diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index a46d78583ae1..7d8dc93fe2eb 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -588,9 +588,6 @@ tcp_limit_output_bytes - INTEGER typical pfifo_fast qdiscs. tcp_limit_output_bytes limits the number of bytes on qdisc or device to reduce artificial RTT/cwnd and reduce bufferbloat. - Note: For GSO/TSO enabled flows, we try to have at least two - packets in flight. Reducing tcp_limit_output_bytes might also - reduce the size of individual GSO packet (64KB being the max) Default: 131072 tcp_challenge_ack_limit - INTEGER diff --git a/Makefile b/Makefile index b28bc57d1769..3b7165eb4734 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 12 -SUBLEVEL = 3 +SUBLEVEL = 4 EXTRAVERSION = NAME = One Giant Leap for Frogkind diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 516593e1ce33..26328e800869 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -788,5 +788,7 @@ void bpf_jit_free(struct sk_filter *fp) if (fp->bpf_func != sk_run_filter) { INIT_WORK(&fp->work, bpf_jit_free_deferred); schedule_work(&fp->work); + } else { + kfree(fp); } } diff --git a/block/blk-core.c b/block/blk-core.c index 0c611d89d748..fce4b9387f36 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -741,9 +741,17 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, q->sg_reserved_size = INT_MAX; + /* Protect q->elevator from elevator_change */ + mutex_lock(&q->sysfs_lock); + /* init elevator */ - if (elevator_init(q, NULL)) + if (elevator_init(q, NULL)) { + mutex_unlock(&q->sysfs_lock); return NULL; + } + + mutex_unlock(&q->sysfs_lock); + return q; } EXPORT_SYMBOL(blk_init_allocated_queue); diff --git a/block/elevator.c b/block/elevator.c index 2bcbd8cc14d4..b7ff2861b6bd 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -186,6 +186,12 @@ int elevator_init(struct request_queue *q, char *name) struct elevator_type *e = NULL; int err; + /* + * q->sysfs_lock must be held to provide mutual exclusion between + * elevator_switch() and here. + */ + lockdep_assert_held(&q->sysfs_lock); + if (unlikely(q->elevator)) return 0; @@ -959,7 +965,7 @@ fail_init: /* * Switch this queue to the given IO scheduler. */ -int elevator_change(struct request_queue *q, const char *name) +static int __elevator_change(struct request_queue *q, const char *name) { char elevator_name[ELV_NAME_MAX]; struct elevator_type *e; @@ -981,6 +987,18 @@ int elevator_change(struct request_queue *q, const char *name) return elevator_switch(q, e); } + +int elevator_change(struct request_queue *q, const char *name) +{ + int ret; + + /* Protect q->elevator from elevator_init() */ + mutex_lock(&q->sysfs_lock); + ret = __elevator_change(q, name); + mutex_unlock(&q->sysfs_lock); + + return ret; +} EXPORT_SYMBOL(elevator_change); ssize_t elv_iosched_store(struct request_queue *q, const char *name, @@ -991,7 +1009,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name, if (!q->elevator) return count; - ret = elevator_change(q, name); + ret = __elevator_change(q, name); if (!ret) return count; diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 0262210cad38..850246206b12 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -114,6 +114,9 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, struct hash_ctx *ctx = ask->private; int err; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + lock_sock(sk); sg_init_table(ctx->sgl.sg, 1); sg_set_page(ctx->sgl.sg, page, size, offset); @@ -161,8 +164,6 @@ static int hash_recvmsg(struct kiocb *unused, struct socket *sock, else if (len < ds) msg->msg_flags |= MSG_TRUNC; - msg->msg_namelen = 0; - lock_sock(sk); if (ctx->more) { ctx->more = 0; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index a1c4f0a55583..a19c027b29bd 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -378,6 +378,9 @@ static ssize_t skcipher_sendpage(struct socket *sock, struct