_kick;
+ return vq->packed ? virtqueue_kick_prepare_packed(_vq) :
+ virtqueue_kick_prepare_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
@@ -626,58 +994,9 @@ bool virtqueue_kick(struct virtqueue *vq)
}
EXPORT_SYMBOL_GPL(virtqueue_kick);
-static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
- void **ctx)
-{
- unsigned int i, j;
- __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
-
- /* Clear data ptr. */
- vq->desc_state[head].data = NULL;
-
- /* Put back on free list: unmap first-level descriptors and find end */
- i = head;
-
- while (vq->vring.desc[i].flags & nextflag) {
- vring_unmap_one(vq, &vq->vring.desc[i]);
- i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
- vq->vq.num_free++;
- }
-
- vring_unmap_one(vq, &vq->vring.desc[i]);
- vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
- vq->free_head = head;
-
- /* Plus final descriptor */
- vq->vq.num_free++;
-
- if (vq->indirect) {
- struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
- u32 len;
-
- /* Free the indirect table, if any, now that it's unmapped. */
- if (!indir_desc)
- return;
-
- len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
-
- BUG_ON(!(vq->vring.desc[head].flags &
- cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
- BUG_ON(len == 0 || len % sizeof(struct vring_desc));
-
- for (j = 0; j < len / sizeof(struct vring_desc); j++)
- vring_unmap_one(vq, &indir_desc[j]);
-
- kfree(indir_desc);
- vq->desc_state[head].indir_desc = NULL;
- } else if (ctx) {
- *ctx = vq->desc_state[head].indir_desc;
- }
-}
-
static inline bool more_used(const struct vring_virtqueue *vq)
{
- return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
+ return vq->packed ? more_used_packed(vq) : more_used_split(vq);
}
/**
@@ -700,57 +1019,9 @@ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
void **ctx)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- void *ret;
- unsigned int i;
- u16 last_used;
- START_USE(vq);
-
- if (unlikely(vq->broken)) {
- END_USE(vq);
- return NULL;
- }
-
- if (!more_used(vq)) {
- pr_debug("No more buffers in queue\n");
- END_USE(vq);
- return NULL;
- }
-
- /* Only get used array entries after they have been exposed by host. */
- virtio_rmb(vq->weak_barriers);
-
- last_used = (vq->last_used_idx & (vq->vring.num - 1));
- i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
- *len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
-
- if (unlikely(i >= vq->vring.num)) {
- BAD_RING(vq, "id %u out of range\n", i);
- return NULL;
- }
- if (unlikely(!vq->desc_state[i].data)) {
- BAD_RING(vq, "id %u is not a head!\n", i);
- return NULL;
- }
-
- /* detach_buf clears data, so grab it now. */
- ret = vq->desc_state[i].data;
- detach_buf(vq, i, ctx);
- vq->last_used_idx++;
- /* If we expect an interrupt for the next entry, tell host
- * by writing event index and flush out the write before
- * the read in the next get_buf call. */
- if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
- virtio_store_mb(vq->weak_barriers,
- &vring_used_event(&vq->vring),
- cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
-
-#ifdef DEBUG
- vq->last_add_time_valid = false;
-#endif
-
- END_USE(vq);
- return ret;
+ return vq->packed ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) :
+ virtqueue_get_buf_ctx_split(_vq, len, ctx);
}
EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
@@ -772,12 +1043,10 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
- vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
- }
-
+ if (vq->packed)
+ virtqueue_disable_cb_packed(_vq);
+ else
+ virtqueue_disable_cb_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
@@ -796,23 +1065,9 @@ EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- u16 last_used_idx;
- START_USE(vq);
-
- /* We optimistically turn back on interrupts, then check if there was
- * more to do. */
- /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
- * either clear the flags bit or point the event index at the next
- * entry. Always do both to keep code simple. */
- if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
- vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
- }
- vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
- END_USE(vq);
- return last_used_idx;
+ return vq->packed ? virtqueue_enable_cb_prepare_packed(_vq) :
+ virtqueue_enable_cb_prepare_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
@@ -829,8 +1084,8 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- virtio_mb(vq->weak_barriers);
- return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
+ return vq->packed ? virtqueue_poll_packed(_vq, last_used_idx) :
+ virtqueue_poll_split(_vq, last_used_idx);
}
EXPORT_SYMBOL_GPL(virtqueue_poll);
@@ -868,34 +1123,9 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- u16 bufs;
- START_USE(vq);
-
- /* We optimistically turn back on interrupts, then check if there was
- * more to do. */
- /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
- * either clear the flags bit or point the event index at the next
- * entry. Always update the event index to keep code simple. */
- if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
- vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
- }
- /* TODO: tune this threshold */
- bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
-
- virtio_store_mb(vq->weak_barriers,
- &vring_used_event(&vq->vring),
- cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
-
- if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
- END_USE(vq);
- return false;
- }
-
- END_USE(vq);
- return true;
+ return vq->packed ? virtqueue_enable_cb_delayed_packed(_vq) :
+ virtqueue_enable_cb_delayed_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
@@ -910,27 +1140,9 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- unsigned int i;
- void *buf;
- START_USE(vq);
-
- for (i = 0; i < vq->vring.num; i++) {
- if (!vq->desc_state[i].data)
- continue;
- /* detach_buf clears data, so grab it now. */
- buf = vq->desc_state[i].data;
- detach_buf(vq, i, NULL);
- vq->avail_idx_shadow--;
- vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
- END_USE(vq);
- return buf;
- }
- /* That should have freed everything. */
- BUG_ON(vq->vq.num_free != vq->vring.num);
-
- END_USE(vq);
- return NULL;
+ return vq->packed ? virtqueue_detach_unused_buf_packed(_vq) :
+ virtqueue_detach_unused_buf_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
