From 23a1f8d44c0bca48f04fc2a2f1edafd826ce6133 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 8 Dec 2015 16:04:31 +0200 Subject: mac80211: process and save VHT MU-MIMO group frame The Group ID Management frame is an Action frame of category VHT. It is transmitted by the AP to assign or change the user position of a STA for one or more group IDs. Process and save the group membership data. Notify underlying driver of changes. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 452c0b0d2f32..d9ddb89533a7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -843,6 +843,8 @@ enum ieee80211_vht_opmode_bits { }; #define WLAN_SA_QUERY_TR_ID_LEN 2 +#define WLAN_MEMBERSHIP_LEN 8 +#define WLAN_USER_POSITION_LEN 16 /** * struct ieee80211_tpc_report_ie @@ -989,6 +991,11 @@ struct ieee80211_mgmt { u8 action_code; u8 operating_mode; } __packed vht_opmode_notif; + struct { + u8 action_code; + u8 membership[WLAN_MEMBERSHIP_LEN]; + u8 position[WLAN_USER_POSITION_LEN]; + } __packed vht_group_notif; struct { u8 action_code; u8 dialog_token; -- cgit v1.2.3 From 6e7333d315a768170a59ac771297ee0551bdddbf Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 1 Feb 2016 18:51:05 -0500 Subject: net: add rx_nohandler stat counter This adds an rx_nohandler stat counter, along with a sysfs statistics node, and copies the counter out via netlink as well. CC: "David S. Miller" CC: Eric Dumazet CC: Jiri Pirko CC: Daniel Borkmann CC: Tom Herbert CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ include/uapi/linux/if_link.h | 4 ++++ net/core/dev.c | 6 +++++- net/core/net-sysfs.c | 2 ++ net/core/rtnetlink.c | 2 ++ 5 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 289c2314d766..78a20cec2a0a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1397,6 +1397,8 @@ enum netdev_priv_flags { * do not use this in drivers * @tx_dropped: Dropped packets by core network, * do not use this in drivers + * @rx_nohandler: nohandler dropped packets by core network on + * inactive devices, do not use this in drivers * * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, @@ -1611,6 +1613,7 @@ struct net_device { atomic_long_t rx_dropped; atomic_long_t tx_dropped; + atomic_long_t rx_nohandler; #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def * wireless_handlers; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a30b78090594..d3e90b91e07e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -35,6 +35,8 @@ struct rtnl_link_stats { /* for cslip etc */ __u32 rx_compressed; __u32 tx_compressed; + + __u32 rx_nohandler; /* dropped, no handler found */ }; /* The main device statistics structure */ @@ -68,6 +70,8 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; + + __u64 rx_nohandler; /* dropped, no handler found */ }; /* The struct should be in sync with struct ifmap */ diff --git a/net/core/dev.c b/net/core/dev.c index 65863e512227..f1284835b8c9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4154,7 +4154,10 @@ ncls: ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { drop: - atomic_long_inc(&skb->dev->rx_dropped); + if (!deliver_exact) + atomic_long_inc(&skb->dev->rx_dropped); + else + atomic_long_inc(&skb->dev->rx_nohandler); kfree_skb(skb); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) @@ -7307,6 +7310,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } storage->rx_dropped += atomic_long_read(&dev->rx_dropped); storage->tx_dropped += atomic_long_read(&dev->tx_dropped); + storage->rx_nohandler += atomic_long_read(&dev->rx_nohandler); return storage; } EXPORT_SYMBOL(dev_get_stats); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index b6c8a6629b39..da7dbc237a5f 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -574,6 +574,7 @@ NETSTAT_ENTRY(tx_heartbeat_errors); NETSTAT_ENTRY(tx_window_errors); NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); +NETSTAT_ENTRY(rx_nohandler); static struct attribute *netstat_attrs[] = { &dev_attr_rx_packets.attr, @@ -599,6 +600,7 @@ static struct attribute *netstat_attrs[] = { &dev_attr_tx_window_errors.attr, &dev_attr_rx_compressed.attr, &dev_attr_tx_compressed.attr, + &dev_attr_rx_nohandler.attr, NULL }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d735e854f916..20d71358c143 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -804,6 +804,8 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->rx_compressed = b->rx_compressed; a->tx_compressed = b->tx_compressed; + + a->rx_nohandler = b->rx_nohandler; } static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) -- cgit v1.2.3 From bb63daf9efb4f2bcb657d7179a53bd808f978dc9 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 1 Feb 2016 18:51:06 -0500 Subject: team: track sum of rx_nohandler for all slaves CC: Jiri Pirko CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- drivers/net/team/team.c | 10 +++++++--- include/linux/if_team.h | 1 + 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 718ceeab4dbc..00558e139584 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -758,6 +758,8 @@ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) u64_stats_update_end(&pcpu_stats->syncp); skb->dev = team->dev; + } else if (res == RX_HANDLER_EXACT) { + this_cpu_inc(team->pcpu_stats->rx_nohandler); } else { this_cpu_inc(team->pcpu_stats->rx_dropped); } @@ -1807,7 +1809,7 @@ team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) struct team *team = netdev_priv(dev); struct team_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; - u32 rx_dropped = 0, tx_dropped = 0; + u32 rx_dropped = 0, tx_dropped = 0, rx_nohandler = 0; unsigned int start; int i; @@ -1828,14 +1830,16 @@ team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* - * rx_dropped & tx_dropped are u32, updated - * without syncp protection. + * rx_dropped, tx_dropped & rx_nohandler are u32, + * updated without syncp protection. */ rx_dropped += p->rx_dropped; tx_dropped += p->tx_dropped; + rx_nohandler += p->rx_nohandler; } stats->rx_dropped = rx_dropped; stats->tx_dropped = tx_dropped; + stats->rx_nohandler = rx_nohandler; return stats; } diff --git a/include/linux/if_team.h b/include/linux/if_team.h index b84e49c3a738..174f43f43aff 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -24,6 +24,7 @@ struct team_pcpu_stats { struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; + u32 rx_nohandler; }; struct team; -- cgit v1.2.3 From ba905f5e2f63d86ed4cfbd3d9096fb28d156f1ee Mon Sep 17 00:00:00 2001 From: Kim Jones Date: Tue, 2 Feb 2016 03:51:16 +0000 Subject: ethtool: Declare netdev_rss_key as __read_mostly. netdev_rss_key is written to once and thereafter is read by drivers when they are initialising. The fact that it is mostly read and not written to makes it a candidate for a __read_mostly declaration. Signed-off-by: Kim Jones Signed-off-by: Alan Carey Acked-by: Rami Rosen Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/ethtool.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 78a20cec2a0a..219f53c30cb3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3744,7 +3744,7 @@ void netdev_lower_state_changed(struct net_device *lower_dev, /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 -extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN]; +extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index daf04709dd3c..453c803f1c87 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -632,7 +632,7 @@ static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr, return 0; } -u8 netdev_rss_key[NETDEV_RSS_KEY_LEN]; +u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len) { -- cgit v1.2.3 From a10423b87a7eae75da79ce80a8d9475047a674ee Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Feb 2016 22:39:54 -0800 Subject: bpf: introduce BPF_MAP_TYPE_PERCPU_ARRAY map Primary use case is a histogram array of latency where bpf program computes the latency of block requests or other events and stores histogram of latency into array of 64 elements. All cpus are constantly running, so normal increment is not accurate, bpf_xadd causes cache ping-pong and this per-cpu approach allows fastest collision-free counters. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/arraymap.c | 102 ++++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 93 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 83d1926c61e4..141fb0d45731 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -151,6 +151,7 @@ struct bpf_array { union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); + void __percpu *pptrs[0] __aligned(8); }; }; #define MAX_TAIL_CALL_CNT 32 diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ae40c8763e..2ee0fde1bf96 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -82,6 +82,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PROG_ARRAY, BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, }; enum bpf_prog_type { diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 89ebbc4d1164..b9bf1d7949ca 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -17,11 +17,39 @@ #include #include +static void bpf_array_free_percpu(struct bpf_array *array) +{ + int i; + + for (i = 0; i < array->map.max_entries; i++) + free_percpu(array->pptrs[i]); +} + +static int bpf_array_alloc_percpu(struct bpf_array *array) +{ + void __percpu *ptr; + int i; + + for (i = 0; i < array->map.max_entries; i++) { + ptr = __alloc_percpu_gfp(array->elem_size, 8, + GFP_USER | __GFP_NOWARN); + if (!ptr) { + bpf_array_free_percpu(array); + return -ENOMEM; + } + array->pptrs[i] = ptr; + } + + return 0; +} + /* Called from syscall */ static struct bpf_map *array_map_alloc(union bpf_attr *attr) { + bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; struct bpf_array *array; - u32 elem_size, array_size; + u64 array_size; + u32 elem_size; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -36,12 +64,16 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) elem_size = round_up(attr->value_size, 8); - /* check round_up into zero and u32 overflow */ - if (elem_size == 0 || - attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size) + array_size = sizeof(*array); + if (percpu) + array_size += (u64) attr->max_entries * sizeof(void *); + else + array_size += (u64) attr->max_entries * elem_size; + + /* make sure there is no u32 overflow later in round_up() */ + if (array_size >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); - array_size = sizeof(*array) + attr->max_entries * elem_size; /* allocate all map elements and zero-initialize them */ array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); @@ -52,12 +84,25 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) } /* copy mandatory map attributes */ + array->map.map_type = attr->map_type; array->map.key_size = attr->key_size; array->map.value_size = attr->value_size; array->map.max_entries = attr->max_entries; - array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT; array->elem_size = elem_size; + if (!percpu) + goto out; + + array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); + + if (array_size >= U32_MAX - PAGE_SIZE || + elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { + kvfree(array); + return ERR_PTR(-ENOMEM); + } +out: + array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT; + return &array->map; } @@ -67,12 +112,24 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; - if (index >= array->map.max_entries) + if (unlikely(index >= array->map.max_entries)) return NULL; return array->value + array->elem_size * index; } +/* Called from eBPF program */ +static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + + if (unlikely(index >= array->map.max_entries)) + return NULL; + + return this_cpu_ptr(array->pptrs[index]); +} + /* Called from syscall */ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { @@ -99,19 +156,24 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; - if (map_flags > BPF_EXIST) + if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; - if (index >= array->map.max_entries) + if (unlikely(index >= array->map.max_entries)) /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; - if (map_flags == BPF_NOEXIST) + if (unlikely(map_flags == BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; - memcpy(array->value + array->elem_size * index, value, map->value_size); + if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + memcpy(this_cpu_ptr(array->pptrs[index]), + value, map->value_size); + else + memcpy(array->value + array->elem_size * index, + value, map->value_size); return 0; } @@ -133,6 +195,9 @@ static void array_map_free(struct bpf_map *map) */ synchronize_rcu(); + if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + bpf_array_free_percpu(array); + kvfree(array); } @@ -150,9 +215,24 @@ static struct bpf_map_type_list array_type __read_mostly = { .type = BPF_MAP_TYPE_ARRAY, }; +static const struct bpf_map_ops percpu_array_ops = { + .map_alloc = array_map_alloc, + .map_free = array_map_free, + .map_get_next_key = array_map_get_next_key, + .map_lookup_elem = percpu_array_map_lookup_elem, + .map_update_elem = array_map_update_elem, + .map_delete_elem = array_map_delete_elem, +}; + +static struct bpf_map_type_list percpu_array_type __read_mostly = { + .ops = &percpu_array_ops, + .type = BPF_MAP_TYPE_PERCPU_ARRAY, +}; + static int __init register_array_map(void) { bpf_register_map_type(&array_type); + bpf_register_map_type(&percpu_array_type); return 0; } late_initcall(register_array_map); -- cgit v1.2.3 From 15a07b33814d14ca817887dbea8530728dc0fbe4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 1 Feb 2016 22:39:55 -0800 Subject: bpf: add lookup/update support for per-cpu hash and array maps The functions bpf_map_lookup_elem(map, key, value) and bpf_map_update_elem(map, key, value, flags) need to get/set values from all-cpus for per-cpu hash and array maps, so that user space can aggregate/update them as necessary. Example of single counter aggregation in user space: unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); long values[nr_cpus]; long value = 0; bpf_lookup_elem(fd, key, values); for (i = 0; i < nr_cpus; i++) value += values[i]; The user space must provide round_up(value_size, 8) * nr_cpus array to get/set values, since kernel will use 'long' copy of per-cpu values to try to copy good counters atomically. It's a best-effort, since bpf programs and user space are racing to access the same memory. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 23 ++++++++++++++ kernel/bpf/arraymap.c | 64 +++++++++++++++++++++++++++++++++++++++ kernel/bpf/hashtab.c | 83 +++++++++++++++++++++++++++++++++++++++++++++------ kernel/bpf/syscall.c | 57 ++++++++++++++++++++++++----------- 4 files changed, 201 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 141fb0d45731..90ee6ab24bc5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -183,6 +183,29 @@ int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname); +int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, + u64 flags); +int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, + u64 flags); + +/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and + * forced to use 'long' read/writes to try to atomically copy long counters. + * Best-effort only. No barriers here, since it _will_ race with concurrent + * updates from BPF programs. Called from bpf syscall and mostly used with + * size 8 or 16 bytes, so ask compiler to inline it. + */ +static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) +{ + const long *lsrc = src; + long *ldst = dst; + + size /= sizeof(long); + while (size--) + *ldst++ = *lsrc++; +} + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b9bf1d7949ca..bd3bdf2486a7 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -130,6 +130,32 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) return this_cpu_ptr(array->pptrs[index]); } +int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + void __percpu *pptr; + int cpu, off = 0; + u32 size; + + if (unlikely(index >= array->map.max_entries)) + return -ENOENT; + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(map->value_size, 8); + rcu_read_lock(); + pptr = array->pptrs[index]; + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size); + off += size; + } + rcu_read_unlock(); + return 0; +} + /* Called from syscall */ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { @@ -177,6 +203,44 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return 0; } +int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + void __percpu *pptr; + int cpu, off = 0; + u32 size; + + if (unlikely(map_flags > BPF_EXIST)) + /* unknown flags */ + return -EINVAL; + + if (unlikely(index >= array->map.max_entries)) + /* all elements were pre-allocated, cannot insert a new one */ + return -E2BIG; + + if (unlikely(map_flags == BPF_NOEXIST)) + /* all elements already exist */ + return -EEXIST; + + /* the user space will provide round_up(value_size, 8) bytes that + * will be copied into per-cpu area. bpf programs can only access + * value_size of it. During lookup the same extra bytes will be + * returned or zeros which were zero-filled by percpu_alloc, + * so no kernel data leaks possible + */ + size = round_up(map->value_size, 8); + rcu_read_lock(); + pptr = array->pptrs[index]; + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size); + off += size; + } + rcu_read_unlock(); + return 0; +} + /* Called from syscall or from eBPF program */ static int array_map_delete_elem(struct bpf_map *map, void *key) { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 2be5f6e8bb04..fd5db8fe9360 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -290,7 +290,7 @@ static void free_htab_elem(struct htab_elem *l, bool percpu, u32 key_size) static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, - bool percpu) + bool percpu, bool onallcpus) { u32 size = htab->map.value_size; struct htab_elem *l_new; @@ -312,8 +312,18 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, return NULL; } - /* copy true value_size bytes */ - memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + if (!onallcpus) { + /* copy true value_size bytes */ + memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); + } else { + int off = 0, cpu; + + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), + value + off, size); + off += size; + } + } htab_elem_set_ptr(l_new, key_size, pptr); } else { memcpy(l_new->key + round_up(key_size, 8), value, size); @@ -368,7 +378,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* allocate new element outside of the lock, since * we're most likley going to insert it */ - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false); + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); if (!l_new) return -ENOMEM; @@ -402,8 +412,9 @@ err: return ret; } -static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags, + bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; @@ -436,12 +447,25 @@ static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, goto err; if (l_old) { + void __percpu *pptr = htab_elem_get_ptr(l_old, key_size); + u32 size = htab->map.value_size; + /* per-cpu hash map can update value in-place */ - memcpy(this_cpu_ptr(htab_elem_get_ptr(l_old, key_size)), - value, htab->map.value_size); + if (!onallcpus) { + memcpy(this_cpu_ptr(pptr), value, size); + } else { + int off = 0, cpu; + + size = round_up(size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), + value + off, size); + off += size; + } + } } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true); + hash, true, onallcpus); if (!l_new) { ret = -ENOMEM; goto err; @@ -455,6 +479,12 @@ err: return ret; } +static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + return __htab_percpu_map_update_elem(map, key, value, map_flags, false); +} + /* Called from syscall or from eBPF program */ static int htab_map_delete_elem(struct bpf_map *map, void *key) { @@ -557,6 +587,41 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) +{ + struct htab_elem *l; + void __percpu *pptr; + int ret = -ENOENT; + int cpu, off = 0; + u32 size; + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(map->value_size, 8); + rcu_read_lock(); + l = __htab_map_lookup_elem(map, key); + if (!l) + goto out; + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(pptr, cpu), size); + off += size; + } + ret = 0; +out: + rcu_read_unlock(); + return ret; +} + +int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __htab_percpu_map_update_elem(map, key, value, map_flags, true); +} + static const struct bpf_map_ops htab_percpu_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 637397059f76..c95a753c2007 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -239,6 +239,7 @@ static int map_lookup_elem(union bpf_attr *attr) int ufd = attr->map_fd; struct bpf_map *map; void *key, *value, *ptr; + u32 value_size; struct fd f; int err; @@ -259,23 +260,35 @@ static int map_lookup_elem(union bpf_attr *attr) if (copy_from_user(key, ukey, map->key_size) != 0) goto free_key; + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + value_size = round_up(map->value_size, 8) * num_possible_cpus(); + else + value_size = map->value_size; + err = -ENOMEM; - value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; - rcu_read_lock(); - ptr = map->ops->map_lookup_elem(map, key); - if (ptr) - memcpy(value, ptr, map->value_size); - rcu_read_unlock(); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { + err = bpf_percpu_hash_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_copy(map, key, value); + } else { + rcu_read_lock(); + ptr = map->ops->map_lookup_elem(map, key); + if (ptr) + memcpy(value, ptr, value_size); + rcu_read_unlock(); + err = ptr ? 0 : -ENOENT; + } - err = -ENOENT; - if (!ptr) + if (err) goto free_value; err = -EFAULT; - if (copy_to_user(uvalue, value, map->value_size) != 0) + if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; err = 0; @@ -298,6 +311,7 @@ static int map_update_elem(union bpf_attr *attr) int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; + u32 value_size; struct fd f; int err; @@ -318,21 +332,30 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(key, ukey, map->key_size) != 0) goto free_key; + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + value_size = round_up(map->value_size, 8) * num_possible_cpus(); + else + value_size = map->value_size; + err = -ENOMEM; - value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -EFAULT; - if (copy_from_user(value, uvalue, map->value_size) != 0) + if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; - /* eBPF program that use maps are running under rcu_read_lock(), - * therefore all map accessors rely on this fact, so do the same here - */ - rcu_read_lock(); - err = map->ops->map_update_elem(map, key, value, attr->flags); - rcu_read_unlock(); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { + err = bpf_percpu_hash_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_update(map, key, value, attr->flags); + } else { + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, attr->flags); + rcu_read_unlock(); + } free_value: kfree(value); -- cgit v1.2.3 From 7267bcda332e2782e21a559f3b1b859a35b4062d Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Sat, 16 Jan 2016 00:48:52 +0100 Subject: bcma: identify bus cores (devices) found on BCM47189 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing defines and print proper names. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- drivers/bcma/scan.c | 3 +++ include/linux/bcma/bcma.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c index df806b9c5490..5ee731132365 100644 --- a/drivers/bcma/scan.c +++ b/drivers/bcma/scan.c @@ -98,6 +98,9 @@ static const struct bcma_device_id_name bcma_bcm_device_names[] = { { BCMA_CORE_SHIM, "SHIM" }, { BCMA_CORE_PCIE2, "PCIe Gen2" }, { BCMA_CORE_ARM_CR4, "ARM CR4" }, + { BCMA_CORE_GCI, "GCI" }, + { BCMA_CORE_CMEM, "CNDS DDR2/3 memory controller" }, + { BCMA_CORE_ARM_CA7, "ARM CA7" }, { BCMA_CORE_DEFAULT, "Default" }, }; diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 3feb1b2d75d8..991ebb4c2015 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -151,6 +151,8 @@ struct bcma_host_ops { #define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */ #define BCMA_CORE_USB30_DEV 0x83D #define BCMA_CORE_ARM_CR4 0x83E +#define BCMA_CORE_GCI 0x840 +#define BCMA_CORE_CMEM 0x846 /* CNDS DDR2/3 memory controller */ #define BCMA_CORE_ARM_CA7 0x847 #define BCMA_CORE_SYS_MEM 0x849 #define BCMA_CORE_DEFAULT 0xFFF -- cgit v1.2.3 From 67edf354faaf93156646e741483b2313bc756c0f Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Tue, 19 Jan 2016 08:45:25 +0100 Subject: bcma: use _PMU_ in all names of PMU registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PMU (Power Management Unit) seems to be a separated piece of hardware, just accessed using ChipCommon core registers. In recent Broadcom chipsets PMU is not bounded to CC but available as separated core. To make code cleaner & easier to review (for a correct R/W access) use clearer names. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- drivers/bcma/driver_chipcommon_pmu.c | 46 ++++++++++++++--------------- drivers/net/wireless/broadcom/b43/main.c | 8 ++--- include/linux/bcma/bcma_driver_chipcommon.h | 12 ++++---- 3 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index fe0d48cb1778..472f39dc5a38 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -15,44 +15,44 @@ u32 bcma_chipco_pll_read(struct bcma_drv_cc *cc, u32 offset) { - bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PLLCTL_ADDR); - return bcma_cc_read32(cc, BCMA_CC_PLLCTL_DATA); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); + return bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); } EXPORT_SYMBOL_GPL(bcma_chipco_pll_read); void bcma_chipco_pll_write(struct bcma_drv_cc *cc, u32 offset, u32 value) { - bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PLLCTL_ADDR); - bcma_cc_write32(cc, BCMA_CC_PLLCTL_DATA, value); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, value); } EXPORT_SYMBOL_GPL(bcma_chipco_pll_write); void bcma_chipco_pll_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set) { - bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PLLCTL_ADDR); - bcma_cc_maskset32(cc, BCMA_CC_PLLCTL_DATA, mask, set); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); + bcma_cc_maskset32(cc, BCMA_CC_PMU_PLLCTL_DATA, mask, set); } EXPORT_SYMBOL_GPL(bcma_chipco_pll_maskset); void bcma_chipco_chipctl_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set) { - bcma_cc_write32(cc, BCMA_CC_CHIPCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_CHIPCTL_ADDR); - bcma_cc_maskset32(cc, BCMA_CC_CHIPCTL_DATA, mask, set); + bcma_cc_write32(cc, BCMA_CC_PMU_CHIPCTL_ADDR, offset); + bcma_cc_read32(cc, BCMA_CC_PMU_CHIPCTL_ADDR); + bcma_cc_maskset32(cc, BCMA_CC_PMU_CHIPCTL_DATA, mask, set); } EXPORT_SYMBOL_GPL(bcma_chipco_chipctl_maskset); void bcma_chipco_regctl_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set) { - bcma_cc_write32(cc, BCMA_CC_REGCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_REGCTL_ADDR); - bcma_cc_maskset32(cc, BCMA_CC_REGCTL_DATA, mask, set); + bcma_cc_write32(cc, BCMA_CC_PMU_REGCTL_ADDR, offset); + bcma_cc_read32(cc, BCMA_CC_PMU_REGCTL_ADDR); + bcma_cc_maskset32(cc, BCMA_CC_PMU_REGCTL_DATA, mask, set); } EXPORT_SYMBOL_GPL(bcma_chipco_regctl_maskset); @@ -472,8 +472,8 @@ u32 bcma_pmu_get_cpu_clock(struct bcma_drv_cc *cc) static void bcma_pmu_spuravoid_pll_write(struct bcma_drv_cc *cc, u32 offset, u32 value) { - bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, offset); - bcma_cc_write32(cc, BCMA_CC_PLLCTL_DATA, value); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, value); } void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid) @@ -497,20 +497,20 @@ void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid) bus->chipinfo.id == BCMA_CHIP_ID_BCM53572) ? 6 : 0; /* RMW only the P1 divider */ - bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, BCMA_CC_PMU_PLL_CTL0 + phypll_offset); - tmp = bcma_cc_read32(cc, BCMA_CC_PLLCTL_DATA); + tmp = bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); tmp &= (~(BCMA_CC_PMU1_PLL0_PC0_P1DIV_MASK)); tmp |= (bcm5357_bcm43236_p1div[spuravoid] << BCMA_CC_PMU1_PLL0_PC0_P1DIV_SHIFT); - bcma_cc_write32(cc, BCMA_CC_PLLCTL_DATA, tmp); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, tmp); /* RMW only the int feedback divider */ - bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, BCMA_CC_PMU_PLL_CTL2 + phypll_offset); - tmp = bcma_cc_read32(cc, BCMA_CC_PLLCTL_DATA); + tmp = bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); tmp &= ~(BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_MASK); tmp |= (bcm5357_bcm43236_ndiv[spuravoid]) << BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_SHIFT; - bcma_cc_write32(cc, BCMA_CC_PLLCTL_DATA, tmp); + bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, tmp); tmp = BCMA_CC_PMU_CTL_PLL_UPD; break; diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c index ec013fbd6a81..c279211e49f9 100644 --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -1215,10 +1215,10 @@ void b43_wireless_core_phy_pll_reset(struct b43_wldev *dev) case B43_BUS_BCMA: bcma_cc = &dev->dev->bdev->bus->drv_cc; - bcma_cc_write32(bcma_cc, BCMA_CC_CHIPCTL_ADDR, 0); - bcma_cc_mask32(bcma_cc, BCMA_CC_CHIPCTL_DATA, ~0x4); - bcma_cc_set32(bcma_cc, BCMA_CC_CHIPCTL_DATA, 0x4); - bcma_cc_mask32(bcma_cc, BCMA_CC_CHIPCTL_DATA, ~0x4); + bcma_cc_write32(bcma_cc, BCMA_CC_PMU_CHIPCTL_ADDR, 0); + bcma_cc_mask32(bcma_cc, BCMA_CC_PMU_CHIPCTL_DATA, ~0x4); + bcma_cc_set32(bcma_cc, BCMA_CC_PMU_CHIPCTL_DATA, 0x4); + bcma_cc_mask32(bcma_cc, BCMA_CC_PMU_CHIPCTL_DATA, ~0x4); break; #endif #ifdef CONFIG_B43_SSB diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index db51a6ffb7d6..96d8d56f240f 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -351,12 +351,12 @@ #define BCMA_CC_PMU_RES_REQTS 0x0640 /* PMU res req timer sel */ #define BCMA_CC_PMU_RES_REQT 0x0644 /* PMU res req timer */ #define BCMA_CC_PMU_RES_REQM 0x0648 /* PMU res req mask */ -#define BCMA_CC_CHIPCTL_ADDR 0x0650 -#define BCMA_CC_CHIPCTL_DATA 0x0654 -#define BCMA_CC_REGCTL_ADDR 0x0658 -#define BCMA_CC_REGCTL_DATA 0x065C -#define BCMA_CC_PLLCTL_ADDR 0x0660 -#define BCMA_CC_PLLCTL_DATA 0x0664 +#define BCMA_CC_PMU_CHIPCTL_ADDR 0x0650 +#define BCMA_CC_PMU_CHIPCTL_DATA 0x0654 +#define BCMA_CC_PMU_REGCTL_ADDR 0x0658 +#define BCMA_CC_PMU_REGCTL_DATA 0x065C +#define BCMA_CC_PMU_PLLCTL_ADDR 0x0660 +#define BCMA_CC_PMU_PLLCTL_DATA 0x0664 #define BCMA_CC_PMU_STRAPOPT 0x0668 /* (corerev >= 28) */ #define BCMA_CC_PMU_XTAL_FREQ 0x066C /* (pmurev >= 10) */ #define BCMA_CC_PMU_XTAL_FREQ_ILPCTL_MASK 0x00001FFF -- cgit v1.2.3 From b3c47afbf54d86daa0473895e8ca9e8b663f5c1a Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Tue, 19 Jan 2016 08:45:26 +0100 Subject: bcma: support PMU present as separated bus core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On recent Broadcom chipsets PMU is present as separated core and it can't be accessed using ChipCommon anymore as it fails with e.g.: [ 0.000577] Unhandled fault: external abort on non-linefetch (0x1008) at 0xf1000604 Solve it by using a new (PMU) core pointer set to ChipCommon or PMU depending on the hardware capabilities. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- drivers/bcma/driver_chipcommon.c | 2 +- drivers/bcma/driver_chipcommon_pmu.c | 94 ++++++++++++++++------------- include/linux/bcma/bcma_driver_chipcommon.h | 19 ++++++ 3 files changed, 72 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c index b7c8a8d4e6d1..36ee221e298f 100644 --- a/drivers/bcma/driver_chipcommon.c +++ b/drivers/bcma/driver_chipcommon.c @@ -185,7 +185,7 @@ u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks) ticks = 2; else if (ticks > maxt) ticks = maxt; - bcma_cc_write32(cc, BCMA_CC_PMU_WATCHDOG, ticks); + bcma_pmu_write32(cc, BCMA_CC_PMU_WATCHDOG, ticks); } else { struct bcma_bus *bus = cc->core->bus; diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index 472f39dc5a38..f1eb4d3e1d57 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -15,44 +15,44 @@ u32 bcma_chipco_pll_read(struct bcma_drv_cc *cc, u32 offset) { - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); - return bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_pmu_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); + return bcma_pmu_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); } EXPORT_SYMBOL_GPL(bcma_chipco_pll_read); void bcma_chipco_pll_write(struct bcma_drv_cc *cc, u32 offset, u32 value) { - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, value); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_pmu_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, value); } EXPORT_SYMBOL_GPL(bcma_chipco_pll_write); void bcma_chipco_pll_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set) { - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); - bcma_cc_maskset32(cc, BCMA_CC_PMU_PLLCTL_DATA, mask, set); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_pmu_read32(cc, BCMA_CC_PMU_PLLCTL_ADDR); + bcma_pmu_maskset32(cc, BCMA_CC_PMU_PLLCTL_DATA, mask, set); } EXPORT_SYMBOL_GPL(bcma_chipco_pll_maskset); void bcma_chipco_chipctl_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set) { - bcma_cc_write32(cc, BCMA_CC_PMU_CHIPCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PMU_CHIPCTL_ADDR); - bcma_cc_maskset32(cc, BCMA_CC_PMU_CHIPCTL_DATA, mask, set); + bcma_pmu_write32(cc, BCMA_CC_PMU_CHIPCTL_ADDR, offset); + bcma_pmu_read32(cc, BCMA_CC_PMU_CHIPCTL_ADDR); + bcma_pmu_maskset32(cc, BCMA_CC_PMU_CHIPCTL_DATA, mask, set); } EXPORT_SYMBOL_GPL(bcma_chipco_chipctl_maskset); void bcma_chipco_regctl_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set) { - bcma_cc_write32(cc, BCMA_CC_PMU_REGCTL_ADDR, offset); - bcma_cc_read32(cc, BCMA_CC_PMU_REGCTL_ADDR); - bcma_cc_maskset32(cc, BCMA_CC_PMU_REGCTL_DATA, mask, set); + bcma_pmu_write32(cc, BCMA_CC_PMU_REGCTL_ADDR, offset); + bcma_pmu_read32(cc, BCMA_CC_PMU_REGCTL_ADDR); + bcma_pmu_maskset32(cc, BCMA_CC_PMU_REGCTL_DATA, mask, set); } EXPORT_SYMBOL_GPL(bcma_chipco_regctl_maskset); @@ -60,18 +60,18 @@ static u32 bcma_pmu_xtalfreq(struct bcma_drv_cc *cc) { u32 ilp_ctl, alp_hz; - if (!(bcma_cc_read32(cc, BCMA_CC_PMU_STAT) & + if (!(bcma_pmu_read32(cc, BCMA_CC_PMU_STAT) & BCMA_CC_PMU_STAT_EXT_LPO_AVAIL)) return 0; - bcma_cc_write32(cc, BCMA_CC_PMU_XTAL_FREQ, - BIT(BCMA_CC_PMU_XTAL_FREQ_MEASURE_SHIFT)); + bcma_pmu_write32(cc, BCMA_CC_PMU_XTAL_FREQ, + BIT(BCMA_CC_PMU_XTAL_FREQ_MEASURE_SHIFT)); usleep_range(1000, 2000); - ilp_ctl = bcma_cc_read32(cc, BCMA_CC_PMU_XTAL_FREQ); + ilp_ctl = bcma_pmu_read32(cc, BCMA_CC_PMU_XTAL_FREQ); ilp_ctl &= BCMA_CC_PMU_XTAL_FREQ_ILPCTL_MASK; - bcma_cc_write32(cc, BCMA_CC_PMU_XTAL_FREQ, 0); + bcma_pmu_write32(cc, BCMA_CC_PMU_XTAL_FREQ, 0); alp_hz = ilp_ctl * 32768 / 4; return (alp_hz + 50000) / 100000 * 100; @@ -127,8 +127,8 @@ static void bcma_pmu2_pll_init0(struct bcma_drv_cc *cc, u32 xtalfreq) mask = (u32)~(BCMA_RES_4314_HT_AVAIL | BCMA_RES_4314_MACPHY_CLK_AVAIL); - bcma_cc_mask32(cc, BCMA_CC_PMU_MINRES_MSK, mask); - bcma_cc_mask32(cc, BCMA_CC_PMU_MAXRES_MSK, mask); + bcma_pmu_mask32(cc, BCMA_CC_PMU_MINRES_MSK, mask); + bcma_pmu_mask32(cc, BCMA_CC_PMU_MAXRES_MSK, mask); bcma_wait_value(cc->core, BCMA_CLKCTLST, BCMA_CLKCTLST_HAVEHT, 0, 20000); break; @@ -140,7 +140,7 @@ static void bcma_pmu2_pll_init0(struct bcma_drv_cc *cc, u32 xtalfreq) /* Flush */ if (cc->pmu.rev >= 2) - bcma_cc_set32(cc, BCMA_CC_PMU_CTL, BCMA_CC_PMU_CTL_PLL_UPD); + bcma_pmu_set32(cc, BCMA_CC_PMU_CTL, BCMA_CC_PMU_CTL_PLL_UPD); /* TODO: Do we need to update OTP? */ } @@ -195,9 +195,9 @@ static void bcma_pmu_resources_init(struct bcma_drv_cc *cc) /* Set the resource masks. */ if (min_msk) - bcma_cc_write32(cc, BCMA_CC_PMU_MINRES_MSK, min_msk); + bcma_pmu_write32(cc, BCMA_CC_PMU_MINRES_MSK, min_msk); if (max_msk) - bcma_cc_write32(cc, BCMA_CC_PMU_MAXRES_MSK, max_msk); + bcma_pmu_write32(cc, BCMA_CC_PMU_MAXRES_MSK, max_msk); /* * Add some delay; allow resources to come up and settle. @@ -269,23 +269,33 @@ static void bcma_pmu_workarounds(struct bcma_drv_cc *cc) void bcma_pmu_early_init(struct bcma_drv_cc *cc) { + struct bcma_bus *bus = cc->core->bus; u32 pmucap; - pmucap = bcma_cc_read32(cc, BCMA_CC_PMU_CAP); + if (cc->core->id.rev >= 35 && + cc->capabilities_ext & BCMA_CC_CAP_EXT_AOB_PRESENT) { + cc->pmu.core = bcma_find_core(bus, BCMA_CORE_PMU); + if (!cc->pmu.core) + bcma_warn(bus, "Couldn't find expected PMU core"); + } + if (!cc->pmu.core) + cc->pmu.core = cc->core; + + pmucap = bcma_pmu_read32(cc, BCMA_CC_PMU_CAP); cc->pmu.rev = (pmucap & BCMA_CC_PMU_CAP_REVISION); - bcma_debug(cc->core->bus, "Found rev %u PMU (capabilities 0x%08X)\n", - cc->pmu.rev, pmucap); + bcma_debug(bus, "Found rev %u PMU (capabilities 0x%08X)\n", cc->pmu.rev, + pmucap); } void bcma_pmu_init(struct bcma_drv_cc *cc) { if (cc->pmu.rev == 1) - bcma_cc_mask32(cc, BCMA_CC_PMU_CTL, - ~BCMA_CC_PMU_CTL_NOILPONW); + bcma_pmu_mask32(cc, BCMA_CC_PMU_CTL, + ~BCMA_CC_PMU_CTL_NOILPONW); else - bcma_cc_set32(cc, BCMA_CC_PMU_CTL, - BCMA_CC_PMU_CTL_NOILPONW); + bcma_pmu_set32(cc, BCMA_CC_PMU_CTL, + BCMA_CC_PMU_CTL_NOILPONW); bcma_pmu_pll_init(cc); bcma_pmu_resources_init(cc); @@ -472,8 +482,8 @@ u32 bcma_pmu_get_cpu_clock(struct bcma_drv_cc *cc) static void bcma_pmu_spuravoid_pll_write(struct bcma_drv_cc *cc, u32 offset, u32 value) { - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, value); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, offset); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, value); } void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid) @@ -497,20 +507,20 @@ void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid) bus->chipinfo.id == BCMA_CHIP_ID_BCM53572) ? 6 : 0; /* RMW only the P1 divider */ - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, BCMA_CC_PMU_PLL_CTL0 + phypll_offset); - tmp = bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); + tmp = bcma_pmu_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); tmp &= (~(BCMA_CC_PMU1_PLL0_PC0_P1DIV_MASK)); tmp |= (bcm5357_bcm43236_p1div[spuravoid] << BCMA_CC_PMU1_PLL0_PC0_P1DIV_SHIFT); - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, tmp); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, tmp); /* RMW only the int feedback divider */ - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_ADDR, BCMA_CC_PMU_PLL_CTL2 + phypll_offset); - tmp = bcma_cc_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); + tmp = bcma_pmu_read32(cc, BCMA_CC_PMU_PLLCTL_DATA); tmp &= ~(BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_MASK); tmp |= (bcm5357_bcm43236_ndiv[spuravoid]) << BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_SHIFT; - bcma_cc_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, tmp); + bcma_pmu_write32(cc, BCMA_CC_PMU_PLLCTL_DATA, tmp); tmp = BCMA_CC_PMU_CTL_PLL_UPD; break; @@ -646,7 +656,7 @@ void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid) break; } - tmp |= bcma_cc_read32(cc, BCMA_CC_PMU_CTL); - bcma_cc_write32(cc, BCMA_CC_PMU_CTL, tmp); + tmp |= bcma_pmu_read32(cc, BCMA_CC_PMU_CTL); + bcma_pmu_write32(cc, BCMA_CC_PMU_CTL, tmp); } EXPORT_SYMBOL_GPL(bcma_pmu_spuravoid_pllupdate); diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 96d8d56f240f..700d0c6f7480 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -217,6 +217,11 @@ #define BCMA_CC_CLKDIV_JTAG_SHIFT 8 #define BCMA_CC_CLKDIV_UART 0x000000FF #define BCMA_CC_CAP_EXT 0x00AC /* Capabilities */ +#define BCMA_CC_CAP_EXT_SECI_PRESENT 0x00000001 +#define BCMA_CC_CAP_EXT_GSIO_PRESENT 0x00000002 +#define BCMA_CC_CAP_EXT_GCI_PRESENT 0x00000004 +#define BCMA_CC_CAP_EXT_SECI_PUART_PRESENT 0x00000008 /* UART present */ +#define BCMA_CC_CAP_EXT_AOB_PRESENT 0x00000040 #define BCMA_CC_PLLONDELAY 0x00B0 /* Rev >= 4 only */ #define BCMA_CC_FREFSELDELAY 0x00B4 /* Rev >= 4 only */ #define BCMA_CC_SLOWCLKCTL 0x00B8 /* 6 <= Rev <= 9 only */ @@ -566,6 +571,7 @@ * Check availability with ((struct bcma_chipcommon)->capabilities & BCMA_CC_CAP_PMU) */ struct bcma_chipcommon_pmu { + struct bcma_device *core; /* Can be separated core or just ChipCommon one */ u8 rev; /* PMU revision */ u32 crystalfreq; /* The active crystal frequency (in kHz) */ }; @@ -660,6 +666,19 @@ struct bcma_drv_cc_b { #define bcma_cc_maskset32(cc, offset, mask, set) \ bcma_cc_write32(cc, offset, (bcma_cc_read32(cc, offset) & (mask)) | (set)) +/* PMU registers access */ +#define bcma_pmu_read32(cc, offset) \ + bcma_read32((cc)->pmu.core, offset) +#define bcma_pmu_write32(cc, offset, val) \ + bcma_write32((cc)->pmu.core, offset, val) + +#define bcma_pmu_mask32(cc, offset, mask) \ + bcma_pmu_write32(cc, offset, bcma_pmu_read32(cc, offset) & (mask)) +#define bcma_pmu_set32(cc, offset, set) \ + bcma_pmu_write32(cc, offset, bcma_pmu_read32(cc, offset) | (set)) +#define bcma_pmu_maskset32(cc, offset, mask, set) \ + bcma_pmu_write32(cc, offset, (bcma_pmu_read32(cc, offset) & (mask)) | (set)) + extern u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks); extern u32 bcma_chipco_get_alp_clock(struct bcma_drv_cc *cc); -- cgit v1.2.3 From 61dba73cdbba8ec5c01b31beaf9e2debc2d2f273 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Sun, 24 Jan 2016 16:37:33 +0100 Subject: bcma: add support for BCM47094 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's another SoC with 32 GPIOs and simplified watchdog handling. It was tested on D-Link DIR-885L. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- drivers/bcma/driver_chipcommon.c | 1 + drivers/bcma/driver_gpio.c | 1 + include/linux/bcma/bcma.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c index bdb73d97da63..b0f44a2937b9 100644 --- a/drivers/bcma/driver_chipcommon.c +++ b/drivers/bcma/driver_chipcommon.c @@ -197,6 +197,7 @@ u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks) struct bcma_bus *bus = cc->core->bus; if (bus->chipinfo.id != BCMA_CHIP_ID_BCM4707 && + bus->chipinfo.id != BCMA_CHIP_ID_BCM47094 && bus->chipinfo.id != BCMA_CHIP_ID_BCM53018) bcma_core_set_clockmode(cc->core, ticks ? BCMA_CLKMODE_FAST : BCMA_CLKMODE_DYNAMIC); diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c index 504899a72966..77b0738fbe1b 100644 --- a/drivers/bcma/driver_gpio.c +++ b/drivers/bcma/driver_gpio.c @@ -197,6 +197,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) case BCMA_CHIP_ID_BCM4707: case BCMA_CHIP_ID_BCM5357: case BCMA_CHIP_ID_BCM53572: + case BCMA_CHIP_ID_BCM47094: chip->ngpio = 32; break; default: diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 991ebb4c2015..0367c63f5960 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -201,6 +201,7 @@ struct bcma_host_ops { #define BCMA_PKG_ID_BCM4707 1 #define BCMA_PKG_ID_BCM4708 2 #define BCMA_PKG_ID_BCM4709 0 +#define BCMA_CHIP_ID_BCM47094 53030 #define BCMA_CHIP_ID_BCM53018 53018 /* Board types (on PCI usually equals to the subsystem dev id) */ -- cgit v1.2.3 From ddf1af6fa00e772fdb67a7d22cb83fac2b8968a8 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 2 Feb 2016 10:33:06 -0800 Subject: tcp: new delivery accounting This patch changes the accounting of how many packets are newly acked or sacked when the sender receives an ACK. The current approach basically computes newly_acked_sacked = (prior_packets - prior_sacked) - (tp->packets_out - tp->sacked_out) where prior_packets and prior_sacked out are snapshot at the beginning of the ACK processing. The new approach tracks the delivery information via a new TCP state variable "delivered" which monotically increases as new packets are delivered in order or out-of-order. The reason for this change is that the current approach is brittle that produces negative or inaccurate estimate. 1) For non-SACK connections, an ACK that advances the SND.UNA could reset the DUPACK counters (tp->sacked_out) in tcp_process_loss() or tcp_fastretrans_alert(). This inflates the inflight suddenly and causes under-estimate or even negative estimate. Here is a real example: before after (processing ACK) packets_out 75 73 sacked_out 23 0 ca state Loss Open The old approach computes (75-23) - (73 - 0) = -21 delivered while the new approach computes 1 delivered since it considers the 2nd-24th packets are delivered OOO. 2) MSS change would re-count packets_out and sacked_out so the estimate is in-accurate and can even become negative. E.g., the inflight is doubled when MSS is halved. 3) Spurious retransmission signaled by DSACK is not accounted The new approach is simpler and more robust. For SACK connections, tp->delivered increments as packets are being acked or sacked in SACK and ACK processing. For non-sack connections, it's done in tcp_remove_reno_sacks() and tcp_add_reno_sack(). When an ACK advances the SND.UNA, tp->delivered is incremented by the number of packets ACKed (less the current number of DUPACKs received plus one packet hole). Upon receiving a DUPACK, tp->delivered is incremented assuming one out-of-order packet is delivered. Upon receiving a DSACK, tp->delivered is incremtened assuming one retransmission is delivered in tcp_sacktag_write_queue(). Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + net/ipv4/tcp_input.c | 21 +++++++++++++++------ 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b386361ba3e8..d909feeeaea2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -256,6 +256,7 @@ struct tcp_sock { u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ + u32 delivered; /* Total data packets delivered incl. rexmits */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index dc810df53e90..2d690b3f0a7b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1214,6 +1214,7 @@ static u8 tcp_sacktag_one(struct sock *sk, sacked |= TCPCB_SACKED_ACKED; state->flag |= FLAG_DATA_SACKED; tp->sacked_out += pcount; + tp->delivered += pcount; /* Out-of-order packets delivered */ fack_count += pcount; @@ -1825,8 +1826,12 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) static void tcp_add_reno_sack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 prior_sacked = tp->sacked_out; + tp->sacked_out++; tcp_check_reno_reordering(sk, 0); + if (tp->sacked_out > prior_sacked) + tp->delivered++; /* Some out-of-order packet is delivered */ tcp_verify_left_out(tp); } @@ -1838,6 +1843,7 @@ static void tcp_remove_reno_sacks(struct sock *sk, int acked) if (acked > 0) { /* One ACK acked hole. The rest eat duplicate ACKs. */ + tp->delivered += max_t(int, acked - tp->sacked_out, 1); if (acked - 1 >= tp->sacked_out) tp->sacked_out = 0; else @@ -3156,10 +3162,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_ORIG_SACK_ACKED; } - if (sacked & TCPCB_SACKED_ACKED) + if (sacked & TCPCB_SACKED_ACKED) { tp->sacked_out -= acked_pcount; - else if (tcp_is_sack(tp) && !tcp_skb_spurious_retrans(tp, skb)) - tcp_rack_advance(tp, &skb->skb_mstamp, sacked); + } else if (tcp_is_sack(tp)) { + tp->delivered += acked_pcount; + if (!tcp_skb_spurious_retrans(tp, skb)) + tcp_rack_advance(tp, &skb->skb_mstamp, sacked); + } if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; @@ -3541,9 +3550,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) bool is_dupack = false; u32 prior_fackets; int prior_packets = tp->packets_out; - const int prior_unsacked = tp->packets_out - tp->sacked_out; + u32 prior_delivered = tp->delivered; int acked = 0; /* Number of packets newly acked */ - int acked_sacked; /* Number of packets newly acked or sacked */ + u32 acked_sacked; /* Number of packets newly acked or sacked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ sack_state.first_sackt.v64 = 0; @@ -3645,7 +3654,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); - acked_sacked = prior_unsacked - (tp->packets_out - tp->sacked_out); + acked_sacked = tp->delivered - prior_delivered; /* Advance cwnd if state allows */ if (tcp_in_cwnd_reduction(sk)) { /* Reduce cwnd if state mandates */ -- cgit v1.2.3 From d9b3fca27385eafe61c3ca6feab6cb1e7dc77482 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Wed, 10 Feb 2016 11:50:37 -0500 Subject: tcp: __tcp_hdrlen() helper tcp_hdrlen is wasteful if you already have a pointer to struct tcphdr. This splits the size calculation into a helper function that can be used if a struct tcphdr is already available. Signed-off-by: Craig Gallek Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d909feeeaea2..bcbf51da4e1e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -29,9 +29,14 @@ static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb) return (struct tcphdr *)skb_transport_header(skb); } +static inline unsigned int __tcp_hdrlen(const struct tcphdr *th) +{ + return th->doff * 4; +} + static inline unsigned int tcp_hdrlen(const struct sk_buff *skb) { - return tcp_hdr(skb)->doff * 4; + return __tcp_hdrlen(tcp_hdr(skb)); } static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb) -- cgit v1.2.3 From abbc30436d39dfed8ebfca338d253f211ac7b094 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 Feb 2016 13:31:19 +0100 Subject: ipv6: add option to drop unicast encapsulated in L2 multicast In order to solve a problem with 802.11, the so-called hole-196 attack, add an option (sysctl) called "drop_unicast_in_l2_multicast" which, if enabled, causes the stack to drop IPv6 unicast packets encapsulated in link-layer multi- or broadcast frames. Such frames can (as an attack) be created by any member of the same wireless network and transmitted as valid encrypted frames since the symmetric key for broadcast frames is shared between all stations. Reviewed-by: Julian Anastasov Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 6 ++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 8 ++++++++ net/ipv6/ip6_input.c | 10 ++++++++++ 5 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index a53bbfaff1c7..e0e7350a4e6a 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1674,6 +1674,12 @@ stable_secret - IPv6 address By default the stable secret is unset. +drop_unicast_in_l2_multicast - BOOLEAN + Drop any unicast IPv6 packets that are received in link-layer + multicast (or broadcast) frames. + + By default this is turned off. + icmp/*: ratelimit - INTEGER Limit the maximal rates for sending ICMPv6 packets. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 402753bccafa..4a4c1ae826cb 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -50,6 +50,7 @@ struct ipv6_devconf { __s32 mc_forwarding; #endif __s32 disable_ipv6; + __s32 drop_unicast_in_l2_multicast; __s32 accept_dad; __s32 force_tllao; __s32 ndisc_notify; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 38b4fef20219..4c413570efe8 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -174,6 +174,7 @@ enum { DEVCONF_USE_OIF_ADDRS_ONLY, DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT, DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, + DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 38eeddedfc21..23e325f39f8e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4711,6 +4711,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown; /* we omit DEVCONF_STABLE_SECRET for now */ array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; + array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; } static inline size_t inet6_ifla6_size(void) @@ -5784,6 +5785,13 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = addrconf_sysctl_ignore_routes_with_linkdown, }, + { + .procname = "drop_unicast_in_l2_multicast", + .data = &ipv6_devconf.drop_unicast_in_l2_multicast, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { /* sentinel */ } diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 9075acf081dd..31ac3c56da4b 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -134,6 +134,16 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1) goto err; + /* If enabled, drop unicast packets that were encapsulated in link-layer + * multicast or broadcast to protected against the so-called "hole-196" + * attack in 802.11 wireless. + */ + if (!ipv6_addr_is_multicast(&hdr->daddr) && + (skb->pkt_type == PACKET_BROADCAST || + skb->pkt_type == PACKET_MULTICAST) && + idev->cnf.drop_unicast_in_l2_multicast) + goto err; + /* RFC4291 2.7 * Nodes must not originate a packet to a multicast address whose scope * field contains the reserved value 0; if such a packet is received, it -- cgit v1.2.3 From 7a02bf892d8f1e5298af1676f001bee410509d80 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 Feb 2016 13:31:20 +0100 Subject: ipv6: add option to drop unsolicited neighbor advertisements In certain 802.11 wireless deployments, there will be NA proxies that use knowledge of the network to correctly answer requests. To prevent unsolicitd advertisements on the shared medium from being a problem, on such deployments wireless needs to drop them. Enable this by providing an option called "drop_unsolicited_na". Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 7 +++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 8 ++++++++ net/ipv6/ndisc.c | 9 +++++++++ 5 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index e0e7350a4e6a..24ce97f42d35 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1680,6 +1680,13 @@ drop_unicast_in_l2_multicast - BOOLEAN By default this is turned off. +drop_unsolicited_na - BOOLEAN + Drop all unsolicited neighbor advertisements, for example if there's + a known good NA proxy on the network and such frames need not be used + (or in the case of 802.11, must not be used to prevent attacks.) + + By default this is turned off. + icmp/*: ratelimit - INTEGER Limit the maximal rates for sending ICMPv6 packets. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4a4c1ae826cb..4b2267e1b7c3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -56,6 +56,7 @@ struct ipv6_devconf { __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; + __s32 drop_unsolicited_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 4c413570efe8..ec117b65d5a5 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -175,6 +175,7 @@ enum { DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT, DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, + DEVCONF_DROP_UNSOLICITED_NA, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 23e325f39f8e..ac0ba9e4e06b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4712,6 +4712,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, /* we omit DEVCONF_STABLE_SECRET for now */ array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; + array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; } static inline size_t inet6_ifla6_size(void) @@ -5792,6 +5793,13 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "drop_unsolicited_na", + .data = &ipv6_devconf.drop_unsolicited_na, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { /* sentinel */ } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 84afb9a77278..c245895a3d41 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -883,6 +883,7 @@ static void ndisc_recv_na(struct sk_buff *skb) offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; + struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; @@ -902,6 +903,14 @@ static void ndisc_recv_na(struct sk_buff *skb) return; } + /* For some 802.11 wireless deployments (and possibly other networks), + * there will be a NA proxy and unsolicitd packets are attacks + * and thus should not be accepted. + */ + if (!msg->icmph.icmp6_solicited && idev && + idev->cnf.drop_unsolicited_na) + return; + if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) { ND_PRINTK(2, warn, "NS: invalid ND option\n"); return; -- cgit v1.2.3 From 76443456227097179c14826425f88a95d81a892e Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 5 Feb 2016 15:27:37 -0800 Subject: net: Move GSO csum into SKB_GSO_CB This patch moves the checksum maintained by GSO out of skb->csum and into the GSO context block in order to allow for us to work on outer checksums while maintaining the inner checksum offsets in the case of the inner checksum being offloaded, while the outer checksums will be computed. While updating the code I also did a minor cleanu-up on gso_make_checksum. The change is mostly to make it so that we store the values and compute the checksum instead of computing the checksum and then storing the values we needed to update. Signed-off-by: Alexander Duyck Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 14 +++++++------- net/core/skbuff.c | 16 +++++++++------- 2 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 11f935c1a090..acece7ce376f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3549,6 +3549,7 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb) struct skb_gso_cb { int mac_offset; int encap_level; + __wsum csum; __u16 csum_start; }; #define SKB_SGO_CB_OFFSET 32 @@ -3585,15 +3586,14 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) */ static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res) { - int plen = SKB_GSO_CB(skb)->csum_start - skb_headroom(skb) - - skb_transport_offset(skb); - __wsum partial; + unsigned char *csum_start = skb_transport_header(skb); + int plen = (skb->head + SKB_GSO_CB(skb)->csum_start) - csum_start; + __wsum partial = SKB_GSO_CB(skb)->csum; - partial = csum_partial(skb_transport_header(skb), plen, skb->csum); - skb->csum = res; - SKB_GSO_CB(skb)->csum_start -= plen; + SKB_GSO_CB(skb)->csum = res; + SKB_GSO_CB(skb)->csum_start = csum_start - skb->head; - return csum_fold(partial); + return csum_fold(csum_partial(csum_start, plen, partial)); } static inline bool skb_is_gso(const struct sk_buff *skb) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2df375ec9c2..02c638a643ea 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3100,11 +3100,12 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, if (!sg && !nskb->remcsum_offload) { nskb->ip_summed = CHECKSUM_NONE; - nskb->csum = skb_copy_and_csum_bits(head_skb, offset, - skb_put(nskb, len), - len, 0); + SKB_GSO_CB(nskb)->csum = + skb_copy_and_csum_bits(head_skb, offset, + skb_put(nskb, len), + len, 0); SKB_GSO_CB(nskb)->csum_start = - skb_headroom(nskb) + doffset; + skb_headroom(nskb) + doffset; continue; } @@ -3171,11 +3172,12 @@ skip_fraglist: perform_csum_check: if (!csum && !nskb->remcsum_offload) { - nskb->csum = skb_checksum(nskb, doffset, - nskb->len - doffset, 0); nskb->ip_summed = CHECKSUM_NONE; + SKB_GSO_CB(nskb)->csum = + skb_checksum(nskb, doffset, + nskb->len - doffset, 0); SKB_GSO_CB(nskb)->csum_start = - skb_headroom(nskb) + doffset; + skb_headroom(nskb) + doffset; } } while ((offset += len) < head_skb->len); -- cgit v1.2.3 From 08b64fcca942733413bc5ac2321d57021d3e8578 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 5 Feb 2016 15:27:49 -0800 Subject: net: Store checksum result for offloaded GSO checksums This patch makes it so that we can offload the checksums for a packet up to a certain point and then begin computing the checksums via software. Setting this up is fairly straight forward as all we need to do is reset the values stored in csum and csum_start for the GSO context block. One complication for this is remote checksum offload. In order to allow the inner checksums to be offloaded while computing the outer checksum manually we needed to have some way of indicating that the offload wasn't real. In order to do that I replaced CHECKSUM_PARTIAL with CHECKSUM_UNNECESSARY in the case of us computing checksums for the outer header while skipping computing checksums for the inner headers. We clean up the ip_summed flag and set it to either CHECKSUM_PARTIAL or CHECKSUM_NONE once we hand the packet off to the next lower level. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 15 +++++++++++++++ net/ipv4/tcp_offload.c | 8 ++++++-- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index acece7ce376f..a8fc2220e8ce 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2161,6 +2161,11 @@ static inline int skb_checksum_start_offset(const struct sk_buff *skb) return skb->csum_start - skb_headroom(skb); } +static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) +{ + return skb->head + skb->csum_start; +} + static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; @@ -3576,6 +3581,16 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) return 0; } +static inline void gso_reset_checksum(struct sk_buff *skb, __wsum res) +{ + /* Do not update partial checksums if remote checksum is enabled. */ + if (skb->remcsum_offload) + return; + + SKB_GSO_CB(skb)->csum = res; + SKB_GSO_CB(skb)->csum_start = skb_checksum_start(skb) - skb->head; +} + /* Compute the checksum for a gso segment. First compute the checksum value * from the start of transport header to SKB_GSO_CB(skb)->csum_start, and * then add in skb->csum (checksum from csum_start to end of packet). diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 9864a2dbadce..773083b7f1e9 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -135,7 +135,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th->fin = th->psh = 0; th->check = newcheck; - if (skb->ip_summed != CHECKSUM_PARTIAL) + if (skb->ip_summed == CHECKSUM_PARTIAL) + gso_reset_checksum(skb, ~th->check); + else th->check = gso_make_checksum(skb, ~th->check); seq += mss; @@ -169,7 +171,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, skb->data_len); th->check = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); - if (skb->ip_summed != CHECKSUM_PARTIAL) + if (skb->ip_summed == CHECKSUM_PARTIAL) + gso_reset_checksum(skb, ~th->check); + else th->check = gso_make_checksum(skb, ~th->check); out: return segs; -- cgit v1.2.3 From 815c52700746cdcc0874a33390bac334a4b90107 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:21 +0200 Subject: igmp: Namespaceify igmp_max_memberships sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - include/net/netns/ipv4.h | 2 ++ net/ipv4/igmp.c | 4 +--- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 2 ++ 5 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 9c9de11549a7..57d6d06ce0b3 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,6 @@ static inline struct igmpv3_query * } extern int sysctl_igmp_llm_reports; -extern int sysctl_igmp_max_memberships; extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 4d6ec3f6fafe..759cf624eec2 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -108,6 +108,8 @@ struct netns_ipv4 { int sysctl_tcp_fin_timeout; unsigned int sysctl_tcp_notsent_lowat; + int sysctl_igmp_max_memberships; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 05e4cba14162..5b86257c9d6b 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,7 +107,6 @@ #include #endif -#define IP_MAX_MEMBERSHIPS 20 #define IP_MAX_MSF 10 /* IGMP reports for link-local multicast groups are enabled by default */ @@ -1727,7 +1726,6 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) /* * Join a socket to a group */ -int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS; int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; #ifdef CONFIG_IP_MULTICAST int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE; @@ -2074,7 +2072,7 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) count++; } err = -ENOBUFS; - if (count >= sysctl_igmp_max_memberships) + if (count >= net->ipv4.sysctl_igmp_max_memberships) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 44bb59824267..6ea3dbb96db4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -367,13 +367,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "igmp_max_memberships", - .data = &sysctl_igmp_max_memberships, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "igmp_max_msf", .data = &sysctl_igmp_max_msf, @@ -871,6 +864,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "igmp_max_memberships", + .data = &init_net.ipv4.sysctl_igmp_max_memberships, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3f872a6bc274..4b203789900b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2399,6 +2399,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; + net->ipv4.sysctl_igmp_max_memberships = 20; + return 0; fail: tcp_sk_exit(net); -- cgit v1.2.3 From 166b6b2d6f01be67a83b87ab5c91350a68b17115 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:22 +0200 Subject: igmp: Namespaceify igmp_max_msf sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - include/net/netns/ipv4.h | 1 + net/ipv4/igmp.c | 5 +---- net/ipv4/ip_sockglue.c | 5 +++-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 1 + 6 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 57d6d06ce0b3..a91ec9f575e7 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,6 @@ static inline struct igmpv3_query * } extern int sysctl_igmp_llm_reports; -extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; struct ip_sf_socklist { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 759cf624eec2..522a2cfe1ad9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -109,6 +109,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_notsent_lowat; int sysctl_igmp_max_memberships; + int sysctl_igmp_max_msf; struct ping_group_range ping_group_range; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 5b86257c9d6b..6da2e467b63c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,8 +107,6 @@ #include #endif -#define IP_MAX_MSF 10 - /* IGMP reports for link-local multicast groups are enabled by default */ int sysctl_igmp_llm_reports __read_mostly = 1; @@ -1726,7 +1724,6 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) /* * Join a socket to a group */ -int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; #ifdef CONFIG_IP_MULTICAST int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE; #endif @@ -2244,7 +2241,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= sysctl_igmp_max_msf) { + if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) { err = -ENOBUFS; goto done; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f73a7c03e27..92808f147ef5 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -571,6 +571,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); int val = 0, err; bool needs_rtnl = setsockopt_needs_rtnl(optname); @@ -910,7 +911,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, } /* numsrc >= (1G-4) overflow in 32 bits */ if (msf->imsf_numsrc >= 0x3ffffffcU || - msf->imsf_numsrc > sysctl_igmp_max_msf) { + msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) { kfree(msf); err = -ENOBUFS; break; @@ -1065,7 +1066,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, /* numsrc >= (4G-140)/128 overflow in 32 bits */ if (gsf->gf_numsrc >= 0x1ffffff || - gsf->gf_numsrc > sysctl_igmp_max_msf) { + gsf->gf_numsrc > net->ipv4.sysctl_igmp_max_msf) { err = -ENOBUFS; goto mc_msf_out; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 6ea3dbb96db4..225659a02cf2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -367,13 +367,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "igmp_max_msf", - .data = &sysctl_igmp_max_msf, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, #ifdef CONFIG_IP_MULTICAST { .procname = "igmp_qrv", @@ -871,6 +864,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "igmp_max_msf", + .data = &init_net.ipv4.sysctl_igmp_max_msf, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4b203789900b..055d8a9a0c61 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2400,6 +2400,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_igmp_max_memberships = 20; + net->ipv4.sysctl_igmp_max_msf = 10; return 0; fail: -- cgit v1.2.3 From 87a8a2ae65b7721893c7922f963502be8fa01c94 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Tue, 9 Feb 2016 00:13:50 +0200 Subject: igmp: Namespaceify igmp_llm_reports sysctl knob This was initially introduced in df2cf4a78e488d26 ("IGMP: Inhibit reports for local multicast groups") by defining the sysctl in the ipv4_net_table array, however it was never implemented to be namespace aware. Fix this by changing the code accordingly. Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 - include/net/netns/ipv4.h | 1 + net/ipv4/igmp.c | 26 +++++++++++++++----------- net/ipv4/sysctl_net_ipv4.c | 2 +- net/ipv4/tcp_ipv4.c | 2 ++ 5 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index a91ec9f575e7..c683f4bf642b 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -37,7 +37,6 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } -extern int sysctl_igmp_llm_reports; extern int sysctl_igmp_qrv; struct ip_sf_socklist { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 522a2cfe1ad9..cbbf8115e8a7 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -110,6 +110,7 @@ struct netns_ipv4 { int sysctl_igmp_max_memberships; int sysctl_igmp_max_msf; + int sysctl_igmp_llm_reports; struct ping_group_range ping_group_range; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6da2e467b63c..2e22ee0efc98 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,9 +107,6 @@ #include #endif -/* IGMP reports for link-local multicast groups are enabled by default */ -int sysctl_igmp_llm_reports __read_mostly = 1; - #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ @@ -430,6 +427,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; + struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; @@ -437,7 +435,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; - if (ipv4_is_local_multicast(pmc->multiaddr) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || @@ -540,6 +538,7 @@ empty_source: static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; + struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { @@ -548,7 +547,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && - !sysctl_igmp_llm_reports) + !net->ipv4.sysctl_igmp_llm_reports) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -684,7 +683,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) @@ -855,12 +854,13 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; + struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; - if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) return false; rcu_read_lock(); @@ -884,6 +884,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, __be32 group = ih->group; int max_delay; int mark = 0; + struct net *net = dev_net(in_dev->dev); if (len == 8) { @@ -969,7 +970,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !sysctl_igmp_llm_reports) + !net->ipv4.sysctl_igmp_llm_reports) continue; spin_lock_bh(&im->lock); if (im->tm_running) @@ -1184,6 +1185,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST + struct net *net = dev_net(in_dev->dev); int reporter; #endif @@ -1195,7 +1197,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return; reporter = im->reporter; @@ -1220,6 +1222,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; + struct net *net = dev_net(in_dev->dev); if (im->loaded == 0) { im->loaded = 1; @@ -1229,7 +1232,7 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) return; if (in_dev->dead) @@ -1530,6 +1533,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); @@ -1537,7 +1541,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !sysctl_igmp_llm_reports) + !net->ipv4.sysctl_igmp_llm_reports) continue; /* a failover is happening and switches diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 225659a02cf2..fc40fa1303d3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -852,7 +852,7 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "igmp_link_local_mcast_reports", - .data = &sysctl_igmp_llm_reports, + .data = &init_net.ipv4.sysctl_igmp_llm_reports, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 055d8a9a0c61..6c3c1d5232c6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2401,6 +2401,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_igmp_max_memberships = 20; net->ipv4.sysctl_igmp_max_msf = 10; + /* IGMP reports for link-local multicast groups are enabled by default */ + net->ipv4.sysctl_igmp_llm_reports = 1; return 0; fail: -- cgit v1.2.3 From 165094afcee79e4d5b6e94032a5d3be157460b4a Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 8 Feb 2016 23:29:24 +0200 Subject: igmp: Namespacify igmp_qrv sysctl knob Signed-off-by: Nikolay Borisov Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 -- include/net/netns/ipv4.h | 1 + net/ipv4/igmp.c | 29 +++++++++++++++++------------ net/ipv4/sysctl_net_ipv4.c | 20 ++++++++++---------- net/ipv4/tcp_ipv4.c | 1 + 5 files changed, 29 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index c683f4bf642b..12f6fba6d21a 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -37,8 +37,6 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } -extern int sysctl_igmp_qrv; - struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index cbbf8115e8a7..848fe8056534 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -111,6 +111,7 @@ struct netns_ipv4 { int sysctl_igmp_max_memberships; int sysctl_igmp_max_msf; int sysctl_igmp_llm_reports; + int sysctl_igmp_qrv; struct ping_group_range ping_group_range; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 2e22ee0efc98..7c95335bf85e 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -762,9 +762,10 @@ static void igmp_ifc_timer_expire(unsigned long data) static void igmp_ifc_event(struct in_device *in_dev) { + struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: sysctl_igmp_qrv; + in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; igmp_ifc_start_timer(in_dev, 1); } @@ -1086,6 +1087,7 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc; + struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not @@ -1100,7 +1102,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; - pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; @@ -1245,7 +1247,7 @@ static void igmp_group_added(struct ip_mc_list *im) } /* else, v3 */ - im->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; igmp_ifc_event(in_dev); #endif } @@ -1314,6 +1316,7 @@ static void ip_mc_hash_remove(struct in_device *in_dev, void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { struct ip_mc_list *im; + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); @@ -1340,7 +1343,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im); - im->unsolicit_count = sysctl_igmp_qrv; + im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; #endif im->next_rcu = in_dev->mc_list; @@ -1640,6 +1643,7 @@ void ip_mc_down(struct in_device *in_dev) void ip_mc_init_dev(struct in_device *in_dev) { + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST @@ -1647,7 +1651,7 @@ void ip_mc_init_dev(struct in_device *in_dev) (unsigned long)in_dev); setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, (unsigned long)in_dev); - in_dev->mr_qrv = sysctl_igmp_qrv; + in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; #endif spin_lock_init(&in_dev->mc_tomb_lock); @@ -1658,11 +1662,12 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; + struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_qrv = sysctl_igmp_qrv; + in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; #endif ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); @@ -1728,9 +1733,6 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) /* * Join a socket to a group */ -#ifdef CONFIG_IP_MULTICAST -int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE; -#endif static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) @@ -1755,6 +1757,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; + struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ @@ -1765,7 +1768,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; @@ -1823,12 +1826,13 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; + struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST - pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; @@ -1995,6 +1999,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; + struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif @@ -2006,7 +2011,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ - pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index fc40fa1303d3..b537338f5c97 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -367,16 +367,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, -#ifdef CONFIG_IP_MULTICAST - { - .procname = "igmp_qrv", - .data = &sysctl_igmp_qrv, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one - }, -#endif { .procname = "inet_peer_threshold", .data = &inet_peer_threshold, @@ -871,6 +861,16 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_IP_MULTICAST + { + .procname = "igmp_qrv", + .data = &init_net.ipv4.sysctl_igmp_qrv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one + }, +#endif { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6c3c1d5232c6..ba5d0146e3f0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2403,6 +2403,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_igmp_max_msf = 10; /* IGMP reports for link-local multicast groups are enabled by default */ net->ipv4.sysctl_igmp_llm_reports = 1; + net->ipv4.sysctl_igmp_qrv = 2; return 0; fail: -- cgit v1.2.3 From 795bb1c00dd338aa0d12f9a7f1f4776fb3160416 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 8 Feb 2016 13:14:59 +0100 Subject: net: bulk free infrastructure for NAPI context, use napi_consume_skb Discovered that network stack were hitting the kmem_cache/SLUB slowpath when freeing SKBs. Doing bulk free with kmem_cache_free_bulk can speedup this slowpath. NAPI context is a bit special, lets take advantage of that for bulk free'ing SKBs. In NAPI context we are running in softirq, which gives us certain protection. A softirq can run on several CPUs at once. BUT the important part is a softirq will never preempt another softirq running on the same CPU. This gives us the opportunity to access per-cpu variables in softirq context. Extend napi_alloc_cache (before only contained page_frag_cache) to be a struct with a small array based stack for holding SKBs. Introduce a SKB defer and flush API for accessing this. Introduce napi_consume_skb() as replacement for e.g. dev_consume_skb_any() when running in NAPI context. A small trick to handle/detect if we are called from netpoll is to see if budget is 0. In that case, we need to invoke dev_consume_skb_irq(). Joint work with Alexander Duyck. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++ net/core/dev.c | 1 + net/core/skbuff.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 81 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a8fc2220e8ce..b56c0103fa15 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2404,6 +2404,9 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, { return __napi_alloc_skb(napi, length, GFP_ATOMIC); } +void napi_consume_skb(struct sk_buff *skb, int budget); + +void __kfree_skb_flush(void); /** * __dev_alloc_pages - allocate page for network Rx diff --git a/net/core/dev.c b/net/core/dev.c index f1284835b8c9..9b2c7a999e71 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5155,6 +5155,7 @@ static void net_rx_action(struct softirq_action *h) } } + __kfree_skb_flush(); local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b0cce744e2a0..b64187b87773 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -347,8 +347,16 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) } EXPORT_SYMBOL(build_skb); +#define NAPI_SKB_CACHE_SIZE 64 + +struct napi_alloc_cache { + struct page_frag_cache page; + size_t skb_count; + void *skb_cache[NAPI_SKB_CACHE_SIZE]; +}; + static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); -static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache); +static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { @@ -378,9 +386,9 @@ EXPORT_SYMBOL(netdev_alloc_frag); static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { - struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - return __alloc_page_frag(nc, fragsz, gfp_mask); + return __alloc_page_frag(&nc->page, fragsz, gfp_mask); } void *napi_alloc_frag(unsigned int fragsz) @@ -474,7 +482,7 @@ EXPORT_SYMBOL(__netdev_alloc_skb); struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, gfp_t gfp_mask) { - struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; void *data; @@ -494,7 +502,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; - data = __alloc_page_frag(nc, len, gfp_mask); + data = __alloc_page_frag(&nc->page, len, gfp_mask); if (unlikely(!data)) return NULL; @@ -505,7 +513,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, } /* use OR instead of assignment to avoid clearing of bits in mask */ - if (nc->pfmemalloc) + if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -747,6 +755,69 @@ void consume_skb(struct sk_buff *skb) } EXPORT_SYMBOL(consume_skb); +void __kfree_skb_flush(void) +{ + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + + /* flush skb_cache if containing objects */ + if (nc->skb_count) { + kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, + nc->skb_cache); + nc->skb_count = 0; + } +} + +static void __kfree_skb_defer(struct sk_buff *skb) +{ + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + + /* drop skb->head and call any destructors for packet */ + skb_release_all(skb); + + /* record skb to CPU local list */ + nc->skb_cache[nc->skb_count++] = skb; + +#ifdef CONFIG_SLUB + /* SLUB writes into objects when freeing */ + prefetchw(skb); +#endif + + /* flush skb_cache if it is filled */ + if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { + kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_SIZE, + nc->skb_cache); + nc->skb_count = 0; + } +} + +void napi_consume_skb(struct sk_buff *skb, int budget) +{ + if (unlikely(!skb)) + return; + + /* if budget is 0 assume netpoll w/ IRQs disabled */ + if (unlikely(!budget)) { + dev_consume_skb_irq(skb); + return; + } + + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; + /* if reaching here SKB is ready to free */ + trace_consume_skb(skb); + + /* if SKB is a clone, don't handle this case */ + if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { + __kfree_skb(skb); + return; + } + + __kfree_skb_defer(skb); +} +EXPORT_SYMBOL(napi_consume_skb); + /* Make sure a field is enclosed inside headers_start/headers_end section */ #define CHECK_SKB_FIELD(field) \ BUILD_BUG_ON(offsetof(struct sk_buff, field) < \ -- cgit v1.2.3 From 15fad714be86eab13e7568fecaf475b2a9730d3e Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 8 Feb 2016 13:15:04 +0100 Subject: net: bulk free SKBs that were delay free'ed due to IRQ context The network stack defers SKBs free, in-case free happens in IRQ or when IRQs are disabled. This happens in __dev_kfree_skb_irq() that writes SKBs that were free'ed during IRQ to the softirq completion queue (softnet_data.completion_queue). These SKBs are naturally delayed, and cleaned up during NET_TX_SOFTIRQ in function net_tx_action(). Take advantage of this a use the skb defer and flush API, as we are already in softirq context. For modern drivers this rarely happens. Although most drivers do call dev_kfree_skb_any(), which detects the situation and calls __dev_kfree_skb_irq() when needed. This due to netpoll can call from IRQ context. Signed-off-by: Alexander Duyck Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/dev.c | 8 +++++++- net/core/skbuff.c | 8 ++++++-- 3 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b56c0103fa15..6ec86f1a2ed9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2407,6 +2407,7 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, void napi_consume_skb(struct sk_buff *skb, int budget); void __kfree_skb_flush(void); +void __kfree_skb_defer(struct sk_buff *skb); /** * __dev_alloc_pages - allocate page for network Rx diff --git a/net/core/dev.c b/net/core/dev.c index 9b2c7a999e71..3f4071a84a03 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3829,8 +3829,14 @@ static void net_tx_action(struct softirq_action *h) trace_consume_skb(skb); else trace_kfree_skb(skb, net_tx_action); - __kfree_skb(skb); + + if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); + else + __kfree_skb_defer(skb); } + + __kfree_skb_flush(); } if (sd->output_queue) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b64187b87773..a5bd067ec1a3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -767,7 +767,7 @@ void __kfree_skb_flush(void) } } -static void __kfree_skb_defer(struct sk_buff *skb) +static inline void _kfree_skb_defer(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -789,6 +789,10 @@ static void __kfree_skb_defer(struct sk_buff *skb) nc->skb_count = 0; } } +void __kfree_skb_defer(struct sk_buff *skb) +{ + _kfree_skb_defer(skb); +} void napi_consume_skb(struct sk_buff *skb, int budget) { @@ -814,7 +818,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget) return; } - __kfree_skb_defer(skb); + _kfree_skb_defer(skb); } EXPORT_SYMBOL(napi_consume_skb); -- cgit v1.2.3 From 179bc67f69b6cb53ad68cfdec5a917c2a2248355 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 20:48:04 +0000 Subject: net: local checksum offload for encapsulation The arithmetic properties of the ones-complement checksum mean that a correctly checksummed inner packet, including its checksum, has a ones complement sum depending only on whatever value was used to initialise the checksum field before checksumming (in the case of TCP and UDP, this is the ones complement sum of the pseudo header, complemented). Consequently, if we are going to offload the inner checksum with CHECKSUM_PARTIAL, we can compute the outer checksum based only on the packed data not covered by the inner checksum, and the initial value of the inner checksum field. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/skbuff.h | 24 ++++++++++++++++++++++++ net/ipv4/ip_tunnel_core.c | 10 +++++----- net/ipv4/udp.c | 20 ++++++++++---------- net/ipv6/ip6_checksum.c | 14 +++++++------- 4 files changed, 46 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6ec86f1a2ed9..cf906d1ce8a7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3702,5 +3702,29 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) return hdr_len + skb_gso_transport_seglen(skb); } +/* Local Checksum Offload. + * Compute outer checksum based on the assumption that the + * inner checksum will be offloaded later. + * Fill in outer checksum adjustment (e.g. with sum of outer + * pseudo-header) before calling. + * Also ensure that inner checksum is in linear data area. + */ +static inline __wsum lco_csum(struct sk_buff *skb) +{ + char *inner_csum_field; + __wsum csum; + + /* Start with complement of inner checksum adjustment */ + inner_csum_field = skb->data + skb_checksum_start_offset(skb) + + skb->csum_offset; + csum = ~csum_unfold(*(__force __sum16 *)inner_csum_field); + /* Add in checksum of our headers (incl. outer checksum + * adjustment filled in by caller) + */ + csum = skb_checksum(skb, 0, skb_checksum_start_offset(skb), csum); + /* The result is the checksum from skb->data to end of packet */ + return csum; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 859d415c0b2d..d74ce93de1fe 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -166,20 +166,20 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, return skb; } - /* If packet is not gso and we are resolving any partial checksum, + /* If packet is not gso and we are not offloading inner checksum, * clear encapsulation flag. This allows setting CHECKSUM_PARTIAL * on the outer header without confusing devices that implement * NETIF_F_IP_CSUM with encapsulation. */ - if (csum_help) - skb->encapsulation = 0; - if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) { + skb->encapsulation = 0; err = skb_checksum_help(skb); if (unlikely(err)) goto error; - } else if (skb->ip_summed != CHECKSUM_PARTIAL) + } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_NONE; + skb->encapsulation = 0; + } return skb; error: diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ac3cedb25a9f..a59341cf483e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -848,16 +848,18 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, { struct udphdr *uh = udp_hdr(skb); - if (nocheck) + if (nocheck) { uh->check = 0; - else if (skb_is_gso(skb)) + } else if (skb_is_gso(skb)) { uh->check = ~udp_v4_check(len, saddr, daddr, 0); - else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & - (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { - - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + uh->check = 0; + uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb)); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); @@ -865,8 +867,6 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, } else { __wsum csum; - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - uh->check = 0; csum = skb_checksum(skb, 0, len, 0); uh->check = udp_v4_check(len, saddr, daddr, csum); diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 9a4d7322fb22..4924bd704e89 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -98,11 +98,13 @@ void udp6_set_csum(bool nocheck, struct sk_buff *skb, uh->check = 0; else if (skb_is_gso(skb)) uh->check = ~udp_v6_check(len, saddr, daddr, 0); - else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { - - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - + else if (skb->ip_summed == CHECKSUM_PARTIAL) { + uh->check = 0; + uh->check = udp_v6_check(len, saddr, daddr, lco_csum(skb)); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); @@ -110,8 +112,6 @@ void udp6_set_csum(bool nocheck, struct sk_buff *skb, } else { __wsum csum; - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - uh->check = 0; csum = skb_checksum(skb, 0, len, 0); uh->check = udp_v6_check(len, saddr, daddr, csum); -- cgit v1.2.3 From e8ae7b000e64cf76283c72cae5e3ecd246618ef4 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 21:03:37 +0000 Subject: Documentation/networking: add checksum-offloads.txt to explain LCO Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- Documentation/networking/00-INDEX | 2 + Documentation/networking/checksum-offloads.txt | 119 +++++++++++++++++++++++++ include/linux/skbuff.h | 2 + 3 files changed, 123 insertions(+) create mode 100644 Documentation/networking/checksum-offloads.txt (limited to 'include/linux') diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index df27a1a50776..415154a487d0 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -44,6 +44,8 @@ can.txt - documentation on CAN protocol family. cdc_mbim.txt - 3G/LTE USB modem (Mobile Broadband Interface Model) +checksum-offloads.txt + - Explanation of checksum offloads; LCO, RCO cops.txt - info on the COPS LocalTalk Linux driver cs89x0.txt diff --git a/Documentation/networking/checksum-offloads.txt b/Documentation/networking/checksum-offloads.txt new file mode 100644 index 000000000000..de2a327766a7 --- /dev/null +++ b/Documentation/networking/checksum-offloads.txt @@ -0,0 +1,119 @@ +Checksum Offloads in the Linux Networking Stack + + +Introduction +============ + +This document describes a set of techniques in the Linux networking stack + to take advantage of checksum offload capabilities of various NICs. + +The following technologies are described: + * TX Checksum Offload + * LCO: Local Checksum Offload + * RCO: Remote Checksum Offload + +Things that should be documented here but aren't yet: + * RX Checksum Offload + * CHECKSUM_UNNECESSARY conversion + + +TX Checksum Offload +=================== + +The interface for offloading a transmit checksum to a device is explained + in detail in comments near the top of include/linux/skbuff.h. +In brief, it allows to request the device fill in a single ones-complement + checksum defined by the sk_buff fields skb->csum_start and + skb->csum_offset. The device should compute the 16-bit ones-complement + checksum (i.e. the 'IP-style' checksum) from csum_start to the end of the + packet, and fill in the result at (csum_start + csum_offset). +Because csum_offset cannot be negative, this ensures that the previous + value of the checksum field is included in the checksum computation, thus + it can be used to supply any needed corrections to the checksum (such as + the sum of the pseudo-header for UDP or TCP). +This interface only allows a single checksum to be offloaded. Where + encapsulation is used, the packet may have multiple checksum fields in + different header layers, and the rest will have to be handled by another + mechanism such as LCO or RCO. +No offloading of the IP header checksum is performed; it is always done in + software. This is OK because when we build the IP header, we obviously + have it in cache, so summing it isn't expensive. It's also rather short. +The requirements for GSO are more complicated, because when segmenting an + encapsulated packet both the inner and outer checksums may need to be + edited or recomputed for each resulting segment. See the skbuff.h comment + (section 'E') for more details. + +A driver declares its offload capabilities in netdev->hw_features; see + Documentation/networking/netdev-features for more. Note that a device + which only advertises NETIF_F_IP[V6]_CSUM must still obey the csum_start + and csum_offset given in the SKB; if it tries to deduce these itself in + hardware (as some NICs do) the driver should check that the values in the + SKB match those which the hardware will deduce, and if not, fall back to + checksumming in software instead (with skb_checksum_help or one of the + skb_csum_off_chk* functions as mentioned in include/linux/skbuff.h). This + is a pain, but that's what you get when hardware tries to be clever. + +The stack should, for the most part, assume that checksum offload is + supported by the underlying device. The only place that should check is + validate_xmit_skb(), and the functions it calls directly or indirectly. + That function compares the offload features requested by the SKB (which + may include other offloads besides TX Checksum Offload) and, if they are + not supported or enabled on the device (determined by netdev->features), + performs the corresponding offload in software. In the case of TX + Checksum Offload, that means calling skb_checksum_help(skb). + + +LCO: Local Checksum Offload +=========================== + +LCO is a technique for efficiently computing the outer checksum of an + encapsulated datagram when the inner checksum is due to be offloaded. +The ones-complement sum of a correctly checksummed TCP or UDP packet is + equal to the sum of the pseudo header, because everything else gets + 'cancelled out' by the checksum field. This is because the sum was + complemented before being written to the checksum field. +More generally, this holds in any case where the 'IP-style' ones complement + checksum is used, and thus any checksum that TX Checksum Offload supports. +That is, if we have set up TX Checksum Offload with a start/offset pair, we + know that _after the device has filled in that checksum_, the ones + complement sum from csum_start to the end of the packet will be equal to + _whatever value we put in the checksum field beforehand_. This allows us + to compute the outer checksum without looking at the payload: we simply + stop summing when we get to csum_start, then add the 16-bit word at + (csum_start + csum_offset). +Then, when the true inner checksum is filled in (either by hardware or by + skb_checksum_help()), the outer checksum will become correct by virtue of + the arithmetic. + +LCO is performed by the stack when constructing an outer UDP header for an + encapsulation such as VXLAN or GENEVE, in udp_set_csum(). Similarly for + the IPv6 equivalents, in udp6_set_csum(). +It is also performed when constructing an IPv4 GRE header, in + net/ipv4/ip_gre.c:build_header(). It is *not* currently performed when + constructing an IPv6 GRE header; the GRE checksum is computed over the + whole packet in net/ipv6/ip6_gre.c:ip6gre_xmit2(), but it should be + possible to use LCO here as IPv6 GRE still uses an IP-style checksum. +All of the LCO implementations use a helper function lco_csum(), in + include/linux/skbuff.h. + +LCO can safely be used for nested encapsulations; in this case, the outer + encapsulation layer will sum over both its own header and the 'middle' + header. This does mean that the 'middle' header will get summed multiple + times, but there doesn't seem to be a way to avoid that without incurring + bigger costs (e.g. in SKB bloat). + + +RCO: Remote Checksum Offload +============================ + +RCO is a technique for eliding the inner checksum of an encapsulated + datagram, allowing the outer checksum to be offloaded. It does, however, + involve a change to the encapsulation protocols, which the receiver must + also support. For this reason, it is disabled by default. +RCO is detailed in the following Internet-Drafts: +https://tools.ietf.org/html/draft-herbert-remotecsumoffload-00 +https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 +In Linux, RCO is implemented individually in each encapsulation protocol, + and most tunnel types have flags controlling its use. For instance, VXLAN + has the flag VXLAN_F_REMCSUM_TX (per struct vxlan_rdst) to indicate that + RCO should be used when transmitting to a given remote destination. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf906d1ce8a7..39206751463e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3705,6 +3705,8 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. + * See Documentation/networking/checksum-offloads.txt for + * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. -- cgit v1.2.3 From d4ab4286276fcd6c155bafdf4422b712068d2516 Mon Sep 17 00:00:00 2001 From: "Keller, Jacob E" Date: Mon, 8 Feb 2016 16:05:03 -0800 Subject: ethtool: correctly ensure {GS}CHANNELS doesn't conflict with GS{RXFH} Ethernet drivers implementing both {GS}RXFH and {GS}CHANNELS ethtool ops incorrectly allow SCHANNELS when it would conflict with the settings from SRXFH. This occurs because it is not possible for drivers to understand whether their Rx flow indirection table has been configured or is in the default state. In addition, drivers currently behave in various ways when increasing the number of Rx channels. Some drivers will always destroy the Rx flow indirection table when this occurs, whether it has been set by the user or not. Other drivers will attempt to preserve the table even if the user has never modified it from the default driver settings. Neither of these situation is desirable because it leads to unexpected behavior or loss of user configuration. The correct behavior is to simply return -EINVAL when SCHANNELS would conflict with the current Rx flow table settings. However, it should only do so if the current settings were modified by the user. If we required that the new settings never conflict with the current (default) Rx flow settings, we would force users to first reduce their Rx flow settings and then reduce the number of Rx channels. This patch proposes a solution implemented in net/core/ethtool.c which ensures that all drivers behave correctly. It checks whether the RXFH table has been configured to non-default settings, and stores this information in a private netdev flag. When the number of channels is requested to change, it first ensures that the current Rx flow table is not going to assign flows to now disabled channels. Signed-off-by: Jacob Keller Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +++++++ net/core/ethtool.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 219f53c30cb3..0499569c256d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1291,6 +1291,7 @@ struct net_device_ops { * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device + * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1318,6 +1319,7 @@ enum netdev_priv_flags { IFF_OPENVSWITCH = 1<<22, IFF_L3MDEV_SLAVE = 1<<23, IFF_TEAM = 1<<24, + IFF_RXFH_CONFIGURED = 1<<25, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1345,6 +1347,7 @@ enum netdev_priv_flags { #define IFF_OPENVSWITCH IFF_OPENVSWITCH #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE #define IFF_TEAM IFF_TEAM +#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED /** * struct net_device - The DEVICE structure. @@ -4048,6 +4051,11 @@ static inline bool netif_is_lag_port(const struct net_device *dev) return netif_is_bond_slave(dev) || netif_is_team_port(dev); } +static inline bool netif_is_rxfh_configured(const struct net_device *dev) +{ + return dev->priv_flags & IFF_RXFH_CONFIGURED; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 453c803f1c87..379bdc59b1c8 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -642,6 +642,37 @@ void netdev_rss_key_fill(void *buffer, size_t len) } EXPORT_SYMBOL(netdev_rss_key_fill); +static int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) +{ + u32 dev_size, current_max = 0; + u32 *indir; + int ret; + + if (!dev->ethtool_ops->get_rxfh_indir_size || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; + dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + if (dev_size == 0) + return -EOPNOTSUPP; + + indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); + if (!indir) + return -ENOMEM; + + ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); + if (ret) + goto out; + + while (dev_size--) + current_max = max(current_max, indir[dev_size]); + + *max = current_max; + +out: + kfree(indir); + return ret; +} + static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, void __user *useraddr) { @@ -738,6 +769,14 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, } ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE); + if (ret) + goto out; + + /* indicate whether rxfh was set to default */ + if (user_size == 0) + dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + else + dev->priv_flags |= IFF_RXFH_CONFIGURED; out: kfree(indir); @@ -897,6 +936,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc); + if (ret) + goto out; + + /* indicate whether rxfh was set to default */ + if (rxfh.indir_size == 0) + dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) + dev->priv_flags |= IFF_RXFH_CONFIGURED; out: kfree(rss_config); @@ -1228,6 +1275,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, void __user *useraddr) { struct ethtool_channels channels; + u32 max_rx_in_use = 0; if (!dev->ethtool_ops->set_channels) return -EOPNOTSUPP; @@ -1235,6 +1283,13 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, if (copy_from_user(&channels, useraddr, sizeof(channels))) return -EFAULT; + /* ensure the new Rx count fits within the configured Rx flow + * indirection table settings */ + if (netif_is_rxfh_configured(dev) && + !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && + (channels.combined_count + channels.rx_count) <= max_rx_in_use) + return -EINVAL; + return dev->ethtool_ops->set_channels(dev, &channels); } -- cgit v1.2.3 From e4c6734eaab90695db0ea8456307790cb0c1ccb5 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:16:15 -0800 Subject: net: rework ndo tc op to consume additional qdisc handle parameter The ndo_setup_tc() op was added to support drivers offloading tx qdiscs however only support for mqprio was ever added. So we only ever added support for passing the number of traffic classes to the driver. This patch generalizes the ndo_setup_tc op so that a handle can be provided to indicate if the offload is for ingress or egress or potentially even child qdiscs. CC: Murali Karicheri CC: Shradha Shah CC: Or Gerlitz CC: Ariel Elior CC: Jeff Kirsher CC: Bruce Allan CC: Jesse Brandeburg CC: Don Skidmore Signed-off-by: John Fastabend Acked-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 5 ++++- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 7 +++++++ drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 1 + drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 ++++- drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 10 +++++++++- drivers/net/ethernet/intel/i40e/i40e.h | 2 +- drivers/net/ethernet/intel/i40e/i40e_fcoe.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 17 ++++++++++++----- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 11 ++++++++++- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 12 ++++++++++-- drivers/net/ethernet/sfc/efx.h | 2 +- drivers/net/ethernet/sfc/tx.c | 5 ++++- drivers/net/ethernet/ti/netcp_core.c | 5 ++++- include/linux/netdevice.h | 3 ++- net/sched/sch_mqprio.c | 5 +++-- 16 files changed, 74 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 8a9b493566c9..9955cae3cabc 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1626,12 +1626,15 @@ static void xgbe_poll_controller(struct net_device *netdev) } #endif /* End CONFIG_NET_POLL_CONTROLLER */ -static int xgbe_setup_tc(struct net_device *netdev, u8 tc) +static int xgbe_setup_tc(struct net_device *netdev, u32 handle, u8 tc) { struct xgbe_prv_data *pdata = netdev_priv(netdev); unsigned int offset, queue; u8 i; + if (handle != TC_H_ROOT) + return -EINVAL; + if (tc && (tc != pdata->hw_feat.tc_cnt)) return -EINVAL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 9e42bcaf9917..b262cba34dfa 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -4272,6 +4272,13 @@ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc) return 0; } +int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u8 num_tc) +{ + if (handle != TC_H_ROOT) + return -EINVAL; + return bnx2x_setup_tc(dev, num_tc); +} + /* called with rtnl_lock */ int bnx2x_change_mac_addr(struct net_device *dev, void *p) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 37369865ca6d..60a4109dcdeb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -486,6 +486,7 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev); /* setup_tc callback */ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc); +int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u8 num_tc); int bnx2x_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index c5845252c920..81fc51c4ec2b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13061,7 +13061,7 @@ static const struct net_device_ops bnx2x_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = poll_bnx2x, #endif - .ndo_setup_tc = bnx2x_setup_tc, + .ndo_setup_tc = __bnx2x_setup_tc, #ifdef CONFIG_BNX2X_SRIOV .ndo_set_vf_mac = bnx2x_set_vf_mac, .ndo_set_vf_vlan = bnx2x_set_vf_vlan, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5dc89e527e7d..ff08faf44ee5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5370,10 +5370,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu) return 0; } -static int bnxt_setup_tc(struct net_device *dev, u8 tc) +static int bnxt_setup_tc(struct net_device *dev, u32 handle, u8 tc) { struct bnxt *bp = netdev_priv(dev); + if (handle != TC_H_ROOT) + return -EINVAL; + if (tc > bp->max_tc) { netdev_err(dev, "too many traffic classes requested: %d Max supported is %d\n", tc, bp->max_tc); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 662569d5b7c0..12701a492325 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1204,6 +1204,14 @@ err_queueing_scheme: return err; } +static int __fm10k_setup_tc(struct net_device *dev, u32 handle, u8 tc) +{ + if (handle != TC_H_ROOT) + return -EINVAL; + + return fm10k_setup_tc(dev, tc); +} + static int fm10k_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) { switch (cmd) { @@ -1386,7 +1394,7 @@ static const struct net_device_ops fm10k_netdev_ops = { .ndo_vlan_rx_kill_vid = fm10k_vlan_rx_kill_vid, .ndo_set_rx_mode = fm10k_set_rx_mode, .ndo_get_stats64 = fm10k_get_stats64, - .ndo_setup_tc = fm10k_setup_tc, + .ndo_setup_tc = __fm10k_setup_tc, .ndo_set_vf_mac = fm10k_ndo_set_vf_mac, .ndo_set_vf_vlan = fm10k_ndo_set_vf_vlan, .ndo_set_vf_rate = fm10k_ndo_set_vf_bw, diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 53ed3bdd8363..ef9ca075d5e5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -788,7 +788,7 @@ struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr, bool is_vf, bool is_netdev); #ifdef I40E_FCOE int i40e_close(struct net_device *netdev); -int i40e_setup_tc(struct net_device *netdev, u8 tc); +int __i40e_setup_tc(struct net_device *netdev, u32 handle, u8 tc); void i40e_netpoll(struct net_device *netdev); int i40e_fcoe_enable(struct net_device *netdev); int i40e_fcoe_disable(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c index 579a46ca82df..7c66ce416ec7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c +++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c @@ -1457,7 +1457,7 @@ static const struct net_device_ops i40e_fcoe_netdev_ops = { .ndo_tx_timeout = i40e_tx_timeout, .ndo_vlan_rx_add_vid = i40e_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = i40e_vlan_rx_kill_vid, - .ndo_setup_tc = i40e_setup_tc, + .ndo_setup_tc = __i40e_setup_tc, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40e_netpoll, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 320b0491abd9..abcb6c152186 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5253,11 +5253,7 @@ void i40e_down(struct i40e_vsi *vsi) * @netdev: net device to configure * @tc: number of traffic classes to enable **/ -#ifdef I40E_FCOE -int i40e_setup_tc(struct net_device *netdev, u8 tc) -#else static int i40e_setup_tc(struct net_device *netdev, u8 tc) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -5310,6 +5306,17 @@ exit: return ret; } +#ifdef I40E_FCOE +int __i40e_setup_tc(struct net_device *netdev, u32 handle, u8 tc) +#else +static int __i40e_setup_tc(struct net_device *netdev, u32 handle, u8 tc) +#endif +{ + if (handle != TC_H_ROOT) + return -EINVAL; + return i40e_setup_tc(netdev, tc); +} + /** * i40e_open - Called when a network interface is made active * @netdev: network interface device structure @@ -8951,7 +8958,7 @@ static const struct net_device_ops i40e_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40e_netpoll, #endif - .ndo_setup_tc = i40e_setup_tc, + .ndo_setup_tc = __i40e_setup_tc, #ifdef I40E_FCOE .ndo_fcoe_enable = i40e_fcoe_enable, .ndo_fcoe_disable = i40e_fcoe_disable, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0c701b8438b6..1ba714efd78c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8200,6 +8200,15 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) return 0; } +int __ixgbe_setup_tc(struct net_device *dev, u32 handle, u8 tc) +{ + /* Only support egress tc setup for now */ + if (handle != TC_H_ROOT) + return -EINVAL; + + return ixgbe_setup_tc(dev, tc); +} + #ifdef CONFIG_PCI_IOV void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter) { @@ -8658,7 +8667,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_get_vf_config = ixgbe_ndo_get_vf_config, .ndo_get_stats64 = ixgbe_get_stats64, #ifdef CONFIG_IXGBE_DCB - .ndo_setup_tc = ixgbe_setup_tc, + .ndo_setup_tc = __ixgbe_setup_tc, #endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ixgbe_netpoll, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 0c7e3f69a73b..d5c6c16b9457 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -69,6 +69,14 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up) return 0; } +static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, u8 up) +{ + if (handle != TC_H_ROOT) + return -EINVAL; + + return mlx4_en_setup_tc(dev, up); +} + #ifdef CONFIG_RFS_ACCEL struct mlx4_en_filter { @@ -2466,7 +2474,7 @@ static const struct net_device_ops mlx4_netdev_ops = { #endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, - .ndo_setup_tc = mlx4_en_setup_tc, + .ndo_setup_tc = __mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif @@ -2504,7 +2512,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { #endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, - .ndo_setup_tc = mlx4_en_setup_tc, + .ndo_setup_tc = __mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 10827476bc0b..7815fa09b15d 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -32,7 +32,7 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); -int efx_setup_tc(struct net_device *net_dev, u8 num_tc); +int efx_setup_tc(struct net_device *net_dev, u32 handle, u8 num_tc); unsigned int efx_tx_max_skb_descs(struct efx_nic *efx); extern unsigned int efx_piobuf_size; extern bool efx_separate_tx_channels; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index f7a0ec1bca97..8f1d53e2aca7 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -562,7 +562,7 @@ void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue) efx->n_tx_channels : 0)); } -int efx_setup_tc(struct net_device *net_dev, u8 num_tc) +int efx_setup_tc(struct net_device *net_dev, u32 handle, u8 num_tc) { struct efx_nic *efx = netdev_priv(net_dev); struct efx_channel *channel; @@ -570,6 +570,9 @@ int efx_setup_tc(struct net_device *net_dev, u8 num_tc) unsigned tc; int rc; + if (handle != TC_H_ROOT) + return -EINVAL; + if (efx_nic_rev(efx) < EFX_REV_FALCON_B0 || num_tc > EFX_MAX_TX_TC) return -EINVAL; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index c61d66d38634..40cde814608b 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1835,13 +1835,16 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb, return 0; } -static int netcp_setup_tc(struct net_device *dev, u8 num_tc) +static int netcp_setup_tc(struct net_device *dev, u32 handle, u8 num_tc) { int i; /* setup tc must be called under rtnl lock */ ASSERT_RTNL(); + if (handle != TC_H_ROOT) + return -EINVAL; + /* Sanity-check the number of traffic classes requested */ if ((dev->real_num_tx_queues <= 1) || (dev->real_num_tx_queues < num_tc)) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0499569c256d..48928b6f9cb6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -51,6 +51,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -1150,7 +1151,7 @@ struct net_device_ops { int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); - int (*ndo_setup_tc)(struct net_device *dev, u8 tc); + int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u8 tc); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index ad70ecf57ce7..f5a0e8a4dbd7 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -39,7 +39,7 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) - dev->netdev_ops->ndo_setup_tc(dev, 0); + dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0); else netdev_set_num_tc(dev, 0); } @@ -141,7 +141,8 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) */ if (qopt->hw) { priv->hw_owned = 1; - err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc); + err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, + qopt->num_tc); if (err) goto err; } else { -- cgit v1.2.3 From 16e5cc647173a97e33b3e3ba81f73eb455561794 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:16:43 -0800 Subject: net: rework setup_tc ndo op to consume general tc operand This patch updates setup_tc so we can pass additional parameters into the ndo op in a generic way. To do this we provide structured union and type flag. This lets each classifier and qdisc provide its own set of attributes without having to add new ndo ops or grow the signature of the callback. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 9 ++++++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 7 ++++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 ++- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++-- drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 7 ++++--- drivers/net/ethernet/intel/i40e/i40e.h | 3 ++- drivers/net/ethernet/intel/i40e/i40e_main.c | 10 ++++++---- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 7 ++++--- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 7 ++++--- drivers/net/ethernet/sfc/efx.h | 3 ++- drivers/net/ethernet/sfc/tx.c | 9 ++++++--- drivers/net/ethernet/ti/netcp_core.c | 13 +++++++------ include/linux/netdevice.h | 20 +++++++++++++++++++- net/sched/sch_mqprio.c | 9 ++++++--- 14 files changed, 78 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 9955cae3cabc..cfd3f7efda1c 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1626,15 +1626,18 @@ static void xgbe_poll_controller(struct net_device *netdev) } #endif /* End CONFIG_NET_POLL_CONTROLLER */ -static int xgbe_setup_tc(struct net_device *netdev, u32 handle, u8 tc) +static int xgbe_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, + struct tc_to_netdev *tc_to_netdev) { struct xgbe_prv_data *pdata = netdev_priv(netdev); unsigned int offset, queue; - u8 i; + u8 i, tc; - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || tc_to_netdev->type != TC_SETUP_MQPRIO) return -EINVAL; + tc = tc_to_netdev->tc; + if (tc && (tc != pdata->hw_feat.tc_cnt)) return -EINVAL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index b262cba34dfa..45843d150868 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -4272,11 +4272,12 @@ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc) return 0; } -int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u8 num_tc) +int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) { - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return bnx2x_setup_tc(dev, num_tc); + return bnx2x_setup_tc(dev, tc->tc); } /* called with rtnl_lock */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 60a4109dcdeb..0e68fadecfdb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -486,7 +486,8 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev); /* setup_tc callback */ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc); -int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u8 num_tc); +int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc); int bnx2x_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ff08faf44ee5..169920aa39f3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5370,13 +5370,17 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu) return 0; } -static int bnxt_setup_tc(struct net_device *dev, u32 handle, u8 tc) +static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *ntc) { struct bnxt *bp = netdev_priv(dev); + u8 tc; - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || ntc->type != TC_SETUP_MQPRIO) return -EINVAL; + tc = ntc->tc; + if (tc > bp->max_tc) { netdev_err(dev, "too many traffic classes requested: %d Max supported is %d\n", tc, bp->max_tc); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 12701a492325..dc1a82148ff0 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1204,12 +1204,13 @@ err_queueing_scheme: return err; } -static int __fm10k_setup_tc(struct net_device *dev, u32 handle, u8 tc) +static int __fm10k_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) { - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return fm10k_setup_tc(dev, tc); + return fm10k_setup_tc(dev, tc->tc); } static int fm10k_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index ef9ca075d5e5..933c4b3d92c8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -788,7 +788,8 @@ struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr, bool is_vf, bool is_netdev); #ifdef I40E_FCOE int i40e_close(struct net_device *netdev); -int __i40e_setup_tc(struct net_device *netdev, u32 handle, u8 tc); +int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, + struct tc_to_netdev *tc); void i40e_netpoll(struct net_device *netdev); int i40e_fcoe_enable(struct net_device *netdev); int i40e_fcoe_disable(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index abcb6c152186..257d16207976 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5307,14 +5307,16 @@ exit: } #ifdef I40E_FCOE -int __i40e_setup_tc(struct net_device *netdev, u32 handle, u8 tc) +int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) #else -static int __i40e_setup_tc(struct net_device *netdev, u32 handle, u8 tc) +static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) #endif { - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return i40e_setup_tc(netdev, tc); + return i40e_setup_tc(netdev, tc->tc); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 1ba714efd78c..dca2298f4c36 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8200,13 +8200,14 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) return 0; } -int __ixgbe_setup_tc(struct net_device *dev, u32 handle, u8 tc) +int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) { /* Only support egress tc setup for now */ - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return ixgbe_setup_tc(dev, tc); + return ixgbe_setup_tc(dev, tc->tc); } #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index d5c6c16b9457..01d6a9695586 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -69,12 +69,13 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up) return 0; } -static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, u8 up) +static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) { - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return mlx4_en_setup_tc(dev, up); + return mlx4_en_setup_tc(dev, tc->tc); } #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 7815fa09b15d..5e3f93f04e62 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -32,7 +32,8 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); -int efx_setup_tc(struct net_device *net_dev, u32 handle, u8 num_tc); +int efx_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc); unsigned int efx_tx_max_skb_descs(struct efx_nic *efx); extern unsigned int efx_piobuf_size; extern bool efx_separate_tx_channels; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 8f1d53e2aca7..2cdb5718ed66 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -562,17 +562,20 @@ void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue) efx->n_tx_channels : 0)); } -int efx_setup_tc(struct net_device *net_dev, u32 handle, u8 num_tc) +int efx_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto, + struct tc_to_netdev *ntc) { struct efx_nic *efx = netdev_priv(net_dev); struct efx_channel *channel; struct efx_tx_queue *tx_queue; - unsigned tc; + unsigned tc, num_tc; int rc; - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || ntc->type != TC_SETUP_MQPRIO) return -EINVAL; + num_tc = ntc->tc; + if (efx_nic_rev(efx) < EFX_REV_FALCON_B0 || num_tc > EFX_MAX_TX_TC) return -EINVAL; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 40cde814608b..8586a2034019 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1835,25 +1835,26 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb, return 0; } -static int netcp_setup_tc(struct net_device *dev, u32 handle, u8 num_tc) +static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev tc) { int i; /* setup tc must be called under rtnl lock */ ASSERT_RTNL(); - if (handle != TC_H_ROOT) + if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) return -EINVAL; /* Sanity-check the number of traffic classes requested */ if ((dev->real_num_tx_queues <= 1) || - (dev->real_num_tx_queues < num_tc)) + (dev->real_num_tx_queues < tc->tc)) return -EINVAL; /* Configure traffic class to queue mappings */ - if (num_tc) { - netdev_set_num_tc(dev, num_tc); - for (i = 0; i < num_tc; i++) + if (tc->tc) { + netdev_set_num_tc(dev, tc->tc); + for (i = 0; i < tc->tc; i++) netdev_set_tc_queue(dev, i, 1, i); } else { netdev_reset_tc(dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 48928b6f9cb6..e396060f815f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -779,6 +779,21 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); +/* This structure holds attributes of qdisc and classifiers + * that are being passed to the netdevice through the setup_tc op. + */ +enum { + TC_SETUP_MQPRIO, +}; + +struct tc_to_netdev { + unsigned int type; + union { + u8 tc; + }; +}; + + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1151,7 +1166,10 @@ struct net_device_ops { int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); - int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u8 tc); + int (*ndo_setup_tc)(struct net_device *dev, + u32 handle, + __be16 protocol, + struct tc_to_netdev *tc); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index f5a0e8a4dbd7..f9947d1f4952 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -28,6 +28,7 @@ static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); + struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO}; unsigned int ntx; if (priv->qdiscs) { @@ -39,7 +40,7 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) - dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0); + dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); else netdev_set_num_tc(dev, 0); } @@ -140,9 +141,11 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { + struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO, + .tc = qopt->num_tc}; + priv->hw_owned = 1; - err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, - qopt->num_tc); + err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc); if (err) goto err; } else { -- cgit v1.2.3 From a1b7c5fd7fe98f51fbbc393ee1fc4c1cdb2f0119 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:17:09 -0800 Subject: net: sched: add cls_u32 offload hooks for netdevs This patch allows netdev drivers to consume cls_u32 offloads via the ndo_setup_tc ndo op. This works aligns with how network drivers have been doing qdisc offloads for mqprio. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++- include/net/pkt_cls.h | 34 ++++++++++++++++ net/sched/cls_u32.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 136 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e396060f815f..47671ce04ac4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -779,17 +779,21 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -/* This structure holds attributes of qdisc and classifiers +/* These structures hold the attributes of qdisc and classifiers * that are being passed to the netdevice through the setup_tc op. */ enum { TC_SETUP_MQPRIO, + TC_SETUP_CLSU32, }; +struct tc_cls_u32_offload; + struct tc_to_netdev { unsigned int type; union { u8 tc; + struct tc_cls_u32_offload *cls_u32; }; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bc49967e1a68..59789ca6e2c8 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -358,4 +358,38 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +struct tc_cls_u32_knode { + struct tcf_exts *exts; + u8 fshift; + u32 handle; + u32 val; + u32 mask; + u32 link_handle; + struct tc_u32_sel *sel; +}; + +struct tc_cls_u32_hnode { + u32 handle; + u32 prio; + unsigned int divisor; +}; + +enum tc_clsu32_command { + TC_CLSU32_NEW_KNODE, + TC_CLSU32_REPLACE_KNODE, + TC_CLSU32_DELETE_KNODE, + TC_CLSU32_NEW_HNODE, + TC_CLSU32_REPLACE_HNODE, + TC_CLSU32_DELETE_HNODE, +}; + +struct tc_cls_u32_offload { + /* knode values */ + enum tc_clsu32_command command; + union { + struct tc_cls_u32_knode knode; + struct tc_cls_u32_hnode hnode; + }; +}; + #endif diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 4fbb67430ce4..d54bc942ea87 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -43,6 +43,7 @@ #include #include #include +#include struct tc_u_knode { struct tc_u_knode __rcu *next; @@ -424,6 +425,93 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) return 0; } +static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; + offload.cls_u32->knode.handle = handle; + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + +static void u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_NEW_HNODE; + offload.cls_u32->hnode.divisor = h->divisor; + offload.cls_u32->hnode.handle = h->handle; + offload.cls_u32->hnode.prio = h->prio; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + +static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_DELETE_HNODE; + offload.cls_u32->hnode.divisor = h->divisor; + offload.cls_u32->hnode.handle = h->handle; + offload.cls_u32->hnode.prio = h->prio; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + +static void u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_u32_offload u32_offload = {0}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSU32; + offload.cls_u32 = &u32_offload; + + if (dev->netdev_ops->ndo_setup_tc) { + offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE; + offload.cls_u32->knode.handle = n->handle; + offload.cls_u32->knode.fshift = n->fshift; +#ifdef CONFIG_CLS_U32_MARK + offload.cls_u32->knode.val = n->val; + offload.cls_u32->knode.mask = n->mask; +#else + offload.cls_u32->knode.val = 0; + offload.cls_u32->knode.mask = 0; +#endif + offload.cls_u32->knode.sel = &n->sel; + offload.cls_u32->knode.exts = &n->exts; + if (n->ht_down) + offload.cls_u32->knode.link_handle = n->ht_down->handle; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); + } +} + static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) { struct tc_u_knode *n; @@ -434,6 +522,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) RCU_INIT_POINTER(ht->ht[h], rtnl_dereference(n->next)); tcf_unbind_filter(tp, &n->res); + u32_remove_hw_knode(tp, n->handle); call_rcu(&n->rcu, u32_delete_key_freepf_rcu); } } @@ -454,6 +543,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) phn; hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { + u32_clear_hw_hnode(tp, ht); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -540,8 +630,10 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg) if (ht == NULL) return 0; - if (TC_U32_KEY(ht->handle)) + if (TC_U32_KEY(ht->handle)) { + u32_remove_hw_knode(tp, ht->handle); return u32_delete_key(tp, (struct tc_u_knode *)ht); + } if (root_ht == ht) return -EINVAL; @@ -769,6 +861,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); call_rcu(&n->rcu, u32_delete_key_rcu); + u32_replace_hw_knode(tp, new); return 0; } @@ -795,6 +888,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, ht); *arg = (unsigned long)ht; + + u32_replace_hw_hnode(tp, ht); return 0; } @@ -877,7 +972,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); - + u32_replace_hw_knode(tp, n); *arg = (unsigned long)n; return 0; } -- cgit v1.2.3 From 1c78c64e9c6f43a490427d55cd2d213b7c6795c1 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Feb 2016 21:17:37 -0800 Subject: net: add tc offload feature flag Its useful to turn off the qdisc offload feature at a per device level. This gives us a big hammer to enable/disable offloading. More fine grained control (i.e. per rule) may be supported later. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 3 +++ net/core/ethtool.c | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index d9654f0eecb3..a734bf43d190 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -67,6 +67,8 @@ enum { NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_BUSY_POLL_BIT, /* Busy poll */ + NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ + /* * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/core/ethtool.c and maybe @@ -124,6 +126,7 @@ enum { #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) +#define NETIF_F_HW_TC __NETIF_F(HW_TC) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 65f907aea777..c2d3118b1395 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -98,6 +98,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", [NETIF_F_BUSY_POLL_BIT] = "busy-poll", + [NETIF_F_HW_TC_BIT] = "hw-tc-offload", }; static const char -- cgit v1.2.3 From fc48b7a6148af974b49db145812a8b060324a503 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 15 Feb 2016 13:22:35 -0500 Subject: qed/qede: use 8.7.3.0 FW. This patch moves the qed* driver into utilizing the 8.7.3.0 FW. This new FW is required for a lot of new SW features, including: - Vlan filtering offload - Encapsulation offload support - HW ingress aggregations As well as paving the way for the possibility of adding storage protocols in the future. V2: - Fix kbuild test robot error/warnings. Signed-off-by: Yuval Mintz Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Manish Chopra Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 43 +- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 3 +- drivers/net/ethernet/qlogic/qed/qed_dev.c | 88 +- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 2690 +++++++++----------- .../net/ethernet/qlogic/qed/qed_init_fw_funcs.c | 22 +- drivers/net/ethernet/qlogic/qed/qed_init_ops.c | 155 +- drivers/net/ethernet/qlogic/qed/qed_l2.c | 13 +- drivers/net/ethernet/qlogic/qed/qed_main.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 37 +- drivers/net/ethernet/qlogic/qed/qed_sp.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 17 +- drivers/net/ethernet/qlogic/qede/qede.h | 8 +- drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 6 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 264 +- include/linux/qed/common_hsi.h | 36 +- include/linux/qed/eth_common.h | 171 +- include/linux/qed/qed_if.h | 8 +- 17 files changed, 1795 insertions(+), 1770 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 1292c360390c..d34da638b5d5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -70,8 +70,8 @@ struct qed_sb_sp_info; struct qed_mcp_info; struct qed_rt_data { - u32 init_val; - bool b_valid; + u32 *init_val; + bool *b_valid; }; /* The PCI personality is not quite synonymous to protocol ID: @@ -120,6 +120,10 @@ enum QED_PORT_MODE { QED_PORT_MODE_DE_1X25G }; +enum qed_dev_cap { + QED_DEV_CAP_ETH, +}; + struct qed_hw_info { /* PCI personality */ enum qed_pci_personality personality; @@ -151,6 +155,7 @@ struct qed_hw_info { u32 port_mode; u32 hw_mode; + unsigned long device_capabilities; }; struct qed_hw_cid_data { @@ -267,7 +272,7 @@ struct qed_hwfn { struct qed_hw_info hw_info; /* rt_array (for init-tool) */ - struct qed_rt_data *rt_data; + struct qed_rt_data rt_data; /* SPQ */ struct qed_spq *p_spq; @@ -350,9 +355,20 @@ struct qed_dev { char name[NAME_SIZE]; u8 type; -#define QED_DEV_TYPE_BB_A0 (0 << 0) -#define QED_DEV_TYPE_MASK (0x3) -#define QED_DEV_TYPE_SHIFT (0) +#define QED_DEV_TYPE_BB (0 << 0) +#define QED_DEV_TYPE_AH BIT(0) +/* Translate type/revision combo into the proper conditions */ +#define QED_IS_BB(dev) ((dev)->type == QED_DEV_TYPE_BB) +#define QED_IS_BB_A0(dev) (QED_IS_BB(dev) && \ + CHIP_REV_IS_A0(dev)) +#define QED_IS_BB_B0(dev) (QED_IS_BB(dev) && \ + CHIP_REV_IS_B0(dev)) + +#define QED_GET_TYPE(dev) (QED_IS_BB_A0(dev) ? CHIP_BB_A0 : \ + QED_IS_BB_B0(dev) ? CHIP_BB_B0 : CHIP_K2) + + u16 vendor_id; + u16 device_id; u16 chip_num; #define CHIP_NUM_MASK 0xffff @@ -361,6 +377,8 @@ struct qed_dev { u16 chip_rev; #define CHIP_REV_MASK 0xf #define CHIP_REV_SHIFT 12 +#define CHIP_REV_IS_A0(_cdev) (!(_cdev)->chip_rev) +#define CHIP_REV_IS_B0(_cdev) ((_cdev)->chip_rev == 1) u16 chip_metal; #define CHIP_METAL_MASK 0xff @@ -375,10 +393,10 @@ struct qed_dev { u8 num_funcs_in_port; u8 path_id; - enum mf_mode mf_mode; -#define IS_MF(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode != SF) -#define IS_MF_SI(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == MF_NPAR) -#define IS_MF_SD(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == MF_OVLAN) + enum qed_mf_mode mf_mode; +#define IS_MF_DEFAULT(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_DEFAULT) +#define IS_MF_SI(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_NPAR) +#define IS_MF_SD(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_OVLAN) int pcie_width; int pcie_speed; @@ -441,11 +459,6 @@ struct qed_dev { const struct firmware *firmware; }; -#define QED_GET_TYPE(dev) (((dev)->type & QED_DEV_TYPE_MASK) >> \ - QED_DEV_TYPE_SHIFT) -#define QED_IS_BB_A0(dev) (QED_GET_TYPE(dev) == QED_DEV_TYPE_BB_A0) -#define QED_IS_BB(dev) (QED_IS_BB_A0(dev)) - #define NUM_OF_SBS(dev) MAX_SB_PER_PATH_BB #define NUM_OF_ENG_PFS(dev) MAX_NUM_PFS_BB diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 7ccdb46c6764..d3f7a0215e7e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -581,7 +581,8 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn) params.num_pf_cids = iids.cids; params.start_pq = qm_info->start_pq; params.num_pf_pqs = qm_info->num_pqs; - params.start_vport = qm_info->num_vports; + params.start_vport = qm_info->start_vport; + params.num_vports = qm_info->num_vports; params.pf_wfq = qm_info->pf_wfq; params.pf_rl = qm_info->pf_rl; params.pq_params = qm_info->qm_pq_params; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 817bbd5476ff..bc17ed2c9cac 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -341,11 +341,6 @@ void qed_resc_setup(struct qed_dev *cdev) } } -#define FINAL_CLEANUP_CMD_OFFSET (0) -#define FINAL_CLEANUP_CMD (0x1) -#define FINAL_CLEANUP_VALID_OFFSET (6) -#define FINAL_CLEANUP_VFPF_ID_SHIFT (7) -#define FINAL_CLEANUP_COMP (0x2) #define FINAL_CLEANUP_POLL_CNT (100) #define FINAL_CLEANUP_POLL_TIME (10) int qed_final_cleanup(struct qed_hwfn *p_hwfn, @@ -355,12 +350,14 @@ int qed_final_cleanup(struct qed_hwfn *p_hwfn, u32 command = 0, addr, count = FINAL_CLEANUP_POLL_CNT; int rc = -EBUSY; - addr = GTT_BAR0_MAP_REG_USDM_RAM + USTORM_FLR_FINAL_ACK_OFFSET; + addr = GTT_BAR0_MAP_REG_USDM_RAM + + USTORM_FLR_FINAL_ACK_OFFSET(p_hwfn->rel_pf_id); - command |= FINAL_CLEANUP_CMD << FINAL_CLEANUP_CMD_OFFSET; - command |= 1 << FINAL_CLEANUP_VALID_OFFSET; - command |= id << FINAL_CLEANUP_VFPF_ID_SHIFT; - command |= FINAL_CLEANUP_COMP << SDM_OP_GEN_COMP_TYPE_SHIFT; + command |= X_FINAL_CLEANUP_AGG_INT << + SDM_AGG_INT_COMP_PARAMS_AGG_INT_INDEX_SHIFT; + command |= 1 << SDM_AGG_INT_COMP_PARAMS_AGG_VECTOR_ENABLE_SHIFT; + command |= id << SDM_AGG_INT_COMP_PARAMS_AGG_VECTOR_BIT_SHIFT; + command |= SDM_COMP_TYPE_AGG_INT << SDM_OP_GEN_COMP_TYPE_SHIFT; /* Make sure notification is not set before initiating final cleanup */ if (REG_RD(p_hwfn, addr)) { @@ -415,18 +412,16 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) } switch (p_hwfn->cdev->mf_mode) { - case SF: - hw_mode |= 1 << MODE_SF; + case QED_MF_DEFAULT: + case QED_MF_NPAR: + hw_mode |= 1 << MODE_MF_SI; break; - case MF_OVLAN: + case QED_MF_OVLAN: hw_mode |= 1 << MODE_MF_SD; break; - case MF_NPAR: - hw_mode |= 1 << MODE_MF_SI; - break; default: - DP_NOTICE(p_hwfn, "Unsupported MF mode, init as SF\n"); - hw_mode |= 1 << MODE_SF; + DP_NOTICE(p_hwfn, "Unsupported MF mode, init as DEFAULT\n"); + hw_mode |= 1 << MODE_MF_SI; } hw_mode |= 1 << MODE_ASIC; @@ -1018,8 +1013,7 @@ static void qed_hw_get_resc(struct qed_hwfn *p_hwfn) u32 *resc_num = p_hwfn->hw_info.resc_num; int num_funcs, i; - num_funcs = IS_MF(p_hwfn) ? MAX_NUM_PFS_BB - : p_hwfn->cdev->num_ports_in_engines; + num_funcs = MAX_NUM_PFS_BB; resc_num[QED_SB] = min_t(u32, (MAX_SB_PER_PATH_BB / num_funcs), @@ -1071,7 +1065,7 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u32 nvm_cfg1_offset, mf_mode, addr, generic_cont0, core_cfg; - u32 port_cfg_addr, link_temp, val, nvm_cfg_addr; + u32 port_cfg_addr, link_temp, nvm_cfg_addr, device_capabilities; struct qed_mcp_link_params *link; /* Read global nvm_cfg address */ @@ -1134,21 +1128,6 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, break; } - addr = MCP_REG_SCRATCH + nvm_cfg1_offset + - offsetof(struct nvm_cfg1, func[MCP_PF_ID(p_hwfn)]) + - offsetof(struct nvm_cfg1_func, device_id); - val = qed_rd(p_hwfn, p_ptt, addr); - - if (IS_MF(p_hwfn)) { - p_hwfn->hw_info.device_id = - (val & NVM_CFG1_FUNC_MF_VENDOR_DEVICE_ID_MASK) >> - NVM_CFG1_FUNC_MF_VENDOR_DEVICE_ID_OFFSET; - } else { - p_hwfn->hw_info.device_id = - (val & NVM_CFG1_FUNC_VENDOR_DEVICE_ID_MASK) >> - NVM_CFG1_FUNC_VENDOR_DEVICE_ID_OFFSET; - } - /* Read default link configuration */ link = &p_hwfn->mcp_info->link_input; port_cfg_addr = MCP_REG_SCRATCH + nvm_cfg1_offset + @@ -1220,18 +1199,28 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, switch (mf_mode) { case NVM_CFG1_GLOB_MF_MODE_MF_ALLOWED: - p_hwfn->cdev->mf_mode = MF_OVLAN; + p_hwfn->cdev->mf_mode = QED_MF_OVLAN; break; case NVM_CFG1_GLOB_MF_MODE_NPAR1_0: - p_hwfn->cdev->mf_mode = MF_NPAR; + p_hwfn->cdev->mf_mode = QED_MF_NPAR; break; - case NVM_CFG1_GLOB_MF_MODE_FORCED_SF: - p_hwfn->cdev->mf_mode = SF; + case NVM_CFG1_GLOB_MF_MODE_DEFAULT: + p_hwfn->cdev->mf_mode = QED_MF_DEFAULT; break; } DP_INFO(p_hwfn, "Multi function mode is %08x\n", p_hwfn->cdev->mf_mode); + /* Read Multi-function information from shmem */ + addr = MCP_REG_SCRATCH + nvm_cfg1_offset + + offsetof(struct nvm_cfg1, glob) + + offsetof(struct nvm_cfg1_glob, device_capabilities); + + device_capabilities = qed_rd(p_hwfn, p_ptt, addr); + if (device_capabilities & NVM_CFG1_GLOB_DEVICE_CAPABILITIES_ETHERNET) + __set_bit(QED_DEV_CAP_ETH, + &p_hwfn->hw_info.device_capabilities); + return qed_mcp_fill_shmem_func_info(p_hwfn, p_ptt); } @@ -1293,29 +1282,36 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, static void qed_get_dev_info(struct qed_dev *cdev) { + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); u32 tmp; - cdev->chip_num = (u16)qed_rd(cdev->hwfns, cdev->hwfns[0].p_main_ptt, + /* Read Vendor Id / Device Id */ + pci_read_config_word(cdev->pdev, PCI_VENDOR_ID, + &cdev->vendor_id); + pci_read_config_word(cdev->pdev, PCI_DEVICE_ID, + &cdev->device_id); + cdev->chip_num = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_NUM); - cdev->chip_rev = (u16)qed_rd(cdev->hwfns, cdev->hwfns[0].p_main_ptt, + cdev->chip_rev = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_REV); MASK_FIELD(CHIP_REV, cdev->chip_rev); + cdev->type = QED_DEV_TYPE_BB; /* Learn number of HW-functions */ - tmp = qed_rd(cdev->hwfns, cdev->hwfns[0].p_main_ptt, + tmp = qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CMT_ENABLED_FOR_PAIR); - if (tmp & (1 << cdev->hwfns[0].rel_pf_id)) { + if (tmp & (1 << p_hwfn->rel_pf_id)) { DP_NOTICE(cdev->hwfns, "device in CMT mode\n"); cdev->num_hwfns = 2; } else { cdev->num_hwfns = 1; } - cdev->chip_bond_id = qed_rd(cdev->hwfns, cdev->hwfns[0].p_main_ptt, + cdev->chip_bond_id = qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_TEST_REG) >> 4; MASK_FIELD(CHIP_BOND_ID, cdev->chip_bond_id); - cdev->chip_metal = (u16)qed_rd(cdev->hwfns, cdev->hwfns[0].p_main_ptt, + cdev->chip_metal = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt, MISCS_REG_CHIP_METAL); MASK_FIELD(CHIP_METAL, cdev->chip_metal); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 264e954675d1..49bbf696a16d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -34,6 +34,8 @@ enum common_event_opcode { COMMON_EVENT_RESERVED3, COMMON_EVENT_RESERVED4, COMMON_EVENT_RESERVED5, + COMMON_EVENT_RESERVED6, + COMMON_EVENT_EMPTY, MAX_COMMON_EVENT_OPCODE }; @@ -45,6 +47,7 @@ enum common_ramrod_cmd_id { COMMON_RAMROD_RESERVED, COMMON_RAMROD_RESERVED2, COMMON_RAMROD_RESERVED3, + COMMON_RAMROD_EMPTY, MAX_COMMON_RAMROD_CMD_ID }; @@ -331,6 +334,179 @@ struct xstorm_core_conn_ag_ctx { __le16 word15 /* word15 */; }; +struct tstorm_core_conn_ag_ctx { + u8 byte0 /* cdu_validation */; + u8 byte1 /* state */; + u8 flags0; +#define TSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ +#define TSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ +#define TSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_CORE_CONN_AG_CTX_BIT2_MASK 0x1 /* bit2 */ +#define TSTORM_CORE_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_BIT3_MASK 0x1 /* bit3 */ +#define TSTORM_CORE_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_CORE_CONN_AG_CTX_BIT4_MASK 0x1 /* bit4 */ +#define TSTORM_CORE_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_BIT5_MASK 0x1 /* bit5 */ +#define TSTORM_CORE_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 /* timer0cf */ +#define TSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 6 + u8 flags1; +#define TSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 /* timer1cf */ +#define TSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ +#define TSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 /* timer_stop_all */ +#define TSTORM_CORE_CONN_AG_CTX_CF3_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 /* cf4 */ +#define TSTORM_CORE_CONN_AG_CTX_CF4_SHIFT 6 + u8 flags2; +#define TSTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 /* cf5 */ +#define TSTORM_CORE_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 /* cf6 */ +#define TSTORM_CORE_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF7_MASK 0x3 /* cf7 */ +#define TSTORM_CORE_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF8_MASK 0x3 /* cf8 */ +#define TSTORM_CORE_CONN_AG_CTX_CF8_SHIFT 6 + u8 flags3; +#define TSTORM_CORE_CONN_AG_CTX_CF9_MASK 0x3 /* cf9 */ +#define TSTORM_CORE_CONN_AG_CTX_CF9_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF10_MASK 0x3 /* cf10 */ +#define TSTORM_CORE_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ +#define TSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ +#define TSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ +#define TSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ +#define TSTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 7 + u8 flags4; +#define TSTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 /* cf4en */ +#define TSTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 /* cf5en */ +#define TSTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 /* cf6en */ +#define TSTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF7EN_MASK 0x1 /* cf7en */ +#define TSTORM_CORE_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_CORE_CONN_AG_CTX_CF8EN_MASK 0x1 /* cf8en */ +#define TSTORM_CORE_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF9EN_MASK 0x1 /* cf9en */ +#define TSTORM_CORE_CONN_AG_CTX_CF9EN_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_CF10EN_MASK 0x1 /* cf10en */ +#define TSTORM_CORE_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 + u8 flags5; +#define TSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 /* rule6en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ +#define TSTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 + __le32 reg0 /* reg0 */; + __le32 reg1 /* reg1 */; + __le32 reg2 /* reg2 */; + __le32 reg3 /* reg3 */; + __le32 reg4 /* reg4 */; + __le32 reg5 /* reg5 */; + __le32 reg6 /* reg6 */; + __le32 reg7 /* reg7 */; + __le32 reg8 /* reg8 */; + u8 byte2 /* byte2 */; + u8 byte3 /* byte3 */; + __le16 word0 /* word0 */; + u8 byte4 /* byte4 */; + u8 byte5 /* byte5 */; + __le16 word1 /* word1 */; + __le16 word2 /* conn_dpi */; + __le16 word3 /* word3 */; + __le32 reg9 /* reg9 */; + __le32 reg10 /* reg10 */; +}; + +struct ustorm_core_conn_ag_ctx { + u8 reserved /* cdu_validation */; + u8 byte1 /* state */; + u8 flags0; +#define USTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ +#define USTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ +#define USTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 /* timer0cf */ +#define USTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 /* timer1cf */ +#define USTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ +#define USTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 + u8 flags1; +#define USTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 /* timer_stop_all */ +#define USTORM_CORE_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 /* cf4 */ +#define USTORM_CORE_CONN_AG_CTX_CF4_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 /* cf5 */ +#define USTORM_CORE_CONN_AG_CTX_CF5_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 /* cf6 */ +#define USTORM_CORE_CONN_AG_CTX_CF6_SHIFT 6 + u8 flags2; +#define USTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ +#define USTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ +#define USTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ +#define USTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ +#define USTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 /* cf4en */ +#define USTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 /* cf5en */ +#define USTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 5 +#define USTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 /* cf6en */ +#define USTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ +#define USTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 + u8 flags3; +#define USTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ +#define USTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ +#define USTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ +#define USTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ +#define USTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ +#define USTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 /* rule6en */ +#define USTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ +#define USTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ +#define USTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 + u8 byte2 /* byte2 */; + u8 byte3 /* byte3 */; + __le16 word0 /* conn_dpi */; + __le16 word1 /* word1 */; + __le32 rx_producers /* reg0 */; + __le32 reg1 /* reg1 */; + __le32 reg2 /* reg2 */; + __le32 reg3 /* reg3 */; + __le16 word2 /* word2 */; + __le16 word3 /* word3 */; +}; + /* The core storm context for the Mstorm */ struct mstorm_core_conn_st_ctx { __le32 reserved[24]; @@ -349,8 +525,9 @@ struct core_conn_context { struct regpair pstorm_st_padding[2]; struct xstorm_core_conn_st_ctx xstorm_st_context; struct xstorm_core_conn_ag_ctx xstorm_ag_context; + struct tstorm_core_conn_ag_ctx tstorm_ag_context; + struct ustorm_core_conn_ag_ctx ustorm_ag_context; struct mstorm_core_conn_st_ctx mstorm_st_context; - struct regpair mstorm_st_padding[2]; struct ustorm_core_conn_st_ctx ustorm_st_context; struct regpair ustorm_st_padding[2] /* padding */; }; @@ -397,10 +574,12 @@ union event_ring_element { }; enum personality_type { + BAD_PERSONALITY_TYP, PERSONALITY_RESERVED, PERSONALITY_RESERVED2, PERSONALITY_RDMA_AND_ETH /* Roce or Iwarp */, PERSONALITY_RESERVED3, + PERSONALITY_CORE, PERSONALITY_ETH /* Ethernet */, PERSONALITY_RESERVED4, MAX_PERSONALITY_TYPE @@ -570,7 +749,7 @@ enum block_addr { GRCBASE_NWM = 0x800000, GRCBASE_NWS = 0x700000, GRCBASE_MS = 0x6a0000, - GRCBASE_PHY_PCIE = 0x618000, + GRCBASE_PHY_PCIE = 0x620000, GRCBASE_MISC_AEU = 0x8000, GRCBASE_BAR0_MAP = 0x1c00000, MAX_BLOCK_ADDR @@ -795,13 +974,13 @@ enum init_modes { MODE_RESERVED3, MODE_RESERVED4, MODE_RESERVED5, + MODE_RESERVED6, MODE_SF, MODE_MF_SD, MODE_MF_SI, MODE_PORTS_PER_ENG_1, MODE_PORTS_PER_ENG_2, MODE_PORTS_PER_ENG_4, - MODE_40G, MODE_100G, MODE_EAGLE_ENG1_WORKAROUND, MAX_INIT_MODES @@ -816,43 +995,6 @@ enum init_phases { MAX_INIT_PHASES }; -struct mstorm_core_conn_ag_ctx { - u8 byte0 /* cdu_validation */; - u8 byte1 /* state */; - u8 flags0; -#define MSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ -#define MSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define MSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ -#define MSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define MSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 /* cf0 */ -#define MSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 -#define MSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 /* cf1 */ -#define MSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 -#define MSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 /* cf2 */ -#define MSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 - u8 flags1; -#define MSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ -#define MSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define MSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ -#define MSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define MSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ -#define MSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define MSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ -#define MSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define MSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ -#define MSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define MSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ -#define MSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define MSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ -#define MSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define MSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ -#define MSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 7 - __le16 word0 /* word0 */; - __le16 word1 /* word1 */; - __le32 reg0 /* reg0 */; - __le32 reg1 /* reg1 */; -}; - /* per encapsulation type enabling flags */ struct prs_reg_encapsulation_type_en { u8 flags; @@ -927,250 +1069,44 @@ struct qm_rf_opportunistic_mask { }; /* QM hardware structure of QM map memory */ -struct qm_rf_pq_map { - u32 reg; -#define QM_RF_PQ_MAP_PQ_VALID_MASK 0x1 /* PQ active */ -#define QM_RF_PQ_MAP_PQ_VALID_SHIFT 0 -#define QM_RF_PQ_MAP_RL_ID_MASK 0xFF /* RL ID */ -#define QM_RF_PQ_MAP_RL_ID_SHIFT 1 -#define QM_RF_PQ_MAP_VP_PQ_ID_MASK 0x1FF -#define QM_RF_PQ_MAP_VP_PQ_ID_SHIFT 9 -#define QM_RF_PQ_MAP_VOQ_MASK 0x1F /* VOQ */ -#define QM_RF_PQ_MAP_VOQ_SHIFT 18 -#define QM_RF_PQ_MAP_WRR_WEIGHT_GROUP_MASK 0x3 /* WRR weight */ -#define QM_RF_PQ_MAP_WRR_WEIGHT_GROUP_SHIFT 23 -#define QM_RF_PQ_MAP_RL_VALID_MASK 0x1 /* RL active */ -#define QM_RF_PQ_MAP_RL_VALID_SHIFT 25 -#define QM_RF_PQ_MAP_RESERVED_MASK 0x3F -#define QM_RF_PQ_MAP_RESERVED_SHIFT 26 -}; - -/* SDM operation gen command (generate aggregative interrupt) */ -struct sdm_op_gen { - __le32 command; -#define SDM_OP_GEN_COMP_PARAM_MASK 0xFFFF /* completion parameters 0-15 */ -#define SDM_OP_GEN_COMP_PARAM_SHIFT 0 -#define SDM_OP_GEN_COMP_TYPE_MASK 0xF /* completion type 16-19 */ -#define SDM_OP_GEN_COMP_TYPE_SHIFT 16 -#define SDM_OP_GEN_RESERVED_MASK 0xFFF /* reserved 20-31 */ -#define SDM_OP_GEN_RESERVED_SHIFT 20 -}; - -struct tstorm_core_conn_ag_ctx { - u8 byte0 /* cdu_validation */; - u8 byte1 /* state */; - u8 flags0; -#define TSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ -#define TSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define TSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ -#define TSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define TSTORM_CORE_CONN_AG_CTX_BIT2_MASK 0x1 /* bit2 */ -#define TSTORM_CORE_CONN_AG_CTX_BIT2_SHIFT 2 -#define TSTORM_CORE_CONN_AG_CTX_BIT3_MASK 0x1 /* bit3 */ -#define TSTORM_CORE_CONN_AG_CTX_BIT3_SHIFT 3 -#define TSTORM_CORE_CONN_AG_CTX_BIT4_MASK 0x1 /* bit4 */ -#define TSTORM_CORE_CONN_AG_CTX_BIT4_SHIFT 4 -#define TSTORM_CORE_CONN_AG_CTX_BIT5_MASK 0x1 /* bit5 */ -#define TSTORM_CORE_CONN_AG_CTX_BIT5_SHIFT 5 -#define TSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 /* timer0cf */ -#define TSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 6 - u8 flags1; -#define TSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 /* timer1cf */ -#define TSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 0 -#define TSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ -#define TSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 2 -#define TSTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 /* timer_stop_all */ -#define TSTORM_CORE_CONN_AG_CTX_CF3_SHIFT 4 -#define TSTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 /* cf4 */ -#define TSTORM_CORE_CONN_AG_CTX_CF4_SHIFT 6 - u8 flags2; -#define TSTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 /* cf5 */ -#define TSTORM_CORE_CONN_AG_CTX_CF5_SHIFT 0 -#define TSTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 /* cf6 */ -#define TSTORM_CORE_CONN_AG_CTX_CF6_SHIFT 2 -#define TSTORM_CORE_CONN_AG_CTX_CF7_MASK 0x3 /* cf7 */ -#define TSTORM_CORE_CONN_AG_CTX_CF7_SHIFT 4 -#define TSTORM_CORE_CONN_AG_CTX_CF8_MASK 0x3 /* cf8 */ -#define TSTORM_CORE_CONN_AG_CTX_CF8_SHIFT 6 - u8 flags3; -#define TSTORM_CORE_CONN_AG_CTX_CF9_MASK 0x3 /* cf9 */ -#define TSTORM_CORE_CONN_AG_CTX_CF9_SHIFT 0 -#define TSTORM_CORE_CONN_AG_CTX_CF10_MASK 0x3 /* cf10 */ -#define TSTORM_CORE_CONN_AG_CTX_CF10_SHIFT 2 -#define TSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ -#define TSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 4 -#define TSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ -#define TSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 5 -#define TSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ -#define TSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 6 -#define TSTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ -#define TSTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 7 - u8 flags4; -#define TSTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 /* cf4en */ -#define TSTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 0 -#define TSTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 /* cf5en */ -#define TSTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 1 -#define TSTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 /* cf6en */ -#define TSTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 2 -#define TSTORM_CORE_CONN_AG_CTX_CF7EN_MASK 0x1 /* cf7en */ -#define TSTORM_CORE_CONN_AG_CTX_CF7EN_SHIFT 3 -#define TSTORM_CORE_CONN_AG_CTX_CF8EN_MASK 0x1 /* cf8en */ -#define TSTORM_CORE_CONN_AG_CTX_CF8EN_SHIFT 4 -#define TSTORM_CORE_CONN_AG_CTX_CF9EN_MASK 0x1 /* cf9en */ -#define TSTORM_CORE_CONN_AG_CTX_CF9EN_SHIFT 5 -#define TSTORM_CORE_CONN_AG_CTX_CF10EN_MASK 0x1 /* cf10en */ -#define TSTORM_CORE_CONN_AG_CTX_CF10EN_SHIFT 6 -#define TSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 - u8 flags5; -#define TSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define TSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define TSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define TSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define TSTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define TSTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 /* rule6en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define TSTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define TSTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ -#define TSTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 - __le32 reg0 /* reg0 */; - __le32 reg1 /* reg1 */; - __le32 reg2 /* reg2 */; - __le32 reg3 /* reg3 */; - __le32 reg4 /* reg4 */; - __le32 reg5 /* reg5 */; - __le32 reg6 /* reg6 */; - __le32 reg7 /* reg7 */; - __le32 reg8 /* reg8 */; - u8 byte2 /* byte2 */; - u8 byte3 /* byte3 */; - __le16 word0 /* word0 */; - u8 byte4 /* byte4 */; - u8 byte5 /* byte5 */; - __le16 word1 /* word1 */; - __le16 word2 /* conn_dpi */; - __le16 word3 /* word3 */; - __le32 reg9 /* reg9 */; - __le32 reg10 /* reg10 */; +struct qm_rf_pq_map { + u32 reg; +#define QM_RF_PQ_MAP_PQ_VALID_MASK 0x1 /* PQ active */ +#define QM_RF_PQ_MAP_PQ_VALID_SHIFT 0 +#define QM_RF_PQ_MAP_RL_ID_MASK 0xFF /* RL ID */ +#define QM_RF_PQ_MAP_RL_ID_SHIFT 1 +#define QM_RF_PQ_MAP_VP_PQ_ID_MASK 0x1FF +#define QM_RF_PQ_MAP_VP_PQ_ID_SHIFT 9 +#define QM_RF_PQ_MAP_VOQ_MASK 0x1F /* VOQ */ +#define QM_RF_PQ_MAP_VOQ_SHIFT 18 +#define QM_RF_PQ_MAP_WRR_WEIGHT_GROUP_MASK 0x3 /* WRR weight */ +#define QM_RF_PQ_MAP_WRR_WEIGHT_GROUP_SHIFT 23 +#define QM_RF_PQ_MAP_RL_VALID_MASK 0x1 /* RL active */ +#define QM_RF_PQ_MAP_RL_VALID_SHIFT 25 +#define QM_RF_PQ_MAP_RESERVED_MASK 0x3F +#define QM_RF_PQ_MAP_RESERVED_SHIFT 26 }; -struct ustorm_core_conn_ag_ctx { - u8 reserved /* cdu_validation */; - u8 byte1 /* state */; - u8 flags0; -#define USTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ -#define USTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define USTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ -#define USTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define USTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 /* timer0cf */ -#define USTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 -#define USTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 /* timer1cf */ -#define USTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 -#define USTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ -#define USTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 - u8 flags1; -#define USTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 /* timer_stop_all */ -#define USTORM_CORE_CONN_AG_CTX_CF3_SHIFT 0 -#define USTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 /* cf4 */ -#define USTORM_CORE_CONN_AG_CTX_CF4_SHIFT 2 -#define USTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 /* cf5 */ -#define USTORM_CORE_CONN_AG_CTX_CF5_SHIFT 4 -#define USTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 /* cf6 */ -#define USTORM_CORE_CONN_AG_CTX_CF6_SHIFT 6 - u8 flags2; -#define USTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ -#define USTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define USTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ -#define USTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define USTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ -#define USTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define USTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ -#define USTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 3 -#define USTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 /* cf4en */ -#define USTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 4 -#define USTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 /* cf5en */ -#define USTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 5 -#define USTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 /* cf6en */ -#define USTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 6 -#define USTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ -#define USTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 - u8 flags3; -#define USTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ -#define USTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define USTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ -#define USTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define USTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ -#define USTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define USTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ -#define USTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define USTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ -#define USTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define USTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 /* rule6en */ -#define USTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define USTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ -#define USTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define USTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ -#define USTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 - u8 byte2 /* byte2 */; - u8 byte3 /* byte3 */; - __le16 word0 /* conn_dpi */; - __le16 word1 /* word1 */; - __le32 rx_producers /* reg0 */; - __le32 reg1 /* reg1 */; - __le32 reg2 /* reg2 */; - __le32 reg3 /* reg3 */; - __le16 word2 /* word2 */; - __le16 word3 /* word3 */; +/* Completion params for aggregated interrupt completion */ +struct sdm_agg_int_comp_params { + __le16 params; +#define SDM_AGG_INT_COMP_PARAMS_AGG_INT_INDEX_MASK 0x3F +#define SDM_AGG_INT_COMP_PARAMS_AGG_INT_INDEX_SHIFT 0 +#define SDM_AGG_INT_COMP_PARAMS_AGG_VECTOR_ENABLE_MASK 0x1 +#define SDM_AGG_INT_COMP_PARAMS_AGG_VECTOR_ENABLE_SHIFT 6 +#define SDM_AGG_INT_COMP_PARAMS_AGG_VECTOR_BIT_MASK 0x1FF +#define SDM_AGG_INT_COMP_PARAMS_AGG_VECTOR_BIT_SHIFT 7 }; -struct ystorm_core_conn_ag_ctx { - u8 byte0 /* cdu_validation */; - u8 byte1 /* state */; - u8 flags0; -#define YSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ -#define YSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define YSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ -#define YSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define YSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 /* cf0 */ -#define YSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 -#define YSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 /* cf1 */ -#define YSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 -#define YSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 /* cf2 */ -#define YSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 - u8 flags1; -#define YSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ -#define YSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define YSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ -#define YSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define YSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ -#define YSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define YSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ -#define YSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define YSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ -#define YSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define YSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ -#define YSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define YSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ -#define YSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define YSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ -#define YSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 7 - u8 byte2 /* byte2 */; - u8 byte3 /* byte3 */; - __le16 word0 /* word0 */; - __le32 reg0 /* reg0 */; - __le32 reg1 /* reg1 */; - __le16 word1 /* word1 */; - __le16 word2 /* word2 */; - __le16 word3 /* word3 */; - __le16 word4 /* word4 */; - __le32 reg2 /* reg2 */; - __le32 reg3 /* reg3 */; +/* SDM operation gen command (generate aggregative interrupt) */ +struct sdm_op_gen { + __le32 command; +#define SDM_OP_GEN_COMP_PARAM_MASK 0xFFFF /* completion parameters 0-15 */ +#define SDM_OP_GEN_COMP_PARAM_SHIFT 0 +#define SDM_OP_GEN_COMP_TYPE_MASK 0xF /* completion type 16-19 */ +#define SDM_OP_GEN_COMP_TYPE_SHIFT 16 +#define SDM_OP_GEN_RESERVED_MASK 0xFFF /* reserved 20-31 */ +#define SDM_OP_GEN_RESERVED_SHIFT 20 }; /*********************************** Init ************************************/ @@ -1274,13 +1210,6 @@ enum chip_ids { MAX_CHIP_IDS }; -enum idle_chk_severity_types { - IDLE_CHK_SEVERITY_ERROR /* idle check failure should cause an error */, - IDLE_CHK_SEVERITY_ERROR_NO_TRAFFIC, - IDLE_CHK_SEVERITY_WARNING, - MAX_IDLE_CHK_SEVERITY_TYPES -}; - struct init_array_raw_hdr { __le32 data; #define INIT_ARRAY_RAW_HDR_TYPE_MASK 0xF @@ -1340,14 +1269,6 @@ struct init_callback_op { __le16 block_id /* Blocks ID */; }; -/* init comparison types */ -enum init_comparison_types { - INIT_COMPARISON_EQ /* init value is included in the init command */, - INIT_COMPARISON_OR /* init value is all zeros */, - INIT_COMPARISON_AND /* init value is an array of values */, - MAX_INIT_COMPARISON_TYPES -}; - /* init operation: delay */ struct init_delay_op { __le32 op_data; @@ -1444,12 +1365,10 @@ struct init_read_op { __le32 op_data; #define INIT_READ_OP_OP_MASK 0xF #define INIT_READ_OP_OP_SHIFT 0 -#define INIT_READ_OP_POLL_COMP_MASK 0x7 -#define INIT_READ_OP_POLL_COMP_SHIFT 4 +#define INIT_READ_OP_POLL_TYPE_MASK 0xF +#define INIT_READ_OP_POLL_TYPE_SHIFT 4 #define INIT_READ_OP_RESERVED_MASK 0x1 -#define INIT_READ_OP_RESERVED_SHIFT 7 -#define INIT_READ_OP_POLL_MASK 0x1 -#define INIT_READ_OP_POLL_SHIFT 8 +#define INIT_READ_OP_RESERVED_SHIFT 8 #define INIT_READ_OP_ADDRESS_MASK 0x7FFFFF #define INIT_READ_OP_ADDRESS_SHIFT 9 __le32 expected_val; @@ -1477,6 +1396,14 @@ enum init_op_types { MAX_INIT_OP_TYPES }; +enum init_poll_types { + INIT_POLL_NONE /* No polling */, + INIT_POLL_EQ /* init value is included in the init command */, + INIT_POLL_OR /* init value is all zeros */, + INIT_POLL_AND /* init value is an array of values */, + MAX_INIT_POLL_TYPES +}; + /* init source types */ enum init_source_types { INIT_SRC_INLINE /* init value is included in the init command */, @@ -1677,175 +1604,213 @@ bool qed_send_qm_stop_cmd(struct qed_hwfn *p_hwfn, u16 num_pqs); /* Ystorm flow control mode. Use enum fw_flow_ctrl_mode */ -#define YSTORM_FLOW_CONTROL_MODE_OFFSET (IRO[0].base) -#define YSTORM_FLOW_CONTROL_MODE_SIZE (IRO[0].size) +#define YSTORM_FLOW_CONTROL_MODE_OFFSET (IRO[0].base) +#define YSTORM_FLOW_CONTROL_MODE_SIZE (IRO[0].size) /* Tstorm port statistics */ -#define TSTORM_PORT_STAT_OFFSET(port_id) (IRO[1].base + \ - ((port_id) * \ - IRO[1].m1)) -#define TSTORM_PORT_STAT_SIZE (IRO[1].size) +#define TSTORM_PORT_STAT_OFFSET(port_id) (IRO[1].base + ((port_id) * IRO[1].m1)) +#define TSTORM_PORT_STAT_SIZE (IRO[1].size) +/* Tstorm ll2 port statistics */ +#define TSTORM_LL2_PORT_STAT_OFFSET(port_id) \ + (IRO[2].base + ((port_id) * IRO[2].m1)) +#define TSTORM_LL2_PORT_STAT_SIZE (IRO[2].size) /* Ustorm VF-PF Channel ready flag */ -#define USTORM_VF_PF_CHANNEL_READY_OFFSET(vf_id) (IRO[2].base + \ - ((vf_id) * \ - IRO[2].m1)) -#define USTORM_VF_PF_CHANNEL_READY_SIZE (IRO[2].size) +#define USTORM_VF_PF_CHANNEL_READY_OFFSET(vf_id) \ + (IRO[3].base + ((vf_id) * IRO[3].m1)) +#define USTORM_VF_PF_CHANNEL_READY_SIZE (IRO[3].size) /* Ustorm Final flr cleanup ack */ -#define USTORM_FLR_FINAL_ACK_OFFSET (IRO[3].base) -#define USTORM_FLR_FINAL_ACK_SIZE (IRO[3].size) +#define USTORM_FLR_FINAL_ACK_OFFSET(pf_id) (IRO[4].base + ((pf_id) * IRO[4].m1)) +#define USTORM_FLR_FINAL_ACK_SIZE (IRO[4].size) /* Ustorm Event ring consumer */ -#define USTORM_EQE_CONS_OFFSET(pf_id) (IRO[4].base + \ - ((pf_id) * \ - IRO[4].m1)) -#define USTORM_EQE_CONS_SIZE (IRO[4].size) -/* Ustorm Completion ring consumer */ -#define USTORM_CQ_CONS_OFFSET(global_queue_id) (IRO[5].base + \ - ((global_queue_id) * \ - IRO[5].m1)) -#define USTORM_CQ_CONS_SIZE (IRO[5].size) +#define USTORM_EQE_CONS_OFFSET(pf_id) (IRO[5].base + ((pf_id) * IRO[5].m1)) +#define USTORM_EQE_CONS_SIZE (IRO[5].size) +/* Ustorm Common Queue ring consumer */ +#define USTORM_COMMON_QUEUE_CONS_OFFSET(global_queue_id) \ + (IRO[6].base + ((global_queue_id) * IRO[6].m1)) +#define USTORM_COMMON_QUEUE_CONS_SIZE (IRO[6].size) /* Xstorm Integration Test Data */ -#define XSTORM_INTEG_TEST_DATA_OFFSET (IRO[6].base) -#define XSTORM_INTEG_TEST_DATA_SIZE (IRO[6].size) +#define XSTORM_INTEG_TEST_DATA_OFFSET (IRO[7].base) +#define XSTORM_INTEG_TEST_DATA_SIZE (IRO[7].size) /* Ystorm Integration Test Data */ -#define YSTORM_INTEG_TEST_DATA_OFFSET (IRO[7].base) -#define YSTORM_INTEG_TEST_DATA_SIZE (IRO[7].size) +#define YSTORM_INTEG_TEST_DATA_OFFSET (IRO[8].base) +#define YSTORM_INTEG_TEST_DATA_SIZE (IRO[8].size) /* Pstorm Integration Test Data */ -#define PSTORM_INTEG_TEST_DATA_OFFSET (IRO[8].base) -#define PSTORM_INTEG_TEST_DATA_SIZE (IRO[8].size) +#define PSTORM_INTEG_TEST_DATA_OFFSET (IRO[9].base) +#define PSTORM_INTEG_TEST_DATA_SIZE (IRO[9].size) /* Tstorm Integration Test Data */ -#define TSTORM_INTEG_TEST_DATA_OFFSET (IRO[9].base) -#define TSTORM_INTEG_TEST_DATA_SIZE (IRO[9].size) +#define TSTORM_INTEG_TEST_DATA_OFFSET (IRO[10].base) +#define TSTORM_INTEG_TEST_DATA_SIZE (IRO[10].size) /* Mstorm Integration Test Data */ -#define MSTORM_INTEG_TEST_DATA_OFFSET (IRO[10].base) -#define MSTORM_INTEG_TEST_DATA_SIZE (IRO[10].size) +#define MSTORM_INTEG_TEST_DATA_OFFSET (IRO[11].base) +#define MSTORM_INTEG_TEST_DATA_SIZE (IRO[11].size) /* Ustorm Integration Test Data */ -#define USTORM_INTEG_TEST_DATA_OFFSET (IRO[11].base) -#define USTORM_INTEG_TEST_DATA_SIZE (IRO[11].size) +#define USTORM_INTEG_TEST_DATA_OFFSET (IRO[12].base) +#define USTORM_INTEG_TEST_DATA_SIZE (IRO[12].size) /* Tstorm producers */ -#define TSTORM_LL2_RX_PRODS_OFFSET(core_rx_queue_id) (IRO[12].base + \ - ((core_rx_queue_id) * \ - IRO[12].m1)) -#define TSTORM_LL2_RX_PRODS_SIZE (IRO[12].size) -/* Tstorm LiteL2 queue statistics */ -#define CORE_LL2_TSTORM_PER_QUEUE_STAT_OFFSET(core_rx_q_id) (IRO[13].base + \ - ((core_rx_q_id) * \ - IRO[13].m1)) -#define CORE_LL2_TSTORM_PER_QUEUE_STAT_SIZE (IRO[13].size) +#define TSTORM_LL2_RX_PRODS_OFFSET(core_rx_queue_id) \ + (IRO[13].base + ((core_rx_queue_id) * IRO[13].m1)) +#define TSTORM_LL2_RX_PRODS_SIZE (IRO[13].size) +/* Tstorm LightL2 queue statistics */ +#define CORE_LL2_TSTORM_PER_QUEUE_STAT_OFFSET(core_rx_queue_id) \ + (IRO[14].base + ((core_rx_queue_id) * IRO[14].m1)) +#define CORE_LL2_TSTORM_PER_QUEUE_STAT_SIZE (IRO[14].size) /* Ustorm LiteL2 queue statistics */ -#define CORE_LL2_USTORM_PER_QUEUE_STAT_OFFSET(core_rx_q_id) (IRO[14].base + \ - ((core_rx_q_id) * \ - IRO[14].m1)) -#define CORE_LL2_USTORM_PER_QUEUE_STAT_SIZE (IRO[14].size) +#define CORE_LL2_USTORM_PER_QUEUE_STAT_OFFSET(core_rx_queue_id) \ + (IRO[15].base + ((core_rx_queue_id) * IRO[15].m1)) +#define CORE_LL2_USTORM_PER_QUEUE_STAT_SIZE (IRO[15].size) /* Pstorm LiteL2 queue statistics */ -#define CORE_LL2_PSTORM_PER_QUEUE_STAT_OFFSET(core_txst_id) (IRO[15].base + \ - ((core_txst_id) * \ - IRO[15].m1)) -#define CORE_LL2_PSTORM_PER_QUEUE_STAT_SIZE (IRO[15].size) +#define CORE_LL2_PSTORM_PER_QUEUE_STAT_OFFSET(core_tx_stats_id) \ + (IRO[16].base + ((core_tx_stats_id) * IRO[16].m1)) +#define CORE_LL2_PSTORM_PER_QUEUE_STAT_SIZE (IRO[16].size) /* Mstorm queue statistics */ -#define MSTORM_QUEUE_STAT_OFFSET(stat_counter_id) (IRO[16].base + \ - ((stat_counter_id) * \ - IRO[16].m1)) -#define MSTORM_QUEUE_STAT_SIZE (IRO[16].size) +#define MSTORM_QUEUE_STAT_OFFSET(stat_counter_id) \ + (IRO[17].base + ((stat_counter_id) * IRO[17].m1)) +#define MSTORM_QUEUE_STAT_SIZE (IRO[17].size) /* Mstorm producers */ -#define MSTORM_PRODS_OFFSET(queue_id) (IRO[17].base + \ - ((queue_id) * \ - IRO[17].m1)) -#define MSTORM_PRODS_SIZE (IRO[17].size) +#define MSTORM_PRODS_OFFSET(queue_id) (IRO[18].base + ((queue_id) * IRO[18].m1)) +#define MSTORM_PRODS_SIZE (IRO[18].size) /* TPA agregation timeout in us resolution (on ASIC) */ -#define MSTORM_TPA_TIMEOUT_US_OFFSET (IRO[18].base) -#define MSTORM_TPA_TIMEOUT_US_SIZE (IRO[18].size) +#define MSTORM_TPA_TIMEOUT_US_OFFSET (IRO[19].base) +#define MSTORM_TPA_TIMEOUT_US_SIZE (IRO[19].size) /* Ustorm queue statistics */ -#define USTORM_QUEUE_STAT_OFFSET(stat_counter_id) (IRO[19].base + \ - ((stat_counter_id) * \ - IRO[19].m1)) -#define USTORM_QUEUE_STAT_SIZE (IRO[19].size) +#define USTORM_QUEUE_STAT_OFFSET(stat_counter_id) \ + (IRO[20].base + ((stat_counter_id) * IRO[20].m1)) +#define USTORM_QUEUE_STAT_SIZE (IRO[20].size) /* Ustorm queue zone */ -#define USTORM_ETH_QUEUE_ZONE_OFFSET(queue_id) (IRO[20].base + \ - ((queue_id) * \ - IRO[20].m1)) -#define USTORM_ETH_QUEUE_ZONE_SIZE (IRO[20].size) +#define USTORM_ETH_QUEUE_ZONE_OFFSET(queue_id) \ + (IRO[21].base + ((queue_id) * IRO[21].m1)) +#define USTORM_ETH_QUEUE_ZONE_SIZE (IRO[21].size) /* Pstorm queue statistics */ -#define PSTORM_QUEUE_STAT_OFFSET(stat_counter_id) (IRO[21].base + \ - ((stat_counter_id) * \ - IRO[21].m1)) -#define PSTORM_QUEUE_STAT_SIZE (IRO[21].size) +#define PSTORM_QUEUE_STAT_OFFSET(stat_counter_id) \ + (IRO[22].base + ((stat_counter_id) * IRO[22].m1)) +#define PSTORM_QUEUE_STAT_SIZE (IRO[22].size) /* Tstorm last parser message */ -#define TSTORM_ETH_PRS_INPUT_OFFSET(pf_id) (IRO[22].base + \ - ((pf_id) * \ - IRO[22].m1)) -#define TSTORM_ETH_PRS_INPUT_SIZE (IRO[22].size) +#define TSTORM_ETH_PRS_INPUT_OFFSET (IRO[23].base) +#define TSTORM_ETH_PRS_INPUT_SIZE (IRO[23].size) +/* Tstorm Eth limit Rx rate */ +#define ETH_RX_RATE_LIMIT_OFFSET(pf_id) (IRO[24].base + ((pf_id) * IRO[24].m1)) +#define ETH_RX_RATE_LIMIT_SIZE (IRO[24].size) /* Ystorm queue zone */ -#define YSTORM_ETH_QUEUE_ZONE_OFFSET(queue_id) (IRO[23].base + \ - ((queue_id) * \ - IRO[23].m1)) -#define YSTORM_ETH_QUEUE_ZONE_SIZE (IRO[23].size) +#define YSTORM_ETH_QUEUE_ZONE_OFFSET(queue_id) \ + (IRO[25].base + ((queue_id) * IRO[25].m1)) +#define YSTORM_ETH_QUEUE_ZONE_SIZE (IRO[25].size) /* Ystorm cqe producer */ -#define YSTORM_TOE_CQ_PROD_OFFSET(rss_id) (IRO[24].base + \ - ((rss_id) * \ - IRO[24].m1)) -#define YSTORM_TOE_CQ_PROD_SIZE (IRO[24].size) +#define YSTORM_TOE_CQ_PROD_OFFSET(rss_id) \ + (IRO[26].base + ((rss_id) * IRO[26].m1)) +#define YSTORM_TOE_CQ_PROD_SIZE (IRO[26].size) /* Ustorm cqe producer */ -#define USTORM_TOE_CQ_PROD_OFFSET(rss_id) (IRO[25].base + \ - ((rss_id) * \ - IRO[25].m1)) -#define USTORM_TOE_CQ_PROD_SIZE (IRO[25].size) +#define USTORM_TOE_CQ_PROD_OFFSET(rss_id) \ + (IRO[27].base + ((rss_id) * IRO[27].m1)) +#define USTORM_TOE_CQ_PROD_SIZE (IRO[27].size) /* Ustorm grq producer */ -#define USTORM_TOE_GRQ_PROD_OFFSET(pf_id) (IRO[26].base + \ - ((pf_id) * \ - IRO[26].m1)) -#define USTORM_TOE_GRQ_PROD_SIZE (IRO[26].size) +#define USTORM_TOE_GRQ_PROD_OFFSET(pf_id) \ + (IRO[28].base + ((pf_id) * IRO[28].m1)) +#define USTORM_TOE_GRQ_PROD_SIZE (IRO[28].size) /* Tstorm cmdq-cons of given command queue-id */ -#define TSTORM_SCSI_CMDQ_CONS_OFFSET(cmdq_queue_id) (IRO[27].base + \ - ((cmdq_queue_id) * \ - IRO[27].m1)) -#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[27].size) +#define TSTORM_SCSI_CMDQ_CONS_OFFSET(cmdq_queue_id) \ + (IRO[29].base + ((cmdq_queue_id) * IRO[29].m1)) +#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[29].size) /* Mstorm rq-cons of given queue-id */ -#define MSTORM_SCSI_RQ_CONS_OFFSET(rq_queue_id) (IRO[28].base + \ - ((rq_queue_id) * \ - IRO[28].m1)) -#define MSTORM_SCSI_RQ_CONS_SIZE (IRO[28].size) +#define MSTORM_SCSI_RQ_CONS_OFFSET(rq_queue_id) \ + (IRO[30].base + ((rq_queue_id) * IRO[30].m1)) +#define MSTORM_SCSI_RQ_CONS_SIZE (IRO[30].size) +/* Mstorm bdq-external-producer of given BDQ function ID, BDqueue-id */ +#define MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ + (IRO[31].base + ((func_id) * IRO[31].m1) + ((bdq_id) * IRO[31].m2)) +#define MSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[31].size) +/* Tstorm (reflects M-Storm) bdq-external-producer of given fn ID, BDqueue-id */ +#define TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ + (IRO[32].base + ((func_id) * IRO[32].m1) + ((bdq_id) * IRO[32].m2)) +#define TSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[32].size) +/* Tstorm iSCSI RX stats */ +#define TSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ + (IRO[33].base + ((pf_id) * IRO[33].m1)) +#define TSTORM_ISCSI_RX_STATS_SIZE (IRO[33].size) +/* Mstorm iSCSI RX stats */ +#define MSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ + (IRO[34].base + ((pf_id) * IRO[34].m1)) +#define MSTORM_ISCSI_RX_STATS_SIZE (IRO[34].size) +/* Ustorm iSCSI RX stats */ +#define USTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ + (IRO[35].base + ((pf_id) * IRO[35].m1)) +#define USTORM_ISCSI_RX_STATS_SIZE (IRO[35].size) +/* Xstorm iSCSI TX stats */ +#define XSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ + (IRO[36].base + ((pf_id) * IRO[36].m1)) +#define XSTORM_ISCSI_TX_STATS_SIZE (IRO[36].size) +/* Ystorm iSCSI TX stats */ +#define YSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ + (IRO[37].base + ((pf_id) * IRO[37].m1)) +#define YSTORM_ISCSI_TX_STATS_SIZE (IRO[37].size) +/* Pstorm iSCSI TX stats */ +#define PSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ + (IRO[38].base + ((pf_id) * IRO[38].m1)) +#define PSTORM_ISCSI_TX_STATS_SIZE (IRO[38].size) +/* Tstorm FCoE RX stats */ +#define TSTORM_FCOE_RX_STATS_OFFSET(pf_id) \ + (IRO[39].base + ((pf_id) * IRO[39].m1)) +#define TSTORM_FCOE_RX_STATS_SIZE (IRO[39].size) +/* Mstorm FCoE RX stats */ +#define MSTORM_FCOE_RX_STATS_OFFSET(pf_id) \ + (IRO[40].base + ((pf_id) * IRO[40].m1)) +#define MSTORM_FCOE_RX_STATS_SIZE (IRO[40].size) +/* Pstorm FCoE TX stats */ +#define PSTORM_FCOE_TX_STATS_OFFSET(pf_id) \ + (IRO[41].base + ((pf_id) * IRO[41].m1)) +#define PSTORM_FCOE_TX_STATS_SIZE (IRO[41].size) /* Pstorm RoCE statistics */ -#define PSTORM_ROCE_STAT_OFFSET(stat_counter_id) (IRO[29].base + \ - ((stat_counter_id) * \ - IRO[29].m1)) -#define PSTORM_ROCE_STAT_SIZE (IRO[29].size) +#define PSTORM_ROCE_STAT_OFFSET(stat_counter_id) \ + (IRO[42].base + ((stat_counter_id) * IRO[42].m1)) +#define PSTORM_ROCE_STAT_SIZE (IRO[42].size) /* Tstorm RoCE statistics */ -#define TSTORM_ROCE_STAT_OFFSET(stat_counter_id) (IRO[30].base + \ - ((stat_counter_id) * \ - IRO[30].m1)) -#define TSTORM_ROCE_STAT_SIZE (IRO[30].size) - -static const struct iro iro_arr[31] = { - { 0x10, 0x0, 0x0, 0x0, 0x8 }, - { 0x4448, 0x60, 0x0, 0x0, 0x60 }, - { 0x498, 0x8, 0x0, 0x0, 0x4 }, - { 0x494, 0x0, 0x0, 0x0, 0x4 }, - { 0x10, 0x8, 0x0, 0x0, 0x2 }, - { 0x90, 0x8, 0x0, 0x0, 0x2 }, - { 0x4540, 0x0, 0x0, 0x0, 0xf8 }, - { 0x39e0, 0x0, 0x0, 0x0, 0xf8 }, - { 0x2598, 0x0, 0x0, 0x0, 0xf8 }, - { 0x4350, 0x0, 0x0, 0x0, 0xf8 }, - { 0x52d0, 0x0, 0x0, 0x0, 0xf8 }, - { 0x7a48, 0x0, 0x0, 0x0, 0xf8 }, - { 0x100, 0x8, 0x0, 0x0, 0x8 }, - { 0x5808, 0x10, 0x0, 0x0, 0x10 }, - { 0xb100, 0x30, 0x0, 0x0, 0x30 }, - { 0x95c0, 0x30, 0x0, 0x0, 0x30 }, - { 0x54f8, 0x40, 0x0, 0x0, 0x40 }, - { 0x200, 0x10, 0x0, 0x0, 0x8 }, - { 0x9e70, 0x0, 0x0, 0x0, 0x4 }, - { 0x7ca0, 0x40, 0x0, 0x0, 0x30 }, - { 0xd00, 0x8, 0x0, 0x0, 0x8 }, - { 0x2790, 0x80, 0x0, 0x0, 0x38 }, - { 0xa520, 0xf0, 0x0, 0x0, 0xf0 }, - { 0x80, 0x8, 0x0, 0x0, 0x8 }, - { 0xac0, 0x8, 0x0, 0x0, 0x8 }, - { 0x2580, 0x8, 0x0, 0x0, 0x8 }, - { 0x2500, 0x8, 0x0, 0x0, 0x8 }, - { 0x440, 0x8, 0x0, 0x0, 0x2 }, - { 0x1800, 0x8, 0x0, 0x0, 0x2 }, - { 0x27c8, 0x80, 0x0, 0x0, 0x10 }, - { 0x4710, 0x10, 0x0, 0x0, 0x10 }, +#define TSTORM_ROCE_STAT_OFFSET(stat_counter_id) \ + (IRO[43].base + ((stat_counter_id) * IRO[43].m1)) +#define TSTORM_ROCE_STAT_SIZE (IRO[43].size) + +static const struct iro iro_arr[44] = { + { 0x10, 0x0, 0x0, 0x0, 0x8 }, + { 0x47c8, 0x60, 0x0, 0x0, 0x60 }, + { 0x5e30, 0x20, 0x0, 0x0, 0x20 }, + { 0x510, 0x8, 0x0, 0x0, 0x4 }, + { 0x490, 0x8, 0x0, 0x0, 0x4 }, + { 0x10, 0x8, 0x0, 0x0, 0x2 }, + { 0x90, 0x8, 0x0, 0x0, 0x2 }, + { 0x4940, 0x0, 0x0, 0x0, 0x78 }, + { 0x3de0, 0x0, 0x0, 0x0, 0x78 }, + { 0x2998, 0x0, 0x0, 0x0, 0x78 }, + { 0x4750, 0x0, 0x0, 0x0, 0x78 }, + { 0x56d0, 0x0, 0x0, 0x0, 0x78 }, + { 0x7e50, 0x0, 0x0, 0x0, 0x78 }, + { 0x100, 0x8, 0x0, 0x0, 0x8 }, + { 0x5c10, 0x10, 0x0, 0x0, 0x10 }, + { 0xb508, 0x30, 0x0, 0x0, 0x30 }, + { 0x95c0, 0x30, 0x0, 0x0, 0x30 }, + { 0x58a0, 0x40, 0x0, 0x0, 0x40 }, + { 0x200, 0x10, 0x0, 0x0, 0x8 }, + { 0xa230, 0x0, 0x0, 0x0, 0x4 }, + { 0x8058, 0x40, 0x0, 0x0, 0x30 }, + { 0xd00, 0x8, 0x0, 0x0, 0x8 }, + { 0x2b30, 0x80, 0x0, 0x0, 0x38 }, + { 0xa808, 0x0, 0x0, 0x0, 0xf0 }, + { 0xa8f8, 0x8, 0x0, 0x0, 0x8 }, + { 0x80, 0x8, 0x0, 0x0, 0x8 }, + { 0xac0, 0x8, 0x0, 0x0, 0x8 }, + { 0x2580, 0x8, 0x0, 0x0, 0x8 }, + { 0x2500, 0x8, 0x0, 0x0, 0x8 }, + { 0x440, 0x8, 0x0, 0x0, 0x2 }, + { 0x1800, 0x8, 0x0, 0x0, 0x2 }, + { 0x1a00, 0x10, 0x8, 0x0, 0x2 }, + { 0x640, 0x10, 0x8, 0x0, 0x2 }, + { 0xd9b8, 0x38, 0x0, 0x0, 0x24 }, + { 0x11048, 0x10, 0x0, 0x0, 0x8 }, + { 0x11678, 0x38, 0x0, 0x0, 0x18 }, + { 0xaec0, 0x30, 0x0, 0x0, 0x10 }, + { 0x8700, 0x28, 0x0, 0x0, 0x18 }, + { 0xec00, 0x10, 0x0, 0x0, 0x10 }, + { 0xde38, 0x40, 0x0, 0x0, 0x30 }, + { 0x121a8, 0x38, 0x0, 0x0, 0x8 }, + { 0xf068, 0x20, 0x0, 0x0, 0x20 }, + { 0x2b68, 0x80, 0x0, 0x0, 0x10 }, + { 0x4ab8, 0x10, 0x0, 0x0, 0x10 }, }; /* Runtime array offsets */ @@ -1866,426 +1831,427 @@ static const struct iro iro_arr[31] = { #define DORQ_REG_VF_MAX_ICID_6_RT_OFFSET 14 #define DORQ_REG_VF_MAX_ICID_7_RT_OFFSET 15 #define DORQ_REG_PF_WAKE_ALL_RT_OFFSET 16 -#define IGU_REG_PF_CONFIGURATION_RT_OFFSET 17 -#define IGU_REG_VF_CONFIGURATION_RT_OFFSET 18 -#define IGU_REG_ATTN_MSG_ADDR_L_RT_OFFSET 19 -#define IGU_REG_ATTN_MSG_ADDR_H_RT_OFFSET 20 -#define IGU_REG_LEADING_EDGE_LATCH_RT_OFFSET 21 -#define IGU_REG_TRAILING_EDGE_LATCH_RT_OFFSET 22 -#define CAU_REG_CQE_AGG_UNIT_SIZE_RT_OFFSET 23 -#define CAU_REG_SB_VAR_MEMORY_RT_OFFSET 760 +#define DORQ_REG_TAG1_ETHERTYPE_RT_OFFSET 17 +#define IGU_REG_PF_CONFIGURATION_RT_OFFSET 18 +#define IGU_REG_VF_CONFIGURATION_RT_OFFSET 19 +#define IGU_REG_ATTN_MSG_ADDR_L_RT_OFFSET 20 +#define IGU_REG_ATTN_MSG_ADDR_H_RT_OFFSET 21 +#define IGU_REG_LEADING_EDGE_LATCH_RT_OFFSET 22 +#define IGU_REG_TRAILING_EDGE_LATCH_RT_OFFSET 23 +#define CAU_REG_CQE_AGG_UNIT_SIZE_RT_OFFSET 24 +#define CAU_REG_SB_VAR_MEMORY_RT_OFFSET 761 #define CAU_REG_SB_VAR_MEMORY_RT_SIZE 736 -#define CAU_REG_SB_VAR_MEMORY_RT_OFFSET 760 +#define CAU_REG_SB_VAR_MEMORY_RT_OFFSET 761 #define CAU_REG_SB_VAR_MEMORY_RT_SIZE 736 -#define CAU_REG_SB_ADDR_MEMORY_RT_OFFSET 1496 +#define CAU_REG_SB_ADDR_MEMORY_RT_OFFSET 1497 #define CAU_REG_SB_ADDR_MEMORY_RT_SIZE 736 -#define CAU_REG_PI_MEMORY_RT_OFFSET 2232 +#define CAU_REG_PI_MEMORY_RT_OFFSET 2233 #define CAU_REG_PI_MEMORY_RT_SIZE 4416 -#define PRS_REG_SEARCH_RESP_INITIATOR_TYPE_RT_OFFSET 6648 -#define PRS_REG_TASK_ID_MAX_INITIATOR_PF_RT_OFFSET 6649 -#define PRS_REG_TASK_ID_MAX_INITIATOR_VF_RT_OFFSET 6650 -#define PRS_REG_TASK_ID_MAX_TARGET_PF_RT_OFFSET 6651 -#define PRS_REG_TASK_ID_MAX_TARGET_VF_RT_OFFSET 6652 -#define PRS_REG_SEARCH_TCP_RT_OFFSET 6653 -#define PRS_REG_SEARCH_FCOE_RT_OFFSET 6654 -#define PRS_REG_SEARCH_ROCE_RT_OFFSET 6655 -#define PRS_REG_ROCE_DEST_QP_MAX_VF_RT_OFFSET 6656 -#define PRS_REG_ROCE_DEST_QP_MAX_PF_RT_OFFSET 6657 -#define PRS_REG_SEARCH_OPENFLOW_RT_OFFSET 6658 -#define PRS_REG_SEARCH_NON_IP_AS_OPENFLOW_RT_OFFSET 6659 -#define PRS_REG_OPENFLOW_SUPPORT_ONLY_KNOWN_OVER_IP_RT_OFFSET 6660 -#define PRS_REG_OPENFLOW_SEARCH_KEY_MASK_RT_OFFSET 6661 -#define PRS_REG_LIGHT_L2_ETHERTYPE_EN_RT_OFFSET 6662 -#define SRC_REG_FIRSTFREE_RT_OFFSET 6663 +#define PRS_REG_SEARCH_RESP_INITIATOR_TYPE_RT_OFFSET 6649 +#define PRS_REG_TASK_ID_MAX_INITIATOR_PF_RT_OFFSET 6650 +#define PRS_REG_TASK_ID_MAX_INITIATOR_VF_RT_OFFSET 6651 +#define PRS_REG_TASK_ID_MAX_TARGET_PF_RT_OFFSET 6652 +#define PRS_REG_TASK_ID_MAX_TARGET_VF_RT_OFFSET 6653 +#define PRS_REG_SEARCH_TCP_RT_OFFSET 6654 +#define PRS_REG_SEARCH_FCOE_RT_OFFSET 6655 +#define PRS_REG_SEARCH_ROCE_RT_OFFSET 6656 +#define PRS_REG_ROCE_DEST_QP_MAX_VF_RT_OFFSET 6657 +#define PRS_REG_ROCE_DEST_QP_MAX_PF_RT_OFFSET 6658 +#define PRS_REG_SEARCH_OPENFLOW_RT_OFFSET 6659 +#define PRS_REG_SEARCH_NON_IP_AS_OPENFLOW_RT_OFFSET 6660 +#define PRS_REG_OPENFLOW_SUPPORT_ONLY_KNOWN_OVER_IP_RT_OFFSET 6661 +#define PRS_REG_OPENFLOW_SEARCH_KEY_MASK_RT_OFFSET 6662 +#define PRS_REG_TAG_ETHERTYPE_0_RT_OFFSET 6663 +#define PRS_REG_LIGHT_L2_ETHERTYPE_EN_RT_OFFSET 6664 +#define SRC_REG_FIRSTFREE_RT_OFFSET 6665 #define SRC_REG_FIRSTFREE_RT_SIZE 2 -#define SRC_REG_LASTFREE_RT_OFFSET 6665 +#define SRC_REG_LASTFREE_RT_OFFSET 6667 #define SRC_REG_LASTFREE_RT_SIZE 2 -#define SRC_REG_COUNTFREE_RT_OFFSET 6667 -#define SRC_REG_NUMBER_HASH_BITS_RT_OFFSET 6668 -#define PSWRQ2_REG_CDUT_P_SIZE_RT_OFFSET 6669 -#define PSWRQ2_REG_CDUC_P_SIZE_RT_OFFSET 6670 -#define PSWRQ2_REG_TM_P_SIZE_RT_OFFSET 6671 -#define PSWRQ2_REG_QM_P_SIZE_RT_OFFSET 6672 -#define PSWRQ2_REG_SRC_P_SIZE_RT_OFFSET 6673 -#define PSWRQ2_REG_TM_FIRST_ILT_RT_OFFSET 6674 -#define PSWRQ2_REG_TM_LAST_ILT_RT_OFFSET 6675 -#define PSWRQ2_REG_QM_FIRST_ILT_RT_OFFSET 6676 -#define PSWRQ2_REG_QM_LAST_ILT_RT_OFFSET 6677 -#define PSWRQ2_REG_SRC_FIRST_ILT_RT_OFFSET 6678 -#define PSWRQ2_REG_SRC_LAST_ILT_RT_OFFSET 6679 -#define PSWRQ2_REG_CDUC_FIRST_ILT_RT_OFFSET 6680 -#define PSWRQ2_REG_CDUC_LAST_ILT_RT_OFFSET 6681 -#define PSWRQ2_REG_CDUT_FIRST_ILT_RT_OFFSET 6682 -#define PSWRQ2_REG_CDUT_LAST_ILT_RT_OFFSET 6683 -#define PSWRQ2_REG_TSDM_FIRST_ILT_RT_OFFSET 6684 -#define PSWRQ2_REG_TSDM_LAST_ILT_RT_OFFSET 6685 -#define PSWRQ2_REG_TM_NUMBER_OF_PF_BLOCKS_RT_OFFSET 6686 -#define PSWRQ2_REG_CDUT_NUMBER_OF_PF_BLOCKS_RT_OFFSET 6687 -#define PSWRQ2_REG_CDUC_NUMBER_OF_PF_BLOCKS_RT_OFFSET 6688 -#define PSWRQ2_REG_TM_VF_BLOCKS_RT_OFFSET 6689 -#define PSWRQ2_REG_CDUT_VF_BLOCKS_RT_OFFSET 6690 -#define PSWRQ2_REG_CDUC_VF_BLOCKS_RT_OFFSET 6691 -#define PSWRQ2_REG_TM_BLOCKS_FACTOR_RT_OFFSET 6692 -#define PSWRQ2_REG_CDUT_BLOCKS_FACTOR_RT_OFFSET 6693 -#define PSWRQ2_REG_CDUC_BLOCKS_FACTOR_RT_OFFSET 6694 -#define PSWRQ2_REG_VF_BASE_RT_OFFSET 6695 -#define PSWRQ2_REG_VF_LAST_ILT_RT_OFFSET 6696 -#define PSWRQ2_REG_WR_MBS0_RT_OFFSET 6697 -#define PSWRQ2_REG_RD_MBS0_RT_OFFSET 6698 -#define PSWRQ2_REG_DRAM_ALIGN_WR_RT_OFFSET 6699 -#define PSWRQ2_REG_DRAM_ALIGN_RD_RT_OFFSET 6700 -#define PSWRQ2_REG_ILT_MEMORY_RT_OFFSET 6701 +#define SRC_REG_COUNTFREE_RT_OFFSET 6669 +#define SRC_REG_NUMBER_HASH_BITS_RT_OFFSET 6670 +#define PSWRQ2_REG_CDUT_P_SIZE_RT_OFFSET 6671 +#define PSWRQ2_REG_CDUC_P_SIZE_RT_OFFSET 6672 +#define PSWRQ2_REG_TM_P_SIZE_RT_OFFSET 6673 +#define PSWRQ2_REG_QM_P_SIZE_RT_OFFSET 6674 +#define PSWRQ2_REG_SRC_P_SIZE_RT_OFFSET 6675 +#define PSWRQ2_REG_TM_FIRST_ILT_RT_OFFSET 6676 +#define PSWRQ2_REG_TM_LAST_ILT_RT_OFFSET 6677 +#define PSWRQ2_REG_QM_FIRST_ILT_RT_OFFSET 6678 +#define PSWRQ2_REG_QM_LAST_ILT_RT_OFFSET 6679 +#define PSWRQ2_REG_SRC_FIRST_ILT_RT_OFFSET 6680 +#define PSWRQ2_REG_SRC_LAST_ILT_RT_OFFSET 6681 +#define PSWRQ2_REG_CDUC_FIRST_ILT_RT_OFFSET 6682 +#define PSWRQ2_REG_CDUC_LAST_ILT_RT_OFFSET 6683 +#define PSWRQ2_REG_CDUT_FIRST_ILT_RT_OFFSET 6684 +#define PSWRQ2_REG_CDUT_LAST_ILT_RT_OFFSET 6685 +#define PSWRQ2_REG_TSDM_FIRST_ILT_RT_OFFSET 6686 +#define PSWRQ2_REG_TSDM_LAST_ILT_RT_OFFSET 6687 +#define PSWRQ2_REG_TM_NUMBER_OF_PF_BLOCKS_RT_OFFSET 6688 +#define PSWRQ2_REG_CDUT_NUMBER_OF_PF_BLOCKS_RT_OFFSET 6689 +#define PSWRQ2_REG_CDUC_NUMBER_OF_PF_BLOCKS_RT_OFFSET 6690 +#define PSWRQ2_REG_TM_VF_BLOCKS_RT_OFFSET 6691 +#define PSWRQ2_REG_CDUT_VF_BLOCKS_RT_OFFSET 6692 +#define PSWRQ2_REG_CDUC_VF_BLOCKS_RT_OFFSET 6693 +#define PSWRQ2_REG_TM_BLOCKS_FACTOR_RT_OFFSET 6694 +#define PSWRQ2_REG_CDUT_BLOCKS_FACTOR_RT_OFFSET 6695 +#define PSWRQ2_REG_CDUC_BLOCKS_FACTOR_RT_OFFSET 6696 +#define PSWRQ2_REG_VF_BASE_RT_OFFSET 6697 +#define PSWRQ2_REG_VF_LAST_ILT_RT_OFFSET 6698 +#define PSWRQ2_REG_WR_MBS0_RT_OFFSET 6699 +#define PSWRQ2_REG_RD_MBS0_RT_OFFSET 6700 +#define PSWRQ2_REG_DRAM_ALIGN_WR_RT_OFFSET 6701 +#define PSWRQ2_REG_DRAM_ALIGN_RD_RT_OFFSET 6702 +#define PSWRQ2_REG_ILT_MEMORY_RT_OFFSET 6703 #define PSWRQ2_REG_ILT_MEMORY_RT_SIZE 22000 -#define PGLUE_REG_B_VF_BASE_RT_OFFSET 28701 -#define PGLUE_REG_B_CACHE_LINE_SIZE_RT_OFFSET 28702 -#define PGLUE_REG_B_PF_BAR0_SIZE_RT_OFFSET 28703 -#define PGLUE_REG_B_PF_BAR1_SIZE_RT_OFFSET 28704 -#define PGLUE_REG_B_VF_BAR1_SIZE_RT_OFFSET 28705 -#define TM_REG_VF_ENABLE_CONN_RT_OFFSET 28706 -#define TM_REG_PF_ENABLE_CONN_RT_OFFSET 28707 -#define TM_REG_PF_ENABLE_TASK_RT_OFFSET 28708 -#define TM_REG_GROUP_SIZE_RESOLUTION_CONN_RT_OFFSET 28709 -#define TM_REG_GROUP_SIZE_RESOLUTION_TASK_RT_OFFSET 28710 -#define TM_REG_CONFIG_CONN_MEM_RT_OFFSET 28711 +#define PGLUE_REG_B_VF_BASE_RT_OFFSET 28703 +#define PGLUE_REG_B_CACHE_LINE_SIZE_RT_OFFSET 28704 +#define PGLUE_REG_B_PF_BAR0_SIZE_RT_OFFSET 28705 +#define PGLUE_REG_B_PF_BAR1_SIZE_RT_OFFSET 28706 +#define PGLUE_REG_B_VF_BAR1_SIZE_RT_OFFSET 28707 +#define TM_REG_VF_ENABLE_CONN_RT_OFFSET 28708 +#define TM_REG_PF_ENABLE_CONN_RT_OFFSET 28709 +#define TM_REG_PF_ENABLE_TASK_RT_OFFSET 28710 +#define TM_REG_GROUP_SIZE_RESOLUTION_CONN_RT_OFFSET 28711 +#define TM_REG_GROUP_SIZE_RESOLUTION_TASK_RT_OFFSET 28712 +#define TM_REG_CONFIG_CONN_MEM_RT_OFFSET 28713 #define TM_REG_CONFIG_CONN_MEM_RT_SIZE 416 -#define TM_REG_CONFIG_TASK_MEM_RT_OFFSET 29127 +#define TM_REG_CONFIG_TASK_MEM_RT_OFFSET 29129 #define TM_REG_CONFIG_TASK_MEM_RT_SIZE 512 -#define QM_REG_MAXPQSIZE_0_RT_OFFSET 29639 -#define QM_REG_MAXPQSIZE_1_RT_OFFSET 29640 -#define QM_REG_MAXPQSIZE_2_RT_OFFSET 29641 -#define QM_REG_MAXPQSIZETXSEL_0_RT_OFFSET 29642 -#define QM_REG_MAXPQSIZETXSEL_1_RT_OFFSET 29643 -#define QM_REG_MAXPQSIZETXSEL_2_RT_OFFSET 29644 -#define QM_REG_MAXPQSIZETXSEL_3_RT_OFFSET 29645 -#define QM_REG_MAXPQSIZETXSEL_4_RT_OFFSET 29646 -#define QM_REG_MAXPQSIZETXSEL_5_RT_OFFSET 29647 -#define QM_REG_MAXPQSIZETXSEL_6_RT_OFFSET 29648 -#define QM_REG_MAXPQSIZETXSEL_7_RT_OFFSET 29649 -#define QM_REG_MAXPQSIZETXSEL_8_RT_OFFSET 29650 -#define QM_REG_MAXPQSIZETXSEL_9_RT_OFFSET 29651 -#define QM_REG_MAXPQSIZETXSEL_10_RT_OFFSET 29652 -#define QM_REG_MAXPQSIZETXSEL_11_RT_OFFSET 29653 -#define QM_REG_MAXPQSIZETXSEL_12_RT_OFFSET 29654 -#define QM_REG_MAXPQSIZETXSEL_13_RT_OFFSET 29655 -#define QM_REG_MAXPQSIZETXSEL_14_RT_OFFSET 29656 -#define QM_REG_MAXPQSIZETXSEL_15_RT_OFFSET 29657 -#define QM_REG_MAXPQSIZETXSEL_16_RT_OFFSET 29658 -#define QM_REG_MAXPQSIZETXSEL_17_RT_OFFSET 29659 -#define QM_REG_MAXPQSIZETXSEL_18_RT_OFFSET 29660 -#define QM_REG_MAXPQSIZETXSEL_19_RT_OFFSET 29661 -#define QM_REG_MAXPQSIZETXSEL_20_RT_OFFSET 29662 -#define QM_REG_MAXPQSIZETXSEL_21_RT_OFFSET 29663 -#define QM_REG_MAXPQSIZETXSEL_22_RT_OFFSET 29664 -#define QM_REG_MAXPQSIZETXSEL_23_RT_OFFSET 29665 -#define QM_REG_MAXPQSIZETXSEL_24_RT_OFFSET 29666 -#define QM_REG_MAXPQSIZETXSEL_25_RT_OFFSET 29667 -#define QM_REG_MAXPQSIZETXSEL_26_RT_OFFSET 29668 -#define QM_REG_MAXPQSIZETXSEL_27_RT_OFFSET 29669 -#define QM_REG_MAXPQSIZETXSEL_28_RT_OFFSET 29670 -#define QM_REG_MAXPQSIZETXSEL_29_RT_OFFSET 29671 -#define QM_REG_MAXPQSIZETXSEL_30_RT_OFFSET 29672 -#define QM_REG_MAXPQSIZETXSEL_31_RT_OFFSET 29673 -#define QM_REG_MAXPQSIZETXSEL_32_RT_OFFSET 29674 -#define QM_REG_MAXPQSIZETXSEL_33_RT_OFFSET 29675 -#define QM_REG_MAXPQSIZETXSEL_34_RT_OFFSET 29676 -#define QM_REG_MAXPQSIZETXSEL_35_RT_OFFSET 29677 -#define QM_REG_MAXPQSIZETXSEL_36_RT_OFFSET 29678 -#define QM_REG_MAXPQSIZETXSEL_37_RT_OFFSET 29679 -#define QM_REG_MAXPQSIZETXSEL_38_RT_OFFSET 29680 -#define QM_REG_MAXPQSIZETXSEL_39_RT_OFFSET 29681 -#define QM_REG_MAXPQSIZETXSEL_40_RT_OFFSET 29682 -#define QM_REG_MAXPQSIZETXSEL_41_RT_OFFSET 29683 -#define QM_REG_MAXPQSIZETXSEL_42_RT_OFFSET 29684 -#define QM_REG_MAXPQSIZETXSEL_43_RT_OFFSET 29685 -#define QM_REG_MAXPQSIZETXSEL_44_RT_OFFSET 29686 -#define QM_REG_MAXPQSIZETXSEL_45_RT_OFFSET 29687 -#define QM_REG_MAXPQSIZETXSEL_46_RT_OFFSET 29688 -#define QM_REG_MAXPQSIZETXSEL_47_RT_OFFSET 29689 -#define QM_REG_MAXPQSIZETXSEL_48_RT_OFFSET 29690 -#define QM_REG_MAXPQSIZETXSEL_49_RT_OFFSET 29691 -#define QM_REG_MAXPQSIZETXSEL_50_RT_OFFSET 29692 -#define QM_REG_MAXPQSIZETXSEL_51_RT_OFFSET 29693 -#define QM_REG_MAXPQSIZETXSEL_52_RT_OFFSET 29694 -#define QM_REG_MAXPQSIZETXSEL_53_RT_OFFSET 29695 -#define QM_REG_MAXPQSIZETXSEL_54_RT_OFFSET 29696 -#define QM_REG_MAXPQSIZETXSEL_55_RT_OFFSET 29697 -#define QM_REG_MAXPQSIZETXSEL_56_RT_OFFSET 29698 -#define QM_REG_MAXPQSIZETXSEL_57_RT_OFFSET 29699 -#define QM_REG_MAXPQSIZETXSEL_58_RT_OFFSET 29700 -#define QM_REG_MAXPQSIZETXSEL_59_RT_OFFSET 29701 -#define QM_REG_MAXPQSIZETXSEL_60_RT_OFFSET 29702 -#define QM_REG_MAXPQSIZETXSEL_61_RT_OFFSET 29703 -#define QM_REG_MAXPQSIZETXSEL_62_RT_OFFSET 29704 -#define QM_REG_MAXPQSIZETXSEL_63_RT_OFFSET 29705 -#define QM_REG_BASEADDROTHERPQ_RT_OFFSET 29706 +#define QM_REG_MAXPQSIZE_0_RT_OFFSET 29641 +#define QM_REG_MAXPQSIZE_1_RT_OFFSET 29642 +#define QM_REG_MAXPQSIZE_2_RT_OFFSET 29643 +#define QM_REG_MAXPQSIZETXSEL_0_RT_OFFSET 29644 +#define QM_REG_MAXPQSIZETXSEL_1_RT_OFFSET 29645 +#define QM_REG_MAXPQSIZETXSEL_2_RT_OFFSET 29646 +#define QM_REG_MAXPQSIZETXSEL_3_RT_OFFSET 29647 +#define QM_REG_MAXPQSIZETXSEL_4_RT_OFFSET 29648 +#define QM_REG_MAXPQSIZETXSEL_5_RT_OFFSET 29649 +#define QM_REG_MAXPQSIZETXSEL_6_RT_OFFSET 29650 +#define QM_REG_MAXPQSIZETXSEL_7_RT_OFFSET 29651 +#define QM_REG_MAXPQSIZETXSEL_8_RT_OFFSET 29652 +#define QM_REG_MAXPQSIZETXSEL_9_RT_OFFSET 29653 +#define QM_REG_MAXPQSIZETXSEL_10_RT_OFFSET 29654 +#define QM_REG_MAXPQSIZETXSEL_11_RT_OFFSET 29655 +#define QM_REG_MAXPQSIZETXSEL_12_RT_OFFSET 29656 +#define QM_REG_MAXPQSIZETXSEL_13_RT_OFFSET 29657 +#define QM_REG_MAXPQSIZETXSEL_14_RT_OFFSET 29658 +#define QM_REG_MAXPQSIZETXSEL_15_RT_OFFSET 29659 +#define QM_REG_MAXPQSIZETXSEL_16_RT_OFFSET 29660 +#define QM_REG_MAXPQSIZETXSEL_17_RT_OFFSET 29661 +#define QM_REG_MAXPQSIZETXSEL_18_RT_OFFSET 29662 +#define QM_REG_MAXPQSIZETXSEL_19_RT_OFFSET 29663 +#define QM_REG_MAXPQSIZETXSEL_20_RT_OFFSET 29664 +#define QM_REG_MAXPQSIZETXSEL_21_RT_OFFSET 29665 +#define QM_REG_MAXPQSIZETXSEL_22_RT_OFFSET 29666 +#define QM_REG_MAXPQSIZETXSEL_23_RT_OFFSET 29667 +#define QM_REG_MAXPQSIZETXSEL_24_RT_OFFSET 29668 +#define QM_REG_MAXPQSIZETXSEL_25_RT_OFFSET 29669 +#define QM_REG_MAXPQSIZETXSEL_26_RT_OFFSET 29670 +#define QM_REG_MAXPQSIZETXSEL_27_RT_OFFSET 29671 +#define QM_REG_MAXPQSIZETXSEL_28_RT_OFFSET 29672 +#define QM_REG_MAXPQSIZETXSEL_29_RT_OFFSET 29673 +#define QM_REG_MAXPQSIZETXSEL_30_RT_OFFSET 29674 +#define QM_REG_MAXPQSIZETXSEL_31_RT_OFFSET 29675 +#define QM_REG_MAXPQSIZETXSEL_32_RT_OFFSET 29676 +#define QM_REG_MAXPQSIZETXSEL_33_RT_OFFSET 29677 +#define QM_REG_MAXPQSIZETXSEL_34_RT_OFFSET 29678 +#define QM_REG_MAXPQSIZETXSEL_35_RT_OFFSET 29679 +#define QM_REG_MAXPQSIZETXSEL_36_RT_OFFSET 29680 +#define QM_REG_MAXPQSIZETXSEL_37_RT_OFFSET 29681 +#define QM_REG_MAXPQSIZETXSEL_38_RT_OFFSET 29682 +#define QM_REG_MAXPQSIZETXSEL_39_RT_OFFSET 29683 +#define QM_REG_MAXPQSIZETXSEL_40_RT_OFFSET 29684 +#define QM_REG_MAXPQSIZETXSEL_41_RT_OFFSET 29685 +#define QM_REG_MAXPQSIZETXSEL_42_RT_OFFSET 29686 +#define QM_REG_MAXPQSIZETXSEL_43_RT_OFFSET 29687 +#define QM_REG_MAXPQSIZETXSEL_44_RT_OFFSET 29688 +#define QM_REG_MAXPQSIZETXSEL_45_RT_OFFSET 29689 +#define QM_REG_MAXPQSIZETXSEL_46_RT_OFFSET 29690 +#define QM_REG_MAXPQSIZETXSEL_47_RT_OFFSET 29691 +#define QM_REG_MAXPQSIZETXSEL_48_RT_OFFSET 29692 +#define QM_REG_MAXPQSIZETXSEL_49_RT_OFFSET 29693 +#define QM_REG_MAXPQSIZETXSEL_50_RT_OFFSET 29694 +#define QM_REG_MAXPQSIZETXSEL_51_RT_OFFSET 29695 +#define QM_REG_MAXPQSIZETXSEL_52_RT_OFFSET 29696 +#define QM_REG_MAXPQSIZETXSEL_53_RT_OFFSET 29697 +#define QM_REG_MAXPQSIZETXSEL_54_RT_OFFSET 29698 +#define QM_REG_MAXPQSIZETXSEL_55_RT_OFFSET 29699 +#define QM_REG_MAXPQSIZETXSEL_56_RT_OFFSET 29700 +#define QM_REG_MAXPQSIZETXSEL_57_RT_OFFSET 29701 +#define QM_REG_MAXPQSIZETXSEL_58_RT_OFFSET 29702 +#define QM_REG_MAXPQSIZETXSEL_59_RT_OFFSET 29703 +#define QM_REG_MAXPQSIZETXSEL_60_RT_OFFSET 29704 +#define QM_REG_MAXPQSIZETXSEL_61_RT_OFFSET 29705 +#define QM_REG_MAXPQSIZETXSEL_62_RT_OFFSET 29706 +#define QM_REG_MAXPQSIZETXSEL_63_RT_OFFSET 29707 +#define QM_REG_BASEADDROTHERPQ_RT_OFFSET 29708 #define QM_REG_BASEADDROTHERPQ_RT_SIZE 128 -#define QM_REG_VOQCRDLINE_RT_OFFSET 29834 +#define QM_REG_VOQCRDLINE_RT_OFFSET 29836 #define QM_REG_VOQCRDLINE_RT_SIZE 20 -#define QM_REG_VOQINITCRDLINE_RT_OFFSET 29854 +#define QM_REG_VOQINITCRDLINE_RT_OFFSET 29856 #define QM_REG_VOQINITCRDLINE_RT_SIZE 20 -#define QM_REG_AFULLQMBYPTHRPFWFQ_RT_OFFSET 29874 -#define QM_REG_AFULLQMBYPTHRVPWFQ_RT_OFFSET 29875 -#define QM_REG_AFULLQMBYPTHRPFRL_RT_OFFSET 29876 -#define QM_REG_AFULLQMBYPTHRGLBLRL_RT_OFFSET 29877 -#define QM_REG_AFULLOPRTNSTCCRDMASK_RT_OFFSET 29878 -#define QM_REG_WRROTHERPQGRP_0_RT_OFFSET 29879 -#define QM_REG_WRROTHERPQGRP_1_RT_OFFSET 29880 -#define QM_REG_WRROTHERPQGRP_2_RT_OFFSET 29881 -#define QM_REG_WRROTHERPQGRP_3_RT_OFFSET 29882 -#define QM_REG_WRROTHERPQGRP_4_RT_OFFSET 29883 -#define QM_REG_WRROTHERPQGRP_5_RT_OFFSET 29884 -#define QM_REG_WRROTHERPQGRP_6_RT_OFFSET 29885 -#define QM_REG_WRROTHERPQGRP_7_RT_OFFSET 29886 -#define QM_REG_WRROTHERPQGRP_8_RT_OFFSET 29887 -#define QM_REG_WRROTHERPQGRP_9_RT_OFFSET 29888 -#define QM_REG_WRROTHERPQGRP_10_RT_OFFSET 29889 -#define QM_REG_WRROTHERPQGRP_11_RT_OFFSET 29890 -#define QM_REG_WRROTHERPQGRP_12_RT_OFFSET 29891 -#define QM_REG_WRROTHERPQGRP_13_RT_OFFSET 29892 -#define QM_REG_WRROTHERPQGRP_14_RT_OFFSET 29893 -#define QM_REG_WRROTHERPQGRP_15_RT_OFFSET 29894 -#define QM_REG_WRROTHERGRPWEIGHT_0_RT_OFFSET 29895 -#define QM_REG_WRROTHERGRPWEIGHT_1_RT_OFFSET 29896 -#define QM_REG_WRROTHERGRPWEIGHT_2_RT_OFFSET 29897 -#define QM_REG_WRROTHERGRPWEIGHT_3_RT_OFFSET 29898 -#define QM_REG_WRRTXGRPWEIGHT_0_RT_OFFSET 29899 -#define QM_REG_WRRTXGRPWEIGHT_1_RT_OFFSET 29900 -#define QM_REG_PQTX2PF_0_RT_OFFSET 29901 -#define QM_REG_PQTX2PF_1_RT_OFFSET 29902 -#define QM_REG_PQTX2PF_2_RT_OFFSET 29903 -#define QM_REG_PQTX2PF_3_RT_OFFSET 29904 -#define QM_REG_PQTX2PF_4_RT_OFFSET 29905 -#define QM_REG_PQTX2PF_5_RT_OFFSET 29906 -#define QM_REG_PQTX2PF_6_RT_OFFSET 29907 -#define QM_REG_PQTX2PF_7_RT_OFFSET 29908 -#define QM_REG_PQTX2PF_8_RT_OFFSET 29909 -#define QM_REG_PQTX2PF_9_RT_OFFSET 29910 -#define QM_REG_PQTX2PF_10_RT_OFFSET 29911 -#define QM_REG_PQTX2PF_11_RT_OFFSET 29912 -#define QM_REG_PQTX2PF_12_RT_OFFSET 29913 -#define QM_REG_PQTX2PF_13_RT_OFFSET 29914 -#define QM_REG_PQTX2PF_14_RT_OFFSET 29915 -#define QM_REG_PQTX2PF_15_RT_OFFSET 29916 -#define QM_REG_PQTX2PF_16_RT_OFFSET 29917 -#define QM_REG_PQTX2PF_17_RT_OFFSET 29918 -#define QM_REG_PQTX2PF_18_RT_OFFSET 29919 -#define QM_REG_PQTX2PF_19_RT_OFFSET 29920 -#define QM_REG_PQTX2PF_20_RT_OFFSET 29921 -#define QM_REG_PQTX2PF_21_RT_OFFSET 29922 -#define QM_REG_PQTX2PF_22_RT_OFFSET 29923 -#define QM_REG_PQTX2PF_23_RT_OFFSET 29924 -#define QM_REG_PQTX2PF_24_RT_OFFSET 29925 -#define QM_REG_PQTX2PF_25_RT_OFFSET 29926 -#define QM_REG_PQTX2PF_26_RT_OFFSET 29927 -#define QM_REG_PQTX2PF_27_RT_OFFSET 29928 -#define QM_REG_PQTX2PF_28_RT_OFFSET 29929 -#define QM_REG_PQTX2PF_29_RT_OFFSET 29930 -#define QM_REG_PQTX2PF_30_RT_OFFSET 29931 -#define QM_REG_PQTX2PF_31_RT_OFFSET 29932 -#define QM_REG_PQTX2PF_32_RT_OFFSET 29933 -#define QM_REG_PQTX2PF_33_RT_OFFSET 29934 -#define QM_REG_PQTX2PF_34_RT_OFFSET 29935 -#define QM_REG_PQTX2PF_35_RT_OFFSET 29936 -#define QM_REG_PQTX2PF_36_RT_OFFSET 29937 -#define QM_REG_PQTX2PF_37_RT_OFFSET 29938 -#define QM_REG_PQTX2PF_38_RT_OFFSET 29939 -#define QM_REG_PQTX2PF_39_RT_OFFSET 29940 -#define QM_REG_PQTX2PF_40_RT_OFFSET 29941 -#define QM_REG_PQTX2PF_41_RT_OFFSET 29942 -#define QM_REG_PQTX2PF_42_RT_OFFSET 29943 -#define QM_REG_PQTX2PF_43_RT_OFFSET 29944 -#define QM_REG_PQTX2PF_44_RT_OFFSET 29945 -#define QM_REG_PQTX2PF_45_RT_OFFSET 29946 -#define QM_REG_PQTX2PF_46_RT_OFFSET 29947 -#define QM_REG_PQTX2PF_47_RT_OFFSET 29948 -#define QM_REG_PQTX2PF_48_RT_OFFSET 29949 -#define QM_REG_PQTX2PF_49_RT_OFFSET 29950 -#define QM_REG_PQTX2PF_50_RT_OFFSET 29951 -#define QM_REG_PQTX2PF_51_RT_OFFSET 29952 -#define QM_REG_PQTX2PF_52_RT_OFFSET 29953 -#define QM_REG_PQTX2PF_53_RT_OFFSET 29954 -#define QM_REG_PQTX2PF_54_RT_OFFSET 29955 -#define QM_REG_PQTX2PF_55_RT_OFFSET 29956 -#define QM_REG_PQTX2PF_56_RT_OFFSET 29957 -#define QM_REG_PQTX2PF_57_RT_OFFSET 29958 -#define QM_REG_PQTX2PF_58_RT_OFFSET 29959 -#define QM_REG_PQTX2PF_59_RT_OFFSET 29960 -#define QM_REG_PQTX2PF_60_RT_OFFSET 29961 -#define QM_REG_PQTX2PF_61_RT_OFFSET 29962 -#define QM_REG_PQTX2PF_62_RT_OFFSET 29963 -#define QM_REG_PQTX2PF_63_RT_OFFSET 29964 -#define QM_REG_PQOTHER2PF_0_RT_OFFSET 29965 -#define QM_REG_PQOTHER2PF_1_RT_OFFSET 29966 -#define QM_REG_PQOTHER2PF_2_RT_OFFSET 29967 -#define QM_REG_PQOTHER2PF_3_RT_OFFSET 29968 -#define QM_REG_PQOTHER2PF_4_RT_OFFSET 29969 -#define QM_REG_PQOTHER2PF_5_RT_OFFSET 29970 -#define QM_REG_PQOTHER2PF_6_RT_OFFSET 29971 -#define QM_REG_PQOTHER2PF_7_RT_OFFSET 29972 -#define QM_REG_PQOTHER2PF_8_RT_OFFSET 29973 -#define QM_REG_PQOTHER2PF_9_RT_OFFSET 29974 -#define QM_REG_PQOTHER2PF_10_RT_OFFSET 29975 -#define QM_REG_PQOTHER2PF_11_RT_OFFSET 29976 -#define QM_REG_PQOTHER2PF_12_RT_OFFSET 29977 -#define QM_REG_PQOTHER2PF_13_RT_OFFSET 29978 -#define QM_REG_PQOTHER2PF_14_RT_OFFSET 29979 -#define QM_REG_PQOTHER2PF_15_RT_OFFSET 29980 -#define QM_REG_RLGLBLPERIOD_0_RT_OFFSET 29981 -#define QM_REG_RLGLBLPERIOD_1_RT_OFFSET 29982 -#define QM_REG_RLGLBLPERIODTIMER_0_RT_OFFSET 29983 -#define QM_REG_RLGLBLPERIODTIMER_1_RT_OFFSET 29984 -#define QM_REG_RLGLBLPERIODSEL_0_RT_OFFSET 29985 -#define QM_REG_RLGLBLPERIODSEL_1_RT_OFFSET 29986 -#define QM_REG_RLGLBLPERIODSEL_2_RT_OFFSET 29987 -#define QM_REG_RLGLBLPERIODSEL_3_RT_OFFSET 29988 -#define QM_REG_RLGLBLPERIODSEL_4_RT_OFFSET 29989 -#define QM_REG_RLGLBLPERIODSEL_5_RT_OFFSET 29990 -#define QM_REG_RLGLBLPERIODSEL_6_RT_OFFSET 29991 -#define QM_REG_RLGLBLPERIODSEL_7_RT_OFFSET 29992 -#define QM_REG_RLGLBLINCVAL_RT_OFFSET 29993 +#define QM_REG_AFULLQMBYPTHRPFWFQ_RT_OFFSET 29876 +#define QM_REG_AFULLQMBYPTHRVPWFQ_RT_OFFSET 29877 +#define QM_REG_AFULLQMBYPTHRPFRL_RT_OFFSET 29878 +#define QM_REG_AFULLQMBYPTHRGLBLRL_RT_OFFSET 29879 +#define QM_REG_AFULLOPRTNSTCCRDMASK_RT_OFFSET 29880 +#define QM_REG_WRROTHERPQGRP_0_RT_OFFSET 29881 +#define QM_REG_WRROTHERPQGRP_1_RT_OFFSET 29882 +#define QM_REG_WRROTHERPQGRP_2_RT_OFFSET 29883 +#define QM_REG_WRROTHERPQGRP_3_RT_OFFSET 29884 +#define QM_REG_WRROTHERPQGRP_4_RT_OFFSET 29885 +#define QM_REG_WRROTHERPQGRP_5_RT_OFFSET 29886 +#define QM_REG_WRROTHERPQGRP_6_RT_OFFSET 29887 +#define QM_REG_WRROTHERPQGRP_7_RT_OFFSET 29888 +#define QM_REG_WRROTHERPQGRP_8_RT_OFFSET 29889 +#define QM_REG_WRROTHERPQGRP_9_RT_OFFSET 29890 +#define QM_REG_WRROTHERPQGRP_10_RT_OFFSET 29891 +#define QM_REG_WRROTHERPQGRP_11_RT_OFFSET 29892 +#define QM_REG_WRROTHERPQGRP_12_RT_OFFSET 29893 +#define QM_REG_WRROTHERPQGRP_13_RT_OFFSET 29894 +#define QM_REG_WRROTHERPQGRP_14_RT_OFFSET 29895 +#define QM_REG_WRROTHERPQGRP_15_RT_OFFSET 29896 +#define QM_REG_WRROTHERGRPWEIGHT_0_RT_OFFSET 29897 +#define QM_REG_WRROTHERGRPWEIGHT_1_RT_OFFSET 29898 +#define QM_REG_WRROTHERGRPWEIGHT_2_RT_OFFSET 29899 +#define QM_REG_WRROTHERGRPWEIGHT_3_RT_OFFSET 29900 +#define QM_REG_WRRTXGRPWEIGHT_0_RT_OFFSET 29901 +#define QM_REG_WRRTXGRPWEIGHT_1_RT_OFFSET 29902 +#define QM_REG_PQTX2PF_0_RT_OFFSET 29903 +#define QM_REG_PQTX2PF_1_RT_OFFSET 29904 +#define QM_REG_PQTX2PF_2_RT_OFFSET 29905 +#define QM_REG_PQTX2PF_3_RT_OFFSET 29906 +#define QM_REG_PQTX2PF_4_RT_OFFSET 29907 +#define QM_REG_PQTX2PF_5_RT_OFFSET 29908 +#define QM_REG_PQTX2PF_6_RT_OFFSET 29909 +#define QM_REG_PQTX2PF_7_RT_OFFSET 29910 +#define QM_REG_PQTX2PF_8_RT_OFFSET 29911 +#define QM_REG_PQTX2PF_9_RT_OFFSET 29912 +#define QM_REG_PQTX2PF_10_RT_OFFSET 29913 +#define QM_REG_PQTX2PF_11_RT_OFFSET 29914 +#define QM_REG_PQTX2PF_12_RT_OFFSET 29915 +#define QM_REG_PQTX2PF_13_RT_OFFSET 29916 +#define QM_REG_PQTX2PF_14_RT_OFFSET 29917 +#define QM_REG_PQTX2PF_15_RT_OFFSET 29918 +#define QM_REG_PQTX2PF_16_RT_OFFSET 29919 +#define QM_REG_PQTX2PF_17_RT_OFFSET 29920 +#define QM_REG_PQTX2PF_18_RT_OFFSET 29921 +#define QM_REG_PQTX2PF_19_RT_OFFSET 29922 +#define QM_REG_PQTX2PF_20_RT_OFFSET 29923 +#define QM_REG_PQTX2PF_21_RT_OFFSET 29924 +#define QM_REG_PQTX2PF_22_RT_OFFSET 29925 +#define QM_REG_PQTX2PF_23_RT_OFFSET 29926 +#define QM_REG_PQTX2PF_24_RT_OFFSET 29927 +#define QM_REG_PQTX2PF_25_RT_OFFSET 29928 +#define QM_REG_PQTX2PF_26_RT_OFFSET 29929 +#define QM_REG_PQTX2PF_27_RT_OFFSET 29930 +#define QM_REG_PQTX2PF_28_RT_OFFSET 29931 +#define QM_REG_PQTX2PF_29_RT_OFFSET 29932 +#define QM_REG_PQTX2PF_30_RT_OFFSET 29933 +#define QM_REG_PQTX2PF_31_RT_OFFSET 29934 +#define QM_REG_PQTX2PF_32_RT_OFFSET 29935 +#define QM_REG_PQTX2PF_33_RT_OFFSET 29936 +#define QM_REG_PQTX2PF_34_RT_OFFSET 29937 +#define QM_REG_PQTX2PF_35_RT_OFFSET 29938 +#define QM_REG_PQTX2PF_36_RT_OFFSET 29939 +#define QM_REG_PQTX2PF_37_RT_OFFSET 29940 +#define QM_REG_PQTX2PF_38_RT_OFFSET 29941 +#define QM_REG_PQTX2PF_39_RT_OFFSET 29942 +#define QM_REG_PQTX2PF_40_RT_OFFSET 29943 +#define QM_REG_PQTX2PF_41_RT_OFFSET 29944 +#define QM_REG_PQTX2PF_42_RT_OFFSET 29945 +#define QM_REG_PQTX2PF_43_RT_OFFSET 29946 +#define QM_REG_PQTX2PF_44_RT_OFFSET 29947 +#define QM_REG_PQTX2PF_45_RT_OFFSET 29948 +#define QM_REG_PQTX2PF_46_RT_OFFSET 29949 +#define QM_REG_PQTX2PF_47_RT_OFFSET 29950 +#define QM_REG_PQTX2PF_48_RT_OFFSET 29951 +#define QM_REG_PQTX2PF_49_RT_OFFSET 29952 +#define QM_REG_PQTX2PF_50_RT_OFFSET 29953 +#define QM_REG_PQTX2PF_51_RT_OFFSET 29954 +#define QM_REG_PQTX2PF_52_RT_OFFSET 29955 +#define QM_REG_PQTX2PF_53_RT_OFFSET 29956 +#define QM_REG_PQTX2PF_54_RT_OFFSET 29957 +#define QM_REG_PQTX2PF_55_RT_OFFSET 29958 +#define QM_REG_PQTX2PF_56_RT_OFFSET 29959 +#define QM_REG_PQTX2PF_57_RT_OFFSET 29960 +#define QM_REG_PQTX2PF_58_RT_OFFSET 29961 +#define QM_REG_PQTX2PF_59_RT_OFFSET 29962 +#define QM_REG_PQTX2PF_60_RT_OFFSET 29963 +#define QM_REG_PQTX2PF_61_RT_OFFSET 29964 +#define QM_REG_PQTX2PF_62_RT_OFFSET 29965 +#define QM_REG_PQTX2PF_63_RT_OFFSET 29966 +#define QM_REG_PQOTHER2PF_0_RT_OFFSET 29967 +#define QM_REG_PQOTHER2PF_1_RT_OFFSET 29968 +#define QM_REG_PQOTHER2PF_2_RT_OFFSET 29969 +#define QM_REG_PQOTHER2PF_3_RT_OFFSET 29970 +#define QM_REG_PQOTHER2PF_4_RT_OFFSET 29971 +#define QM_REG_PQOTHER2PF_5_RT_OFFSET 29972 +#define QM_REG_PQOTHER2PF_6_RT_OFFSET 29973 +#define QM_REG_PQOTHER2PF_7_RT_OFFSET 29974 +#define QM_REG_PQOTHER2PF_8_RT_OFFSET 29975 +#define QM_REG_PQOTHER2PF_9_RT_OFFSET 29976 +#define QM_REG_PQOTHER2PF_10_RT_OFFSET 29977 +#define QM_REG_PQOTHER2PF_11_RT_OFFSET 29978 +#define QM_REG_PQOTHER2PF_12_RT_OFFSET 29979 +#define QM_REG_PQOTHER2PF_13_RT_OFFSET 29980 +#define QM_REG_PQOTHER2PF_14_RT_OFFSET 29981 +#define QM_REG_PQOTHER2PF_15_RT_OFFSET 29982 +#define QM_REG_RLGLBLPERIOD_0_RT_OFFSET 29983 +#define QM_REG_RLGLBLPERIOD_1_RT_OFFSET 29984 +#define QM_REG_RLGLBLPERIODTIMER_0_RT_OFFSET 29985 +#define QM_REG_RLGLBLPERIODTIMER_1_RT_OFFSET 29986 +#define QM_REG_RLGLBLPERIODSEL_0_RT_OFFSET 29987 +#define QM_REG_RLGLBLPERIODSEL_1_RT_OFFSET 29988 +#define QM_REG_RLGLBLPERIODSEL_2_RT_OFFSET 29989 +#define QM_REG_RLGLBLPERIODSEL_3_RT_OFFSET 29990 +#define QM_REG_RLGLBLPERIODSEL_4_RT_OFFSET 29991 +#define QM_REG_RLGLBLPERIODSEL_5_RT_OFFSET 29992 +#define QM_REG_RLGLBLPERIODSEL_6_RT_OFFSET 29993 +#define QM_REG_RLGLBLPERIODSEL_7_RT_OFFSET 29994 +#define QM_REG_RLGLBLINCVAL_RT_OFFSET 29995 #define QM_REG_RLGLBLINCVAL_RT_SIZE 256 -#define QM_REG_RLGLBLUPPERBOUND_RT_OFFSET 30249 +#define QM_REG_RLGLBLUPPERBOUND_RT_OFFSET 30251 #define QM_REG_RLGLBLUPPERBOUND_RT_SIZE 256 -#define QM_REG_RLGLBLCRD_RT_OFFSET 30505 +#define QM_REG_RLGLBLCRD_RT_OFFSET 30507 #define QM_REG_RLGLBLCRD_RT_SIZE 256 -#define QM_REG_RLGLBLENABLE_RT_OFFSET 30761 -#define QM_REG_RLPFPERIOD_RT_OFFSET 30762 -#define QM_REG_RLPFPERIODTIMER_RT_OFFSET 30763 -#define QM_REG_RLPFINCVAL_RT_OFFSET 30764 +#define QM_REG_RLGLBLENABLE_RT_OFFSET 30763 +#define QM_REG_RLPFPERIOD_RT_OFFSET 30764 +#define QM_REG_RLPFPERIODTIMER_RT_OFFSET 30765 +#define QM_REG_RLPFINCVAL_RT_OFFSET 30766 #define QM_REG_RLPFINCVAL_RT_SIZE 16 -#define QM_REG_RLPFUPPERBOUND_RT_OFFSET 30780 +#define QM_REG_RLPFUPPERBOUND_RT_OFFSET 30782 #define QM_REG_RLPFUPPERBOUND_RT_SIZE 16 -#define QM_REG_RLPFCRD_RT_OFFSET 30796 +#define QM_REG_RLPFCRD_RT_OFFSET 30798 #define QM_REG_RLPFCRD_RT_SIZE 16 -#define QM_REG_RLPFENABLE_RT_OFFSET 30812 -#define QM_REG_RLPFVOQENABLE_RT_OFFSET 30813 -#define QM_REG_WFQPFWEIGHT_RT_OFFSET 30814 +#define QM_REG_RLPFENABLE_RT_OFFSET 30814 +#define QM_REG_RLPFVOQENABLE_RT_OFFSET 30815 +#define QM_REG_WFQPFWEIGHT_RT_OFFSET 30816 #define QM_REG_WFQPFWEIGHT_RT_SIZE 16 -#define QM_REG_WFQPFUPPERBOUND_RT_OFFSET 30830 +#define QM_REG_WFQPFUPPERBOUND_RT_OFFSET 30832 #define QM_REG_WFQPFUPPERBOUND_RT_SIZE 16 -#define QM_REG_WFQPFCRD_RT_OFFSET 30846 +#define QM_REG_WFQPFCRD_RT_OFFSET 30848 #define QM_REG_WFQPFCRD_RT_SIZE 160 -#define QM_REG_WFQPFENABLE_RT_OFFSET 31006 -#define QM_REG_WFQVPENABLE_RT_OFFSET 31007 -#define QM_REG_BASEADDRTXPQ_RT_OFFSET 31008 +#define QM_REG_WFQPFENABLE_RT_OFFSET 31008 +#define QM_REG_WFQVPENABLE_RT_OFFSET 31009 +#define QM_REG_BASEADDRTXPQ_RT_OFFSET 31010 #define QM_REG_BASEADDRTXPQ_RT_SIZE 512 -#define QM_REG_TXPQMAP_RT_OFFSET 31520 +#define QM_REG_TXPQMAP_RT_OFFSET 31522 #define QM_REG_TXPQMAP_RT_SIZE 512 -#define QM_REG_WFQVPWEIGHT_RT_OFFSET 32032 +#define QM_REG_WFQVPWEIGHT_RT_OFFSET 32034 #define QM_REG_WFQVPWEIGHT_RT_SIZE 512 -#define QM_REG_WFQVPUPPERBOUND_RT_OFFSET 32544 -#define QM_REG_WFQVPUPPERBOUND_RT_SIZE 512 -#define QM_REG_WFQVPCRD_RT_OFFSET 33056 +#define QM_REG_WFQVPCRD_RT_OFFSET 32546 #define QM_REG_WFQVPCRD_RT_SIZE 512 -#define QM_REG_WFQVPMAP_RT_OFFSET 33568 +#define QM_REG_WFQVPMAP_RT_OFFSET 33058 #define QM_REG_WFQVPMAP_RT_SIZE 512 -#define QM_REG_WFQPFCRD_MSB_RT_OFFSET 34080 +#define QM_REG_WFQPFCRD_MSB_RT_OFFSET 33570 #define QM_REG_WFQPFCRD_MSB_RT_SIZE 160 -#define NIG_REG_LLH_CLS_TYPE_DUALMODE_RT_OFFSET 34240 -#define NIG_REG_OUTER_TAG_VALUE_LIST0_RT_OFFSET 34241 -#define NIG_REG_OUTER_TAG_VALUE_LIST1_RT_OFFSET 34242 -#define NIG_REG_OUTER_TAG_VALUE_LIST2_RT_OFFSET 34243 -#define NIG_REG_OUTER_TAG_VALUE_LIST3_RT_OFFSET 34244 -#define NIG_REG_OUTER_TAG_VALUE_MASK_RT_OFFSET 34245 -#define NIG_REG_LLH_FUNC_TAGMAC_CLS_TYPE_RT_OFFSET 34246 -#define NIG_REG_LLH_FUNC_TAG_EN_RT_OFFSET 34247 +#define NIG_REG_TAG_ETHERTYPE_0_RT_OFFSET 33730 +#define NIG_REG_OUTER_TAG_VALUE_LIST0_RT_OFFSET 33731 +#define NIG_REG_OUTER_TAG_VALUE_LIST1_RT_OFFSET 33732 +#define NIG_REG_OUTER_TAG_VALUE_LIST2_RT_OFFSET 33733 +#define NIG_REG_OUTER_TAG_VALUE_LIST3_RT_OFFSET 33734 +#define NIG_REG_OUTER_TAG_VALUE_MASK_RT_OFFSET 33735 +#define NIG_REG_LLH_FUNC_TAGMAC_CLS_TYPE_RT_OFFSET 33736 +#define NIG_REG_LLH_FUNC_TAG_EN_RT_OFFSET 33737 #define NIG_REG_LLH_FUNC_TAG_EN_RT_SIZE 4 -#define NIG_REG_LLH_FUNC_TAG_HDR_SEL_RT_OFFSET 34251 +#define NIG_REG_LLH_FUNC_TAG_HDR_SEL_RT_OFFSET 33741 #define NIG_REG_LLH_FUNC_TAG_HDR_SEL_RT_SIZE 4 -#define NIG_REG_LLH_FUNC_TAG_VALUE_RT_OFFSET 34255 +#define NIG_REG_LLH_FUNC_TAG_VALUE_RT_OFFSET 33745 #define NIG_REG_LLH_FUNC_TAG_VALUE_RT_SIZE 4 -#define NIG_REG_LLH_FUNC_NO_TAG_RT_OFFSET 34259 -#define NIG_REG_LLH_FUNC_FILTER_VALUE_RT_OFFSET 34260 +#define NIG_REG_LLH_FUNC_NO_TAG_RT_OFFSET 33749 +#define NIG_REG_LLH_FUNC_FILTER_VALUE_RT_OFFSET 33750 #define NIG_REG_LLH_FUNC_FILTER_VALUE_RT_SIZE 32 -#define NIG_REG_LLH_FUNC_FILTER_EN_RT_OFFSET 34292 +#define NIG_REG_LLH_FUNC_FILTER_EN_RT_OFFSET 33782 #define NIG_REG_LLH_FUNC_FILTER_EN_RT_SIZE 16 -#define NIG_REG_LLH_FUNC_FILTER_MODE_RT_OFFSET 34308 +#define NIG_REG_LLH_FUNC_FILTER_MODE_RT_OFFSET 33798 #define NIG_REG_LLH_FUNC_FILTER_MODE_RT_SIZE 16 -#define NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE_RT_OFFSET 34324 +#define NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE_RT_OFFSET 33814 #define NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE_RT_SIZE 16 -#define NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_OFFSET 34340 +#define NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_OFFSET 33830 #define NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_SIZE 16 -#define NIG_REG_TX_EDPM_CTRL_RT_OFFSET 34356 -#define CDU_REG_CID_ADDR_PARAMS_RT_OFFSET 34357 -#define CDU_REG_SEGMENT0_PARAMS_RT_OFFSET 34358 -#define CDU_REG_SEGMENT1_PARAMS_RT_OFFSET 34359 -#define CDU_REG_PF_SEG0_TYPE_OFFSET_RT_OFFSET 34360 -#define CDU_REG_PF_SEG1_TYPE_OFFSET_RT_OFFSET 34361 -#define CDU_REG_PF_SEG2_TYPE_OFFSET_RT_OFFSET 34362 -#define CDU_REG_PF_SEG3_TYPE_OFFSET_RT_OFFSET 34363 -#define CDU_REG_PF_FL_SEG0_TYPE_OFFSET_RT_OFFSET 34364 -#define CDU_REG_PF_FL_SEG1_TYPE_OFFSET_RT_OFFSET 34365 -#define CDU_REG_PF_FL_SEG2_TYPE_OFFSET_RT_OFFSET 34366 -#define CDU_REG_PF_FL_SEG3_TYPE_OFFSET_RT_OFFSET 34367 -#define CDU_REG_VF_SEG_TYPE_OFFSET_RT_OFFSET 34368 -#define CDU_REG_VF_FL_SEG_TYPE_OFFSET_RT_OFFSET 34369 -#define PBF_REG_BTB_SHARED_AREA_SIZE_RT_OFFSET 34370 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ0_RT_OFFSET 34371 -#define PBF_REG_BTB_GUARANTEED_VOQ0_RT_OFFSET 34372 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ0_RT_OFFSET 34373 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ1_RT_OFFSET 34374 -#define PBF_REG_BTB_GUARANTEED_VOQ1_RT_OFFSET 34375 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ1_RT_OFFSET 34376 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ2_RT_OFFSET 34377 -#define PBF_REG_BTB_GUARANTEED_VOQ2_RT_OFFSET 34378 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ2_RT_OFFSET 34379 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ3_RT_OFFSET 34380 -#define PBF_REG_BTB_GUARANTEED_VOQ3_RT_OFFSET 34381 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ3_RT_OFFSET 34382 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ4_RT_OFFSET 34383 -#define PBF_REG_BTB_GUARANTEED_VOQ4_RT_OFFSET 34384 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ4_RT_OFFSET 34385 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ5_RT_OFFSET 34386 -#define PBF_REG_BTB_GUARANTEED_VOQ5_RT_OFFSET 34387 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ5_RT_OFFSET 34388 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ6_RT_OFFSET 34389 -#define PBF_REG_BTB_GUARANTEED_VOQ6_RT_OFFSET 34390 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ6_RT_OFFSET 34391 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ7_RT_OFFSET 34392 -#define PBF_REG_BTB_GUARANTEED_VOQ7_RT_OFFSET 34393 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ7_RT_OFFSET 34394 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ8_RT_OFFSET 34395 -#define PBF_REG_BTB_GUARANTEED_VOQ8_RT_OFFSET 34396 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ8_RT_OFFSET 34397 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ9_RT_OFFSET 34398 -#define PBF_REG_BTB_GUARANTEED_VOQ9_RT_OFFSET 34399 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ9_RT_OFFSET 34400 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ10_RT_OFFSET 34401 -#define PBF_REG_BTB_GUARANTEED_VOQ10_RT_OFFSET 34402 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ10_RT_OFFSET 34403 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ11_RT_OFFSET 34404 -#define PBF_REG_BTB_GUARANTEED_VOQ11_RT_OFFSET 34405 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ11_RT_OFFSET 34406 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ12_RT_OFFSET 34407 -#define PBF_REG_BTB_GUARANTEED_VOQ12_RT_OFFSET 34408 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ12_RT_OFFSET 34409 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ13_RT_OFFSET 34410 -#define PBF_REG_BTB_GUARANTEED_VOQ13_RT_OFFSET 34411 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ13_RT_OFFSET 34412 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ14_RT_OFFSET 34413 -#define PBF_REG_BTB_GUARANTEED_VOQ14_RT_OFFSET 34414 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ14_RT_OFFSET 34415 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ15_RT_OFFSET 34416 -#define PBF_REG_BTB_GUARANTEED_VOQ15_RT_OFFSET 34417 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ15_RT_OFFSET 34418 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ16_RT_OFFSET 34419 -#define PBF_REG_BTB_GUARANTEED_VOQ16_RT_OFFSET 34420 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ16_RT_OFFSET 34421 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ17_RT_OFFSET 34422 -#define PBF_REG_BTB_GUARANTEED_VOQ17_RT_OFFSET 34423 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ17_RT_OFFSET 34424 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ18_RT_OFFSET 34425 -#define PBF_REG_BTB_GUARANTEED_VOQ18_RT_OFFSET 34426 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ18_RT_OFFSET 34427 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ19_RT_OFFSET 34428 -#define PBF_REG_BTB_GUARANTEED_VOQ19_RT_OFFSET 34429 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ19_RT_OFFSET 34430 -#define XCM_REG_CON_PHY_Q3_RT_OFFSET 34431 - -#define RUNTIME_ARRAY_SIZE 34432 +#define NIG_REG_TX_EDPM_CTRL_RT_OFFSET 33846 +#define CDU_REG_CID_ADDR_PARAMS_RT_OFFSET 33847 +#define CDU_REG_SEGMENT0_PARAMS_RT_OFFSET 33848 +#define CDU_REG_SEGMENT1_PARAMS_RT_OFFSET 33849 +#define CDU_REG_PF_SEG0_TYPE_OFFSET_RT_OFFSET 33850 +#define CDU_REG_PF_SEG1_TYPE_OFFSET_RT_OFFSET 33851 +#define CDU_REG_PF_SEG2_TYPE_OFFSET_RT_OFFSET 33852 +#define CDU_REG_PF_SEG3_TYPE_OFFSET_RT_OFFSET 33853 +#define CDU_REG_PF_FL_SEG0_TYPE_OFFSET_RT_OFFSET 33854 +#define CDU_REG_PF_FL_SEG1_TYPE_OFFSET_RT_OFFSET 33855 +#define CDU_REG_PF_FL_SEG2_TYPE_OFFSET_RT_OFFSET 33856 +#define CDU_REG_PF_FL_SEG3_TYPE_OFFSET_RT_OFFSET 33857 +#define CDU_REG_VF_SEG_TYPE_OFFSET_RT_OFFSET 33858 +#define CDU_REG_VF_FL_SEG_TYPE_OFFSET_RT_OFFSET 33859 +#define PBF_REG_TAG_ETHERTYPE_0_RT_OFFSET 33860 +#define PBF_REG_BTB_SHARED_AREA_SIZE_RT_OFFSET 33861 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ0_RT_OFFSET 33862 +#define PBF_REG_BTB_GUARANTEED_VOQ0_RT_OFFSET 33863 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ0_RT_OFFSET 33864 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ1_RT_OFFSET 33865 +#define PBF_REG_BTB_GUARANTEED_VOQ1_RT_OFFSET 33866 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ1_RT_OFFSET 33867 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ2_RT_OFFSET 33868 +#define PBF_REG_BTB_GUARANTEED_VOQ2_RT_OFFSET 33869 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ2_RT_OFFSET 33870 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ3_RT_OFFSET 33871 +#define PBF_REG_BTB_GUARANTEED_VOQ3_RT_OFFSET 33872 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ3_RT_OFFSET 33873 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ4_RT_OFFSET 33874 +#define PBF_REG_BTB_GUARANTEED_VOQ4_RT_OFFSET 33875 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ4_RT_OFFSET 33876 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ5_RT_OFFSET 33877 +#define PBF_REG_BTB_GUARANTEED_VOQ5_RT_OFFSET 33878 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ5_RT_OFFSET 33879 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ6_RT_OFFSET 33880 +#define PBF_REG_BTB_GUARANTEED_VOQ6_RT_OFFSET 33881 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ6_RT_OFFSET 33882 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ7_RT_OFFSET 33883 +#define PBF_REG_BTB_GUARANTEED_VOQ7_RT_OFFSET 33884 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ7_RT_OFFSET 33885 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ8_RT_OFFSET 33886 +#define PBF_REG_BTB_GUARANTEED_VOQ8_RT_OFFSET 33887 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ8_RT_OFFSET 33888 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ9_RT_OFFSET 33889 +#define PBF_REG_BTB_GUARANTEED_VOQ9_RT_OFFSET 33890 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ9_RT_OFFSET 33891 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ10_RT_OFFSET 33892 +#define PBF_REG_BTB_GUARANTEED_VOQ10_RT_OFFSET 33893 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ10_RT_OFFSET 33894 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ11_RT_OFFSET 33895 +#define PBF_REG_BTB_GUARANTEED_VOQ11_RT_OFFSET 33896 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ11_RT_OFFSET 33897 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ12_RT_OFFSET 33898 +#define PBF_REG_BTB_GUARANTEED_VOQ12_RT_OFFSET 33899 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ12_RT_OFFSET 33900 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ13_RT_OFFSET 33901 +#define PBF_REG_BTB_GUARANTEED_VOQ13_RT_OFFSET 33902 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ13_RT_OFFSET 33903 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ14_RT_OFFSET 33904 +#define PBF_REG_BTB_GUARANTEED_VOQ14_RT_OFFSET 33905 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ14_RT_OFFSET 33906 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ15_RT_OFFSET 33907 +#define PBF_REG_BTB_GUARANTEED_VOQ15_RT_OFFSET 33908 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ15_RT_OFFSET 33909 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ16_RT_OFFSET 33910 +#define PBF_REG_BTB_GUARANTEED_VOQ16_RT_OFFSET 33911 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ16_RT_OFFSET 33912 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ17_RT_OFFSET 33913 +#define PBF_REG_BTB_GUARANTEED_VOQ17_RT_OFFSET 33914 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ17_RT_OFFSET 33915 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ18_RT_OFFSET 33916 +#define PBF_REG_BTB_GUARANTEED_VOQ18_RT_OFFSET 33917 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ18_RT_OFFSET 33918 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ19_RT_OFFSET 33919 +#define PBF_REG_BTB_GUARANTEED_VOQ19_RT_OFFSET 33920 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ19_RT_OFFSET 33921 +#define XCM_REG_CON_PHY_Q3_RT_OFFSET 33922 + +#define RUNTIME_ARRAY_SIZE 33923 -/* The eth storm context for the Ystorm */ -struct ystorm_eth_conn_st_ctx { +/* The eth storm context for the Tstorm */ +struct tstorm_eth_conn_st_ctx { __le32 reserved[4]; }; @@ -2535,41 +2501,253 @@ struct xstorm_eth_conn_ag_ctx { __le32 reg7 /* reg7 */; __le32 reg8 /* reg8 */; __le32 reg9 /* reg9 */; - u8 byte7 /* byte7 */; - u8 byte8 /* byte8 */; - u8 byte9 /* byte9 */; - u8 byte10 /* byte10 */; - u8 byte11 /* byte11 */; - u8 byte12 /* byte12 */; - u8 byte13 /* byte13 */; - u8 byte14 /* byte14 */; - u8 byte15 /* byte15 */; - u8 byte16 /* byte16 */; - __le16 word11 /* word11 */; + u8 byte7 /* byte7 */; + u8 byte8 /* byte8 */; + u8 byte9 /* byte9 */; + u8 byte10 /* byte10 */; + u8 byte11 /* byte11 */; + u8 byte12 /* byte12 */; + u8 byte13 /* byte13 */; + u8 byte14 /* byte14 */; + u8 byte15 /* byte15 */; + u8 byte16 /* byte16 */; + __le16 word11 /* word11 */; + __le32 reg10 /* reg10 */; + __le32 reg11 /* reg11 */; + __le32 reg12 /* reg12 */; + __le32 reg13 /* reg13 */; + __le32 reg14 /* reg14 */; + __le32 reg15 /* reg15 */; + __le32 reg16 /* reg16 */; + __le32 reg17 /* reg17 */; + __le32 reg18 /* reg18 */; + __le32 reg19 /* reg19 */; + __le16 word12 /* word12 */; + __le16 word13 /* word13 */; + __le16 word14 /* word14 */; + __le16 word15 /* word15 */; +}; + +/* The eth storm context for the Ystorm */ +struct ystorm_eth_conn_st_ctx { + __le32 reserved[8]; +}; + +struct ystorm_eth_conn_ag_ctx { + u8 byte0 /* cdu_validation */; + u8 byte1 /* state */; + u8 flags0; +#define YSTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ +#define YSTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ +#define YSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_MASK 0x3 /* cf0 */ +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_SHIFT 2 +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_MASK 0x3 /* cf1 */ +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_SHIFT 4 +#define YSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 /* cf2 */ +#define YSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 + u8 flags1; +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_MASK 0x1 /* cf0en */ +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_SHIFT 0 +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_EN_MASK 0x1 /* cf1en */ +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_EN_SHIFT 1 +#define YSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ +#define YSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ +#define YSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ +#define YSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ +#define YSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ +#define YSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ +#define YSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 + u8 byte2 /* byte2 */; + u8 byte3 /* byte3 */; + __le16 word0 /* word0 */; + __le32 terminate_spqe /* reg0 */; + __le32 reg1 /* reg1 */; + __le16 tx_bd_cons_upd /* word1 */; + __le16 word2 /* word2 */; + __le16 word3 /* word3 */; + __le16 word4 /* word4 */; + __le32 reg2 /* reg2 */; + __le32 reg3 /* reg3 */; +}; + +struct tstorm_eth_conn_ag_ctx { + u8 byte0 /* cdu_validation */; + u8 byte1 /* state */; + u8 flags0; +#define TSTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ +#define TSTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ +#define TSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_ETH_CONN_AG_CTX_BIT2_MASK 0x1 /* bit2 */ +#define TSTORM_ETH_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_BIT3_MASK 0x1 /* bit3 */ +#define TSTORM_ETH_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_ETH_CONN_AG_CTX_BIT4_MASK 0x1 /* bit4 */ +#define TSTORM_ETH_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_BIT5_MASK 0x1 /* bit5 */ +#define TSTORM_ETH_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 /* timer0cf */ +#define TSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 6 + u8 flags1; +#define TSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 /* timer1cf */ +#define TSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ +#define TSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 /* timer_stop_all */ +#define TSTORM_ETH_CONN_AG_CTX_CF3_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF4_MASK 0x3 /* cf4 */ +#define TSTORM_ETH_CONN_AG_CTX_CF4_SHIFT 6 + u8 flags2; +#define TSTORM_ETH_CONN_AG_CTX_CF5_MASK 0x3 /* cf5 */ +#define TSTORM_ETH_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF6_MASK 0x3 /* cf6 */ +#define TSTORM_ETH_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF7_MASK 0x3 /* cf7 */ +#define TSTORM_ETH_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF8_MASK 0x3 /* cf8 */ +#define TSTORM_ETH_CONN_AG_CTX_CF8_SHIFT 6 + u8 flags3; +#define TSTORM_ETH_CONN_AG_CTX_CF9_MASK 0x3 /* cf9 */ +#define TSTORM_ETH_CONN_AG_CTX_CF9_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF10_MASK 0x3 /* cf10 */ +#define TSTORM_ETH_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ +#define TSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ +#define TSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ +#define TSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ +#define TSTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 7 + u8 flags4; +#define TSTORM_ETH_CONN_AG_CTX_CF4EN_MASK 0x1 /* cf4en */ +#define TSTORM_ETH_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF5EN_MASK 0x1 /* cf5en */ +#define TSTORM_ETH_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_ETH_CONN_AG_CTX_CF6EN_MASK 0x1 /* cf6en */ +#define TSTORM_ETH_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF7EN_MASK 0x1 /* cf7en */ +#define TSTORM_ETH_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_ETH_CONN_AG_CTX_CF8EN_MASK 0x1 /* cf8en */ +#define TSTORM_ETH_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF9EN_MASK 0x1 /* cf9en */ +#define TSTORM_ETH_CONN_AG_CTX_CF9EN_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_CF10EN_MASK 0x1 /* cf10en */ +#define TSTORM_ETH_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 + u8 flags5; +#define TSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_MASK 0x1 /* rule6en */ +#define TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ +#define TSTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 + __le32 reg0 /* reg0 */; + __le32 reg1 /* reg1 */; + __le32 reg2 /* reg2 */; + __le32 reg3 /* reg3 */; + __le32 reg4 /* reg4 */; + __le32 reg5 /* reg5 */; + __le32 reg6 /* reg6 */; + __le32 reg7 /* reg7 */; + __le32 reg8 /* reg8 */; + u8 byte2 /* byte2 */; + u8 byte3 /* byte3 */; + __le16 rx_bd_cons /* word0 */; + u8 byte4 /* byte4 */; + u8 byte5 /* byte5 */; + __le16 rx_bd_prod /* word1 */; + __le16 word2 /* conn_dpi */; + __le16 word3 /* word3 */; + __le32 reg9 /* reg9 */; __le32 reg10 /* reg10 */; - __le32 reg11 /* reg11 */; - __le32 reg12 /* reg12 */; - __le32 reg13 /* reg13 */; - __le32 reg14 /* reg14 */; - __le32 reg15 /* reg15 */; - __le32 reg16 /* reg16 */; - __le32 reg17 /* reg17 */; - __le32 reg18 /* reg18 */; - __le32 reg19 /* reg19 */; - __le16 word12 /* word12 */; - __le16 word13 /* word13 */; - __le16 word14 /* word14 */; - __le16 word15 /* word15 */; -}; - -/* The eth storm context for the Tstorm */ -struct tstorm_eth_conn_st_ctx { - __le32 reserved[4]; }; -/* The eth storm context for the Mstorm */ -struct mstorm_eth_conn_st_ctx { - __le32 reserved[8]; +struct ustorm_eth_conn_ag_ctx { + u8 byte0 /* cdu_validation */; + u8 byte1 /* state */; + u8 flags0; +#define USTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ +#define USTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ +#define USTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_MASK 0x3 /* timer0cf */ +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_MASK 0x3 /* timer1cf */ +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ +#define USTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 + u8 flags1; +#define USTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 /* timer_stop_all */ +#define USTORM_ETH_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_MASK 0x3 /* cf4 */ +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_MASK 0x3 /* cf5 */ +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_MASK 0x3 /* cf6 */ +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_SHIFT 6 + u8 flags2; +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_EN_MASK 0x1 /* cf0en */ +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_EN_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_EN_MASK 0x1 /* cf1en */ +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_EN_SHIFT 1 +#define USTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ +#define USTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ +#define USTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_MASK 0x1 /* cf4en */ +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_MASK 0x1 /* cf5en */ +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_SHIFT 5 +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_MASK 0x1 /* cf6en */ +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_SHIFT 6 +#define USTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ +#define USTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 + u8 flags3; +#define USTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ +#define USTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ +#define USTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ +#define USTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ +#define USTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ +#define USTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_RULE6EN_MASK 0x1 /* rule6en */ +#define USTORM_ETH_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ +#define USTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ +#define USTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 + u8 byte2 /* byte2 */; + u8 byte3 /* byte3 */; + __le16 word0 /* conn_dpi */; + __le16 tx_bd_cons /* word1 */; + __le32 reg0 /* reg0 */; + __le32 reg1 /* reg1 */; + __le32 reg2 /* reg2 */; + __le32 tx_int_coallecing_timeset /* reg3 */; + __le16 tx_drv_bd_cons /* word2 */; + __le16 rx_drv_cqe_cons /* word3 */; }; /* The eth storm context for the Ustorm */ @@ -2577,24 +2755,30 @@ struct ustorm_eth_conn_st_ctx { __le32 reserved[40]; }; +/* The eth storm context for the Mstorm */ +struct mstorm_eth_conn_st_ctx { + __le32 reserved[8]; +}; + /* eth connection context */ struct eth_conn_context { - struct ystorm_eth_conn_st_ctx ystorm_st_context; - struct regpair ystorm_st_padding[2] /* padding */; + struct tstorm_eth_conn_st_ctx tstorm_st_context; + struct regpair tstorm_st_padding[2]; struct pstorm_eth_conn_st_ctx pstorm_st_context; - struct regpair pstorm_st_padding[2] /* padding */; struct xstorm_eth_conn_st_ctx xstorm_st_context; struct xstorm_eth_conn_ag_ctx xstorm_ag_context; - struct tstorm_eth_conn_st_ctx tstorm_st_context; - struct regpair tstorm_st_padding[2] /* padding */; - struct mstorm_eth_conn_st_ctx mstorm_st_context; + struct ystorm_eth_conn_st_ctx ystorm_st_context; + struct ystorm_eth_conn_ag_ctx ystorm_ag_context; + struct tstorm_eth_conn_ag_ctx tstorm_ag_context; + struct ustorm_eth_conn_ag_ctx ustorm_ag_context; struct ustorm_eth_conn_st_ctx ustorm_st_context; + struct mstorm_eth_conn_st_ctx mstorm_st_context; }; enum eth_filter_action { ETH_FILTER_ACTION_REMOVE, ETH_FILTER_ACTION_ADD, - ETH_FILTER_ACTION_REPLACE, + ETH_FILTER_ACTION_REMOVE_ALL, MAX_ETH_FILTER_ACTION }; @@ -2653,6 +2837,32 @@ enum eth_ramrod_cmd_id { MAX_ETH_RAMROD_CMD_ID }; +enum eth_tx_err { + ETH_TX_ERR_DROP /* Drop erronous packet. */, + ETH_TX_ERR_ASSERT_MALICIOUS, + MAX_ETH_TX_ERR +}; + +struct eth_tx_err_vals { + __le16 values; +#define ETH_TX_ERR_VALS_ILLEGAL_VLAN_MODE_MASK 0x1 +#define ETH_TX_ERR_VALS_ILLEGAL_VLAN_MODE_SHIFT 0 +#define ETH_TX_ERR_VALS_PACKET_TOO_SMALL_MASK 0x1 +#define ETH_TX_ERR_VALS_PACKET_TOO_SMALL_SHIFT 1 +#define ETH_TX_ERR_VALS_ANTI_SPOOFING_ERR_MASK 0x1 +#define ETH_TX_ERR_VALS_ANTI_SPOOFING_ERR_SHIFT 2 +#define ETH_TX_ERR_VALS_ILLEGAL_INBAND_TAGS_MASK 0x1 +#define ETH_TX_ERR_VALS_ILLEGAL_INBAND_TAGS_SHIFT 3 +#define ETH_TX_ERR_VALS_VLAN_INSERTION_W_INBAND_TAG_MASK 0x1 +#define ETH_TX_ERR_VALS_VLAN_INSERTION_W_INBAND_TAG_SHIFT 4 +#define ETH_TX_ERR_VALS_MTU_VIOLATION_MASK 0x1 +#define ETH_TX_ERR_VALS_MTU_VIOLATION_SHIFT 5 +#define ETH_TX_ERR_VALS_ILLEGAL_CONTROL_FRAME_MASK 0x1 +#define ETH_TX_ERR_VALS_ILLEGAL_CONTROL_FRAME_SHIFT 6 +#define ETH_TX_ERR_VALS_RESERVED_MASK 0x1FF +#define ETH_TX_ERR_VALS_RESERVED_SHIFT 7 +}; + struct eth_vport_rss_config { __le16 capabilities; #define ETH_VPORT_RSS_CONFIG_IPV4_CAPABILITY_MASK 0x1 @@ -2669,12 +2879,8 @@ struct eth_vport_rss_config { #define ETH_VPORT_RSS_CONFIG_IPV6_UDP_CAPABILITY_SHIFT 5 #define ETH_VPORT_RSS_CONFIG_EN_5_TUPLE_CAPABILITY_MASK 0x1 #define ETH_VPORT_RSS_CONFIG_EN_5_TUPLE_CAPABILITY_SHIFT 6 -#define ETH_VPORT_RSS_CONFIG_CALC_4TUP_TCP_FRAG_MASK 0x1 -#define ETH_VPORT_RSS_CONFIG_CALC_4TUP_TCP_FRAG_SHIFT 7 -#define ETH_VPORT_RSS_CONFIG_CALC_4TUP_UDP_FRAG_MASK 0x1 -#define ETH_VPORT_RSS_CONFIG_CALC_4TUP_UDP_FRAG_SHIFT 8 -#define ETH_VPORT_RSS_CONFIG_RESERVED0_MASK 0x7F -#define ETH_VPORT_RSS_CONFIG_RESERVED0_SHIFT 9 +#define ETH_VPORT_RSS_CONFIG_RESERVED0_MASK 0x1FF +#define ETH_VPORT_RSS_CONFIG_RESERVED0_SHIFT 7 u8 rss_id; u8 rss_mode; u8 update_rss_key; @@ -2749,10 +2955,14 @@ struct rx_queue_start_ramrod_data { u8 pxp_tph_valid_pkt; u8 pxp_st_hint; __le16 pxp_st_index; - u8 reserved[4]; - struct regpair cqe_pbl_addr; - struct regpair bd_base; - struct regpair sge_base; + u8 pmd_mode; + u8 notify_en; + u8 toggle_val; + u8 reserved[7]; + __le16 reserved1; + struct regpair cqe_pbl_addr; + struct regpair bd_base; + struct regpair reserved2; }; struct rx_queue_stop_ramrod_data { @@ -2764,23 +2974,24 @@ struct rx_queue_stop_ramrod_data { }; struct rx_queue_update_ramrod_data { - __le16 rx_queue_id; - u8 complete_cqe_flg; - u8 complete_event_flg; - u8 init_sge_ring_flg; - u8 vport_id; - u8 pxp_tph_valid_sge; - u8 pxp_st_hint; - __le16 pxp_st_index; - u8 reserved[6]; - struct regpair sge_base; + __le16 rx_queue_id; + u8 complete_cqe_flg; + u8 complete_event_flg; + u8 vport_id; + u8 reserved[4]; + u8 reserved1; + u8 reserved2; + u8 reserved3; + __le16 reserved4; + __le16 reserved5; + struct regpair reserved6; }; struct tx_queue_start_ramrod_data { __le16 sb_id; u8 sb_index; u8 vport_id; - u8 tc; + u8 reserved0; u8 stats_counter_id; __le16 qm_pq_id; u8 flags; @@ -2790,18 +3001,25 @@ struct tx_queue_start_ramrod_data { #define TX_QUEUE_START_RAMROD_DATA_TEST_MODE_PKT_DUP_SHIFT 1 #define TX_QUEUE_START_RAMROD_DATA_TEST_MODE_TX_DEST_MASK 0x1 #define TX_QUEUE_START_RAMROD_DATA_TEST_MODE_TX_DEST_SHIFT 2 -#define TX_QUEUE_START_RAMROD_DATA_RESERVED0_MASK 0x1F -#define TX_QUEUE_START_RAMROD_DATA_RESERVED0_SHIFT 3 - u8 pin_context; - u8 pxp_tph_valid_bd; - u8 pxp_tph_valid_pkt; - __le16 pxp_st_index; - u8 pxp_st_hint; - u8 reserved1[3]; - __le16 queue_zone_id; - __le16 test_dup_count; - __le16 pbl_size; - struct regpair pbl_base_addr; +#define TX_QUEUE_START_RAMROD_DATA_PMD_MODE_MASK 0x1 +#define TX_QUEUE_START_RAMROD_DATA_PMD_MODE_SHIFT 3 +#define TX_QUEUE_START_RAMROD_DATA_NOTIFY_EN_MASK 0x1 +#define TX_QUEUE_START_RAMROD_DATA_NOTIFY_EN_SHIFT 4 +#define TX_QUEUE_START_RAMROD_DATA_PIN_CONTEXT_MASK 0x1 +#define TX_QUEUE_START_RAMROD_DATA_PIN_CONTEXT_SHIFT 5 +#define TX_QUEUE_START_RAMROD_DATA_RESERVED1_MASK 0x3 +#define TX_QUEUE_START_RAMROD_DATA_RESERVED1_SHIFT 6 + u8 pxp_st_hint; + u8 pxp_tph_valid_bd; + u8 pxp_tph_valid_pkt; + __le16 pxp_st_index; + __le16 comp_agg_size; + __le16 queue_zone_id; + __le16 test_dup_count; + __le16 pbl_size; + __le16 tx_queue_id; + struct regpair pbl_base_addr; + struct regpair bd_cons_address; }; struct tx_queue_stop_ramrod_data { @@ -2822,16 +3040,16 @@ struct vport_start_ramrod_data { struct eth_vport_rx_mode rx_mode; struct eth_vport_tx_mode tx_mode; struct eth_vport_tpa_param tpa_param; - __le16 sge_buff_size; - u8 max_sges_num; - u8 tx_switching_en; - u8 anti_spoofing_en; - u8 default_vlan_en; - u8 handle_ptp_pkts; - u8 silent_vlan_removal_en; - __le16 default_vlan; - u8 untagged; - u8 reserved[7]; + __le16 default_vlan; + u8 tx_switching_en; + u8 anti_spoofing_en; + u8 default_vlan_en; + u8 handle_ptp_pkts; + u8 silent_vlan_removal_en; + u8 untagged; + struct eth_tx_err_vals tx_err_behav; + u8 zero_placement_offset; + u8 reserved[7]; }; struct vport_stop_ramrod_data { @@ -2840,36 +3058,35 @@ struct vport_stop_ramrod_data { }; struct vport_update_ramrod_data_cmn { - u8 vport_id; - u8 update_rx_active_flg; - u8 rx_active_flg; - u8 update_tx_active_flg; - u8 tx_active_flg; - u8 update_rx_mode_flg; - u8 update_tx_mode_flg; - u8 update_approx_mcast_flg; - u8 update_rss_flg; - u8 update_inner_vlan_removal_en_flg; - u8 inner_vlan_removal_en; - u8 update_tpa_param_flg; - u8 update_tpa_en_flg; - u8 update_sge_param_flg; - __le16 sge_buff_size; - u8 max_sges_num; - u8 update_tx_switching_en_flg; - u8 tx_switching_en; - u8 update_anti_spoofing_en_flg; - u8 anti_spoofing_en; - u8 update_handle_ptp_pkts; - u8 handle_ptp_pkts; - u8 update_default_vlan_en_flg; - u8 default_vlan_en; - u8 update_default_vlan_flg; - __le16 default_vlan; - u8 update_accept_any_vlan_flg; - u8 accept_any_vlan; - u8 silent_vlan_removal_en; - u8 reserved; + u8 vport_id; + u8 update_rx_active_flg; + u8 rx_active_flg; + u8 update_tx_active_flg; + u8 tx_active_flg; + u8 update_rx_mode_flg; + u8 update_tx_mode_flg; + u8 update_approx_mcast_flg; + u8 update_rss_flg; + u8 update_inner_vlan_removal_en_flg; + u8 inner_vlan_removal_en; + u8 update_tpa_param_flg; + u8 update_tpa_en_flg; + u8 update_tx_switching_en_flg; + u8 tx_switching_en; + u8 update_anti_spoofing_en_flg; + u8 anti_spoofing_en; + u8 update_handle_ptp_pkts; + u8 handle_ptp_pkts; + u8 update_default_vlan_en_flg; + u8 default_vlan_en; + u8 update_default_vlan_flg; + __le16 default_vlan; + u8 update_accept_any_vlan_flg; + u8 accept_any_vlan; + u8 silent_vlan_removal_en; + u8 update_mtu_flg; + __le16 mtu; + u8 reserved[2]; }; struct vport_update_ramrod_mcast { @@ -2885,436 +3102,6 @@ struct vport_update_ramrod_data { struct eth_vport_rss_config rss_config; }; -struct mstorm_eth_conn_ag_ctx { - u8 byte0 /* cdu_validation */; - u8 byte1 /* state */; - u8 flags0; -#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 /* exist_in_qm0 */ -#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define MSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ -#define MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 -#define MSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 /* cf0 */ -#define MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 2 -#define MSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 /* cf1 */ -#define MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 4 -#define MSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 /* cf2 */ -#define MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 - u8 flags1; -#define MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ -#define MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 0 -#define MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ -#define MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 1 -#define MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ -#define MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 -#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ -#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ -#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ -#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ -#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ -#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 - __le16 word0 /* word0 */; - __le16 word1 /* word1 */; - __le32 reg0 /* reg0 */; - __le32 reg1 /* reg1 */; -}; - -struct tstorm_eth_conn_ag_ctx { - u8 byte0 /* cdu_validation */; - u8 byte1 /* state */; - u8 flags0; -#define TSTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 /* exist_in_qm0 */ -#define TSTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 -#define TSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 /* exist_in_qm1 */ -#define TSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 -#define TSTORM_ETH_CONN_AG_CTX_BIT2_MASK 0x1 /* bit2 */ -#define TSTORM_ETH_CONN_AG_CTX_BIT2_SHIFT 2 -#define TSTORM_ETH_CONN_AG_CTX_BIT3_MASK 0x1 /* bit3 */ -#define TSTORM_ETH_CONN_AG_CTX_BIT3_SHIFT 3 -#define TSTORM_ETH_CONN_AG_CTX_BIT4_MASK 0x1 /* bit4 */ -#define TSTORM_ETH_CONN_AG_CTX_BIT4_SHIFT 4 -#define TSTORM_ETH_CONN_AG_CTX_BIT5_MASK 0x1 /* bit5 */ -#define TSTORM_ETH_CONN_AG_CTX_BIT5_SHIFT 5 -#define TSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 /* timer0cf */ -#define TSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 6 - u8 flags1; -#define TSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 /* timer1cf */ -#define TSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 0 -#define TSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ -#define TSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 2 -#define TSTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 /* timer_stop_all */ -#define TSTORM_ETH_CONN_AG_CTX_CF3_SHIFT 4 -#define TSTORM_ETH_CONN_AG_CTX_CF4_MASK 0x3 /* cf4 */ -#define TSTORM_ETH_CONN_AG_CTX_CF4_SHIFT 6 - u8 flags2; -#define TSTORM_ETH_CONN_AG_CTX_CF5_MASK 0x3 /* cf5 */ -#define TSTORM_ETH_CONN_AG_CTX_CF5_SHIFT 0 -#define TSTORM_ETH_CONN_AG_CTX_CF6_MASK 0x3 /* cf6 */ -#define TSTORM_ETH_CONN_AG_CTX_CF6_SHIFT 2 -#define TSTORM_ETH_CONN_AG_CTX_CF7_MASK 0x3 /* cf7 */ -#define TSTORM_ETH_CONN_AG_CTX_CF7_SHIFT 4 -#define TSTORM_ETH_CONN_AG_CTX_CF8_MASK 0x3 /* cf8 */ -#define TSTORM_ETH_CONN_AG_CTX_CF8_SHIFT 6 - u8 flags3; -#define TSTORM_ETH_CONN_AG_CTX_CF9_MASK 0x3 /* cf9 */ -#define TSTORM_ETH_CONN_AG_CTX_CF9_SHIFT 0 -#define TSTORM_ETH_CONN_AG_CTX_CF10_MASK 0x3 /* cf10 */ -#define TSTORM_ETH_CONN_AG_CTX_CF10_SHIFT 2 -#define TSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ -#define TSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 4 -#define TSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ -#define TSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 5 -#define TSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ -#define TSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 6 -#define TSTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ -#define TSTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 7 - u8 flags4; -#define TSTORM_ETH_CONN_AG_CTX_CF4EN_MASK 0x1 /* cf4en */ -#define TSTORM_ETH_CONN_AG_CTX_CF4EN_SHIFT 0 -#define TSTORM_ETH_CONN_AG_CTX_CF5EN_MASK 0x1 /* cf5en */ -#define TSTORM_ETH_CONN_AG_CTX_CF5EN_SHIFT 1 -#define TSTORM_ETH_CONN_AG_CTX_CF6EN_MASK 0x1 /* cf6en */ -#define TSTORM_ETH_CONN_AG_CTX_CF6EN_SHIFT 2 -#define TSTORM_ETH_CONN_AG_CTX_CF7EN_MASK 0x1 /* cf7en */ -#define TSTORM_ETH_CONN_AG_CTX_CF7EN_SHIFT 3 -#define TSTORM_ETH_CONN_AG_CTX_CF8EN_MASK 0x1 /* cf8en */ -#define TSTORM_ETH_CONN_AG_CTX_CF8EN_SHIFT 4 -#define TSTORM_ETH_CONN_AG_CTX_CF9EN_MASK 0x1 /* cf9en */ -#define TSTORM_ETH_CONN_AG_CTX_CF9EN_SHIFT 5 -#define TSTORM_ETH_CONN_AG_CTX_CF10EN_MASK 0x1 /* cf10en */ -#define TSTORM_ETH_CONN_AG_CTX_CF10EN_SHIFT 6 -#define TSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 - u8 flags5; -#define TSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define TSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define TSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define TSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define TSTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_MASK 0x1 /* rule6en */ -#define TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_SHIFT 5 -#define TSTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define TSTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ -#define TSTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 - __le32 reg0 /* reg0 */; - __le32 reg1 /* reg1 */; - __le32 reg2 /* reg2 */; - __le32 reg3 /* reg3 */; - __le32 reg4 /* reg4 */; - __le32 reg5 /* reg5 */; - __le32 reg6 /* reg6 */; - __le32 reg7 /* reg7 */; - __le32 reg8 /* reg8 */; - u8 byte2 /* byte2 */; - u8 byte3 /* byte3 */; - __le16 rx_bd_cons /* word0 */; - u8 byte4 /* byte4 */; - u8 byte5 /* byte5 */; - __le16 rx_bd_prod /* word1 */; - __le16 word2 /* conn_dpi */; - __le16 word3 /* word3 */; - __le32 reg9 /* reg9 */; - __le32 reg10 /* reg10 */; -}; - -struct ustorm_eth_conn_ag_ctx { - u8 byte0 /* cdu_validation */; - u8 byte1 /* state */; - u8 flags0; -#define USTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 -#define USTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 -#define USTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 -#define USTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 -#define USTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 /* timer0cf */ -#define USTORM_ETH_CONN_AG_CTX_CF0_SHIFT 2 -#define USTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 /* timer1cf */ -#define USTORM_ETH_CONN_AG_CTX_CF1_SHIFT 4 -#define USTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 /* timer2cf */ -#define USTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 - u8 flags1; -#define USTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 -#define USTORM_ETH_CONN_AG_CTX_CF3_SHIFT 0 -#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_MASK 0x3 /* cf4 */ -#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_SHIFT 2 -#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_MASK 0x3 /* cf5 */ -#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_SHIFT 4 -#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_MASK 0x3 /* cf6 */ -#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_SHIFT 6 - u8 flags2; -#define USTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 /* cf0en */ -#define USTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 0 -#define USTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 /* cf1en */ -#define USTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 1 -#define USTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 /* cf2en */ -#define USTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 -#define USTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 /* cf3en */ -#define USTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 3 -#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_MASK 0x1 /* cf4en */ -#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_SHIFT 4 -#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_MASK 0x1 /* cf5en */ -#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_SHIFT 5 -#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_MASK 0x1 /* cf6en */ -#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_SHIFT 6 -#define USTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 /* rule0en */ -#define USTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 - u8 flags3; -#define USTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 /* rule1en */ -#define USTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define USTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 /* rule2en */ -#define USTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define USTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 /* rule3en */ -#define USTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define USTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 /* rule4en */ -#define USTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define USTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 /* rule5en */ -#define USTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define USTORM_ETH_CONN_AG_CTX_RULE6EN_MASK 0x1 /* rule6en */ -#define USTORM_ETH_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define USTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 /* rule7en */ -#define USTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define USTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 /* rule8en */ -#define USTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 - u8 byte2 /* byte2 */; - u8 byte3 /* byte3 */; - __le16 word0 /* conn_dpi */; - __le16 tx_bd_cons /* word1 */; - __le32 reg0 /* reg0 */; - __le32 reg1 /* reg1 */; - __le32 reg2 /* reg2 */; - __le32 reg3 /* reg3 */; - __le16 tx_drv_bd_cons /* word2 */; - __le16 rx_drv_cqe_cons /* word3 */; -}; - -struct xstorm_eth_hw_conn_ag_ctx { - u8 reserved0 /* cdu_validation */; - u8 eth_state /* state */; - u8 flags0; -#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT 7 - u8 flags1; -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 - u8 flags2; -#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT 6 - u8 flags3; -#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT 6 - u8 flags4; -#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT 6 - u8 flags5; -#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT 6 - u8 flags6; -#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 - u8 flags7; -#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT 7 - u8 flags8; -#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT 7 - u8 flags9; -#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7 - u8 flags10; -#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT 7 - u8 flags11; -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT 7 - u8 flags12; -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT 7 - u8 flags13; -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 - u8 flags14; -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0 -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1 -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2 -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3 -#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4 -#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 -#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 -#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK 0x3 -#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT 6 - u8 edpm_event_id /* byte2 */; - __le16 physical_q0 /* physical_q0 */; - __le16 word1 /* physical_q1 */; - __le16 edpm_num_bds /* physical_q2 */; - __le16 tx_bd_cons /* word3 */; - __le16 tx_bd_prod /* word4 */; - __le16 go_to_bd_cons /* word5 */; - __le16 conn_dpi /* conn_dpi */; -}; - #define VF_MAX_STATIC 192 /* In case of K2 */ #define MCP_GLOB_PATH_MAX 2 @@ -3818,6 +3605,10 @@ struct public_port { struct dcbx_local_params local_admin_dcbx_mib; struct dcbx_mib remote_dcbx_mib; struct dcbx_mib operational_dcbx_mib; + + u32 fc_npiv_nvram_tbl_addr; + u32 fc_npiv_nvram_tbl_size; + u32 transceiver_data; }; /**************************************/ @@ -3830,7 +3621,11 @@ struct public_func { u32 iscsi_boot_signature; u32 iscsi_boot_block_offset; - u32 reserved[8]; + u32 mtu_size; + u32 c2s_pcp_map_lower; + u32 c2s_pcp_map_upper; + u32 c2s_pcp_map_default; + u32 reserved[4]; u32 config; @@ -3894,10 +3689,10 @@ struct public_func { #define DRV_ID_MCP_HSI_VER_SHIFT 16 #define DRV_ID_MCP_HSI_VER_CURRENT BIT(DRV_ID_MCP_HSI_VER_SHIFT) -#define DRV_ID_DRV_TYPE_MASK 0xff000000 +#define DRV_ID_DRV_TYPE_MASK 0x7f000000 #define DRV_ID_DRV_TYPE_SHIFT 24 #define DRV_ID_DRV_TYPE_UNKNOWN (0 << DRV_ID_DRV_TYPE_SHIFT) -#define DRV_ID_DRV_TYPE_LINUX BIT(DRV_ID_DRV_TYPE_SHIFT) +#define DRV_ID_DRV_TYPE_LINUX (1 << DRV_ID_DRV_TYPE_SHIFT) #define DRV_ID_DRV_TYPE_WINDOWS (2 << DRV_ID_DRV_TYPE_SHIFT) #define DRV_ID_DRV_TYPE_DIAG (3 << DRV_ID_DRV_TYPE_SHIFT) #define DRV_ID_DRV_TYPE_PREBOOT (4 << DRV_ID_DRV_TYPE_SHIFT) @@ -3905,6 +3700,10 @@ struct public_func { #define DRV_ID_DRV_TYPE_VMWARE (6 << DRV_ID_DRV_TYPE_SHIFT) #define DRV_ID_DRV_TYPE_FREEBSD (7 << DRV_ID_DRV_TYPE_SHIFT) #define DRV_ID_DRV_TYPE_AIX (8 << DRV_ID_DRV_TYPE_SHIFT) + +#define DRV_ID_DRV_INIT_HW_MASK 0x80000000 +#define DRV_ID_DRV_INIT_HW_SHIFT 31 +#define DRV_ID_DRV_INIT_HW_FLAG BIT(DRV_ID_DRV_INIT_HW_SHIFT) }; /**************************************/ @@ -3964,6 +3763,7 @@ struct public_drv_mb { #define DRV_MSG_CODE_MASK 0xffff0000 #define DRV_MSG_CODE_LOAD_REQ 0x10000000 #define DRV_MSG_CODE_LOAD_DONE 0x11000000 +#define DRV_MSG_CODE_INIT_HW 0x12000000 #define DRV_MSG_CODE_UNLOAD_REQ 0x20000000 #define DRV_MSG_CODE_UNLOAD_DONE 0x21000000 #define DRV_MSG_CODE_INIT_PHY 0x22000000 @@ -4100,6 +3900,7 @@ struct public_drv_mb { #define FW_MSG_CODE_SET_SECURE_MODE_ERROR 0x00130000 #define FW_MSG_CODE_SET_SECURE_MODE_OK 0x00140000 #define FW_MSG_MODE_PHY_PRIVILEGE_ERROR 0x00150000 +#define FW_MSG_CODE_OK 0x00160000 #define FW_MSG_SEQ_NUMBER_MASK 0x0000ffff @@ -4212,7 +4013,7 @@ struct nvm_cfg1_glob { #define NVM_CFG1_GLOB_MF_MODE_MASK 0x00000FF0 #define NVM_CFG1_GLOB_MF_MODE_OFFSET 4 #define NVM_CFG1_GLOB_MF_MODE_MF_ALLOWED 0x0 -#define NVM_CFG1_GLOB_MF_MODE_FORCED_SF 0x1 +#define NVM_CFG1_GLOB_MF_MODE_DEFAULT 0x1 #define NVM_CFG1_GLOB_MF_MODE_SPIO4 0x2 #define NVM_CFG1_GLOB_MF_MODE_NPAR1_0 0x3 #define NVM_CFG1_GLOB_MF_MODE_NPAR1_5 0x4 @@ -4643,8 +4444,12 @@ struct nvm_cfg1_glob { #define NVM_CFG1_GLOB_I2C_MUX_SEL_GPIO__GPIO29 0x1E #define NVM_CFG1_GLOB_I2C_MUX_SEL_GPIO__GPIO30 0x1F #define NVM_CFG1_GLOB_I2C_MUX_SEL_GPIO__GPIO31 0x20 - - u32 reserved[46]; /* 0x88 */ + u32 device_capabilities; /* 0x88 */ +#define NVM_CFG1_GLOB_DEVICE_CAPABILITIES_ETHERNET 0x1 + u32 power_dissipated; /* 0x8C */ + u32 power_consumed; /* 0x90 */ + u32 efi_version; /* 0x94 */ + u32 reserved[42]; /* 0x98 */ }; struct nvm_cfg1_path { @@ -4652,26 +4457,8 @@ struct nvm_cfg1_path { }; struct nvm_cfg1_port { - u32 power_dissipated; /* 0x0 */ -#define NVM_CFG1_PORT_POWER_DIS_D0_MASK 0x000000FF -#define NVM_CFG1_PORT_POWER_DIS_D0_OFFSET 0 -#define NVM_CFG1_PORT_POWER_DIS_D1_MASK 0x0000FF00 -#define NVM_CFG1_PORT_POWER_DIS_D1_OFFSET 8 -#define NVM_CFG1_PORT_POWER_DIS_D2_MASK 0x00FF0000 -#define NVM_CFG1_PORT_POWER_DIS_D2_OFFSET 16 -#define NVM_CFG1_PORT_POWER_DIS_D3_MASK 0xFF000000 -#define NVM_CFG1_PORT_POWER_DIS_D3_OFFSET 24 - - u32 power_consumed; /* 0x4 */ -#define NVM_CFG1_PORT_POWER_CONS_D0_MASK 0x000000FF -#define NVM_CFG1_PORT_POWER_CONS_D0_OFFSET 0 -#define NVM_CFG1_PORT_POWER_CONS_D1_MASK 0x0000FF00 -#define NVM_CFG1_PORT_POWER_CONS_D1_OFFSET 8 -#define NVM_CFG1_PORT_POWER_CONS_D2_MASK 0x00FF0000 -#define NVM_CFG1_PORT_POWER_CONS_D2_OFFSET 16 -#define NVM_CFG1_PORT_POWER_CONS_D3_MASK 0xFF000000 -#define NVM_CFG1_PORT_POWER_CONS_D3_OFFSET 24 - + u32 reserved__m_relocated_to_option_123; /* 0x0 */ + u32 reserved__m_relocated_to_option_124; /* 0x4 */ u32 generic_cont0; /* 0x8 */ #define NVM_CFG1_PORT_LED_MODE_MASK 0x000000FF #define NVM_CFG1_PORT_LED_MODE_OFFSET 0 @@ -4699,7 +4486,9 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_DCBX_MODE_IEEE 0x1 #define NVM_CFG1_PORT_DCBX_MODE_CEE 0x2 #define NVM_CFG1_PORT_DCBX_MODE_DYNAMIC 0x3 - +#define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_MASK 0x00F00000 +#define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_OFFSET 20 +#define NVM_CFG1_PORT_DEFAULT_ENABLED_PROTOCOLS_ETHERNET 0x1 u32 pcie_cfg; /* 0xC */ #define NVM_CFG1_PORT_RESERVED15_MASK 0x00000007 #define NVM_CFG1_PORT_RESERVED15_OFFSET 0 @@ -4784,10 +4573,11 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_SERDES_NET_INTERFACE_SFI 0x9 #define NVM_CFG1_PORT_SERDES_NET_INTERFACE_1000X 0xB #define NVM_CFG1_PORT_SERDES_NET_INTERFACE_SGMII 0xC -#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_XLAUI 0xD -#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_CAUI 0xE -#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_XLPPI 0xF -#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_CPPI 0x10 +#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_XLAUI 0x11 +#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_XLPPI 0x12 +#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_CAUI 0x21 +#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_CPPI 0x22 +#define NVM_CFG1_PORT_SERDES_NET_INTERFACE_25GAUI 0x31 #define NVM_CFG1_PORT_AN_MODE_MASK 0xFF000000 #define NVM_CFG1_PORT_AN_MODE_OFFSET 24 #define NVM_CFG1_PORT_AN_MODE_NONE 0x0 @@ -4801,9 +4591,6 @@ struct nvm_cfg1_port { u32 mgmt_traffic; /* 0x20 */ #define NVM_CFG1_PORT_RESERVED61_MASK 0x0000000F #define NVM_CFG1_PORT_RESERVED61_OFFSET 0 -#define NVM_CFG1_PORT_RESERVED61_DISABLED 0x0 -#define NVM_CFG1_PORT_RESERVED61_NCSI_OVER_RMII 0x1 -#define NVM_CFG1_PORT_RESERVED61_NCSI_OVER_SMBUS 0x2 u32 ext_phy; /* 0x24 */ #define NVM_CFG1_PORT_EXTERNAL_PHY_TYPE_MASK 0x000000FF @@ -4814,16 +4601,12 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_EXTERNAL_PHY_ADDRESS_OFFSET 8 u32 mba_cfg1; /* 0x28 */ -#define NVM_CFG1_PORT_MBA_MASK 0x00000001 -#define NVM_CFG1_PORT_MBA_OFFSET 0 -#define NVM_CFG1_PORT_MBA_DISABLED 0x0 -#define NVM_CFG1_PORT_MBA_ENABLED 0x1 -#define NVM_CFG1_PORT_MBA_BOOT_TYPE_MASK 0x00000006 -#define NVM_CFG1_PORT_MBA_BOOT_TYPE_OFFSET 1 -#define NVM_CFG1_PORT_MBA_BOOT_TYPE_AUTO 0x0 -#define NVM_CFG1_PORT_MBA_BOOT_TYPE_BBS 0x1 -#define NVM_CFG1_PORT_MBA_BOOT_TYPE_INT18H 0x2 -#define NVM_CFG1_PORT_MBA_BOOT_TYPE_INT19H 0x3 +#define NVM_CFG1_PORT_PREBOOT_OPROM_MASK 0x00000001 +#define NVM_CFG1_PORT_PREBOOT_OPROM_OFFSET 0 +#define NVM_CFG1_PORT_PREBOOT_OPROM_DISABLED 0x0 +#define NVM_CFG1_PORT_PREBOOT_OPROM_ENABLED 0x1 +#define NVM_CFG1_PORT_RESERVED__M_MBA_BOOT_TYPE_MASK 0x00000006 +#define NVM_CFG1_PORT_RESERVED__M_MBA_BOOT_TYPE_OFFSET 1 #define NVM_CFG1_PORT_MBA_DELAY_TIME_MASK 0x00000078 #define NVM_CFG1_PORT_MBA_DELAY_TIME_OFFSET 3 #define NVM_CFG1_PORT_MBA_SETUP_HOT_KEY_MASK 0x00000080 @@ -4836,61 +4619,30 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_MBA_HIDE_SETUP_PROMPT_ENABLED 0x1 #define NVM_CFG1_PORT_RESERVED5_MASK 0x0001FE00 #define NVM_CFG1_PORT_RESERVED5_OFFSET 9 -#define NVM_CFG1_PORT_RESERVED5_DISABLED 0x0 -#define NVM_CFG1_PORT_RESERVED5_2K 0x1 -#define NVM_CFG1_PORT_RESERVED5_4K 0x2 -#define NVM_CFG1_PORT_RESERVED5_8K 0x3 -#define NVM_CFG1_PORT_RESERVED5_16K 0x4 -#define NVM_CFG1_PORT_RESERVED5_32K 0x5 -#define NVM_CFG1_PORT_RESERVED5_64K 0x6 -#define NVM_CFG1_PORT_RESERVED5_128K 0x7 -#define NVM_CFG1_PORT_RESERVED5_256K 0x8 -#define NVM_CFG1_PORT_RESERVED5_512K 0x9 -#define NVM_CFG1_PORT_RESERVED5_1M 0xA -#define NVM_CFG1_PORT_RESERVED5_2M 0xB -#define NVM_CFG1_PORT_RESERVED5_4M 0xC -#define NVM_CFG1_PORT_RESERVED5_8M 0xD -#define NVM_CFG1_PORT_RESERVED5_16M 0xE -#define NVM_CFG1_PORT_RESERVED5_32M 0xF -#define NVM_CFG1_PORT_MBA_LINK_SPEED_MASK 0x001E0000 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_OFFSET 17 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_AUTONEG 0x0 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_1G 0x1 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_10G 0x2 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_25G 0x4 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_40G 0x5 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_50G 0x6 -#define NVM_CFG1_PORT_MBA_LINK_SPEED_100G 0x7 -#define NVM_CFG1_PORT_MBA_BOOT_RETRY_COUNT_MASK 0x00E00000 -#define NVM_CFG1_PORT_MBA_BOOT_RETRY_COUNT_OFFSET 21 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_MASK 0x001E0000 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_OFFSET 17 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_AUTONEG 0x0 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_1G 0x1 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_10G 0x2 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_25G 0x4 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_40G 0x5 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_50G 0x6 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_100G 0x7 +#define NVM_CFG1_PORT_PREBOOT_LINK_SPEED_SMARTLINQ 0x8 +#define NVM_CFG1_PORT_RESERVED__M_MBA_BOOT_RETRY_COUNT_MASK 0x00E00000 +#define NVM_CFG1_PORT_RESERVED__M_MBA_BOOT_RETRY_COUNT_OFFSET 21 u32 mba_cfg2; /* 0x2C */ -#define NVM_CFG1_PORT_MBA_VLAN_VALUE_MASK 0x0000FFFF -#define NVM_CFG1_PORT_MBA_VLAN_VALUE_OFFSET 0 -#define NVM_CFG1_PORT_MBA_VLAN_MASK 0x00010000 -#define NVM_CFG1_PORT_MBA_VLAN_OFFSET 16 +#define NVM_CFG1_PORT_RESERVED65_MASK 0x0000FFFF +#define NVM_CFG1_PORT_RESERVED65_OFFSET 0 +#define NVM_CFG1_PORT_RESERVED66_MASK 0x00010000 +#define NVM_CFG1_PORT_RESERVED66_OFFSET 16 u32 vf_cfg; /* 0x30 */ #define NVM_CFG1_PORT_RESERVED8_MASK 0x0000FFFF #define NVM_CFG1_PORT_RESERVED8_OFFSET 0 #define NVM_CFG1_PORT_RESERVED6_MASK 0x000F0000 #define NVM_CFG1_PORT_RESERVED6_OFFSET 16 -#define NVM_CFG1_PORT_RESERVED6_DISABLED 0x0 -#define NVM_CFG1_PORT_RESERVED6_4K 0x1 -#define NVM_CFG1_PORT_RESERVED6_8K 0x2 -#define NVM_CFG1_PORT_RESERVED6_16K 0x3 -#define NVM_CFG1_PORT_RESERVED6_32K 0x4 -#define NVM_CFG1_PORT_RESERVED6_64K 0x5 -#define NVM_CFG1_PORT_RESERVED6_128K 0x6 -#define NVM_CFG1_PORT_RESERVED6_256K 0x7 -#define NVM_CFG1_PORT_RESERVED6_512K 0x8 -#define NVM_CFG1_PORT_RESERVED6_1M 0x9 -#define NVM_CFG1_PORT_RESERVED6_2M 0xA -#define NVM_CFG1_PORT_RESERVED6_4M 0xB -#define NVM_CFG1_PORT_RESERVED6_8M 0xC -#define NVM_CFG1_PORT_RESERVED6_16M 0xD -#define NVM_CFG1_PORT_RESERVED6_32M 0xE -#define NVM_CFG1_PORT_RESERVED6_64M 0xF struct nvm_cfg_mac_address lldp_mac_address; /* 0x34 */ @@ -4973,18 +4725,16 @@ struct nvm_cfg1_func { u32 device_id; /* 0x10 */ #define NVM_CFG1_FUNC_MF_VENDOR_DEVICE_ID_MASK 0x0000FFFF #define NVM_CFG1_FUNC_MF_VENDOR_DEVICE_ID_OFFSET 0 -#define NVM_CFG1_FUNC_VENDOR_DEVICE_ID_MASK 0xFFFF0000 -#define NVM_CFG1_FUNC_VENDOR_DEVICE_ID_OFFSET 16 +#define NVM_CFG1_FUNC_RESERVED77_MASK 0xFFFF0000 +#define NVM_CFG1_FUNC_RESERVED77_OFFSET 16 u32 cmn_cfg; /* 0x14 */ -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_MASK 0x00000007 -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_OFFSET 0 -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_PXE 0x0 -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_RPL 0x1 -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_BOOTP 0x2 -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_ISCSI_BOOT 0x3 -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_FCOE_BOOT 0x4 -#define NVM_CFG1_FUNC_MBA_BOOT_PROTOCOL_NONE 0x7 +#define NVM_CFG1_FUNC_PREBOOT_BOOT_PROTOCOL_MASK 0x00000007 +#define NVM_CFG1_FUNC_PREBOOT_BOOT_PROTOCOL_OFFSET 0 +#define NVM_CFG1_FUNC_PREBOOT_BOOT_PROTOCOL_PXE 0x0 +#define NVM_CFG1_FUNC_PREBOOT_BOOT_PROTOCOL_ISCSI_BOOT 0x3 +#define NVM_CFG1_FUNC_PREBOOT_BOOT_PROTOCOL_FCOE_BOOT 0x4 +#define NVM_CFG1_FUNC_PREBOOT_BOOT_PROTOCOL_NONE 0x7 #define NVM_CFG1_FUNC_VF_PCI_DEVICE_ID_MASK 0x0007FFF8 #define NVM_CFG1_FUNC_VF_PCI_DEVICE_ID_OFFSET 3 #define NVM_CFG1_FUNC_PERSONALITY_MASK 0x00780000 @@ -5029,8 +4779,8 @@ struct nvm_cfg1_func { struct nvm_cfg_mac_address fcoe_node_wwn_mac_addr; /* 0x1C */ struct nvm_cfg_mac_address fcoe_port_wwn_mac_addr; /* 0x24 */ - - u32 reserved[9]; /* 0x2C */ + u32 preboot_generic_cfg; /* 0x2C */ + u32 reserved[8]; /* 0x30 */ }; struct nvm_cfg1 { diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index 0b21a553cc7d..f55ebdc3c832 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -513,17 +513,14 @@ static int qed_pf_rl_rt_init(struct qed_hwfn *p_hwfn, * Return -1 on error. */ static int qed_vp_wfq_rt_init(struct qed_hwfn *p_hwfn, - u8 start_vport, u8 num_vports, struct init_qm_vport_params *vport_params) { - u8 tc, i, vport_id; u32 inc_val; + u8 tc, i; /* go over all PF VPORTs */ - for (i = 0, vport_id = start_vport; i < num_vports; i++, vport_id++) { - u32 temp = QM_REG_WFQVPUPPERBOUND_RT_OFFSET; - u16 *pq_ids = &vport_params[i].first_tx_pq_id[0]; + for (i = 0; i < num_vports; i++) { if (!vport_params[i].vport_wfq) continue; @@ -539,20 +536,16 @@ static int qed_vp_wfq_rt_init(struct qed_hwfn *p_hwfn, * different TCs */ for (tc = 0; tc < NUM_OF_TCS; tc++) { - u16 vport_pq_id = pq_ids[tc]; + u16 vport_pq_id = vport_params[i].first_tx_pq_id[tc]; if (vport_pq_id != QM_INVALID_PQ_ID) { - STORE_RT_REG(p_hwfn, - QM_REG_WFQVPWEIGHT_RT_OFFSET + - vport_pq_id, inc_val); - STORE_RT_REG(p_hwfn, temp + vport_pq_id, - QM_WFQ_UPPER_BOUND | - QM_WFQ_CRD_REG_SIGN_BIT); STORE_RT_REG(p_hwfn, QM_REG_WFQVPCRD_RT_OFFSET + vport_pq_id, - QM_WFQ_INIT_CRD(inc_val) | QM_WFQ_CRD_REG_SIGN_BIT); + STORE_RT_REG(p_hwfn, + QM_REG_WFQVPWEIGHT_RT_OFFSET + + vport_pq_id, inc_val); } } } @@ -709,8 +702,7 @@ int qed_qm_pf_rt_init(struct qed_hwfn *p_hwfn, if (qed_pf_rl_rt_init(p_hwfn, p_params->pf_id, p_params->pf_rl)) return -1; - if (qed_vp_wfq_rt_init(p_hwfn, p_params->start_vport, - p_params->num_vports, vport_params)) + if (qed_vp_wfq_rt_init(p_hwfn, p_params->num_vports, vport_params)) return -1; if (qed_vport_rl_rt_init(p_hwfn, p_params->start_vport, diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c index 796f1390e598..3269b3610e03 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c @@ -55,63 +55,98 @@ void qed_init_clear_rt_data(struct qed_hwfn *p_hwfn) int i; for (i = 0; i < RUNTIME_ARRAY_SIZE; i++) - p_hwfn->rt_data[i].b_valid = false; + p_hwfn->rt_data.b_valid[i] = false; } void qed_init_store_rt_reg(struct qed_hwfn *p_hwfn, u32 rt_offset, u32 val) { - p_hwfn->rt_data[rt_offset].init_val = val; - p_hwfn->rt_data[rt_offset].b_valid = true; + p_hwfn->rt_data.init_val[rt_offset] = val; + p_hwfn->rt_data.b_valid[rt_offset] = true; } void qed_init_store_rt_agg(struct qed_hwfn *p_hwfn, - u32 rt_offset, - u32 *val, + u32 rt_offset, u32 *p_val, size_t size) { size_t i; for (i = 0; i < size / sizeof(u32); i++) { - p_hwfn->rt_data[rt_offset + i].init_val = val[i]; - p_hwfn->rt_data[rt_offset + i].b_valid = true; + p_hwfn->rt_data.init_val[rt_offset + i] = p_val[i]; + p_hwfn->rt_data.b_valid[rt_offset + i] = true; } } -static void qed_init_rt(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - u32 addr, - u32 rt_offset, - u32 size) +static int qed_init_rt(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 addr, + u16 rt_offset, + u16 size, + bool b_must_dmae) { - struct qed_rt_data *rt_data = p_hwfn->rt_data + rt_offset; - u32 i; + u32 *p_init_val = &p_hwfn->rt_data.init_val[rt_offset]; + bool *p_valid = &p_hwfn->rt_data.b_valid[rt_offset]; + u16 i, segment; + int rc = 0; + /* Since not all RT entries are initialized, go over the RT and + * for each segment of initialized values use DMA. + */ for (i = 0; i < size; i++) { - if (!rt_data[i].b_valid) + if (!p_valid[i]) continue; - qed_wr(p_hwfn, p_ptt, addr + (i << 2), rt_data[i].init_val); + + /* In case there isn't any wide-bus configuration here, + * simply write the data instead of using dmae. + */ + if (!b_must_dmae) { + qed_wr(p_hwfn, p_ptt, addr + (i << 2), + p_init_val[i]); + continue; + } + + /* Start of a new segment */ + for (segment = 1; i + segment < size; segment++) + if (!p_valid[i + segment]) + break; + + rc = qed_dmae_host2grc(p_hwfn, p_ptt, + (uintptr_t)(p_init_val + i), + addr + (i << 2), segment, 0); + if (rc != 0) + return rc; + + /* Jump over the entire segment, including invalid entry */ + i += segment; } + + return rc; } int qed_init_alloc(struct qed_hwfn *p_hwfn) { - struct qed_rt_data *rt_data; + struct qed_rt_data *rt_data = &p_hwfn->rt_data; - rt_data = kzalloc(sizeof(*rt_data) * RUNTIME_ARRAY_SIZE, GFP_ATOMIC); - if (!rt_data) + rt_data->b_valid = kzalloc(sizeof(bool) * RUNTIME_ARRAY_SIZE, + GFP_KERNEL); + if (!rt_data->b_valid) return -ENOMEM; - p_hwfn->rt_data = rt_data; + rt_data->init_val = kzalloc(sizeof(u32) * RUNTIME_ARRAY_SIZE, + GFP_KERNEL); + if (!rt_data->init_val) { + kfree(rt_data->b_valid); + return -ENOMEM; + } return 0; } void qed_init_free(struct qed_hwfn *p_hwfn) { - kfree(p_hwfn->rt_data); - p_hwfn->rt_data = NULL; + kfree(p_hwfn->rt_data.init_val); + kfree(p_hwfn->rt_data.b_valid); } static int qed_init_array_dmae(struct qed_hwfn *p_hwfn, @@ -289,7 +324,8 @@ static int qed_init_cmd_wr(struct qed_hwfn *p_hwfn, case INIT_SRC_RUNTIME: qed_init_rt(p_hwfn, p_ptt, addr, le16_to_cpu(arg->runtime.offset), - le16_to_cpu(arg->runtime.size)); + le16_to_cpu(arg->runtime.size), + b_must_dmae); break; } @@ -316,49 +352,50 @@ static void qed_init_cmd_rd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct init_read_op *cmd) { - u32 data = le32_to_cpu(cmd->op_data); - u32 addr = GET_FIELD(data, INIT_READ_OP_ADDRESS) << 2; + bool (*comp_check)(u32 val, u32 expected_val); + u32 delay = QED_INIT_POLL_PERIOD_US, val; + u32 data, addr, poll; + int i; + + data = le32_to_cpu(cmd->op_data); + addr = GET_FIELD(data, INIT_READ_OP_ADDRESS) << 2; + poll = GET_FIELD(data, INIT_READ_OP_POLL_TYPE); - bool (*comp_check)(u32 val, - u32 expected_val); - u32 delay = QED_INIT_POLL_PERIOD_US, val; val = qed_rd(p_hwfn, p_ptt, addr); - data = le32_to_cpu(cmd->op_data); - if (GET_FIELD(data, INIT_READ_OP_POLL)) { - int i; + if (poll == INIT_POLL_NONE) + return; - switch (GET_FIELD(data, INIT_READ_OP_POLL_COMP)) { - case INIT_COMPARISON_EQ: - comp_check = comp_eq; - break; - case INIT_COMPARISON_OR: - comp_check = comp_or; - break; - case INIT_COMPARISON_AND: - comp_check = comp_and; - break; - default: - comp_check = NULL; - DP_ERR(p_hwfn, "Invalid poll comparison type %08x\n", - data); - return; - } + switch (poll) { + case INIT_POLL_EQ: + comp_check = comp_eq; + break; + case INIT_POLL_OR: + comp_check = comp_or; + break; + case INIT_POLL_AND: + comp_check = comp_and; + break; + default: + DP_ERR(p_hwfn, "Invalid poll comparison type %08x\n", + cmd->op_data); + return; + } - for (i = 0; - i < QED_INIT_MAX_POLL_COUNT && - !comp_check(val, le32_to_cpu(cmd->expected_val)); - i++) { - udelay(delay); - val = qed_rd(p_hwfn, p_ptt, addr); - } + data = le32_to_cpu(cmd->expected_val); + for (i = 0; + i < QED_INIT_MAX_POLL_COUNT && !comp_check(val, data); + i++) { + udelay(delay); + val = qed_rd(p_hwfn, p_ptt, addr); + } - if (i == QED_INIT_MAX_POLL_COUNT) - DP_ERR(p_hwfn, - "Timeout when polling reg: 0x%08x [ Waiting-for: %08x Got: %08x (comparsion %08x)]\n", - addr, le32_to_cpu(cmd->expected_val), - val, data); + if (i == QED_INIT_MAX_POLL_COUNT) { + DP_ERR(p_hwfn, + "Timeout when polling reg: 0x%08x [ Waiting-for: %08x Got: %08x (comparsion %08x)]\n", + addr, le32_to_cpu(cmd->expected_val), + val, le32_to_cpu(cmd->op_data)); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index f72036a2ef5b..978d07a61bbf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -714,7 +714,6 @@ qed_sp_eth_txq_start_ramrod(struct qed_hwfn *p_hwfn, p_ramrod->sb_id = cpu_to_le16(p_params->sb); p_ramrod->sb_index = p_params->sb_idx; p_ramrod->stats_counter_id = stats_id; - p_ramrod->tc = p_pq_params->eth.tc; p_ramrod->pbl_size = cpu_to_le16(pbl_size); p_ramrod->pbl_base_addr.hi = DMA_HI_LE(pbl_addr); @@ -821,9 +820,8 @@ qed_filter_action(enum qed_filter_opcode opcode) case QED_FILTER_REMOVE: action = ETH_FILTER_ACTION_REMOVE; break; - case QED_FILTER_REPLACE: case QED_FILTER_FLUSH: - action = ETH_FILTER_ACTION_REPLACE; + action = ETH_FILTER_ACTION_REMOVE_ALL; break; default: action = MAX_ETH_FILTER_ACTION; @@ -892,8 +890,7 @@ qed_filter_ucast_common(struct qed_hwfn *p_hwfn, p_ramrod->filter_cmd_hdr.tx = p_filter_cmd->is_tx_filter ? 