page *page, struct skcipher_sg_list *sgl; int err = -EINVAL; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + lock_sock(sk); if (!ctx->more && ctx->used) goto unlock; @@ -432,7 +435,6 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock, long copied = 0; lock_sock(sk); - msg->msg_namelen = 0; for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0; iovlen--, iov++) { unsigned long seglen = iov->iov_len; diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 272f00927761..1bdf104e90bb 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -3511,7 +3511,7 @@ static int init_card(struct atm_dev *dev) tmp = dev_get_by_name(&init_net, tname); /* jhs: was "tmp = dev_get(tname);" */ if (tmp) { memcpy(card->atmdev->esi, tmp->dev_addr, 6); - + dev_put(tmp); printk("%s: ESI %pM\n", card->name, card->atmdev->esi); } /* diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index c73fc2b74de2..18c5b9b16645 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -32,11 +32,23 @@ #include #include -#include - #include -#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event)) +/* + * Size of a cn_msg followed by a proc_event structure. Since the + * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we + * add one 4-byte word to the size here, and then start the actual + * cn_msg structure 4 bytes into the stack buffer. The result is that + * the immediately following proc_event structure is aligned to 8 bytes. + */ +#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4) + +/* See comment above; we test our assumption about sizeof struct cn_msg here. */ +static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer) +{ + BUILD_BUG_ON(sizeof(struct cn_msg) != 20); + return (struct cn_msg *)(buffer + 4); +} static atomic_t proc_event_num_listeners = ATOMIC_INIT(0); static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; @@ -56,19 +68,19 @@ void proc_fork_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct timespec ts; struct task_struct *parent; if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->what = PROC_EVENT_FORK; rcu_read_lock(); parent = rcu_dereference(task->real_parent); @@ -91,17 +103,17 @@ void proc_exec_connector(struct task_struct *task) struct cn_msg *msg; struct proc_event *ev; struct timespec ts; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->what = PROC_EVENT_EXEC; ev->event_data.exec.process_pid = task->pid; ev->event_data.exec.process_tgid = task->tgid; @@ -117,14 +129,14 @@ void proc_id_connector(struct task_struct *task, int which_id) { struct cn_msg *msg; struct proc_event *ev; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct timespec ts; const struct cred *cred; if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->what = which_id; @@ -145,7 +157,7 @@ void proc_id_connector(struct task_struct *task, int which_id) rcu_read_unlock(); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ @@ -159,17 +171,17 @@ void proc_sid_connector(struct task_struct *task) struct cn_msg *msg; struct proc_event *ev; struct timespec ts; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->what = PROC_EVENT_SID; ev->event_data.sid.process_pid = task->pid; ev->event_data.sid.process_tgid = task->tgid; @@ -186,17 +198,17 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) struct cn_msg *msg; struct proc_event *ev; struct timespec ts; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->what = PROC_EVENT_PTRACE; ev->event_data.ptrace.process_pid = task->pid; ev->event_data.ptrace.process_tgid = task->tgid; @@ -221,17 +233,17 @@ void proc_comm_connector(struct task_struct *task) struct cn_msg *msg; struct proc_event *ev; struct timespec ts; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->what = PROC_EVENT_COMM; ev->event_data.comm.process_pid = task->pid; ev->event_data.comm.process_tgid = task->tgid; @@ -248,18 +260,18 @@ void