@@ -955,7 +1167,8 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
EXPORT_SYMBOL_GPL(vring_interrupt);
struct virtqueue *__vring_new_virtqueue(unsigned int index,
- struct vring vring,
+ union vring_union vring,
+ bool packed,
struct virtio_device *vdev,
bool weak_barriers,
bool context,
@@ -963,19 +1176,22 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
void (*callback)(struct virtqueue *),
const char *name)
{
- unsigned int i;
struct vring_virtqueue *vq;
+ unsigned int num, i;
+ size_t size;
- vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state),
- GFP_KERNEL);
+ num = packed ? vring.vring_packed.num : vring.vring_split.num;
+ size = packed ? num * sizeof(struct vring_desc_state_packed) :
+ num * sizeof(struct vring_desc_state);
+
+ vq = kmalloc(sizeof(*vq) + size, GFP_KERNEL);
if (!vq)
return NULL;
- vq->vring = vring;
vq->vq.callback = callback;
vq->vq.vdev = vdev;
vq->vq.name = name;
- vq->vq.num_free = vring.num;
+ vq->vq.num_free = num;
vq->vq.index = index;
vq->we_own_ring = false;
vq->queue_dma_addr = 0;
@@ -984,9 +1200,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
vq->weak_barriers = weak_barriers;
vq->broken = false;
vq->last_used_idx = 0;
- vq->avail_flags_shadow = 0;
- vq->avail_idx_shadow = 0;
vq->num_added = 0;
+ vq->packed = packed;
list_add_tail(&vq->vq.list, &vdev->vqs);
#ifdef DEBUG
vq->in_use = false;
@@ -997,19 +1212,48 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
!context;
vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+ if (vq->packed) {
+ vq->vring_packed = vring.vring_packed;
+ vq->next_avail_idx = 0;
+ vq->avail_wrap_counter = 1;
+ vq->used_wrap_counter = 1;
+ vq->event_flags_shadow = 0;
+
+ memset(vq->desc_state_packed, 0,
+ num * sizeof(struct vring_desc_state_packed));
+
+ /* Put everything in free lists. */
+ vq->free_head = 0;
+ for (i = 0; i < num-1; i++)
+ vq->desc_state_packed[i].next = i + 1;
+ } else {
+ vq->vring = vring.vring_split;
+ vq->avail_flags_shadow = 0;
+ vq->avail_idx_shadow = 0;
+
+ /* Put everything in free lists. */
+ vq->free_head = 0;
+ for (i = 0; i < num-1; i++)
+ vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
+
+ memset(vq->desc_state, 0,
+ num * sizeof(struct vring_desc_state));
+ }
+
/* No callback? Tell other side not to bother us. */
if (!callback) {
- vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+ if (packed) {
+ vq->event_flags_shadow = VRING_EVENT_F_DISABLE;
+ vq->vring_packed.driver->flags = cpu_to_virtio16(vdev,
+ vq->event_flags_shadow);
+ } else {
+ vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(vdev,
+ vq->avail_flags_shadow);
+ }
}
- /* Put everything in free lists. */
- vq->free_head = 0;
- for (i = 0; i < vring.num-1; i++)
- vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
- memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));
-
return &vq->vq;
}
EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
@@ -1056,6 +1300,12 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size,
}
}
+static inline int
+__vring_size(unsigned int num, unsigned long align, bool packed)
+{
+ return packed ? vring_size_packed(num, align) : vring_size(num, align);
+}
+
struct virtqueue *vring_create_virtqueue(
unsigned int index,
unsigned int num,
@@ -1072,7 +1322,8 @@ struct virtqueue *vring_create_virtqueue(
void *queue = NULL;
dma_addr_t dma_addr;
size_t queue_size_in_bytes;
- struct vring vring;
+ union vring_union vring;
+ bool packed;
/* We assume num is a power of 2. */
if (num & (num - 1)) {
@@ -1080,9 +1331,13 @@ struct virtqueue *vring_create_virtqueue(
return NULL;
}
+ packed = virtio_has_feature(vdev, VIRTIO_F_RING_PACKED);
+
/* TODO: allocate each queue chunk individually */
- for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
- queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+ for (; num && __vring_size(num, vring_align, packed) > PAGE_SIZE;
+ num /= 2) {
+ queue = vring_alloc_queue(vdev, __vring_size(num, vring_align,
+ packed),
&dma_addr,
GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
if (queue)
@@ -1094,17 +1349,21 @@ struct virtqueue *vring_create_virtqueue(
if (!queue) {
/* Try to get a single page. You are my only hope! */
- queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+ queue = vring_alloc_queue(vdev, __vring_size(num, vring_align,
+ packed),
&dma_addr, GFP_KERNEL|__GFP_ZERO);
}
if (!queue)
return NULL;
- queue_size_in_bytes = vring_size(num, vring_align);
- vring_init(&vring, num, queue, vring_align);
+ queue_size_in_bytes = __vring_size(num, vring_align, packed);
+ if (packed)
+ vring_init_packed(&vring.vring_packed, num, queue, vring_align);
+ else
+ vring_init(&vring.vring_split, num, queue, vring_align);
- vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
- notify, callback, name);
+ vq = __vring_new_virtqueue(index, vring, packed, vdev, weak_barriers,
+ context, notify, callback, name);
if (!vq) {
vring_free_queue(vdev, queue_size_in_bytes, queue,
dma_addr);
@@ -1130,10 +1389,17 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
void (*callback)(struct virtqueue *vq),
const char *name)
{
- struct vring vring;
- vring_init(&vring, num, pages, vring_align);
- return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
- notify, callback, name);
+ union vring_union vring;
+ bool packed;
+
+ packed = virtio_has_feature(vdev, VIRTIO_F_RING_PACKED);
+ if (packed)
+ vring_init_packed(&vring.vring_packed, num, pages, vring_align);
+ else
+ vring_init(&vring.vring_split, num, pages, vring_align);
+
+ return __vring_new_virtqueue(index, vring, packed, vdev, weak_barriers,
+ context, notify, callback, name);
}
EXPORT_SYMBOL_GPL(vring_new_virtqueue);
@@ -1143,7 +1409,9 @@ void vring_del_virtqueue(struct virtqueue *_vq)
if (vq->we_own_ring) {
vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
- vq->vring.desc, vq->queue_dma_addr);
+ vq->packed ? (void *)vq->vring_packed.desc :
+ (void *)vq->vring.desc,
+ vq->queue_dma_addr);
}
list_del(&_vq->list);
kfree(vq);
@@ -1185,7 +1453,7 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
struct vring_virtqueue *vq = to_vvq(_vq);
- return vq->vring.num;
+ return vq->packed ? vq->vring_packed.num : vq->vring.num;
}
EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
@@ -1228,6 +1496,10 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
BUG_ON(!vq->we_own_ring);
+ if (vq->packed)