1 : 0; switch (p_filter_cmd->opcode) { - case QED_FILTER_FLUSH: - p_ramrod->filter_cmd_hdr.cmd_cnt = 0; break; + case QED_FILTER_REPLACE: case QED_FILTER_MOVE: p_ramrod->filter_cmd_hdr.cmd_cnt = 2; break; default: @@ -962,6 +959,12 @@ qed_filter_ucast_common(struct qed_hwfn *p_hwfn, p_second_filter->action = ETH_FILTER_ACTION_ADD; p_second_filter->vport_id = vport_to_add_to; + } else if (p_filter_cmd->opcode == QED_FILTER_REPLACE) { + p_first_filter->vport_id = vport_to_add_to; + memcpy(p_second_filter, p_first_filter, + sizeof(*p_second_filter)); + p_first_filter->action = ETH_FILTER_ACTION_REMOVE_ALL; + p_second_filter->action = ETH_FILTER_ACTION_ADD; } else { action = qed_filter_action(p_filter_cmd->opcode); diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 9d76ce249277..593f8871adb6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -190,7 +190,7 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->pci_mem_start = cdev->pci_params.mem_start; dev_info->pci_mem_end = cdev->pci_params.mem_end; dev_info->pci_irq = cdev->pci_params.irq; - dev_info->is_mf = IS_MF(&cdev->hwfns[0]); + dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]); ether_addr_copy(dev_info->hw_mac, cdev->hwfns[0].hw_info.hw_mac_addr); dev_info->fw_major = FW_MAJOR_VERSION; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index ba1b1f1ef789..1457e30faccf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -720,26 +720,25 @@ int qed_mcp_fill_shmem_func_info(struct qed_hwfn *p_hwfn, return -EINVAL; } - if (p_hwfn->cdev->mf_mode != SF) { - info->bandwidth_min = (shmem_info.config & - FUNC_MF_CFG_MIN_BW_MASK) >> - FUNC_MF_CFG_MIN_BW_SHIFT; - if (info->bandwidth_min < 1 || info->bandwidth_min > 100) { - DP_INFO(p_hwfn, - "bandwidth minimum out of bounds [%02x]. Set to 1\n", - info->bandwidth_min); - info->bandwidth_min = 1; - } - info->bandwidth_max = (shmem_info.config & - FUNC_MF_CFG_MAX_BW_MASK) >> - FUNC_MF_CFG_MAX_BW_SHIFT; - if (info->bandwidth_max < 1 || info->bandwidth_max > 100) { - DP_INFO(p_hwfn, - "bandwidth maximum out of bounds [%02x]. Set to 100\n", - info->bandwidth_max); - info->bandwidth_max = 100; - } + info->bandwidth_min = (shmem_info.config & + FUNC_MF_CFG_MIN_BW_MASK) >> + FUNC_MF_CFG_MIN_BW_SHIFT; + if (info->bandwidth_min < 1 || info->bandwidth_min > 100) { + DP_INFO(p_hwfn, + "bandwidth minimum out of bounds [%02x]. Set to 1\n", + info->bandwidth_min); + info->bandwidth_min = 1; + } + + info->bandwidth_max = (shmem_info.config & + FUNC_MF_CFG_MAX_BW_MASK) >> + FUNC_MF_CFG_MAX_BW_SHIFT; + if (info->bandwidth_max < 1 || info->bandwidth_max > 100) { + DP_INFO(p_hwfn, + "bandwidth maximum out of bounds [%02x]. Set to 100\n", + info->bandwidth_max); + info->bandwidth_max = 100; } if (shmem_info.mac_upper || shmem_info.mac_lower) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 287fadfab52d..8a83609c443c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -343,7 +343,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, */ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, - enum mf_mode mode); + enum qed_mf_mode mode); /** * @brief qed_sp_pf_stop - PF Function Stop Ramrod diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 6f7879136633..33090f63548c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -90,7 +90,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, } int qed_sp_pf_start(struct qed_hwfn *p_hwfn, - enum mf_mode mode) + enum qed_mf_mode mode) { struct qed_sp_init_request_params params; struct pf_start_ramrod_data *p_ramrod = NULL; @@ -125,6 +125,18 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->dont_log_ramrods = 0; p_ramrod->log_type_mask = cpu_to_le16(0xf); p_ramrod->mf_mode = mode; + switch (mode) { + case QED_MF_DEFAULT: + case QED_MF_NPAR: + p_ramrod->mf_mode = MF_NPAR; + break; + case QED_MF_OVLAN: + p_ramrod->mf_mode = MF_OVLAN; + break; + default: + DP_NOTICE(p_hwfn, "Unsupported MF mode, init as DEFAULT\n"); + p_ramrod->mf_mode = MF_NPAR; + } p_ramrod->outer_tag = p_hwfn->hw_info.ovlan; /* Place EQ address in RAMROD */ @@ -142,9 +154,8 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_hwfn->hw_info.personality = PERSONALITY_ETH; DP_VERBOSE(p_hwfn, QED_MSG_SPQ, - "Setting event_ring_sb [id %04x index %02x], mf [%s] outer_tag [%d]\n", + "Setting event_ring_sb [id %04x index %02x], outer_tag [%d]\n", sb, sb_index, - (p_ramrod->mf_mode == SF) ? "SF" : "Multi-Pf", p_ramrod->outer_tag); return qed_spq_post(p_hwfn, p_ent, NULL); diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 7c6caf7f6612..f75d9e0676ce 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -173,9 +173,9 @@ enum QEDE_STATE { * skb are built only after the frame was DMA-ed. */ struct sw_rx_data { - u8 *data; - - DEFINE_DMA_UNMAP_ADDR(mapping); + struct page *data; + dma_addr_t mapping; + unsigned int page_offset; }; struct qede_rx_queue { @@ -188,6 +188,7 @@ struct qede_rx_queue { void __iomem *hw_rxq_prod_addr; int rx_buf_size; + unsigned int rx_buf_seg_size; u16 num_rx_buffers; u16 rxq_id; @@ -281,6 +282,7 @@ void qede_fill_by_demand_stats(struct qede_dev *edev); #define NUM_TX_BDS_MIN 128 #define NUM_TX_BDS_DEF NUM_TX_BDS_MAX +#define QEDE_RX_HDR_SIZE 256 #define for_each_rss(i) for (i = 0; i < edev->num_rss; i++) #endif /* _QEDE_H_ */ diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index e442b85c9a5e..c49dc10ce151 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -217,9 +217,9 @@ static int qede_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) struct qed_link_params params; u32 speed; - if (edev->dev_info.common.is_mf) { + if (!edev->dev_info.common.is_mf_default) { DP_INFO(edev, - "Link parameters can not be changed in MF mode\n"); + "Link parameters can not be changed in non-default mode\n"); return -EOPNOTSUPP; } @@ -428,7 +428,7 @@ static int qede_set_pauseparam(struct net_device *dev, struct qed_link_params params; struct qed_link_output current_link; - if (!edev->dev_info.common.is_mf) { + if (!edev->dev_info.common.is_mf_default) { DP_INFO(edev, "Pause parameters can not be updated in non-default mode\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 6237f10b5119..f50e0bd7fb2c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -330,15 +330,15 @@ static void qede_set_params_for_ipv6_ext(struct sk_buff *skb, struct eth_tx_3rd_bd *third_bd) { u8 l4_proto; - u16 bd2_bits = 0, bd2_bits2 = 0; + u16 bd2_bits1 = 0, bd2_bits2 = 0; - bd2_bits2 |= (1 << ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT); + bd2_bits1 |= (1 << ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT); - bd2_bits |= ((((u8 *)skb_transport_header(skb) - skb->data) >> 1) & + bd2_bits2 |= ((((u8 *)skb_transport_header(skb) - skb->data) >> 1) & ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK) << ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT; - bd2_bits2 |= (ETH_L4_PSEUDO_CSUM_CORRECT_LENGTH << + bd2_bits1 |= (ETH_L4_PSEUDO_CSUM_CORRECT_LENGTH << ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT); if (vlan_get_protocol(skb) == htons(ETH_P_IPV6)) @@ -347,16 +347,15 @@ static void qede_set_params_for_ipv6_ext(struct sk_buff *skb, l4_proto = ip_hdr(skb)->protocol; if (l4_proto == IPPROTO_UDP) - bd2_bits2 |= 1 << ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT; + bd2_bits1 |= 1 << ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT; - if (third_bd) { + if (third_bd) third_bd->data.bitfields |= - ((tcp_hdrlen(skb) / 4) & - ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_MASK) << - ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_SHIFT; - } + cpu_to_le16(((tcp_hdrlen(skb) / 4) & + ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_MASK) << + ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_SHIFT); - second_bd->data.bitfields = cpu_to_le16(bd2_bits); + second_bd->data.bitfields1 = cpu_to_le16(bd2_bits1); second_bd->data.bitfields2 = cpu_to_le16(bd2_bits2); } @@ -464,12 +463,16 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, /* Fill the parsing flags & params according to the requested offload */ if (xmit_type & XMIT_L4_CSUM) { + u16 temp = 1 << ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_SHIFT; + /* We don't re-calculate IP checksum as it is already done by * the upper stack */ first_bd->data.bd_flags.bitfields |= 1 << ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT; + first_bd->data.bitfields |= cpu_to_le16(temp); + /* If the packet is IPv6 with extension header, indicate that * to FW and pass few params, since the device cracker doesn't * support parsing IPv6 with extension header/s. @@ -491,7 +494,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, /* @@@TBD - if will not be removed need to check */ third_bd->data.bitfields |= - (1 << ETH_TX_DATA_3RD_BD_HDR_NBD_SHIFT); + cpu_to_le16((1 << ETH_TX_DATA_3RD_BD_HDR_NBD_SHIFT)); /* Make life easier for FW guys who can't deal with header and * data on same BD. If we need to split, use the second bd... @@ -719,26 +722,52 @@ static bool qede_has_tx_work(struct qede_fastpath *fp) return false; } -/* This function copies the Rx buffer from the CONS position to the PROD - * position, since we failed to allocate a new Rx buffer. +/* This function reuses the buffer(from an offset) from + * consumer index to producer index in the bd ring */ -static void qede_reuse_rx_data(struct qede_rx_queue *rxq) +static inline void qede_reuse_page(struct qede_dev *edev, + struct qede_rx_queue *rxq, + struct sw_rx_data *curr_cons) { - struct eth_rx_bd *rx_bd_cons = qed_chain_consume(&rxq->rx_bd_ring); struct eth_rx_bd *rx_bd_prod = qed_chain_produce(&rxq->rx_bd_ring); - struct sw_rx_data *sw_rx_data_cons = - &rxq->sw_rx_ring[rxq->sw_rx_cons & NUM_RX_BDS_MAX]; - struct sw_rx_data *sw_rx_data_prod = - &rxq->sw_rx_ring[rxq->sw_rx_prod & NUM_RX_BDS_MAX]; + struct sw_rx_data *curr_prod; + dma_addr_t new_mapping; - dma_unmap_addr_set(sw_rx_data_prod, mapping, - dma_unmap_addr(sw_rx_data_cons, mapping)); + curr_prod = &rxq->sw_rx_ring[rxq->sw_rx_prod & NUM_RX_BDS_MAX]; + *curr_prod = *curr_cons; - sw_rx_data_prod->data = sw_rx_data_cons->data; - memcpy(rx_bd_prod, rx_bd_cons, sizeof(struct eth_rx_bd)); + new_mapping = curr_prod->mapping + curr_prod->page_offset; + + rx_bd_prod->addr.hi = cpu_to_le32(upper_32_bits(new_mapping)); + rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(new_mapping)); - rxq->sw_rx_cons++; rxq->sw_rx_prod++; + curr_cons->data = NULL; +} + +static inline int qede_realloc_rx_buffer(struct qede_dev *edev, + struct qede_rx_queue *rxq, + struct sw_rx_data *curr_cons) +{ + /* Move to the next segment in the page */ + curr_cons->page_offset += rxq->rx_buf_seg_size; + + if (curr_cons->page_offset == PAGE_SIZE) { + if (unlikely(qede_alloc_rx_buffer(edev, rxq))) + return -ENOMEM; + + dma_unmap_page(&edev->pdev->dev, curr_cons->mapping, + PAGE_SIZE, DMA_FROM_DEVICE); + } else { + /* Increment refcount of the page as we don't want + * network stack to take the ownership of the page + * which can be recycled multiple times by the driver. + */ + atomic_inc(&curr_cons->data->_count); + qede_reuse_page(edev, rxq, curr_cons); + } + + return 0; } static inline void qede_update_rx_prod(struct qede_dev *edev, @@ -857,9 +886,10 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget) struct sw_rx_data *sw_rx_data; union eth_rx_cqe *cqe; struct sk_buff *skb; + struct page *data; + __le16 flags; u16 len, pad; u32 rx_hash; - u8 *data; /* Get the CQE from the completion ring */ cqe = (union eth_rx_cqe *) @@ -879,56 +909,110 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget) data = sw_rx_data->data; fp_cqe = &cqe->fast_path_regular; - len = le16_to_cpu(fp_cqe->pkt_len); + len = le16_to_cpu(fp_cqe->len_on_first_bd); pad = fp_cqe->placement_offset; + flags = cqe->fast_path_regular.pars_flags.flags; - /* For every Rx BD consumed, we allocate a new BD so the BD ring - * is always with a fixed size. If allocation fails, we take the - * consumed BD and return it to the ring in the PROD position. - * The packet that was received on that BD will be dropped (and - * not passed to the upper stack). - */ - if (likely(qede_alloc_rx_buffer(edev, rxq) == 0)) { - dma_unmap_single(&edev->pdev->dev, - dma_unmap_addr(sw_rx_data, mapping), - rxq->rx_buf_size, DMA_FROM_DEVICE); - - /* If this is an error packet then drop it */ - parse_flag = - le16_to_cpu(cqe->fast_path_regular.pars_flags.flags); - csum_flag = qede_check_csum(parse_flag); - if (csum_flag == QEDE_CSUM_ERROR) { - DP_NOTICE(edev, - "CQE in CONS = %u has error, flags = %x, dropping incoming packet\n", - sw_comp_cons, parse_flag); - rxq->rx_hw_errors++; - kfree(data); - goto next_rx; - } - - skb = build_skb(data, 0); - - if (unlikely(!skb)) { - DP_NOTICE(edev, - "Build_skb failed, dropping incoming packet\n"); - kfree(data); - rxq->rx_alloc_errors++; - goto next_rx; - } + /* If this is an error packet then drop it */ + parse_flag = le16_to_cpu(flags); - skb_reserve(skb, pad); + csum_flag = qede_check_csum(parse_flag); + if (unlikely(csum_flag == QEDE_CSUM_ERROR)) { + DP_NOTICE(edev, + "CQE in CONS = %u has error, flags = %x, dropping incoming packet\n", + sw_comp_cons, parse_flag); + rxq->rx_hw_errors++; + qede_reuse_page(edev, rxq, sw_rx_data); + goto next_rx; + } - } else { + skb = netdev_alloc_skb(edev->ndev, QEDE_RX_HDR_SIZE); + if (unlikely(!skb)) { DP_NOTICE(edev, - "New buffer allocation failed, dropping incoming packet and reusing its buffer\n"); - qede_reuse_rx_data(rxq); + "Build_skb failed, dropping incoming packet\n"); + qede_reuse_page(edev, rxq, sw_rx_data); rxq->rx_alloc_errors++; - goto next_cqe; + goto next_rx; } - sw_rx_data->data = NULL; + /* Copy data into SKB */ + if (len + pad <= QEDE_RX_HDR_SIZE) { + memcpy(skb_put(skb, len), + page_address(data) + pad + + sw_rx_data->page_offset, len); + qede_reuse_page(edev, rxq, sw_rx_data); + } else { + struct skb_frag_struct *frag; + unsigned int pull_len; + unsigned char *va; - skb_put(skb, len); + frag = &skb_shinfo(skb)->frags[0]; + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, data, + pad + sw_rx_data->page_offset, + len, rxq->rx_buf_seg_size); + + va = skb_frag_address(frag); + pull_len = eth_get_headlen(va, QEDE_RX_HDR_SIZE); + + /* Align the pull_len to optimize memcpy */ + memcpy(skb->data, va, ALIGN(pull_len, sizeof(long))); + + skb_frag_size_sub(frag, pull_len); + frag->page_offset += pull_len; + skb->data_len -= pull_len; + skb->tail += pull_len; + + if (unlikely(qede_realloc_rx_buffer(edev, rxq, + sw_rx_data))) { + DP_ERR(edev, "Failed to allocate rx buffer\n"); + rxq->rx_alloc_errors++; + goto next_cqe; + } + } + + if (fp_cqe->bd_num != 1) { + u16 pkt_len = le16_to_cpu(fp_cqe->pkt_len); + u8 num_frags; + + pkt_len -= len; + + for (num_frags = fp_cqe->bd_num - 1; num_frags > 0; + num_frags--) { + u16 cur_size = pkt_len > rxq->rx_buf_size ? + rxq->rx_buf_size : pkt_len; + + WARN_ONCE(!cur_size, + "Still got %d BDs for mapping jumbo, but length became 0\n", + num_frags); + + if (unlikely(qede_alloc_rx_buffer(edev, rxq))) + goto next_cqe; + + rxq->sw_rx_cons++; + sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX; + sw_rx_data = &rxq->sw_rx_ring[sw_rx_index]; + qed_chain_consume(&rxq->rx_bd_ring); + dma_unmap_page(&edev->pdev->dev, + sw_rx_data->mapping, + PAGE_SIZE, DMA_FROM_DEVICE); + + skb_fill_page_desc(skb, + skb_shinfo(skb)->nr_frags++, + sw_rx_data->data, 0, + cur_size); + + skb->truesize += PAGE_SIZE; + skb->data_len += cur_size; + skb->len += cur_size; + pkt_len -= cur_size; + } + + if (pkt_len) + DP_ERR(edev, + "Mapped all BDs of jumbo, but still have %d bytes\n", + pkt_len); + } skb->protocol = eth_type_trans(skb, edev->ndev); @@ -1566,17 +1650,17 @@ static void qede_free_rx_buffers(struct qede_dev *edev, for (i = rxq->sw_rx_cons; i != rxq->sw_rx_prod; i++) { struct sw_rx_data *rx_buf; - u8 *data; + struct page *data; rx_buf = &rxq->sw_rx_ring[i & NUM_RX_BDS_MAX]; data = rx_buf->data; - dma_unmap_single(&edev->pdev->dev, - dma_unmap_addr(rx_buf, mapping), - rxq->rx_buf_size, DMA_FROM_DEVICE); + dma_unmap_page(&edev->pdev->dev, + rx_buf->mapping, + PAGE_SIZE, DMA_FROM_DEVICE); rx_buf->data = NULL; - kfree(data); + __free_page(data); } } @@ -1600,29 +1684,32 @@ static int qede_alloc_rx_buffer(struct qede_dev *edev, struct sw_rx_data *sw_rx_data; struct eth_rx_bd *rx_bd; dma_addr_t mapping; + struct page *data; u16 rx_buf_size; - u8 *data; rx_buf_size = rxq->rx_buf_size; - data = kmalloc(rx_buf_size, GFP_ATOMIC); + data = alloc_pages(GFP_ATOMIC, 0); if (unlikely(!data)) { - DP_NOTICE(edev, "Failed to allocate Rx data\n"); + DP_NOTICE(edev, "Failed to allocate Rx data [page]\n"); return -ENOMEM; } - mapping = dma_map_single(&edev->pdev->dev, data, - rx_buf_size, DMA_FROM_DEVICE); + /* Map the entire page as it would be used + * for multiple RX buffer segment size mapping. + */ + mapping = dma_map_page(&edev->pdev->dev, data, 0, + PAGE_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(&edev->pdev->dev, mapping))) { - kfree(data); + __free_page(data); DP_NOTICE(edev, "Failed to map Rx buffer\n"); return -ENOMEM; } sw_rx_data = &rxq->sw_rx_ring[rxq->sw_rx_prod & NUM_RX_BDS_MAX]; + sw_rx_data->page_offset = 0; sw_rx_data->data = data; - - dma_unmap_addr_set(sw_rx_data, mapping, mapping); + sw_rx_data->mapping = mapping; /* Advance PROD and get BD pointer */ rx_bd = (struct eth_rx_bd *)qed_chain_produce(&rxq->rx_bd_ring); @@ -1643,13 +1730,16 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, rxq->num_rx_buffers = edev->q_num_rx_buffers; - rxq->rx_buf_size = NET_IP_ALIGN + - ETH_OVERHEAD + - edev->ndev->mtu + - QEDE_FW_RX_ALIGN_END; + rxq->rx_buf_size = NET_IP_ALIGN + ETH_OVERHEAD + + edev->ndev->mtu; + if (rxq->rx_buf_size > PAGE_SIZE) + rxq->rx_buf_size = PAGE_SIZE; + + /* Segment size to spilt a page in multiple equal parts */ + rxq->rx_buf_seg_size = roundup_pow_of_two(rxq->rx_buf_size); /* Allocate the parallel driver ring for Rx buffers */ - size = sizeof(*rxq->sw_rx_ring) * NUM_RX_BDS_MAX; + size = sizeof(*rxq->sw_rx_ring) * RX_RING_SIZE; rxq->sw_rx_ring = kzalloc(size, GFP_KERNEL); if (!rxq->sw_rx_ring) { DP_ERR(edev, "Rx buffers ring allocation failed\n"); @@ -1660,7 +1750,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, rc = edev->ops->common->chain_alloc(edev->cdev, QED_CHAIN_USE_TO_CONSUME_PRODUCE, QED_CHAIN_MODE_NEXT_PTR, - NUM_RX_BDS_MAX, + RX_RING_SIZE, sizeof(struct eth_rx_bd), &rxq->rx_bd_ring); @@ -1671,7 +1761,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, rc = edev->ops->common->chain_alloc(edev->cdev, QED_CHAIN_USE_TO_CONSUME, QED_CHAIN_MODE_PBL, - NUM_RX_BDS_MAX, + RX_RING_SIZE, sizeof(union eth_rx_cqe), &rxq->rx_comp_ring); if (rc) diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 1d1ba2c5ee7a..53ecb37ae563 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -11,9 +11,11 @@ #define CORE_SPQE_PAGE_SIZE_BYTES 4096 +#define X_FINAL_CLEANUP_AGG_INT 1 + #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 4 -#define FW_REVISION_VERSION 2 +#define FW_MINOR_VERSION 7 +#define FW_REVISION_VERSION 3 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -152,6 +154,9 @@ /* number of queues in a PF queue group */ #define QM_PF_QUEUE_GROUP_SIZE 8 +/* the size of a single queue element in bytes */ +#define QM_PQ_ELEMENT_SIZE 4 + /* base number of Tx PQs in the CM PQ representation. * should be used when storing PQ IDs in CM PQ registers and context */ @@ -285,6 +290,16 @@ #define PXP_NUM_ILT_RECORDS_K2 11000 #define MAX_NUM_ILT_RECORDS MAX(PXP_NUM_ILT_RECORDS_BB, PXP_NUM_ILT_RECORDS_K2) +#define SDM_COMP_TYPE_NONE 0 +#define SDM_COMP_TYPE_WAKE_THREAD 1 +#define SDM_COMP_TYPE_AGG_INT 2 +#define SDM_COMP_TYPE_CM 3 +#define SDM_COMP_TYPE_LOADER 4 +#define SDM_COMP_TYPE_PXP 5 +#define SDM_COMP_TYPE_INDICATE_ERROR 6 +#define SDM_COMP_TYPE_RELEASE_THREAD 7 +#define SDM_COMP_TYPE_RAM 8 + /******************/ /* PBF CONSTANTS */ /******************/ @@ -335,7 +350,7 @@ struct event_ring_entry { /* Multi function mode */ enum mf_mode { - SF, + ERROR_MODE /* Unsupported mode */, MF_OVLAN, MF_NPAR, MAX_MF_MODE @@ -606,4 +621,19 @@ struct status_block { #define STATUS_BLOCK_ZERO_PAD3_SHIFT 24 }; +struct tunnel_parsing_flags { + u8 flags; +#define TUNNEL_PARSING_FLAGS_TYPE_MASK 0x3 +#define TUNNEL_PARSING_FLAGS_TYPE_SHIFT 0 +#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_SHIFT 2 +#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_MASK 0x3 +#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_SHIFT 3 +#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_SHIFT 5 +#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_SHIFT 6 +#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_MASK 0x1 +#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_SHIFT 7 +}; #endif /* __COMMON_HSI__ */ diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 320b3373ac1d..092cb0c1afcb 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -17,10 +17,8 @@ #define ETH_MAX_RAMROD_PER_CON 8 #define ETH_TX_BD_PAGE_SIZE_BYTES 4096 #define ETH_RX_BD_PAGE_SIZE_BYTES 4096 -#define ETH_RX_SGE_PAGE_SIZE_BYTES 4096 #define ETH_RX_CQE_PAGE_SIZE_BYTES 4096 #define ETH_RX_NUM_NEXT_PAGE_BDS 2 -#define ETH_RX_NUM_NEXT_PAGE_SGES 2 #define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1 #define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18 @@ -34,7 +32,8 @@ #define ETH_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS -#define ETH_REG_CQE_PBL_SIZE 3 +/* Maximum number of buffers, used for RX packet placement */ +#define ETH_RX_MAX_BUFF_PER_PKT 5 /* num of MAC/VLAN filters */ #define ETH_NUM_MAC_FILTERS 512 @@ -54,9 +53,9 @@ /* TPA constants */ #define ETH_TPA_MAX_AGGS_NUM 64 -#define ETH_TPA_CQE_START_SGL_SIZE 3 -#define ETH_TPA_CQE_CONT_SGL_SIZE 6 -#define ETH_TPA_CQE_END_SGL_SIZE 4 +#define ETH_TPA_CQE_START_LEN_LIST_SIZE ETH_RX_MAX_BUFF_PER_PKT +#define ETH_TPA_CQE_CONT_LEN_LIST_SIZE 6 +#define ETH_TPA_CQE_END_LEN_LIST_SIZE 4 /* Queue Zone sizes */ #define TSTORM_QZONE_SIZE 0 @@ -74,18 +73,18 @@ struct coalescing_timeset { struct eth_tx_1st_bd_flags { u8 bitfields; +#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 0 #define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0 +#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 1 #define ETH_TX_1ST_BD_FLAGS_IP_CSUM_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 1 +#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 2 #define ETH_TX_1ST_BD_FLAGS_L4_CSUM_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 2 +#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 3 #define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 3 +#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 4 #define ETH_TX_1ST_BD_FLAGS_LSO_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 4 -#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1 -#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 5 +#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 5 #define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_MASK 0x1 #define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_SHIFT 6 #define ETH_TX_1ST_BD_FLAGS_TUNN_L4_CSUM_MASK 0x1 @@ -97,38 +96,44 @@ struct eth_tx_data_1st_bd { __le16 vlan; u8 nbds; struct eth_tx_1st_bd_flags bd_flags; - __le16 fw_use_only; + __le16 bitfields; +#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_MASK 0x1 +#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_SHIFT 0 +#define ETH_TX_DATA_1ST_BD_RESERVED0_MASK 0x1 +#define ETH_TX_DATA_1ST_BD_RESERVED0_SHIFT 1 +#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_MASK 0x3FFF +#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_SHIFT 2 }; /* The parsing information data for the second tx bd of a given packet. */ struct eth_tx_data_2nd_bd { __le16 tunn_ip_size; - __le16 bitfields; -#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF -#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0 -#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7 -#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13 - __le16 bitfields2; + __le16 bitfields1; #define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_MASK 0xF #define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_SHIFT 0 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_MASK 0x3 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_SHIFT 4 #define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_MASK 0x3 #define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_SHIFT 6 +#define ETH_TX_DATA_2ND_BD_START_BD_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_START_BD_SHIFT 8 #define ETH_TX_DATA_2ND_BD_TUNN_TYPE_MASK 0x3 -#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 8 +#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 9 #define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 10 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 11 #define ETH_TX_DATA_2ND_BD_IPV6_EXT_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 11 +#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 12 #define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 12 +#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 13 #define ETH_TX_DATA_2ND_BD_L4_UDP_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 13 +#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 14 #define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 14 -#define ETH_TX_DATA_2ND_BD_RESERVED1_MASK 0x1 -#define ETH_TX_DATA_2ND_BD_RESERVED1_SHIFT 15 +#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 15 + __le16 bitfields2; +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0 +#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7 +#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13 }; /* Regular ETH Rx FP CQE. */ @@ -145,11 +150,68 @@ struct eth_fast_path_rx_reg_cqe { struct parsing_and_err_flags pars_flags; __le16 vlan_tag; __le32 rss_hash; - __le16 len_on_bd; + __le16 len_on_first_bd; u8 placement_offset; - u8 reserved; - __le16 pbl[ETH_REG_CQE_PBL_SIZE]; - u8 reserved1[10]; + struct tunnel_parsing_flags tunnel_pars_flags; + u8 bd_num; + u8 reserved[7]; + u32 fw_debug; + u8 reserved1[3]; + u8 flags; +#define ETH_FAST_PATH_RX_REG_CQE_VALID_MASK 0x1 +#define ETH_FAST_PATH_RX_REG_CQE_VALID_SHIFT 0 +#define ETH_FAST_PATH_RX_REG_CQE_VALID_TOGGLE_MASK 0x1 +#define ETH_FAST_PATH_RX_REG_CQE_VALID_TOGGLE_SHIFT 1 +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED2_MASK 0x3F +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED2_SHIFT 2 +}; + +/* TPA-continue ETH Rx FP CQE. */ +struct eth_fast_path_rx_tpa_cont_cqe { + u8 type; + u8 tpa_agg_index; + __le16 len_list[ETH_TPA_CQE_CONT_LEN_LIST_SIZE]; + u8 reserved[5]; + u8 reserved1; + __le16 reserved2[ETH_TPA_CQE_CONT_LEN_LIST_SIZE]; +}; + +/* TPA-end ETH Rx FP CQE. */ +struct eth_fast_path_rx_tpa_end_cqe { + u8 type; + u8 tpa_agg_index; + __le16 total_packet_len; + u8 num_of_bds; + u8 end_reason; + __le16 num_of_coalesced_segs; + __le32 ts_delta; + __le16 len_list[ETH_TPA_CQE_END_LEN_LIST_SIZE]; + u8 reserved1[3]; + u8 reserved2; + __le16 reserved3[ETH_TPA_CQE_END_LEN_LIST_SIZE]; +}; + +/* TPA-start ETH Rx FP CQE. */ +struct eth_fast_path_rx_tpa_start_cqe { + u8 type; + u8 bitfields; +#define ETH_FAST_PATH_RX_TPA_START_CQE_RSS_HASH_TYPE_MASK 0x7 +#define ETH_FAST_PATH_RX_TPA_START_CQE_RSS_HASH_TYPE_SHIFT 0 +#define ETH_FAST_PATH_RX_TPA_START_CQE_TC_MASK 0xF +#define ETH_FAST_PATH_RX_TPA_START_CQE_TC_SHIFT 3 +#define ETH_FAST_PATH_RX_TPA_START_CQE_RESERVED0_MASK 0x1 +#define ETH_FAST_PATH_RX_TPA_START_CQE_RESERVED0_SHIFT 7 + __le16 seg_len; + struct parsing_and_err_flags pars_flags; + __le16 vlan_tag; + __le32 rss_hash; + __le16 len_on_first_bd; + u8 placement_offset; + struct tunnel_parsing_flags tunnel_pars_flags; + u8 tpa_agg_index; + u8 header_len; + __le16 ext_bd_len_list[ETH_TPA_CQE_START_LEN_LIST_SIZE]; + u32 fw_debug; }; /* The L4 pseudo checksum mode for Ethernet */ @@ -168,13 +230,26 @@ struct eth_slow_path_rx_cqe { u8 type; u8 ramrod_cmd_id; u8 error_flag; - u8 reserved[27]; + u8 reserved[25]; __le16 echo; + u8 reserved1; + u8 flags; +/* for PMD mode - valid indication */ +#define ETH_SLOW_PATH_RX_CQE_VALID_MASK 0x1 +#define ETH_SLOW_PATH_RX_CQE_VALID_SHIFT 0 +/* for PMD mode - valid toggle indication */ +#define ETH_SLOW_PATH_RX_CQE_VALID_TOGGLE_MASK 0x1 +#define ETH_SLOW_PATH_RX_CQE_VALID_TOGGLE_SHIFT 1 +#define ETH_SLOW_PATH_RX_CQE_RESERVED2_MASK 0x3F +#define ETH_SLOW_PATH_RX_CQE_RESERVED2_SHIFT 2 }; /* union for all ETH Rx CQE types */ union eth_rx_cqe { struct eth_fast_path_rx_reg_cqe fast_path_regular; + struct eth_fast_path_rx_tpa_start_cqe fast_path_tpa_start; + struct eth_fast_path_rx_tpa_cont_cqe fast_path_tpa_cont; + struct eth_fast_path_rx_tpa_end_cqe fast_path_tpa_end; struct eth_slow_path_rx_cqe slow_path; }; @@ -183,15 +258,18 @@ enum eth_rx_cqe_type { ETH_RX_CQE_TYPE_UNUSED, ETH_RX_CQE_TYPE_REGULAR, ETH_RX_CQE_TYPE_SLOW_PATH, + ETH_RX_CQE_TYPE_TPA_START, + ETH_RX_CQE_TYPE_TPA_CONT, + ETH_RX_CQE_TYPE_TPA_END, MAX_ETH_RX_CQE_TYPE }; /* ETH Rx producers data */ struct eth_rx_prod_data { __le16 bd_prod; - __le16 sge_prod; __le16 cqe_prod; __le16 reserved; + __le16 reserved1; }; /* The first tx bd of a given packet */ @@ -211,12 +289,17 @@ struct eth_tx_2nd_bd { /* The parsing information data for the third tx bd of a given packet. */ struct eth_tx_data_3rd_bd { __le16 lso_mss; - u8 bitfields; + __le16 bitfields; #define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_MASK 0xF #define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_SHIFT 0 #define ETH_TX_DATA_3RD_BD_HDR_NBD_MASK 0xF #define ETH_TX_DATA_3RD_BD_HDR_NBD_SHIFT 4 - u8 resereved0[3]; +#define ETH_TX_DATA_3RD_BD_START_BD_MASK 0x1 +#define ETH_TX_DATA_3RD_BD_START_BD_SHIFT 8 +#define ETH_TX_DATA_3RD_BD_RESERVED0_MASK 0x7F +#define ETH_TX_DATA_3RD_BD_RESERVED0_SHIFT 9 + u8 tunn_l4_hdr_start_offset_w; + u8 tunn_hdr_size_w; }; /* The third tx bd of a given packet */ @@ -226,12 +309,24 @@ struct eth_tx_3rd_bd { struct eth_tx_data_3rd_bd data; }; +/* Complementary information for the regular tx bd of a given packet. */ +struct eth_tx_data_bd { + __le16 reserved0; + __le16 bitfields; +#define ETH_TX_DATA_BD_RESERVED1_MASK 0xFF +#define ETH_TX_DATA_BD_RESERVED1_SHIFT 0 +#define ETH_TX_DATA_BD_START_BD_MASK 0x1 +#define ETH_TX_DATA_BD_START_BD_SHIFT 8 +#define ETH_TX_DATA_BD_RESERVED2_MASK 0x7F +#define ETH_TX_DATA_BD_RESERVED2_SHIFT 9 + __le16 reserved3; +}; + /* The common non-special TX BD ring element */ struct eth_tx_bd { struct regpair addr; __le16 nbytes; - __le16 reserved0; - __le32 reserved1; + struct eth_tx_data_bd data; }; union eth_tx_bd_types { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index d4a32e878180..3d43c1d4ecef 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -80,7 +80,7 @@ struct qed_dev_info { u8 num_hwfns; u8 hw_mac[ETH_ALEN]; - bool is_mf; + bool is_mf_default; /* FW version */ u16 fw_major; @@ -360,6 +360,12 @@ enum DP_MODULE { /* to be added...up to 0x8000000 */ }; +enum qed_mf_mode { + QED_MF_DEFAULT, + QED_MF_OVLAN, + QED_MF_NPAR, +}; + struct qed_eth_stats { u64 no_buff_discards; u64 packet_too_big_discard; -- cgit v1.2.3 From 7bbf3cae65b6e438bf52033b63fdce4a86e89e17 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 15 Feb 2016 21:25:57 +0000 Subject: ipv4: Remove inet_lro library There are no longer any in-tree drivers that use it. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/inet_lro.h | 142 ------------------ net/ipv4/Kconfig | 8 - net/ipv4/Makefile | 1 - net/ipv4/inet_lro.c | 374 ----------------------------------------------- 4 files changed, 525 deletions(-) delete mode 100644 include/linux/inet_lro.h delete mode 100644 net/ipv4/inet_lro.c (limited to 'include/linux') diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h deleted file mode 100644 index 9a715cfa1fe3..000000000000 --- a/include/linux/inet_lro.h +++ /dev/null @@ -1,142 +0,0 @@ -/* - * linux/include/linux/inet_lro.h - * - * Large Receive Offload (ipv4 / tcp) - * - * (C) Copyright IBM Corp. 2007 - * - * Authors: - * Jan-Bernd Themann - * Christoph Raisch - * - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef __INET_LRO_H_ -#define __INET_LRO_H_ - -#include -#include - -/* - * LRO statistics - */ - -struct net_lro_stats { - unsigned long aggregated; - unsigned long flushed; - unsigned long no_desc; -}; - -/* - * LRO descriptor for a tcp session - */ -struct net_lro_desc { - struct sk_buff *parent; - struct sk_buff *last_skb; - struct skb_frag_struct *next_frag; - struct iphdr *iph; - struct tcphdr *tcph; - __wsum data_csum; - __be32 tcp_rcv_tsecr; - __be32 tcp_rcv_tsval; - __be32 tcp_ack; - u32 tcp_next_seq; - u32 skb_tot_frags_len; - u16 ip_tot_len; - u16 tcp_saw_tstamp; /* timestamps enabled */ - __be16 tcp_window; - int pkt_aggr_cnt; /* counts aggregated packets */ - int vlan_packet; - int mss; - int active; -}; - -/* - * Large Receive Offload (LRO) Manager - * - * Fields must be set by driver - */ - -struct net_lro_mgr { - struct net_device *dev; - struct net_lro_stats stats; - - /* LRO features */ - unsigned long features; -#define LRO_F_NAPI 1 /* Pass packets to stack via NAPI */ -#define LRO_F_EXTRACT_VLAN_ID 2 /* Set flag if VLAN IDs are extracted - from received packets and eth protocol - is still ETH_P_8021Q */ - - /* - * Set for generated SKBs that are not added to - * the frag list in fragmented mode - */ - u32 ip_summed; - u32 ip_summed_aggr; /* Set in aggregated SKBs: CHECKSUM_UNNECESSARY - * or CHECKSUM_NONE */ - - int max_desc; /* Max number of LRO descriptors */ - int max_aggr; /* Max number of LRO packets to be aggregated */ - - int frag_align_pad; /* Padding required to properly align layer 3 - * headers in generated skb when using frags */ - - struct net_lro_desc *lro_arr; /* Array of LRO descriptors */ - - /* - * Optimized driver functions - * - * get_skb_header: returns tcp and ip header for packet in SKB - */ - int (*get_skb_header)(struct sk_buff *skb, void **ip_hdr, - void **tcpudp_hdr, u64 *hdr_flags, void *priv); - - /* hdr_flags: */ -#define LRO_IPV4 1 /* ip_hdr is IPv4 header */ -#define LRO_TCP 2 /* tcpudp_hdr is TCP header */ - - /* - * get_frag_header: returns mac, tcp and ip header for packet in SKB - * - * @hdr_flags: Indicate what kind of LRO has to be done - * (IPv4/IPv6/TCP/UDP) - */ - int (*get_frag_header)(struct skb_frag_struct *frag, void **mac_hdr, - void **ip_hdr, void **tcpudp_hdr, u64 *hdr_flags, - void *priv); -}; - -/* - * Processes a SKB - * - * @lro_mgr: LRO manager to use - * @skb: SKB to aggregate - * @priv: Private data that may be used by driver functions - * (for example get_tcp_ip_hdr) - */ - -void lro_receive_skb(struct net_lro_mgr *lro_mgr, - struct sk_buff *skb, - void *priv); -/* - * Forward all aggregated SKBs held by lro_mgr to network stack - */ - -void lro_flush_all(struct net_lro_mgr *lro_mgr); - -#endif diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 395d82754626..238225b0c970 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -406,14 +406,6 @@ config INET_XFRM_MODE_BEET If unsure, say Y. -config INET_LRO - tristate "Large Receive Offload (ipv4/tcp)" - default y - ---help--- - Support for Large Receive Offload (ipv4/tcp). - - If unsure, say Y. - config INET_DIAG tristate "INET: socket monitoring interface" default y diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 62c049b647e9..bfa133691cde 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -32,7 +32,6 @@ obj-$(CONFIG_INET_ESP) += esp4.o obj-$(CONFIG_INET_IPCOMP) += ipcomp.o obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o obj-$(CONFIG_INET_XFRM_MODE_BEET) += xfrm4_mode_beet.o -obj-$(CONFIG_INET_LRO) += inet_lro.o obj-$(CONFIG_INET_TUNNEL) += tunnel4.o obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c deleted file mode 100644 index f17ea49b28fb..000000000000 --- a/net/ipv4/inet_lro.c +++ /dev/null @@ -1,374 +0,0 @@ -/* - * linux/net/ipv4/inet_lro.c - * - * Large Receive Offload (ipv4 / tcp) - * - * (C) Copyright IBM Corp. 2007 - * - * Authors: - * Jan-Bernd Themann - * Christoph Raisch - * - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - - -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jan-Bernd Themann "); -MODULE_DESCRIPTION("Large Receive Offload (ipv4 / tcp)"); - -#define TCP_HDR_LEN(tcph) (tcph->doff << 2) -#define IP_HDR_LEN(iph) (iph->ihl << 2) -#define TCP_PAYLOAD_LENGTH(iph, tcph) \ - (ntohs(iph->tot_len) - IP_HDR_LEN(iph) - TCP_HDR_LEN(tcph)) - -#define IPH_LEN_WO_OPTIONS 5 -#define TCPH_LEN_WO_OPTIONS 5 -#define TCPH_LEN_W_TIMESTAMP 8 - -#define LRO_MAX_PG_HLEN 64 - -#define LRO_INC_STATS(lro_mgr, attr) { lro_mgr->stats.attr++; } - -/* - * Basic tcp checks whether packet is suitable for LRO - */ - -static int lro_tcp_ip_check(const struct iphdr *iph, const struct tcphdr *tcph, - int len, const struct net_lro_desc *lro_desc) -{ - /* check ip header: don't aggregate padded frames */ - if (ntohs(iph->tot_len) != len) - return -1; - - if (TCP_PAYLOAD_LENGTH(iph, tcph) == 0) - return -1; - - if (iph->ihl != IPH_LEN_WO_OPTIONS) - return -1; - - if (tcph->cwr || tcph->ece || tcph->urg || !tcph->ack || - tcph->rst || tcph->syn || tcph->fin) - return -1; - - if (INET_ECN_is_ce(ipv4_get_dsfield(iph))) - return -1; - - if (tcph->doff != TCPH_LEN_WO_OPTIONS && - tcph->doff != TCPH_LEN_W_TIMESTAMP) - return -1; - - /* check tcp options (only timestamp allowed) */ - if (tcph->doff == TCPH_LEN_W_TIMESTAMP) { - __be32 *topt = (__be32 *)(tcph + 1); - - if (*topt != htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) - | (TCPOPT_TIMESTAMP << 8) - | TCPOLEN_TIMESTAMP)) - return -1; - - /* timestamp should be in right order */ - topt++; - if (lro_desc && after(ntohl(lro_desc->tcp_rcv_tsval), - ntohl(*topt))) - return -1; - - /* timestamp reply should not be zero */ - topt++; - if (*topt == 0) - return -1; - } - - return 0; -} - -static void lro_update_tcp_ip_header(struct net_lro_desc *lro_desc) -{ - struct iphdr *iph = lro_desc->iph; - struct tcphdr *tcph = lro_desc->tcph; - __be32 *p; - __wsum tcp_hdr_csum; - - tcph->ack_seq = lro_desc->tcp_ack; - tcph->window = lro_desc->tcp_window; - - if (lro_desc->tcp_saw_tstamp) { - p = (__be32 *)(tcph + 1); - *(p+2) = lro_desc->tcp_rcv_tsecr; - } - - csum_replace2(&iph->check, iph->tot_len, htons(lro_desc->ip_tot_len)); - iph->tot_len = htons(lro_desc->ip_tot_len); - - tcph->check = 0; - tcp_hdr_csum = csum_partial(tcph, TCP_HDR_LEN(tcph), 0); - lro_desc->data_csum = csum_add(lro_desc->data_csum, tcp_hdr_csum); - tcph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, - lro_desc->ip_tot_len - - IP_HDR_LEN(iph), IPPROTO_TCP, - lro_desc->data_csum); -} - -static __wsum lro_tcp_data_csum(struct iphdr *iph, struct tcphdr *tcph, int len) -{ - __wsum tcp_csum; - __wsum tcp_hdr_csum; - __wsum tcp_ps_hdr_csum; - - tcp_csum = ~csum_unfold(tcph->check); - tcp_hdr_csum = csum_partial(tcph, TCP_HDR_LEN(tcph), tcp_csum); - - tcp_ps_hdr_csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - len + TCP_HDR_LEN(tcph), - IPPROTO_TCP, 0); - - return csum_sub(csum_sub(tcp_csum, tcp_hdr_csum), - tcp_ps_hdr_csum); -} - -static void lro_init_desc(struct net_lro_desc *lro_desc, struct sk_buff *skb, - struct iphdr *iph, struct tcphdr *tcph) -{ - int nr_frags; - __be32 *ptr; - u32 tcp_data_len = TCP_PAYLOAD_LENGTH(iph, tcph); - - nr_frags = skb_shinfo(skb)->nr_frags; - lro_desc->parent = skb; - lro_desc->next_frag = &(skb_shinfo(skb)->frags[nr_frags]); - lro_desc->iph = iph; - lro_desc->tcph = tcph; - lro_desc->tcp_next_seq = ntohl(tcph->seq) + tcp_data_len; - lro_desc->tcp_ack = tcph->ack_seq; - lro_desc->tcp_window = tcph->window; - - lro_desc->pkt_aggr_cnt = 1; - lro_desc->ip_tot_len = ntohs(iph->tot_len); - - if (tcph->doff == 8) { - ptr = (__be32 *)(tcph+1); - lro_desc->tcp_saw_tstamp = 1; - lro_desc->tcp_rcv_tsval = *(ptr+1); - lro_desc->tcp_rcv_tsecr = *(ptr+2); - } - - lro_desc->mss = tcp_data_len; - lro_desc->active = 1; - - lro_desc->data_csum = lro_tcp_data_csum(iph, tcph, - tcp_data_len); -} - -static inline void lro_clear_desc(struct net_lro_desc *lro_desc) -{ - memset(lro_desc, 0, sizeof(struct net_lro_desc)); -} - -static void lro_add_common(struct net_lro_desc *lro_desc, struct iphdr *iph, - struct tcphdr *tcph, int tcp_data_len) -{ - struct sk_buff *parent = lro_desc->parent; - __be32 *topt; - - lro_desc->pkt_aggr_cnt++; - lro_desc->ip_tot_len += tcp_data_len; - lro_desc->tcp_next_seq += tcp_data_len; - lro_desc->tcp_window = tcph->window; - lro_desc->tcp_ack = tcph->ack_seq; - - /* don't update tcp_rcv_tsval, would not work with PAWS */ - if (lro_desc->tcp_saw_tstamp) { - topt = (__be32 *) (tcph + 1); - lro_desc->tcp_rcv_tsecr = *(topt + 2); - } - - lro_desc->data_csum = csum_block_add(lro_desc->data_csum, - lro_tcp_data_csum(iph, tcph, - tcp_data_len), - parent->len); - - parent->len += tcp_data_len; - parent->data_len += tcp_data_len; - if (tcp_data_len > lro_desc->mss) - lro_desc->mss = tcp_data_len; -} - -static void lro_add_packet(struct net_lro_desc *lro_desc, struct sk_buff *skb, - struct iphdr *iph, struct tcphdr *tcph) -{ - struct sk_buff *parent = lro_desc->parent; - int tcp_data_len = TCP_PAYLOAD_LENGTH(iph, tcph); - - lro_add_common(lro_desc, iph, tcph, tcp_data_len); - - skb_pull(skb, (skb->len - tcp_data_len)); - parent->truesize += skb->truesize; - - if (lro_desc->last_skb) - lro_desc->last_skb->next = skb; - else - skb_shinfo(parent)->frag_list = skb; - - lro_desc->last_skb = skb; -} - - -static int lro_check_tcp_conn(struct net_lro_desc *lro_desc, - struct iphdr *iph, - struct tcphdr *tcph) -{ - if ((lro_desc->iph->saddr != iph->saddr) || - (lro_desc->iph->daddr != iph->daddr) || - (lro_desc->tcph->source != tcph->source) || - (lro_desc->tcph->dest != tcph->dest)) - return -1; - return 0; -} - -static struct net_lro_desc *lro_get_desc(struct net_lro_mgr *lro_mgr, - struct net_lro_desc *lro_arr, - struct iphdr *iph, - struct tcphdr *tcph) -{ - struct net_lro_desc *lro_desc = NULL; - struct net_lro_desc *tmp; - int max_desc = lro_mgr->max_desc; - int i; - - for (i = 0; i < max_desc; i++) { - tmp = &lro_arr[i]; - if (tmp->active) - if (!lro_check_tcp_conn(tmp, iph, tcph)) { - lro_desc = tmp; - goto out; - } - } - - for (i = 0; i < max_desc; i++) { - if (!lro_arr[i].active) { - lro_desc = &lro_arr[i]; - goto out; - } - } - - LRO_INC_STATS(lro_mgr, no_desc); -out: - return lro_desc; -} - -static void lro_flush(struct net_lro_mgr *lro_mgr, - struct net_lro_desc *lro_desc) -{ - if (lro_desc->pkt_aggr_cnt > 1) - lro_update_tcp_ip_header(lro_desc); - - skb_shinfo(lro_desc->parent)->gso_size = lro_desc->mss; - - if (lro_mgr->features & LRO_F_NAPI) - netif_receive_skb(lro_desc->parent); - else - netif_rx(lro_desc->parent); - - LRO_INC_STATS(lro_mgr, flushed); - lro_clear_desc(lro_desc); -} - -static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, - void *priv) -{ - struct net_lro_desc *lro_desc; - struct iphdr *iph; - struct tcphdr *tcph; - u64 flags; - int vlan_hdr_len = 0; - - if (!lro_mgr->get_skb_header || - lro_mgr->get_skb_header(skb, (void *)&iph, (void *)&tcph, - &flags, priv)) - goto out; - - if (!(flags & LRO_IPV4) || !(flags & LRO_TCP)) - goto out; - - lro_desc = lro_get_desc(lro_mgr, lro_mgr->lro_arr, iph, tcph); - if (!lro_desc) - goto out; - - if ((skb->protocol == htons(ETH_P_8021Q)) && - !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) - vlan_hdr_len = VLAN_HLEN; - - if (!lro_desc->active) { /* start new lro session */ - if (lro_tcp_ip_check(iph, tcph, skb->len - vlan_hdr_len, NULL)) - goto out; - - skb->ip_summed = lro_mgr->ip_summed_aggr; - lro_init_desc(lro_desc, skb, iph, tcph); - LRO_INC_STATS(lro_mgr, aggregated); - return 0; - } - - if (lro_desc->tcp_next_seq != ntohl(tcph->seq)) - goto out2; - - if (lro_tcp_ip_check(iph, tcph, skb->len, lro_desc)) - goto out2; - - lro_add_packet(lro_desc, skb, iph, tcph); - LRO_INC_STATS(lro_mgr, aggregated); - - if ((lro_desc->pkt_aggr_cnt >= lro_mgr->max_aggr) || - lro_desc->parent->len > (0xFFFF - lro_mgr->dev->mtu)) - lro_flush(lro_mgr, lro_desc); - - return 0; - -out2: /* send aggregated SKBs to stack */ - lro_flush(lro_mgr, lro_desc); - -out: - return 1; -} - -void lro_receive_skb(struct net_lro_mgr *lro_mgr, - struct sk_buff *skb, - void *priv) -{ - if (__lro_proc_skb(lro_mgr, skb, priv)) { - if (lro_mgr->features & LRO_F_NAPI) - netif_receive_skb(skb); - else - netif_rx(skb); - } -} -EXPORT_SYMBOL(lro_receive_skb); - -void lro_flush_all(struct net_lro_mgr *lro_mgr) -{ - int i; - struct net_lro_desc *lro_desc = lro_mgr->lro_arr; - - for (i = 0; i < lro_mgr->max_desc; i++) { - if (lro_desc[i].active) - lro_flush(lro_mgr, &lro_desc[i]); - } -} -EXPORT_SYMBOL(lro_flush_all); -- cgit v1.2.3 From 905f0a739ad82c6371fb0cb0e71db14a750702ad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 18 Feb 2016 15:03:27 +0100 Subject: nfnetlink: remove nfnetlink_alloc_skb Following mmapped netlink removal this code can be simplified by removing the alloc wrapper. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 2 -- net/netfilter/nfnetlink.c | 7 ------- net/netfilter/nfnetlink_log.c | 5 ++--- 3 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index ba0d9789eb6e..1d82dd5e9a08 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -34,8 +34,6 @@ int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); int nfnetlink_has_listeners(struct net *net, unsigned int group); -struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size, - u32 dst_portid, gfp_t gfp_mask); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a7ba23353dab..9a99f686d06f 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -127,13 +127,6 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group) } EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); -struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size, - u32 dst_portid, gfp_t gfp_mask) -{ - return netlink_alloc_skb(net->nfnl, size, dst_portid, gfp_mask); -} -EXPORT_SYMBOL_GPL(nfnetlink_alloc_skb); - int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags) { diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 8ca932057c13..11f81c8385fc 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -330,14 +330,13 @@ nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size, * message. WARNING: has to be <= 128k due to slab restrictions */ n = max(inst_size, pkt_size); - skb = nfnetlink_alloc_skb(net, n, peer_portid, GFP_ATOMIC); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { if (n > pkt_size) { /* try to allocate only as much as we need for current * packet */ - skb = nfnetlink_alloc_skb(net, pkt_size, - peer_portid, GFP_ATOMIC); + skb = alloc_skb(pkt_size, GFP_ATOMIC); } } -- cgit v1.2.3 From c5b0db3263b92526bc0c1b6380c0c99f91f069fc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 18 Feb 2016 15:03:28 +0100 Subject: nfnetlink: Revert "nfnetlink: add support for memory mapped netlink" reverts commit 3ab1f683bf8b ("nfnetlink: add support for memory mapped netlink")' Like previous commits in the series, remove wrappers that are not needed after mmapped netlink removal. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netlink.h | 10 ---------- net/netfilter/nfnetlink_queue.c | 6 ++---- net/netlink/af_netlink.c | 20 ++++---------------- 3 files changed, 6 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 0b41959aab9f..da14ab61f363 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -69,16 +69,6 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group) extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); -extern struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, - unsigned int ldiff, u32 dst_portid, - gfp_t gfp_mask); -static inline struct sk_buff * -netlink_alloc_skb(struct sock *ssk, unsigned int size, u32 dst_portid, - gfp_t gfp_mask) -{ - return __netlink_alloc_skb(ssk, size, 0, dst_portid, gfp_mask); -} - extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 1d3936587ace..75429997ed41 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -301,7 +301,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, __be32 **packet_id_ptr) { size_t size; - size_t data_len = 0, cap_len = 0, rem_len = 0; + size_t data_len = 0, cap_len = 0; unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; @@ -361,7 +361,6 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; - rem_len = data_len - hlen; break; } @@ -386,8 +385,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, size += nla_total_size(seclen); } - skb = __netlink_alloc_skb(net->nfnl, size, rem_len, queue->peer_portid, - GFP_ATOMIC); + skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { skb_tx_error(entskb); return NULL; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 85aa6ef86dfd..c8416792cce0 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1248,14 +1248,6 @@ retry: } EXPORT_SYMBOL(netlink_unicast); -struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, - unsigned int ldiff, u32 dst_portid, - gfp_t gfp_mask) -{ - return alloc_skb(size, gfp_mask); -} -EXPORT_SYMBOL_GPL(__netlink_alloc_skb); - int netlink_has_listeners(struct sock *sk, unsigned int group) { int res = 0; @@ -2082,15 +2074,12 @@ static int netlink_dump(struct sock *sk) if (alloc_min_size < nlk->max_recvmsg_len) { alloc_size = nlk->max_recvmsg_len; - skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, - GFP_KERNEL | - __GFP_NOWARN | - __GFP_NORETRY); + skb = alloc_skb(alloc_size, GFP_KERNEL | + __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; - skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, - GFP_KERNEL); + skb = alloc_skb(alloc_size, GFP_KERNEL); } if (!skb) goto errout_skb; @@ -2230,8 +2219,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) if (!(nlk->flags & NETLINK_F_CAP_ACK) && err) payload += nlmsg_len(nlh); - skb = netlink_alloc_skb(in_skb->sk, nlmsg_total_size(payload), - NETLINK_CB(in_skb).portid, GFP_KERNEL); + skb = nlmsg_new(payload, GFP_KERNEL); if (!skb) { struct sock *sk; -- cgit v1.2.3 From 9e74a6dadbbf31ac18a2712048bf866c8e32aab2 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 17 Feb 2016 11:23:55 -0800 Subject: net: Optimize local checksum offload This patch takes advantage of several assumptions we can make about the headers of the frame in order to reduce overall processing overhead for computing the outer header checksum. First we can assume the entire header is in the region pointed to by skb->head as this is what csum_start is based on. Second, as a result of our first assumption, we can just call csum_partial instead of making a call to skb_checksum which would end up having to configure things so that we could walk through the frags list. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 39206751463e..89b536796e53 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3713,19 +3713,18 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) */ static inline __wsum lco_csum(struct sk_buff *skb) { - char *inner_csum_field; - __wsum csum; + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *l4_hdr = skb_transport_header(skb); + __wsum partial; /* Start with complement of inner checksum adjustment */ - inner_csum_field = skb->data + skb_checksum_start_offset(skb) + - skb->csum_offset; - csum = ~csum_unfold(*(__force __sum16 *)inner_csum_field); + partial = ~csum_unfold(*(__force __sum16 *)(csum_start + + skb->csum_offset)); + /* Add in checksum of our headers (incl. outer checksum - * adjustment filled in by caller) + * adjustment filled in by caller) and return result. */ - csum = skb_checksum(skb, 0, skb_checksum_start_offset(skb), csum); - /* The result is the checksum from skb->data to end of packet */ - return csum; + return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 3f9b4a6972d50562613daa649ed064244e6bc7bb Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Thu, 18 Feb 2016 17:00:39 +0200 Subject: qed: Lay infrastructure for vlan filtering offload Today, interfaces are working in vlan-promisc mode; But once vlan filtering offloaded would be supported, we'll need a method to control it directly [e.g., when setting device to PROMISC, or when running out of vlan credits]. This adds the necessary API for L2 client to manually choose whether to accept all vlans or only those for which filters were configured. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 23 +++++++++++++++++++---- include/linux/qed/qed_eth_if.h | 2 ++ 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 978d07a61bbf..73feaf7eedb8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -124,6 +124,8 @@ struct qed_sp_vport_update_params { u8 update_vport_active_tx_flg; u8 vport_active_tx_flg; u8 update_approx_mcast_flg; + u8 update_accept_any_vlan_flg; + u8 accept_any_vlan; unsigned long bins[8]; struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; @@ -393,7 +395,9 @@ qed_sp_vport_update(struct qed_hwfn *p_hwfn, p_cmn->update_rx_active_flg = p_params->update_vport_active_rx_flg; p_cmn->tx_active_flg = p_params->vport_active_tx_flg; p_cmn->update_tx_active_flg = p_params->update_vport_active_tx_flg; - + p_cmn->accept_any_vlan = p_params->accept_any_vlan; + p_cmn->update_accept_any_vlan_flg = + p_params->update_accept_any_vlan_flg; rc = qed_sp_vport_update_rss(p_hwfn, p_ramrod, p_rss_params); if (rc) { /* Return spq entry which is taken in qed_sp_init_request()*/ @@ -444,8 +448,10 @@ static int qed_sp_vport_stop(struct qed_hwfn *p_hwfn, static int qed_filter_accept_cmd(struct qed_dev *cdev, u8 vport, struct qed_filter_accept_flags accept_flags, - enum spq_mode comp_mode, - struct qed_spq_comp_cb *p_comp_data) + u8 update_accept_any_vlan, + u8 accept_any_vlan, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_data) { struct qed_sp_vport_update_params vport_update_params; int i, rc; @@ -454,6 +460,8 @@ static int qed_filter_accept_cmd(struct qed_dev *cdev, memset(&vport_update_params, 0, sizeof(vport_update_params)); vport_update_params.vport_id = vport; vport_update_params.accept_flags = accept_flags; + vport_update_params.update_accept_any_vlan_flg = update_accept_any_vlan; + vport_update_params.accept_any_vlan = accept_any_vlan; for_each_hwfn(cdev, i) { struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; @@ -471,6 +479,10 @@ static int qed_filter_accept_cmd(struct qed_dev *cdev, "Accept filter configured, flags = [Rx]%x [Tx]%x\n", accept_flags.rx_accept_filter, accept_flags.tx_accept_filter); + if (update_accept_any_vlan) + DP_VERBOSE(p_hwfn, QED_MSG_SP, + "accept_any_vlan=%d configured\n", + accept_any_vlan); } return 0; @@ -1347,6 +1359,9 @@ static int qed_update_vport(struct qed_dev *cdev, params->update_vport_active_flg; sp_params.vport_active_rx_flg = params->vport_active_flg; sp_params.vport_active_tx_flg = params->vport_active_flg; + sp_params.accept_any_vlan = params->accept_any_vlan; + sp_params.update_accept_any_vlan_flg = + params->update_accept_any_vlan_flg; /* RSS - is a bit tricky, since upper-layer isn't familiar with hwfns. * We need to re-fix the rss values per engine for CMT. @@ -1566,7 +1581,7 @@ static int qed_configure_filter_rx_mode(struct qed_dev *cdev, else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; - return qed_filter_accept_cmd(cdev, 0, accept_flags, + return qed_filter_accept_cmd(cdev, 0, accept_flags, false, false, QED_SPQ_MODE_CB, NULL); } diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 81ab178e31c1..e53b0ca49e41 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -33,6 +33,8 @@ struct qed_update_vport_params { u8 vport_id; u8 update_vport_active_flg; u8 vport_active_flg; + u8 update_accept_any_vlan_flg; + u8 accept_any_vlan; u8 update_rss_flg; struct qed_update_vport_rss_params rss_params; }; -- cgit v1.2.3 From e52bc7c28ac9f54db6f86b19ed65c599def18c98 Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Fri, 19 Feb 2016 09:23:59 -0500 Subject: lib/bitmap.c: conversion routines to/from u32 array Aimed at transferring bitmaps to/from user-space in a 32/64-bit agnostic way. Tested: unit tests (next patch) on qemu i386, x86_64, ppc, ppc64 BE and LE, ARM. Signed-off-by: David Decotigny Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/bitmap.h | 10 ++++++ lib/bitmap.c | 89 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 9653fdb76a42..e9b0b9ab07e5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -59,6 +59,8 @@ * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region + * bitmap_from_u32array(dst, nbits, buf, nwords) *dst = *buf (nwords 32b words) + * bitmap_to_u32array(buf, nwords, src, nbits) *buf = *dst (nwords 32b words) */ /* @@ -163,6 +165,14 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); +extern unsigned int bitmap_from_u32array(unsigned long *bitmap, + unsigned int nbits, + const u32 *buf, + unsigned int nwords); +extern unsigned int bitmap_to_u32array(u32 *buf, + unsigned int nwords, + const unsigned long *bitmap, + unsigned int nbits); #ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else diff --git a/lib/bitmap.c b/lib/bitmap.c index 814814397cce..c66da508cbf7 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include @@ -1059,6 +1061,93 @@ int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) } EXPORT_SYMBOL(bitmap_allocate_region); +/** + * bitmap_from_u32array - copy the contents of a u32 array of bits to bitmap + * @bitmap: array of unsigned longs, the destination bitmap, non NULL + * @nbits: number of bits in @bitmap + * @buf: array of u32 (in host byte order), the source bitmap, non NULL + * @nwords: number of u32 words in @buf + * + * copy min(nbits, 32*nwords) bits from @buf to @bitmap, remaining + * bits between nword and nbits in @bitmap (if any) are cleared. In + * last word of @bitmap, the bits beyond nbits (if any) are kept + * unchanged. + * + * Return the number of bits effectively copied. + */ +unsigned int +bitmap_from_u32array(unsigned long *bitmap, unsigned int nbits, + const u32 *buf, unsigned int nwords) +{ + unsigned int dst_idx, src_idx; + + for (src_idx = dst_idx = 0; dst_idx < BITS_TO_LONGS(nbits); ++dst_idx) { + unsigned long part = 0; + + if (src_idx < nwords) + part = buf[src_idx++]; + +#if BITS_PER_LONG == 64 + if (src_idx < nwords) + part |= ((unsigned long) buf[src_idx++]) << 32; +#endif + + if (dst_idx < nbits/BITS_PER_LONG) + bitmap[dst_idx] = part; + else { + unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); + + bitmap[dst_idx] = (bitmap[dst_idx] & ~mask) + | (part & mask); + } + } + + return min_t(unsigned int, nbits, 32*nwords); +} +EXPORT_SYMBOL(bitmap_from_u32array); + +/** + * bitmap_to_u32array - copy the contents of bitmap to a u32 array of bits + * @buf: array of u32 (in host byte order), the dest bitmap, non NULL + * @nwords: number of u32 words in @buf + * @bitmap: array of unsigned longs, the source bitmap, non NULL + * @nbits: number of bits in @bitmap + * + * copy min(nbits, 32*nwords) bits from @bitmap to @buf. Remaining + * bits after nbits in @buf (if any) are cleared. + * + * Return the number of bits effectively copied. + */ +unsigned int +bitmap_to_u32array(u32 *buf, unsigned int nwords, + const unsigned long *bitmap, unsigned int nbits) +{ + unsigned int dst_idx = 0, src_idx = 0; + + while (dst_idx < nwords) { + unsigned long part = 0; + + if (src_idx < BITS_TO_LONGS(nbits)) { + part = bitmap[src_idx]; + if (src_idx >= nbits/BITS_PER_LONG) + part &= BITMAP_LAST_WORD_MASK(nbits); + src_idx++; + } + + buf[dst_idx++] = part & 0xffffffffUL; + +#if BITS_PER_LONG == 64 + if (dst_idx < nwords) { + part >>= 32; + buf[dst_idx++] = part & 0xffffffffUL; + } +#endif + } + + return min_t(unsigned int, nbits, 32*nwords); +} +EXPORT_SYMBOL(bitmap_to_u32array); + /** * bitmap_copy_le - copy a bitmap, putting the bits into little-endian order. * @dst: destination buffer -- cgit v1.2.3 From 421797b1aa363cb897f29f7d365e068dc9d9db81 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 19 Feb 2016 09:24:02 -0500 Subject: net/ethtool: support get coalesce per queue This patch implements sub command ETHTOOL_GCOALESCE for ioctl ETHTOOL_PERQUEUE. It introduces an interface get_per_queue_coalesce to get coalesce of each masked queue from device driver. Then the interrupt coalescing parameters will be copied back to user space one by one. Signed-off-by: Kan Liang Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 8 +++++++- net/core/ethtool.c | 35 ++++++++++++++++++++++++++++++++++- 2 files changed, 41 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 653dc9c4ebac..de56600023a7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -201,6 +201,11 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * @get_module_eeprom: Get the eeprom information from the plug-in module * @get_eee: Get Energy-Efficient (EEE) supported and status. * @set_eee: Set EEE status (enable/disable) as well as LPI timers. + * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue. + * It must check that the given queue number is valid. If neither a RX nor + * a TX queue has this number, return -EINVAL. If only a RX queue or a TX + * queue has this number, set the inapplicable fields to ~0 and return 0. + * Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -279,7 +284,8 @@ struct ethtool_ops { const struct ethtool_tunable *, void *); int (*set_tunable)(struct net_device *, const struct ethtool_tunable *, const void *); - + int (*get_per_queue_coalesce)(struct net_device *, u32, + struct ethtool_coalesce *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d640ecf71e74..2a6c3a26f63f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1888,6 +1888,38 @@ out: return ret; } +static int ethtool_get_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) +{ + u32 bit; + int ret; + DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); + + if (!dev->ethtool_ops->get_per_queue_coalesce) + return -EOPNOTSUPP; + + useraddr += sizeof(*per_queue_opt); + + bitmap_from_u32array(queue_mask, + MAX_NUM_QUEUE, + per_queue_opt->queue_mask, + DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + + for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { + struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; + + ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, &coalesce); + if (ret != 0) + return ret; + if (copy_to_user(useraddr, &coalesce, sizeof(coalesce))) + return -EFAULT; + useraddr += sizeof(coalesce); + } + + return 0; +} + static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) { struct ethtool_per_queue_op per_queue_opt; @@ -1896,7 +1928,8 @@ static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) return -EFAULT; switch (per_queue_opt.sub_command) { - + case ETHTOOL_GCOALESCE: + return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt); default: return -EOPNOTSUPP; }; -- cgit v1.2.3 From f38d138a7da6510a1184e3bc5f425deb187c3265 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 19 Feb 2016 09:24:03 -0500 Subject: net/ethtool: support set coalesce per queue This patch implements sub command ETHTOOL_SCOALESCE for ioctl ETHTOOL_PERQUEUE. It introduces an interface set_per_queue_coalesce to set coalesce of each masked queue to device driver. The wanted coalesce information are stored in "data" for each masked queue, which can copy from userspace. If it fails to set coalesce to device driver, the value which already set to specific queue will be tried to rollback. Signed-off-by: Kan Liang Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 7 ++++++ net/core/ethtool.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de56600023a7..472d7d7b01c2 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -206,6 +206,11 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, set the inapplicable fields to ~0 and return 0. * Returns a negative error code or zero. + * @set_per_queue_coalesce: Set interrupt coalescing parameters per queue. + * It must check that the given queue number is valid. If neither a RX nor + * a TX queue has this number, return -EINVAL. If only a RX queue or a TX + * queue has this number, ignore the inapplicable fields. + * Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -286,6 +291,8 @@ struct ethtool_ops { const struct ethtool_tunable *, const void *); int (*get_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); + int (*set_per_queue_coalesce)(struct net_device *, u32, + struct ethtool_coalesce *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 2a6c3a26f63f..2406101002b1 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1920,6 +1920,65 @@ static int ethtool_get_per_queue_coalesce(struct net_device *dev, return 0; } +static int ethtool_set_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) +{ + u32 bit; + int i, ret = 0; + int n_queue; + struct ethtool_coalesce *backup = NULL, *tmp = NULL; + DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); + + if ((!dev->ethtool_ops->set_per_queue_coalesce) || + (!dev->ethtool_ops->get_per_queue_coalesce)) + return -EOPNOTSUPP; + + useraddr += sizeof(*per_queue_opt); + + bitmap_from_u32array(queue_mask, + MAX_NUM_QUEUE, + per_queue_opt->queue_mask, + DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + n_queue = bitmap_weight(queue_mask, MAX_NUM_QUEUE); + tmp = backup = kmalloc_array(n_queue, sizeof(*backup), GFP_KERNEL); + if (!backup) + return -ENOMEM; + + for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { + struct ethtool_coalesce coalesce; + + ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, tmp); + if (ret != 0) + goto roll_back; + + tmp++; + + if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) { + ret = -EFAULT; + goto roll_back; + } + + ret = dev->ethtool_ops->set_per_queue_coalesce(dev, bit, &coalesce); + if (ret != 0) + goto roll_back; + + useraddr += sizeof(coalesce); + } + +roll_back: + if (ret != 0) { + tmp = backup; + for_each_set_bit(i, queue_mask, bit) { + dev->ethtool_ops->set_per_queue_coalesce(dev, i, tmp); + tmp++; + } + } + kfree(backup); + + return ret; +} + static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) { struct ethtool_per_queue_op per_queue_opt; @@ -1930,6 +1989,8 @@ static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) switch (per_queue_opt.sub_command) { case ETHTOOL_GCOALESCE: return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt); + case ETHTOOL_SCOALESCE: + return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt); default: return -EOPNOTSUPP; }; -- cgit v1.2.3 From 568b329a02f75ed3aaae5eb2cca384cb9e09cb29 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:57 -0800 Subject: perf: generalize perf_callchain . avoid walking the stack when there is no room left in the buffer . generalize get_perf_callchain() to be called from bpf helper Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- arch/x86/include/asm/stacktrace.h | 2 +- arch/x86/kernel/cpu/perf_event.c | 4 ++-- arch/x86/kernel/dumpstack.c | 6 ++++-- arch/x86/kernel/stacktrace.c | 18 +++++++++++------- arch/x86/oprofile/backtrace.c | 3 ++- include/linux/perf_event.h | 13 +++++++++++-- kernel/events/callchain.c | 32 ++++++++++++++++++++------------ kernel/events/internal.h | 2 -- 8 files changed, 51 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 70bbe39043a9..7c247e7404be 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -37,7 +37,7 @@ print_context_stack_bp(struct thread_info *tinfo, /* Generic stack tracer with callbacks */ struct stacktrace_ops { - void (*address)(void *data, unsigned long address, int reliable); + int (*address)(void *data, unsigned long address, int reliable); /* On negative return stop dumping */ int (*stack)(void *data, char *name); walk_stack_t walk_stack; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1b443db2db50..d276b31ca473 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2180,11 +2180,11 @@ static int backtrace_stack(void *data, char *name) return 0; } -static void backtrace_address(void *data, unsigned long addr, int reliable) +static int backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - perf_callchain_store(entry, addr); + return perf_callchain_store(entry, addr); } static const struct stacktrace_ops backtrace_ops = { diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 9c30acfadae2..0d1ff4b407d4 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -135,7 +135,8 @@ print_context_stack_bp(struct thread_info *tinfo, if (!__kernel_text_address(addr)) break; - ops->address(data, addr, 1); + if (ops->address(data, addr, 1)) + break; frame = frame->next_frame; ret_addr = &frame->return_address; print_ftrace_graph_addr(addr, data, ops, tinfo, graph); @@ -154,10 +155,11 @@ static int print_trace_stack(void *data, char *name) /* * Print one address/symbol entries per line. */ -static void print_trace_address(void *data, unsigned long addr, int reliable) +static int print_trace_address(void *data, unsigned long addr, int reliable) { touch_nmi_watchdog(); printk_stack_address(addr, reliable, data); + return 0; } static const struct stacktrace_ops print_trace_ops = { diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index fdd0c6430e5a..9ee98eefc44d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -14,30 +14,34 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void +static int __save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; #ifdef CONFIG_FRAME_POINTER if (!reliable) - return; + return 0; #endif if (nosched && in_sched_functions(addr)) - return; + return 0; if (trace->skip > 0) { trace->skip--; - return; + return 0; } - if (trace->nr_entries < trace->max_entries) + if (trace->nr_entries < trace->max_entries) { trace->entries[trace->nr_entries++] = addr; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static int save_stack_address(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, false); } -static void +static int save_stack_address_nosched(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, true); diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 4e664bdb535a..cb31a4440e58 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -23,12 +23,13 @@ static int backtrace_stack(void *data, char *name) return 0; } -static void backtrace_address(void *data, unsigned long addr, int reliable) +static int backtrace_address(void *data, unsigned long addr, int reliable) { unsigned int *depth = data; if ((*depth)--) oprofile_add_trace(addr); + return 0; } static struct stacktrace_ops backtrace_ops = { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b35a61a481fa..7da3c25999df 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -964,11 +964,20 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs); +extern struct perf_callchain_entry * +get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, + bool crosstask, bool add_mark); +extern int get_callchain_buffers(void); +extern void put_callchain_buffers(void); -static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) +static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) { - if (entry->nr < PERF_MAX_STACK_DEPTH) + if (entry->nr < PERF_MAX_STACK_DEPTH) { entry->ip[entry->nr++] = ip; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } extern int sysctl_perf_event_paranoid; diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 9c418002b8c1..343c22f5e867 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -159,15 +159,24 @@ put_callchain_entry(int rctx) struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { - int rctx; - struct perf_callchain_entry *entry; - - int kernel = !event->attr.exclude_callchain_kernel; - int user = !event->attr.exclude_callchain_user; + bool kernel = !event->attr.exclude_callchain_kernel; + bool user = !event->attr.exclude_callchain_user; + /* Disallow cross-task user callchains. */ + bool crosstask = event->ctx->task && event->ctx->task != current; if (!kernel && !user) return NULL; + return get_perf_callchain(regs, 0, kernel, user, crosstask, true); +} + +struct perf_callchain_entry * +get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, + bool crosstask, bool add_mark) +{ + struct perf_callchain_entry *entry; + int rctx; + entry = get_callchain_entry(&rctx); if (rctx == -1) return NULL; @@ -175,10 +184,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) if (!entry) goto exit_put; - entry->nr = 0; + entry->nr = init_nr; if (kernel && !user_mode(regs)) { - perf_callchain_store(entry, PERF_CONTEXT_KERNEL); + if (add_mark) + perf_callchain_store(entry, PERF_CONTEXT_KERNEL); perf_callchain_kernel(entry, regs); } @@ -191,13 +201,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) } if (regs) { - /* - * Disallow cross-task user callchains. - */ - if (event->ctx->task && event->ctx->task != current) + if (crosstask) goto exit_put; - perf_callchain_store(entry, PERF_CONTEXT_USER); + if (add_mark) + perf_callchain_store(entry, PERF_CONTEXT_USER); perf_callchain_user(entry, regs); } } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 2bbad9c1274c..4199b6d193f5 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -182,8 +182,6 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) /* Callchain handling */ extern struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs); -extern int get_callchain_buffers(void); -extern void put_callchain_buffers(void); static inline int get_recursion_context(int *recursion) { -- cgit v1.2.3 From d5a3b1f691865be576c2bffa708549b8cdccda19 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:58 -0800 Subject: bpf: introduce BPF_MAP_TYPE_STACK_TRACE add new map type to store stack traces and corresponding helper bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id @ctx: struct pt_regs* @map: pointer to stack_trace map @flags: bits 0-7 - numer of stack frames to skip bit 8 - collect user stack instead of kernel bit 9 - compare stacks by hash only bit 10 - if two different stacks hash into the same stackid discard old other bits - reserved Return: >= 0 stackid on success or negative error stackid is a 32-bit integer handle that can be further combined with other data (including other stackid) and used as a key into maps. Userspace will access stackmap using standard lookup/delete syscall commands to retrieve full stack trace for given stackid. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 21 +++++ kernel/bpf/Makefile | 3 + kernel/bpf/stackmap.c | 237 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 6 +- kernel/trace/bpf_trace.c | 2 + 6 files changed, 269 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/stackmap.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 90ee6ab24bc5..0cadbb7456c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -237,6 +237,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; +extern const struct bpf_func_proto bpf_get_stackid_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2ee0fde1bf96..d3e77da8e9e8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -83,6 +83,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, }; enum bpf_prog_type { @@ -272,6 +273,20 @@ enum bpf_func_id { */ BPF_FUNC_perf_event_output, BPF_FUNC_skb_load_bytes, + + /** + * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + */ + BPF_FUNC_get_stackid, __BPF_FUNC_MAX_ID, }; @@ -294,6 +309,12 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) +/* BPF_FUNC_get_stackid flags. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 13272582eee0..8a932d079c24 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,3 +2,6 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o +ifeq ($(CONFIG_PERF_EVENTS),y) +obj-$(CONFIG_BPF_SYSCALL) += stackmap.o +endif diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c new file mode 100644 index 000000000000..8a60ee14a977 --- /dev/null +++ b/kernel/bpf/stackmap.c @@ -0,0 +1,237 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include + +struct stack_map_bucket { + struct rcu_head rcu; + u32 hash; + u32 nr; + u64 ip[]; +}; + +struct bpf_stack_map { + struct bpf_map map; + u32 n_buckets; + struct stack_map_bucket __rcu *buckets[]; +}; + +/* Called from syscall */ +static struct bpf_map *stack_map_alloc(union bpf_attr *attr) +{ + u32 value_size = attr->value_size; + struct bpf_stack_map *smap; + u64 cost, n_buckets; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + value_size < 8 || value_size % 8 || + value_size / 8 > PERF_MAX_STACK_DEPTH) + return ERR_PTR(-EINVAL); + + /* hash table size must be power of 2 */ + n_buckets = roundup_pow_of_two(attr->max_entries); + + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); + if (!smap) { + smap = vzalloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); + } + + err = -E2BIG; + cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_smap; + + smap->map.map_type = attr->map_type; + smap->map.key_size = attr->key_size; + smap->map.value_size = value_size; + smap->map.max_entries = attr->max_entries; + smap->n_buckets = n_buckets; + smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + err = get_callchain_buffers(); + if (err) + goto free_smap; + + return &smap->map; + +free_smap: + kvfree(smap); + return ERR_PTR(err); +} + +static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +{ + struct pt_regs *regs = (struct pt_regs *) (long) r1; + struct bpf_map *map = (struct bpf_map *) (long) r2; + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct perf_callchain_entry *trace; + struct stack_map_bucket *bucket, *new_bucket, *old_bucket; + u32 max_depth = map->value_size / 8; + /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */ + u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 hash, id, trace_nr, trace_len; + bool user = flags & BPF_F_USER_STACK; + bool kernel = !user; + u64 *ips; + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) + return -EINVAL; + + trace = get_perf_callchain(regs, init_nr, kernel, user, false, false); + + if (unlikely(!trace)) + /* couldn't fetch the stack trace */ + return -EFAULT; + + /* get_perf_callchain() guarantees that trace->nr >= init_nr + * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth + */ + trace_nr = trace->nr - init_nr; + + if (trace_nr <= skip) + /* skipping more than usable stack trace */ + return -EFAULT; + + trace_nr -= skip; + trace_len = trace_nr * sizeof(u64); + ips = trace->ip + skip + init_nr; + hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); + id = hash & (smap->n_buckets - 1); + bucket = rcu_dereference(smap->buckets[id]); + + if (bucket && bucket->hash == hash) { + if (flags & BPF_F_FAST_STACK_CMP) + return id; + if (bucket->nr == trace_nr && + memcmp(bucket->ip, ips, trace_len) == 0) + return id; + } + + /* this call stack is not in the map, try to add it */ + if (bucket && !(flags & BPF_F_REUSE_STACKID)) + return -EEXIST; + + new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!new_bucket)) + return -ENOMEM; + + memcpy(new_bucket->ip, ips, trace_len); + memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len); + new_bucket->hash = hash; + new_bucket->nr = trace_nr; + + old_bucket = xchg(&smap->buckets[id], new_bucket); + if (old_bucket) + kfree_rcu(old_bucket, rcu); + return id; +} + +const struct bpf_func_proto bpf_get_stackid_proto = { + .func = bpf_get_stackid, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +/* Called from syscall or from eBPF program */ +static void *stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return NULL; + bucket = rcu_dereference(smap->buckets[id]); + return bucket ? bucket->ip : NULL; +} + +static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EINVAL; +} + +static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int stack_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *old_bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return -E2BIG; + + old_bucket = xchg(&smap->buckets[id], NULL); + if (old_bucket) { + kfree_rcu(old_bucket, rcu); + return 0; + } else { + return -ENOENT; + } +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void stack_map_free(struct bpf_map *map) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + int i; + + synchronize_rcu(); + + for (i = 0; i < smap->n_buckets; i++) + if (smap->buckets[i]) + kfree_rcu(smap->buckets[i], rcu); + kvfree(smap); + put_callchain_buffers(); +} + +static const struct bpf_map_ops stack_map_ops = { + .map_alloc = stack_map_alloc, + .map_free = stack_map_free, + .map_get_next_key = stack_map_get_next_key, + .map_lookup_elem = stack_map_lookup_elem, + .map_update_elem = stack_map_update_elem, + .map_delete_elem = stack_map_delete_elem, +}; + +static struct bpf_map_type_list stack_map_type __read_mostly = { + .ops = &stack_map_ops, + .type = BPF_MAP_TYPE_STACK_TRACE, +}; + +static int __init register_stack_map(void) +{ + bpf_register_map_type(&stack_map_type); + return 0; +} +late_initcall(register_stack_map); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d1d3e8f57de9..42ba4ccc020b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -246,6 +246,7 @@ static const struct { {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, + {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid}, }; static void print_verifier_state(struct verifier_env *env) @@ -911,8 +912,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) * don't allow any other map type to be passed into * the special func; */ - if (bool_func && bool_map != bool_func) + if (bool_func && bool_map != bool_func) { + verbose("cannot pass map_type %d into func %d\n", + map->map_type, func_id); return -EINVAL; + } } return 0; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 326a75e884db..4b8caa392b86 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -299,6 +299,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_read_proto; case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; + case BPF_FUNC_get_stackid: + return &bpf_get_stackid_proto; default: return NULL; } -- cgit v1.2.3 From 8e2fe1d9f1a20924f98ea46931a1d7fb092aa876 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:22 +0100 Subject: bpf: add new arg_type that allows for 0 sized stack buffer Currently, when we pass a buffer from the eBPF stack into a helper function, the function proto indicates argument types as ARG_PTR_TO_STACK and ARG_CONST_STACK_SIZE pair. If R contains the former, then R must be of the latter type. Then, verifier checks whether the buffer points into eBPF stack, is initialized, etc. The verifier also guarantees that the constant value passed in R is greater than 0, so helper functions don't need to test for it and can always assume a non-NULL initialized buffer as well as non-0 buffer size. This patch adds a new argument types ARG_CONST_STACK_SIZE_OR_ZERO that allows to also pass NULL as R and 0 as R into the helper function. Such helper functions, of course, need to be able to handle these cases internally then. Verifier guarantees that either R == NULL && R == 0 or R != NULL && R != 0 (like the case of ARG_CONST_STACK_SIZE), any other combinations are not possible to load. I went through various options of extending the verifier, and introducing the type ARG_CONST_STACK_SIZE_OR_ZERO seems to have most minimal changes needed to the verifier. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 42 ++++++++++++++++++++++++++++++++---------- 2 files changed, 33 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0cadbb7456c0..51e498e5470e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -65,6 +65,7 @@ enum bpf_arg_type { */ ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ + ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 42ba4ccc020b..36dc497deaa3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -779,15 +779,24 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) * bytes from that pointer, make sure that it's within stack boundary * and all elements of stack are initialized */ -static int check_stack_boundary(struct verifier_env *env, - int regno, int access_size) +static int check_stack_boundary(struct verifier_env *env, int regno, + int access_size, bool zero_size_allowed) { struct verifier_state *state = &env->cur_state; struct reg_state *regs = state->regs; int off, i; - if (regs[regno].type != PTR_TO_STACK) + if (regs[regno].type != PTR_TO_STACK) { + if (zero_size_allowed && access_size == 0 && + regs[regno].type == CONST_IMM && + regs[regno].imm == 0) + return 0; + + verbose("R%d type=%s expected=%s\n", regno, + reg_type_str[regs[regno].type], + reg_type_str[PTR_TO_STACK]); return -EACCES; + } off = regs[regno].imm; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || @@ -830,15 +839,24 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return 0; } - if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || + if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - } else if (arg_type == ARG_CONST_STACK_SIZE) { + } else if (arg_type == ARG_CONST_STACK_SIZE || + arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) { expected_type = CONST_IMM; } else if (arg_type == ARG_CONST_MAP_PTR) { expected_type = CONST_PTR_TO_MAP; } else if (arg_type == ARG_PTR_TO_CTX) { expected_type = PTR_TO_CTX; + } else if (arg_type == ARG_PTR_TO_STACK) { + expected_type = PTR_TO_STACK; + /* One exception here. In case function allows for NULL to be + * passed in as argument, it's a CONST_IMM type. Final test + * happens during stack boundary checking. + */ + if (reg->type == CONST_IMM && reg->imm == 0) + expected_type = CONST_IMM; } else { verbose("unsupported arg_type %d\n", arg_type); return -EFAULT; @@ -868,8 +886,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - err = check_stack_boundary(env, regno, (*mapp)->key_size); - + err = check_stack_boundary(env, regno, (*mapp)->key_size, + false); } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -879,9 +897,12 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - err = check_stack_boundary(env, regno, (*mapp)->value_size); + err = check_stack_boundary(env, regno, (*mapp)->value_size, + false); + } else if (arg_type == ARG_CONST_STACK_SIZE || + arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) { + bool zero_size_allowed = (arg_type == ARG_CONST_STACK_SIZE_OR_ZERO); - } else if (arg_type == ARG_CONST_STACK_SIZE) { /* bpf_xxx(..., buf, len) call will access 'len' bytes * from stack pointer 'buf'. Check it * note: regno == len, regno - 1 == buf @@ -891,7 +912,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("ARG_CONST_STACK_SIZE cannot be first argument\n"); return -EACCES; } - err = check_stack_boundary(env, regno - 1, reg->imm); + err = check_stack_boundary(env, regno - 1, reg->imm, + zero_size_allowed); } return err; -- cgit v1.2.3 From 3697649ff29e0f647565eed04b27a7779c646a22 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:25 +0100 Subject: bpf: try harder on clones when writing into skb When we're dealing with clones and the area is not writeable, try harder and get a copy via pskb_expand_head(). Replace also other occurences in tc actions with the new skb_try_make_writable(). Reported-by: Ashhad Sheikh Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 +++++++ net/core/filter.c | 19 ++++++++++--------- net/sched/act_csum.c | 8 ++------ net/sched/act_nat.c | 18 +++++------------- 4 files changed, 24 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 89b536796e53..6a57757a86cf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2630,6 +2630,13 @@ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len skb_headroom(skb) + len <= skb->hdr_len; } +static inline int skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC); +} + static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { diff --git a/net/core/filter.c b/net/core/filter.c index ea391e6be7fa..f031b82128f3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1364,9 +1364,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) */ if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff))) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + len))) + if (unlikely(skb_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb_header_pointer(skb, offset, len, sp->buff); @@ -1439,9 +1437,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; if (unlikely((u32) offset > 0xffff)) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1488,9 +1484,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; if (unlikely((u32) offset > 0xffff)) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1734,6 +1728,13 @@ bool bpf_helper_changes_skb_data(void *func) return true; if (func == bpf_skb_vlan_pop) return true; + if (func == bpf_skb_store_bytes) + return true; + if (func == bpf_l3_csum_replace) + return true; + if (func == bpf_l4_csum_replace) + return true; + return false; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b07c535ba8e7..eeb3eb3ea9eb 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -105,9 +105,7 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb, int hl = ihl + jhl; if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) || - (skb_cloned(skb) && - !skb_clone_writable(skb, hl + ntkoff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + skb_try_make_writable(skb, hl + ntkoff)) return NULL; else return (void *)(skb_network_header(skb) + ihl); @@ -365,9 +363,7 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) } if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) { - if (skb_cloned(skb) && - !skb_clone_writable(skb, sizeof(*iph) + ntkoff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff)) goto fail; ip_send_check(ip_hdr(skb)); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index b7c4ead8b5a8..27607b863aba 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -126,9 +126,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, addr = iph->daddr; if (!((old_addr ^ addr) & mask)) { - if (skb_cloned(skb) && - !skb_clone_writable(skb, sizeof(*iph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_try_make_writable(skb, sizeof(*iph) + noff)) goto drop; new_addr &= mask; @@ -156,9 +154,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, struct tcphdr *tcph; if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) || - (skb_cloned(skb) && - !skb_clone_writable(skb, ihl + sizeof(*tcph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff)) goto drop; tcph = (void *)(skb_network_header(skb) + ihl); @@ -171,9 +167,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, struct udphdr *udph; if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) || - (skb_cloned(skb) && - !skb_clone_writable(skb, ihl + sizeof(*udph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + skb_try_make_writable(skb, ihl + sizeof(*udph) + noff)) goto drop; udph = (void *)(skb_network_header(skb) + ihl); @@ -213,10 +207,8 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, if ((old_addr ^ addr) & mask) break; - if (skb_cloned(skb) && - !skb_clone_writable(skb, ihl + sizeof(*icmph) + - sizeof(*iph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_try_make_writable(skb, ihl + sizeof(*icmph) + + sizeof(*iph) + noff)) goto drop; icmph = (void *)(skb_network_header(skb) + ihl); -- cgit v1.2.3 From 944945986f125bdbbeaa78dac0c0eadb963eb34a Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 11:40:10 +0200 Subject: qed: Introduce DMA_REGPAIR_LE FW hsi contains regpairs, mostly for 64-bit address representations. Since same paradigm is applied each time a regpair is filled, this introduces a new utility macro for setting such regpairs. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 9 +++------ drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 12 ++++-------- drivers/net/ethernet/qlogic/qed/qed_spq.c | 9 +++------ include/linux/qed/qed_chain.h | 4 ++++ 4 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 8d1bc7e7e996..bba59c51f72c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -557,12 +557,10 @@ qed_sp_eth_rxq_start_ramrod(struct qed_hwfn *p_hwfn, p_ramrod->complete_event_flg = 1; p_ramrod->bd_max_bytes = cpu_to_le16(bd_max_bytes); - p_ramrod->bd_base.hi = DMA_HI_LE(bd_chain_phys_addr); - p_ramrod->bd_base.lo = DMA_LO_LE(bd_chain_phys_addr); + DMA_REGPAIR_LE(p_ramrod->bd_base, bd_chain_phys_addr); p_ramrod->num_of_pbl_pages = cpu_to_le16(cqe_pbl_size); - p_ramrod->cqe_pbl_addr.hi = DMA_HI_LE(cqe_pbl_addr); - p_ramrod->cqe_pbl_addr.lo = DMA_LO_LE(cqe_pbl_addr); + DMA_REGPAIR_LE(p_ramrod->cqe_pbl_addr, cqe_pbl_addr); rc = qed_spq_post(p_hwfn, p_ent, NULL); @@ -721,8 +719,7 @@ qed_sp_eth_txq_start_ramrod(struct qed_hwfn *p_hwfn, p_ramrod->stats_counter_id = stats_id; p_ramrod->pbl_size = cpu_to_le16(pbl_size); - p_ramrod->pbl_base_addr.hi = DMA_HI_LE(pbl_addr); - p_ramrod->pbl_base_addr.lo = DMA_LO_LE(pbl_addr); + DMA_REGPAIR_LE(p_ramrod->pbl_base_addr, pbl_addr); pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index e271ef95745c..1c06c37d4c3d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -136,16 +136,12 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->outer_tag = p_hwfn->hw_info.ovlan; /* Place EQ address in RAMROD */ - p_ramrod->event_ring_pbl_addr.hi = - DMA_HI_LE(p_hwfn->p_eq->chain.pbl.p_phys_table); - p_ramrod->event_ring_pbl_addr.lo = - DMA_LO_LE(p_hwfn->p_eq->chain.pbl.p_phys_table); + DMA_REGPAIR_LE(p_ramrod->event_ring_pbl_addr, + p_hwfn->p_eq->chain.pbl.p_phys_table); p_ramrod->event_ring_num_pages = (u8)p_hwfn->p_eq->chain.page_cnt; - p_ramrod->consolid_q_pbl_addr.hi = - DMA_HI_LE(p_hwfn->p_consq->chain.pbl.p_phys_table); - p_ramrod->consolid_q_pbl_addr.lo = - DMA_LO_LE(p_hwfn->p_consq->chain.pbl.p_phys_table); + DMA_REGPAIR_LE(p_ramrod->consolid_q_pbl_addr, + p_hwfn->p_consq->chain.pbl.p_phys_table); p_hwfn->hw_info.personality = PERSONALITY_ETH; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index f6c6c21601d7..89469d5aae25 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -183,10 +183,8 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, p_cxt->xstorm_st_context.spq_base_hi = DMA_HI_LE(p_spq->chain.p_phys_addr); - p_cxt->xstorm_st_context.consolid_base_addr.lo = - DMA_LO_LE(p_hwfn->p_consq->chain.p_phys_addr); - p_cxt->xstorm_st_context.consolid_base_addr.hi = - DMA_HI_LE(p_hwfn->p_consq->chain.p_phys_addr); + DMA_REGPAIR_LE(p_cxt->xstorm_st_context.consolid_base_addr, + p_hwfn->p_consq->chain.p_phys_addr); } static int qed_spq_hw_post(struct qed_hwfn *p_hwfn, @@ -423,8 +421,7 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn) p_virt = p_spq->p_virt; for (i = 0; i < p_spq->chain.capacity; i++) { - p_virt->elem.data_ptr.hi = DMA_HI_LE(p_phys); - p_virt->elem.data_ptr.lo = DMA_LO_LE(p_phys); + DMA_REGPAIR_LE(p_virt->elem.data_ptr, p_phys); list_add_tail(&p_virt->list, &p_spq->free_pool); diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 41b9049b57e2..5f8fcaaa6504 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -19,6 +19,10 @@ /* dma_addr_t manip */ #define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x)) #define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x)) +#define DMA_REGPAIR_LE(x, val) do { \ + (x).hi = DMA_HI_LE((val)); \ + (x).lo = DMA_LO_LE((val)); \ + } while (0) #define HILO_GEN(hi, lo, type) ((((type)(hi)) << 32) + (lo)) #define HILO_DMA(hi, lo) HILO_GEN(hi, lo, dma_addr_t) -- cgit v1.2.3 From 506bcfa8abebdbcebdc17b03e96e38dc0b8ce765 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 13 Dec 2015 15:41:05 +0200 Subject: mac80211: limit the A-MSDU Tx based on peer's capabilities In VHT, the specification allows to limit the number of MSDUs in an A-MSDU in the Extended Capabilities IE. There is also a limitation on the byte size in the VHT IE. In HT, the only limitation is on the byte size. Parse the capabilities from the peer and make them available to the driver. In HT, there is another limitation when a BA agreement is active: the byte size can't be greater than 4095. This is not enforced here. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 19 +++++++++++++++++++ include/net/mac80211.h | 14 ++++++++++++++ net/mac80211/cfg.c | 29 +++++++++++++++++++++++++++++ net/mac80211/ht.c | 5 +++++ net/mac80211/vht.c | 17 +++++++++++++++++ 5 files changed, 84 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9ddb89533a7..3b1f6cef9513 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -163,6 +163,14 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 +/* Maximal size of an A-MSDU */ +#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 +#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 + +#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 +#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 +#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 + #define IEEE80211_MAX_SSID_LEN 32 #define IEEE80211_MAX_MESH_ID_LEN 32 @@ -1505,6 +1513,7 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 +#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C @@ -2086,6 +2095,16 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) +/* Defines the maximal number of MSDUs in an A-MSDU. */ +#define WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB BIT(7) +#define WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB BIT(0) + +/* + * Fine Timing Measurement Initiator - bit 71 of @WLAN_EID_EXT_CAPABILITY + * information element + */ +#define WLAN_EXT_CAPA9_FTM_INITIATOR BIT(7) + /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5910085af9e6..df5698ed8052 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1714,6 +1714,18 @@ struct ieee80211_sta_rates { * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. * @mfp: indicates whether the STA uses management frame protection or not. + * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single + * A-MSDU. Taken from the Extended Capabilities element. 0 means + * unlimited. + * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. This + * field is always valid for packets with a VHT preamble. For packets + * with a HT preamble, additional limits apply: + * + If the skb is transmitted as part of a BA agreement, the + * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. + * + If the skb is not part of a BA aggreement, the A-MSDU maximal + * size is min(max_amsdu_len, 7935) bytes. + * Both additional HT limits must be enforced by the low level driver. + * This is defined by the spec (IEEE 802.11-2012 section 8.3.2.2 NOTE 2). * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { @@ -1732,6 +1744,8 @@ struct ieee80211_sta { bool tdls; bool tdls_initiator; bool mfp; + u8 max_amsdu_subframes; + u16 max_amsdu_len; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 166a29fe6c35..66d22de93c8d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1131,6 +1131,34 @@ static int sta_apply_parameters(struct ieee80211_local *local, sta->sta.max_sp = params->max_sp; } + /* The sender might not have sent the last bit, consider it to be 0 */ + if (params->ext_capab_len >= 8) { + u8 val = (params->ext_capab[7] & + WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB) >> 7; + + /* we did get all the bits, take the MSB as well */ + if (params->ext_capab_len >= 9) { + u8 val_msb = params->ext_capab[8] & + WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB; + val_msb <<= 1; + val |= val_msb; + } + + switch (val) { + case 1: + sta->sta.max_amsdu_subframes = 32; + break; + case 2: + sta->sta.max_amsdu_subframes = 16; + break; + case 3: + sta->sta.max_amsdu_subframes = 8; + break; + default: + sta->sta.max_amsdu_subframes = 0; + } + } + /* * cfg80211 validates this (1-2007) and allows setting the AID * only when creating a new station entry @@ -1160,6 +1188,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, params->ht_capa, sta); + /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, sta); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 7a76ce639d58..f4a528773563 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -230,6 +230,11 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, /* set Rx highest rate */ ht_cap.mcs.rx_highest = ht_cap_ie->mcs.rx_highest; + if (ht_cap.cap & IEEE80211_HT_CAP_MAX_AMSDU) + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_7935; + else + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_3839; + apply: changed = memcmp(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap)); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 050de08bf82e..204cf9ad3019 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -281,6 +281,23 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, } sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); + + /* If HT IE reported 3839 bytes only, stay with that size. */ + if (sta->sta.max_amsdu_len == IEEE80211_MAX_MPDU_LEN_HT_3839) + return; + + switch (vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK) { + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454; + break; + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_7991; + break; + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895: + default: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_3895; + break; + } } enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta) -- cgit v1.2.3 From dd21dfc645d5dce0657af78761b3fa11a3a95398 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jan 2016 10:39:23 +0100 Subject: rfkill: disentangle polling pause and suspend When suspended while polling is paused, polling will erroneously resume at resume time. Fix this by tracking pause and suspend in separate state variable and adding the necessary checks. Clarify the documentation on this as well. Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 3 ++- net/rfkill/core.c | 17 +++++++++++++++-- 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index d9010789b4e8..7af625f6d226 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -104,7 +104,8 @@ int __must_check rfkill_register(struct rfkill *rfkill); * * Pause polling -- say transmitter is off for other reasons. * NOTE: not necessary for suspend/resume -- in that case the - * core stops polling anyway + * core stops polling anyway (but will also correctly handle + * the case of polling having been paused before suspend.) */ void rfkill_pause_polling(struct rfkill *rfkill); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f53bf3b6558b..166439995f34 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -57,6 +57,8 @@ struct rfkill { bool registered; bool persistent; + bool polling_paused; + bool suspended; const struct rfkill_ops *ops; void *data; @@ -786,6 +788,7 @@ void rfkill_pause_polling(struct rfkill *rfkill) if (!rfkill->ops->poll) return; + rfkill->polling_paused = true; cancel_delayed_work_sync(&rfkill->poll_work); } EXPORT_SYMBOL(rfkill_pause_polling); @@ -797,6 +800,11 @@ void rfkill_resume_polling(struct rfkill *rfkill) if (!rfkill->ops->poll) return; + rfkill->polling_paused = false; + + if (rfkill->suspended) + return; + queue_delayed_work(system_power_efficient_wq, &rfkill->poll_work, 0); } @@ -807,7 +815,8 @@ static int rfkill_suspend(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); - rfkill_pause_polling(rfkill); + rfkill->suspended = true; + cancel_delayed_work_sync(&rfkill->poll_work); return 0; } @@ -817,12 +826,16 @@ static int rfkill_resume(struct device *dev) struct rfkill *rfkill = to_rfkill(dev); bool cur; + rfkill->suspended = false; + if (!rfkill->persistent) { cur = !!(rfkill->state & RFKILL_BLOCK_SW); rfkill_set_block(rfkill, cur); } - rfkill_resume_polling(rfkill); + if (rfkill->ops->poll && !rfkill->polling_paused) + queue_delayed_work(system_power_efficient_wq, + &rfkill->poll_work, 0); return 0; } -- cgit v1.2.3 From 648b50dd6abf8e6e5b589bb8e6873a4596389dbe Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Jan 2016 12:03:46 +0300 Subject: net: rfkill: add rfkill_find_type function Helper for finding the type based on name. Useful if the type needs to be determined based on device property. Signed-off-by: Heikki Krogerus [modify rfkill_types array and BUILD_BUG_ON to not cause errors] Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 15 +++++++++++++ net/rfkill/core.c | 58 ++++++++++++++++++++++++++------------------------ 2 files changed, 45 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 7af625f6d226..e6a0031d1b1f 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -213,6 +213,15 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); * @rfkill: rfkill struct to query */ bool rfkill_blocked(struct rfkill *rfkill); + +/** + * rfkill_find_type - Helpper for finding rfkill type by name + * @name: the name of the type + * + * Returns enum rfkill_type that conrresponds the name. + */ +enum rfkill_type rfkill_find_type(const char *name); + #else /* !RFKILL */ static inline struct rfkill * __must_check rfkill_alloc(const char *name, @@ -269,6 +278,12 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) { return false; } + +static inline enum rfkill_type rfkill_find_type(const char *name) +{ + return RFKILL_TYPE_ALL; +} + #endif /* RFKILL || RFKILL_MODULE */ diff --git a/net/rfkill/core.c b/net/rfkill/core.c index a805831d5d9b..2a23479a49f2 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -572,6 +572,34 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw) } EXPORT_SYMBOL(rfkill_set_states); +static const char * const rfkill_types[] = { + NULL, /* RFKILL_TYPE_ALL */ + "wlan", + "bluetooth", + "ultrawideband", + "wimax", + "wwan", + "gps", + "fm", + "nfc", +}; + +enum rfkill_type rfkill_find_type(const char *name) +{ + int i; + + BUILD_BUG_ON(ARRAY_SIZE(rfkill_types) != NUM_RFKILL_TYPES); + + if (!name) + return RFKILL_TYPE_ALL; + + for (i = 1; i < NUM_RFKILL_TYPES; i++) + if (!strcmp(name, rfkill_types[i])) + return i; + return RFKILL_TYPE_ALL; +} +EXPORT_SYMBOL(rfkill_find_type); + static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -581,38 +609,12 @@ static ssize_t name_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(name); -static const char *rfkill_get_type_str(enum rfkill_type type) -{ - BUILD_BUG_ON(NUM_RFKILL_TYPES != RFKILL_TYPE_NFC + 1); - - switch (type) { - case RFKILL_TYPE_WLAN: - return "wlan"; - case RFKILL_TYPE_BLUETOOTH: - return "bluetooth"; - case RFKILL_TYPE_UWB: - return "ultrawideband"; - case RFKILL_TYPE_WIMAX: - return "wimax"; - case RFKILL_TYPE_WWAN: - return "wwan"; - case RFKILL_TYPE_GPS: - return "gps"; - case RFKILL_TYPE_FM: - return "fm"; - case RFKILL_TYPE_NFC: - return "nfc"; - default: - BUG(); - } -} - static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); - return sprintf(buf, "%s\n", rfkill_get_type_str(rfkill->type)); + return sprintf(buf, "%s\n", rfkill_types[rfkill->type]); } static DEVICE_ATTR_RO(type); @@ -750,7 +752,7 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env) if (error) return error; error = add_uevent_var(env, "RFKILL_TYPE=%s", - rfkill_get_type_str(rfkill->type)); + rfkill_types[rfkill->type]); if (error) return error; spin_lock_irqsave(&rfkill->lock, flags); -- cgit v1.2.3 From fb2e6b7b7b02ab35a9d5355a69097a6f60c69d38 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Jan 2016 12:03:49 +0300 Subject: net: rfkill: gpio: remove rfkill_gpio_platform_data No more users for it. Signed-off-by: Heikki Krogerus Signed-off-by: Johannes Berg --- include/linux/rfkill-gpio.h | 37 ------------------------------------- net/rfkill/Kconfig | 3 +-- net/rfkill/rfkill-gpio.c | 8 -------- 3 files changed, 1 insertion(+), 47 deletions(-) delete mode 100644 include/linux/rfkill-gpio.h (limited to 'include/linux') diff --git a/include/linux/rfkill-gpio.h b/include/linux/rfkill-gpio.h deleted file mode 100644 index 20bcb55498cd..000000000000 --- a/include/linux/rfkill-gpio.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Copyright (c) 2011, NVIDIA Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - */ - - -#ifndef __RFKILL_GPIO_H -#define __RFKILL_GPIO_H - -#include -#include - -/** - * struct rfkill_gpio_platform_data - platform data for rfkill gpio device. - * for unused gpio's, the expected value is -1. - * @name: name for the gpio rf kill instance - */ - -struct rfkill_gpio_platform_data { - char *name; - enum rfkill_type type; -}; - -#endif /* __RFKILL_GPIO_H */ diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig index 598d374f6a35..868f1ad0415a 100644 --- a/net/rfkill/Kconfig +++ b/net/rfkill/Kconfig @@ -41,5 +41,4 @@ config RFKILL_GPIO default n help If you say yes here you get support of a generic gpio RFKILL - driver. The platform should fill in the appropriate fields in the - rfkill_gpio_platform_data structure and pass that to the driver. + driver. diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 1a9c0316aad1..76c01cbd56e3 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -27,8 +27,6 @@ #include #include -#include - struct rfkill_gpio_data { const char *name; enum rfkill_type type; @@ -89,7 +87,6 @@ static int rfkill_gpio_acpi_probe(struct device *dev, static int rfkill_gpio_probe(struct platform_device *pdev) { - struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data; struct rfkill_gpio_data *rfkill; struct gpio_desc *gpio; const char *type_name; @@ -111,11 +108,6 @@ static int rfkill_gpio_probe(struct platform_device *pdev) ret = rfkill_gpio_acpi_probe(&pdev->dev, rfkill); if (ret) return ret; - } else if (pdata) { - rfkill->name = pdata->name; - rfkill->type = pdata->type; - } else { - return -ENODEV; } rfkill->clk = devm_clk_get(&pdev->dev, NULL); -- cgit v1.2.3 From ada68c31ba9c02d7aabdd87db979fe670b499d54 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Mon, 22 Feb 2016 18:17:23 +0200 Subject: net/mlx5: Introduce a new header file for physical port functions All the device physical port access functions are implemented in the port.c file. We just extract the exposure of these functions from driver.h into a dedicated header file called port.h. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx5/main.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/port.c | 1 + include/linux/mlx5/driver.h | 31 ------------ include/linux/mlx5/port.h | 69 ++++++++++++++++++++++++++ 5 files changed, 72 insertions(+), 31 deletions(-) create mode 100644 include/linux/mlx5/port.h (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 03c418ccbc98..e1cea4415704 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index aac071a7e830..15f6cdb842d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include "wq.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index a87e773e93f3..1e863216ac4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -32,6 +32,7 @@ #include #include +#include #include #include "mlx5_core.h" diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1e3006dcf35d..02adc67720ce 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -794,37 +794,6 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); -int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, - int ptys_size, int proto_mask, u8 local_port); -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask); -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask); -int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, - u8 *link_width_oper, u8 local_port); -int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, - u8 *proto_oper, int proto_mask, - u8 local_port); -int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, - int proto_mask); -int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status); -int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status *status); - -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, - u8 port); - -int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, - u8 *vl_hw_cap, u8 local_port); - -int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); -int mlx5_query_port_pause(struct mlx5_core_dev *dev, - u32 *rx_pause, u32 *tx_pause); - int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h new file mode 100644 index 000000000000..7accd4a65da5 --- /dev/null +++ b/include/linux/mlx5/port.h @@ -0,0 +1,69 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_PORT_H__ +#define __MLX5_PORT_H__ + +#include + +int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); +int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, + int ptys_size, int proto_mask, u8 local_port); +int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, + u32 *proto_cap, int proto_mask); +int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, + u32 *proto_admin, int proto_mask); +int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, + u8 *link_width_oper, u8 local_port); +int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, + u8 *proto_oper, int proto_mask, + u8 local_port); +int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, + int proto_mask); +int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status *status); + +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, + u8 port); + +int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, + u8 *vl_hw_cap, u8 local_port); + +int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); +int mlx5_query_port_pause(struct mlx5_core_dev *dev, + u32 *rx_pause, u32 *tx_pause); + +#endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From ad909eb064219a64fd10e9c7d9f39a3042760025 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Mon, 22 Feb 2016 18:17:24 +0200 Subject: net/mlx5: Introduce physical port PFC access functions Add access functions to set and query a physical port PFC (Priority Flow Control) parameters. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/port.c | 41 ++++++++++++++++++++++++++ include/linux/mlx5/port.h | 4 +++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 1e863216ac4a..dae70500b6a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -364,3 +364,44 @@ int mlx5_query_port_pause(struct mlx5_core_dev *dev, return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_pause); + +int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + MLX5_SET(pfcc_reg, in, pfctx, pfc_en_tx); + MLX5_SET(pfcc_reg, in, pfcrx, pfc_en_rx); + MLX5_SET_TO_ONES(pfcc_reg, in, prio_mask_tx); + MLX5_SET_TO_ONES(pfcc_reg, in, prio_mask_rx); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 1); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_pfc); + +int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + int err; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 0); + if (err) + return err; + + if (pfc_en_tx) + *pfc_en_tx = MLX5_GET(pfcc_reg, out, pfctx); + + if (pfc_en_rx) + *pfc_en_rx = MLX5_GET(pfcc_reg, out, pfcrx); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 7accd4a65da5..4b3644caa936 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -66,4 +66,8 @@ int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); int mlx5_query_port_pause(struct mlx5_core_dev *dev, u32 *rx_pause, u32 *tx_pause); +int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); +int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, + u8 *pfc_en_rx); + #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 4f3961eeafe0aca8f6b0933899ef0d91f561352d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 22 Feb 2016 18:17:25 +0200 Subject: net/mlx5: Introduce physical port TC/prio access functions Add access functions to set and query a physical port TC groups and prio parameters. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/port.c | 76 ++++++++++++++++++++++++++ include/linux/mlx5/driver.h | 2 + include/linux/mlx5/mlx5_ifc.h | 49 ++++++++++++++++- include/linux/mlx5/port.h | 6 ++ 4 files changed, 132 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index dae70500b6a9..569100d3f57b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -405,3 +405,79 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); + +int mlx5_max_tc(struct mlx5_core_dev *mdev) +{ + u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8; + + return num_tc - 1; +} + +int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc) +{ + u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + int err; + int i; + + memset(in, 0, sizeof(in)); + for (i = 0; i < 8; i++) { + if (prio_tc[i] > mlx5_max_tc(mdev)) + return -EINVAL; + + MLX5_SET(qtct_reg, in, prio, i); + MLX5_SET(qtct_reg, in, tclass, prio_tc[i]); + + err = mlx5_core_access_reg(mdev, in, sizeof(in), out, + sizeof(out), MLX5_REG_QTCT, 0, 1); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_set_port_prio_tc); + +static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, + int inlen) +{ + u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + + if (!MLX5_CAP_GEN(mdev, ets)) + return -ENOTSUPP; + + return mlx5_core_access_reg(mdev, in, inlen, out, sizeof(out), + MLX5_REG_QETCR, 0, 1); +} + +int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + int i; + + memset(in, 0, sizeof(in)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + MLX5_SET(qetc_reg, in, tc_configuration[i].g, 1); + MLX5_SET(qetc_reg, in, tc_configuration[i].group, tc_group[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group); + +int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + int i; + + memset(in, 0, sizeof(in)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + MLX5_SET(qetc_reg, in, tc_configuration[i].b, 1); + MLX5_SET(qetc_reg, in, tc_configuration[i].bw_allocation, tc_bw[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 02adc67720ce..a815da92d4eb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -99,6 +99,8 @@ enum { }; enum { + MLX5_REG_QETCR = 0x4005, + MLX5_REG_QTCT = 0x400a, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..ec957e059de8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -729,7 +729,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_1bf[0x3]; u8 log_max_msg[0x5]; - u8 reserved_at_1c7[0x18]; + u8 reserved_at_1c7[0x4]; + u8 max_tc[0x4]; + u8 reserved_at_1cf[0x10]; u8 stat_rate_support[0x10]; u8 reserved_at_1ef[0xc]; @@ -7061,4 +7063,49 @@ struct mlx5_ifc_modify_flow_table_in_bits { u8 reserved_at_100[0x100]; }; +struct mlx5_ifc_ets_tcn_config_reg_bits { + u8 g[0x1]; + u8 b[0x1]; + u8 r[0x1]; + u8 reserved_at_3[0x9]; + u8 group[0x4]; + u8 reserved_at_10[0x9]; + u8 bw_allocation[0x7]; + + u8 reserved_at_20[0xc]; + u8 max_bw_units[0x4]; + u8 reserved_at_30[0x8]; + u8 max_bw_value[0x8]; +}; + +struct mlx5_ifc_ets_global_config_reg_bits { + u8 reserved_at_0[0x2]; + u8 r[0x1]; + u8 reserved_at_3[0x1d]; + + u8 reserved_at_20[0xc]; + u8 max_bw_units[0x4]; + u8 reserved_at_30[0x8]; + u8 max_bw_value[0x8]; +}; + +struct mlx5_ifc_qetc_reg_bits { + u8 reserved_at_0[0x8]; + u8 port_number[0x8]; + u8 reserved_at_10[0x30]; + + struct mlx5_ifc_ets_tcn_config_reg_bits tc_configuration[0x8]; + struct mlx5_ifc_ets_global_config_reg_bits global_configuration; +}; + +struct mlx5_ifc_qtct_reg_bits { + u8 reserved_at_0[0x8]; + u8 port_number[0x8]; + u8 reserved_at_10[0xd]; + u8 prio[0x3]; + + u8 reserved_at_20[0x1d]; + u8 tclass[0x3]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 4b3644caa936..0c67e699d017 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -70,4 +70,10 @@ int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx); +int mlx5_max_tc(struct mlx5_core_dev *mdev); + +int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); +int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); +int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); + #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From d8880795dabf2381ed1e98348f6d9c7ea6fab950 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 22 Feb 2016 18:17:28 +0200 Subject: net/mlx5e: Implement DCBNL IEEE max rate Add support for DCBNL IEEE get/set max rate. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 73 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/port.c | 65 +++++++++++++++++++ include/linux/mlx5/device.h | 6 ++ include/linux/mlx5/port.h | 6 ++ 4 files changed, 150 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 39d8069ba9e3..3036f279a8fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -35,6 +35,9 @@ #define MLX5E_MAX_PRIORITY 8 +#define MLX5E_100MB (100000) +#define MLX5E_1GB (1000000) + static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, struct ieee_ets *ets) { @@ -219,9 +222,79 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) return 0; } +static int mlx5e_dcbnl_ieee_getmaxrate(struct net_device *netdev, + struct ieee_maxrate *maxrate) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; + u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; + int err; + int i; + + err = mlx5_query_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); + if (err) + return err; + + memset(maxrate->tc_maxrate, 0, sizeof(maxrate->tc_maxrate)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + switch (max_bw_unit[i]) { + case MLX5_100_MBPS_UNIT: + maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_100MB; + break; + case MLX5_GBPS_UNIT: + maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_1GB; + break; + case MLX5_BW_NO_LIMIT: + break; + default: + WARN(true, "non-supported BW unit"); + break; + } + } + + return 0; +} + +static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, + struct ieee_maxrate *maxrate) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; + u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; + __u64 upper_limit_mbps = roundup(255 * MLX5E_100MB, MLX5E_1GB); + int i; + + memset(max_bw_value, 0, sizeof(max_bw_value)); + memset(max_bw_unit, 0, sizeof(max_bw_unit)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + if (!maxrate->tc_maxrate[i]) { + max_bw_unit[i] = MLX5_BW_NO_LIMIT; + continue; + } + if (maxrate->tc_maxrate[i] < upper_limit_mbps) { + max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], + MLX5E_100MB); + max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1; + max_bw_unit[i] = MLX5_100_MBPS_UNIT; + } else { + max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], + MLX5E_1GB); + max_bw_unit[i] = MLX5_GBPS_UNIT; + } + } + + return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); +} + const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = { .ieee_getets = mlx5e_dcbnl_ieee_getets, .ieee_setets = mlx5e_dcbnl_ieee_setets, + .ieee_getmaxrate = mlx5e_dcbnl_ieee_getmaxrate, + .ieee_setmaxrate = mlx5e_dcbnl_ieee_setmaxrate, .ieee_getpfc = mlx5e_dcbnl_ieee_getpfc, .ieee_setpfc = mlx5e_dcbnl_ieee_setpfc, .getdcbx = mlx5e_dcbnl_getdcbx, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 569100d3f57b..d97605ef3efd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -450,6 +450,19 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, MLX5_REG_QETCR, 0, 1); } +static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, + int outlen) +{ + u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + + if (!MLX5_CAP_GEN(mdev, ets)) + return -ENOTSUPP; + + memset(in, 0, sizeof(in)); + return mlx5_core_access_reg(mdev, in, sizeof(in), out, outlen, + MLX5_REG_QETCR, 0, 0); +} + int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group) { u32 in[MLX5_ST_SZ_DW(qetc_reg)]; @@ -481,3 +494,55 @@ int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw) return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); } EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc); + +int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_units) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int i; + + memset(in, 0, sizeof(in)); + + MLX5_SET(qetc_reg, in, port_number, 1); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, in, tc_configuration[i]); + + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, r, 1); + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, max_bw_units, + max_bw_units[i]); + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, max_bw_value, + max_bw_value[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_modify_port_ets_rate_limit); + +int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_units) +{ + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int err; + int i; + + err = mlx5_query_port_qetcr_reg(mdev, out, sizeof(out)); + if (err) + return err; + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, out, tc_configuration[i]); + + max_bw_value[i] = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + max_bw_value); + max_bw_units[i] = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + max_bw_units); + } + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 987764afa65c..bfc1ab0552d3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -350,6 +350,12 @@ enum { MLX5_SET_PORT_PKEY_TABLE = 20, }; +enum { + MLX5_BW_NO_LIMIT = 0, + MLX5_100_MBPS_UNIT = 3, + MLX5_GBPS_UNIT = 4, +}; + enum { MLX5_MAX_PAGE_SHIFT = 31 }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 0c67e699d017..595c7b2d9bfa 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -75,5 +75,11 @@ int mlx5_max_tc(struct mlx5_core_dev *mdev); int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); +int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_unit); +int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_unit); #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 928cfe8745a62e60c1e8e06676a74724e7786024 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 22 Feb 2016 18:17:29 +0200 Subject: net/mlx5e: Wake On LAN support Implement set/get WOL by ethtool and added the needed device commands and structures to mlx5_ifc. Signed-off-by: Tariq Toukan Signed-off-by: Rana Shahout Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 6 + .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 125 +++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/port.c | 38 +++++++ include/linux/mlx5/device.h | 11 ++ include/linux/mlx5/mlx5_ifc.h | 62 +++++++++- include/linux/mlx5/port.h | 2 + 6 files changed, 243 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 037fc4cdf5af..9ce87c624450 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -560,6 +560,12 @@ const char *mlx5_command_str(int command) case MLX5_CMD_OP_ACCESS_REG: return "MLX5_CMD_OP_ACCESS_REG"; + case MLX5_CMD_OP_SET_WOL_ROL: + return "SET_WOL_ROL"; + + case MLX5_CMD_OP_QUERY_WOL_ROL: + return "QUERY_WOL_ROL"; + default: return "unknown command opcode"; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 65624ac65b4c..e9760f895744 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -884,6 +884,129 @@ static int mlx5e_get_ts_info(struct net_device *dev, return 0; } +static __u32 mlx5e_get_wol_supported(struct mlx5_core_dev *mdev) +{ + __u32 ret = 0; + + if (MLX5_CAP_GEN(mdev, wol_g)) + ret |= WAKE_MAGIC; + + if (MLX5_CAP_GEN(mdev, wol_s)) + ret |= WAKE_MAGICSECURE; + + if (MLX5_CAP_GEN(mdev, wol_a)) + ret |= WAKE_ARP; + + if (MLX5_CAP_GEN(mdev, wol_b)) + ret |= WAKE_BCAST; + + if (MLX5_CAP_GEN(mdev, wol_m)) + ret |= WAKE_MCAST; + + if (MLX5_CAP_GEN(mdev, wol_u)) + ret |= WAKE_UCAST; + + if (MLX5_CAP_GEN(mdev, wol_p)) + ret |= WAKE_PHY; + + return ret; +} + +static __u32 mlx5e_refomrat_wol_mode_mlx5_to_linux(u8 mode) +{ + __u32 ret = 0; + + if (mode & MLX5_WOL_MAGIC) + ret |= WAKE_MAGIC; + + if (mode & MLX5_WOL_SECURED_MAGIC) + ret |= WAKE_MAGICSECURE; + + if (mode & MLX5_WOL_ARP) + ret |= WAKE_ARP; + + if (mode & MLX5_WOL_BROADCAST) + ret |= WAKE_BCAST; + + if (mode & MLX5_WOL_MULTICAST) + ret |= WAKE_MCAST; + + if (mode & MLX5_WOL_UNICAST) + ret |= WAKE_UCAST; + + if (mode & MLX5_WOL_PHY_ACTIVITY) + ret |= WAKE_PHY; + + return ret; +} + +static u8 mlx5e_refomrat_wol_mode_linux_to_mlx5(__u32 mode) +{ + u8 ret = 0; + + if (mode & WAKE_MAGIC) + ret |= MLX5_WOL_MAGIC; + + if (mode & WAKE_MAGICSECURE) + ret |= MLX5_WOL_SECURED_MAGIC; + + if (mode & WAKE_ARP) + ret |= MLX5_WOL_ARP; + + if (mode & WAKE_BCAST) + ret |= MLX5_WOL_BROADCAST; + + if (mode & WAKE_MCAST) + ret |= MLX5_WOL_MULTICAST; + + if (mode & WAKE_UCAST) + ret |= MLX5_WOL_UNICAST; + + if (mode & WAKE_PHY) + ret |= MLX5_WOL_PHY_ACTIVITY; + + return ret; +} + +static void mlx5e_get_wol(struct net_device *netdev, + struct ethtool_wolinfo *wol) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 mlx5_wol_mode; + int err; + + memset(wol, 0, sizeof(*wol)); + + wol->supported = mlx5e_get_wol_supported(mdev); + if (!wol->supported) + return; + + err = mlx5_query_port_wol(mdev, &mlx5_wol_mode); + if (err) + return; + + wol->wolopts = mlx5e_refomrat_wol_mode_mlx5_to_linux(mlx5_wol_mode); +} + +static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + __u32 wol_supported = mlx5e_get_wol_supported(mdev); + u32 mlx5_wol_mode; + + if (!wol_supported) + return -ENOTSUPP; + + if (wol->wolopts & ~wol_supported) + return -EINVAL; + + mlx5_wol_mode = mlx5e_refomrat_wol_mode_linux_to_mlx5(wol->wolopts); + + return mlx5_set_port_wol(mdev, mlx5_wol_mode); +} + const struct ethtool_ops mlx5e_ethtool_ops = { .get_drvinfo = mlx5e_get_drvinfo, .get_link = ethtool_op_get_link, @@ -908,4 +1031,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_pauseparam = mlx5e_get_pauseparam, .set_pauseparam = mlx5e_set_pauseparam, .get_ts_info = mlx5e_get_ts_info, + .get_wol = mlx5e_get_wol, + .set_wol = mlx5e_set_wol, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index d97605ef3efd..e1f2e1059cfd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -546,3 +546,41 @@ int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit); + +int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode) +{ + u32 in[MLX5_ST_SZ_DW(set_wol_rol_in)]; + u32 out[MLX5_ST_SZ_DW(set_wol_rol_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(set_wol_rol_in, in, opcode, MLX5_CMD_OP_SET_WOL_ROL); + MLX5_SET(set_wol_rol_in, in, wol_mode_valid, 1); + MLX5_SET(set_wol_rol_in, in, wol_mode, wol_mode); + + return mlx5_cmd_exec_check_status(mdev, in, sizeof(in), + out, sizeof(out)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_wol); + +int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode) +{ + u32 in[MLX5_ST_SZ_DW(query_wol_rol_in)]; + u32 out[MLX5_ST_SZ_DW(query_wol_rol_out)]; + int err; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(query_wol_rol_in, in, opcode, MLX5_CMD_OP_QUERY_WOL_ROL); + + err = mlx5_cmd_exec_check_status(mdev, in, sizeof(in), + out, sizeof(out)); + + if (!err) + *wol_mode = MLX5_GET(query_wol_rol_out, out, wol_mode); + + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_wol); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index bfc1ab0552d3..68a56bc37df2 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1183,6 +1183,17 @@ enum { MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1, }; +enum mlx5_wol_mode { + MLX5_WOL_DISABLE = 0, + MLX5_WOL_SECURED_MAGIC = 1 << 1, + MLX5_WOL_MAGIC = 1 << 2, + MLX5_WOL_ARP = 1 << 3, + MLX5_WOL_BROADCAST = 1 << 4, + MLX5_WOL_MULTICAST = 1 << 5, + MLX5_WOL_UNICAST = 1 << 6, + MLX5_WOL_PHY_ACTIVITY = 1 << 7, +}; + /* MLX5 DEV CAPs */ /* TODO: EAT.ME */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ec957e059de8..03ffe9530365 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -166,6 +166,8 @@ enum { MLX5_CMD_OP_SET_L2_TABLE_ENTRY = 0x829, MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY = 0x82a, MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY = 0x82b, + MLX5_CMD_OP_SET_WOL_ROL = 0x830, + MLX5_CMD_OP_QUERY_WOL_ROL = 0x831, MLX5_CMD_OP_CREATE_TIR = 0x900, MLX5_CMD_OP_MODIFY_TIR = 0x901, MLX5_CMD_OP_DESTROY_TIR = 0x902, @@ -731,7 +733,17 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_msg[0x5]; u8 reserved_at_1c7[0x4]; u8 max_tc[0x4]; - u8 reserved_at_1cf[0x10]; + u8 reserved_at_1cf[0x6]; + u8 rol_s[0x1]; + u8 rol_g[0x1]; + u8 reserved_at_1d7[0x1]; + u8 wol_s[0x1]; + u8 wol_g[0x1]; + u8 wol_a[0x1]; + u8 wol_b[0x1]; + u8 wol_m[0x1]; + u8 wol_u[0x1]; + u8 wol_p[0x1]; u8 stat_rate_support[0x10]; u8 reserved_at_1ef[0xc]; @@ -6873,6 +6885,54 @@ struct mlx5_ifc_mtt_bits { u8 rd_en[0x1]; }; +struct mlx5_ifc_query_wol_rol_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x10]; + u8 rol_mode[0x8]; + u8 wol_mode[0x8]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_query_wol_rol_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_set_wol_rol_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_set_wol_rol_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 rol_mode_valid[0x1]; + u8 wol_mode_valid[0x1]; + u8 reserved_at_42[0xe]; + u8 rol_mode[0x8]; + u8 wol_mode[0x8]; + + u8 reserved_at_60[0x20]; +}; + enum { MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0, MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1, diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 595c7b2d9bfa..a1d145abd4eb 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -81,5 +81,7 @@ int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, u8 *max_bw_value, u8 *max_bw_unit); +int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode); +int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode); #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From f1705ec197e705b79ea40fe7a2cc5acfa1d3bfac Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 24 Feb 2016 09:25:37 -0800 Subject: net: ipv6: Make address flushing on ifdown optional Currently, all ipv6 addresses are flushed when the interface is configured down, including global, static addresses: $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 << nothing; all addresses have been flushed>> Add a new sysctl to make this behavior optional. The new setting defaults to flush all addresses to maintain backwards compatibility. When the set global addresses with no expire times are not flushed on an admin down. The sysctl is per-interface or system-wide for all interfaces $ sysctl -w net.ipv6.conf.eth1.keep_addr_on_down=1 or $ sysctl -w net.ipv6.conf.all.keep_addr_on_down=1 Will keep addresses on eth1 on an admin down. $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state DOWN qlen 1000 inet6 2100:1::2/120 scope global tentative valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link tentative valid_lft forever preferred_lft forever Signed-off-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 +++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 136 +++++++++++++++++++++++++++++---- 4 files changed, 132 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 24ce97f42d35..d5df40c75aa4 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1563,6 +1563,15 @@ temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. Default: 86400 (1 day) +keep_addr_on_down - INTEGER + Keep all IPv6 addresses on an interface down event. If set static + global addresses with no expiration time are not flushed. + >0 : enabled + 0 : system default + <0 : disabled + + Default: 0 (addresses are removed) + max_desync_factor - INTEGER Maximum value for DESYNC_FACTOR, which is a random value that ensures that clients don't synchronize with each diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4b2267e1b7c3..7edc14fb66b6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,6 +62,7 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; + __s32 keep_addr_on_down; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index ec117b65d5a5..395876060f50 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -176,6 +176,7 @@ enum { DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, + DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4751f8922362..a2d6f6c242af 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -216,6 +216,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; /* Check if a valid qdisc is available */ @@ -3168,6 +3170,55 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +static int fixup_permanent_addr(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ + if (!ifp->rt) { + struct rt6_info *rt; + + rt = addrconf_dst_alloc(idev, &ifp->addr, false); + if (unlikely(IS_ERR(rt))) + return PTR_ERR(rt); + + ifp->rt = rt; + } + + if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + idev->dev, 0, 0); + } + + addrconf_dad_start(ifp); + + return 0; +} + +static void addrconf_permanent_addr(struct net_device *dev) +{ + struct inet6_ifaddr *ifp, *tmp; + struct inet6_dev *idev; + + idev = __in6_dev_get(dev); + if (!idev) + return; + + write_lock_bh(&idev->lock); + + list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { + if ((ifp->flags & IFA_F_PERMANENT) && + fixup_permanent_addr(idev, ifp) < 0) { + write_unlock_bh(&idev->lock); + ipv6_del_addr(ifp); + write_lock_bh(&idev->lock); + + net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", + idev->dev->name, &ifp->addr); + } + } + + write_unlock_bh(&idev->lock); +} + static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -3253,6 +3304,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3356,7 +3410,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) { struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + struct inet6_ifaddr *ifa, *tmp; + struct list_head del_list; + int _keep_addr; + bool keep_addr; int state, i; ASSERT_RTNL(); @@ -3383,6 +3440,16 @@ static int addrconf_ifdown(struct net_device *dev, int how) } + /* aggregate the system setting and interface setting */ + _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + /* combine the user config with event to determine if permanent + * addresses are to be removed from address hash table + */ + keep_addr = !(how || _keep_addr <= 0); + /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; @@ -3391,9 +3458,15 @@ static int addrconf_ifdown(struct net_device *dev, int how) restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { - hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_dad_work(ifa); - goto restart; + /* combined flag + permanent flag decide if + * address is retained on a down event + */ + if (!keep_addr || + !(ifa->flags & IFA_F_PERMANENT)) { + hlist_del_init_rcu(&ifa->addr_lst); + goto restart; + } } } spin_unlock_bh(&addrconf_hash_lock); @@ -3427,31 +3500,53 @@ restart: write_lock_bh(&idev->lock); } - while (!list_empty(&idev->addr_list)) { - ifa = list_first_entry(&idev->addr_list, - struct inet6_ifaddr, if_list); - addrconf_del_dad_work(ifa); + /* re-combine the user config with event to determine if permanent + * addresses are to be removed from the interface list + */ + keep_addr = (!how && _keep_addr > 0); - list_del(&ifa->if_list); + INIT_LIST_HEAD(&del_list); + list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + addrconf_del_dad_work(ifa); write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->lock); - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; + + if (keep_addr && (ifa->flags & IFA_F_PERMANENT)) { + /* set state to skip the notifier below */ + state = INET6_IFADDR_STATE_DEAD; + ifa->state = 0; + if (!(ifa->flags & IFA_F_NODAD)) + ifa->flags |= IFA_F_TENTATIVE; + } else { + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + + list_del(&ifa->if_list); + list_add(&ifa->if_list, &del_list); + } + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } - in6_ifa_put(ifa); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); + /* now clean up addresses to be removed */ + while (!list_empty(&del_list)) { + ifa = list_first_entry(&del_list, + struct inet6_ifaddr, if_list); + list_del(&ifa->if_list); + + in6_ifa_put(ifa); + } + /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4716,6 +4811,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; + array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; } static inline size_t inet6_ifla6_size(void) @@ -5197,10 +5293,12 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (rt) ip6_del_rt(rt); } - dst_hold(&ifp->rt->dst); - - ip6_del_rt(ifp->rt); + if (ifp->rt) { + dst_hold(&ifp->rt->dst); + ip6_del_rt(ifp->rt); + ifp->rt = NULL; + } rt_genid_bump_ipv6(net); break; } @@ -5803,6 +5901,14 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "keep_addr_on_down", + .data = &ipv6_devconf.keep_addr_on_down, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + + }, { /* sentinel */ } -- cgit v1.2.3 From 3f1ac7a700d039c61d8d8b99f28d605d489a60cf Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Wed, 24 Feb 2016 10:57:59 -0800 Subject: net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/ethtool.h | 91 ++++++++- include/uapi/linux/ethtool.h | 322 +++++++++++++++++++++++------- net/core/ethtool.c | 453 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 786 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 472d7d7b01c2..8a400a54c92e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -12,6 +12,7 @@ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H +#include #include #include @@ -40,9 +41,6 @@ struct compat_ethtool_rxnfc { #include -extern int __ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd); - /** * enum ethtool_phys_id_state - indicator state for physical identification * @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated @@ -97,13 +95,74 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) return index % n_rx_rings; } +/* number of link mode bits/ulongs handled internally by kernel */ +#define __ETHTOOL_LINK_MODE_MASK_NBITS \ + (__ETHTOOL_LINK_MODE_LAST + 1) + +/* declare a link mode bitmap */ +#define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ + DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/* drivers must ignore base.cmd and base.link_mode_masks_nwords + * fields, but they are allowed to overwrite them (will be ignored). + */ +struct ethtool_link_ksettings { + struct ethtool_link_settings base; + struct { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + } link_modes; +}; + +/** + * ethtool_link_ksettings_zero_link_mode - clear link_ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + */ +#define ethtool_link_ksettings_zero_link_mode(ptr, name) \ + bitmap_zero((ptr)->link_modes.name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/** + * ethtool_link_ksettings_add_link_mode - set bit in link_ksettings + * link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + */ +#define ethtool_link_ksettings_add_link_mode(ptr, name, mode) \ + __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +/** + * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + * + * Returns true/false. + */ +#define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \ + test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +extern int +__ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings); + +/* DEPRECATED, use __ethtool_get_link_ksettings */ +extern int __ethtool_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd); + /** * struct ethtool_ops - optional netdev operations - * @get_settings: Get various device settings including Ethernet link + * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Get various device settings including Ethernet link * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code or - * zero. - * @set_settings: Set various device settings including Ethernet link + * before get_settings is called. Returns a negative error code + * or zero. + * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Set various device settings including Ethernet link * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not @@ -211,6 +270,19 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. + * @get_link_ksettings: When defined, takes precedence over the + * %get_settings method. Get various device settings + * including Ethernet link settings. The %cmd and + * %link_mode_masks_nwords fields should be ignored (use + * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any + * change to them will be overwritten by kernel. Returns a + * negative error code or zero. + * @set_link_ksettings: When defined, takes precedence over the + * %set_settings method. Set various device settings including + * Ethernet link settings. The %cmd and %link_mode_masks_nwords + * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS + * instead of the latter), any change to them will be overwritten + * by kernel. Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -293,6 +365,9 @@ struct ethtool_ops { struct ethtool_coalesce *); int (*set_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); - + int (*get_link_ksettings)(struct net_device *, + struct ethtool_link_ksettings *); + int (*set_link_ksettings)(struct net_device *, + const struct ethtool_link_ksettings *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index f15ae02621a1..37fd6dc33de4 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -21,7 +21,8 @@ */ /** - * struct ethtool_cmd - link control and status + * struct ethtool_cmd - DEPRECATED, link control and status + * This structure is DEPRECATED, please use struct ethtool_link_settings. * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET * @supported: Bitmask of %SUPPORTED_* flags for the link modes, * physical connectors and other link features for which the @@ -1219,8 +1220,12 @@ struct ethtool_per_queue_op { }; /* CMDs currently supported */ -#define ETHTOOL_GSET 0x00000001 /* Get settings. */ -#define ETHTOOL_SSET 0x00000002 /* Set settings. */ +#define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. + * Please use ETHTOOL_GLINKSETTINGS + */ +#define ETHTOOL_SSET 0x00000002 /* DEPRECATED, Set settings. + * Please use ETHTOOL_SLINKSETTINGS + */ #define ETHTOOL_GDRVINFO 0x00000003 /* Get driver info. */ #define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ #define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ @@ -1302,73 +1307,139 @@ struct ethtool_per_queue_op { #define ETHTOOL_PERQUEUE 0x0000004b /* Set per queue options */ +#define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */ +#define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ + + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET -#define SUPPORTED_10baseT_Half (1 << 0) -#define SUPPORTED_10baseT_Full (1 << 1) -#define SUPPORTED_100baseT_Half (1 << 2) -#define SUPPORTED_100baseT_Full (1 << 3) -#define SUPPORTED_1000baseT_Half (1 << 4) -#define SUPPORTED_1000baseT_Full (1 << 5) -#define SUPPORTED_Autoneg (1 << 6) -#define SUPPORTED_TP (1 << 7) -#define SUPPORTED_AUI (1 << 8) -#define SUPPORTED_MII (1 << 9) -#define SUPPORTED_FIBRE (1 << 10) -#define SUPPORTED_BNC (1 << 11) -#define SUPPORTED_10000baseT_Full (1 << 12) -#define SUPPORTED_Pause (1 << 13) -#define SUPPORTED_Asym_Pause (1 << 14) -#define SUPPORTED_2500baseX_Full (1 << 15) -#define SUPPORTED_Backplane (1 << 16) -#define SUPPORTED_1000baseKX_Full (1 << 17) -#define SUPPORTED_10000baseKX4_Full (1 << 18) -#define SUPPORTED_10000baseKR_Full (1 << 19) -#define SUPPORTED_10000baseR_FEC (1 << 20) -#define SUPPORTED_20000baseMLD2_Full (1 << 21) -#define SUPPORTED_20000baseKR2_Full (1 << 22) -#define SUPPORTED_40000baseKR4_Full (1 << 23) -#define SUPPORTED_40000baseCR4_Full (1 << 24) -#define SUPPORTED_40000baseSR4_Full (1 << 25) -#define SUPPORTED_40000baseLR4_Full (1 << 26) -#define SUPPORTED_56000baseKR4_Full (1 << 27) -#define SUPPORTED_56000baseCR4_Full (1 << 28) -#define SUPPORTED_56000baseSR4_Full (1 << 29) -#define SUPPORTED_56000baseLR4_Full (1 << 30) - -#define ADVERTISED_10baseT_Half (1 << 0) -#define ADVERTISED_10baseT_Full (1 << 1) -#define ADVERTISED_100baseT_Half (1 << 2) -#define ADVERTISED_100baseT_Full (1 << 3) -#define ADVERTISED_1000baseT_Half (1 << 4) -#define ADVERTISED_1000baseT_Full (1 << 5) -#define ADVERTISED_Autoneg (1 << 6) -#define ADVERTISED_TP (1 << 7) -#define ADVERTISED_AUI (1 << 8) -#define ADVERTISED_MII (1 << 9) -#define ADVERTISED_FIBRE (1 << 10) -#define ADVERTISED_BNC (1 << 11) -#define ADVERTISED_10000baseT_Full (1 << 12) -#define ADVERTISED_Pause (1 << 13) -#define ADVERTISED_Asym_Pause (1 << 14) -#define ADVERTISED_2500baseX_Full (1 << 15) -#define ADVERTISED_Backplane (1 << 16) -#define ADVERTISED_1000baseKX_Full (1 << 17) -#define ADVERTISED_10000baseKX4_Full (1 << 18) -#define ADVERTISED_10000baseKR_Full (1 << 19) -#define ADVERTISED_10000baseR_FEC (1 << 20) -#define ADVERTISED_20000baseMLD2_Full (1 << 21) -#define ADVERTISED_20000baseKR2_Full (1 << 22) -#define ADVERTISED_40000baseKR4_Full (1 << 23) -#define ADVERTISED_40000baseCR4_Full (1 << 24) -#define ADVERTISED_40000baseSR4_Full (1 << 25) -#define ADVERTISED_40000baseLR4_Full (1 << 26) -#define ADVERTISED_56000baseKR4_Full (1 << 27) -#define ADVERTISED_56000baseCR4_Full (1 << 28) -#define ADVERTISED_56000baseSR4_Full (1 << 29) -#define ADVERTISED_56000baseLR4_Full (1 << 30) +/* Link mode bit indices */ +enum ethtool_link_mode_bit_indices { + ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0, + ETHTOOL_LINK_MODE_10baseT_Full_BIT = 1, + ETHTOOL_LINK_MODE_100baseT_Half_BIT = 2, + ETHTOOL_LINK_MODE_100baseT_Full_BIT = 3, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT = 4, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT = 5, + ETHTOOL_LINK_MODE_Autoneg_BIT = 6, + ETHTOOL_LINK_MODE_TP_BIT = 7, + ETHTOOL_LINK_MODE_AUI_BIT = 8, + ETHTOOL_LINK_MODE_MII_BIT = 9, + ETHTOOL_LINK_MODE_FIBRE_BIT = 10, + ETHTOOL_LINK_MODE_BNC_BIT = 11, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT = 12, + ETHTOOL_LINK_MODE_Pause_BIT = 13, + ETHTOOL_LINK_MODE_Asym_Pause_BIT = 14, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT = 15, + ETHTOOL_LINK_MODE_Backplane_BIT = 16, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT = 17, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT = 18, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT = 19, + ETHTOOL_LINK_MODE_10000baseR_FEC_BIT = 20, + ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21, + ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT = 22, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT = 23, + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT = 24, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT = 25, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT = 26, + ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT = 27, + ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28, + ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29, + ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30, + + /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit + * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* + * macro for bits > 31. The only way to use indices > 31 is to + * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. + */ + + __ETHTOOL_LINK_MODE_LAST + = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT, +}; + +#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ + (1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT)) + +/* DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new SUPPORTED_* macro for bits > 31. + */ +#define SUPPORTED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define SUPPORTED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define SUPPORTED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define SUPPORTED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define SUPPORTED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define SUPPORTED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define SUPPORTED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define SUPPORTED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define SUPPORTED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define SUPPORTED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define SUPPORTED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define SUPPORTED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define SUPPORTED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define SUPPORTED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define SUPPORTED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define SUPPORTED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define SUPPORTED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define SUPPORTED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define SUPPORTED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define SUPPORTED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define SUPPORTED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define SUPPORTED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define SUPPORTED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define SUPPORTED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define SUPPORTED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define SUPPORTED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define SUPPORTED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define SUPPORTED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define SUPPORTED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define SUPPORTED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define SUPPORTED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new SUPPORTED_* macro for bits > 31, see + * notice above. + */ + +/* + * DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new ADERTISE_* macro for bits > 31. + */ +#define ADVERTISED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define ADVERTISED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define ADVERTISED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define ADVERTISED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define ADVERTISED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define ADVERTISED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define ADVERTISED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define ADVERTISED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define ADVERTISED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define ADVERTISED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define ADVERTISED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define ADVERTISED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define ADVERTISED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define ADVERTISED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define ADVERTISED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define ADVERTISED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define ADVERTISED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define ADVERTISED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define ADVERTISED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define ADVERTISED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define ADVERTISED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define ADVERTISED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define ADVERTISED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define ADVERTISED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define ADVERTISED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define ADVERTISED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define ADVERTISED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define ADVERTISED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define ADVERTISED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define ADVERTISED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define ADVERTISED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new ADVERTISED_* macro for bits > 31, see + * notice above. + */ /* The following are all involved in forcing a particular link * mode for the device for setting things. When getting the @@ -1533,4 +1604,123 @@ enum ethtool_reset_flags { }; #define ETH_RESET_SHARED_SHIFT 16 + +/** + * struct ethtool_link_settings - link control and status + * + * IMPORTANT, Backward compatibility notice: When implementing new + * user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and + * if it succeeds use %ETHTOOL_SLINKSETTINGS to change link + * settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS + * succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in + * that case. Conversely, if %ETHTOOL_GLINKSETTINGS fails, use + * %ETHTOOL_GSET to query and %ETHTOOL_SSET to change link + * settings; do not use %ETHTOOL_SLINKSETTINGS if + * %ETHTOOL_GLINKSETTINGS failed: stick to + * %ETHTOOL_GSET/%ETHTOOL_SSET in that case. + * + * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS + * @speed: Link speed (Mbps) + * @duplex: Duplex mode; one of %DUPLEX_* + * @port: Physical connector type; one of %PORT_* + * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not + * applicable. For clause 45 PHYs this is the PRTAD. + * @autoneg: Enable/disable autonegotiation and auto-detection; + * either %AUTONEG_DISABLE or %AUTONEG_ENABLE + * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO + * protocols supported by the interface; 0 if unknown. + * Read-only. + * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of + * %ETH_TP_MDI_*. If the status is unknown or not applicable, the + * value will be %ETH_TP_MDI_INVALID. Read-only. + * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of + * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads + * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. + * When written successfully, the link should be renegotiated if + * necessary. + * @link_mode_masks_nwords: Number of 32-bit words for each of the + * supported, advertising, lp_advertising link mode bitmaps. For + * %ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user + * (>= 0); on return, if handshake in progress, negative if + * request size unsupported by kernel: absolute value indicates + * kernel recommended size and cmd field is 0, as well as all the + * other fields; otherwise (handshake completed), strictly + * positive to indicate size used by kernel and cmd field is + * %ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For + * %ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive + * value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise + * refused. For drivers: ignore this field (use kernel's + * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will + * be overwritten by kernel. + * @supported: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features for which the interface + * supports autonegotiation or auto-detection. Read-only. + * @advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features that are advertised through + * autonegotiation or enabled for auto-detection. + * @lp_advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, and other + * link features that the link partner advertised through + * autonegotiation; 0 if unknown or not applicable. Read-only. + * + * If autonegotiation is disabled, the speed and @duplex represent the + * fixed link mode and are writable if the driver supports multiple + * link modes. If it is enabled then they are read-only; if the link + * is up they represent the negotiated link mode; if the link is down, + * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and + * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. + * + * Some hardware interfaces may have multiple PHYs and/or physical + * connectors fitted or do not allow the driver to detect which are + * fitted. For these interfaces @port and/or @phy_address may be + * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. + * Otherwise, attempts to write different values may be ignored or + * rejected. + * + * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt + * are not available in %ethtool_link_settings. Until all drivers are + * converted to ignore them or to the new %ethtool_link_settings API, + * for both queries and changes, users should always try + * %ETHTOOL_GLINKSETTINGS first, and if it fails with -ENOTSUPP stick + * only to %ETHTOOL_GSET and %ETHTOOL_SSET consistently. If it + * succeeds, then users should stick to %ETHTOOL_GLINKSETTINGS and + * %ETHTOOL_SLINKSETTINGS (which would support drivers implementing + * either %ethtool_cmd or %ethtool_link_settings). + * + * Users should assume that all fields not marked read-only are + * writable and subject to validation by the driver. They should use + * %ETHTOOL_GLINKSETTINGS to get the current values before making specific + * changes and then applying them with %ETHTOOL_SLINKSETTINGS. + * + * Drivers that implement %get_link_ksettings and/or + * %set_link_ksettings should ignore the @cmd + * and @link_mode_masks_nwords fields (any change to them overwritten + * by kernel), and rely only on kernel's internal + * %__ETHTOOL_LINK_MODE_MASK_NBITS and + * %ethtool_link_mode_mask_t. Drivers that implement + * %set_link_ksettings() should validate all fields other than @cmd + * and @link_mode_masks_nwords that are not described as read-only or + * deprecated, and must ignore all fields described as read-only. + */ +struct ethtool_link_settings { + __u32 cmd; + __u32 speed; + __u8 duplex; + __u8 port; + __u8 phy_address; + __u8 autoneg; + __u8 mdio_support; + __u8 eth_tp_mdix; + __u8 eth_tp_mdix_ctrl; + __s8 link_mode_masks_nwords; + __u32 reserved[8]; + __u32 link_mode_masks[0]; + /* layout of link_mode_masks fields: + * __u32 map_supported[link_mode_masks_nwords]; + * __u32 map_advertising[link_mode_masks_nwords]; + * __u32 map_lp_advertising[link_mode_masks_nwords]; + */ +}; #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 2406101002b1..edcec56ed228 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -387,6 +387,359 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) return 0; } +static void convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32) +{ + bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); + dst[0] = legacy_u32; +} + +/* return false if src had higher bits set. lower bits always updated. */ +static bool convert_link_mode_to_legacy_u32(u32 *legacy_u32, + const unsigned long *src) +{ + bool retval = true; + + /* TODO: following test will soon always be true */ + if (__ETHTOOL_LINK_MODE_MASK_NBITS > 32) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(ext); + + bitmap_zero(ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_fill(ext, 32); + bitmap_complement(ext, ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + if (bitmap_intersects(ext, src, + __ETHTOOL_LINK_MODE_MASK_NBITS)) { + /* src mask goes beyond bit 31 */ + retval = false; + } + } + *legacy_u32 = src[0]; + return retval; +} + +/* return false if legacy contained non-0 deprecated fields + * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated + */ +static bool +convert_legacy_settings_to_link_ksettings( + struct ethtool_link_ksettings *link_ksettings, + const struct ethtool_cmd *legacy_settings) +{ + bool retval = true; + + memset(link_ksettings, 0, sizeof(*link_ksettings)); + + /* This is used to tell users that driver is still using these + * deprecated legacy fields, and they should not use + * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS + */ + if (legacy_settings->transceiver || + legacy_settings->maxtxpkt || + legacy_settings->maxrxpkt) + retval = false; + + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.supported, + legacy_settings->supported); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.advertising, + legacy_settings->advertising); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.lp_advertising, + legacy_settings->lp_advertising); + link_ksettings->base.speed + = ethtool_cmd_speed(legacy_settings); + link_ksettings->base.duplex + = legacy_settings->duplex; + link_ksettings->base.port + = legacy_settings->port; + link_ksettings->base.phy_address + = legacy_settings->phy_address; + link_ksettings->base.autoneg + = legacy_settings->autoneg; + link_ksettings->base.mdio_support + = legacy_settings->mdio_support; + link_ksettings->base.eth_tp_mdix + = legacy_settings->eth_tp_mdix; + link_ksettings->base.eth_tp_mdix_ctrl + = legacy_settings->eth_tp_mdix_ctrl; + return retval; +} + +/* return false if ksettings link modes had higher bits + * set. legacy_settings always updated (best effort) + */ +static bool +convert_link_ksettings_to_legacy_settings( + struct ethtool_cmd *legacy_settings, + const struct ethtool_link_ksettings *link_ksettings) +{ + bool retval = true; + + memset(legacy_settings, 0, sizeof(*legacy_settings)); + /* this also clears the deprecated fields in legacy structure: + * __u8 transceiver; + * __u32 maxtxpkt; + * __u32 maxrxpkt; + */ + + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->supported, + link_ksettings->link_modes.supported); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->advertising, + link_ksettings->link_modes.advertising); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->lp_advertising, + link_ksettings->link_modes.lp_advertising); + ethtool_cmd_speed_set(legacy_settings, link_ksettings->base.speed); + legacy_settings->duplex + = link_ksettings->base.duplex; + legacy_settings->port + = link_ksettings->base.port; + legacy_settings->phy_address + = link_ksettings->base.phy_address; + legacy_settings->autoneg + = link_ksettings->base.autoneg; + legacy_settings->mdio_support + = link_ksettings->base.mdio_support; + legacy_settings->eth_tp_mdix + = link_ksettings->base.eth_tp_mdix; + legacy_settings->eth_tp_mdix_ctrl + = link_ksettings->base.eth_tp_mdix_ctrl; + return retval; +} + +/* number of 32-bit words to store the user's link mode bitmaps */ +#define __ETHTOOL_LINK_MODE_MASK_NU32 \ + DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) + +/* layout of the struct passed from/to userland */ +struct ethtool_link_usettings { + struct ethtool_link_settings base; + struct { + __u32 supported[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 lp_advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + } link_modes; +}; + +/* Internal kernel helper to query a device ethtool_link_settings. + * + * Backward compatibility note: for compatibility with legacy drivers + * that implement only the ethtool_cmd API, this has to work with both + * drivers implementing get_link_ksettings API and drivers + * implementing get_settings API. When drivers implement get_settings + * and report ethtool_cmd deprecated fields + * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored + * because the resulting struct ethtool_link_settings does not report them. + */ +int __ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) +{ + int err; + struct ethtool_cmd cmd; + + ASSERT_RTNL(); + + if (dev->ethtool_ops->get_link_ksettings) { + memset(link_ksettings, 0, sizeof(*link_ksettings)); + return dev->ethtool_ops->get_link_ksettings(dev, + link_ksettings); + } + + /* driver doesn't support %ethtool_link_ksettings API. revert to + * legacy %ethtool_cmd API, unless it's not supported either. + * TODO: remove when ethtool_ops::get_settings disappears internally + */ + err = __ethtool_get_settings(dev, &cmd); + if (err < 0) + return err; + + /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt + */ + convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd); + return err; +} +EXPORT_SYMBOL(__ethtool_get_link_ksettings); + +/* convert ethtool_link_usettings in user space to a kernel internal + * ethtool_link_ksettings. return 0 on success, errno on error. + */ +static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to, + const void __user *from) +{ + struct ethtool_link_usettings link_usettings; + + if (copy_from_user(&link_usettings, from, sizeof(link_usettings))) + return -EFAULT; + + memcpy(&to->base, &link_usettings.base, sizeof(to->base)); + bitmap_from_u32array(to->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + + return 0; +} + +/* convert a kernel internal ethtool_link_ksettings to + * ethtool_link_usettings in user space. return 0 on success, errno on + * error. + */ +static int +store_link_ksettings_for_user(void __user *to, + const struct ethtool_link_ksettings *from) +{ + struct ethtool_link_usettings link_usettings; + + memcpy(&link_usettings.base, &from->base, sizeof(link_usettings)); + bitmap_to_u32array(link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + if (copy_to_user(to, &link_usettings, sizeof(link_usettings))) + return -EFAULT; + + return 0; +} + +/* Query device for its ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::get_link_ksettings, even if legacy + * ethtool_ops::get_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_GSET for + * this driver, so that they can correctly access the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_get_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err = 0; + struct ethtool_link_ksettings link_ksettings; + + ASSERT_RTNL(); + + if (!dev->ethtool_ops->get_link_ksettings) + return -EOPNOTSUPP; + + /* handle bitmap nbits handshake */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) { + /* wrong link mode nbits requested */ + memset(&link_ksettings, 0, sizeof(link_ksettings)); + /* keep cmd field reset to 0 */ + /* send back number of words required as negative val */ + compiletime_assert(__ETHTOOL_LINK_MODE_MASK_NU32 <= S8_MAX, + "need too many bits for link modes!"); + link_ksettings.base.link_mode_masks_nwords + = -((s8)__ETHTOOL_LINK_MODE_MASK_NU32); + + /* copy the base fields back to user, not the link + * mode bitmaps + */ + if (copy_to_user(useraddr, &link_ksettings.base, + sizeof(link_ksettings.base))) + return -EFAULT; + + return 0; + } + + /* handshake successful: user/kernel agree on + * link_mode_masks_nwords + */ + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); + if (err < 0) + return err; + + /* make sure we tell the right values to user */ + link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + + return store_link_ksettings_for_user(useraddr, &link_ksettings); +} + +/* Update device ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::set_link_ksettings, even if legacy + * ethtool_ops::set_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_SSET for + * this driver, so that they can correctly update the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_set_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err; + struct ethtool_link_ksettings link_ksettings; + + ASSERT_RTNL(); + + if (!dev->ethtool_ops->set_link_ksettings) + return -EOPNOTSUPP; + + /* make sure nbits field has expected value */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + /* copy the whole structure, now that we know it has expected + * format + */ + err = load_link_ksettings_from_user(&link_ksettings, useraddr); + if (err) + return err; + + /* re-check nwords field, just in case */ + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); +} + +/* Internal kernel helper to query a device ethtool_cmd settings. + * + * Note about transition to ethtool_link_settings API: We do not need + * (or want) this function to support "dev" instances that implement + * the ethtool_link_settings API as we will update the drivers calling + * this function to call __ethtool_get_link_ksettings instead, before + * the first drivers implement ethtool_ops::get_link_ksettings. + * + * TODO 1: at least make this function static when no driver is using it + * TODO 2: remove when ethtool_ops::get_settings disappears internally + */ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { ASSERT_RTNL(); @@ -400,30 +753,112 @@ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) } EXPORT_SYMBOL(__ethtool_get_settings); +static void +warn_incomplete_ethtool_legacy_settings_conversion(const char *details) +{ + char name[sizeof(current->comm)]; + + pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n", + get_task_comm(name, current), details); +} + +/* Query device for its ethtool_cmd settings. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing get_link_ksettings + * API and drivers implementing get_settings API. When drivers + * implement get_link_ksettings and report higher link mode bits, a + * kernel warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, but the command is successful + * (only the lower link mode bits reported back to user). + */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { - int err; struct ethtool_cmd cmd; - err = __ethtool_get_settings(dev, &cmd); - if (err < 0) - return err; + ASSERT_RTNL(); + + if (dev->ethtool_ops->get_link_ksettings) { + /* First, use link_ksettings API if it is supported */ + int err; + struct ethtool_link_ksettings link_ksettings; + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, + &link_ksettings); + if (err < 0) + return err; + if (!convert_link_ksettings_to_legacy_settings(&cmd, + &link_ksettings)) + warn_incomplete_ethtool_legacy_settings_conversion( + "link modes are only partially reported"); + + /* send a sensible cmd tag back to user */ + cmd.cmd = ETHTOOL_GSET; + } else { + int err; + /* TODO: return -EOPNOTSUPP when + * ethtool_ops::get_settings disappears internally + */ + + /* driver doesn't support %ethtool_link_ksettings + * API. revert to legacy %ethtool_cmd API, unless it's + * not supported either. + */ + err = __ethtool_get_settings(dev, &cmd); + if (err < 0) + return err; + } if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; + return 0; } +/* Update device link settings with given ethtool_cmd. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing set_link_ksettings + * API and drivers implementing set_settings API. When drivers + * implement set_link_ksettings and user's request updates deprecated + * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel + * warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, and the request is rejected. + */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_cmd cmd; - if (!dev->ethtool_ops->set_settings) - return -EOPNOTSUPP; + ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; + /* first, try new %ethtool_link_ksettings API. */ + if (dev->ethtool_ops->set_link_ksettings) { + struct ethtool_link_ksettings link_ksettings; + + if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, + &cmd)) + return -EINVAL; + + link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + return dev->ethtool_ops->set_link_ksettings(dev, + &link_ksettings); + } + + /* legacy %ethtool_cmd API */ + + /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings + * disappears internally + */ + + if (!dev->ethtool_ops->set_settings) + return -EOPNOTSUPP; + return dev->ethtool_ops->set_settings(dev, &cmd); } @@ -2252,6 +2687,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_PERQUEUE: rc = ethtool_set_per_queue(dev, useraddr); break; + case ETHTOOL_GLINKSETTINGS: + rc = ethtool_get_link_ksettings(dev, useraddr); + break; + case ETHTOOL_SLINKSETTINGS: + rc = ethtool_set_link_ksettings(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } -- cgit v1.2.3 From 3237fc63a3297d472a8cec33cb914f20570cfc23 Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Wed, 24 Feb 2016 10:58:11 -0800 Subject: net: ethtool: remove unused __ethtool_get_settings replaced by __ethtool_get_link_ksettings. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 ---- net/core/ethtool.c | 45 ++++++++++++++------------------------------- 2 files changed, 14 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 8a400a54c92e..e2b7bf27c03e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -150,10 +150,6 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); -/* DEPRECATED, use __ethtool_get_link_ksettings */ -extern int __ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd); - /** * struct ethtool_ops - optional netdev operations * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings diff --git a/net/core/ethtool.c b/net/core/ethtool.c index edcec56ed228..2966cd0d7c93 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -551,7 +551,12 @@ int __ethtool_get_link_ksettings(struct net_device *dev, * legacy %ethtool_cmd API, unless it's not supported either. * TODO: remove when ethtool_ops::get_settings disappears internally */ - err = __ethtool_get_settings(dev, &cmd); + if (!dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = ETHTOOL_GSET; + err = dev->ethtool_ops->get_settings(dev, &cmd); if (err < 0) return err; @@ -729,30 +734,6 @@ static int ethtool_set_link_ksettings(struct net_device *dev, return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); } -/* Internal kernel helper to query a device ethtool_cmd settings. - * - * Note about transition to ethtool_link_settings API: We do not need - * (or want) this function to support "dev" instances that implement - * the ethtool_link_settings API as we will update the drivers calling - * this function to call __ethtool_get_link_ksettings instead, before - * the first drivers implement ethtool_ops::get_link_ksettings. - * - * TODO 1: at least make this function static when no driver is using it - * TODO 2: remove when ethtool_ops::get_settings disappears internally - */ -int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - ASSERT_RTNL(); - - if (!dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; - - memset(cmd, 0, sizeof(struct ethtool_cmd)); - cmd->cmd = ETHTOOL_GSET; - return dev->ethtool_ops->get_settings(dev, cmd); -} -EXPORT_SYMBOL(__ethtool_get_settings); - static void warn_incomplete_ethtool_legacy_settings_conversion(const char *details) { @@ -796,16 +777,18 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) /* send a sensible cmd tag back to user */ cmd.cmd = ETHTOOL_GSET; } else { - int err; - /* TODO: return -EOPNOTSUPP when - * ethtool_ops::get_settings disappears internally - */ - /* driver doesn't support %ethtool_link_ksettings * API. revert to legacy %ethtool_cmd API, unless it's * not supported either. */ - err = __ethtool_get_settings(dev, &cmd); + int err; + + if (!dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = ETHTOOL_GSET; + err = dev->ethtool_ops->get_settings(dev, &cmd); if (err < 0) return err; } -- cgit v1.2.3 From 871b642adebe300be2e50aa5f65a418510f636ec Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 26 Feb 2016 10:45:37 +0100 Subject: netdev: introduce ndo_set_rx_headroom This method allows the controlling device (i.e. the bridge) to specify additional headroom to be allocated for skb head on frame reception. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e52077ffe5ed..efe7cec111fa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1093,6 +1093,12 @@ struct tc_to_netdev { * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while * sampling packet. + * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); + * This function is used to specify the headroom that the skb must + * consider when allocation skb during packet reception. Setting + * appropriate rx headroom value allows avoiding skb head copy on + * forward. Setting a negative value reset the rx headroom to the + * default value. * */ struct net_device_ops { @@ -1278,6 +1284,8 @@ struct net_device_ops { bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); + void (*ndo_set_rx_headroom)(struct net_device *dev, + int needed_headroom); }; /** @@ -1315,6 +1323,8 @@ struct net_device_ops { * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured + * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external + * entity (i.e. the master device for bridged veth) */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1343,6 +1353,7 @@ enum netdev_priv_flags { IFF_L3MDEV_SLAVE = 1<<23, IFF_TEAM = 1<<24, IFF_RXFH_CONFIGURED = 1<<25, + IFF_PHONY_HEADROOM = 1<<26, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1937,6 +1948,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); +/* returns the headroom that the master device needs to take in account + * when forwarding to this dev + */ +static inline unsigned netdev_get_fwd_headroom(struct net_device *dev) +{ + return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom; +} + +static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr) +{ + if (dev->netdev_ops->ndo_set_rx_headroom) + dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr); +} + +/* set the device rx headroom to the dev's default */ +static inline void netdev_reset_rx_headroom(struct net_device *dev) +{ + netdev_set_rx_headroom(dev, -1); +} + /* * Net namespace inlines */ -- cgit v1.2.3 From 09d4d087cd4869859fcc5dfc692f0830550a1b48 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 26 Feb 2016 17:32:24 +0100 Subject: mlx4: Implement devlink interface Implement newly introduced devlink interface. Add devlink port instances for every port and set the port types accordingly. Signed-off-by: Jiri Pirko v2->v3: -add dev param to devlink_register (api change) Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 7 ++++ drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 ++++- drivers/net/ethernet/mellanox/mlx4/intf.c | 9 ++++++ drivers/net/ethernet/mellanox/mlx4/main.c | 44 +++++++++++++++++++------- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 ++ include/linux/mlx4/driver.h | 3 ++ 6 files changed, 60 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 1c7ab6cabbb8..a15a7b37d386 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -2519,6 +2520,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) } ibdev->ib_active = true; + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + devlink_port_type_ib_set(mlx4_get_devlink_port(dev, i), + &ibdev->ib_dev); if (mlx4_is_mfunc(ibdev->dev)) init_pkeys(ibdev); @@ -2643,7 +2647,10 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) { struct mlx4_ib_dev *ibdev = ibdev_ptr; int p; + int i; + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + devlink_port_type_clear(mlx4_get_devlink_port(dev, i)); ibdev->ib_active = false; flush_workqueue(wq); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 96d95cb36c52..e26b110e27da 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -2033,8 +2034,11 @@ void mlx4_en_destroy_netdev(struct net_device *dev) en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); /* Unregister device - this will close the port if it was up */ - if (priv->registered) + if (priv->registered) { + devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, + priv->port)); unregister_netdev(dev); + } if (priv->allocated) mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE); @@ -3051,6 +3055,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } priv->registered = 1; + devlink_port_type_eth_set(mlx4_get_devlink_port(mdev->dev, priv->port), + dev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 0472941af820..dec77d6f0ac9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "mlx4.h" @@ -249,3 +250,11 @@ void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int return result; } EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev); + +struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port) +{ + struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; + + return &info->devlink_port; +} +EXPORT_SYMBOL_GPL(mlx4_get_devlink_port); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2cc3c626c3fe..4f5cfe4989ce 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -2881,8 +2882,13 @@ no_msi: static int mlx4_init_port_info(struct mlx4_dev *dev, int port) { + struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; - int err = 0; + int err; + + err = devlink_port_register(devlink, &info->devlink_port, port); + if (err) + return err; info->dev = dev; info->port = port; @@ -2907,6 +2913,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) err = device_create_file(&dev->persist->pdev->dev, &info->port_attr); if (err) { mlx4_err(dev, "Failed to create file for port %d\n", port); + devlink_port_unregister(&info->devlink_port); info->port = -1; } @@ -3680,21 +3687,23 @@ err_disable_pdev: static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { + struct devlink *devlink; struct mlx4_priv *priv; struct mlx4_dev *dev; int ret; printk_once(KERN_INFO "%s", mlx4_version); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) + devlink = devlink_alloc(NULL, sizeof(*priv)); + if (!devlink) return -ENOMEM; + priv = devlink_priv(devlink); dev = &priv->dev; dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL); if (!dev->persist) { - kfree(priv); - return -ENOMEM; + ret = -ENOMEM; + goto err_devlink_free; } dev->persist->pdev = pdev; dev->persist->dev = dev; @@ -3703,14 +3712,23 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&dev->persist->device_state_mutex); mutex_init(&dev->persist->interface_state_mutex); + ret = devlink_register(devlink, &pdev->dev); + if (ret) + goto err_persist_free; + ret = __mlx4_init_one(pdev, id->driver_data, priv); - if (ret) { - kfree(dev->persist); - kfree(priv); - } else { - pci_save_state(pdev); - } + if (ret) + goto err_devlink_unregister; + pci_save_state(pdev); + return 0; + +err_devlink_unregister: + devlink_unregister(devlink); +err_persist_free: + kfree(dev->persist); +err_devlink_free: + devlink_free(devlink); return ret; } @@ -3811,6 +3829,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); struct mlx4_dev *dev = persist->dev; struct mlx4_priv *priv = mlx4_priv(dev); + struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; mutex_lock(&persist->interface_state_mutex); @@ -3841,8 +3860,9 @@ static void mlx4_remove_one(struct pci_dev *pdev) pci_release_regions(pdev); pci_disable_device(pdev); + devlink_unregister(devlink); kfree(dev->persist); - kfree(priv); + devlink_free(devlink); pci_set_drvdata(pdev, NULL); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 7baef52db6b7..ef9683101ead 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -828,6 +829,7 @@ struct mlx4_port_info { struct mlx4_roce_gid_table gid_table; int base_qpn; struct cpu_rmap *rmap; + struct devlink_port devlink_port; }; struct mlx4_sense { diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 2e8af001c5da..bd0e7075ea6d 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -33,6 +33,7 @@ #ifndef MLX4_DRIVER_H #define MLX4_DRIVER_H +#include #include struct mlx4_dev; @@ -89,6 +90,8 @@ int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); +struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); + static inline u64 mlx4_mac_to_u64(u8 *addr) { u64 mac = 0; -- cgit v1.2.3 From 6b6c07bdcdc97ccac2596063bfc32a5faddfe884 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 2 Mar 2016 00:13:39 +0200 Subject: net/mlx5: Make command timeout way shorter The command timeout is terribly long, whole two hours. Make it 60s so if things do go wrong, the user gets feedback in relatively short time, so they can take corrective actions and/or investigate using tools and such. Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Or Gerlitz Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a815da92d4eb..3388a43b78f6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -54,7 +54,7 @@ enum { /* one minute for the sake of bringup. Generally, commands must always * complete and we may need to increase this timeout value */ - MLX5_CMD_TIMEOUT_MSEC = 7200 * 1000, + MLX5_CMD_TIMEOUT_MSEC = 60 * 1000, MLX5_CMD_WQ_MAX_NAME = 32, }; -- cgit v1.2.3 From 0ba422410bbf7081c3c7d7b2dcc10e9eb5cb46f7 Mon Sep 17 00:00:00 2001 From: Moshe Lazer Date: Wed, 2 Mar 2016 00:13:40 +0200 Subject: net/mlx5: Fix global UAR mapping Avoid double mapping of io mapped memory, Device page may be mapped to non-cached(NC) or to write-combining(WC). The code before this fix tries to map it both to WC and NC contrary to what stated in Intel's software developer manual. Here we remove the global WC mapping of all UARS "dev->priv.bf_mapping", since UAR mapping should be decided per UAR (e.g we want different mappings for EQs, CQs vs QPs). Caller will now have to choose whether to map via write-combining API or not. mlx5e SQs will choose write-combining in order to perform BlueFlame writes. Fixes: 88a85f99e51f ('TX latency optimization to save DMA reads') Signed-off-by: Moshe Lazer Reviewed-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 16 +++++-------- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 ++++++---- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 28 +--------------------- drivers/net/ethernet/mellanox/mlx5/core/uar.c | 29 ++++++++++++++--------- include/linux/mlx5/driver.h | 5 ++-- 6 files changed, 36 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b289660568cf..9c0e80e64b43 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -388,6 +388,7 @@ struct mlx5e_sq_dma { enum { MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, + MLX5E_SQ_STATE_BF_ENABLE, }; struct mlx5e_sq { @@ -416,7 +417,6 @@ struct mlx5e_sq { struct mlx5_wq_cyc wq; u32 dma_fifo_mask; void __iomem *uar_map; - void __iomem *uar_bf_map; struct netdev_queue *txq; u32 sqn; u16 bf_buf_size; @@ -664,16 +664,12 @@ static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, * doorbell */ wmb(); - - if (bf_sz) { - __iowrite64_copy(sq->uar_bf_map + ofst, &wqe->ctrl, bf_sz); - - /* flush the write-combining mapped buffer */ - wmb(); - - } else { + if (bf_sz) + __iowrite64_copy(sq->uar_map + ofst, &wqe->ctrl, bf_sz); + else mlx5_write64((__be32 *)&wqe->ctrl, sq->uar_map + ofst, NULL); - } + /* flush the write-combining mapped buffer */ + wmb(); sq->bf_offset ^= sq->bf_buf_size; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b20a35bd1d4f..5063c0e0f8ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -548,7 +548,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, int txq_ix; int err; - err = mlx5_alloc_map_uar(mdev, &sq->uar); + err = mlx5_alloc_map_uar(mdev, &sq->uar, true); if (err) return err; @@ -560,8 +560,12 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, goto err_unmap_free_uar; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - sq->uar_map = sq->uar.map; - sq->uar_bf_map = sq->uar.bf_map; + if (sq->uar.bf_map) { + set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state); + sq->uar_map = sq->uar.bf_map; + } else { + sq->uar_map = sq->uar.map; + } sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2; sq->max_inline = param->max_inline; @@ -2418,7 +2422,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) priv = netdev_priv(netdev); - err = mlx5_alloc_map_uar(mdev, &priv->cq_uar); + err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false); if (err) { mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err); goto err_free_netdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index a05c070cbc2f..c34f4f3e9537 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -303,7 +303,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) { int bf_sz = 0; - if (bf && sq->uar_bf_map) + if (bf && test_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state)) bf_sz = wi->num_wqebbs << 3; cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 1545a944c309..8b7133de498e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -767,22 +767,6 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) return -ENOTSUPP; } -static int map_bf_area(struct mlx5_core_dev *dev) -{ - resource_size_t bf_start = pci_resource_start(dev->pdev, 0); - resource_size_t bf_len = pci_resource_len(dev->pdev, 0); - - dev->priv.bf_mapping = io_mapping_create_wc(bf_start, bf_len); - - return dev->priv.bf_mapping ? 0 : -ENOMEM; -} - -static void unmap_bf_area(struct mlx5_core_dev *dev) -{ - if (dev->priv.bf_mapping) - io_mapping_free(dev->priv.bf_mapping); -} - static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) { struct mlx5_device_context *dev_ctx; @@ -1103,14 +1087,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto err_stop_eqs; } - if (map_bf_area(dev)) - dev_err(&pdev->dev, "Failed to map blue flame area\n"); - err = mlx5_irq_set_affinity_hints(dev); - if (err) { + if (err) dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); - goto err_unmap_bf_area; - } MLX5_INIT_DOORBELL_LOCK(&priv->cq_uar_lock); @@ -1169,10 +1148,6 @@ err_fs: mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); mlx5_irq_clear_affinity_hints(dev); - -err_unmap_bf_area: - unmap_bf_area(dev); - free_comp_eqs(dev); err_stop_eqs: @@ -1242,7 +1217,6 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); mlx5_irq_clear_affinity_hints(dev); - unmap_bf_area(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_free_uuars(dev, &priv->uuari); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index eb05c845ece9..8ba080e441a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -226,7 +226,8 @@ int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari) return 0; } -int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar, + bool map_wc) { phys_addr_t pfn; phys_addr_t uar_bar_start; @@ -240,20 +241,26 @@ int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) uar_bar_start = pci_resource_start(mdev->pdev, 0); pfn = (uar_bar_start >> PAGE_SHIFT) + uar->index; - uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); - if (!uar->map) { - mlx5_core_warn(mdev, "ioremap() failed, %d\n", err); - err = -ENOMEM; - goto err_free_uar; - } - if (mdev->priv.bf_mapping) - uar->bf_map = io_mapping_map_wc(mdev->priv.bf_mapping, - uar->index << PAGE_SHIFT); + if (map_wc) { + uar->bf_map = ioremap_wc(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->bf_map) { + mlx5_core_warn(mdev, "ioremap_wc() failed\n"); + uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->map) + goto err_free_uar; + } + } else { + uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->map) + goto err_free_uar; + } return 0; err_free_uar: + mlx5_core_warn(mdev, "ioremap() failed\n"); + err = -ENOMEM; mlx5_cmd_free_uar(mdev, uar->index); return err; @@ -262,8 +269,8 @@ EXPORT_SYMBOL(mlx5_alloc_map_uar); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) { - io_mapping_unmap(uar->bf_map); iounmap(uar->map); + iounmap(uar->bf_map); mlx5_cmd_free_uar(mdev, uar->index); } EXPORT_SYMBOL(mlx5_unmap_free_uar); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3388a43b78f6..bb1a880a5bc5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -460,8 +460,6 @@ struct mlx5_priv { struct mlx5_uuar_info uuari; MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); - struct io_mapping *bf_mapping; - /* pages stuff */ struct workqueue_struct *pg_wq; struct rb_root page_root; @@ -719,7 +717,8 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); -int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar, + bool map_wc); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 64d4e3431e686dc37ce388ba531c4c4e866fb141 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Sat, 27 Feb 2016 20:19:54 -0800 Subject: net: remove skb_sender_cpu_clear() After commit 52bd2d62ce67 ("net: better skb->sender_cpu and skb->napi_id cohabitation") skb_sender_cpu_clear() becomes empty and can be removed. Cc: Eric Dumazet Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ---- net/bridge/br_forward.c | 1 - net/core/filter.c | 2 -- net/core/skbuff.c | 1 - net/ipv4/ip_forward.c | 1 - net/ipv6/ip6_output.c | 1 - net/netfilter/ipvs/ip_vs_xmit.c | 6 ------ net/netfilter/nf_dup_netdev.c | 1 - net/sched/act_mirred.c | 1 - 9 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eab4f8fbed58..797cefb888fb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1161,10 +1161,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; -static inline void skb_sender_cpu_clear(struct sk_buff *skb) -{ -} - #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index fcdb86dd5a23..f47759f05b6d 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -44,7 +44,6 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb skb_push(skb, ETH_HLEN); br_drop_fake_rtable(skb); - skb_sender_cpu_clear(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && (skb->protocol == htons(ETH_P_8021Q) || diff --git a/net/core/filter.c b/net/core/filter.c index a3aba15a8025..5e2a3b5e5196 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1597,7 +1597,6 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) } skb2->dev = dev; - skb_sender_cpu_clear(skb2); return dev_queue_xmit(skb2); } @@ -1650,7 +1649,6 @@ int skb_do_redirect(struct sk_buff *skb) } skb->dev = dev; - skb_sender_cpu_clear(skb); return dev_queue_xmit(skb); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 488566b09c6d..7af7ec635d90 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4302,7 +4302,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - skb_sender_cpu_clear(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index da0d7ce85844..af18f1e4889e 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -71,7 +71,6 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s if (unlikely(opt->optlen)) ip_forward_options(skb); - skb_sender_cpu_clear(skb); return dst_output(net, sk, skb); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a163102f1803..9428345d3a07 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -332,7 +332,6 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - skb_sender_cpu_clear(skb); return dst_output(net, sk, skb); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index a3f5cd9b3c4c..dc196a0f501d 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -531,8 +531,6 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset(skb); skb_forward_csum(skb); - if (!skb->sk) - skb_sender_cpu_clear(skb); } return ret; } @@ -573,8 +571,6 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!local) { skb_forward_csum(skb); - if (!skb->sk) - skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else @@ -595,8 +591,6 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!local) { ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); - if (!skb->sk) - skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index 8414ee1a0319..7ec69723940f 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -31,7 +31,6 @@ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif) skb_push(skb, skb->mac_len); skb->dev = dev; - skb_sender_cpu_clear(skb); dev_queue_xmit(skb); } EXPORT_SYMBOL_GPL(nf_dup_netdev_egress); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6b284d991e0b..e8a760cf7775 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -182,7 +182,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; - skb_sender_cpu_clear(skb2); err = dev_queue_xmit(skb2); if (err) { -- cgit v1.2.3 From 4ac801b77e6f06e6b12c069fd29216a4102065fb Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 28 Feb 2016 12:26:52 +0200 Subject: qed: Semantic refactoring of interrupt code Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 6 +- drivers/net/ethernet/qlogic/qed/qed_int.c | 155 ++++++++++++++++------------- drivers/net/ethernet/qlogic/qed/qed_int.h | 6 +- drivers/net/ethernet/qlogic/qed/qed_main.c | 15 +-- include/linux/qed/qed_if.h | 6 ++ 5 files changed, 111 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index acfe7be49a58..d9a5175ebd04 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1011,13 +1011,17 @@ static void qed_hw_get_resc(struct qed_hwfn *p_hwfn) { u32 *resc_start = p_hwfn->hw_info.resc_start; u32 *resc_num = p_hwfn->hw_info.resc_num; + struct qed_sb_cnt_info sb_cnt_info; int num_funcs, i; num_funcs = MAX_NUM_PFS_BB; + memset(&sb_cnt_info, 0, sizeof(sb_cnt_info)); + qed_int_get_num_sbs(p_hwfn, &sb_cnt_info); + resc_num[QED_SB] = min_t(u32, (MAX_SB_PER_PATH_BB / num_funcs), - qed_int_get_num_sbs(p_hwfn, NULL)); + sb_cnt_info.sb_cnt); resc_num[QED_L2_QUEUE] = MAX_NUM_L2_QUEUES_BB / num_funcs; resc_num[QED_VPORT] = MAX_NUM_VPORTS_BB / num_funcs; resc_num[QED_RSS_ENG] = ETH_RSS_ENGINE_NUM_BB / num_funcs; diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index fa73daa94655..7fd1be61de5c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -343,17 +343,17 @@ void qed_int_sp_dpc(unsigned long hwfn_cookie) static void qed_int_sb_attn_free(struct qed_hwfn *p_hwfn) { - struct qed_dev *cdev = p_hwfn->cdev; - struct qed_sb_attn_info *p_sb = p_hwfn->p_sb_attn; - - if (p_sb) { - if (p_sb->sb_attn) - dma_free_coherent(&cdev->pdev->dev, - SB_ATTN_ALIGNED_SIZE(p_hwfn), - p_sb->sb_attn, - p_sb->sb_phys); - kfree(p_sb); - } + struct qed_sb_attn_info *p_sb = p_hwfn->p_sb_attn; + + if (!p_sb) + return; + + if (p_sb->sb_attn) + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + SB_ATTN_ALIGNED_SIZE(p_hwfn), + p_sb->sb_attn, + p_sb->sb_phys); + kfree(p_sb); } static void qed_int_sb_attn_setup(struct qed_hwfn *p_hwfn, @@ -433,6 +433,7 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn, u16 vf_number, u8 vf_valid) { + struct qed_dev *cdev = p_hwfn->cdev; u32 cau_state; memset(p_sb_entry, 0, sizeof(*p_sb_entry)); @@ -451,14 +452,12 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn, cau_state = CAU_HC_DISABLE_STATE; - if (p_hwfn->cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) { + if (cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) { cau_state = CAU_HC_ENABLE_STATE; - if (!p_hwfn->cdev->rx_coalesce_usecs) - p_hwfn->cdev->rx_coalesce_usecs = - QED_CAU_DEF_RX_USECS; - if (!p_hwfn->cdev->tx_coalesce_usecs) - p_hwfn->cdev->tx_coalesce_usecs = - QED_CAU_DEF_TX_USECS; + if (!cdev->rx_coalesce_usecs) + cdev->rx_coalesce_usecs = QED_CAU_DEF_RX_USECS; + if (!cdev->tx_coalesce_usecs) + cdev->tx_coalesce_usecs = QED_CAU_DEF_TX_USECS; } SET_FIELD(p_sb_entry->data, CAU_SB_ENTRY_STATE0, cau_state); @@ -638,8 +637,10 @@ int qed_int_sb_release(struct qed_hwfn *p_hwfn, sb_info->sb_ack = 0; memset(sb_info->sb_virt, 0, sizeof(*sb_info->sb_virt)); - p_hwfn->sbs_info[sb_id] = NULL; - p_hwfn->num_sbs--; + if (p_hwfn->sbs_info[sb_id] != NULL) { + p_hwfn->sbs_info[sb_id] = NULL; + p_hwfn->num_sbs--; + } return 0; } @@ -648,14 +649,15 @@ static void qed_int_sp_sb_free(struct qed_hwfn *p_hwfn) { struct qed_sb_sp_info *p_sb = p_hwfn->p_sp_sb; - if (p_sb) { - if (p_sb->sb_info.sb_virt) - dma_free_coherent(&p_hwfn->cdev->pdev->dev, - SB_ALIGNED_SIZE(p_hwfn), - p_sb->sb_info.sb_virt, - p_sb->sb_info.sb_phys); - kfree(p_sb); - } + if (!p_sb) + return; + + if (p_sb->sb_info.sb_virt) + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + SB_ALIGNED_SIZE(p_hwfn), + p_sb->sb_info.sb_virt, + p_sb->sb_info.sb_phys); + kfree(p_sb); } static int qed_int_sp_sb_alloc(struct qed_hwfn *p_hwfn, @@ -718,36 +720,36 @@ int qed_int_register_cb(struct qed_hwfn *p_hwfn, __le16 **p_fw_cons) { struct qed_sb_sp_info *p_sp_sb = p_hwfn->p_sp_sb; - int qed_status = -ENOMEM; + int rc = -ENOMEM; u8 pi; /* Look for a free index */ for (pi = 0; pi < ARRAY_SIZE(p_sp_sb->pi_info_arr); pi++) { - if (!p_sp_sb->pi_info_arr[pi].comp_cb) { - p_sp_sb->pi_info_arr[pi].comp_cb = comp_cb; - p_sp_sb->pi_info_arr[pi].cookie = cookie; - *sb_idx = pi; - *p_fw_cons = &p_sp_sb->sb_info.sb_virt->pi_array[pi]; - qed_status = 0; - break; - } + if (p_sp_sb->pi_info_arr[pi].comp_cb) + continue; + + p_sp_sb->pi_info_arr[pi].comp_cb = comp_cb; + p_sp_sb->pi_info_arr[pi].cookie = cookie; + *sb_idx = pi; + *p_fw_cons = &p_sp_sb->sb_info.sb_virt->pi_array[pi]; + rc = 0; + break; } - return qed_status; + return rc; } int qed_int_unregister_cb(struct qed_hwfn *p_hwfn, u8 pi) { struct qed_sb_sp_info *p_sp_sb = p_hwfn->p_sp_sb; - int qed_status = -ENOMEM; - if (p_sp_sb->pi_info_arr[pi].comp_cb) { - p_sp_sb->pi_info_arr[pi].comp_cb = NULL; - p_sp_sb->pi_info_arr[pi].cookie = NULL; - qed_status = 0; - } + if (p_sp_sb->pi_info_arr[pi].comp_cb == NULL) + return -ENOMEM; - return qed_status; + p_sp_sb->pi_info_arr[pi].comp_cb = NULL; + p_sp_sb->pi_info_arr[pi].cookie = NULL; + + return 0; } u16 qed_int_get_sp_sb_id(struct qed_hwfn *p_hwfn) @@ -937,6 +939,39 @@ void qed_int_igu_init_pure_rt(struct qed_hwfn *p_hwfn, } } +static u32 qed_int_igu_read_cam_block(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u16 sb_id) +{ + u32 val = qed_rd(p_hwfn, p_ptt, + IGU_REG_MAPPING_MEMORY + + sizeof(u32) * sb_id); + struct qed_igu_block *p_block; + + p_block = &p_hwfn->hw_info.p_igu_info->igu_map.igu_blocks[sb_id]; + + /* stop scanning when hit first invalid PF entry */ + if (!GET_FIELD(val, IGU_MAPPING_LINE_VALID) && + GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID)) + goto out; + + /* Fill the block information */ + p_block->status = QED_IGU_STATUS_VALID; + p_block->function_id = GET_FIELD(val, + IGU_MAPPING_LINE_FUNCTION_NUMBER); + p_block->is_pf = GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID); + p_block->vector_number = GET_FIELD(val, + IGU_MAPPING_LINE_VECTOR_NUMBER); + + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, + "IGU_BLOCK: [SB 0x%04x, Value in CAM 0x%08x] func_id = %d is_pf = %d vector_num = 0x%x\n", + sb_id, val, p_block->function_id, + p_block->is_pf, p_block->vector_number); + +out: + return val; +} + int qed_int_igu_read_cam(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { @@ -963,26 +998,13 @@ int qed_int_igu_read_cam(struct qed_hwfn *p_hwfn, sb_id++) { blk = &p_igu_info->igu_map.igu_blocks[sb_id]; - val = qed_rd(p_hwfn, p_ptt, - IGU_REG_MAPPING_MEMORY + sizeof(u32) * sb_id); + val = qed_int_igu_read_cam_block(p_hwfn, p_ptt, sb_id); /* stop scanning when hit first invalid PF entry */ if (!GET_FIELD(val, IGU_MAPPING_LINE_VALID) && GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID)) break; - blk->status = QED_IGU_STATUS_VALID; - blk->function_id = GET_FIELD(val, - IGU_MAPPING_LINE_FUNCTION_NUMBER); - blk->is_pf = GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID); - blk->vector_number = GET_FIELD(val, - IGU_MAPPING_LINE_VECTOR_NUMBER); - - DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, - "IGU_BLOCK[sb_id]:%x:func_id = %d is_pf = %d vector_num = 0x%x\n", - val, blk->function_id, blk->is_pf, - blk->vector_number); - if (blk->is_pf) { if (blk->function_id == p_hwfn->rel_pf_id) { blk->status |= QED_IGU_STATUS_PF; @@ -1121,18 +1143,17 @@ void qed_int_setup(struct qed_hwfn *p_hwfn, qed_int_sp_dpc_setup(p_hwfn); } -int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, - int *p_iov_blks) +void qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, + struct qed_sb_cnt_info *p_sb_cnt_info) { struct qed_igu_info *info = p_hwfn->hw_info.p_igu_info; - if (!info) - return 0; - - if (p_iov_blks) - *p_iov_blks = info->free_blks; + if (!info || !p_sb_cnt_info) + return; - return info->igu_sb_cnt; + p_sb_cnt_info->sb_cnt = info->igu_sb_cnt; + p_sb_cnt_info->sb_iov_cnt = info->igu_sb_cnt_iov; + p_sb_cnt_info->sb_free_blk = info->free_blks; } void qed_int_disable_post_isr_release(struct qed_dev *cdev) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index 51e0b09a7f47..c57f2e680770 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -161,12 +161,12 @@ void qed_int_sp_dpc(unsigned long hwfn_cookie); * blocks configured for this funciton in the igu. * * @param p_hwfn - * @param p_iov_blks - configured free blks for vfs + * @param p_sb_cnt_info * * @return int - number of status blocks configured */ -int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, - int *p_iov_blks); +void qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, + struct qed_sb_cnt_info *p_sb_cnt_info); /** * @brief qed_int_disable_post_isr_release - performs the cleanup post ISR diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 25d6e91335ea..caa689e6575c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -634,15 +634,18 @@ static int qed_get_int_fp(struct qed_dev *cdev, struct qed_int_info *info) static int qed_slowpath_setup_int(struct qed_dev *cdev, enum qed_int_mode int_mode) { - int rc, i; - u8 num_vectors = 0; - + struct qed_sb_cnt_info sb_cnt_info; + int rc; + int i; memset(&cdev->int_params, 0, sizeof(struct qed_int_params)); cdev->int_params.in.int_mode = int_mode; - for_each_hwfn(cdev, i) - num_vectors += qed_int_get_num_sbs(&cdev->hwfns[i], NULL) + 1; - cdev->int_params.in.num_vectors = num_vectors; + for_each_hwfn(cdev, i) { + memset(&sb_cnt_info, 0, sizeof(sb_cnt_info)); + qed_int_get_num_sbs(&cdev->hwfns[i], &sb_cnt_info); + cdev->int_params.in.num_vectors += sb_cnt_info.sb_cnt; + cdev->int_params.in.num_vectors++; /* slowpath */ + } /* We want a minimum of one slowpath and one fastpath vector per hwfn */ cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 3d43c1d4ecef..1f7599c77cd4 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -446,6 +446,12 @@ struct qed_eth_stats { #define RX_PI 0 #define TX_PI(tc) (RX_PI + 1 + tc) +struct qed_sb_cnt_info { + int sb_cnt; + int sb_iov_cnt; + int sb_free_blk; +}; + static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) { u32 prod = 0; -- cgit v1.2.3 From a67dd266adf42a24df31380e9da78390bb4d65ef Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 25 Feb 2016 10:08:35 +0100 Subject: netfilter: xtables: prepare for on-demand hook register This change prepares for upcoming on-demand xtables hook registration. We change the protoypes of the register/unregister functions. A followup patch will then add nf_hook_register/unregister calls to the iptables one. Once a hook is registered packets will be picked up, so all assignments of the form net->ipv4.iptable_$table = new_table have to be moved to ip(6)t_register_table, else we can see NULL net->ipv4.iptable_$table later. This patch doesn't change functionality; without this the actual change simply gets too big. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_arp/arp_tables.h | 9 +++++---- include/linux/netfilter_ipv4/ip_tables.h | 9 +++++---- include/linux/netfilter_ipv6/ip6_tables.h | 9 +++++---- net/ipv4/netfilter/arp_tables.c | 25 ++++++++++++++----------- net/ipv4/netfilter/arptable_filter.c | 11 ++++++----- net/ipv4/netfilter/ip_tables.c | 21 ++++++++++----------- net/ipv4/netfilter/iptable_filter.c | 9 +++++---- net/ipv4/netfilter/iptable_mangle.c | 9 +++++---- net/ipv4/netfilter/iptable_nat.c | 8 +++++--- net/ipv4/netfilter/iptable_raw.c | 9 +++++---- net/ipv4/netfilter/iptable_security.c | 9 +++++---- net/ipv6/netfilter/ip6_tables.c | 23 ++++++++++++----------- net/ipv6/netfilter/ip6table_filter.c | 9 +++++---- net/ipv6/netfilter/ip6table_mangle.c | 9 +++++---- net/ipv6/netfilter/ip6table_nat.c | 8 +++++--- net/ipv6/netfilter/ip6table_raw.c | 9 +++++---- net/ipv6/netfilter/ip6table_security.c | 9 +++++---- 17 files changed, 107 insertions(+), 88 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 6f074db2f23d..029b95e8924e 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -48,10 +48,11 @@ struct arpt_error { } extern void *arpt_alloc_initial_table(const struct xt_table *); -extern struct xt_table *arpt_register_table(struct net *net, - const struct xt_table *table, - const struct arpt_replace *repl); -extern void arpt_unregister_table(struct xt_table *table); +int arpt_register_table(struct net *net, const struct xt_table *table, + const struct arpt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void arpt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index aa598f942c01..7bfc5893ec31 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -24,10 +24,11 @@ extern void ipt_init(void) __init; -extern struct xt_table *ipt_register_table(struct net *net, - const struct xt_table *table, - const struct ipt_replace *repl); -extern void ipt_unregister_table(struct net *net, struct xt_table *table); +int ipt_register_table(struct net *net, const struct xt_table *table, + const struct ipt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void ipt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); /* Standard entry. */ struct ipt_standard { diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 0f76e5c674f9..b21c392d6012 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -25,10 +25,11 @@ extern void ip6t_init(void) __init; extern void *ip6t_alloc_initial_table(const struct xt_table *); -extern struct xt_table *ip6t_register_table(struct net *net, - const struct xt_table *table, - const struct ip6t_replace *repl); -extern void ip6t_unregister_table(struct net *net, struct xt_table *table); +int ip6t_register_table(struct net *net, const struct xt_table *table, + const struct ip6t_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void ip6t_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b488cac9c5ca..00eed0852dfc 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1780,9 +1780,11 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -struct xt_table *arpt_register_table(struct net *net, - const struct xt_table *table, - const struct arpt_replace *repl) +int arpt_register_table(struct net *net, + const struct xt_table *table, + const struct arpt_replace *repl, + const struct nf_hook_ops *ops, + struct xt_table **res) { int ret; struct xt_table_info *newinfo; @@ -1791,10 +1793,8 @@ struct xt_table *arpt_register_table(struct net *net, struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); - if (!newinfo) { - ret = -ENOMEM; - goto out; - } + if (!newinfo) + return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); @@ -1809,15 +1809,18 @@ struct xt_table *arpt_register_table(struct net *net, ret = PTR_ERR(new_table); goto out_free; } - return new_table; + + WRITE_ONCE(*res, new_table); + + return ret; out_free: xt_free_table_info(newinfo); -out: - return ERR_PTR(ret); + return ret; } -void arpt_unregister_table(struct xt_table *table) +void arpt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { struct xt_table_info *private; void *loc_cpu_entry; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 1897ee160920..4c0241692576 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -38,19 +38,20 @@ static struct nf_hook_ops *arpfilter_ops __read_mostly; static int __net_init arptable_filter_net_init(struct net *net) { struct arpt_replace *repl; - + int err; + repl = arpt_alloc_initial_table(&packet_filter); if (repl == NULL) return -ENOMEM; - net->ipv4.arptable_filter = - arpt_register_table(net, &packet_filter, repl); + err = arpt_register_table(net, &packet_filter, repl, arpfilter_ops, + &net->ipv4.arptable_filter); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.arptable_filter); + return err; } static void __net_exit arptable_filter_net_exit(struct net *net) { - arpt_unregister_table(net->ipv4.arptable_filter); + arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops); } static struct pernet_operations arptable_filter_net_ops = { diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index b99affad6ba1..1eb4fe5b4702 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -2062,9 +2062,9 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -struct xt_table *ipt_register_table(struct net *net, - const struct xt_table *table, - const struct ipt_replace *repl) +int ipt_register_table(struct net *net, const struct xt_table *table, + const struct ipt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res) { int ret; struct xt_table_info *newinfo; @@ -2073,10 +2073,8 @@ struct xt_table *ipt_register_table(struct net *net, struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); - if (!newinfo) { - ret = -ENOMEM; - goto out; - } + if (!newinfo) + return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); @@ -2091,15 +2089,16 @@ struct xt_table *ipt_register_table(struct net *net, goto out_free; } - return new_table; + WRITE_ONCE(*res, new_table); + return ret; out_free: xt_free_table_info(newinfo); -out: - return ERR_PTR(ret); + return ret; } -void ipt_unregister_table(struct net *net, struct xt_table *table) +void ipt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { struct xt_table_info *private; void *loc_cpu_entry; diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 397ef2dd133e..3fbe4acacb27 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -54,6 +54,7 @@ module_param(forward, bool, 0000); static int __net_init iptable_filter_net_init(struct net *net) { struct ipt_replace *repl; + int err; repl = ipt_alloc_initial_table(&packet_filter); if (repl == NULL) @@ -62,15 +63,15 @@ static int __net_init iptable_filter_net_init(struct net *net) ((struct ipt_standard *)repl->entries)[1].target.verdict = forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; - net->ipv4.iptable_filter = - ipt_register_table(net, &packet_filter, repl); + err = ipt_register_table(net, &packet_filter, repl, filter_ops, + &net->ipv4.iptable_filter); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_filter); + return err; } static void __net_exit iptable_filter_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_filter); + ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops); } static struct pernet_operations iptable_filter_net_ops = { diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index ba5d392a13c4..668e79166b81 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -96,19 +96,20 @@ static struct nf_hook_ops *mangle_ops __read_mostly; static int __net_init iptable_mangle_net_init(struct net *net) { struct ipt_replace *repl; + int ret; repl = ipt_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; - net->ipv4.iptable_mangle = - ipt_register_table(net, &packet_mangler, repl); + ret = ipt_register_table(net, &packet_mangler, repl, mangle_ops, + &net->ipv4.iptable_mangle); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_mangle); + return ret; } static void __net_exit iptable_mangle_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_mangle); + ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops); } static struct pernet_operations iptable_mangle_net_ops = { diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index ae2cd2752046..e984f1d3017f 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -98,18 +98,20 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { static int __net_init iptable_nat_net_init(struct net *net) { struct ipt_replace *repl; + int ret; repl = ipt_alloc_initial_table(&nf_nat_ipv4_table); if (repl == NULL) return -ENOMEM; - net->ipv4.nat_table = ipt_register_table(net, &nf_nat_ipv4_table, repl); + ret = ipt_register_table(net, &nf_nat_ipv4_table, repl, + nf_nat_ipv4_ops, &net->ipv4.nat_table); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.nat_table); + return ret; } static void __net_exit iptable_nat_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.nat_table); + ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops); } static struct pernet_operations iptable_nat_net_ops = { diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 1ba02811acb0..9d78780a9036 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -37,19 +37,20 @@ static struct nf_hook_ops *rawtable_ops __read_mostly; static int __net_init iptable_raw_net_init(struct net *net) { struct ipt_replace *repl; + int ret; repl = ipt_alloc_initial_table(&packet_raw); if (repl == NULL) return -ENOMEM; - net->ipv4.iptable_raw = - ipt_register_table(net, &packet_raw, repl); + ret = ipt_register_table(net, &packet_raw, repl, rawtable_ops, + &net->ipv4.iptable_raw); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_raw); + return ret; } static void __net_exit iptable_raw_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_raw); + ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops); } static struct pernet_operations iptable_raw_net_ops = { diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index c2e23d5e9cd4..88bc52fb8f4a 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -54,19 +54,20 @@ static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init iptable_security_net_init(struct net *net) { struct ipt_replace *repl; + int ret; repl = ipt_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; - net->ipv4.iptable_security = - ipt_register_table(net, &security_table, repl); + ret = ipt_register_table(net, &security_table, repl, sectbl_ops, + &net->ipv4.iptable_security); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_security); + return ret; } static void __net_exit iptable_security_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_security); + ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops); } static struct pernet_operations iptable_security_net_ops = { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 99425cf2819b..052d7447b52e 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -2071,9 +2071,10 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -struct xt_table *ip6t_register_table(struct net *net, - const struct xt_table *table, - const struct ip6t_replace *repl) +int ip6t_register_table(struct net *net, const struct xt_table *table, + const struct ip6t_replace *repl, + const struct nf_hook_ops *ops, + struct xt_table **res) { int ret; struct xt_table_info *newinfo; @@ -2082,10 +2083,8 @@ struct xt_table *ip6t_register_table(struct net *net, struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); - if (!newinfo) { - ret = -ENOMEM; - goto out; - } + if (!newinfo) + return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); @@ -2099,15 +2098,17 @@ struct xt_table *ip6t_register_table(struct net *net, ret = PTR_ERR(new_table); goto out_free; } - return new_table; + + WRITE_ONCE(*res, new_table); + return ret; out_free: xt_free_table_info(newinfo); -out: - return ERR_PTR(ret); + return ret; } -void ip6t_unregister_table(struct net *net, struct xt_table *table) +void ip6t_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { struct xt_table_info *private; void *loc_cpu_entry; diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 8b277b983ca5..d191d54cdf50 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -47,6 +47,7 @@ module_param(forward, bool, 0000); static int __net_init ip6table_filter_net_init(struct net *net) { struct ip6t_replace *repl; + int err; repl = ip6t_alloc_initial_table(&packet_filter); if (repl == NULL) @@ -55,15 +56,15 @@ static int __net_init ip6table_filter_net_init(struct net *net) ((struct ip6t_standard *)repl->entries)[1].target.verdict = forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; - net->ipv6.ip6table_filter = - ip6t_register_table(net, &packet_filter, repl); + err = ip6t_register_table(net, &packet_filter, repl, filter_ops, + &net->ipv6.ip6table_filter); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_filter); + return err; } static void __net_exit ip6table_filter_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_filter); + ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops); } static struct pernet_operations ip6table_filter_net_ops = { diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index abe278b07932..fe43d08284bc 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -91,19 +91,20 @@ static struct nf_hook_ops *mangle_ops __read_mostly; static int __net_init ip6table_mangle_net_init(struct net *net) { struct ip6t_replace *repl; + int ret; repl = ip6t_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_mangle = - ip6t_register_table(net, &packet_mangler, repl); + ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops, + &net->ipv6.ip6table_mangle); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_mangle); + return ret; } static void __net_exit ip6table_mangle_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_mangle); + ip6t_unregister_table(net, net->ipv6.ip6table_mangle, mangle_ops); } static struct pernet_operations ip6table_mangle_net_ops = { diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index de2a10a565f5..7f9740e8ef47 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -100,18 +100,20 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { static int __net_init ip6table_nat_net_init(struct net *net) { struct ip6t_replace *repl; + int ret; repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl); + ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl, + nf_nat_ipv6_ops, &net->ipv6.ip6table_nat); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_nat); + return ret; } static void __net_exit ip6table_nat_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_nat); + ip6t_unregister_table(net, net->ipv6.ip6table_nat, nf_nat_ipv6_ops); } static struct pernet_operations ip6table_nat_net_ops = { diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 9021963565c3..5fac433da069 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -30,19 +30,20 @@ static struct nf_hook_ops *rawtable_ops __read_mostly; static int __net_init ip6table_raw_net_init(struct net *net) { struct ip6t_replace *repl; + int ret; repl = ip6t_alloc_initial_table(&packet_raw); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_raw = - ip6t_register_table(net, &packet_raw, repl); + ret = ip6t_register_table(net, &packet_raw, repl, rawtable_ops, + &net->ipv6.ip6table_raw); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_raw); + return ret; } static void __net_exit ip6table_raw_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_raw); + ip6t_unregister_table(net, net->ipv6.ip6table_raw, rawtable_ops); } static struct pernet_operations ip6table_raw_net_ops = { diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 0d856fedfeb0..cf587453e322 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -47,19 +47,20 @@ static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init ip6table_security_net_init(struct net *net) { struct ip6t_replace *repl; + int ret; repl = ip6t_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_security = - ip6t_register_table(net, &security_table, repl); + ret = ip6t_register_table(net, &security_table, repl, sectbl_ops, + &net->ipv6.ip6table_security); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_security); + return ret; } static void __net_exit ip6table_security_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_security); + ip6t_unregister_table(net, net->ipv6.ip6table_security, sectbl_ops); } static struct pernet_operations ip6table_security_net_ops = { -- cgit v1.2.3 From b9e69e127397187b70c813a4397cce7afb5e8cb1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 25 Feb 2016 10:08:36 +0100 Subject: netfilter: xtables: don't hook tables by default delay hook registration until the table is being requested inside a namespace. Historically, a particular table (iptables mangle, ip6tables filter, etc) was registered on module load. When netns support was added to iptables only the ip/ip6tables ruleset was made namespace aware, not the actual hook points. This means f.e. that when ipt_filter table/module is loaded on a system, then each namespace on that system has an (empty) iptables filter ruleset. In other words, if a namespace sends a packet, such skb is 'caught' by netfilter machinery and fed to hooking points for that table (i.e. INPUT, FORWARD, etc). Thanks to Eric Biederman, hooks are no longer global, but per namespace. This means that we can avoid allocation of empty ruleset in a namespace and defer hook registration until we need the functionality. We register a tables hook entry points ONLY in the initial namespace. When an iptables get/setockopt is issued inside a given namespace, we check if the table is found in the per-namespace list. If not, we attempt to find it in the initial namespace, and, if found, create an empty default table in the requesting namespace and register the needed hooks. Hook points are destroyed only once namespace is deleted, there is no 'usage count' (it makes no sense since there is no 'remove table' operation in xtables api). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 6 ++-- net/ipv4/netfilter/arp_tables.c | 41 +++++++++++++-------- net/ipv4/netfilter/arptable_filter.c | 29 ++++++++------- net/ipv4/netfilter/ip_tables.c | 42 ++++++++++++++-------- net/ipv4/netfilter/iptable_filter.c | 35 ++++++++++++------ net/ipv4/netfilter/iptable_mangle.c | 32 ++++++++++++----- net/ipv4/netfilter/iptable_nat.c | 33 ++++++++--------- net/ipv4/netfilter/iptable_raw.c | 29 ++++++++++----- net/ipv4/netfilter/iptable_security.c | 35 +++++++++++------- net/ipv6/netfilter/ip6_tables.c | 42 ++++++++++++++-------- net/ipv6/netfilter/ip6table_filter.c | 38 ++++++++++++-------- net/ipv6/netfilter/ip6table_mangle.c | 37 +++++++++++-------- net/ipv6/netfilter/ip6table_nat.c | 33 ++++++++--------- net/ipv6/netfilter/ip6table_raw.c | 37 +++++++++++-------- net/ipv6/netfilter/ip6table_security.c | 35 +++++++++++------- net/netfilter/x_tables.c | 65 +++++++++++++++++++++------------- 16 files changed, 361 insertions(+), 208 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index c5577410c25d..80a305b85323 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -200,6 +200,9 @@ struct xt_table { u_int8_t af; /* address/protocol family */ int priority; /* hook order */ + /* called when table is needed in the given netns */ + int (*table_init)(struct net *net); + /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; @@ -408,8 +411,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) return cnt; } -struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *); -void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *); +struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); #ifdef CONFIG_COMPAT #include diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 00eed0852dfc..bf081927e06b 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1780,6 +1780,24 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } +static void __arpt_unregister_table(struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct arpt_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); +} + int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, @@ -1810,8 +1828,15 @@ int arpt_register_table(struct net *net, goto out_free; } + /* set res now, will see skbs right after nf_register_net_hooks */ WRITE_ONCE(*res, new_table); + ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ret != 0) { + __arpt_unregister_table(new_table); + *res = NULL; + } + return ret; out_free: @@ -1822,20 +1847,8 @@ out_free: void arpt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { - struct xt_table_info *private; - void *loc_cpu_entry; - struct module *table_owner = table->me; - struct arpt_entry *iter; - - private = xt_unregister_table(table); - - /* Decrease module usage counts and free resources */ - loc_cpu_entry = private->entries; - xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter); - if (private->number > private->initial_entries) - module_put(table_owner); - xt_free_table_info(private); + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + __arpt_unregister_table(table); } /* The built-in targets: standard (NULL) and error. */ diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 4c0241692576..dd8c80dc32a2 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -17,12 +17,15 @@ MODULE_DESCRIPTION("arptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \ (1 << NF_ARP_FORWARD)) +static int __net_init arptable_filter_table_init(struct net *net); + static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_ARP, .priority = NF_IP_PRI_FILTER, + .table_init = arptable_filter_table_init, }; /* The work comes in here from netfilter.c */ @@ -35,11 +38,14 @@ arptable_filter_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *arpfilter_ops __read_mostly; -static int __net_init arptable_filter_net_init(struct net *net) +static int __net_init arptable_filter_table_init(struct net *net) { struct arpt_replace *repl; int err; + if (net->ipv4.arptable_filter) + return 0; + repl = arpt_alloc_initial_table(&packet_filter); if (repl == NULL) return -ENOMEM; @@ -51,11 +57,13 @@ static int __net_init arptable_filter_net_init(struct net *net) static void __net_exit arptable_filter_net_exit(struct net *net) { + if (!net->ipv4.arptable_filter) + return; arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops); + net->ipv4.arptable_filter = NULL; } static struct pernet_operations arptable_filter_net_ops = { - .init = arptable_filter_net_init, .exit = arptable_filter_net_exit, }; @@ -63,26 +71,23 @@ static int __init arptable_filter_init(void) { int ret; + arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook); + if (IS_ERR(arpfilter_ops)) + return PTR_ERR(arpfilter_ops); + ret = register_pernet_subsys(&arptable_filter_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(arpfilter_ops); return ret; - - arpfilter_ops = xt_hook_link(&packet_filter, arptable_filter_hook); - if (IS_ERR(arpfilter_ops)) { - ret = PTR_ERR(arpfilter_ops); - goto cleanup_table; } - return ret; -cleanup_table: - unregister_pernet_subsys(&arptable_filter_net_ops); return ret; } static void __exit arptable_filter_fini(void) { - xt_hook_unlink(&packet_filter, arpfilter_ops); unregister_pernet_subsys(&arptable_filter_net_ops); + kfree(arpfilter_ops); } module_init(arptable_filter_init); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 1eb4fe5b4702..e53f8d6f326d 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -2062,6 +2062,24 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } +static void __ipt_unregister_table(struct net *net, struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct ipt_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter, net); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); +} + int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res) @@ -2089,7 +2107,15 @@ int ipt_register_table(struct net *net, const struct xt_table *table, goto out_free; } + /* set res now, will see skbs right after nf_register_net_hooks */ WRITE_ONCE(*res, new_table); + + ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ret != 0) { + __ipt_unregister_table(net, new_table); + *res = NULL; + } + return ret; out_free: @@ -2100,20 +2126,8 @@ out_free: void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { - struct xt_table_info *private; - void *loc_cpu_entry; - struct module *table_owner = table->me; - struct ipt_entry *iter; - - private = xt_unregister_table(table); - - /* Decrease module usage counts and free resources */ - loc_cpu_entry = private->entries; - xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter, net); - if (private->number > private->initial_entries) - module_put(table_owner); - xt_free_table_info(private); + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + __ipt_unregister_table(net, table); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 3fbe4acacb27..7667f223d7f8 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -23,6 +23,7 @@ MODULE_DESCRIPTION("iptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) +static int __net_init iptable_filter_table_init(struct net *net); static const struct xt_table packet_filter = { .name = "filter", @@ -30,6 +31,7 @@ static const struct xt_table packet_filter = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_FILTER, + .table_init = iptable_filter_table_init, }; static unsigned int @@ -48,14 +50,17 @@ iptable_filter_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ -static bool forward = true; +static bool forward __read_mostly = true; module_param(forward, bool, 0000); -static int __net_init iptable_filter_net_init(struct net *net) +static int __net_init iptable_filter_table_init(struct net *net) { struct ipt_replace *repl; int err; + if (net->ipv4.iptable_filter) + return 0; + repl = ipt_alloc_initial_table(&packet_filter); if (repl == NULL) return -ENOMEM; @@ -69,9 +74,20 @@ static int __net_init iptable_filter_net_init(struct net *net) return err; } +static int __net_init iptable_filter_net_init(struct net *net) +{ + if (net == &init_net || !forward) + return iptable_filter_table_init(net); + + return 0; +} + static void __net_exit iptable_filter_net_exit(struct net *net) { + if (!net->ipv4.iptable_filter) + return; ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops); + net->ipv4.iptable_filter = NULL; } static struct pernet_operations iptable_filter_net_ops = { @@ -83,24 +99,21 @@ static int __init iptable_filter_init(void) { int ret; + filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook); + if (IS_ERR(filter_ops)) + return PTR_ERR(filter_ops); + ret = register_pernet_subsys(&iptable_filter_net_ops); if (ret < 0) - return ret; - - /* Register hooks */ - filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook); - if (IS_ERR(filter_ops)) { - ret = PTR_ERR(filter_ops); - unregister_pernet_subsys(&iptable_filter_net_ops); - } + kfree(filter_ops); return ret; } static void __exit iptable_filter_fini(void) { - xt_hook_unlink(&packet_filter, filter_ops); unregister_pernet_subsys(&iptable_filter_net_ops); + kfree(filter_ops); } module_init(iptable_filter_init); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 668e79166b81..57fc97cdac70 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) +static int __net_init iptable_mangle_table_init(struct net *net); + static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_MANGLE, + .table_init = iptable_mangle_table_init, }; static unsigned int @@ -92,12 +95,14 @@ iptable_mangle_hook(void *priv, } static struct nf_hook_ops *mangle_ops __read_mostly; - -static int __net_init iptable_mangle_net_init(struct net *net) +static int __net_init iptable_mangle_table_init(struct net *net) { struct ipt_replace *repl; int ret; + if (net->ipv4.iptable_mangle) + return 0; + repl = ipt_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; @@ -109,11 +114,13 @@ static int __net_init iptable_mangle_net_init(struct net *net) static void __net_exit iptable_mangle_net_exit(struct net *net) { + if (!net->ipv4.iptable_mangle) + return; ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops); + net->ipv4.iptable_mangle = NULL; } static struct pernet_operations iptable_mangle_net_ops = { - .init = iptable_mangle_net_init, .exit = iptable_mangle_net_exit, }; @@ -121,15 +128,22 @@ static int __init iptable_mangle_init(void) { int ret; + mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); + if (IS_ERR(mangle_ops)) { + ret = PTR_ERR(mangle_ops); + return ret; + } + ret = register_pernet_subsys(&iptable_mangle_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(mangle_ops); return ret; + } - /* Register hooks */ - mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook); - if (IS_ERR(mangle_ops)) { - ret = PTR_ERR(mangle_ops); + ret = iptable_mangle_table_init(&init_net); + if (ret) { unregister_pernet_subsys(&iptable_mangle_net_ops); + kfree(mangle_ops); } return ret; @@ -137,8 +151,8 @@ static int __init iptable_mangle_init(void) static void __exit iptable_mangle_fini(void) { - xt_hook_unlink(&packet_mangler, mangle_ops); unregister_pernet_subsys(&iptable_mangle_net_ops); + kfree(mangle_ops); } module_init(iptable_mangle_init); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index e984f1d3017f..138a24bc76ad 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -18,6 +18,8 @@ #include #include +static int __net_init iptable_nat_table_init(struct net *net); + static const struct xt_table nf_nat_ipv4_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | @@ -26,6 +28,7 @@ static const struct xt_table nf_nat_ipv4_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV4, + .table_init = iptable_nat_table_init, }; static unsigned int iptable_nat_do_chain(void *priv, @@ -95,11 +98,14 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { }, }; -static int __net_init iptable_nat_net_init(struct net *net) +static int __net_init iptable_nat_table_init(struct net *net) { struct ipt_replace *repl; int ret; + if (net->ipv4.nat_table) + return 0; + repl = ipt_alloc_initial_table(&nf_nat_ipv4_table); if (repl == NULL) return -ENOMEM; @@ -111,36 +117,31 @@ static int __net_init iptable_nat_net_init(struct net *net) static void __net_exit iptable_nat_net_exit(struct net *net) { + if (!net->ipv4.nat_table) + return; ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops); + net->ipv4.nat_table = NULL; } static struct pernet_operations iptable_nat_net_ops = { - .init = iptable_nat_net_init, .exit = iptable_nat_net_exit, }; static int __init iptable_nat_init(void) { - int err; - - err = register_pernet_subsys(&iptable_nat_net_ops); - if (err < 0) - goto err1; + int ret = register_pernet_subsys(&iptable_nat_net_ops); - err = nf_register_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); - if (err < 0) - goto err2; - return 0; + if (ret) + return ret; -err2: - unregister_pernet_subsys(&iptable_nat_net_ops); -err1: - return err; + ret = iptable_nat_table_init(&init_net); + if (ret) + unregister_pernet_subsys(&iptable_nat_net_ops); + return ret; } static void __exit iptable_nat_exit(void) { - nf_unregister_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); unregister_pernet_subsys(&iptable_nat_net_ops); } diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 9d78780a9036..2642ecd2645c 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -10,12 +10,15 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) +static int __net_init iptable_raw_table_init(struct net *net); + static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW, + .table_init = iptable_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -34,11 +37,14 @@ iptable_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init iptable_raw_net_init(struct net *net) +static int __net_init iptable_raw_table_init(struct net *net) { struct ipt_replace *repl; int ret; + if (net->ipv4.iptable_raw) + return 0; + repl = ipt_alloc_initial_table(&packet_raw); if (repl == NULL) return -ENOMEM; @@ -50,11 +56,13 @@ static int __net_init iptable_raw_net_init(struct net *net) static void __net_exit iptable_raw_net_exit(struct net *net) { + if (!net->ipv4.iptable_raw) + return; ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops); + net->ipv4.iptable_raw = NULL; } static struct pernet_operations iptable_raw_net_ops = { - .init = iptable_raw_net_init, .exit = iptable_raw_net_exit, }; @@ -62,15 +70,20 @@ static int __init iptable_raw_init(void) { int ret; + rawtable_ops = xt_hook_ops_alloc(&packet_raw, iptable_raw_hook); + if (IS_ERR(rawtable_ops)) + return PTR_ERR(rawtable_ops); + ret = register_pernet_subsys(&iptable_raw_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(rawtable_ops); return ret; + } - /* Register hooks */ - rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook); - if (IS_ERR(rawtable_ops)) { - ret = PTR_ERR(rawtable_ops); + ret = iptable_raw_table_init(&init_net); + if (ret) { unregister_pernet_subsys(&iptable_raw_net_ops); + kfree(rawtable_ops); } return ret; @@ -78,8 +91,8 @@ static int __init iptable_raw_init(void) static void __exit iptable_raw_fini(void) { - xt_hook_unlink(&packet_raw, rawtable_ops); unregister_pernet_subsys(&iptable_raw_net_ops); + kfree(rawtable_ops); } module_init(iptable_raw_init); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 88bc52fb8f4a..ff226596e4b5 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) +static int __net_init iptable_security_table_init(struct net *net); + static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_SECURITY, + .table_init = iptable_security_table_init, }; static unsigned int @@ -51,11 +54,14 @@ iptable_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init iptable_security_net_init(struct net *net) +static int __net_init iptable_security_table_init(struct net *net) { struct ipt_replace *repl; int ret; + if (net->ipv4.iptable_security) + return 0; + repl = ipt_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; @@ -67,11 +73,14 @@ static int __net_init iptable_security_net_init(struct net *net) static void __net_exit iptable_security_net_exit(struct net *net) { + if (!net->ipv4.iptable_security) + return; + ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops); + net->ipv4.iptable_security = NULL; } static struct pernet_operations iptable_security_net_ops = { - .init = iptable_security_net_init, .exit = iptable_security_net_exit, }; @@ -79,27 +88,29 @@ static int __init iptable_security_init(void) { int ret; + sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook); + if (IS_ERR(sectbl_ops)) + return PTR_ERR(sectbl_ops); + ret = register_pernet_subsys(&iptable_security_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(sectbl_ops); return ret; - - sectbl_ops = xt_hook_link(&security_table, iptable_security_hook); - if (IS_ERR(sectbl_ops)) { - ret = PTR_ERR(sectbl_ops); - goto cleanup_table; } - return ret; + ret = iptable_security_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&iptable_security_net_ops); + kfree(sectbl_ops); + } -cleanup_table: - unregister_pernet_subsys(&iptable_security_net_ops); return ret; } static void __exit iptable_security_fini(void) { - xt_hook_unlink(&security_table, sectbl_ops); unregister_pernet_subsys(&iptable_security_net_ops); + kfree(sectbl_ops); } module_init(iptable_security_init); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 052d7447b52e..84f9baf7aee8 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -2071,6 +2071,24 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } +static void __ip6t_unregister_table(struct net *net, struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct ip6t_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter, net); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); +} + int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops, @@ -2099,7 +2117,15 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, goto out_free; } + /* set res now, will see skbs right after nf_register_net_hooks */ WRITE_ONCE(*res, new_table); + + ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ret != 0) { + __ip6t_unregister_table(net, new_table); + *res = NULL; + } + return ret; out_free: @@ -2110,20 +2136,8 @@ out_free: void ip6t_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { - struct xt_table_info *private; - void *loc_cpu_entry; - struct module *table_owner = table->me; - struct ip6t_entry *iter; - - private = xt_unregister_table(table); - - /* Decrease module usage counts and free resources */ - loc_cpu_entry = private->entries; - xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter, net); - if (private->number > private->initial_entries) - module_put(table_owner); - xt_free_table_info(private); + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + __ip6t_unregister_table(net, table); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index d191d54cdf50..1343077dde93 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -22,12 +22,15 @@ MODULE_DESCRIPTION("ip6tables filter table"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) +static int __net_init ip6table_filter_table_init(struct net *net); + static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_FILTER, + .table_init = ip6table_filter_table_init, }; /* The work comes in here from netfilter.c. */ @@ -44,11 +47,14 @@ static struct nf_hook_ops *filter_ops __read_mostly; static bool forward = true; module_param(forward, bool, 0000); -static int __net_init ip6table_filter_net_init(struct net *net) +static int __net_init ip6table_filter_table_init(struct net *net) { struct ip6t_replace *repl; int err; + if (net->ipv6.ip6table_filter) + return 0; + repl = ip6t_alloc_initial_table(&packet_filter); if (repl == NULL) return -ENOMEM; @@ -62,9 +68,20 @@ static int __net_init ip6table_filter_net_init(struct net *net) return err; } +static int __net_init ip6table_filter_net_init(struct net *net) +{ + if (net == &init_net || !forward) + return ip6table_filter_table_init(net); + + return 0; +} + static void __net_exit ip6table_filter_net_exit(struct net *net) { + if (!net->ipv6.ip6table_filter) + return; ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops); + net->ipv6.ip6table_filter = NULL; } static struct pernet_operations ip6table_filter_net_ops = { @@ -76,28 +93,21 @@ static int __init ip6table_filter_init(void) { int ret; + filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook); + if (IS_ERR(filter_ops)) + return PTR_ERR(filter_ops); + ret = register_pernet_subsys(&ip6table_filter_net_ops); if (ret < 0) - return ret; - - /* Register hooks */ - filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook); - if (IS_ERR(filter_ops)) { - ret = PTR_ERR(filter_ops); - goto cleanup_table; - } + kfree(filter_ops); return ret; - - cleanup_table: - unregister_pernet_subsys(&ip6table_filter_net_ops); - return ret; } static void __exit ip6table_filter_fini(void) { - xt_hook_unlink(&packet_filter, filter_ops); unregister_pernet_subsys(&ip6table_filter_net_ops); + kfree(filter_ops); } module_init(ip6table_filter_init); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index fe43d08284bc..cb2b28883252 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -23,12 +23,15 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) +static int __net_init ip6table_mangle_table_init(struct net *net); + static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_MANGLE, + .table_init = ip6table_mangle_table_init, }; static unsigned int @@ -88,11 +91,14 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb, } static struct nf_hook_ops *mangle_ops __read_mostly; -static int __net_init ip6table_mangle_net_init(struct net *net) +static int __net_init ip6table_mangle_table_init(struct net *net) { struct ip6t_replace *repl; int ret; + if (net->ipv6.ip6table_mangle) + return 0; + repl = ip6t_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; @@ -104,11 +110,14 @@ static int __net_init ip6table_mangle_net_init(struct net *net) static void __net_exit ip6table_mangle_net_exit(struct net *net) { + if (!net->ipv6.ip6table_mangle) + return; + ip6t_unregister_table(net, net->ipv6.ip6table_mangle, mangle_ops); + net->ipv6.ip6table_mangle = NULL; } static struct pernet_operations ip6table_mangle_net_ops = { - .init = ip6table_mangle_net_init, .exit = ip6table_mangle_net_exit, }; @@ -116,28 +125,28 @@ static int __init ip6table_mangle_init(void) { int ret; + mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); + if (IS_ERR(mangle_ops)) + return PTR_ERR(mangle_ops); + ret = register_pernet_subsys(&ip6table_mangle_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(mangle_ops); return ret; - - /* Register hooks */ - mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook); - if (IS_ERR(mangle_ops)) { - ret = PTR_ERR(mangle_ops); - goto cleanup_table; } - return ret; - - cleanup_table: - unregister_pernet_subsys(&ip6table_mangle_net_ops); + ret = ip6table_mangle_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&ip6table_mangle_net_ops); + kfree(mangle_ops); + } return ret; } static void __exit ip6table_mangle_fini(void) { - xt_hook_unlink(&packet_mangler, mangle_ops); unregister_pernet_subsys(&ip6table_mangle_net_ops); + kfree(mangle_ops); } module_init(ip6table_mangle_init); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 7f9740e8ef47..7d2bd940291f 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -20,6 +20,8 @@ #include #include +static int __net_init ip6table_nat_table_init(struct net *net); + static const struct xt_table nf_nat_ipv6_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | @@ -28,6 +30,7 @@ static const struct xt_table nf_nat_ipv6_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV6, + .table_init = ip6table_nat_table_init, }; static unsigned int ip6table_nat_do_chain(void *priv, @@ -97,11 +100,14 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { }, }; -static int __net_init ip6table_nat_net_init(struct net *net) +static int __net_init ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; int ret; + if (net->ipv6.ip6table_nat) + return 0; + repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); if (repl == NULL) return -ENOMEM; @@ -113,36 +119,31 @@ static int __net_init ip6table_nat_net_init(struct net *net) static void __net_exit ip6table_nat_net_exit(struct net *net) { + if (!net->ipv6.ip6table_nat) + return; ip6t_unregister_table(net, net->ipv6.ip6table_nat, nf_nat_ipv6_ops); + net->ipv6.ip6table_nat = NULL; } static struct pernet_operations ip6table_nat_net_ops = { - .init = ip6table_nat_net_init, .exit = ip6table_nat_net_exit, }; static int __init ip6table_nat_init(void) { - int err; - - err = register_pernet_subsys(&ip6table_nat_net_ops); - if (err < 0) - goto err1; + int ret = register_pernet_subsys(&ip6table_nat_net_ops); - err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); - if (err < 0) - goto err2; - return 0; + if (ret) + return ret; -err2: - unregister_pernet_subsys(&ip6table_nat_net_ops); -err1: - return err; + ret = ip6table_nat_table_init(&init_net); + if (ret) + unregister_pernet_subsys(&ip6table_nat_net_ops); + return ret; } static void __exit ip6table_nat_exit(void) { - nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); unregister_pernet_subsys(&ip6table_nat_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 5fac433da069..d4bc56443dc1 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -9,12 +9,15 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) +static int __net_init ip6table_raw_table_init(struct net *net); + static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW, + .table_init = ip6table_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -27,11 +30,14 @@ ip6table_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init ip6table_raw_net_init(struct net *net) +static int __net_init ip6table_raw_table_init(struct net *net) { struct ip6t_replace *repl; int ret; + if (net->ipv6.ip6table_raw) + return 0; + repl = ip6t_alloc_initial_table(&packet_raw); if (repl == NULL) return -ENOMEM; @@ -43,11 +49,13 @@ static int __net_init ip6table_raw_net_init(struct net *net) static void __net_exit ip6table_raw_net_exit(struct net *net) { + if (!net->ipv6.ip6table_raw) + return; ip6t_unregister_table(net, net->ipv6.ip6table_raw, rawtable_ops); + net->ipv6.ip6table_raw = NULL; } static struct pernet_operations ip6table_raw_net_ops = { - .init = ip6table_raw_net_init, .exit = ip6table_raw_net_exit, }; @@ -55,28 +63,29 @@ static int __init ip6table_raw_init(void) { int ret; + /* Register hooks */ + rawtable_ops = xt_hook_ops_alloc(&packet_raw, ip6table_raw_hook); + if (IS_ERR(rawtable_ops)) + return PTR_ERR(rawtable_ops); + ret = register_pernet_subsys(&ip6table_raw_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(rawtable_ops); return ret; - - /* Register hooks */ - rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook); - if (IS_ERR(rawtable_ops)) { - ret = PTR_ERR(rawtable_ops); - goto cleanup_table; } - return ret; - - cleanup_table: - unregister_pernet_subsys(&ip6table_raw_net_ops); + ret = ip6table_raw_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&ip6table_raw_net_ops); + kfree(rawtable_ops); + } return ret; } static void __exit ip6table_raw_fini(void) { - xt_hook_unlink(&packet_raw, rawtable_ops); unregister_pernet_subsys(&ip6table_raw_net_ops); + kfree(rawtable_ops); } module_init(ip6table_raw_init); diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index cf587453e322..cf26ccb04056 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -27,12 +27,15 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) +static int __net_init ip6table_security_table_init(struct net *net); + static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_SECURITY, + .table_init = ip6table_security_table_init, }; static unsigned int @@ -44,11 +47,14 @@ ip6table_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init ip6table_security_net_init(struct net *net) +static int __net_init ip6table_security_table_init(struct net *net) { struct ip6t_replace *repl; int ret; + if (net->ipv6.ip6table_security) + return 0; + repl = ip6t_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; @@ -60,11 +66,13 @@ static int __net_init ip6table_security_net_init(struct net *net) static void __net_exit ip6table_security_net_exit(struct net *net) { + if (!net->ipv6.ip6table_security) + return; ip6t_unregister_table(net, net->ipv6.ip6table_security, sectbl_ops); + net->ipv6.ip6table_security = NULL; } static struct pernet_operations ip6table_security_net_ops = { - .init = ip6table_security_net_init, .exit = ip6table_security_net_exit, }; @@ -72,27 +80,28 @@ static int __init ip6table_security_init(void) { int ret; + sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook); + if (IS_ERR(sectbl_ops)) + return PTR_ERR(sectbl_ops); + ret = register_pernet_subsys(&ip6table_security_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(sectbl_ops); return ret; - - sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook); - if (IS_ERR(sectbl_ops)) { - ret = PTR_ERR(sectbl_ops); - goto cleanup_table; } - return ret; - -cleanup_table: - unregister_pernet_subsys(&ip6table_security_net_ops); + ret = ip6table_security_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&ip6table_security_net_ops); + kfree(sectbl_ops); + } return ret; } static void __exit ip6table_security_fini(void) { - xt_hook_unlink(&security_table, sectbl_ops); unregister_pernet_subsys(&ip6table_security_net_ops); + kfree(sectbl_ops); } module_init(ip6table_security_init); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index c8a0b7da5ff4..d0cd2b9bf844 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -694,12 +694,45 @@ EXPORT_SYMBOL(xt_free_table_info); struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { - struct xt_table *t; + struct xt_table *t, *found = NULL; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &net->xt.tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; + + if (net == &init_net) + goto out; + + /* Table doesn't exist in this netns, re-try init */ + list_for_each_entry(t, &init_net.xt.tables[af], list) { + if (strcmp(t->name, name)) + continue; + if (!try_module_get(t->me)) + return NULL; + + mutex_unlock(&xt[af].mutex); + if (t->table_init(net) != 0) { + module_put(t->me); + return NULL; + } + + found = t; + + mutex_lock(&xt[af].mutex); + break; + } + + if (!found) + goto out; + + /* and once again: */ + list_for_each_entry(t, &net->xt.tables[af], list) + if (strcmp(t->name, name) == 0) + return t; + + module_put(found->me); + out: mutex_unlock(&xt[af].mutex); return NULL; } @@ -1170,20 +1203,20 @@ static const struct file_operations xt_target_ops = { #endif /* CONFIG_PROC_FS */ /** - * xt_hook_link - set up hooks for a new table + * xt_hook_ops_alloc - set up hooks for a new table * @table: table with metadata needed to set up hooks * @fn: Hook function * - * This function will take care of creating and registering the necessary - * Netfilter hooks for XT tables. + * This function will create the nf_hook_ops that the x_table needs + * to hand to xt_hook_link_net(). */ -struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn) +struct nf_hook_ops * +xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) { unsigned int hook_mask = table->valid_hooks; uint8_t i, num_hooks = hweight32(hook_mask); uint8_t hooknum; struct nf_hook_ops *ops; - int ret; ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL); if (ops == NULL) @@ -1200,27 +1233,9 @@ struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn) ++i; } - ret = nf_register_hooks(ops, num_hooks); - if (ret < 0) { - kfree(ops); - return ERR_PTR(ret); - } - return ops; } -EXPORT_SYMBOL_GPL(xt_hook_link); - -/** - * xt_hook_unlink - remove hooks for a table - * @ops: nf_hook_ops array as returned by nf_hook_link - * @hook_mask: the very same mask that was passed to nf_hook_link - */ -void xt_hook_unlink(const struct xt_table *table, struct nf_hook_ops *ops) -{ - nf_unregister_hooks(ops, hweight32(table->valid_hooks)); - kfree(ops); -} -EXPORT_SYMBOL_GPL(xt_hook_unlink); +EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_proto_init(struct net *net, u_int8_t af) { -- cgit v1.2.3 From af4610c39589d839551da104f7da342d86f23ea0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 25 Feb 2016 10:08:38 +0100 Subject: netfilter: don't call hooks unless needed With the previous patches in place, a netns nf_hook_list might be empty, even if e.g. init_net performs filtering. Thus change nf_hook_thresh to check the hook_list as well before initializing hook_state and calling nf_hook_slow(). We still make use of static keys; if no netfilter modules are loaded list is guaranteed to be empty. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0ad556726181..9230f9aee896 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -141,22 +141,6 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; - -static inline bool nf_hook_list_active(struct list_head *hook_list, - u_int8_t pf, unsigned int hook) -{ - if (__builtin_constant_p(pf) && - __builtin_constant_p(hook)) - return static_key_false(&nf_hooks_needed[pf][hook]); - - return !list_empty(hook_list); -} -#else -static inline bool nf_hook_list_active(struct list_head *hook_list, - u_int8_t pf, unsigned int hook) -{ - return !list_empty(hook_list); -} #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); @@ -177,9 +161,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { - struct list_head *hook_list = &net->nf.hooks[pf][hook]; + struct list_head *hook_list; + +#ifdef HAVE_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return 1; +#endif + + hook_list = &net->nf.hooks[pf][hook]; - if (nf_hook_list_active(hook_list, pf, hook)) { + if (!list_empty(hook_list)) { struct nf_hook_state state; nf_hook_state_init(&state, hook_list, hook, thresh, -- cgit v1.2.3 From afea03656add70a0e00f5b0039f87288c7af8b9f Mon Sep 17 00:00:00 2001 From: Giuseppe Cavallaro Date: Mon, 29 Feb 2016 14:27:28 +0100 Subject: stmmac: rework DMA bus setting and introduce new platform AXI structure This patch restructures the DMA bus settings and this is done by introducing a new platform structure used for programming the AXI Bus Mode Register inside the DMA module. This structure can be populated from device-tree as documented in the binding txt file. After initializing the DMA, the AXI register can be optionally tuned for platform drivers based. This patch also reworks some parameters to make coherent the DMA configuration now that AXI register is introduced. For example, the burst_len is managed by using the mentioned axi support above; so the snps,burst-len parameter has been removed. It makes sense to provide the AAL parameter from DT to Address-Aligned Beats inside the Register0 and review the PBL settings when initialize the engine. For PCI glue, rebuilding the story of this setting, it was added to align a configuration so not for fixing some known problem. No issue raised after this patch. It is safe to use the default burst length instead of tuning it to the maximum value Signed-off-by: Giuseppe Cavallaro Signed-off-by: Alexandre TORGUE Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/stmmac.txt | 54 ++++++++---- drivers/net/ethernet/stmicro/stmmac/common.h | 5 +- drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 2 +- .../net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 99 +++++++++++++++------- drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h | 34 +++++++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 4 +- .../net/ethernet/stmicro/stmmac/stmmac_platform.c | 42 ++++++++- include/linux/stmmac.h | 17 +++- 10 files changed, 209 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index e862a922bd3f..6605d19601c2 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -17,7 +17,25 @@ Required properties: The 1st cell is reset pre-delay in micro seconds. The 2nd cell is reset pulse in micro seconds. The 3rd cell is reset post-delay in micro seconds. + +Optional properties: +- resets: Should contain a phandle to the STMMAC reset signal, if any +- reset-names: Should contain the reset signal name "stmmaceth", if a + reset phandle is given +- max-frame-size: See ethernet.txt file in the same directory +- clocks: If present, the first clock should be the GMAC main clock and + the second clock should be peripheral's register interface clock. Further + clocks may be specified in derived bindings. +- clock-names: One name for each entry in the clocks property, the + first one should be "stmmaceth" and the second one should be "pclk". +- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is + available this clock is used for programming the Timestamp Addend Register. + If not passed then the system clock will be used and this is fine on some + platforms. +- tx-fifo-depth: See ethernet.txt file in the same directory +- rx-fifo-depth: See ethernet.txt file in the same directory - snps,pbl Programmable Burst Length +- snps,aal Address-Aligned Beats - snps,fixed-burst Program the DMA to use the fixed burst mode - snps,mixed-burst Program the DMA to use the mixed burst mode - snps,force_thresh_dma_mode Force DMA to use the threshold mode for @@ -29,27 +47,28 @@ Required properties: supported by this device instance - snps,perfect-filter-entries: Number of perfect filter entries supported by this device instance - -Optional properties: -- resets: Should contain a phandle to the STMMAC reset signal, if any -- reset-names: Should contain the reset signal name "stmmaceth", if a - reset phandle is given -- max-frame-size: See ethernet.txt file in the same directory -- clocks: If present, the first clock should be the GMAC main clock - The optional second clock should be peripheral's register interface clock. - The third optional clock should be the ptp reference clock. - Further clocks may be specified in derived bindings. -- clock-names: One name for each entry in the clocks property. - The first one should be "stmmaceth". - The optional second one should be "pclk". - The optional third one should be "clk_ptp_ref". -- snps,burst_len: The AXI burst lenth value of the AXI BUS MODE register. -- tx-fifo-depth: See ethernet.txt file in the same directory -- rx-fifo-depth: See ethernet.txt file in the same directory +- AXI BUS Mode parameters: below the list of all the parameters to program the + AXI register inside the DMA module: + - snps,lpi_en: enable Low Power Interface + - snps,xit_frm: unlock on WoL + - snps,wr_osr_lmt: max write oustanding req. limit + - snps,rd_osr_lmt: max read oustanding req. limit + - snps,kbbe: do not cross 1KiB boundary. + - snps,axi_all: align address + - snps,blen: this is a vector of supported burst length. + - snps,fb: fixed-burst + - snps,mb: mixed-burst + - snps,rb: rebuild INCRx Burst - mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus. Examples: + stmmac_axi_setup: stmmac-axi-config { + snps,wr_osr_lmt = <0xf>; + snps,rd_osr_lmt = <0xf>; + snps,blen = <256 128 64 32 0 0 0>; + }; + gmac0: ethernet@e0800000 { compatible = "st,spear600-gmac"; reg = <0xe0800000 0x8000>; @@ -65,6 +84,7 @@ Examples: tx-fifo-depth = <16384>; clocks = <&clock>; clock-names = "stmmaceth"; + snps,axi-config = <&stmmac_axi_setup>; mdio0 { #address-cells = <1>; #size-cells = <0>; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index bac0e44d7634..586a33624dd2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -27,6 +27,7 @@ #include #include +#include #include #include #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) @@ -378,7 +379,9 @@ struct stmmac_dma_ops { /* DMA core initialization */ int (*reset)(void __iomem *ioaddr); void (*init)(void __iomem *ioaddr, int pbl, int fb, int mb, - int burst_len, u32 dma_tx, u32 dma_rx, int atds); + int aal, u32 dma_tx, u32 dma_rx, int atds); + /* Configure the AXI Bus Mode Register */ + void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi); /* Dump DMA registers */ void (*dump_regs) (void __iomem *ioaddr); /* Set tx/rx threshold in the csr6 register diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index 9d36ae788429..b0593a4268ee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -240,7 +240,7 @@ enum rx_tx_priority_ratio { #define DMA_BUS_MODE_RPBL_MASK 0x003e0000 /* Rx-Programmable Burst Len */ #define DMA_BUS_MODE_RPBL_SHIFT 17 #define DMA_BUS_MODE_USP 0x00800000 -#define DMA_BUS_MODE_PBL 0x01000000 +#define DMA_BUS_MODE_MAXPBL 0x01000000 #define DMA_BUS_MODE_AAL 0x02000000 /* DMA CRS Control and Status Register Mapping */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index 5f0aea56b298..da32d6037e3e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -30,24 +30,76 @@ #include "dwmac1000.h" #include "dwmac_dma.h" +static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) +{ + u32 value = readl(ioaddr + DMA_AXI_BUS_MODE); + int i; + + pr_info("dwmac1000: Master AXI performs %s burst length\n", + !(value & DMA_AXI_UNDEF) ? "fixed" : "any"); + + if (axi->axi_lpi_en) + value |= DMA_AXI_EN_LPI; + if (axi->axi_xit_frm) + value |= DMA_AXI_LPI_XIT_FRM; + + value |= (axi->axi_wr_osr_lmt & DMA_AXI_WR_OSR_LMT_MASK) << + DMA_AXI_WR_OSR_LMT_SHIFT; + + value |= (axi->axi_rd_osr_lmt & DMA_AXI_RD_OSR_LMT_MASK) << + DMA_AXI_RD_OSR_LMT_SHIFT; + + /* Depending on the UNDEF bit the Master AXI will perform any burst + * length according to the BLEN programmed (by default all BLEN are + * set). + */ + for (i = 0; i < AXI_BLEN; i++) { + switch (axi->axi_blen[i]) { + case 256: + value |= DMA_AXI_BLEN256; + break; + case 128: + value |= DMA_AXI_BLEN128; + break; + case 64: + value |= DMA_AXI_BLEN64; + break; + case 32: + value |= DMA_AXI_BLEN32; + break; + case 16: + value |= DMA_AXI_BLEN16; + break; + case 8: + value |= DMA_AXI_BLEN8; + break; + case 4: + value |= DMA_AXI_BLEN4; + break; + } + } + + writel(value, ioaddr + DMA_AXI_BUS_MODE); +} + static void dwmac1000_dma_init(void __iomem *ioaddr, int pbl, int fb, int mb, - int burst_len, u32 dma_tx, u32 dma_rx, int atds) + int aal, u32 dma_tx, u32 dma_rx, int atds) { - u32 value; + u32 value = readl(ioaddr + DMA_BUS_MODE); /* - * Set the DMA PBL (Programmable Burst Length) mode - * Before stmmac core 3.50 this mode bit was 4xPBL, and + * Set the DMA PBL (Programmable Burst Length) mode. + * + * Note: before stmmac core 3.50 this mode bit was 4xPBL, and * post 3.5 mode bit acts as 8*PBL. - * For core rev < 3.5, when the core is set for 4xPBL mode, the - * DMA transfers the data in 4, 8, 16, 32, 64 & 128 beats - * depending on pbl value. - * For core rev > 3.5, when the core is set for 8xPBL mode, the - * DMA transfers the data in 8, 16, 32, 64, 128 & 256 beats - * depending on pbl value. + * + * This configuration doesn't take care about the Separate PBL + * so only the bits: 13-8 are programmed with the PBL passed from the + * platform. */ - value = DMA_BUS_MODE_PBL | ((pbl << DMA_BUS_MODE_PBL_SHIFT) | - (pbl << DMA_BUS_MODE_RPBL_SHIFT)); + value |= DMA_BUS_MODE_MAXPBL; + value &= ~DMA_BUS_MODE_PBL_MASK; + value |= (pbl << DMA_BUS_MODE_PBL_SHIFT); /* Set the Fixed burst mode */ if (fb) @@ -60,26 +112,10 @@ static void dwmac1000_dma_init(void __iomem *ioaddr, int pbl, int fb, int mb, if (atds) value |= DMA_BUS_MODE_ATDS; - writel(value, ioaddr + DMA_BUS_MODE); + if (aal) + value |= DMA_BUS_MODE_AAL; - /* In case of GMAC AXI configuration, program the DMA_AXI_BUS_MODE - * for supported bursts. - * - * Note: This is applicable only for revision GMACv3.61a. For - * older version this register is reserved and shall have no - * effect. - * - * Note: - * For Fixed Burst Mode: if we directly write 0xFF to this - * register using the configurations pass from platform code, - * this would ensure that all bursts supported by core are set - * and those which are not supported would remain ineffective. - * - * For Non Fixed Burst Mode: provide the maximum value of the - * burst length. Any burst equal or below the provided burst - * length would be allowed to perform. - */ - writel(burst_len, ioaddr + DMA_AXI_BUS_MODE); + writel(value, ioaddr + DMA_BUS_MODE); /* Mask interrupts by writing to CSR7 */ writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA); @@ -192,6 +228,7 @@ static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt) const struct stmmac_dma_ops dwmac1000_dma_ops = { .reset = dwmac_dma_reset, .init = dwmac1000_dma_init, + .axi = dwmac1000_dma_axi, .dump_regs = dwmac1000_dump_dma_regs, .dma_mode = dwmac1000_dma_operation_mode, .enable_dma_transmission = dwmac_enable_dma_transmission, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c index c40582a938a4..61f54c99a7de 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c @@ -33,7 +33,7 @@ #include "dwmac_dma.h" static void dwmac100_dma_init(void __iomem *ioaddr, int pbl, int fb, int mb, - int burst_len, u32 dma_tx, u32 dma_rx, int atds) + int aal, u32 dma_tx, u32 dma_rx, int atds) { /* Enable Application Access by writing to DMA CSR0 */ writel(DMA_BUS_MODE_DEFAULT | (pbl << DMA_BUS_MODE_PBL_SHIFT), diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 13ca90e23479..726d9d9aaf83 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -41,8 +41,40 @@ /* Rx watchdog register */ #define DMA_RX_WATCHDOG 0x00001024 -/* AXI Bus Mode */ + +/* AXI Master Bus Mode */ #define DMA_AXI_BUS_MODE 0x00001028 + +#define DMA_AXI_EN_LPI BIT(31) +#define DMA_AXI_LPI_XIT_FRM BIT(30) +#define DMA_AXI_WR_OSR_LMT GENMASK(23, 20) +#define DMA_AXI_WR_OSR_LMT_SHIFT 20 +#define DMA_AXI_WR_OSR_LMT_MASK 0xf +#define DMA_AXI_RD_OSR_LMT GENMASK(19, 16) +#define DMA_AXI_RD_OSR_LMT_SHIFT 16 +#define DMA_AXI_RD_OSR_LMT_MASK 0xf + +#define DMA_AXI_OSR_MAX 0xf +#define DMA_AXI_MAX_OSR_LIMIT ((DMA_AXI_OSR_MAX << DMA_AXI_WR_OSR_LMT_SHIFT) | \ + (DMA_AXI_OSR_MAX << DMA_AXI_RD_OSR_LMT_SHIFT)) +#define DMA_AXI_1KBBE BIT(13) +#define DMA_AXI_AAL BIT(12) +#define DMA_AXI_BLEN256 BIT(7) +#define DMA_AXI_BLEN128 BIT(6) +#define DMA_AXI_BLEN64 BIT(5) +#define DMA_AXI_BLEN32 BIT(4) +#define DMA_AXI_BLEN16 BIT(3) +#define DMA_AXI_BLEN8 BIT(2) +#define DMA_AXI_BLEN4 BIT(1) +#define DMA_BURST_LEN_DEFAULT (DMA_AXI_BLEN256 | DMA_AXI_BLEN128 | \ + DMA_AXI_BLEN64 | DMA_AXI_BLEN32 | \ + DMA_AXI_BLEN16 | DMA_AXI_BLEN8 | \ + DMA_AXI_BLEN4) + +#define DMA_AXI_UNDEF BIT(0) + +#define DMA_AXI_BURST_LEN_MASK 0x000000FE + #define DMA_CUR_TX_BUF_ADDR 0x00001050 /* Current Host Tx Buffer */ #define DMA_CUR_RX_BUF_ADDR 0x00001054 /* Current Host Rx Buffer */ #define DMA_HW_FEATURE 0x00001058 /* HW Feature Register */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 13752e933e43..89c26268822e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1635,7 +1635,7 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv) */ static int stmmac_init_dma_engine(struct stmmac_priv *priv) { - int pbl = DEFAULT_DMA_PBL, fixed_burst = 0, burst_len = 0; + int pbl = DEFAULT_DMA_PBL, fixed_burst = 0, aal = 0; int mixed_burst = 0; int atds = 0; int ret = 0; @@ -1644,7 +1644,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) pbl = priv->plat->dma_cfg->pbl; fixed_burst = priv->plat->dma_cfg->fixed_burst; mixed_burst = priv->plat->dma_cfg->mixed_burst; - burst_len = priv->plat->dma_cfg->burst_len; + aal = priv->plat->dma_cfg->aal; } if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE)) @@ -1657,8 +1657,12 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } priv->hw->dma->init(priv->ioaddr, pbl, fixed_burst, mixed_burst, - burst_len, priv->dma_tx_phy, - priv->dma_rx_phy, atds); + aal, priv->dma_tx_phy, priv->dma_rx_phy, atds); + + if ((priv->synopsys_id >= DWMAC_CORE_3_50) && + (priv->plat->axi && priv->hw->dma->axi)) + priv->hw->dma->axi(priv->ioaddr, priv->plat->axi); + return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index d71a721ea61c..ae4388735b7f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -81,7 +81,7 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat) plat->mdio_bus_data->phy_mask = 0; plat->dma_cfg->pbl = 32; - plat->dma_cfg->burst_len = DMA_AXI_BLEN_256; + /* TODO: AXI */ /* Set default value for multicast hash bins */ plat->multicast_filter_bins = HASH_TABLE_SIZE; @@ -115,8 +115,8 @@ static int quark_default_data(struct plat_stmmacenet_data *plat, plat->mdio_bus_data->phy_mask = 0; plat->dma_cfg->pbl = 16; - plat->dma_cfg->burst_len = DMA_AXI_BLEN_256; plat->dma_cfg->fixed_burst = 1; + /* AXI (TODO) */ /* Set default value for multicast hash bins */ plat->multicast_filter_bins = HASH_TABLE_SIZE; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6a52fa18cbf2..69ccf486d4fa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -95,6 +95,42 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) return x; } +/** + * stmmac_axi_setup - parse DT parameters for programming the AXI register + * @pdev: platform device + * @priv: driver private struct. + * Description: + * if required, from device-tree the AXI internal register can be tuned + * by using platform parameters. + */ +static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) +{ + struct device_node *np; + struct stmmac_axi *axi; + + np = of_parse_phandle(pdev->dev.of_node, "snps,axi-config", 0); + if (!np) + return NULL; + + axi = kzalloc(sizeof(axi), GFP_KERNEL); + if (!axi) + return ERR_PTR(-ENOMEM); + + axi->axi_lpi_en = of_property_read_bool(np, "snps,lpi_en"); + axi->axi_xit_frm = of_property_read_bool(np, "snps,xit_frm"); + axi->axi_kbbe = of_property_read_bool(np, "snps,axi_kbbe"); + axi->axi_axi_all = of_property_read_bool(np, "snps,axi_all"); + axi->axi_fb = of_property_read_bool(np, "snps,axi_fb"); + axi->axi_mb = of_property_read_bool(np, "snps,axi_mb"); + axi->axi_rb = of_property_read_bool(np, "snps,axi_rb"); + + of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt); + of_property_read_u32(np, "snps,rd_osr_lmt", &axi->axi_rd_osr_lmt); + of_property_read_u32_array(np, "snps,blen", axi->axi_blen, AXI_BLEN); + + return axi; +} + /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure @@ -216,13 +252,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) } plat->dma_cfg = dma_cfg; of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl); + dma_cfg->aal = of_property_read_bool(np, "snps,aal"); dma_cfg->fixed_burst = of_property_read_bool(np, "snps,fixed-burst"); dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst"); - of_property_read_u32(np, "snps,burst_len", &dma_cfg->burst_len); - if (dma_cfg->burst_len < 0 || dma_cfg->burst_len > 256) - dma_cfg->burst_len = 0; } plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode"); if (plat->force_thresh_dma_mode) { @@ -230,6 +264,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) pr_warn("force_sf_dma_mode is ignored if force_thresh_dma_mode is set."); } + plat->axi = stmmac_axi_setup(pdev); + return plat; } #else diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index eead8ab93c0a..6e53fa8942a4 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -90,7 +90,21 @@ struct stmmac_dma_cfg { int pbl; int fixed_burst; int mixed_burst; - int burst_len; + bool aal; +}; + +#define AXI_BLEN 7 +struct stmmac_axi { + bool axi_lpi_en; + bool axi_xit_frm; + u32 axi_wr_osr_lmt; + u32 axi_rd_osr_lmt; + bool axi_kbbe; + bool axi_axi_all; + u32 axi_blen[AXI_BLEN]; + bool axi_fb; + bool axi_mb; + bool axi_rb; }; struct plat_stmmacenet_data { @@ -122,5 +136,6 @@ struct plat_stmmacenet_data { int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); void *bsp_priv; + struct stmmac_axi *axi; }; #endif -- cgit v1.2.3 From b5d3755a22e0cc4c369c0985aef0c52c2477c1e7 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 4 Mar 2016 11:52:16 +0100 Subject: uapi: define DIV_ROUND_UP for userland DIV_ROUND_UP is defined in linux/kernel.h only for the kernel. When ethtool.h is included by a userland app, we got the following error: include/linux/ethtool.h:1218:8: error: variably modified 'queue_mask' at file scope __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; ^ Let's add a common definition in uapi and use it everywhere. Fixes: ac2c7ad0e5d6 ("net/ethtool: introduce a new ioctl for per queue setting") CC: Kan Liang Suggested-by: Ben Hutchings Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/kernel.h | 2 +- include/uapi/linux/ethtool.h | 3 ++- include/uapi/linux/kernel.h | 1 + include/uapi/linux/mroute6.h | 9 ++------- 4 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f31638c6e873..ac1923957236 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -64,7 +64,7 @@ #define round_down(x, y) ((x) & ~__round_mask(x, y)) #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) +#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_UP_ULL(ll,d) \ ({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; }) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 37fd6dc33de4..9c22249ebf35 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -13,6 +13,7 @@ #ifndef _UAPI_LINUX_ETHTOOL_H #define _UAPI_LINUX_ETHTOOL_H +#include #include #include @@ -1215,7 +1216,7 @@ enum ethtool_sfeatures_retval_bits { struct ethtool_per_queue_op { __u32 cmd; __u32 sub_command; - __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; + __u32 queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; char data[]; }; diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h index 321e399457f5..466073f0ce46 100644 --- a/include/uapi/linux/kernel.h +++ b/include/uapi/linux/kernel.h @@ -9,5 +9,6 @@ #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) #endif /* _UAPI_LINUX_KERNEL_H */ diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index ce91215cf7e6..5062fb5751e1 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -1,6 +1,7 @@ #ifndef _UAPI__LINUX_MROUTE6_H #define _UAPI__LINUX_MROUTE6_H +#include #include #include @@ -46,14 +47,8 @@ typedef unsigned short mifi_t; typedef __u32 if_mask; #define NIFBITS (sizeof(if_mask) * 8) /* bits per mask */ -#if !defined(__KERNEL__) -#if !defined(DIV_ROUND_UP) -#define DIV_ROUND_UP(x,y) (((x) + ((y) - 1)) / (y)) -#endif -#endif - typedef struct if_set { - if_mask ifs_bits[DIV_ROUND_UP(IF_SETSIZE, NIFBITS)]; + if_mask ifs_bits[__KERNEL_DIV_ROUND_UP(IF_SETSIZE, NIFBITS)]; } if_set; #define IF_SET(n, p) ((p)->ifs_bits[(n)/NIFBITS] |= (1 << ((n) % NIFBITS))) -- cgit v1.2.3 From 4d7928959832ea41f7f91456b76da19cad01bd09 Mon Sep 17 00:00:00 2001 From: Hante Meuleman Date: Wed, 17 Feb 2016 11:27:07 +0100 Subject: brcmfmac: switch to new platform data Platform data is only available for sdio. With this patch a new platform data structure is being used which allows for platform data for any device and configurable per device. This patch only switches to the new structure and adds support for SDIO devices. Reviewed-by: Arend Van Spriel Reviewed-by: Franky (Zhenhui) Lin Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- .../wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 15 +- .../broadcom/brcm80211/brcmfmac/cfg80211.c | 4 +- .../wireless/broadcom/brcm80211/brcmfmac/common.c | 43 ++++- .../wireless/broadcom/brcm80211/brcmfmac/common.h | 35 +--- .../net/wireless/broadcom/brcm80211/brcmfmac/of.c | 3 +- .../net/wireless/broadcom/brcm80211/brcmfmac/of.h | 5 +- .../wireless/broadcom/brcm80211/brcmfmac/sdio.c | 77 +++++---- .../wireless/broadcom/brcm80211/brcmfmac/sdio.h | 2 +- include/linux/platform_data/brcmfmac-sdio.h | 135 --------------- include/linux/platform_data/brcmfmac.h | 185 +++++++++++++++++++++ 10 files changed, 282 insertions(+), 222 deletions(-) delete mode 100644 include/linux/platform_data/brcmfmac-sdio.h create mode 100644 include/linux/platform_data/brcmfmac.h (limited to 'include/linux') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index 25cd71229c95..bb4aece9ad2c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -103,7 +103,7 @@ static void brcmf_sdiod_dummy_irqhandler(struct sdio_func *func) int brcmf_sdiod_intr_register(struct brcmf_sdio_dev *sdiodev) { - struct brcmfmac_sdio_platform_data *pdata; + struct brcmfmac_sdio_pd *pdata; int ret = 0; u8 data; u32 addr, gpiocontrol; @@ -173,7 +173,7 @@ int brcmf_sdiod_intr_register(struct brcmf_sdio_dev *sdiodev) int brcmf_sdiod_intr_unregister(struct brcmf_sdio_dev *sdiodev) { - struct brcmfmac_sdio_platform_data *pdata; + struct brcmfmac_sdio_pd *pdata; brcmf_dbg(SDIO, "Entering\n"); @@ -1164,17 +1164,6 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, dev_set_drvdata(&func->dev, bus_if); dev_set_drvdata(&sdiodev->func[1]->dev, bus_if); sdiodev->dev = &sdiodev->func[1]->dev; - sdiodev->pdata = brcmf_get_module_param(sdiodev->dev); - -#ifdef CONFIG_PM_SLEEP - /* wowl can be supported when KEEP_POWER is true and (WAKE_SDIO_IRQ - * is true or when platform data OOB irq is true). - */ - if ((sdio_get_host_pm_caps(sdiodev->func[1]) & MMC_PM_KEEP_POWER) && - ((sdio_get_host_pm_caps(sdiodev->func[1]) & MMC_PM_WAKE_SDIO_IRQ) || - (sdiodev->pdata && sdiodev->pdata->oob_irq_supported))) - bus_if->wowl_supported = true; -#endif brcmf_sdiod_change_state(sdiodev, BRCMF_SDIOD_DOWN); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 5609a79df1c1..5e3acaca7231 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -6459,8 +6459,8 @@ int brcmf_cfg80211_wait_vif_event(struct brcmf_cfg80211_info *cfg, static s32 brcmf_translate_country_code(struct brcmf_pub *drvr, char alpha2[2], struct brcmf_fil_country_le *ccreq) { - struct cc_translate *country_codes; - struct cc_entry *cc; + struct brcmfmac_pd_cc *country_codes; + struct brcmfmac_pd_cc_entry *cc; s32 found_index; int i; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c index 020901c2e0ca..4bd3225cdea6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c @@ -80,7 +80,7 @@ module_param_named(ignore_probe_fail, brcmf_ignore_probe_fail, int, 0); MODULE_PARM_DESC(ignore_probe_fail, "always succeed probe for debugging"); #endif -static struct brcmfmac_sdio_platform_data *brcmfmac_pdata; +static struct brcmfmac_platform_data *brcmfmac_pdata; struct brcmf_mp_global_t brcmf_mp_global; int brcmf_c_preinit_dcmds(struct brcmf_if *ifp) @@ -229,15 +229,46 @@ void __brcmf_dbg(u32 level, const char *func, const char *fmt, ...) static void brcmf_mp_attach(void) { + /* If module param firmware path is set then this will always be used, + * if not set then if available use the platform data version. To make + * sure it gets initialized at all, always copy the module param version + */ strlcpy(brcmf_mp_global.firmware_path, brcmf_firmware_path, BRCMF_FW_ALTPATH_LEN); + if ((brcmfmac_pdata) && (brcmfmac_pdata->fw_alternative_path) && + (brcmf_mp_global.firmware_path[0] == '\0')) { + strlcpy(brcmf_mp_global.firmware_path, + brcmfmac_pdata->fw_alternative_path, + BRCMF_FW_ALTPATH_LEN); + } } -struct brcmfmac_sdio_platform_data *brcmf_get_module_param(struct device *dev) +struct brcmfmac_sdio_pd *brcmf_get_module_param(struct device *dev, + enum brcmf_bus_type bus_type, + u32 chip, u32 chiprev) { - if (!brcmfmac_pdata) - brcmf_of_probe(dev, &brcmfmac_pdata); - return brcmfmac_pdata; + struct brcmfmac_sdio_pd *pdata; + struct brcmfmac_pd_device *device_pd; + int i; + + if (brcmfmac_pdata) { + for (i = 0; i < brcmfmac_pdata->device_count; i++) { + device_pd = &brcmfmac_pdata->devices[i]; + if ((device_pd->bus_type == bus_type) && + (device_pd->id == chip) && + ((device_pd->rev == chiprev) || + (device_pd->rev == -1))) { + brcmf_dbg(INFO, "Platform data for device found\n"); + if (device_pd->bus_type == BRCMF_BUSTYPE_SDIO) + return &device_pd->bus.sdio; + break; + } + } + } + pdata = NULL; + brcmf_of_probe(dev, &pdata); + + return pdata; } int brcmf_mp_device_attach(struct brcmf_pub *drvr) @@ -287,7 +318,7 @@ static int brcmf_common_pd_remove(struct platform_device *pdev) static struct platform_driver brcmf_pd = { .remove = brcmf_common_pd_remove, .driver = { - .name = BRCMFMAC_SDIO_PDATA_NAME, + .name = BRCMFMAC_PDATA_NAME, } }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h index 54a26ede808d..a64e40e8bfda 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h @@ -16,7 +16,7 @@ #define BRCMFMAC_COMMON_H #include -#include +#include #include "fwil_types.h" extern const u8 ALLFFMAC[ETH_ALEN]; @@ -42,33 +42,6 @@ struct brcmf_mp_global_t { extern struct brcmf_mp_global_t brcmf_mp_global; -/** - * struct cc_entry - Struct for translating user space country code (iso3166) to - * firmware country code and revision. - * - * @iso3166: iso3166 alpha 2 country code string. - * @cc: firmware country code string. - * @rev: firmware country code revision. - */ -struct cc_entry { - char iso3166[BRCMF_COUNTRY_BUF_SZ]; - char cc[BRCMF_COUNTRY_BUF_SZ]; - s32 rev; -}; - -/** - * struct cc_translate - Struct for translating country codes as set by user - * space to a country code and rev which can be used by - * firmware. - * - * @table_size: number of entries in table (> 0) - * @table: dynamic array of 1 or more elements with translation information. - */ -struct cc_translate { - int table_size; - struct cc_entry table[0]; -}; - /** * struct brcmf_mp_device - Device module paramaters. * @@ -88,10 +61,12 @@ struct brcmf_mp_device { int fcmode; bool roamoff; bool ignore_probe_fail; - struct cc_translate *country_codes; + struct brcmfmac_pd_cc *country_codes; }; -struct brcmfmac_sdio_platform_data *brcmf_get_module_param(struct device *dev); +struct brcmfmac_sdio_pd *brcmf_get_module_param(struct device *dev, + enum brcmf_bus_type bus_type, + u32 chip, u32 chiprev); int brcmf_mp_device_attach(struct brcmf_pub *drvr); void brcmf_mp_device_detach(struct brcmf_pub *drvr); #ifdef DEBUG diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c index 8201d937b826..ece0b65dd039 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c @@ -23,8 +23,7 @@ #include "common.h" #include "of.h" -void -brcmf_of_probe(struct device *dev, struct brcmfmac_sdio_platform_data **sdio) +void brcmf_of_probe(struct device *dev, struct brcmfmac_sdio_pd **sdio) { struct device_node *np = dev->of_node; int irq; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.h index 84b474484cea..1ba951f9b542 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.h @@ -15,10 +15,9 @@ */ #ifdef CONFIG_OF void -brcmf_of_probe(struct device *dev, struct brcmfmac_sdio_platform_data **sdio); +brcmf_of_probe(struct device *dev, struct brcmfmac_sdio_pd **sdio); #else -static void brcmf_of_probe(struct device *dev, - struct brcmfmac_sdio_platform_data **sdio) +static void brcmf_of_probe(struct device *dev, struct brcmfmac_sdio_pd **sdio) { } #endif /* CONFIG_OF */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index c790fa89db05..6e367041f691 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -33,8 +33,6 @@ #include #include #include -#include -#include #include #include #include @@ -44,6 +42,8 @@ #include "sdio.h" #include "chip.h" #include "firmware.h" +#include "core.h" +#include "common.h" #define DCMD_RESP_TIMEOUT msecs_to_jiffies(2500) #define CTL_DONE_TIMEOUT msecs_to_jiffies(2500) @@ -3775,26 +3775,28 @@ static const struct brcmf_buscore_ops brcmf_sdio_buscore_ops = { static bool brcmf_sdio_probe_attach(struct brcmf_sdio *bus) { + struct brcmf_sdio_dev *sdiodev; u8 clkctl = 0; int err = 0; int reg_addr; u32 reg_val; u32 drivestrength; - sdio_claim_host(bus->sdiodev->func[1]); + sdiodev = bus->sdiodev; + sdio_claim_host(sdiodev->func[1]); pr_debug("F1 signature read @0x18000000=0x%4x\n", - brcmf_sdiod_regrl(bus->sdiodev, SI_ENUM_BASE, NULL)); + brcmf_sdiod_regrl(sdiodev, SI_ENUM_BASE, NULL)); /* * Force PLL off until brcmf_chip_attach() * programs PLL control regs */ - brcmf_sdiod_regwb(bus->sdiodev, SBSDIO_FUNC1_CHIPCLKCSR, + brcmf_sdiod_regwb(sdiodev, SBSDIO_FUNC1_CHIPCLKCSR, BRCMF_INIT_CLKCTL1, &err); if (!err) - clkctl = brcmf_sdiod_regrb(bus->sdiodev, + clkctl = brcmf_sdiod_regrb(sdiodev, SBSDIO_FUNC1_CHIPCLKCSR, &err); if (err || ((clkctl & ~SBSDIO_AVBITS) != BRCMF_INIT_CLKCTL1)) { @@ -3803,50 +3805,77 @@ brcmf_sdio_probe_attach(struct brcmf_sdio *bus) goto fail; } - bus->ci = brcmf_chip_attach(bus->sdiodev, &brcmf_sdio_buscore_ops); + bus->ci = brcmf_chip_attach(sdiodev, &brcmf_sdio_buscore_ops); if (IS_ERR(bus->ci)) { brcmf_err("brcmf_chip_attach failed!\n"); bus->ci = NULL; goto fail; } + sdiodev->pdata = brcmf_get_module_param(sdiodev->dev, + BRCMF_BUSTYPE_SDIO, + bus->ci->chip, + bus->ci->chiprev); + /* platform specific configuration: + * alignments must be at least 4 bytes for ADMA + */ + bus->head_align = ALIGNMENT; + bus->sgentry_align = ALIGNMENT; + if (sdiodev->pdata) { + if (sdiodev->pdata->sd_head_align > ALIGNMENT) + bus->head_align = sdiodev->pdata->sd_head_align; + if (sdiodev->pdata->sd_sgentry_align > ALIGNMENT) + bus->sgentry_align = sdiodev->pdata->sd_sgentry_align; + } + /* allocate scatter-gather table. sg support + * will be disabled upon allocation failure. + */ + brcmf_sdiod_sgtable_alloc(sdiodev); + +#ifdef CONFIG_PM_SLEEP + /* wowl can be supported when KEEP_POWER is true and (WAKE_SDIO_IRQ + * is true or when platform data OOB irq is true). + */ + if ((sdio_get_host_pm_caps(sdiodev->func[1]) & MMC_PM_KEEP_POWER) && + ((sdio_get_host_pm_caps(sdiodev->func[1]) & MMC_PM_WAKE_SDIO_IRQ) || + (sdiodev->pdata && sdiodev->pdata->oob_irq_supported))) + sdiodev->bus_if->wowl_supported = true; +#endif if (brcmf_sdio_kso_init(bus)) { brcmf_err("error enabling KSO\n"); goto fail; } - if ((bus->sdiodev->pdata) && (bus->sdiodev->pdata->drive_strength)) - drivestrength = bus->sdiodev->pdata->drive_strength; + if ((sdiodev->pdata) && (sdiodev->pdata->drive_strength)) + drivestrength = sdiodev->pdata->drive_strength; else drivestrength = DEFAULT_SDIO_DRIVE_STRENGTH; - brcmf_sdio_drivestrengthinit(bus->sdiodev, bus->ci, drivestrength); + brcmf_sdio_drivestrengthinit(sdiodev, bus->ci, drivestrength); /* Set card control so an SDIO card reset does a WLAN backplane reset */ - reg_val = brcmf_sdiod_regrb(bus->sdiodev, - SDIO_CCCR_BRCM_CARDCTRL, &err); + reg_val = brcmf_sdiod_regrb(sdiodev, SDIO_CCCR_BRCM_CARDCTRL, &err); if (err) goto fail; reg_val |= SDIO_CCCR_BRCM_CARDCTRL_WLANRESET; - brcmf_sdiod_regwb(bus->sdiodev, - SDIO_CCCR_BRCM_CARDCTRL, reg_val, &err); + brcmf_sdiod_regwb(sdiodev, SDIO_CCCR_BRCM_CARDCTRL, reg_val, &err); if (err) goto fail; /* set PMUControl so a backplane reset does PMU state reload */ reg_addr = CORE_CC_REG(brcmf_chip_get_pmu(bus->ci)->base, pmucontrol); - reg_val = brcmf_sdiod_regrl(bus->sdiodev, reg_addr, &err); + reg_val = brcmf_sdiod_regrl(sdiodev, reg_addr, &err); if (err) goto fail; reg_val |= (BCMA_CC_PMU_CTL_RES_RELOAD << BCMA_CC_PMU_CTL_RES_SHIFT); - brcmf_sdiod_regwl(bus->sdiodev, reg_addr, reg_val, &err); + brcmf_sdiod_regwl(sdiodev, reg_addr, reg_val, &err); if (err) goto fail; - sdio_release_host(bus->sdiodev->func[1]); + sdio_release_host(sdiodev->func[1]); brcmu_pktq_init(&bus->txq, (PRIOMASK + 1), TXQLEN); @@ -3867,7 +3896,7 @@ brcmf_sdio_probe_attach(struct brcmf_sdio *bus) return true; fail: - sdio_release_host(bus->sdiodev->func[1]); + sdio_release_host(sdiodev->func[1]); return false; } @@ -4045,18 +4074,6 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) bus->txminmax = BRCMF_TXMINMAX; bus->tx_seq = SDPCM_SEQ_WRAP - 1; - /* platform specific configuration: - * alignments must be at least 4 bytes for ADMA - */ - bus->head_align = ALIGNMENT; - bus->sgentry_align = ALIGNMENT; - if (sdiodev->pdata) { - if (sdiodev->pdata->sd_head_align > ALIGNMENT) - bus->head_align = sdiodev->pdata->sd_head_align; - if (sdiodev->pdata->sd_sgentry_align > ALIGNMENT) - bus->sgentry_align = sdiodev->pdata->sd_sgentry_align; - } - /* single-threaded workqueue */ wq = alloc_ordered_workqueue("brcmf_wq/%s", WQ_MEM_RECLAIM, dev_name(&sdiodev->func[1]->dev)); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h index 23f223150cef..50df9cb21af2 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h @@ -184,7 +184,7 @@ struct brcmf_sdio_dev { struct brcmf_sdio *bus; struct device *dev; struct brcmf_bus *bus_if; - struct brcmfmac_sdio_platform_data *pdata; + struct brcmfmac_sdio_pd *pdata; bool oob_irq_requested; bool irq_en; /* irq enable flags */ spinlock_t irq_en_lock; diff --git a/include/linux/platform_data/brcmfmac-sdio.h b/include/linux/platform_data/brcmfmac-sdio.h deleted file mode 100644 index e75dcbf2b230..000000000000 --- a/include/linux/platform_data/brcmfmac-sdio.h +++ /dev/null @@ -1,135 +0,0 @@ -/* - * Copyright (c) 2013 Broadcom Corporation - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY - * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION - * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN - * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ - -#ifndef _LINUX_BRCMFMAC_PLATFORM_H -#define _LINUX_BRCMFMAC_PLATFORM_H - -/* - * Platform specific driver functions and data. Through the platform specific - * device data functions can be provided to help the brcmfmac driver to - * operate with the device in combination with the used platform. - * - * Use the platform data in the following (similar) way: - * - * -#include - - -static void brcmfmac_power_on(void) -{ -} - -static void brcmfmac_power_off(void) -{ -} - -static void brcmfmac_reset(void) -{ -} - -static struct brcmfmac_sdio_platform_data brcmfmac_sdio_pdata = { - .power_on = brcmfmac_power_on, - .power_off = brcmfmac_power_off, - .reset = brcmfmac_reset -}; - -static struct platform_device brcmfmac_device = { - .name = BRCMFMAC_SDIO_PDATA_NAME, - .id = PLATFORM_DEVID_NONE, - .dev.platform_data = &brcmfmac_sdio_pdata -}; - -void __init brcmfmac_init_pdata(void) -{ - brcmfmac_sdio_pdata.oob_irq_supported = true; - brcmfmac_sdio_pdata.oob_irq_nr = gpio_to_irq(GPIO_BRCMF_SDIO_OOB); - brcmfmac_sdio_pdata.oob_irq_flags = IORESOURCE_IRQ | - IORESOURCE_IRQ_HIGHLEVEL; - platform_device_register(&brcmfmac_device); -} - * - * - * Note: the brcmfmac can be loaded as module or be statically built-in into - * the kernel. If built-in then do note that it uses module_init (and - * module_exit) routines which equal device_initcall. So if you intend to - * create a module with the platform specific data for the brcmfmac and have - * it built-in to the kernel then use a higher initcall then device_initcall - * (see init.h). If this is not done then brcmfmac will load without problems - * but will not pickup the platform data. - * - * When the driver does not "detect" platform driver data then it will continue - * without reporting anything and just assume there is no data needed. Which is - * probably true for most platforms. - * - * Explanation of the platform_data fields: - * - * drive_strength: is the preferred drive_strength to be used for the SDIO - * pins. If 0 then a default value will be used. This is the target drive - * strength, the exact drive strength which will be used depends on the - * capabilities of the device. - * - * oob_irq_supported: does the board have support for OOB interrupts. SDIO - * in-band interrupts are relatively slow and for having less overhead on - * interrupt processing an out of band interrupt can be used. If the HW - * supports this then enable this by setting this field to true and configure - * the oob related fields. - * - * oob_irq_nr, oob_irq_flags: the OOB interrupt information. The values are - * used for registering the irq using request_irq function. - * - * broken_sg_support: flag for broken sg list support of SDIO host controller. - * Set this to true if the SDIO host controller has higher align requirement - * than 32 bytes for each scatterlist item. - * - * sd_head_align: alignment requirement for start of data buffer - * - * sd_sgentry_align: length alignment requirement for each sg entry - * - * power_on: This function is called by the brcmfmac when the module gets - * loaded. This can be particularly useful for low power devices. The platform - * spcific routine may for example decide to power up the complete device. - * If there is no use-case for this function then provide NULL. - * - * power_off: This function is called by the brcmfmac when the module gets - * unloaded. At this point the device can be powered down or otherwise be reset. - * So if an actual power_off is not supported but reset is then reset the device - * when this function gets called. This can be particularly useful for low power - * devices. If there is no use-case for this function (either power-down or - * reset) then provide NULL. - * - * reset: This function can get called if the device communication broke down. - * This functionality is particularly useful in case of SDIO type devices. It is - * possible to reset a dongle via sdio data interface, but it requires that - * this is fully functional. This function is chip/module specific and this - * function should return only after the complete reset has completed. - */ - -#define BRCMFMAC_SDIO_PDATA_NAME "brcmfmac_sdio" - -struct brcmfmac_sdio_platform_data { - unsigned int drive_strength; - bool oob_irq_supported; - unsigned int oob_irq_nr; - unsigned long oob_irq_flags; - bool broken_sg_support; - unsigned short sd_head_align; - unsigned short sd_sgentry_align; - void (*power_on)(void); - void (*power_off)(void); - void (*reset)(void); -}; - -#endif /* _LINUX_BRCMFMAC_PLATFORM_H */ diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h new file mode 100644 index 000000000000..1d30bf278231 --- /dev/null +++ b/include/linux/platform_data/brcmfmac.h @@ -0,0 +1,185 @@ +/* + * Copyright (c) 201 Broadcom Corporation + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION + * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN + * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef _LINUX_BRCMFMAC_PLATFORM_H +#define _LINUX_BRCMFMAC_PLATFORM_H + + +#define BRCMFMAC_PDATA_NAME "brcmfmac" + +#define BRCMFMAC_COUNTRY_BUF_SZ 4 + + +/* + * Platform specific driver functions and data. Through the platform specific + * device data functions and data can be provided to help the brcmfmac driver to + * operate with the device in combination with the used platform. + */ + + +/** + * Note: the brcmfmac can be loaded as module or be statically built-in into + * the kernel. If built-in then do note that it uses module_init (and + * module_exit) routines which equal device_initcall. So if you intend to + * create a module with the platform specific data for the brcmfmac and have + * it built-in to the kernel then use a higher initcall then device_initcall + * (see init.h). If this is not done then brcmfmac will load without problems + * but will not pickup the platform data. + * + * When the driver does not "detect" platform driver data then it will continue + * without reporting anything and just assume there is no data needed. Which is + * probably true for most platforms. + */ + +/** + * enum brcmf_bus_type - Bus type identifier. Currently SDIO, USB and PCIE are + * supported. + */ +enum brcmf_bus_type { + BRCMF_BUSTYPE_SDIO, + BRCMF_BUSTYPE_USB, + BRCMF_BUSTYPE_PCIE +}; + + +/** + * struct brcmfmac_sdio_pd - SDIO Device specific platform data. + * + * @txglomsz: SDIO txglom size. Use 0 if default of driver is to be + * used. + * @drive_strength: is the preferred drive_strength to be used for the SDIO + * pins. If 0 then a default value will be used. This is + * the target drive strength, the exact drive strength + * which will be used depends on the capabilities of the + * device. + * @oob_irq_supported: does the board have support for OOB interrupts. SDIO + * in-band interrupts are relatively slow and for having + * less overhead on interrupt processing an out of band + * interrupt can be used. If the HW supports this then + * enable this by setting this field to true and configure + * the oob related fields. + * @oob_irq_nr, + * @oob_irq_flags: the OOB interrupt information. The values are used for + * registering the irq using request_irq function. + * @broken_sg_support: flag for broken sg list support of SDIO host controller. + * Set this to true if the SDIO host controller has higher + * align requirement than 32 bytes for each scatterlist + * item. + * @sd_head_align: alignment requirement for start of data buffer. + * @sd_sgentry_align: length alignment requirement for each sg entry. + * @reset: This function can get called if the device communication + * broke down. This functionality is particularly useful in + * case of SDIO type devices. It is possible to reset a + * dongle via sdio data interface, but it requires that + * this is fully functional. This function is chip/module + * specific and this function should return only after the + * complete reset has completed. + */ +struct brcmfmac_sdio_pd { + int txglomsz; + unsigned int drive_strength; + bool oob_irq_supported; + unsigned int oob_irq_nr; + unsigned long oob_irq_flags; + bool broken_sg_support; + unsigned short sd_head_align; + unsigned short sd_sgentry_align; + void (*reset)(void); +}; + +/** + * struct brcmfmac_pd_cc_entry - Struct for translating user space country code + * (iso3166) to firmware country code and + * revision. + * + * @iso3166: iso3166 alpha 2 country code string. + * @cc: firmware country code string. + * @rev: firmware country code revision. + */ +struct brcmfmac_pd_cc_entry { + char iso3166[BRCMFMAC_COUNTRY_BUF_SZ]; + char cc[BRCMFMAC_COUNTRY_BUF_SZ]; + s32 rev; +}; + +/** + * struct brcmfmac_pd_cc - Struct for translating country codes as set by user + * space to a country code and rev which can be used by + * firmware. + * + * @table_size: number of entries in table (> 0) + * @table: array of 1 or more elements with translation information. + */ +struct brcmfmac_pd_cc { + int table_size; + struct brcmfmac_pd_cc_entry table[0]; +}; + +/** + * struct brcmfmac_pd_device - Device specific platform data. (id/rev/bus_type) + * is the unique identifier of the device. + * + * @id: ID of the device for which this data is. In case of SDIO + * or PCIE this is the chipid as identified by chip.c In + * case of USB this is the chipid as identified by the + * device query. + * @rev: chip revision, see id. + * @bus_type: The type of bus. Some chipid/rev exist for different bus + * types. Each bus type has its own set of settings. + * @feature_disable: Bitmask of features to disable (override), See feature.c + * in brcmfmac for details. + * @country_codes: If available, pointer to struct for translating country + * codes. + * @bus: Bus specific (union) device settings. Currently only + * SDIO. + */ +struct brcmfmac_pd_device { + unsigned int id; + unsigned int rev; + enum brcmf_bus_type bus_type; + unsigned int feature_disable; + struct brcmfmac_pd_cc *country_codes; + union { + struct brcmfmac_sdio_pd sdio; + } bus; +}; + +/** + * struct brcmfmac_platform_data - BRCMFMAC specific platform data. + * + * @power_on: This function is called by the brcmfmac driver when the module + * gets loaded. This can be particularly useful for low power + * devices. The platform spcific routine may for example decide to + * power up the complete device. If there is no use-case for this + * function then provide NULL. + * @power_off: This function is called by the brcmfmac when the module gets + * unloaded. At this point the devices can be powered down or + * otherwise be reset. So if an actual power_off is not supported + * but reset is supported by the devices then reset the devices + * when this function gets called. This can be particularly useful + * for low power devices. If there is no use-case for this + * function then provide NULL. + */ +struct brcmfmac_platform_data { + void (*power_on)(void); + void (*power_off)(void); + char *fw_alternative_path; + int device_count; + struct brcmfmac_pd_device devices[0]; +}; + + +#endif /* _LINUX_BRCMFMAC_PLATFORM_H */ -- cgit v1.2.3 From 2e62f9b2a41e4ade1a0bb3c1bbda4defe4c67243 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Fri, 12 Feb 2016 10:15:43 +0100 Subject: bcma: drop unneeded fields from bcma_pflash struct MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Most of info stored in this struct wasn't really used anywhere as we put all that data in platform data & resource as well. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- drivers/bcma/driver_mips.c | 11 ++++------- include/linux/bcma/bcma_driver_chipcommon.h | 3 --- 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c index a40a203314db..20c134c016dc 100644 --- a/drivers/bcma/driver_mips.c +++ b/drivers/bcma/driver_mips.c @@ -288,18 +288,15 @@ static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore) case BCMA_CC_FLASHT_PARA: bcma_debug(bus, "Found parallel flash\n"); pflash->present = true; - pflash->window = BCMA_SOC_FLASH2; - pflash->window_size = BCMA_SOC_FLASH2_SZ; if ((bcma_read32(cc->core, BCMA_CC_FLASH_CFG) & BCMA_CC_FLASH_CFG_DS) == 0) - pflash->buswidth = 1; + bcma_pflash_data.width = 1; else - pflash->buswidth = 2; + bcma_pflash_data.width = 2; - bcma_pflash_data.width = pflash->buswidth; - bcma_pflash_resource.start = pflash->window; - bcma_pflash_resource.end = pflash->window + pflash->window_size; + bcma_pflash_resource.start = BCMA_SOC_FLASH2; + bcma_pflash_resource.end = BCMA_SOC_FLASH2 + BCMA_SOC_FLASH2_SZ; break; default: diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 700d0c6f7480..16eaaad9dda5 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -579,9 +579,6 @@ struct bcma_chipcommon_pmu { #ifdef CONFIG_BCMA_DRIVER_MIPS struct bcma_pflash { bool present; - u8 buswidth; - u32 window; - u32 window_size; }; #ifdef CONFIG_BCMA_SFLASH -- cgit v1.2.3 From d6a3b51ada68c2bd3e184f4729ce626a1721cf74 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Fri, 12 Feb 2016 10:15:44 +0100 Subject: bcma: move parallel flash support to separated file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This follows the way of handling other flashes and cleans code a bit. As next task we will want to move flash code to ChipCommon driver as: 1) Flash controllers are accesible using ChipCommon registers 2) This code isn't MIPS specific This change prepares bcma for that. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- drivers/bcma/Kconfig | 5 +++ drivers/bcma/Makefile | 1 + drivers/bcma/bcma_private.h | 18 +++++++++-- drivers/bcma/driver_chipcommon_pflash.c | 49 +++++++++++++++++++++++++++++ drivers/bcma/driver_mips.c | 35 +-------------------- drivers/bcma/main.c | 2 +- include/linux/bcma/bcma_driver_chipcommon.h | 8 +++-- 7 files changed, 78 insertions(+), 40 deletions(-) create mode 100644 drivers/bcma/driver_chipcommon_pflash.c (limited to 'include/linux') diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig index 023d448ed3fa..efdc2ae8441a 100644 --- a/drivers/bcma/Kconfig +++ b/drivers/bcma/Kconfig @@ -70,6 +70,11 @@ config BCMA_DRIVER_MIPS If unsure, say N +config BCMA_PFLASH + bool + depends on BCMA_DRIVER_MIPS + default y + config BCMA_SFLASH bool depends on BCMA_DRIVER_MIPS diff --git a/drivers/bcma/Makefile b/drivers/bcma/Makefile index f32af9b76bcd..087948a1d20d 100644 --- a/drivers/bcma/Makefile +++ b/drivers/bcma/Makefile @@ -1,6 +1,7 @@ bcma-y += main.o scan.o core.o sprom.o bcma-y += driver_chipcommon.o driver_chipcommon_pmu.o bcma-y += driver_chipcommon_b.o +bcma-$(CONFIG_BCMA_PFLASH) += driver_chipcommon_pflash.o bcma-$(CONFIG_BCMA_SFLASH) += driver_chipcommon_sflash.o bcma-$(CONFIG_BCMA_NFLASH) += driver_chipcommon_nflash.o bcma-$(CONFIG_BCMA_DRIVER_PCI) += driver_pci.o diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index 7e4ddfb076d3..eda09090cb52 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -47,9 +47,6 @@ int bcma_sprom_get(struct bcma_bus *bus); void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc); void bcma_core_chipcommon_init(struct bcma_drv_cc *cc); void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable); -#ifdef CONFIG_BCMA_DRIVER_MIPS -extern struct platform_device bcma_pflash_dev; -#endif /* CONFIG_BCMA_DRIVER_MIPS */ /* driver_chipcommon_b.c */ int bcma_core_chipcommon_b_init(struct bcma_drv_cc_b *ccb); @@ -61,6 +58,21 @@ void bcma_pmu_init(struct bcma_drv_cc *cc); u32 bcma_pmu_get_alp_clock(struct bcma_drv_cc *cc); u32 bcma_pmu_get_cpu_clock(struct bcma_drv_cc *cc); +/************************************************** + * driver_chipcommon_sflash.c + **************************************************/ + +#ifdef CONFIG_BCMA_PFLASH +extern struct platform_device bcma_pflash_dev; +int bcma_pflash_init(struct bcma_drv_cc *cc); +#else +static inline int bcma_pflash_init(struct bcma_drv_cc *cc) +{ + bcma_err(cc->core->bus, "Parallel flash not supported\n"); + return 0; +} +#endif /* CONFIG_BCMA_PFLASH */ + #ifdef CONFIG_BCMA_SFLASH /* driver_chipcommon_sflash.c */ int bcma_sflash_init(struct bcma_drv_cc *cc); diff --git a/drivers/bcma/driver_chipcommon_pflash.c b/drivers/bcma/driver_chipcommon_pflash.c new file mode 100644 index 000000000000..3b497c9ee0d4 --- /dev/null +++ b/drivers/bcma/driver_chipcommon_pflash.c @@ -0,0 +1,49 @@ +/* + * Broadcom specific AMBA + * ChipCommon parallel flash + * + * Licensed under the GNU/GPL. See COPYING for details. + */ + +#include "bcma_private.h" + +#include +#include +#include + +static const char * const part_probes[] = { "bcm47xxpart", NULL }; + +static struct physmap_flash_data bcma_pflash_data = { + .part_probe_types = part_probes, +}; + +static struct resource bcma_pflash_resource = { + .name = "bcma_pflash", + .flags = IORESOURCE_MEM, +}; + +struct platform_device bcma_pflash_dev = { + .name = "physmap-flash", + .dev = { + .platform_data = &bcma_pflash_data, + }, + .resource = &bcma_pflash_resource, + .num_resources = 1, +}; + +int bcma_pflash_init(struct bcma_drv_cc *cc) +{ + struct bcma_pflash *pflash = &cc->pflash; + + pflash->present = true; + + if (!(bcma_read32(cc->core, BCMA_CC_FLASH_CFG) & BCMA_CC_FLASH_CFG_DS)) + bcma_pflash_data.width = 1; + else + bcma_pflash_data.width = 2; + + bcma_pflash_resource.start = BCMA_SOC_FLASH2; + bcma_pflash_resource.end = BCMA_SOC_FLASH2 + BCMA_SOC_FLASH2_SZ; + + return 0; +} diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c index 20c134c016dc..967b0e85e2cc 100644 --- a/drivers/bcma/driver_mips.c +++ b/drivers/bcma/driver_mips.c @@ -14,8 +14,6 @@ #include -#include -#include #include #include #include @@ -32,26 +30,6 @@ enum bcma_boot_dev { BCMA_BOOT_DEV_NAND, }; -static const char * const part_probes[] = { "bcm47xxpart", NULL }; - -static struct physmap_flash_data bcma_pflash_data = { - .part_probe_types = part_probes, -}; - -static struct resource bcma_pflash_resource = { - .name = "bcma_pflash", - .flags = IORESOURCE_MEM, -}; - -struct platform_device bcma_pflash_dev = { - .name = "physmap-flash", - .dev = { - .platform_data = &bcma_pflash_data, - }, - .resource = &bcma_pflash_resource, - .num_resources = 1, -}; - /* The 47162a0 hangs when reading MIPS DMP registers registers */ static inline bool bcma_core_mips_bcm47162a0_quirk(struct bcma_device *dev) { @@ -276,7 +254,6 @@ static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore) { struct bcma_bus *bus = mcore->core->bus; struct bcma_drv_cc *cc = &bus->drv_cc; - struct bcma_pflash *pflash = &cc->pflash; enum bcma_boot_dev boot_dev; switch (cc->capabilities & BCMA_CC_CAP_FLASHT) { @@ -287,17 +264,7 @@ static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore) break; case BCMA_CC_FLASHT_PARA: bcma_debug(bus, "Found parallel flash\n"); - pflash->present = true; - - if ((bcma_read32(cc->core, BCMA_CC_FLASH_CFG) & - BCMA_CC_FLASH_CFG_DS) == 0) - bcma_pflash_data.width = 1; - else - bcma_pflash_data.width = 2; - - bcma_pflash_resource.start = BCMA_SOC_FLASH2; - bcma_pflash_resource.end = BCMA_SOC_FLASH2 + BCMA_SOC_FLASH2_SZ; - + bcma_pflash_init(cc); break; default: bcma_err(bus, "Flash type not supported\n"); diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index c466f752b067..786be8fed39e 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -350,7 +350,7 @@ static int bcma_register_devices(struct bcma_bus *bus) bcma_register_core(bus, core); } -#ifdef CONFIG_BCMA_DRIVER_MIPS +#ifdef CONFIG_BCMA_PFLASH if (bus->drv_cc.pflash.present) { err = platform_device_register(&bcma_pflash_dev); if (err) diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 16eaaad9dda5..846513c73606 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -576,10 +576,11 @@ struct bcma_chipcommon_pmu { u32 crystalfreq; /* The active crystal frequency (in kHz) */ }; -#ifdef CONFIG_BCMA_DRIVER_MIPS +#ifdef CONFIG_BCMA_PFLASH struct bcma_pflash { bool present; }; +#endif #ifdef CONFIG_BCMA_SFLASH struct mtd_info; @@ -603,6 +604,7 @@ struct bcma_nflash { }; #endif +#ifdef CONFIG_BCMA_DRIVER_MIPS struct bcma_serial_port { void *regs; unsigned long clockspeed; @@ -622,8 +624,9 @@ struct bcma_drv_cc { /* Fast Powerup Delay constant */ u16 fast_pwrup_delay; struct bcma_chipcommon_pmu pmu; -#ifdef CONFIG_BCMA_DRIVER_MIPS +#ifdef CONFIG_BCMA_PFLASH struct bcma_pflash pflash; +#endif #ifdef CONFIG_BCMA_SFLASH struct bcma_sflash sflash; #endif @@ -631,6 +634,7 @@ struct bcma_drv_cc { struct bcma_nflash nflash; #endif +#ifdef CONFIG_BCMA_DRIVER_MIPS int nr_serial_ports; struct bcma_serial_port serial_ports[4]; #endif /* CONFIG_BCMA_DRIVER_MIPS */ -- cgit v1.2.3 From 088c86183012495b53ecc1c734909e5712a40b66 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Fri, 4 Mar 2016 12:35:05 -0500 Subject: qed/qede: Add infrastructure support for hardware GRO This patch adds mainly structures and APIs prototype changes in order to give support for qede slowpath/fastpath support for the same. Signed-off-by: Yuval Mintz Signed-off-by: Manish Chopra Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 14 ++++- drivers/net/ethernet/qlogic/qed/qed_l2.c | 81 +++++++++++++++++++--------- drivers/net/ethernet/qlogic/qede/qede_main.c | 17 +++--- include/linux/qed/qed_eth_if.h | 12 +++-- 4 files changed, 88 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 592e0e6d9b42..236db8a99ec3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -2919,7 +2919,19 @@ struct eth_vport_rx_mode { }; struct eth_vport_tpa_param { - u64 reserved[2]; + u8 tpa_ipv4_en_flg; + u8 tpa_ipv6_en_flg; + u8 tpa_ipv4_tunn_en_flg; + u8 tpa_ipv6_tunn_en_flg; + u8 tpa_pkt_split_flg; + u8 tpa_hdr_data_split_flg; + u8 tpa_gro_consistent_flg; + u8 tpa_max_aggs_num; + u16 tpa_max_size; + u16 tpa_min_size_to_start; + u16 tpa_min_size_to_cont; + u8 max_buff_num; + u8 reserved; }; struct eth_vport_tx_mode { diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 102ddc73b841..3f35c6ca9252 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -132,16 +132,29 @@ struct qed_sp_vport_update_params { struct qed_filter_accept_flags accept_flags; }; +enum qed_tpa_mode { + QED_TPA_MODE_NONE, + QED_TPA_MODE_UNUSED, + QED_TPA_MODE_GRO, + QED_TPA_MODE_MAX +}; + +struct qed_sp_vport_start_params { + enum qed_tpa_mode tpa_mode; + bool remove_inner_vlan; + bool drop_ttl0; + u8 max_buffers_per_cqe; + u32 concrete_fid; + u16 opaque_fid; + u8 vport_id; + u16 mtu; +}; + #define QED_MAX_SGES_NUM 16 #define CRC32_POLY 0x1edc6f41 static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, - u32 concrete_fid, - u16 opaque_fid, - u8 vport_id, - u16 mtu, - u8 drop_ttl0_flg, - u8 inner_vlan_removal_en_flg) + struct qed_sp_vport_start_params *p_params) { struct vport_start_ramrod_data *p_ramrod = NULL; struct qed_spq_entry *p_ent = NULL; @@ -150,13 +163,13 @@ static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, u16 rx_mode = 0; u8 abs_vport_id = 0; - rc = qed_fw_vport(p_hwfn, vport_id, &abs_vport_id); + rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id); if (rc != 0) return rc; memset(&init_data, 0, sizeof(init_data)); init_data.cid = qed_spq_get_cid(p_hwfn); - init_data.opaque_fid = opaque_fid; + init_data.opaque_fid = p_params->opaque_fid; init_data.comp_mode = QED_SPQ_MODE_EBLOCK; rc = qed_sp_init_request(p_hwfn, &p_ent, @@ -168,9 +181,9 @@ static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, p_ramrod = &p_ent->ramrod.vport_start; p_ramrod->vport_id = abs_vport_id; - p_ramrod->mtu = cpu_to_le16(mtu); - p_ramrod->inner_vlan_removal_en = inner_vlan_removal_en_flg; - p_ramrod->drop_ttl0_en = drop_ttl0_flg; + p_ramrod->mtu = cpu_to_le16(p_params->mtu); + p_ramrod->inner_vlan_removal_en = p_params->remove_inner_vlan; + p_ramrod->drop_ttl0_en = p_params->drop_ttl0; SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_UCAST_DROP_ALL, 1); SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_MCAST_DROP_ALL, 1); @@ -181,9 +194,26 @@ static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, memset(&p_ramrod->tpa_param, 0, sizeof(struct eth_vport_tpa_param)); + p_ramrod->tpa_param.max_buff_num = p_params->max_buffers_per_cqe; + + switch (p_params->tpa_mode) { + case QED_TPA_MODE_GRO: + p_ramrod->tpa_param.tpa_max_aggs_num = ETH_TPA_MAX_AGGS_NUM; + p_ramrod->tpa_param.tpa_max_size = (u16)-1; + p_ramrod->tpa_param.tpa_min_size_to_cont = p_params->mtu / 2; + p_ramrod->tpa_param.tpa_min_size_to_start = p_params->mtu / 2; + p_ramrod->tpa_param.tpa_ipv4_en_flg = 1; + p_ramrod->tpa_param.tpa_ipv6_en_flg = 1; + p_ramrod->tpa_param.tpa_pkt_split_flg = 1; + p_ramrod->tpa_param.tpa_gro_consistent_flg = 1; + break; + default: + break; + } + /* Software Function ID in hwfn (PFs are 0 - 15, VFs are 16 - 135) */ p_ramrod->sw_fid = qed_concrete_to_sw_fid(p_hwfn->cdev, - concrete_fid); + p_params->concrete_fid); return qed_spq_post(p_hwfn, p_ent, NULL); } @@ -1592,24 +1622,25 @@ static void qed_register_eth_ops(struct qed_dev *cdev, } static int qed_start_vport(struct qed_dev *cdev, - u8 vport_id, - u16 mtu, - u8 drop_ttl0_flg, - u8 inner_vlan_removal_en_flg) + struct qed_start_vport_params *params) { int rc, i; for_each_hwfn(cdev, i) { + struct qed_sp_vport_start_params start = { 0 }; struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; - rc = qed_sp_vport_start(p_hwfn, - p_hwfn->hw_info.concrete_fid, - p_hwfn->hw_info.opaque_fid, - vport_id, - mtu, - drop_ttl0_flg, - inner_vlan_removal_en_flg); - + start.tpa_mode = params->gro_enable ? QED_TPA_MODE_GRO : + QED_TPA_MODE_NONE; + start.remove_inner_vlan = params->remove_inner_vlan; + start.drop_ttl0 = params->drop_ttl0; + start.opaque_fid = p_hwfn->hw_info.opaque_fid; + start.concrete_fid = p_hwfn->hw_info.concrete_fid; + start.vport_id = params->vport_id; + start.max_buffers_per_cqe = 16; + start.mtu = params->mtu; + + rc = qed_sp_vport_start(p_hwfn, &start); if (rc) { DP_ERR(cdev, "Failed to start VPORT\n"); return rc; @@ -1619,7 +1650,7 @@ static int qed_start_vport(struct qed_dev *cdev, DP_VERBOSE(cdev, (QED_MSG_SPQ | NETIF_MSG_IFUP), "Started V-PORT %d with MTU %d\n", - vport_id, mtu); + start.vport_id, start.mtu); } qed_reset_vport_stats(cdev); diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index ddd9e4aaa500..f75f334af7bd 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -2466,11 +2466,12 @@ static int qede_stop_queues(struct qede_dev *edev) static int qede_start_queues(struct qede_dev *edev) { int rc, tc, i; - int vport_id = 0, drop_ttl0_flg = 1, vlan_removal_en = 1; + int vlan_removal_en = 1; struct qed_dev *cdev = edev->cdev; struct qed_update_vport_rss_params *rss_params = &edev->rss_params; struct qed_update_vport_params vport_update_params; struct qed_queue_start_common_params q_params; + struct qed_start_vport_params start = {0}; if (!edev->num_rss) { DP_ERR(edev, @@ -2478,10 +2479,12 @@ static int qede_start_queues(struct qede_dev *edev) return -EINVAL; } - rc = edev->ops->vport_start(cdev, vport_id, - edev->ndev->mtu, - drop_ttl0_flg, - vlan_removal_en); + start.mtu = edev->ndev->mtu; + start.vport_id = 0; + start.drop_ttl0 = true; + start.remove_inner_vlan = vlan_removal_en; + + rc = edev->ops->vport_start(cdev, &start); if (rc) { DP_ERR(edev, "Start V-PORT failed %d\n", rc); @@ -2490,7 +2493,7 @@ static int qede_start_queues(struct qede_dev *edev) DP_VERBOSE(edev, NETIF_MSG_IFUP, "Start vport ramrod passed, vport_id = %d, MTU = %d, vlan_removal_en = %d\n", - vport_id, edev->ndev->mtu + 0xe, vlan_removal_en); + start.vport_id, edev->ndev->mtu + 0xe, vlan_removal_en); for_each_rss(i) { struct qede_fastpath *fp = &edev->fp_array[i]; @@ -2555,7 +2558,7 @@ static int qede_start_queues(struct qede_dev *edev) /* Prepare and send the vport enable */ memset(&vport_update_params, 0, sizeof(vport_update_params)); - vport_update_params.vport_id = vport_id; + vport_update_params.vport_id = start.vport_id; vport_update_params.update_vport_active_flg = 1; vport_update_params.vport_active_flg = 1; diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index e53b0ca49e41..e1d69834a11f 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -39,6 +39,14 @@ struct qed_update_vport_params { struct qed_update_vport_rss_params rss_params; }; +struct qed_start_vport_params { + bool remove_inner_vlan; + bool gro_enable; + bool drop_ttl0; + u8 vport_id; + u16 mtu; +}; + struct qed_stop_rxq_params { u8 rss_id; u8 rx_queue_id; @@ -118,9 +126,7 @@ struct qed_eth_ops { void *cookie); int (*vport_start)(struct qed_dev *cdev, - u8 vport_id, u16 mtu, - u8 drop_ttl0_flg, - u8 inner_vlan_removal_en_flg); + struct qed_start_vport_params *params); int (*vport_stop)(struct qed_dev *cdev, u8 vport_id); -- cgit v1.2.3 From b121d1e74d1f24654bdc3165d3db1ca149501356 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:13 -0800 Subject: bpf: prevent kprobe+bpf deadlocks if kprobe is placed within update or delete hash map helpers that hold bucket spin lock and triggered bpf program is trying to grab the spinlock for the same bucket on the same cpu, it will deadlock. Fix it by extending existing recursion prevention mechanism. Note, map_lookup and other tracing helpers don't have this problem, since they don't hold any locks and don't modify global data. bpf_trace_printk has its own recursive check and ok as well. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ kernel/bpf/syscall.c | 13 +++++++++++++ kernel/trace/bpf_trace.c | 2 -- 3 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 51e498e5470e..4b070827200d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,6 +10,7 @@ #include #include #include +#include struct bpf_map; @@ -163,6 +164,8 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f const struct bpf_func_proto *bpf_get_trace_printk_proto(void); #ifdef CONFIG_BPF_SYSCALL +DECLARE_PER_CPU(int, bpf_prog_active); + void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c95a753c2007..dc99f6a000f5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -18,6 +18,8 @@ #include #include +DEFINE_PER_CPU(int, bpf_prog_active); + int sysctl_unprivileged_bpf_disabled __read_mostly; static LIST_HEAD(bpf_map_types); @@ -347,6 +349,11 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from + * inside bpf map update or delete otherwise deadlocks are possible + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { @@ -356,6 +363,8 @@ static int map_update_elem(union bpf_attr *attr) err = map->ops->map_update_elem(map, key, value, attr->flags); rcu_read_unlock(); } + __this_cpu_dec(bpf_prog_active); + preempt_enable(); free_value: kfree(value); @@ -394,9 +403,13 @@ static int map_delete_elem(union bpf_attr *attr) if (copy_from_user(key, ukey, map->key_size) != 0) goto free_key; + preempt_disable(); + __this_cpu_inc(bpf_prog_active); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); free_key: kfree(key); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4b8caa392b86..3e4ffb3ace5f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -13,8 +13,6 @@ #include #include "trace.h" -static DEFINE_PER_CPU(int, bpf_prog_active); - /** * trace_call_bpf - invoke BPF program * @prog: BPF program -- cgit v1.2.3 From 6c90598174322b8888029e40dd84a4eb01f56afe Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:15 -0800 Subject: bpf: pre-allocate hash map elements If kprobe is placed on spin_unlock then calling kmalloc/kfree from bpf programs is not safe, since the following dead lock is possible: kfree->spin_lock(kmem_cache_node->lock)...spin_unlock->kprobe-> bpf_prog->map_update->kmalloc->spin_lock(of the same kmem_cache_node->lock) and deadlocks. The following solutions were considered and some implemented, but eventually discarded - kmem_cache_create for every map - add recursion check to slow-path of slub - use reserved memory in bpf_map_update for in_irq or in preempt_disabled - kmalloc via irq_work At the end pre-allocation of all map elements turned out to be the simplest solution and since the user is charged upfront for all the memory, such pre-allocation doesn't affect the user space visible behavior. Since it's impossible to tell whether kprobe is triggered in a safe location from kmalloc point of view, use pre-allocation by default and introduce new BPF_F_NO_PREALLOC flag. While testing of per-cpu hash maps it was discovered that alloc_percpu(GFP_ATOMIC) has odd corner cases and often fails to allocate memory even when 90% of it is free. The pre-allocation of per-cpu hash elements solves this problem as well. Turned out that bpf_map_update() quickly followed by bpf_map_lookup()+bpf_map_delete() is very common pattern used in many of iovisor/bcc/tools, so there is additional benefit of pre-allocation, since such use cases are must faster. Since all hash map elements are now pre-allocated we can remove atomic increment of htab->count and save few more cycles. Also add bpf_map_precharge_memlock() to check rlimit_memlock early to avoid large malloc/free done by users who don't have sufficient limits. Pre-allocation is done with vmalloc and alloc/free is done via percpu_freelist. Here are performance numbers for different pre-allocation algorithms that were implemented, but discarded in favor of percpu_freelist: 1 cpu: pcpu_ida 2.1M pcpu_ida nolock 2.3M bt 2.4M kmalloc 1.8M hlist+spinlock 2.3M pcpu_freelist 2.6M 4 cpu: pcpu_ida 1.5M pcpu_ida nolock 1.8M bt w/smp_align 1.7M bt no/smp_align 1.1M kmalloc 0.7M hlist+spinlock 0.2M pcpu_freelist 2.0M 8 cpu: pcpu_ida 0.7M bt w/smp_align 0.8M kmalloc 0.4M pcpu_freelist 1.5M 32 cpu: kmalloc 0.13M pcpu_freelist 0.49M pcpu_ida nolock is a modified percpu_ida algorithm without percpu_ida_cpu locks and without cross-cpu tag stealing. It's faster than existing percpu_ida, but not as fast as pcpu_freelist. bt is a variant of block/blk-mq-tag.c simlified and customized for bpf use case. bt w/smp_align is using cache line for every 'long' (similar to blk-mq-tag). bt no/smp_align allocates 'long' bitmasks continuously to save memory. It's comparable to percpu_ida and in some cases faster, but slower than percpu_freelist hlist+spinlock is the simplest free list with single spinlock. As expeceted it has very bad scaling in SMP. kmalloc is existing implementation which is still available via BPF_F_NO_PREALLOC flag. It's significantly slower in single cpu and in 8 cpu setup it's 3 times slower than pre-allocation with pcpu_freelist, but saves memory, so in cases where map->max_entries can be large and number of map update/delete per second is low, it may make sense to use it. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 3 + kernel/bpf/hashtab.c | 240 +++++++++++++++++++++++++++++++++-------------- kernel/bpf/syscall.c | 15 ++- 4 files changed, 186 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4b070827200d..efd1d4ca95c6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,7 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; + u32 map_flags; u32 pages; struct user_struct *user; const struct bpf_map_ops *ops; @@ -178,6 +179,7 @@ struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); +int bpf_map_precharge_memlock(u32 pages); extern int sysctl_unprivileged_bpf_disabled; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9221f653fee3..0e30b19012a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -101,12 +101,15 @@ enum bpf_prog_type { #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +#define BPF_F_NO_PREALLOC (1U << 0) + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ __u32 key_size; /* size of key in bytes */ __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* prealloc or not */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index a68e95133fcd..fff3650d52fc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1,4 +1,5 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -13,6 +14,7 @@ #include #include #include +#include "percpu_freelist.h" struct bucket { struct hlist_head head; @@ -22,6 +24,8 @@ struct bucket { struct bpf_htab { struct bpf_map map; struct bucket *buckets; + void *elems; + struct pcpu_freelist freelist; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ @@ -29,15 +33,86 @@ struct bpf_htab { /* each htab element is struct htab_elem + key + value */ struct htab_elem { - struct hlist_node hash_node; - struct rcu_head rcu; union { - u32 hash; - u32 key_size; + struct hlist_node hash_node; + struct bpf_htab *htab; + struct pcpu_freelist_node fnode; }; + struct rcu_head rcu; + u32 hash; char key[0] __aligned(8); }; +static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, + void __percpu *pptr) +{ + *(void __percpu **)(l->key + key_size) = pptr; +} + +static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) +{ + return *(void __percpu **)(l->key + key_size); +} + +static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) +{ + return (struct htab_elem *) (htab->elems + i * htab->elem_size); +} + +static void htab_free_elems(struct bpf_htab *htab) +{ + int i; + + if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + goto free_elems; + + for (i = 0; i < htab->map.max_entries; i++) { + void __percpu *pptr; + + pptr = htab_elem_get_ptr(get_htab_elem(htab, i), + htab->map.key_size); + free_percpu(pptr); + } +free_elems: + vfree(htab->elems); +} + +static int prealloc_elems_and_freelist(struct bpf_htab *htab) +{ + int err = -ENOMEM, i; + + htab->elems = vzalloc(htab->elem_size * htab->map.max_entries); + if (!htab->elems) + return -ENOMEM; + + if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + goto skip_percpu_elems; + + for (i = 0; i < htab->map.max_entries; i++) { + u32 size = round_up(htab->map.value_size, 8); + void __percpu *pptr; + + pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN); + if (!pptr) + goto free_elems; + htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, + pptr); + } + +skip_percpu_elems: + err = pcpu_freelist_init(&htab->freelist); + if (err) + goto free_elems; + + pcpu_freelist_populate(&htab->freelist, htab->elems, htab->elem_size, + htab->map.max_entries); + return 0; + +free_elems: + htab_free_elems(htab); + return err; +} + /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { @@ -46,6 +121,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) int err, i; u64 cost; + if (attr->map_flags & ~BPF_F_NO_PREALLOC) + /* reserved bits should not be used */ + return ERR_PTR(-EINVAL); + htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); @@ -55,6 +134,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.key_size = attr->key_size; htab->map.value_size = attr->value_size; htab->map.max_entries = attr->max_entries; + htab->map.map_flags = attr->map_flags; /* check sanity of attributes. * value_size == 0 may be allowed in the future to use map as a set @@ -92,7 +172,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (percpu) htab->elem_size += sizeof(void *); else - htab->elem_size += htab->map.value_size; + htab->elem_size += round_up(htab->map.value_size, 8); /* prevent zero size kmalloc and check for u32 overflow */ if (htab->n_buckets == 0 || @@ -112,6 +192,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(htab->map.pages); + if (err) + goto free_htab; + err = -ENOMEM; htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), GFP_USER | __GFP_NOWARN); @@ -127,10 +212,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } - atomic_set(&htab->count, 0); + if (!