proc_coredump_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct timespec ts; if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; ev->event_data.coredump.process_tgid = task->tgid; @@ -275,18 +287,18 @@ void proc_exit_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct timespec ts; if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->what = PROC_EVENT_EXIT; ev->event_data.exit.process_pid = task->pid; ev->event_data.exit.process_tgid = task->tgid; @@ -312,18 +324,18 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) { struct cn_msg *msg; struct proc_event *ev; - __u8 buffer[CN_PROC_MSG_SIZE]; + __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct timespec ts; if (atomic_read(&proc_event_num_listeners) < 1) return; - msg = (struct cn_msg *)buffer; + msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); msg->seq = rcvd_seq; ktime_get_ts(&ts); /* get high res monotonic timestamp */ - put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); + ev->timestamp_ns = timespec_to_ns(&ts); ev->cpu = -1; ev->what = PROC_EVENT_NONE; ev->event_data.ack.err = err; diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c index 06022e3b9c3b..615c5b290e78 100644 --- a/drivers/gpu/drm/radeon/r600_hdmi.c +++ b/drivers/gpu/drm/radeon/r600_hdmi.c @@ -24,6 +24,7 @@ * Authors: Christian König */ #include +#include #include #include #include "radeon.h" @@ -57,35 +58,57 @@ enum r600_hdmi_iec_status_bits { static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = { /* 32kHz 44.1kHz 48kHz */ /* Clock N CTS N CTS N CTS */ - { 25175, 4576, 28125, 7007, 31250, 6864, 28125 }, /* 25,20/1.001 MHz */ + { 25175, 4096, 25175, 28224, 125875, 6144, 25175 }, /* 25,20/1.001 MHz */ { 25200, 4096, 25200, 6272, 28000, 6144, 25200 }, /* 25.20 MHz */ { 27000, 4096, 27000, 6272, 30000, 6144, 27000 }, /* 27.00 MHz */ { 27027, 4096, 27027, 6272, 30030, 6144, 27027 }, /* 27.00*1.001 MHz */ { 54000, 4096, 54000, 6272, 60000, 6144, 54000 }, /* 54.00 MHz */ { 54054, 4096, 54054, 6272, 60060, 6144, 54054 }, /* 54.00*1.001 MHz */ - { 74176, 11648, 210937, 17836, 234375, 11648, 140625 }, /* 74.25/1.001 MHz */ + { 74176, 4096, 74176, 5733, 75335, 6144, 74176 }, /* 74.25/1.001 MHz */ { 74250, 4096, 74250, 6272, 82500, 6144, 74250 }, /* 74.25 MHz */ - { 148352, 11648, 421875, 8918, 234375, 5824, 140625 }, /* 148.50/1.001 MHz */ + { 148352, 4096, 148352, 5733, 150670, 6144, 148352 }, /* 148.50/1.001 MHz */ { 148500, 4096, 148500, 6272, 165000, 6144, 148500 }, /* 148.50 MHz */ - { 0, 4096, 0, 6272, 0, 6144, 0 } /* Other */ }; + /* - * calculate CTS value if it's not found in the table + * calculate CTS and N values if they are not found in the table */ -static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq) +static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int *N, int freq) { - u64 n; - u32 d; - - if (*CTS == 0) { - n = (u64)clock * (u64)N * 1000ULL; - d = 128 * freq; - do_div(n, d); - *CTS = n; - } - DRM_DEBUG("Using ACR timing N=%d CTS=%d for frequency %d\n", - N, *CTS, freq); + int n, cts; + unsigned long div, mul; + + /* Safe, but overly large values */ + n = 128 * freq; + cts = clock * 1000; + + /* Smallest valid fraction */ + div = gcd(n, cts); + + n /= div; + cts /= div; + + /* + * The optimal N is 128*freq/1000. Calculate the closest larger + * value that doesn't truncate any bits. + */ + mul = ((128*freq/1000) + (n-1))/n; + + n *= mul; + cts *= mul; + + /* Check that we are in spec (not always possible) */ + if (n < (128*freq/1500)) + printk(KERN_WARNING "Calculated ACR N value is too small. You may experience audio problems.\n"); + if (n > (128*freq/300)) + printk(KERN_WARNING "Calculated ACR N value is too large. You may experience audio problems.