+ return vq->queue_dma_addr + ((char *)vq->vring_packed.driver -
+ (char *)vq->vring_packed.desc);
+
return vq->queue_dma_addr +
((char *)vq->vring.avail - (char *)vq->vring.desc);
}
@@ -1239,11 +1511,16 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
BUG_ON(!vq->we_own_ring);
+ if (vq->packed)
+ return vq->queue_dma_addr + ((char *)vq->vring_packed.device -
+ (char *)vq->vring_packed.desc);
+
return vq->queue_dma_addr +
((char *)vq->vring.used - (char *)vq->vring.desc);
}
EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
+/* Only available for split ring */
const struct vring *virtqueue_get_vring(struct virtqueue *vq)
{
return &to_vvq(vq)->vring;
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index bbf32524ab27..a0075894ad16 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -60,6 +60,11 @@ static inline void virtio_store_mb(bool weak_barriers,
struct virtio_device;
struct virtqueue;
+union vring_union {
+ struct vring vring_split;
+ struct vring_packed vring_packed;
+};
+
/*
* Creates a virtqueue and allocates the descriptor ring. If
* may_reduce_num is set, then this may allocate a smaller ring than
@@ -79,7 +84,8 @@ struct virtqueue *vring_create_virtqueue(unsigned int index,
/* Creates a virtqueue with a custom layout. */
struct virtqueue *__vring_new_virtqueue(unsigned int index,
- struct vring vring,
+ union vring_union vring,
+ bool packed,
struct virtio_device *vdev,
bool weak_barriers,
bool ctx,
--
2.17.0
^ permalink raw reply related
* [RFC v6 1/5] virtio: add packed ring definitions
From: Tiwei Bie @ 2018-06-05 7:40 UTC (permalink / raw)
To: mst, jasowang, virtualization, linux-kernel, netdev; +Cc: wexu
In-Reply-To: <20180605074046.20709-1-tiwei.bie@intel.com>
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
---
include/uapi/linux/virtio_config.h | 5 ++++-
include/uapi/linux/virtio_ring.h | 36 ++++++++++++++++++++++++++++++
2 files changed, 40 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 308e2096291f..932a6ecc8e46 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -49,7 +49,7 @@
* transport being used (eg. virtio_ring), the rest are per-device feature
* bits. */
#define VIRTIO_TRANSPORT_F_START 28
-#define VIRTIO_TRANSPORT_F_END 34
+#define VIRTIO_TRANSPORT_F_END 35
#ifndef VIRTIO_CONFIG_NO_LEGACY
/* Do we get callbacks when the ring is completely used, even if we've
@@ -71,4 +71,7 @@
* this is for compatibility with legacy systems.
*/
#define VIRTIO_F_IOMMU_PLATFORM 33
+
+/* This feature indicates support for the packed virtqueue layout. */
+#define VIRTIO_F_RING_PACKED 34
#endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 6d5d5faa989b..7b378da788a7 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -44,6 +44,9 @@
/* This means the buffer contains a list of buffer descriptors. */
#define VRING_DESC_F_INDIRECT 4
+#define VRING_DESC_F_AVAIL(b) ((__u16)(b) << 7)
+#define VRING_DESC_F_USED(b) ((__u16)(b) << 15)
+
/* The Host uses this in used->flags to advise the Guest: don't kick me when
* you add a buffer. It's unreliable, so it's simply an optimization. Guest
* will still kick if it's out of buffers. */
@@ -53,6 +56,10 @@
* optimization. */
#define VRING_AVAIL_F_NO_INTERRUPT 1
+#define VRING_EVENT_F_ENABLE 0x0
+#define VRING_EVENT_F_DISABLE 0x1
+#define VRING_EVENT_F_DESC 0x2
+
/* We support indirect buffer descriptors */
#define VIRTIO_RING_F_INDIRECT_DESC 28
@@ -171,4 +178,33 @@ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
}
+struct vring_packed_desc_event {
+ /* __virtio16 off : 15; // Descriptor Event Offset
+ * __virtio16 wrap : 1; // Descriptor Event Wrap Counter */
+ __virtio16 off_wrap;
+ /* __virtio16 flags : 2; // Descriptor Event Flags */
+ __virtio16 flags;
+};
+
+struct vring_packed_desc {
+ /* Buffer Address. */
+ __virtio64 addr;
+ /* Buffer Length. */
+ __virtio32 len;
+ /* Buffer ID. */
+ __virtio16 id;
+ /* The flags depending on descriptor type. */
+ __virtio16 flags;
+};
+
+struct vring_packed {
+ unsigned int num;
+
+ struct vring_packed_desc *desc;
+
+ struct vring_packed_desc_event *driver;
+
+ struct vring_packed_desc_event *device;
+};
+
#endif /* _UAPI_LINUX_VIRTIO_RING_H */
--
2.17.0
^ permalink raw reply related
* [RFC v6 0/5] virtio: support packed ring
From: Tiwei Bie @ 2018-06-05 7:40 UTC (permalink / raw)
To: mst, jasowang, virtualization, linux-kernel, netdev
Cc: wexu, jfreimann, tiwei.bie
Hello everyone,
This RFC implements packed ring support in virtio driver.
Some functional tests have been done with Jason's
packed ring implementation in vhost (RFC v5):
https://lwn.net/Articles/755862/
Both of ping and netperf worked as expected.
TODO:
- Refinements (for code and commit log);
- More tests and bug fixes if any;
- Send the formal patch set;
RFC v5 -> RFC v6:
- Avoid tracking addr/len/flags when DMA API isn't used (MST/Jason);
- Define wrap counter as bool (Jason);
- Use ALIGN() in vring_init_packed() (Jason);
- Avoid using pointer to track `next` in detach_buf_packed() (Jason);
- Add comments for barriers (Jason);
- Don't enable RING_PACKED on ccw for now (noticed by Jason);
- Refine the memory barrier in virtqueue_poll();
- Add a missing memory barrier in virtqueue_enable_cb_delayed_packed();
- Remove the hacks in virtqueue_enable_cb_prepare_packed();
RFC v4 -> RFC v5:
- Save DMA addr, etc in desc state (Jason);
- Track used wrap counter;
RFC v3 -> RFC v4:
- Make ID allocation support out-of-order (Jason);
- Various fixes for EVENT_IDX support;
RFC v2 -> RFC v3:
- Split into small patches (Jason);
- Add helper virtqueue_use_indirect() (Jason);
- Just set id for the last descriptor of a list (Jason);
- Calculate the prev in virtqueue_add_packed() (Jason);
- Fix/improve desc suppression code (Jason/MST);
- Refine the code layout for XXX_split/packed and wrappers (MST);
- Fix the comments and API in uapi (MST);
- Remove the BUG_ON() for indirect (Jason);
- Some other refinements and bug fixes;
RFC v1 -> RFC v2:
- Add indirect descriptor support - compile test only;
- Add event suppression supprt - compile test only;
- Move vring_packed_init() out of uapi (Jason, MST);
- Merge two loops into one in virtqueue_add_packed() (Jason);
- Split vring_unmap_one() for packed ring and split ring (Jason);
- Avoid using '%' operator (Jason);
- Rename free_head -> next_avail_idx (Jason);
- Add comments for virtio_wmb() in virtqueue_add_packed() (Jason);
- Some other refinements and bug fixes;
Thanks!