(attr->map_flags & BPF_F_NO_PREALLOC)) { + err = prealloc_elems_and_freelist(htab); + if (err) + goto free_buckets; + } return &htab->map; +free_buckets: + kvfree(htab->buckets); free_htab: kfree(htab); return ERR_PTR(err); @@ -249,42 +340,42 @@ find_first_elem: } } - /* itereated over all buckets and all elements */ + /* iterated over all buckets and all elements */ return -ENOENT; } - -static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, - void __percpu *pptr) -{ - *(void __percpu **)(l->key + key_size) = pptr; -} - -static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) -{ - return *(void __percpu **)(l->key + key_size); -} - -static void htab_percpu_elem_free(struct htab_elem *l) +static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { - free_percpu(htab_elem_get_ptr(l, l->key_size)); + if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) + free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); kfree(l); + } -static void htab_percpu_elem_free_rcu(struct rcu_head *head) +static void htab_elem_free_rcu(struct rcu_head *head) { struct htab_elem *l = container_of(head, struct htab_elem, rcu); + struct bpf_htab *htab = l->htab; - htab_percpu_elem_free(l); + /* must increment bpf_prog_active to avoid kprobe+bpf triggering while + * we're calling kfree, otherwise deadlock is possible if kprobes + * are placed somewhere inside of slub + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + htab_elem_free(htab, l); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); } -static void free_htab_elem(struct htab_elem *l, bool percpu, u32 key_size) +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { - if (percpu) { - l->key_size = key_size; - call_rcu(&l->rcu, htab_percpu_elem_free_rcu); + if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { + pcpu_freelist_push(&htab->freelist, &l->fnode); } else { - kfree_rcu(l, rcu); + atomic_dec(&htab->count); + l->htab = htab; + call_rcu(&l->rcu, htab_elem_free_rcu); } } @@ -293,23 +384,39 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, bool percpu, bool onallcpus) { u32 size = htab->map.value_size; + bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); struct htab_elem *l_new; void __percpu *pptr; - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return NULL; + if (prealloc) { + l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); + if (!l_new) + return ERR_PTR(-E2BIG); + } else { + if (atomic_inc_return(&htab->count) > htab->map.max_entries) { + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); + } memcpy(l_new->key, key, key_size); if (percpu) { /* round up value_size to 8 bytes */ size = round_up(size, 8); - /* alloc_percpu zero-fills */ - pptr = __alloc_percpu_gfp(size, 8, GFP_ATOMIC | __GFP_NOWARN); - if (!pptr) { - kfree(l_new); - return NULL; + if (prealloc) { + pptr = htab_elem_get_ptr(l_new, key_size); + } else { + /* alloc_percpu zero-fills */ + pptr = __alloc_percpu_gfp(size, 8, + GFP_ATOMIC | __GFP_NOWARN); + if (!pptr) { + kfree(l_new); + return ERR_PTR(-ENOMEM); + } } if (!onallcpus) { @@ -324,7 +431,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, off += size; } } - htab_elem_set_ptr(l_new, key_size, pptr); + if (!prealloc) + htab_elem_set_ptr(l_new, key_size, pptr); } else { memcpy(l_new->key + round_up(key_size, 8), value, size); } @@ -336,12 +444,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, u64 map_flags) { - if (!l_old && unlikely(atomic_read(&htab->count) >= htab->map.max_entries)) - /* if elem with this 'key' doesn't exist and we've reached - * max_entries limit, fail insertion of new elem - */ - return -E2BIG; - if (l_old && map_flags == BPF_NOEXIST) /* elem already exists */ return -EEXIST; @@ -375,13 +477,6 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hash = htab_map_hash(key, key_size); - /* allocate new element outside of the lock, since - * we're most likley going to insert it - */ - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); - if (!l_new) - return -ENOMEM; - b = __select_bucket(htab, hash); head = &b->head; @@ -394,21 +489,24 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); + if (IS_ERR(l_new)) { + /* all pre-allocated elements are in use or memory exhausted */ + ret = PTR_ERR(l_new); + goto err; + } + /* add new element to the head of the list, so that * concurrent search will find it before old elem */ hlist_add_head_rcu(&l_new->hash_node, head); if (l_old) { hlist_del_rcu(&l_old->hash_node); - kfree_rcu(l_old, rcu); - } else { - atomic_inc(&htab->count); + free_htab_elem(htab, l_old); } - raw_spin_unlock_irqrestore(&b->lock, flags); - return 0; + ret = 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); - kfree(l_new); return ret; } @@ -466,12 +564,11 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } else { l_new = alloc_htab_elem(htab, key, value, key_size, hash, true, onallcpus); - if (!l_new) { - ret = -ENOMEM; + if (IS_ERR(l_new)) { + ret = PTR_ERR(l_new); goto err; } hlist_add_head_rcu(&l_new->hash_node, head); - atomic_inc(&htab->count); } ret = 0; err: @@ -489,7 +586,6 @@ static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_HASH; struct hlist_head *head; struct bucket *b; struct htab_elem *l; @@ -511,8 +607,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) if (l) { hlist_del_rcu(&l->hash_node); - atomic_dec(&htab->count); - free_htab_elem(l, percpu, key_size); + free_htab_elem(htab, l); ret = 0; } @@ -531,17 +626,10 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_for_each_entry_safe(l, n, head, hash_node) { hlist_del_rcu(&l->hash_node); - atomic_dec(&htab->count); - if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) { - l->key_size = htab->map.key_size; - htab_percpu_elem_free(l); - } else { - kfree(l); - } + htab_elem_free(htab, l); } } } - /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void htab_map_free(struct bpf_map *map) { @@ -554,10 +642,16 @@ static void htab_map_free(struct bpf_map *map) */ synchronize_rcu(); - /* some of kfree_rcu() callbacks for elements of this map may not have - * executed. It's ok. Proceed to free residual elements and map itself + /* some of free_htab_elem() callbacks for elements of this map may + * not have executed. Wait for them. */ - delete_all_elements(htab); + rcu_barrier(); + if (htab->map.map_flags & BPF_F_NO_PREALLOC) { + delete_all_elements(htab); + } else { + htab_free_elems(htab); + pcpu_freelist_destroy(&htab->freelist); + } kvfree(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index dc99f6a000f5..cbd94b2144ff 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -48,6 +48,19 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +int bpf_map_precharge_memlock(u32 pages) +{ + struct user_struct *user = get_current_user(); + unsigned long memlock_limit, cur; + + memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + cur = atomic_long_read(&user->locked_vm); + free_uid(user); + if (cur + pages > memlock_limit) + return -EPERM; + return 0; +} + static int bpf_map_charge_memlock(struct bpf_map *map) { struct user_struct *user = get_current_user(); @@ -153,7 +166,7 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL -#define BPF_MAP_CREATE_LAST_FIELD max_entries +#define BPF_MAP_CREATE_LAST_FIELD map_flags /* called via syscall */ static int map_create(union bpf_attr *attr) { -- cgit v1.2.3 From 557c0c6e7df8e14a46bd7560d193fa5bbc00a858 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Mar 2016 21:57:17 -0800 Subject: bpf: convert stackmap to pre-allocation It was observed that calling bpf_get_stackid() from a kprobe inside slub or from spin_unlock causes similar deadlock as with hashmap, therefore convert stackmap to use pre-allocated memory. The call_rcu is no longer feasible mechanism, since delayed freeing causes bpf_get_stackid() to fail unpredictably when number of actual stacks is significantly less than user requested max_entries. Since elements are no longer freed into slub, we can push elements into freelist immediately and let them be recycled. However the very unlikley race between user space map_lookup() and program-side recycling is possible: cpu0 cpu1 ---- ---- user does lookup(stackidX) starts copying ips into buffer delete(stackidX) calls bpf_get_stackid() which recyles the element and overwrites with new stack trace To avoid user space seeing a partial stack trace consisting of two merged stack traces, do bucket = xchg(, NULL); copy; xchg(,bucket); to preserve consistent stack trace delivery to user space. Now we can move memset(,0) of left-over element value from critical path of bpf_get_stackid() into slow-path of user space lookup. Also disallow lookup() from bpf program, since it's useless and program shouldn't be messing with collected stack trace. Note that similar race between user space lookup and kernel side updates is also present in hashmap, but it's not a new race. bpf programs were always allowed to modify hash and array map elements while user space is copying them. Fixes: d5a3b1f69186 ("bpf: introduce BPF_MAP_TYPE_STACK_TRACE") Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + kernel/bpf/stackmap.c | 86 ++++++++++++++++++++++++++++++++++++++++----------- kernel/bpf/syscall.c | 2 ++ 3 files changed, 71 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index efd1d4ca95c6..21ee41b92e8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -195,6 +195,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); +int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index f0a02c344358..499d9e933f8e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -10,9 +10,10 @@ #include #include #include +#include "percpu_freelist.h" struct stack_map_bucket { - struct rcu_head rcu; + struct pcpu_freelist_node fnode; u32 hash; u32 nr; u64 ip[]; @@ -20,10 +21,34 @@ struct stack_map_bucket { struct bpf_stack_map { struct bpf_map map; + void *elems; + struct pcpu_freelist freelist; u32 n_buckets; - struct stack_map_bucket __rcu *buckets[]; + struct stack_map_bucket *buckets[]; }; +static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) +{ + u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + int err; + + smap->elems = vzalloc(elem_size * smap->map.max_entries); + if (!smap->elems) + return -ENOMEM; + + err = pcpu_freelist_init(&smap->freelist); + if (err) + goto free_elems; + + pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size, + smap->map.max_entries); + return 0; + +free_elems: + vfree(smap->elems); + return err; +} + /* Called from syscall */ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { @@ -70,12 +95,22 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) smap->n_buckets = n_buckets; smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + err = bpf_map_precharge_memlock(smap->map.pages); + if (err) + goto free_smap; + err = get_callchain_buffers(); if (err) goto free_smap; + err = prealloc_elems_and_freelist(smap); + if (err) + goto put_buffers; + return &smap->map; +put_buffers: + put_callchain_buffers(); free_smap: kvfree(smap); return ERR_PTR(err); @@ -121,7 +156,7 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) ips = trace->ip + skip + init_nr; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); - bucket = rcu_dereference(smap->buckets[id]); + bucket = READ_ONCE(smap->buckets[id]); if (bucket && bucket->hash == hash) { if (flags & BPF_F_FAST_STACK_CMP) @@ -135,19 +170,18 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) if (bucket && !(flags & BPF_F_REUSE_STACKID)) return -EEXIST; - new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size, - GFP_ATOMIC | __GFP_NOWARN); + new_bucket = (struct stack_map_bucket *) + pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; memcpy(new_bucket->ip, ips, trace_len); - memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len); new_bucket->hash = hash; new_bucket->nr = trace_nr; old_bucket = xchg(&smap->buckets[id], new_bucket); if (old_bucket) - kfree_rcu(old_bucket, rcu); + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return id; } @@ -160,17 +194,34 @@ const struct bpf_func_proto bpf_get_stackid_proto = { .arg3_type = ARG_ANYTHING, }; -/* Called from syscall or from eBPF program */ +/* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +/* Called from syscall */ +int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - struct stack_map_bucket *bucket; - u32 id = *(u32 *)key; + struct stack_map_bucket *bucket, *old_bucket; + u32 id = *(u32 *)key, trace_len; if (unlikely(id >= smap->n_buckets)) - return NULL; - bucket = rcu_dereference(smap->buckets[id]); - return bucket ? bucket->ip : NULL; + return -ENOENT; + + bucket = xchg(&smap->buckets[id], NULL); + if (!bucket) + return -ENOENT; + + trace_len = bucket->nr * sizeof(u64); + memcpy(value, bucket->ip, trace_len); + memset(value + trace_len, 0, map->value_size - trace_len); + + old_bucket = xchg(&smap->buckets[id], bucket); + if (old_bucket) + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); + return 0; } static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -196,7 +247,7 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key) old_bucket = xchg(&smap->buckets[id], NULL); if (old_bucket) { - kfree_rcu(old_bucket, rcu); + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return 0; } else { return -ENOENT; @@ -207,13 +258,12 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key) static void stack_map_free(struct bpf_map *map) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - int i; + /* wait for bpf programs to complete before freeing stack map */ synchronize_rcu(); - for (i = 0; i < smap->n_buckets; i++) - if (smap->buckets[i]) - kfree_rcu(smap->buckets[i], rcu); + vfree(smap->elems); + pcpu_freelist_destroy(&smap->freelist); kvfree(smap); put_callchain_buffers(); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cbd94b2144ff..2978d0d08869 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -290,6 +290,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { + err = bpf_stackmap_copy(map, key, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); -- cgit v1.2.3 From ff3c44e675054533403909ecb76e78c1d4efbd26 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:00 -0800 Subject: rcu: Add list_next_or_null_rcu This is a convenience function that returns the next entry in an RCU list or NULL if at the end of the list. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/rculist.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 14ec1652daf4..17d4f849c65e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -318,6 +318,27 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) +/** + * list_next_or_null_rcu - get the first element from a list + * @head: the head for the list. + * @ptr: the list head to take the next element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the ptr is at the end of the list, NULL is returned. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). + */ +#define list_next_or_null_rcu(head, ptr, type, member) \ +({ \ + struct list_head *__head = (head); \ + struct list_head *__ptr = (ptr); \ + struct list_head *__next = READ_ONCE(__ptr->next); \ + likely(__next != __head) ? list_entry_rcu(__next, type, \ + member) : NULL; \ +}) + /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. -- cgit v1.2.3 From f4a00aacdb5f6784d46e8c999b6bb52ece4b306b Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:01 -0800 Subject: net: Make sock_alloc exportable Export it for cases where we want to create sockets by hand. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/net.h | 1 + net/socket.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 0b4ac7da583a..49175e4ced11 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -215,6 +215,7 @@ int __sock_create(struct net *net, int family, int type, int proto, int sock_create(int family, int type, int proto, struct socket **res); int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); +struct socket *sock_alloc(void); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/net/socket.c b/net/socket.c index c044d1e8508c..38a78d4d50f5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -533,7 +533,7 @@ static const struct inode_operations sockfs_inode_ops = { * NULL is returned. */ -static struct socket *sock_alloc(void) +struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; @@ -554,6 +554,7 @@ static struct socket *sock_alloc(void) this_cpu_add(sockets_in_use, 1); return sock; } +EXPORT_SYMBOL(sock_alloc); /** * sock_release - close a socket -- cgit v1.2.3 From f092276d85b82504e8a07498f4e9e0c51f06745c Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:03 -0800 Subject: net: Add MSG_BATCH flag Add a new msg flag called MSG_BATCH. This flag is used in sendmsg to indicate that more messages will follow (i.e. a batch of messages is being sent). This is similar to MSG_MORE except that the following messages are not merged into one packet, they are sent individually. sendmmsg is updated so that each contained message except for the last one is marked as MSG_BATCH. MSG_BATCH is a performance optimization in cases where a socket implementation can benefit by transmitting packets in a batch. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + net/socket.c | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 5bf59c8493b7..d834af22a460 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -274,6 +274,7 @@ struct ucred { #define MSG_MORE 0x8000 /* Sender will send more */ #define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ +#define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/net/socket.c b/net/socket.c index 0dd4dd818f41..886649c88d8f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2008,6 +2008,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct used_address used_address; + unsigned int oflags = flags; if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; @@ -2022,8 +2023,12 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; err = 0; + flags |= MSG_BATCH; while (datagrams < vlen) { + if (datagrams == vlen - 1) + flags = oflags; + if (MSG_CMSG_COMPAT & flags) { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags, &used_address, MSG_EOR); -- cgit v1.2.3 From ab7ac4eb9832e32a09f4e8042705484d2fb0aad3 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Mar 2016 14:11:06 -0800 Subject: kcm: Kernel Connection Multiplexor module This module implements the Kernel Connection Multiplexor. Kernel Connection Multiplexor (KCM) is a facility that provides a message based interface over TCP for generic application protocols. With KCM an application can efficiently send and receive application protocol messages over TCP using datagram sockets. For more information see the included Documentation/networking/kcm.txt Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/socket.h | 6 +- include/net/kcm.h | 125 +++ include/uapi/linux/kcm.h | 40 + net/Kconfig | 1 + net/Makefile | 1 + net/kcm/Kconfig | 10 + net/kcm/Makefile | 3 + net/kcm/kcmsock.c | 2016 ++++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 2201 insertions(+), 1 deletion(-) create mode 100644 include/net/kcm.h create mode 100644 include/uapi/linux/kcm.h create mode 100644 net/kcm/Kconfig create mode 100644 net/kcm/Makefile create mode 100644 net/kcm/kcmsock.c (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index d834af22a460..73bf6c6a833b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -200,7 +200,9 @@ struct ucred { #define AF_ALG 38 /* Algorithm sockets */ #define AF_NFC 39 /* NFC sockets */ #define AF_VSOCK 40 /* vSockets */ -#define AF_MAX 41 /* For now.. */ +#define AF_KCM 41 /* Kernel Connection Multiplexor*/ + +#define AF_MAX 42 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -246,6 +248,7 @@ struct ucred { #define PF_ALG AF_ALG #define PF_NFC AF_NFC #define PF_VSOCK AF_VSOCK +#define PF_KCM AF_KCM #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -323,6 +326,7 @@ struct ucred { #define SOL_CAIF 278 #define SOL_ALG 279 #define SOL_NFC 280 +#define SOL_KCM 281 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/kcm.h b/include/net/kcm.h new file mode 100644 index 000000000000..1bcae39070ec --- /dev/null +++ b/include/net/kcm.h @@ -0,0 +1,125 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#ifndef __NET_KCM_H_ +#define __NET_KCM_H_ + +#include +#include +#include + +extern unsigned int kcm_net_id; + +struct kcm_tx_msg { + unsigned int sent; + unsigned int fragidx; + unsigned int frag_offset; + unsigned int msg_flags; + struct sk_buff *frag_skb; + struct sk_buff *last_skb; +}; + +struct kcm_rx_msg { + int full_len; + int accum_len; + int offset; +}; + +/* Socket structure for KCM client sockets */ +struct kcm_sock { + struct sock sk; + struct kcm_mux *mux; + struct list_head kcm_sock_list; + int index; + u32 done : 1; + struct work_struct done_work; + + /* Transmit */ + struct kcm_psock *tx_psock; + struct work_struct tx_work; + struct list_head wait_psock_list; + struct sk_buff *seq_skb; + + /* Don't use bit fields here, these are set under different locks */ + bool tx_wait; + bool tx_wait_more; + + /* Receive */ + struct kcm_psock *rx_psock; + struct list_head wait_rx_list; /* KCMs waiting for receiving */ + bool rx_wait; + u32 rx_disabled : 1; +}; + +struct bpf_prog; + +/* Structure for an attached lower socket */ +struct kcm_psock { + struct sock *sk; + struct kcm_mux *mux; + int index; + + u32 tx_stopped : 1; + u32 rx_stopped : 1; + u32 done : 1; + u32 unattaching : 1; + + void (*save_state_change)(struct sock *sk); + void (*save_data_ready)(struct sock *sk); + void (*save_write_space)(struct sock *sk); + + struct list_head psock_list; + + /* Receive */ + struct sk_buff *rx_skb_head; + struct sk_buff **rx_skb_nextp; + struct sk_buff *ready_rx_msg; + struct list_head psock_ready_list; + struct work_struct rx_work; + struct delayed_work rx_delayed_work; + struct bpf_prog *bpf_prog; + struct kcm_sock *rx_kcm; + + /* Transmit */ + struct kcm_sock *tx_kcm; + struct list_head psock_avail_list; +}; + +/* Per net MUX list */ +struct kcm_net { + struct mutex mutex; + struct list_head mux_list; + int count; +}; + +/* Structure for a MUX */ +struct kcm_mux { + struct list_head kcm_mux_list; + struct rcu_head rcu; + struct kcm_net *knet; + + struct list_head kcm_socks; /* All KCM sockets on MUX */ + int kcm_socks_cnt; /* Total KCM socket count for MUX */ + struct list_head psocks; /* List of all psocks on MUX */ + int psocks_cnt; /* Total attached sockets */ + + /* Receive */ + spinlock_t rx_lock ____cacheline_aligned_in_smp; + struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */ + struct list_head psocks_ready; /* List of psocks with a msg ready */ + struct sk_buff_head rx_hold_queue; + + /* Transmit */ + spinlock_t lock ____cacheline_aligned_in_smp; /* TX and mux locking */ + struct list_head psocks_avail; /* List of available psocks */ + struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */ +}; + +#endif /* __NET_KCM_H_ */ diff --git a/include/uapi/linux/kcm.h b/include/uapi/linux/kcm.h new file mode 100644 index 000000000000..a5a530940b99 --- /dev/null +++ b/include/uapi/linux/kcm.h @@ -0,0 +1,40 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * User API to clone KCM sockets and attach transport socket to a KCM + * multiplexor. + */ + +#ifndef KCM_KERNEL_H +#define KCM_KERNEL_H + +struct kcm_attach { + int fd; + int bpf_fd; +}; + +struct kcm_unattach { + int fd; +}; + +struct kcm_clone { + int fd; +}; + +#define SIOCKCMATTACH (SIOCPROTOPRIVATE + 0) +#define SIOCKCMUNATTACH (SIOCPROTOPRIVATE + 1) +#define SIOCKCMCLONE (SIOCPROTOPRIVATE + 2) + +#define KCMPROTO_CONNECTED 0 + +/* Socket options */ +#define KCM_RECV_DISABLE 1 + +#endif + diff --git a/net/Kconfig b/net/Kconfig index 2760825e53fa..10640d5f8bee 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -360,6 +360,7 @@ source "net/can/Kconfig" source "net/irda/Kconfig" source "net/bluetooth/Kconfig" source "net/rxrpc/Kconfig" +source "net/kcm/Kconfig" config FIB_RULES bool diff --git a/net/Makefile b/net/Makefile index a5d04098dfce..81d14119eab5 100644 --- a/net/Makefile +++ b/net/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_IRDA) += irda/ obj-$(CONFIG_BT) += bluetooth/ obj-$(CONFIG_SUNRPC) += sunrpc/ obj-$(CONFIG_AF_RXRPC) += rxrpc/ +obj-$(CONFIG_AF_KCM) += kcm/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_L2TP) += l2tp/ obj-$(CONFIG_DECNET) += decnet/ diff --git a/net/kcm/Kconfig b/net/kcm/Kconfig new file mode 100644 index 000000000000..5db94d940ecc --- /dev/null +++ b/net/kcm/Kconfig @@ -0,0 +1,10 @@ + +config AF_KCM + tristate "KCM sockets" + depends on INET + select BPF_SYSCALL + ---help--- + KCM (Kernel Connection Multiplexor) sockets provide a method + for multiplexing messages of a message based application + protocol over kernel connectons (e.g. TCP connections). + diff --git a/net/kcm/Makefile b/net/kcm/Makefile new file mode 100644 index 000000000000..cb525f7c5a13 --- /dev/null +++ b/net/kcm/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_AF_KCM) += kcm.o + +kcm-y := kcmsock.o diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c new file mode 100644 index 000000000000..30ef69ac6b81 --- /dev/null +++ b/net/kcm/kcmsock.c @@ -0,0 +1,2016 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +unsigned int kcm_net_id; + +static struct kmem_cache *kcm_psockp __read_mostly; +static struct kmem_cache *kcm_muxp __read_mostly; +static struct workqueue_struct *kcm_wq; + +static inline struct kcm_sock *kcm_sk(const struct sock *sk) +{ + return (struct kcm_sock *)sk; +} + +static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) +{ + return (struct kcm_tx_msg *)skb->cb; +} + +static inline struct kcm_rx_msg *kcm_rx_msg(struct sk_buff *skb) +{ + return (struct kcm_rx_msg *)((void *)skb->cb + + offsetof(struct qdisc_skb_cb, data)); +} + +static void report_csk_error(struct sock *csk, int err) +{ + csk->sk_err = EPIPE; + csk->sk_error_report(csk); +} + +/* Callback lock held */ +static void kcm_abort_rx_psock(struct kcm_psock *psock, int err, + struct sk_buff *skb) +{ + struct sock *csk = psock->sk; + + /* Unrecoverable error in receive */ + + if (psock->rx_stopped) + return; + + psock->rx_stopped = 1; + + /* Report an error on the lower socket */ + report_csk_error(csk, err); +} + +static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, + bool wakeup_kcm) +{ + struct sock *csk = psock->sk; + struct kcm_mux *mux = psock->mux; + + /* Unrecoverable error in transmit */ + + spin_lock_bh(&mux->lock); + + if (psock->tx_stopped) { + spin_unlock_bh(&mux->lock); + return; + } + + psock->tx_stopped = 1; + + if (!psock->tx_kcm) { + /* Take off psocks_avail list */ + list_del(&psock->psock_avail_list); + } else if (wakeup_kcm) { + /* In this case psock is being aborted while outside of + * write_msgs and psock is reserved. Schedule tx_work + * to handle the failure there. Need to commit tx_stopped + * before queuing work. + */ + smp_mb(); + + queue_work(kcm_wq, &psock->tx_kcm->tx_work); + } + + spin_unlock_bh(&mux->lock); + + /* Report error on lower socket */ + report_csk_error(csk, err); +} + +static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +/* KCM is ready to receive messages on its queue-- either the KCM is new or + * has become unblocked after being blocked on full socket buffer. Queue any + * pending ready messages on a psock. RX mux lock held. + */ +static void kcm_rcv_ready(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + struct sk_buff *skb; + + if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled)) + return; + + while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) { + if (kcm_queue_rcv_skb(&kcm->sk, skb)) { + /* Assuming buffer limit has been reached */ + skb_queue_head(&mux->rx_hold_queue, skb); + WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); + return; + } + } + + while (!list_empty(&mux->psocks_ready)) { + psock = list_first_entry(&mux->psocks_ready, struct kcm_psock, + psock_ready_list); + + if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) { + /* Assuming buffer limit has been reached */ + WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); + return; + } + + /* Consumed the ready message on the psock. Schedule rx_work to + * get more messages. + */ + list_del(&psock->psock_ready_list); + psock->ready_rx_msg = NULL; + + /* Commit clearing of ready_rx_msg for queuing work */ + smp_mb(); + + queue_work(kcm_wq, &psock->rx_work); + } + + /* Buffer limit is okay now, add to ready list */ + list_add_tail(&kcm->wait_rx_list, + &kcm->mux->kcm_rx_waiters); + kcm->rx_wait = true; +} + +static void kcm_rfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct kcm_sock *kcm = kcm_sk(sk); + struct kcm_mux *mux = kcm->mux; + unsigned int len = skb->truesize; + + sk_mem_uncharge(sk, len); + atomic_sub(len, &sk->sk_rmem_alloc); + + /* For reading rx_wait and rx_psock without holding lock */ + smp_mb__after_atomic(); + + if (!kcm->rx_wait && !kcm->rx_psock && + sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { + spin_lock_bh(&mux->rx_lock); + kcm_rcv_ready(kcm); + spin_unlock_bh(&mux->rx_lock); + } +} + +static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + struct sk_buff_head *list = &sk->sk_receive_queue; + + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + return -ENOMEM; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return -ENOBUFS; + + skb->dev = NULL; + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = kcm_rfree; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_charge(sk, skb->truesize); + + skb_queue_tail(list, skb); + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk); + + return 0; +} + +/* Requeue received messages for a kcm socket to other kcm sockets. This is + * called with a kcm socket is receive disabled. + * RX mux lock held. + */ +static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) +{ + struct sk_buff *skb; + struct kcm_sock *kcm; + + while ((skb = __skb_dequeue(head))) { + /* Reset destructor to avoid calling kcm_rcv_ready */ + skb->destructor = sock_rfree; + skb_orphan(skb); +try_again: + if (list_empty(&mux->kcm_rx_waiters)) { + skb_queue_tail(&mux->rx_hold_queue, skb); + continue; + } + + kcm = list_first_entry(&mux->kcm_rx_waiters, + struct kcm_sock, wait_rx_list); + + if (kcm_queue_rcv_skb(&kcm->sk, skb)) { + /* Should mean socket buffer full */ + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + + /* Commit rx_wait to read in kcm_free */ + smp_wmb(); + + goto try_again; + } + } +} + +/* Lower sock lock held */ +static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, + struct sk_buff *head) +{ + struct kcm_mux *mux = psock->mux; + struct kcm_sock *kcm; + + WARN_ON(psock->ready_rx_msg); + + if (psock->rx_kcm) + return psock->rx_kcm; + + spin_lock_bh(&mux->rx_lock); + + if (psock->rx_kcm) { + spin_unlock_bh(&mux->rx_lock); + return psock->rx_kcm; + } + + if (list_empty(&mux->kcm_rx_waiters)) { + psock->ready_rx_msg = head; + list_add_tail(&psock->psock_ready_list, + &mux->psocks_ready); + spin_unlock_bh(&mux->rx_lock); + return NULL; + } + + kcm = list_first_entry(&mux->kcm_rx_waiters, + struct kcm_sock, wait_rx_list); + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + + psock->rx_kcm = kcm; + kcm->rx_psock = psock; + + spin_unlock_bh(&mux->rx_lock); + + return kcm; +} + +static void kcm_done(struct kcm_sock *kcm); + +static void kcm_done_work(struct work_struct *w) +{ + kcm_done(container_of(w, struct kcm_sock, done_work)); +} + +/* Lower sock held */ +static void unreserve_rx_kcm(struct kcm_psock *psock, + bool rcv_ready) +{ + struct kcm_sock *kcm = psock->rx_kcm; + struct kcm_mux *mux = psock->mux; + + if (!kcm) + return; + + spin_lock_bh(&mux->rx_lock); + + psock->rx_kcm = NULL; + kcm->rx_psock = NULL; + + /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with + * kcm_rfree + */ + smp_mb(); + + if (unlikely(kcm->done)) { + spin_unlock_bh(&mux->rx_lock); + + /* Need to run kcm_done in a task since we need to qcquire + * callback locks which may already be held here. + */ + INIT_WORK(&kcm->done_work, kcm_done_work); + schedule_work(&kcm->done_work); + return; + } + + if (unlikely(kcm->rx_disabled)) { + requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); + } else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) { + /* Check for degenerative race with rx_wait that all + * data was dequeued (accounted for in kcm_rfree). + */ + kcm_rcv_ready(kcm); + } + spin_unlock_bh(&mux->rx_lock); +} + +/* Macro to invoke filter function. */ +#define KCM_RUN_FILTER(prog, ctx) \ + (*prog->bpf_func)(ctx, prog->insnsi) + +/* Lower socket lock held */ +static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, + unsigned int orig_offset, size_t orig_len) +{ + struct kcm_psock *psock = (struct kcm_psock *)desc->arg.data; + struct kcm_rx_msg *rxm; + struct kcm_sock *kcm; + struct sk_buff *head, *skb; + size_t eaten = 0, cand_len; + ssize_t extra; + int err; + bool cloned_orig = false; + + if (psock->ready_rx_msg) + return 0; + + head = psock->rx_skb_head; + if (head) { + /* Message already in progress */ + + if (unlikely(orig_offset)) { + /* Getting data with a non-zero offset when a message is + * in progress is not expected. If it does happen, we + * need to clone and pull since we can't deal with + * offsets in the skbs for a message expect in the head. + */ + orig_skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!orig_skb) { + desc->error = -ENOMEM; + return 0; + } + if (!pskb_pull(orig_skb, orig_offset)) { + kfree_skb(orig_skb); + desc->error = -ENOMEM; + return 0; + } + cloned_orig = true; + orig_offset = 0; + } + + if (!psock->rx_skb_nextp) { + /* We are going to append to the frags_list of head. + * Need to unshare the frag_list. + */ + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + desc->error = err; + return 0; + } + + if (unlikely(skb_shinfo(head)->frag_list)) { + /* We can't append to an sk_buff that already + * has a frag_list. We create a new head, point + * the frag_list of that to the old head, and + * then are able to use the old head->next for + * appending to the message. + */ + if (WARN_ON(head->next)) { + desc->error = -EINVAL; + return 0; + } + + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) { + desc->error = -ENOMEM; + return 0; + } + skb->len = head->len; + skb->data_len = head->len; + skb->truesize = head->truesize; + *kcm_rx_msg(skb) = *kcm_rx_msg(head); + psock->rx_skb_nextp = &head->next; + skb_shinfo(skb)->frag_list = head; + psock->rx_skb_head = skb; + head = skb; + } else { + psock->rx_skb_nextp = + &skb_shinfo(head)->frag_list; + } + } + } + + while (eaten < orig_len) { + /* Always clone since we will consume something */ + skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!skb) { + desc->error = -ENOMEM; + break; + } + + cand_len = orig_len - eaten; + + head = psock->rx_skb_head; + if (!head) { + head = skb; + psock->rx_skb_head = head; + /* Will set rx_skb_nextp on next packet if needed */ + psock->rx_skb_nextp = NULL; + rxm = kcm_rx_msg(head); + memset(rxm, 0, sizeof(*rxm)); + rxm->offset = orig_offset + eaten; + } else { + /* Unclone since we may be appending to an skb that we + * already share a frag_list with. + */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) { + desc->error = err; + break; + } + + rxm = kcm_rx_msg(head); + *psock->rx_skb_nextp = skb; + psock->rx_skb_nextp = &skb->next; + head->data_len += skb->len; + head->len += skb->len; + head->truesize += skb->truesize; + } + + if (!rxm->full_len) { + ssize_t len; + + len = KCM_RUN_FILTER(psock->bpf_prog, head); + + if (!len) { + /* Need more header to determine length */ + rxm->accum_len += cand_len; + eaten += cand_len; + WARN_ON(eaten != orig_len); + break; + } else if (len <= (ssize_t)head->len - + skb->len - rxm->offset) { + /* Length must be into new skb (and also + * greater than zero) + */ + desc->error = -EPROTO; + psock->rx_skb_head = NULL; + kcm_abort_rx_psock(psock, EPROTO, head); + break; + } + + rxm->full_len = len; + } + + extra = (ssize_t)(rxm->accum_len + cand_len) - rxm->full_len; + + if (extra < 0) { + /* Message not complete yet. */ + rxm->accum_len += cand_len; + eaten += cand_len; + WARN_ON(eaten != orig_len); + break; + } + + /* Positive extra indicates ore bytes than needed for the + * message + */ + + WARN_ON(extra > cand_len); + + eaten += (cand_len - extra); + + /* Hurray, we have a new message! */ + psock->rx_skb_head = NULL; + +try_queue: + kcm = reserve_rx_kcm(psock, head); + if (!kcm) { + /* Unable to reserve a KCM, message is held in psock. */ + break; + } + + if (kcm_queue_rcv_skb(&kcm->sk, head)) { + /* Should mean socket buffer full */ + unreserve_rx_kcm(psock, false); + goto try_queue; + } + } + + if (cloned_orig) + kfree_skb(orig_skb); + + return eaten; +} + +/* Called with lock held on lower socket */ +static int psock_tcp_read_sock(struct kcm_psock *psock) +{ + read_descriptor_t desc; + + desc.arg.data = psock; + desc.error = 0; + desc.count = 1; /* give more than one skb per call */ + + /* sk should be locked here, so okay to do tcp_read_sock */ + tcp_read_sock(psock->sk, &desc, kcm_tcp_recv); + + unreserve_rx_kcm(psock, true); + + return desc.error; +} + +/* Lower sock lock held */ +static void psock_tcp_data_ready(struct sock *sk) +{ + struct kcm_psock *psock; + + read_lock_bh(&sk->sk_callback_lock); + + psock = (struct kcm_psock *)sk->sk_user_data; + if (unlikely(!psock || psock->rx_stopped)) + goto out; + + if (psock->ready_rx_msg) + goto out; + + if (psock_tcp_read_sock(psock) == -ENOMEM) + queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); + +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static void do_psock_rx_work(struct kcm_psock *psock) +{ + read_descriptor_t rd_desc; + struct sock *csk = psock->sk; + + /* We need the read lock to synchronize with psock_tcp_data_ready. We + * need the socket lock for calling tcp_read_sock. + */ + lock_sock(csk); + read_lock_bh(&csk->sk_callback_lock); + + if (unlikely(csk->sk_user_data != psock)) + goto out; + + if (unlikely(psock->rx_stopped)) + goto out; + + if (psock->ready_rx_msg) + goto out; + + rd_desc.arg.data = psock; + + if (psock_tcp_read_sock(psock) == -ENOMEM) + queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); + +out: + read_unlock_bh(&csk->sk_callback_lock); + release_sock(csk); +} + +static void psock_rx_work(struct work_struct *w) +{ + do_psock_rx_work(container_of(w, struct kcm_psock, rx_work)); +} + +static void psock_rx_delayed_work(struct work_struct *w) +{ + do_psock_rx_work(container_of(w, struct kcm_psock, + rx_delayed_work.work)); +} + +static void psock_tcp_state_change(struct sock *sk) +{ + /* TCP only does a POLLIN for a half close. Do a POLLHUP here + * since application will normally not poll with POLLIN + * on the TCP sockets. + */ + + report_csk_error(sk, EPIPE); +} + +static void psock_tcp_write_space(struct sock *sk) +{ + struct kcm_psock *psock; + struct kcm_mux *mux; + struct kcm_sock *kcm; + + read_lock_bh(&sk->sk_callback_lock); + + psock = (struct kcm_psock *)sk->sk_user_data; + if (unlikely(!psock)) + goto out; + + mux = psock->mux; + + spin_lock_bh(&mux->lock); + + /* Check if the socket is reserved so someone is waiting for sending. */ + kcm = psock->tx_kcm; + if (kcm) + queue_work(kcm_wq, &kcm->tx_work); + + spin_unlock_bh(&mux->lock); +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static void unreserve_psock(struct kcm_sock *kcm); + +/* kcm sock is locked. */ +static struct kcm_psock *reserve_psock(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + + psock = kcm->tx_psock; + + smp_rmb(); /* Must read tx_psock before tx_wait */ + + if (psock) { + WARN_ON(kcm->tx_wait); + if (unlikely(psock->tx_stopped)) + unreserve_psock(kcm); + else + return kcm->tx_psock; + } + + spin_lock_bh(&mux->lock); + + /* Check again under lock to see if psock was reserved for this + * psock via psock_unreserve. + */ + psock = kcm->tx_psock; + if (unlikely(psock)) { + WARN_ON(kcm->tx_wait); + spin_unlock_bh(&mux->lock); + return kcm->tx_psock; + } + + if (!list_empty(&mux->psocks_avail)) { + psock = list_first_entry(&mux->psocks_avail, + struct kcm_psock, + psock_avail_list); + list_del(&psock->psock_avail_list); + if (kcm->tx_wait) { + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + } + kcm->tx_psock = psock; + psock->tx_kcm = kcm; + } else if (!kcm->tx_wait) { + list_add_tail(&kcm->wait_psock_list, + &mux->kcm_tx_waiters); + kcm->tx_wait = true; + } + + spin_unlock_bh(&mux->lock); + + return psock; +} + +/* mux lock held */ +static void psock_now_avail(struct kcm_psock *psock) +{ + struct kcm_mux *mux = psock->mux; + struct kcm_sock *kcm; + + if (list_empty(&mux->kcm_tx_waiters)) { + list_add_tail(&psock->psock_avail_list, + &mux->psocks_avail); + } else { + kcm = list_first_entry(&mux->kcm_tx_waiters, + struct kcm_sock, + wait_psock_list); + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + psock->tx_kcm = kcm; + + /* Commit before changing tx_psock since that is read in + * reserve_psock before queuing work. + */ + smp_mb(); + + kcm->tx_psock = psock; + queue_work(kcm_wq, &kcm->tx_work); + } +} + +/* kcm sock is locked. */ +static void unreserve_psock(struct kcm_sock *kcm) +{ + struct kcm_psock *psock; + struct kcm_mux *mux = kcm->mux; + + spin_lock_bh(&mux->lock); + + psock = kcm->tx_psock; + + if (WARN_ON(!psock)) { + spin_unlock_bh(&mux->lock); + return; + } + + smp_rmb(); /* Read tx_psock before tx_wait */ + + WARN_ON(kcm->tx_wait); + + kcm->tx_psock = NULL; + psock->tx_kcm = NULL; + + if (unlikely(psock->tx_stopped)) { + if (psock->done) { + /* Deferred free */ + list_del(&psock->psock_list); + mux->psocks_cnt--; + sock_put(psock->sk); + fput(psock->sk->sk_socket->file); + kmem_cache_free(kcm_psockp, psock); + } + + /* Don't put back on available list */ + + spin_unlock_bh(&mux->lock); + + return; + } + + psock_now_avail(psock); + + spin_unlock_bh(&mux->lock); +} + +/* Write any messages ready on the kcm socket. Called with kcm sock lock + * held. Return bytes actually sent or error. + */ +static int kcm_write_msgs(struct kcm_sock *kcm) +{ + struct sock *sk = &kcm->sk; + struct kcm_psock *psock; + struct sk_buff *skb, *head; + struct kcm_tx_msg *txm; + unsigned short fragidx, frag_offset; + unsigned int sent, total_sent = 0; + int ret = 0; + + kcm->tx_wait_more = false; + psock = kcm->tx_psock; + if (unlikely(psock && psock->tx_stopped)) { + /* A reserved psock was aborted asynchronously. Unreserve + * it and we'll retry the message. + */ + unreserve_psock(kcm); + if (skb_queue_empty(&sk->sk_write_queue)) + return 0; + + kcm_tx_msg(skb_peek(&sk->sk_write_queue))->sent = 0; + + } else if (skb_queue_empty(&sk->sk_write_queue)) { + return 0; + } + + head = skb_peek(&sk->sk_write_queue); + txm = kcm_tx_msg(head); + + if (txm->sent) { + /* Send of first skbuff in queue already in progress */ + if (WARN_ON(!psock)) { + ret = -EINVAL; + goto out; + } + sent = txm->sent; + frag_offset = txm->frag_offset; + fragidx = txm->fragidx; + skb = txm->frag_skb; + + goto do_frag; + } + +try_again: + psock = reserve_psock(kcm); + if (!psock) + goto out; + + do { + skb = head; + txm = kcm_tx_msg(head); + sent = 0; + +do_frag_list: + if (WARN_ON(!skb_shinfo(skb)->nr_frags)) { + ret = -EINVAL; + goto out; + } + + for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; + fragidx++) { + skb_frag_t *frag; + + frag_offset = 0; +do_frag: + frag = &skb_shinfo(skb)->frags[fragidx]; + if (WARN_ON(!frag->size)) { + ret = -EINVAL; + goto out; + } + + ret = kernel_sendpage(psock->sk->sk_socket, + frag->page.p, + frag->page_offset + frag_offset, + frag->size - frag_offset, + MSG_DONTWAIT); + if (ret <= 0) { + if (ret == -EAGAIN) { + /* Save state to try again when there's + * write space on the socket + */ + txm->sent = sent; + txm->frag_offset = frag_offset; + txm->fragidx = fragidx; + txm->frag_skb = skb; + + ret = 0; + goto out; + } + + /* Hard failure in sending message, abort this + * psock since it has lost framing + * synchonization and retry sending the + * message from the beginning. + */ + kcm_abort_tx_psock(psock, ret ? -ret : EPIPE, + true); + unreserve_psock(kcm); + + txm->sent = 0; + ret = 0; + + goto try_again; + } + + sent += ret; + frag_offset += ret; + if (frag_offset < frag->size) { + /* Not finished with this frag */ + goto do_frag; + } + } + + if (skb == head) { + if (skb_has_frag_list(skb)) { + skb = skb_shinfo(skb)->frag_list; + goto do_frag_list; + } + } else if (skb->next) { + skb = skb->next; + goto do_frag_list; + } + + /* Successfully sent the whole packet, account for it. */ + skb_dequeue(&sk->sk_write_queue); + kfree_skb(head); + sk->sk_wmem_queued -= sent; + total_sent += sent; + } while ((head = skb_peek(&sk->sk_write_queue))); +out: + if (!head) { + /* Done with all queued messages. */ + WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); + unreserve_psock(kcm); + } + + /* Check if write space is available */ + sk->sk_write_space(sk); + + return total_sent ? : ret; +} + +static void kcm_tx_work(struct work_struct *w) +{ + struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work); + struct sock *sk = &kcm->sk; + int err; + + lock_sock(sk); + + /* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx + * aborts + */ + err = kcm_write_msgs(kcm); + if (err < 0) { + /* Hard failure in write, report error on KCM socket */ + pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err); + report_csk_error(&kcm->sk, -err); + goto out; + } + + /* Primarily for SOCK_SEQPACKET sockets */ + if (likely(sk->sk_socket) && + test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + sk->sk_write_space(sk); + } + +out: + release_sock(sk); +} + +static void kcm_push(struct kcm_sock *kcm) +{ + if (kcm->tx_wait_more) + kcm_write_msgs(kcm); +} + +static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); + struct sk_buff *skb = NULL, *head = NULL; + size_t copy, copied = 0; + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + int eor = (sock->type == SOCK_DGRAM) ? + !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); + int err = -EPIPE; + + lock_sock(sk); + + /* Per tcp_sendmsg this should be in poll */ + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + if (sk->sk_err) + goto out_error; + + if (kcm->seq_skb) { + /* Previously opened message */ + head = kcm->seq_skb; + skb = kcm_tx_msg(head)->last_skb; + goto start; + } + + /* Call the sk_stream functions to manage the sndbuf mem. */ + if (!sk_stream_memory_free(sk)) { + kcm_push(kcm); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + /* New message, alloc head skb */ + head = alloc_skb(0, sk->sk_allocation); + while (!head) { + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + + head = alloc_skb(0, sk->sk_allocation); + } + + skb = head; + + /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling + * csum_and_copy_from_iter from skb_do_copy_data_nocache. + */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + +start: + while (msg_data_left(msg)) { + bool merge = true; + int i = skb_shinfo(skb)->nr_frags; + struct page_frag *pfrag = sk_page_frag(sk); + + if (!sk_page_frag_refill(sk, pfrag)) + goto wait_for_memory; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + if (i == MAX_SKB_FRAGS) { + struct sk_buff *tskb; + + tskb = alloc_skb(0, sk->sk_allocation); + if (!tskb) + goto wait_for_memory; + + if (head == skb) + skb_shinfo(head)->frag_list = tskb; + else + skb->next = tskb; + + skb = tskb; + skb->ip_summed = CHECKSUM_UNNECESSARY; + continue; + } + merge = false; + } + + copy = min_t(int, msg_data_left(msg), + pfrag->size - pfrag->offset); + + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_memory; + + err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, + pfrag->page, + pfrag->offset, + copy); + if (err) + goto out_error; + + /* Update the skb. */ + if (merge) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); + } else { + skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, copy); + get_page(pfrag->page); + } + + pfrag->offset += copy; + copied += copy; + if (head != skb) { + head->len += copy; + head->data_len += copy; + } + + continue; + +wait_for_memory: + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + if (eor) { + bool not_busy = skb_queue_empty(&sk->sk_write_queue); + + /* Message complete, queue it on send buffer */ + __skb_queue_tail(&sk->sk_write_queue, head); + kcm->seq_skb = NULL; + + if (msg->msg_flags & MSG_BATCH) { + kcm->tx_wait_more = true; + } else if (kcm->tx_wait_more || not_busy) { + err = kcm_write_msgs(kcm); + if (err < 0) { + /* We got a hard error in write_msgs but have + * already queued this message. Report an error + * in the socket, but don't affect return value + * from sendmsg + */ + pr_warn("KCM: Hard failure on kcm_write_msgs\n"); + report_csk_error(&kcm->sk, -err); + } + } + } else { + /* Message not complete, save state */ +partial_message: + kcm->seq_skb = head; + kcm_tx_msg(head)->last_skb = skb; + } + + release_sock(sk); + return copied; + +out_error: + kcm_push(kcm); + + if (copied && sock->type == SOCK_SEQPACKET) { + /* Wrote some bytes before encountering an + * error, return partial success. + */ + goto partial_message; + } + + if (head != kcm->seq_skb) + kfree_skb(head); + + err = sk_stream_error(sk, msg->msg_flags, err); + + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); + + release_sock(sk); + return err; +} + +static struct sk_buff *kcm_wait_data(struct sock *sk, int flags, + long timeo, int *err) +{ + struct sk_buff *skb; + + while (!(skb = skb_peek(&sk->sk_receive_queue))) { + if (sk->sk_err) { + *err = sock_error(sk); + return NULL; + } + + if (sock_flag(sk, SOCK_DONE)) + return NULL; + + if ((flags & MSG_DONTWAIT) || !timeo) { + *err = -EAGAIN; + return NULL; + } + + sk_wait_data(sk, &timeo, NULL); + + /* Handle signals */ + if (signal_pending(current)) { + *err = sock_intr_errno(timeo); + return NULL; + } + } + + return skb; +} + +static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + int err = 0; + long timeo; + struct kcm_rx_msg *rxm; + int copied = 0; + struct sk_buff *skb; + + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + + lock_sock(sk); + + skb = kcm_wait_data(sk, flags, timeo, &err); + if (!skb) + goto out; + + /* Okay, have a message on the receive queue */ + + rxm = kcm_rx_msg(skb); + + if (len > rxm->full_len) + len = rxm->full_len; + + err = skb_copy_datagram_msg(skb, rxm->offset, msg, len); + if (err < 0) + goto out; + + copied = len; + if (likely(!(flags & MSG_PEEK))) { + if (copied < rxm->full_len) { + if (sock->type == SOCK_DGRAM) { + /* Truncated message */ + msg->msg_flags |= MSG_TRUNC; + goto msg_finished; + } + rxm->offset += copied; + rxm->full_len -= copied; + } else { +msg_finished: + /* Finished with message */ + msg->msg_flags |= MSG_EOR; + skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); + } + } + +out: + release_sock(sk); + + return copied ? : err; +} + +/* kcm sock lock held */ +static void kcm_recv_disable(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + if (kcm->rx_disabled) + return; + + spin_lock_bh(&mux->rx_lock); + + kcm->rx_disabled = 1; + + /* If a psock is reserved we'll do cleanup in unreserve */ + if (!kcm->rx_psock) { + if (kcm->rx_wait) { + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + } + + requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); + } + + spin_unlock_bh(&mux->rx_lock); +} + +/* kcm sock lock held */ +static void kcm_recv_enable(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + if (!kcm->rx_disabled) + return; + + spin_lock_bh(&mux->rx_lock); + + kcm->rx_disabled = 0; + kcm_rcv_ready(kcm); + + spin_unlock_bh(&mux->rx_lock); +} + +static int kcm_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + int val, valbool; + int err = 0; + + if (level != SOL_KCM) + return -ENOPROTOOPT; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *)optval)) + return -EINVAL; + + valbool = val ? 1 : 0; + + switch (optname) { + case KCM_RECV_DISABLE: + lock_sock(&kcm->sk); + if (valbool) + kcm_recv_disable(kcm); + else + kcm_recv_enable(kcm); + release_sock(&kcm->sk); + break; + default: + err = -ENOPROTOOPT; + } + + return err; +} + +static int kcm_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + int val, len; + + if (level != SOL_KCM) + return -ENOPROTOOPT; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(int)); + if (len < 0) + return -EINVAL; + + switch (optname) { + case KCM_RECV_DISABLE: + val = kcm->rx_disabled; + break; + default: + return -ENOPROTOOPT; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; +} + +static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) +{ + struct kcm_sock *tkcm; + struct list_head *head; + int index = 0; + + /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so + * we set sk_state, otherwise epoll_wait always returns right away with + * POLLHUP + */ + kcm->sk.sk_state = TCP_ESTABLISHED; + + /* Add to mux's kcm sockets list */ + kcm->mux = mux; + spin_lock_bh(&mux->lock); + + head = &mux->kcm_socks; + list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) { + if (tkcm->index != index) + break; + head = &tkcm->kcm_sock_list; + index++; + } + + list_add(&kcm->kcm_sock_list, head); + kcm->index = index; + + mux->kcm_socks_cnt++; + spin_unlock_bh(&mux->lock); + + INIT_WORK(&kcm->tx_work, kcm_tx_work); + + spin_lock_bh(&mux->rx_lock); + kcm_rcv_ready(kcm); + spin_unlock_bh(&mux->rx_lock); +} + +static int kcm_attach(struct socket *sock, struct socket *csock, + struct bpf_prog *prog) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + struct kcm_mux *mux = kcm->mux; + struct sock *csk; + struct kcm_psock *psock = NULL, *tpsock; + struct list_head *head; + int index = 0; + + if (csock->ops->family != PF_INET && + csock->ops->family != PF_INET6) + return -EINVAL; + + csk = csock->sk; + if (!csk) + return -EINVAL; + + /* Only support TCP for now */ + if (csk->sk_protocol != IPPROTO_TCP) + return -EINVAL; + + psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); + if (!psock) + return -ENOMEM; + + psock->mux = mux; + psock->sk = csk; + psock->bpf_prog = prog; + INIT_WORK(&psock->rx_work, psock_rx_work); + INIT_DELAYED_WORK(&psock->rx_delayed_work, psock_rx_delayed_work); + + sock_hold(csk); + + write_lock_bh(&csk->sk_callback_lock); + psock->save_data_ready = csk->sk_data_ready; + psock->save_write_space = csk->sk_write_space; + psock->save_state_change = csk->sk_state_change; + csk->sk_user_data = psock; + csk->sk_data_ready = psock_tcp_data_ready; + csk->sk_write_space = psock_tcp_write_space; + csk->sk_state_change = psock_tcp_state_change; + write_unlock_bh(&csk->sk_callback_lock); + + /* Finished initialization, now add the psock to the MUX. */ + spin_lock_bh(&mux->lock); + head = &mux->psocks; + list_for_each_entry(tpsock, &mux->psocks, psock_list) { + if (tpsock->index != index) + break; + head = &tpsock->psock_list; + index++; + } + + list_add(&psock->psock_list, head); + psock->index = index; + + mux->psocks_cnt++; + psock_now_avail(psock); + spin_unlock_bh(&mux->lock); + + /* Schedule RX work in case there are already bytes queued */ + queue_work(kcm_wq, &psock->rx_work); + + return 0; +} + +static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) +{ + struct socket *csock; + struct bpf_prog *prog; + int err; + + csock = sockfd_lookup(info->fd, &err); + if (!csock) + return -ENOENT; + + prog = bpf_prog_get(info->bpf_fd); + if (IS_ERR(prog)) { + err = PTR_ERR(prog); + goto out; + } + + if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) { + bpf_prog_put(prog); + err = -EINVAL; + goto out; + } + + err = kcm_attach(sock, csock, prog); + if (err) { + bpf_prog_put(prog); + goto out; + } + + /* Keep reference on file also */ + + return 0; +out: + fput(csock->file); + return err; +} + +static void kcm_unattach(struct kcm_psock *psock) +{ + struct sock *csk = psock->sk; + struct kcm_mux *mux = psock->mux; + + /* Stop getting callbacks from TCP socket. After this there should + * be no way to reserve a kcm for this psock. + */ + write_lock_bh(&csk->sk_callback_lock); + csk->sk_user_data = NULL; + csk->sk_data_ready = psock->save_data_ready; + csk->sk_write_space = psock->save_write_space; + csk->sk_state_change = psock->save_state_change; + psock->rx_stopped = 1; + + if (WARN_ON(psock->rx_kcm)) { + write_unlock_bh(&csk->sk_callback_lock); + return; + } + + spin_lock_bh(&mux->rx_lock); + + /* Stop receiver activities. After this point psock should not be + * able to get onto ready list either through callbacks or work. + */ + if (psock->ready_rx_msg) { + list_del(&psock->psock_ready_list); + kfree_skb(psock->ready_rx_msg); + psock->ready_rx_msg = NULL; + } + + spin_unlock_bh(&mux->rx_lock); + + write_unlock_bh(&csk->sk_callback_lock); + + cancel_work_sync(&psock->rx_work); + cancel_delayed_work_sync(&psock->rx_delayed_work); + + bpf_prog_put(psock->bpf_prog); + + kfree_skb(psock->rx_skb_head); + psock->rx_skb_head = NULL; + + spin_lock_bh(&mux->lock); + + if (psock->tx_kcm) { + /* psock was reserved. Just mark it finished and we will clean + * up in the kcm paths, we need kcm lock which can not be + * acquired here. + */ + spin_unlock_bh(&mux->lock); + + /* We are unattaching a socket that is reserved. Abort the + * socket since we may be out of sync in sending on it. We need + * to do this without the mux lock. + */ + kcm_abort_tx_psock(psock, EPIPE, false); + + spin_lock_bh(&mux->lock); + if (!psock->tx_kcm) { + /* psock now unreserved in window mux was unlocked */ + goto no_reserved; + } + psock->done = 1; + + /* Commit done before queuing work to process it */ + smp_mb(); + + /* Queue tx work to make sure psock->done is handled */ + queue_work(kcm_wq, &psock->tx_kcm->tx_work); + spin_unlock_bh(&mux->lock); + } else { +no_reserved: + if (!psock->tx_stopped) + list_del(&psock->psock_avail_list); + list_del(&psock->psock_list); + mux->psocks_cnt--; + spin_unlock_bh(&mux->lock); + + sock_put(csk); + fput(csk->sk_socket->file); + kmem_cache_free(kcm_psockp, psock); + } +} + +static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + struct socket *csock; + struct sock *csk; + int err; + + csock = sockfd_lookup(info->fd, &err); + if (!csock) + return -ENOENT; + + csk = csock->sk; + if (!csk) { + err = -EINVAL; + goto out; + } + + err = -ENOENT; + + spin_lock_bh(&mux->lock); + + list_for_each_entry(psock, &mux->psocks, psock_list) { + if (psock->sk != csk) + continue; + + /* Found the matching psock */ + + if (psock->unattaching || WARN_ON(psock->done)) { + err = -EALREADY; + break; + } + + psock->unattaching = 1; + + spin_unlock_bh(&mux->lock); + + kcm_unattach(psock); + + err = 0; + goto out; + } + + spin_unlock_bh(&mux->lock); + +out: + fput(csock->file); + return err; +} + +static struct proto kcm_proto = { + .name = "KCM", + .owner = THIS_MODULE, + .obj_size = sizeof(struct kcm_sock), +}; + +/* Clone a kcm socket. */ +static int kcm_clone(struct socket *osock, struct kcm_clone *info, + struct socket **newsockp) +{ + struct socket *newsock; + struct sock *newsk; + struct file *newfile; + int err, newfd; + + err = -ENFILE; + newsock = sock_alloc(); + if (!newsock) + goto out; + + newsock->type = osock->type; + newsock->ops = osock->ops; + + __module_get(newsock->ops->owner); + + newfd = get_unused_fd_flags(0); + if (unlikely(newfd < 0)) { + err = newfd; + goto out_fd_fail; + } + + newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); + if (unlikely(IS_ERR(newfile))) { + err = PTR_ERR(newfile); + goto out_sock_alloc_fail; + } + + newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, + &kcm_proto, true); + if (!newsk) { + err = -ENOMEM; + goto out_sk_alloc_fail; + } + + sock_init_data(newsock, newsk); + init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux); + + fd_install(newfd, newfile); + *newsockp = newsock; + info->fd = newfd; + + return 0; + +out_sk_alloc_fail: + fput(newfile); +out_sock_alloc_fail: + put_unused_fd(newfd); +out_fd_fail: + sock_release(newsock); +out: + return err; +} + +static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + int err; + + switch (cmd) { + case SIOCKCMATTACH: { + struct kcm_attach info; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_attach_ioctl(sock, &info); + + break; + } + case SIOCKCMUNATTACH: { + struct kcm_unattach info; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_unattach_ioctl(sock, &info); + + break; + } + case SIOCKCMCLONE: { + struct kcm_clone info; + struct socket *newsock = NULL; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_clone(sock, &info, &newsock); + + if (!err) { + if (copy_to_user((void __user *)arg, &info, + sizeof(info))) { + err = -EFAULT; + sock_release(newsock); + } + } + + break; + } + default: + err = -ENOIOCTLCMD; + break; + } + + return err; +} + +static void free_mux(struct rcu_head *rcu) +{ + struct kcm_mux *mux = container_of(rcu, + struct kcm_mux, rcu); + + kmem_cache_free(kcm_muxp, mux); +} + +static void release_mux(struct kcm_mux *mux) +{ + struct kcm_net *knet = mux->knet; + struct kcm_psock *psock, *tmp_psock; + + /* Release psocks */ + list_for_each_entry_safe(psock, tmp_psock, + &mux->psocks, psock_list) { + if (!WARN_ON(psock->unattaching)) + kcm_unattach(psock); + } + + if (WARN_ON(mux->psocks_cnt)) + return; + + __skb_queue_purge(&mux->rx_hold_queue); + + mutex_lock(&knet->mutex); + list_del_rcu(&mux->kcm_mux_list); + knet->count--; + mutex_unlock(&knet->mutex); + + call_rcu(&mux->rcu, free_mux); +} + +static void kcm_done(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct sock *sk = &kcm->sk; + int socks_cnt; + + spin_lock_bh(&mux->rx_lock); + if (kcm->rx_psock) { + /* Cleanup in unreserve_rx_kcm */ + WARN_ON(kcm->done); + kcm->rx_disabled = 1; + kcm->done = 1; + spin_unlock_bh(&mux->rx_lock); + return; + } + + if (kcm->rx_wait) { + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + } + /* Move any pending receive messages to other kcm sockets */ + requeue_rx_msgs(mux, &sk->sk_receive_queue); + + spin_unlock_bh(&mux->rx_lock); + + if (WARN_ON(sk_rmem_alloc_get(sk))) + return; + + /* Detach from MUX */ + spin_lock_bh(&mux->lock); + + list_del(&kcm->kcm_sock_list); + mux->kcm_socks_cnt--; + socks_cnt = mux->kcm_socks_cnt; + + spin_unlock_bh(&mux->lock); + + if (!socks_cnt) { + /* We are done with the mux now. */ + release_mux(mux); + } + + WARN_ON(kcm->rx_wait); + + sock_put(&kcm->sk); +} + +/* Called by kcm_release to close a KCM socket. + * If this is the last KCM socket on the MUX, destroy the MUX. + */ +static int kcm_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm; + struct kcm_mux *mux; + struct kcm_psock *psock; + + if (!sk) + return 0; + + kcm = kcm_sk(sk); + mux = kcm->mux; + + sock_orphan(sk); + kfree_skb(kcm->seq_skb); + + lock_sock(sk); + /* Purge queue under lock to avoid race condition with tx_work trying + * to act when queue is nonempty. If tx_work runs after this point + * it will just return. + */ + __skb_queue_purge(&sk->sk_write_queue); + release_sock(sk); + + spin_lock_bh(&mux->lock); + if (kcm->tx_wait) { + /* Take of tx_wait list, after this point there should be no way + * that a psock will be assigned to this kcm. + */ + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + } + spin_unlock_bh(&mux->lock); + + /* Cancel work. After this point there should be no outside references + * to the kcm socket. + */ + cancel_work_sync(&kcm->tx_work); + + lock_sock(sk); + psock = kcm->tx_psock; + if (psock) { + /* A psock was reserved, so we need to kill it since it + * may already have some bytes queued from a message. We + * need to do this after removing kcm from tx_wait list. + */ + kcm_abort_tx_psock(psock, EPIPE, false); + unreserve_psock(kcm); + } + release_sock(sk); + + WARN_ON(kcm->tx_wait); + WARN_ON(kcm->tx_psock); + + sock->sk = NULL; + + kcm_done(kcm); + + return 0; +} + +static const struct proto_ops kcm_ops = { + .family = PF_KCM, + .owner = THIS_MODULE, + .release = kcm_release, + .bind = sock_no_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = kcm_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = kcm_setsockopt, + .getsockopt = kcm_getsockopt, + .sendmsg = kcm_sendmsg, + .recvmsg = kcm_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +/* Create proto operation for kcm sockets */ +static int kcm_create(struct net *net, struct socket *sock, + int protocol, int kern) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + struct sock *sk; + struct kcm_mux *mux; + + switch (sock->type) { + case SOCK_DGRAM: + case SOCK_SEQPACKET: + sock->ops = &kcm_ops; + break; + default: + return -ESOCKTNOSUPPORT; + } + + if (protocol != KCMPROTO_CONNECTED) + return -EPROTONOSUPPORT; + + sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern); + if (!sk) + return -ENOMEM; + + /* Allocate a kcm mux, shared between KCM sockets */ + mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL); + if (!mux) { + sk_free(sk); + return -ENOMEM; + } + + spin_lock_init(&mux->lock); + spin_lock_init(&mux->rx_lock); + INIT_LIST_HEAD(&mux->kcm_socks); + INIT_LIST_HEAD(&mux->kcm_rx_waiters); + INIT_LIST_HEAD(&mux->kcm_tx_waiters); + + INIT_LIST_HEAD(&mux->psocks); + INIT_LIST_HEAD(&mux->psocks_ready); + INIT_LIST_HEAD(&mux->psocks_avail); + + mux->knet = knet; + + /* Add new MUX to list */ + mutex_lock(&knet->mutex); + list_add_rcu(&mux->kcm_mux_list, &knet->mux_list); + knet->count++; + mutex_unlock(&knet->mutex); + + skb_queue_head_init(&mux->rx_hold_queue); + + /* Init KCM socket */ + sock_init_data(sock, sk); + init_kcm_sock(kcm_sk(sk), mux); + + return 0; +} + +static struct net_proto_family kcm_family_ops = { + .family = PF_KCM, + .create = kcm_create, + .owner = THIS_MODULE, +}; + +static __net_init int kcm_init_net(struct net *net) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + + INIT_LIST_HEAD_RCU(&knet->mux_list); + mutex_init(&knet->mutex); + + return 0; +} + +static __net_exit void kcm_exit_net(struct net *net) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + + /* All KCM sockets should be closed at this point, which should mean + * that all multiplexors and psocks have been destroyed. + */ + WARN_ON(!list_empty(&knet->mux_list)); +} + +static struct pernet_operations kcm_net_ops = { + .init = kcm_init_net, + .exit = kcm_exit_net, + .id = &kcm_net_id, + .size = sizeof(struct kcm_net), +}; + +static int __init kcm_init(void) +{ + int err = -ENOMEM; + + kcm_muxp = kmem_cache_create("kcm_mux_cache", + sizeof(struct kcm_mux), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + if (!kcm_muxp) + goto fail; + + kcm_psockp = kmem_cache_create("kcm_psock_cache", + sizeof(struct kcm_psock), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + if (!kcm_psockp) + goto fail; + + kcm_wq = create_singlethread_workqueue("kkcmd"); + if (!kcm_wq) + goto fail; + + err = proto_register(&kcm_proto, 1); + if (err) + goto fail; + + err = sock_register(&kcm_family_ops); + if (err) + goto sock_register_fail; + + err = register_pernet_device(&kcm_net_ops); + if (err) + goto net_ops_fail; + + return 0; + +net_ops_fail: + sock_unregister(PF_KCM); + +sock_register_fail: + proto_unregister(&kcm_proto); + +fail: + kmem_cache_destroy(kcm_muxp); + kmem_cache_destroy(kcm_psockp); + + if (kcm_wq) + destroy_workqueue(kcm_wq); + + return err; +} + +static void __exit kcm_exit(void) +{ + unregister_pernet_device(&kcm_net_ops); + sock_unregister(PF_KCM); + proto_unregister(&kcm_proto); + destroy_workqueue(kcm_wq); + + kmem_cache_destroy(kcm_muxp); + kmem_cache_destroy(kcm_psockp); +} + +module_init(kcm_init); +module_exit(kcm_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETPROTO(PF_KCM); + -- cgit v1.2.3 From 87aca73737e379f079993802d2c43606f7c5d26c Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 21 Jan 2016 09:20:12 +0100 Subject: NFC: microread: Drop platform data header file Originally I only wanted to drop the unneeded inclusion of , but then noticed that struct microread_nfc_platform_data isn't actually used, and MICROREAD_DRIVER_NAME is redefined in the only file where it is used, so we can get rid of the header file and dead code altogether. Signed-off-by: Jean Delvare Cc: Lauro Ramos Venancio Cc: Aloisio Almeida Jr Signed-off-by: Samuel Ortiz --- MAINTAINERS | 1 - drivers/nfc/microread/i2c.c | 8 -------- include/linux/platform_data/microread.h | 35 --------------------------------- 3 files changed, 44 deletions(-) delete mode 100644 include/linux/platform_data/microread.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 355e1c85bad6..5e4e50ff87bb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7644,7 +7644,6 @@ F: net/nfc/ F: include/net/nfc/ F: include/uapi/linux/nfc.h F: drivers/nfc/ -F: include/linux/platform_data/microread.h F: include/linux/platform_data/nfcmrvl.h F: include/linux/platform_data/nxp-nci.h F: include/linux/platform_data/pn544.h diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index 918e8f2eac47..e0e8afd27849 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -246,18 +246,10 @@ static int microread_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct microread_i2c_phy *phy; - struct microread_nfc_platform_data *pdata = - dev_get_platdata(&client->dev); int r; dev_dbg(&client->dev, "client %p\n", client); - if (!pdata) { - nfc_err(&client->dev, "client %p: missing platform data\n", - client); - return -EINVAL; - } - phy = devm_kzalloc(&client->dev, sizeof(struct microread_i2c_phy), GFP_KERNEL); if (!phy) diff --git a/include/linux/platform_data/microread.h b/include/linux/platform_data/microread.h deleted file mode 100644 index ca13992089b8..000000000000 --- a/include/linux/platform_data/microread.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Driver include for the Inside Secure microread NFC Chip. - * - * Copyright (C) 2011 Tieto Poland - * Copyright (C) 2012 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _MICROREAD_H -#define _MICROREAD_H - -#include - -#define MICROREAD_DRIVER_NAME "microread" - -/* board config platform data for microread */ -struct microread_nfc_platform_data { - unsigned int rst_gpio; - unsigned int irq_gpio; - unsigned int ioh_gpio; -}; - -#endif /* _MICROREAD_H */ -- cgit v1.2.3 From 2793a23aacbd754dbbb5cb75093deb7e4103bace Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 9 Mar 2016 21:58:32 -0500 Subject: net: validate variable length ll headers Netdevice parameter hard_header_len is variously interpreted both as an upper and lower bound on link layer header length. The field is used as upper bound when reserving room at allocation, as lower bound when validating user input in PF_PACKET. Clarify the definition to be maximum header length. For validation of untrusted headers, add an optional validate member to header_ops. Allow bypassing of validation by passing CAP_SYS_RAWIO, for instance for deliberate testing of corrupt input. In this case, pad trailing bytes, as some device drivers expect completely initialized headers. See also http://comments.gmane.org/gmane.linux.network/401064 Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index efe7cec111fa..fd30cb545c45 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -268,6 +268,7 @@ struct header_ops { void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); + bool (*validate)(const char *ll_header, unsigned int len); }; /* These flag bits are private to the generic network queueing @@ -1459,8 +1460,7 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length, which means that this is the - * minimum size of a packet. + * @hard_header_len: Maximum hardware header length. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -2687,6 +2687,24 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } +/* ll_header must have at least hard_header_len allocated */ +static inline bool dev_validate_header(const struct net_device *dev, + char *ll_header, int len) +{ + if (likely(len >= dev->hard_header_len)) + return true; + + if (capable(CAP_SYS_RAWIO)) { + memset(ll_header + len, 0, dev->hard_header_len - len); + return true; + } + + if (dev->header_ops && dev->header_ops->validate) + return dev->header_ops->validate(ll_header, len); + + return false; +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) -- cgit v1.2.3 From 5b33f48842fa1e13e9c0ea8cc59c1d0df19042db Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 8 Mar 2016 12:42:29 +0200 Subject: net/flower: Introduce hardware offload support This patch is based on a patch made by John Fastabend. It adds support for offloading cls_flower. when NETIF_F_HW_TC is on: flags = 0 => Rule will be processed twice - by hardware, and if still relevant, by software. flags = SKIP_HW => Rull will be processed by software only If hardware fail/not capabale to apply the rule, operation will NOT fail. Filter will be processed by SW only. Acked-by: Jiri Pirko Suggested-by: John Fastabend Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ include/net/pkt_cls.h | 14 ++++++++++ include/uapi/linux/pkt_cls.h | 2 ++ net/sched/cls_flower.c | 64 +++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 81 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fd30cb545c45..41df0b450757 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -786,6 +786,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, enum { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, + TC_SETUP_CLSFLOWER, }; struct tc_cls_u32_offload; @@ -795,6 +796,7 @@ struct tc_to_netdev { union { u8 tc; struct tc_cls_u32_offload *cls_u32; + struct tc_cls_flower_offload *cls_flower; }; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bea14eee373e..5b4e8f08b8f0 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -409,4 +409,18 @@ static inline bool tc_should_offload(struct net_device *dev, u32 flags) return true; } +enum tc_fl_command { + TC_CLSFLOWER_REPLACE, + TC_CLSFLOWER_DESTROY, +}; + +struct tc_cls_flower_offload { + enum tc_fl_command command; + u64 cookie; + struct flow_dissector *dissector; + struct fl_flow_key *mask; + struct fl_flow_key *key; + struct tcf_exts *exts; +}; + #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 9874f5680926..c43c5f78b9c4 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -417,6 +417,8 @@ enum { TCA_FLOWER_KEY_TCP_DST, /* be16 */ TCA_FLOWER_KEY_UDP_SRC, /* be16 */ TCA_FLOWER_KEY_UDP_DST, /* be16 */ + + TCA_FLOWER_FLAGS, __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 95b021243233..25d87666bf1e 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -165,6 +165,51 @@ static void fl_destroy_filter(struct rcu_head *head) kfree(f); } +static void fl_hw_destroy_filter(struct tcf_proto *tp, u64 cookie) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_flower_offload offload = {0}; + struct tc_to_netdev tc; + + if (!tc_should_offload(dev, 0)) + return; + + offload.command = TC_CLSFLOWER_DESTROY; + offload.cookie = cookie; + + tc.type = TC_SETUP_CLSFLOWER; + tc.cls_flower = &offload; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); +} + +static void fl_hw_replace_filter(struct tcf_proto *tp, + struct flow_dissector *dissector, + struct fl_flow_key *mask, + struct fl_flow_key *key, + struct tcf_exts *actions, + u64 cookie, u32 flags) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_flower_offload offload = {0}; + struct tc_to_netdev tc; + + if (!tc_should_offload(dev, flags)) + return; + + offload.command = TC_CLSFLOWER_REPLACE; + offload.cookie = cookie; + offload.dissector = dissector; + offload.mask = mask; + offload.key = key; + offload.exts = actions; + + tc.type = TC_SETUP_CLSFLOWER; + tc.cls_flower = &offload; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); +} + static bool fl_destroy(struct tcf_proto *tp, bool force) { struct cls_fl_head *head = rtnl_dereference(tp->root); @@ -174,6 +219,7 @@ static bool fl_destroy(struct tcf_proto *tp, bool force) return false; list_for_each_entry_safe(f, next, &head->filters, list) { + fl_hw_destroy_filter(tp, (u64)f); list_del_rcu(&f->list); call_rcu(&f->rcu, fl_destroy_filter); } @@ -459,6 +505,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_filter *fnew; struct nlattr *tb[TCA_FLOWER_MAX + 1]; struct fl_flow_mask mask = {}; + u32 flags = 0; int err; if (!tca[TCA_OPTIONS]) @@ -486,6 +533,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } fnew->handle = handle; + if (tb[TCA_FLOWER_FLAGS]) + flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); + err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); if (err) goto errout; @@ -498,9 +548,20 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, head->ht_params); if (err) goto errout; - if (fold) + + fl_hw_replace_filter(tp, + &head->dissector, + &mask.key, + &fnew->key, + &fnew->exts, + (u64)fnew, + flags); + + if (fold) { rhashtable_remove_fast(&head->ht, &fold->ht_node, head->ht_params); + fl_hw_destroy_filter(tp, (u64)fold); + } *arg = (unsigned long) fnew; @@ -527,6 +588,7 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg) rhashtable_remove_fast(&head->ht, &f->ht_node, head->ht_params); list_del_rcu(&f->list); + fl_hw_destroy_filter(tp, (u64)f); tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, fl_destroy_filter); return 0; -- cgit v1.2.3 From 4c656c13b254d598e83e586b7b4d36a2043dad85 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 8 Mar 2016 12:59:35 -0800 Subject: bridge: allow zero ageing time This fixes a regression in the bridge ageing time caused by: commit c62987bbd8a1 ("bridge: push bridge setting ageing_time down to switchdev") There are users of Linux bridge which use the feature that if ageing time is set to 0 it causes entries to never expire. See: https://www.linuxfoundation.org/collaborate/workgroups/networking/bridge For a pure software bridge, it is unnecessary for the code to have arbitrary restrictions on what values are allowable. Signed-off-by: Stephen Hemminger Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 4 ---- net/bridge/br_stp.c | 11 ++++++++--- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index a338a688ee4a..dcb89e3515db 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,10 +46,6 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) -/* values as per ieee8021QBridgeFdbAgingTime */ -#define BR_MIN_AGEING_TIME (10 * HZ) -#define BR_MAX_AGEING_TIME (1000000 * HZ) - #define BR_DEFAULT_AGEING_TIME (300 * HZ) extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index c22816a0b1b1..e23449094188 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -562,6 +562,14 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) } +/* Set time interval that dynamic forwarding entries live + * For pure software bridge, allow values outside the 802.1 + * standard specification for special cases: + * 0 - entry never ages (all permanant) + * 1 - entry disappears (no persistance) + * + * Offloaded switch entries maybe more restrictive + */ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) { struct switchdev_attr attr = { @@ -573,9 +581,6 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) unsigned long t = clock_t_to_jiffies(ageing_time); int err; - if (t < BR_MIN_AGEING_TIME || t > BR_MAX_AGEING_TIME) - return -ERANGE; - err = switchdev_port_attr_set(br->dev, &attr); if (err) return err; -- cgit v1.2.3 From 470c3822d2ab7fadcbb1ac317ef27b31caac370e Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 10 Mar 2016 13:58:58 +0100 Subject: phy: remove documentation of removed members of phy_device structure Commit e5a03bfd873c ("phy: Add an mdio_device structure") removed addr, bus and dev member of the phy_device structure. This patch remove the documentation about those members. Signed-off-by: LABBE Corentin Reviewed-by: Andrew Lunn Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index d6f3641e7933..2abd7918f64f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -327,8 +327,6 @@ struct phy_c45_device_ids { /* phy_device: An instance of a PHY * * drv: Pointer to the driver for this PHY instance - * bus: Pointer to the bus this PHY is on - * dev: driver model device structure for this PHY * phy_id: UID for this device found during discovery * c45_ids: 802.3-c45 Device Identifers if is_c45. * is_c45: Set to true if this phy uses clause 45 addressing. @@ -338,7 +336,6 @@ struct phy_c45_device_ids { * suspended: Set to true if this phy has been suspended successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. - * addr: Bus address of PHY * link_timeout: The number of timer firings to wait before the * giving up on the current attempt at acquiring a link * irq: IRQ number of the PHY's interrupt (-1 if none) -- cgit v1.2.3 From 3c17578473b9be5a6e7680a45ea97e1d56e13249 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 11 Mar 2016 18:07:32 +0100 Subject: net: add MACsec netdevice priv_flags and helper Signed-off-by: Sabrina Dubroca Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 41df0b450757..be693b34662f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1328,6 +1328,7 @@ struct net_device_ops { * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) + * @IFF_MACSEC: device is a MACsec device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1357,6 +1358,7 @@ enum netdev_priv_flags { IFF_TEAM = 1<<24, IFF_RXFH_CONFIGURED = 1<<25, IFF_PHONY_HEADROOM = 1<<26, + IFF_MACSEC = 1<<27, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1385,6 +1387,7 @@ enum netdev_priv_flags { #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE #define IFF_TEAM IFF_TEAM #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED +#define IFF_MACSEC IFF_MACSEC /** * struct net_device - The DEVICE structure. @@ -4045,6 +4048,11 @@ static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, skb->mac_len = mac_len; } +static inline bool netif_is_macsec(const struct net_device *dev) +{ + return dev->priv_flags & IFF_MACSEC; +} + static inline bool netif_is_macvlan(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; -- cgit v1.2.3 From f2900acea8018c4525ddaa86c7f7cd8afd3f0cc4 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Mon, 14 Mar 2016 09:39:02 +0100 Subject: bus: mvebu-mbus: provide api for obtaining IO and DRAM window information This commit enables finding appropriate mbus window and obtaining its target id and attribute for given physical address in two separate routines, both for IO and DRAM windows. This functionality is needed for Armada XP/38x Network Controller's Buffer Manager and PnC configuration. [gregory.clement@free-electrons.com: Fix size test for mvebu_mbus_get_dram_win_info] Signed-off-by: Marcin Wojtas [DRAM window information reference in LKv3.10] Signed-off-by: Evan Wang Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/bus/mvebu-mbus.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mbus.h | 3 +++ 2 files changed, 55 insertions(+) (limited to 'include/linux') diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index c43c3d2baf73..c2e52864bb03 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -948,6 +948,58 @@ void mvebu_mbus_get_pcie_io_aperture(struct resource *res) *res = mbus_state.pcie_io_aperture; } +int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr) +{ + const struct mbus_dram_target_info *dram; + int i; + + /* Get dram info */ + dram = mv_mbus_dram_info(); + if (!dram) { + pr_err("missing DRAM information\n"); + return -ENODEV; + } + + /* Try to find matching DRAM window for phyaddr */ + for (i = 0; i < dram->num_cs; i++) { + const struct mbus_dram_window *cs = dram->cs + i; + + if (cs->base <= phyaddr && + phyaddr <= (cs->base + cs->size - 1)) { + *target = dram->mbus_dram_target_id; + *attr = cs->mbus_attr; + return 0; + } + } + + pr_err("invalid dram address 0x%x\n", phyaddr); + return -EINVAL; +} +EXPORT_SYMBOL_GPL(mvebu_mbus_get_dram_win_info); + +int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size, u8 *target, + u8 *attr) +{ + int win; + + for (win = 0; win < mbus_state.soc->num_wins; win++) { + u64 wbase; + int enabled; + + mvebu_mbus_read_window(&mbus_state, win, &enabled, &wbase, + size, target, attr, NULL); + + if (!enabled) + continue; + + if (wbase <= phyaddr && phyaddr <= wbase + *size) + return win; + } + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(mvebu_mbus_get_io_win_info); + static __init int mvebu_mbus_debugfs_init(void) { struct mvebu_mbus_state *s = &mbus_state; diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 1f7bc630d225..ea34a867caa0 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -69,6 +69,9 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(vo int mvebu_mbus_save_cpu_target(u32 *store_addr); void mvebu_mbus_get_pcie_mem_aperture(struct resource *res); void mvebu_mbus_get_pcie_io_aperture(struct resource *res); +int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr); +int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size, u8 *target, + u8 *attr); int mvebu_mbus_add_window_remap_by_id(unsigned int target, unsigned int attribute, phys_addr_t base, size_t size, -- cgit v1.2.3 From a44d6eacdaf56f74fad699af7f4925a5f5ac0e7f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 14 Mar 2016 10:52:15 -0700 Subject: tcp: Add RFC4898 tcpEStatsPerfDataSegsOut/In Per RFC4898, they count segments sent/received containing a positive length data segment (that includes retransmission segments carrying data). Unlike tcpi_segs_out/in, tcpi_data_segs_out/in excludes segments carrying no data (e.g. pure ack). The patch also updates the segs_in in tcp_fastopen_add_skb() so that segs_in >= data_segs_in property is kept. Together with retransmission data, tcpi_data_segs_out gives a better signal on the rxmit rate. v6: Rebase on the latest net-next v5: Eric pointed out that checking skb->len is still needed in tcp_fastopen_add_skb() because skb can carry a FIN without data. Hence, instead of open coding segs_in and data_segs_in, tcp_segs_in() helper is used. Comment is added to the fastopen case to explain why segs_in has to be reset and tcp_segs_in() has to be called before __skb_pull(). v4: Add comment to the changes in tcp_fastopen_add_skb() and also add remark on this case in the commit message. v3: Add const modifier to the skb parameter in tcp_segs_in() v2: Rework based on recent fix by Eric: commit a9d99ce28ed3 ("tcp: fix tcpi_segs_in after connection establishment") Signed-off-by: Martin KaFai Lau Cc: Chris Rapier Cc: Eric Dumazet Cc: Marcelo Ricardo Leitner Cc: Neal Cardwell Cc: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++++ include/net/tcp.h | 10 ++++++++++ include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_fastopen.c | 8 ++++++++ net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 4 +++- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 34 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index bcbf51da4e1e..7be9b1242354 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -158,6 +158,9 @@ struct tcp_sock { u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn * total number of segments in. */ + u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. + */ u32 rcv_nxt; /* What we want to receive next */ u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ @@ -165,6 +168,9 @@ struct tcp_sock { u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut * The total number of segments sent. */ + u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. diff --git a/include/net/tcp.h b/include/net/tcp.h index 0302636af98c..c8dbd293daae 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1840,4 +1840,14 @@ static inline int tcp_inq(struct sock *sk) return answ; } +static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) +{ + u16 segs_in; + + segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tp->segs_in += segs_in; + if (skb->len > tcp_hdrlen(skb)) + tp->data_segs_in += segs_in; +} + #endif /* _TCP_H */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index fe95446e9abf..53e8e3fe6b1b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -199,6 +199,8 @@ struct tcp_info { __u32 tcpi_notsent_bytes; __u32 tcpi_min_rtt; + __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */ + __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a265f00b9df9..992b3103ec3e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2715,6 +2715,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_notsent_bytes = max(0, notsent_bytes); info->tcpi_min_rtt = tcp_min_rtt(tp); + info->tcpi_data_segs_in = tp->data_segs_in; + info->tcpi_data_segs_out = tp->data_segs_out; } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index fdb286ddba04..4fc0061bebf4 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -140,6 +140,14 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) return; skb_dst_drop(skb); + /* segs_in has been initialized to 1 in tcp_create_openreq_child(). + * Hence, reset segs_in to 0 before calling tcp_segs_in() + * to avoid double counting. Also, tcp_segs_in() expects + * skb->len to include the tcp_hdrlen. Hence, it should + * be called before __skb_pull(). + */ + tp->segs_in = 0; + tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); skb_set_owner_r(skb, sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4c8d58dfac9b..0b02ef773705 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1650,7 +1650,7 @@ process: sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); - tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ae90e4b34bd3..acb366dd61e6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -812,7 +812,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; - tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tcp_segs_in(tcp_sk(child), skb); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7d2c7a400456..7d2dc015cd19 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1003,8 +1003,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); - if (skb->len != tcp_header_size) + if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); + tp->data_segs_out += tcp_skb_pcount(skb); + } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33f2820181f9..9c16565b70cc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1443,7 +1443,7 @@ process: sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); - tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) -- cgit v1.2.3 From 5bcbe0f35fb13e31fdd0b2dc9695f19ab0208207 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 12 Mar 2016 00:01:40 +0100 Subject: phy: fixed: Fix removal of phys. The fixed phys delete function simply removed the fixed phy from the internal linked list and freed the memory. It however did not unregister the associated phy device. This meant it was still possible to find the phy device on the mdio bus. Make fixed_phy_del() an internal function and add a fixed_phy_unregister() to unregisters the phy device and then uses fixed_phy_del() to free resources. Modify DSA to use this new API function, so we don't leak phys. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/fixed_phy.c | 11 +++++++++-- include/linux/phy_fixed.h | 5 ++--- net/dsa/dsa.c | 4 +--- 3 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index ab9c473d75ea..fc07a8866020 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -285,7 +285,7 @@ err_regs: } EXPORT_SYMBOL_GPL(fixed_phy_add); -void fixed_phy_del(int phy_addr) +static void fixed_phy_del(int phy_addr) { struct fixed_mdio_bus *fmb = &platform_fmb; struct fixed_phy *fp, *tmp; @@ -300,7 +300,6 @@ void fixed_phy_del(int phy_addr) } } } -EXPORT_SYMBOL_GPL(fixed_phy_del); static int phy_fixed_addr; static DEFINE_SPINLOCK(phy_fixed_addr_lock); @@ -371,6 +370,14 @@ struct phy_device *fixed_phy_register(unsigned int irq, } EXPORT_SYMBOL_GPL(fixed_phy_register); +void fixed_phy_unregister(struct phy_device *phy) +{ + phy_device_remove(phy); + + fixed_phy_del(phy->mdio.addr); +} +EXPORT_SYMBOL_GPL(fixed_phy_unregister); + static int __init fixed_mdio_bus_init(void) { struct fixed_mdio_bus *fmb = &platform_fmb; diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 2400d2ea4f34..1d41ec44e39d 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -19,7 +19,7 @@ extern struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, int link_gpio, struct device_node *np); -extern void fixed_phy_del(int phy_addr); +extern void fixed_phy_unregister(struct phy_device *phydev); extern int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, struct fixed_phy_status *)); @@ -40,9 +40,8 @@ static inline struct phy_device *fixed_phy_register(unsigned int irq, { return ERR_PTR(-ENODEV); } -static inline int fixed_phy_del(int phy_addr) +static inline void fixed_phy_unregister(struct phy_device *phydev) { - return -ENODEV; } static inline int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index f100f340d93f..c28c47463b7e 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -447,11 +447,9 @@ static void dsa_switch_destroy(struct dsa_switch *ds) if (of_phy_is_fixed_link(port_dn)) { phydev = of_phy_find_device(port_dn); if (phydev) { - int addr = phydev->mdio.addr; - phy_device_free(phydev); of_node_put(port_dn); - fixed_phy_del(addr); + fixed_phy_unregister(phydev); } } } -- cgit v1.2.3