\n"); + + *N = n; + *CTS = cts; + + DRM_DEBUG("Calculated ACR timing N=%d CTS=%d for frequency %d\n", + *N, *CTS, freq); } struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock) @@ -93,15 +116,16 @@ struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock) struct radeon_hdmi_acr res; u8 i; - for (i = 0; r600_hdmi_predefined_acr[i].clock != clock && - r600_hdmi_predefined_acr[i].clock != 0; i++) - ; - res = r600_hdmi_predefined_acr[i]; + /* Precalculated values for common clocks */ + for (i = 0; i < ARRAY_SIZE(r600_hdmi_predefined_acr); i++) { + if (r600_hdmi_predefined_acr[i].clock == clock) + return r600_hdmi_predefined_acr[i]; + } - /* In case some CTS are missing */ - r600_hdmi_calc_cts(clock, &res.cts_32khz, res.n_32khz, 32000); - r600_hdmi_calc_cts(clock, &res.cts_44_1khz, res.n_44_1khz, 44100); - r600_hdmi_calc_cts(clock, &res.cts_48khz, res.n_48khz, 48000); + /* And odd clocks get manually calculated */ + r600_hdmi_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000); + r600_hdmi_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100); + r600_hdmi_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000); return res; } diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c index f042a6cf8b18..55e4920f967b 100644 --- a/drivers/hid/hid-elo.c +++ b/drivers/hid/hid-elo.c @@ -181,7 +181,40 @@ fail: */ static bool elo_broken_firmware(struct usb_device *dev) { - return use_fw_quirk && le16_to_cpu(dev->descriptor.bcdDevice) == 0x10d; + struct usb_device *hub = dev->parent; + struct usb_device *child = NULL; + u16 fw_lvl = le16_to_cpu(dev->descriptor.bcdDevice); + u16 child_vid, child_pid; + int i; + + if (!use_fw_quirk) + return false; + if (fw_lvl != 0x10d) + return false; + + /* iterate sibling devices of the touch controller */ + usb_hub_for_each_child(hub, i, child) { + child_vid = le16_to_cpu(child->descriptor.idVendor); + child_pid = le16_to_cpu(child->descriptor.idProduct); + + /* + * If one of the devices below is present attached as a sibling of + * the touch controller then this is a newer IBM 4820 monitor that + * does not need the IBM-requested workaround if fw level is + * 0x010d - aka 'M'. + * No other HW can have this combination. + */ + if (child_vid==0x04b3) { + switch (child_pid) { + case 0x4676: /* 4820 21x Video */ + case 0x4677: /* 4820 51x Video */ + case 0x4678: /* 4820 2Lx Video */ + case 0x4679: /* 4820 5Lx Video */ + return false; + } + } + } + return true; } static int elo_probe(struct hid_device *hdev, const struct hid_device_id *id) diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c index 1bfd292cac8f..06eb45fa6331 100644 --- a/drivers/hid/hid-lg.c +++ b/drivers/hid/hid-lg.c @@ -47,6 +47,7 @@ #define DFP_RDESC_ORIG_SIZE 97 #define FV_RDESC_ORIG_SIZE 130 #define MOMO_RDESC_ORIG_SIZE 87 +#define MOMO2_RDESC_ORIG_SIZE 87 /* Fixed report descriptors for Logitech Driving Force (and Pro) * wheel controllers @@ -284,6 +285,54 @@ static __u8 momo_rdesc_fixed[] = { 0xC0 /* End Collection */ }; +static __u8 momo2_rdesc_fixed[] = { +0x05, 0x01, /* Usage Page (Desktop), */ +0x09, 0x04, /* Usage (Joystik), */ +0xA1, 0x01, /* Collection (Application), */ +0xA1, 0x02, /* Collection (Logical), */ +0x95, 0x01, /* Report Count (1), */ +0x75, 0x0A, /* Report Size (10), */ +0x15, 0x00, /* Logical Minimum (0), */ +0x26, 0xFF, 0x03, /* Logical Maximum (1023), */ +0x35, 0x00, /* Physical Minimum (0), */ +0x46, 0xFF, 0x03, /* Physical Maximum (1023), */ +0x09, 0x30, /* Usage (X), */ +0x81, 0x02, /* Input (Variable), */ +0x95, 0x0A, /* Report Count (10), */ +0x75, 0x01, /* Report Size (1), */ +0x25, 0x01, /* Logical Maximum (1), */ +0x45, 0x01, /* Physical Maximum (1), */ +0x05, 0x09, /* Usage Page (Button), */ +0x19, 0x01, /* Usage Minimum (01h), */ +0x29, 0x0A, /* Usage Maximum (0Ah), */ +0x81, 0x02, /* Input (Variable), */ +0x06, 0x00, 0xFF, /* Usage Page (FF00h), */ +0x09, 0x00, /* Usage (00h), */ +0x95, 0x04, /* Report Count (4), */ +0x81, 0x02, /* Input (Variable), */ +0x95, 