Tiwei Bie (5):
virtio: add packed ring definitions
virtio_ring: support creating packed ring
virtio_ring: add packed ring support
virtio_ring: add event idx support in packed ring
virtio_ring: enable packed ring
drivers/s390/virtio/virtio_ccw.c | 8 +
drivers/virtio/virtio_ring.c | 1361 ++++++++++++++++++++++------
include/linux/virtio_ring.h | 8 +-
include/uapi/linux/virtio_config.h | 5 +-
include/uapi/linux/virtio_ring.h | 36 +
5 files changed, 1141 insertions(+), 277 deletions(-)
--
2.17.0
^ permalink raw reply
* Re: [PATCH net-next] net: sched: return error code when tcf proto is not found
From: Vlad Buslov @ 2018-06-05 7:00 UTC (permalink / raw)
To: David Miller; +Cc: netdev, jhs, xiyou.wangcong, jiri, dan.carpenter
In-Reply-To: <20180604.173219.1997841279674931039.davem@davemloft.net>
On Mon 04 Jun 2018 at 21:32, David Miller <davem@davemloft.net> wrote:
> From: Vlad Buslov <vladbu@mellanox.com>
> Date: Mon, 4 Jun 2018 18:32:23 +0300
>
>> If requested tcf proto is not found, get and del filter netlink protocol
>> handlers output error message to extack, but do not return actual error
>> code. Add check to return ENOENT when result of tp find function is NULL
>> pointer.
>>
>> Fixes: c431f89b18a2 ("net: sched: split tc_ctl_tfilter into three
>> handlers")
>
> Please do not split up a Fixes: tag into multiple lines. I fixed it
> up for you this time.
Got it, thanks.
>
>> Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
>> Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
>
> Applied, thanks.
^ permalink raw reply
* Re: [PATCH net-next] net/mlx5e: fix error return code in mlx5e_alloc_rq()
From: Tariq Toukan @ 2018-06-05 6:48 UTC (permalink / raw)
To: Wei Yongjun, Saeed Mahameed, Leon Romanovsky, Tariq Toukan
Cc: netdev, linux-rdma, kernel-janitors
In-Reply-To: <1528166576-55047-1-git-send-email-weiyongjun1@huawei.com>
On 05/06/2018 5:42 AM, Wei Yongjun wrote:
> Fix to return error code -ENOMEM from the kvzalloc_node() error handling
> case instead of 0, as done elsewhere in this function.
>
> Fixes: 069d11465a80 ("net/mlx5e: RX, Enhance legacy Receive Queue memory scheme")
> Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
> ---
> drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
> index 333d4ed..89c96a0 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
> @@ -566,8 +566,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
> kvzalloc_node((wq_sz << rq->wqe.info.log_num_frags) *
> sizeof(*rq->wqe.frags),
> GFP_KERNEL, cpu_to_node(c->cpu));
> - if (!rq->wqe.frags)
> + if (!rq->wqe.frags) {
> + err = -ENOMEM;
> goto err_free;
> + }
>
> err = mlx5e_init_di_list(rq, params, wq_sz, c->cpu);
> if (err)
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
Thanks Wei!
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
^ permalink raw reply
* Re: WARNING: CPU: 3 PID: 0 at net/sched/sch_hfsc.c:1388 hfsc_dequeue+0x319/0x350 [sch_hfsc]
From: Marco Berizzi @ 2018-06-05 6:39 UTC (permalink / raw)
To: netdev
In-Reply-To: <746588000.720568.1520524944312@mail.libero.it>
> Il 8 marzo 2018 alle 17.02 Marco Berizzi <pupilla@libero.it> ha scritto:
>
> > Marco Berizzi wrote:
> >
> > Hello everyone,
> >
> > Yesterday I got this error on a slackware linux 4.16-rc4 system
> > running as a traffic shaping gateway and netfilter nat.
> > The error has been arisen after a partial ISP network outage,
> > so unfortunately it will not trivial for me to reproduce it again.
>
> Hello everyone,
>
> I'm getting this error twice/day, so fortunately I'm able to
> reproduce it.
I'm getting the same error also with 4.17 (4.15.18 was
the latest working version):
[ 11.445829] WARNING: CPU: 0 PID: 0 at net/sched/sch_hfsc.c:1388 hfsc_dequeue+0x319/0x350 [sch_hfsc]
[ 11.445831] Modules linked in: cls_u32 sch_sfq sch_hfsc nf_nat_ftp nf_conntrack_ftp nf_nat nf_conntrack nft_set_hash nft_set_rbtree nf_tables nfnetlink ext2 hid_generic usbhid hid uhci_hcd ehci_pci ehci_hcd usbcore intel_cstate usb_common bnx2 rtc_cmos loop
[ 11.445854] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.17.0 #1
[ 11.445856] Hardware name: HP ProLiant DL360 G7, BIOS P68 08/16/2010
[ 11.445859] RIP: 0010:hfsc_dequeue+0x319/0x350 [sch_hfsc]
[ 11.445861] RSP: 0018:ffff88081fa03b20 EFLAGS: 00010246
[ 11.445863] RAX: 0000000000000000 RBX: ffff8807f5055988 RCX: 0000000000000018
[ 11.445864] RDX: 0000000000000002 RSI: 0000000000000000 RDI: ffff8807f5055c80
[ 11.445866] RBP: 000000000aa8e4a6 R08: 0000000000000001 R09: 0000000000000000
[ 11.445867] R10: ffff8807fbe41868 R11: 0000000000000001 R12: ffff8807f5055800
[ 11.445869] R13: ffff8807f5055c80 R14: ffff8807f7f12800 R15: ffff8807f5055800
[ 11.445871] FS: 0000000000000000(0000) GS:ffff88081fa00000(0000) knlGS:0000000000000000
[ 11.445872] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 11.445874] CR2: 00007fdd5de915f8 CR3: 0000000001a0a000 CR4: 00000000000006b0
[ 11.445875] Call Trace:
[ 11.445878] <IRQ>
[ 11.445884] __qdisc_run+0xbe/0x520
[ 11.445890] __dev_queue_xmit+0x387/0x740
[ 11.445895] ? get_nohz_timer_target+0x8c/0x150
[ 11.445897] ? eth_header+0x20/0xb0
[ 11.445900] ? neigh_update+0x34b/0x6b0
[ 11.445902] neigh_update+0x34b/0x6b0
[ 11.445907] arp_process+0x23a/0x780
[ 11.445911] __netif_receive_skb_core+0x338/0xaf0
[ 11.445915] ? __alloc_pages_nodemask+0x99/0x110
[ 11.445918] ? netif_receive_skb_internal+0x2e/0xc0
[ 11.445920] netif_receive_skb_internal+0x2e/0xc0
[ 11.445923] napi_gro_receive+0x70/0x90
[ 11.445928] bnx2_poll_work+0x777/0x1300 [bnx2]
[ 11.445932] ? check_preempt_curr+0x4b/0x80
[ 11.445935] bnx2_poll+0x44/0x210 [bnx2]
[ 11.445938] net_rx_action+0x1ca/0x2b0
[ 11.445942] __do_softirq+0xd4/0x1c9
[ 11.445947] irq_exit+0xa3/0xb0
[ 11.445949] do_IRQ+0x45/0xc0
[ 11.445952] common_interrupt+0xf/0xf
[ 11.445953] </IRQ>
[ 11.445958] RIP: 0010:mwait_idle+0x45/0x70
[ 11.445959] RSP: 0018:ffffffff81a03ef0 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdb
[ 11.445961] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[ 11.445963] RDX: 0000000000000000 RSI: ffff88081fa19060 RDI: ffff88081fa1b5c0
[ 11.445964] RBP: ffffffff81a10480 R08: 0000000000000000 R09: 00000002bbeff5c0
[ 11.445965] R10: 00000000000002a6 R11: 0000000000000c00 R12: ffffffff81a10480
[ 11.445967] R13: ffffffff81c770a0 R14: 0000000000000000 R15: 0000000000000000
[ 11.445971] do_idle+0x86/0xf0
[ 11.445974] cpu_startup_entry+0x14/0x20
[ 11.445977] start_kernel+0x31d/0x325
[ 11.445981] secondary_startup_64+0xa5/0xb0
[ 11.445982] Code: 48 89 c5 e9 06 fe ff ff 48 8b b3 88 00 00 00 48 c7 c7 60 70 08 a0 e8 f7 7c 2c e1 31 c0 e9 c0 fe ff ff 48 85 f6 0f 85 75 ff ff ff <0f> 0b 31 f6 e9 70 ff ff ff 48 89 c6 e9 64 ff ff ff 48 85 db 0f
[ 11.446021] ---[ end trace 977c540fdfcce8ae ]---
^ permalink raw reply
* RE: [PATCH] r8169: Reinstate ALDPS and ASPM support
From: Ryankao @ 2018-06-05 6:34 UTC (permalink / raw)
To: Kai Heng Feng, jrg.otte@gmail.com
Cc: David Miller, Hayes Wang, hkallweit1@gmail.com,
romieu@fr.zoreil.com, Linux Netdev List,
Linux Kernel Mailing List, Hau
In-Reply-To: <9D9E2AF1-CD59-425B-85E9-DB89D620CA67@canonical.com>
Add realtek folk Hau
-----Original Message-----
From: Kai Heng Feng [mailto:kai.heng.feng@canonical.com]
Sent: Tuesday, June 05, 2018 1:02 PM
To: jrg.otte@gmail.com
Cc: David Miller <davem@davemloft.net>; Hayes Wang <hayeswang@realtek.com>; hkallweit1@gmail.com; romieu@fr.zoreil.com; Linux Netdev List <netdev@vger.kernel.org>; Linux Kernel Mailing List <linux-kernel@vger.kernel.org>; Ryankao <ryankao@realtek.com>
Subject: Re: [PATCH] r8169: Reinstate ALDPS and ASPM support
Hi Jörg Otte,
Can you give this patch a try?
Since you are the only one that reported ALDPS/ASPM regression,
And I think this patch should solve the issue you had [1].
Hopefully we don't need to go down the rabbit hole of blacklist/whitelist...
Kai-Heng
[1] https://lkml.org/lkml/2013/1/5/36
> On Jun 5, 2018, at 12:58 PM, Kai-Heng Feng
> <kai.heng.feng@canonical.com>
> wrote:
>
> This patch reinstate ALDPS and ASPM support on r8169.
>
> On some Intel platforms, ASPM support on r8169 is the key factor to
> let Package C-State achieve PC8. Without ASPM support, the deepest
> Package C-State can hit is PC3. PC8 can save additional ~3W in
> comparison with PC3.
>
> This patch is from Realtek.