0x01, /* Report Count (1), */ +0x75, 0x08, /* Report Size (8), */ +0x26, 0xFF, 0x00, /* Logical Maximum (255), */ +0x46, 0xFF, 0x00, /* Physical Maximum (255), */ +0x09, 0x01, /* Usage (01h), */ +0x81, 0x02, /* Input (Variable), */ +0x05, 0x01, /* Usage Page (Desktop), */ +0x09, 0x31, /* Usage (Y), */ +0x81, 0x02, /* Input (Variable), */ +0x09, 0x32, /* Usage (Z), */ +0x81, 0x02, /* Input (Variable), */ +0x06, 0x00, 0xFF, /* Usage Page (FF00h), */ +0x09, 0x00, /* Usage (00h), */ +0x81, 0x02, /* Input (Variable), */ +0xC0, /* End Collection, */ +0xA1, 0x02, /* Collection (Logical), */ +0x09, 0x02, /* Usage (02h), */ +0x95, 0x07, /* Report Count (7), */ +0x91, 0x02, /* Output (Variable), */ +0xC0, /* End Collection, */ +0xC0 /* End Collection */ +}; + /* * Certain Logitech keyboards send in report #3 keys which are far * above the logical maximum described in descriptor. This extends @@ -343,6 +392,15 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc, } break; + case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2: + if (*rsize == MOMO2_RDESC_ORIG_SIZE) { + hid_info(hdev, + "fixing up Logitech Momo Racing Force (Black) report descriptor\n"); + rdesc = momo2_rdesc_fixed; + *rsize = sizeof(momo2_rdesc_fixed); + } + break; + case USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL: if (*rsize == FV_RDESC_ORIG_SIZE) { hid_info(hdev, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 15e9b57e9cf0..40203ada635e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -782,7 +782,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, int offset; BUG_ON(!domain->pgd); - BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width); + + if (addr_width < BITS_PER_LONG && pfn >> addr_width) + /* Address beyond IOMMU's addressing capabilities. */ + return NULL; + parent = domain->pgd; while (level > 0) { diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index f71673dbb23d..b97d70b1abe0 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -525,12 +525,13 @@ static int __init intel_irq_remapping_supported(void) if (disable_irq_remap) return 0; if (irq_remap_broken) { - WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND, - "This system BIOS has enabled interrupt remapping\n" - "on a chipset that contains an erratum making that\n" - "feature unstable. To maintain system stability\n" - "interrupt remapping is being disabled. Please\n" - "contact your BIOS vendor for an update\n"); + printk(KERN_WARNING + "This system BIOS has enabled interrupt remapping\n" + "on a chipset that contains an erratum making that\n" + "feature unstable. To maintain system stability\n" + "interrupt remapping is being disabled. Please\n" + "contact your BIOS vendor for an update\n"); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); disable_irq_remap = 1; return 0; } diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c index baf2686aa8eb..02125e6a9109 100644 --- a/drivers/isdn/isdnloop/isdnloop.c +++ b/drivers/isdn/isdnloop/isdnloop.c @@ -1083,8 +1083,10 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp) spin_unlock_irqrestore(&card->isdnloop_lock, flags); return -ENOMEM; } - for (i = 0; i < 3; i++) - strcpy(card->s0num[i], sdef.num[i]); + for (i = 0; i < 3; i++) { + strlcpy(card->s0num[i], sdef.num[i], + sizeof(card->s0num[0])); + } break; case ISDN_PTYPE_1TR6: if (isdnloop_fake(card, "DRV1.04TC-1TR6-CAPI-CNS-BASIS-29.11.95", @@ -1097,7 +1099,7 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp) spin_unlock_irqrestore(&card->isdnloop_lock, flags); return -ENOMEM; } - strcpy(card->s0num[0], sdef.num[0]); + strlcpy(card->s0num[0], sdef.num[0], sizeof(card->s0num[0])); card->s0num[1][0] = '\0'; card->s0num[2][0] = '\0'; break; diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index e47dcb9d1e91..5cefb479c707 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -117,7 +117,6 