>
> Fixes: e0c075577965 ("r8169: enable ALDPS for power saving")
> Fixes: d64ec841517a ("r8169: enable internal ASPM and clock request
> settings")
>
> Cc: Ryankao <ryankao@realtek.com>
> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> ---
> drivers/net/ethernet/realtek/r8169.c | 190
> +++++++++++++++++++++------
> 1 file changed, 151 insertions(+), 39 deletions(-)
>
> diff --git a/drivers/net/ethernet/realtek/r8169.c
> b/drivers/net/ethernet/realtek/r8169.c
> index 75dfac0248f4..a28ef20be221 100644
> --- a/drivers/net/ethernet/realtek/r8169.c
> +++ b/drivers/net/ethernet/realtek/r8169.c
> @@ -319,6 +319,8 @@ static const struct pci_device_id
> rtl8169_pci_tbl[] = {
>
> MODULE_DEVICE_TABLE(pci, rtl8169_pci_tbl);
>
> +static int enable_aspm = 1;
> +static int enable_aldps = 1;
> static int use_dac = -1;
> static struct {
> u32 msg_enable;
> @@ -817,6 +819,10 @@ struct rtl8169_private {
>
> MODULE_AUTHOR("Realtek and the Linux r8169 crew
> <netdev@vger.kernel.org>"); MODULE_DESCRIPTION("RealTek RTL-8169
> Gigabit Ethernet driver");
> +module_param(enable_aspm, int, 0);
> +MODULE_PARM_DESC(enable_aspm, "Enable ASPM");
> +module_param(enable_aldps, int, 0); MODULE_PARM_DESC(enable_aldps,
> +"Enable ALDPS");
> module_param(use_dac, int, 0);
> MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI
> slot."); module_param_named(debug, debug.msg_enable, int, 0); @@
> -1567,25 +1573,6 @@ static void rtl_link_chg_patch(struct
> rtl8169_private *tp)
> }
> }
>
> -static void rtl8169_check_link_status(struct net_device *dev,
> - struct rtl8169_private *tp)
> -{
> - struct device *d = tp_to_dev(tp);
> -
> - if (tp->link_ok(tp)) {
> - rtl_link_chg_patch(tp);
> - /* This is to cancel a scheduled suspend if there's one. */
> - pm_request_resume(d);
> - netif_carrier_on(dev);
> - if (net_ratelimit())
> - netif_info(tp, ifup, dev, "link up\n");
> - } else {
> - netif_carrier_off(dev);
> - netif_info(tp, ifdown, dev, "link down\n");
> - pm_runtime_idle(d);
> - }
> -}
> -
> #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST |
> WAKE_MCAST)
>
> static u32 __rtl8169_get_wol(struct rtl8169_private *tp) @@ -3520,6
> +3507,15 @@ static void rtl8168e_1_hw_phy_config(struct
> rtl8169_private *tp)
> rtl_writephy(tp, 0x0d, 0x4007);
> rtl_writephy(tp, 0x0e, 0x0000);
> rtl_writephy(tp, 0x0d, 0x0000);
> +
> + /* Check ALDPS bit, disable it if enabled */
> + rtl_writephy(tp, 0x1f, 0x0000);
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x15, 0x1000, 0x0000);
> + else if (rtl_readphy(tp, 0x15) & 0x1000)
> + rtl_w0w1_phy(tp, 0x15, 0x0000, 0x1000);
> +
> + rtl_writephy(tp, 0x1f, 0x0000);
> }
>
> static void rtl_rar_exgmac_set(struct rtl8169_private *tp, u8 *addr)
> @@ -3627,6 +3623,15 @@ static void rtl8168e_2_hw_phy_config(struct
> rtl8169_private *tp)
>
> /* Broken BIOS workaround: feed GigaMAC registers with MAC address. */
> rtl_rar_exgmac_set(tp, tp->dev->dev_addr);
> +
> + /* Check ALDPS bit, disable it if enabled */
> + rtl_writephy(tp, 0x1f, 0x0000);
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x15, 0x1000, 0x0000);
> + else if (rtl_readphy(tp, 0x15) & 0x1000)
> + rtl_w0w1_phy(tp, 0x15, 0x0000, 0x1000);
> +
> + rtl_writephy(tp, 0x1f, 0x0000);
> }
>
> static void rtl8168f_hw_phy_config(struct rtl8169_private *tp) @@
> -3649,6 +3654,15 @@ static void rtl8168f_hw_phy_config(struct
> rtl8169_private *tp)
> rtl_writephy(tp, 0x05, 0x8b86);
> rtl_w0w1_phy(tp, 0x06, 0x0001, 0x0000);
> rtl_writephy(tp, 0x1f, 0x0000);
> +
> + /* Check ALDPS bit, disable it if enabled */
> + rtl_writephy(tp, 0x1f, 0x0000);
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x15, 0x1000, 0x0000);
> + else if (rtl_readphy(tp, 0x15) & 0x1000)
> + rtl_w0w1_phy(tp, 0x15, 0x0000, 0x1000);
> +
> + rtl_writephy(tp, 0x1f, 0x0000);
> }
>
> static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp) @@
> -3865,7 +3879,9 @@ static void rtl8168g_1_hw_phy_config(struct
> rtl8169_private *tp)
>
> /* Check ALDPS bit, disable it if enabled */
> rtl_writephy(tp, 0x1f, 0x0a43);
> - if (rtl_readphy(tp, 0x10) & 0x0004)
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x10, 0x0004, 0x0000);
> + else if (rtl_readphy(tp, 0x10) & 0x0004)
> rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
>
> rtl_writephy(tp, 0x1f, 0x0000);
> @@ -3874,6 +3890,14 @@ static void rtl8168g_1_hw_phy_config(struct
> rtl8169_private *tp) static void rtl8168g_2_hw_phy_config(struct
> rtl8169_private *tp) {
> rtl_apply_firmware(tp);
> +
> + rtl_writephy(tp, 0x1f, 0x0a43);
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x10, 0x0004, 0x0000);
> + else if (rtl_readphy(tp, 0x10) & 0x0004)
> + rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
> +
> + rtl_writephy(tp, 0x1f, 0x0000);
> }
>
> static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp) @@
> -3980,7 +4004,9 @@ static void rtl8168h_1_hw_phy_config(struct
> rtl8169_private *tp)
>
> /* Check ALDPS bit, disable it if enabled */
> rtl_writephy(tp, 0x1f, 0x0a43);
> - if (rtl_readphy(tp, 0x10) & 0x0004)
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x10, 0x0004, 0x0000);
> + else if (rtl_readphy(tp, 0x10) & 0x0004)
> rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
>
> rtl_writephy(tp, 0x1f, 0x0000);
> @@ -4053,7 +4079,9 @@ static void rtl8168h_2_hw_phy_config(struct
> rtl8169_private *tp)
>
> /* Check ALDPS bit, disable it if enabled */
> rtl_writephy(tp, 0x1f, 0x0a43);
> - if (rtl_readphy(tp, 0x10) & 0x0004)
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x10, 0x0004, 0x0000);
> + else if (rtl_readphy(tp, 0x10) & 0x0004)
> rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
>
> rtl_writephy(tp, 0x1f, 0x0000);