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock, { struct sk_buff *skb; struct sock *sk = sock->sk; - struct sockaddr_mISDN *maddr; int copied, err; @@ -135,9 +134,9 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - if (msg->msg_namelen >= sizeof(struct sockaddr_mISDN)) { - msg->msg_namelen = sizeof(struct sockaddr_mISDN); - maddr = (struct sockaddr_mISDN *)msg->msg_name; + if (msg->msg_name) { + struct sockaddr_mISDN *maddr = msg->msg_name; + maddr->family = AF_ISDN; maddr->dev = _pms(sk)->dev->id; if ((sk->sk_protocol == ISDN_P_LAPD_TE) || @@ -150,11 +149,7 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock, maddr->sapi = _pms(sk)->ch.addr & 0xFF; maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xFF; } - } else { - if (msg->msg_namelen) - printk(KERN_WARNING "%s: too small namelen %d\n", - __func__, msg->msg_namelen); - msg->msg_namelen = 0; + msg->msg_namelen = sizeof(*maddr); } copied = skb->len + MISDN_HEADER_LEN; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e4109f618c7b..8a0665d04567 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5214,15 +5214,18 @@ raid5_show_group_thread_cnt(struct mddev *mddev, char *page) return 0; } -static int alloc_thread_groups(struct r5conf *conf, int cnt); +static int alloc_thread_groups(struct r5conf *conf, int cnt, + int *group_cnt, + int *worker_cnt_per_group, + struct r5worker_group **worker_groups); static ssize_t raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf = mddev->private; unsigned long new; int err; - struct r5worker_group *old_groups; - int old_group_cnt; + struct r5worker_group *new_groups, *old_groups; + int group_cnt, worker_cnt_per_group; if (len >= PAGE_SIZE) return -EINVAL; @@ -5238,17 +5241,19 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) mddev_suspend(mddev); old_groups = conf->worker_groups; - old_group_cnt = conf->worker_cnt_per_group; - if (old_groups) flush_workqueue(raid5_wq); - conf->worker_groups = NULL; - err = alloc_thread_groups(conf, new); - if (err) { - conf->worker_groups = old_groups; - conf->worker_cnt_per_group = old_group_cnt; - } else { + err = alloc_thread_groups(conf, new, + &group_cnt, &worker_cnt_per_group, + &new_groups); + if (!err) { + spin_lock_irq(&conf->device_lock); + conf->group_cnt = group_cnt; + conf->worker_cnt_per_group = worker_cnt_per_group; + conf->worker_groups = new_groups; + spin_unlock_irq(&conf->device_lock); + if (old_groups) kfree(old_groups[0].workers); kfree(old_groups); @@ -5278,33 +5283,36 @@ static struct attribute_group raid5_attrs_group = { .attrs = raid5_attrs, }; -static int alloc_thread_groups(struct r5conf *conf, int cnt) +static int alloc_thread_groups(struct r5conf *conf, int cnt, + int *group_cnt, + int *worker_cnt_per_group, + struct r5worker_group **worker_groups) { int i, j; ssize_t size; struct r5worker *workers; - conf->worker_cnt_per_group = cnt; + *worker_cnt_per_group = cnt; if (cnt == 0) { - conf->worker_groups = NULL; + *group_cnt = 0; + *worker_groups = NULL; return 0; } - conf->group_cnt = num_possible_nodes(); + *group_cnt = num_possible_nodes(); size = sizeof(struct r5worker) * cnt; - workers = kzalloc(size * conf->group_cnt, GFP_NOIO); - conf->worker_groups = kzalloc(sizeof(struct r5worker_group) * - conf->group_cnt, GFP_NOIO); - if (!conf->worker_groups || !workers) { + workers = kzalloc(size * *group_cnt, GFP_NOIO); + *worker_groups = kzalloc(sizeof(struct r5worker_group) * + *group_cnt, GFP_NOIO); + if (!