> @@ -4095,7 +4123,9 @@ static void rtl8168ep_1_hw_phy_config(struct
> rtl8169_private *tp)
>
> /* Check ALDPS bit, disable it if enabled */
> rtl_writephy(tp, 0x1f, 0x0a43);
> - if (rtl_readphy(tp, 0x10) & 0x0004)
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x10, 0x0004, 0x0000);
> + else if (rtl_readphy(tp, 0x10) & 0x0004)
> rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
>
> rtl_writephy(tp, 0x1f, 0x0000);
> @@ -4186,7 +4216,9 @@ static void rtl8168ep_2_hw_phy_config(struct
> rtl8169_private *tp)
>
> /* Check ALDPS bit, disable it if enabled */
> rtl_writephy(tp, 0x1f, 0x0a43);
> - if (rtl_readphy(tp, 0x10) & 0x0004)
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x10, 0x0004, 0x0000);
> + else if (rtl_readphy(tp, 0x10) & 0x0004)
> rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
>
> rtl_writephy(tp, 0x1f, 0x0000);
> @@ -4233,6 +4265,15 @@ static void rtl8105e_hw_phy_config(struct
> rtl8169_private *tp)
> rtl_apply_firmware(tp);
>
> rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
> +
> + /* Check ALDPS bit, disable it if enabled */
> + rtl_writephy(tp, 0x1f, 0x0000);
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x18, 0x1000, 0x0000);
> + else if (rtl_readphy(tp, 0x18) & 0x1000)
> + rtl_w0w1_phy(tp, 0x18, 0x0000, 0x1000);
> +
> + rtl_writephy(tp, 0x1f, 0x0000);
> }
>
> static void rtl8402_hw_phy_config(struct rtl8169_private *tp) @@
> -4250,6 +4291,15 @@ static void rtl8402_hw_phy_config(struct
> rtl8169_private *tp)
> rtl_writephy(tp, 0x10, 0x401f);
> rtl_writephy(tp, 0x19, 0x7030);
> rtl_writephy(tp, 0x1f, 0x0000);
> +
> + /* Check ALDPS bit, disable it if enabled */
> + rtl_writephy(tp, 0x1f, 0x0000);
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x18, 0x1000, 0x0000);
> + else if (rtl_readphy(tp, 0x18) & 0x1000)
> + rtl_w0w1_phy(tp, 0x18, 0x0000, 0x1000);
> +
> + rtl_writephy(tp, 0x1f, 0x0000);
> }
>
> static void rtl8106e_hw_phy_config(struct rtl8169_private *tp) @@
> -4272,6 +4322,15 @@ static void rtl8106e_hw_phy_config(struct
> rtl8169_private *tp)
> rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
>
> rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
> +
> + /* Check ALDPS bit, disable it if enabled */
> + rtl_writephy(tp, 0x1f, 0x0000);
> + if (enable_aldps)
> + rtl_w0w1_phy(tp, 0x18, 0x1000, 0x0000);
> + else if (rtl_readphy(tp, 0x18) & 0x1000)
> + rtl_w0w1_phy(tp, 0x18, 0x0000, 0x1000);
> +
> + rtl_writephy(tp, 0x1f, 0x0000);
> }
>
> static void rtl_hw_phy_config(struct net_device *dev) @@ -5290,6
> +5349,18 @@ static void rtl_pcie_state_l2l3_enable(struct
> rtl8169_private *tp, bool enable)
> RTL_W8(tp, Config3, data);
> }
>
> +static void rtl_hw_internal_aspm_clkreq_enable(struct rtl8169_private *tp,
> + bool enable)
> +{
> + if (enable) {
> + RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
> + RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
> + } else {
> + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> + }
> +}
> +
> static void rtl_hw_start_8168bb(struct rtl8169_private *tp) {
> RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); @@ -5646,9
> +5717,10 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private
> *tp)
> rtl_hw_start_8168g(tp);
>
> /* disable aspm and clock request before access ephy */
> - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> + rtl_hw_internal_aspm_clkreq_enable(tp, false);
> rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1));
> + if (enable_aspm)
> + rtl_hw_internal_aspm_clkreq_enable(tp, true);
> }
>
> static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) @@
> -5681,9 +5753,10 @@ static void rtl_hw_start_8411_2(struct
> rtl8169_private *tp)
> rtl_hw_start_8168g(tp);
>
> /* disable aspm and clock request before access ephy */
> - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> + rtl_hw_internal_aspm_clkreq_enable(tp, false);
> rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2));
> + if (enable_aspm)
> + rtl_hw_internal_aspm_clkreq_enable(tp, true);
> }
>
> static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) @@
> -5700,8 +5773,7 @@ static void rtl_hw_start_8168h_1(struct
> rtl8169_private *tp)
> };
>
> /* disable aspm and clock request before access ephy */
> - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> + rtl_hw_internal_aspm_clkreq_enable(tp, false);
> rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1));
>
> RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); @@
> -5780,6 +5852,9 @@ static void rtl_hw_start_8168h_1(struct
> rtl8169_private *tp)
> r8168_mac_ocp_write(tp, 0xe63e, 0x0000);
> r8168_mac_ocp_write(tp, 0xc094, 0x0000);
> r8168_mac_ocp_write(tp, 0xc09e, 0x0000);
> +
> + if (enable_aspm)
> + rtl_hw_internal_aspm_clkreq_enable(tp, true);
> }
>
> static void rtl_hw_start_8168ep(struct rtl8169_private *tp) @@
> -5831,11 +5906,13 @@ static void rtl_hw_start_8168ep_1(struct
> rtl8169_private *tp)
> };
>
> /* disable aspm and clock request before access ephy */
> - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> + rtl_hw_internal_aspm_clkreq_enable(tp, false);
> rtl_ephy_init(tp, e_info_8168ep_1, ARRAY_SIZE(e_info_8168ep_1));
>
> rtl_hw_start_8168ep(tp);
> +
> + if (enable_aspm)
> + rtl_hw_internal_aspm_clkreq_enable(tp, true);
> }
>
> static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) @@
> -5847,14 +5924,16 @@ static void rtl_hw_start_8168ep_2(struct
> rtl8169_private *tp)
> };
>
> /* disable aspm and clock request before access ephy */
> - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> + rtl_hw_internal_aspm_clkreq_enable(tp, false);
> rtl_ephy_init(tp, e_info_8168ep_2, ARRAY_SIZE(e_info_8168ep_2));
>
> rtl_hw_start_8168ep(tp);
>
> RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
> RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN);
> +
> + if (enable_aspm)
> + rtl_hw_internal_aspm_clkreq_enable(tp, true);
> }
>
> static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) @@
> -5868,8 +5947,7 @@ static void rtl_hw_start_8168ep_3(struct
> rtl8169_private *tp)
> };
>
> /* disable aspm and clock request before access ephy */
> - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> + rtl_hw_internal_aspm_clkreq_enable(tp, false);
> rtl_ephy_init(tp, e_info_8168ep_3, ARRAY_SIZE(e_info_8168ep_3));
>
> rtl_hw_start_8168ep(tp);
> @@ -5889,6 +5967,9 @@ static void rtl_hw_start_8168ep_3(struct
> rtl8169_private *tp)
> data = r8168_mac_ocp_read(tp, 0xe860);
> data |= 0x0080;
> r8168_mac_ocp_write(tp, 0xe860, data);
> +
> + if (enable_aspm)
> + rtl_hw_internal_aspm_clkreq_enable(tp, true);
> }
>
> static void rtl_hw_start_8168(struct rtl8169_private *tp) @@ -6364,7
> +6445,7 @@ static void rtl8169_tx_clear(struct rtl8169_private
> *tp)
> tp->cur_tx = tp->dirty_tx = 0;
> }
>
> -static void rtl_reset_work(struct rtl8169_private *tp)
> +static void _rtl_reset_work(struct rtl8169_private *tp)
> {
> struct net_device *dev = tp->dev;
> int i;
> @@ -6384,6 +6465,33 @@ static void rtl_reset_work(struct
> rtl8169_private
> *tp)
> napi_enable(&tp->napi);
> rtl_hw_start(tp);
> netif_wake_queue(dev);
> +}
> +
> +static void rtl8169_check_link_status(struct net_device *dev,
> + struct rtl8169_private *tp) {
> + struct device *d = tp_to_dev(tp);
> +
> + if (tp->link_ok(tp)) {
> + rtl_link_chg_patch(tp);
> + /* This is to cancel a scheduled suspend if there's one. */
> + if (pm_request_resume(d))
> + _rtl_reset_work(tp);
> + netif_carrier_on(dev);
> + if (net_ratelimit())
> + netif_info(tp, ifup, dev, "link up\n");
> + } else {
> + netif_carrier_off(dev);
> + netif_info(tp, ifdown, dev, "link down\n");
> + pm_runtime_idle(d);
> + }
> +}
> +
> +static void rtl_reset_work(struct rtl8169_private *tp) {
> + struct net_device *dev = tp->dev;
> +
> + _rtl_reset_work(tp);
> rtl8169_check_link_status(dev, tp);
> }
>
> @@ -7649,8 +7757,12 @@ static int rtl_init_one(struct pci_dev *pdev,
> const struct pci_device_id *ent)
>
> /* disable ASPM completely as that cause random device stop working
> * problems as well as full system hangs for some PCIe devices users */
> - pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
> - PCIE_LINK_STATE_CLKPM);
> + if (!enable_aspm) {
> + pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
> + PCIE_LINK_STATE_L1 |
> + PCIE_LINK_STATE_CLKPM);
> + netif_info(tp, probe, dev, "ASPM disabled\n");
> + }
>
> /* enable device (incl. PCI PM wakeup and hotplug setup) */
> rc = pcim_enable_device(pdev);
> --
> 2.17.0
------Please consider the environment before printing this e-mail.
^ permalink raw reply
* Re: [PATCH net-next 0/2] net: phy: improve PM handling of PHY/MDIO
From: Heiner Kallweit @ 2018-06-05 6:08 UTC (permalink / raw)
To: Andrew Lunn; +Cc: Florian Fainelli, David Miller, netdev@vger.kernel.org
In-Reply-To: <20180604214829.GA14873@lunn.ch>
On 04.06.2018 23:48, Andrew Lunn wrote:
> On Sat, Jun 02, 2018 at 10:33:36PM +0200, Heiner Kallweit wrote:
>> Current implementation of MDIO bus PM ops doesn't actually implement
>> bus-specific PM ops but just calls PM ops defined on a device level
>> what doesn't seem to be fully in line with the core PM model.
>>
>> When looking e.g. at __device_suspend() the PM core looks for PM ops
>> of a device in a specific order:
>> 1. device PM domain
>> 2. device type
>> 3. device class
>> 4. device bus
>>
>> I think it has good reason that there's no PM ops on device level.
>> The situation can be improved by modeling PHY's as device type of
>> a MDIO device. If for some other type of MDIO device PM ops are
>> needed, it could be modeled as struct device_type as well.
>
> Hi Heiner
>
> I tested that the files in /sys/class/bus/mdio/devices/* are still
> there. And also not there for MDIO devices which are not PHYs,
> e.g. Ethernet switches.
>
> I don't have any boards which do PM. So i cannot test suspend/resume.
>
Thanks for reviewing! I tested suspend / resume by manually suspending
via "systemctl suspend" and resuming via power button or WoL.
The only behavior change I expect is an additional parameter in the PHY
udev calls, see following comment in device.h: If "name" is specified,
the uevent will contain it in the DEVTYPE variable.
This however shouldn't have any impact.
Heiner
> I also took a look at drivers/net/dsa/qca8k.c. This is an MDIO switch
> which has PM operations. I don't think this change will break it.
>
> I would prefer a bit more testing, but i guess that is what -rc
> kernels are for.
>
> Tested-by: Andrew Lunn <andrew@lunn.ch>
>
> Andrew
> .
>
^ permalink raw reply
* Re: [PATCH net-next 3/3] mlxsw: Add extack messages for port_{un,}split failures
From: Ido Schimmel @ 2018-06-05 5:56 UTC (permalink / raw)
To: dsahern; +Cc: netdev, idosch, jiri, jakub.kicinski, David Ahern
In-Reply-To: <20180604221503.20329-4-dsahern@kernel.org>
On Mon, Jun 04, 2018 at 03:15:03PM -0700, dsahern@kernel.org wrote:
> From: David Ahern <dsahern@gmail.com>
>
> Return messages in extack for port split/unsplit errors. e.g.,
> $ devlink port split swp1s1 count 4
> Error: mlxsw_spectrum: Port cannot be split further.
> devlink answers: Invalid argument
>
> $ devlink port unsplit swp4
> Error: mlxsw_spectrum: Port was not split.
> devlink answers: Invalid argument
>
> Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Thanks!
^ permalink raw reply
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