*worker_groups || !workers) { kfree(workers); - kfree(conf->worker_groups); - conf->worker_groups = NULL; + kfree(*worker_groups); return -ENOMEM; } - for (i = 0; i < conf->group_cnt; i++) { + for (i = 0; i < *group_cnt; i++) { struct r5worker_group *group; - group = &conf->worker_groups[i]; + group = &(*worker_groups)[i]; INIT_LIST_HEAD(&group->handle_list); group->conf = conf; group->workers = workers + i * cnt; @@ -5462,6 +5470,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) struct md_rdev *rdev; struct disk_info *disk; char pers_name[6]; + int group_cnt, worker_cnt_per_group; + struct r5worker_group *new_group; if (mddev->new_level != 5 && mddev->new_level != 4 @@ -5496,7 +5506,12 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (conf == NULL) goto abort; /* Don't enable multi-threading by default*/ - if (alloc_thread_groups(conf, 0)) + if (!alloc_thread_groups(conf, 0, &group_cnt, &worker_cnt_per_group, + &new_group)) { + conf->group_cnt = group_cnt; + conf->worker_cnt_per_group = worker_cnt_per_group; + conf->worker_groups = new_group; + } else goto abort; spin_lock_init(&conf->device_lock); seqcount_init(&conf->gen_lock); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e883bfe2e727..dd8057d0bae7 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3395,20 +3395,20 @@ static void bond_set_rx_mode(struct net_device *bond_dev) struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - ASSERT_RTNL(); - + rcu_read_lock(); if (USES_PRIMARY(bond->params.mode)) { - slave = rtnl_dereference(bond->curr_active_slave); + slave = rcu_dereference(bond->curr_active_slave); if (slave) { dev_uc_sync(slave->dev, bond_dev); dev_mc_sync(slave->dev, bond_dev); } } else { - bond_for_each_slave(bond, slave) { + bond_for_each_slave_rcu(bond, slave) { dev_uc_sync_multiple(slave->dev, bond_dev); dev_mc_sync_multiple(slave->dev, bond_dev); } } + rcu_read_unlock(); } static int bond_neigh_init(struct neighbour *n) diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index c29b836749b6..b60f95b2196e 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -587,8 +587,9 @@ static ssize_t bonding_store_arp_interval(struct device *d, goto out; } if (bond->params.mode == BOND_MODE_ALB || - bond->params.mode == BOND_MODE_TLB) { - pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n", + bond->params.mode == BOND_MODE_TLB || + bond->params.mode == BOND_MODE_8023AD) { + pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n", bond->dev->name, bond->dev->name); ret = -EINVAL; goto out; @@ -759,6 +760,8 @@ static ssize_t bonding_store_downdelay(struct device *d, int new_value, ret = count; struct bonding *bond = to_bond(d); + if (!rtnl_trylock()) + return restart_syscall(); if (!(bond->params.miimon)) { pr_err("%s: Unable to set down delay as MII monitoring is disabled\n", bond->dev->name); @@ -792,6 +795,7 @@ static ssize_t bonding_store_downdelay(struct device *d, } out: + rtnl_unlock(); return ret; } static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR, @@ -814,6 +818,8 @@ static ssize_t bonding_store_updelay(struct device *d, int new_value, ret = count; struct bonding *bond = to_bond(d); + if (!rtnl_trylock()) + return restart_syscall(); if (!(bond->params.miimon)) { pr_err("%s: Unable to set up delay as MII monitoring is disabled\n", bond->dev->name); @@ -847,6 +853,7 @@ static ssize_t bonding_store_updelay(struct device *d, } out: + rtnl_unlock(); return ret; } static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR, diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 2c210ec35d59..f2f6d85f3788 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2890,6 +2890,8 @@ static int mv643xx_eth_probe(struct platform_device *pdev) PHY_INTERFACE_MODE_GMII); if (!mp->phy) err = -ENODEV; + else + phy_addr_set(mp, mp->phy->addr); } else if (pd->phy_addr != MV643XX_ETH_PHY_NONE) { mp->phy = phy_scan(mp, pd->phy_addr); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index a071cda2dd04..0d087b03a7b0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -264,6 +264,10 @@ static void *mlx4_en_add(struct mlx4_dev *dev) mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) mdev->port_cnt++; + /* Initialize time stamp mechanism */ + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) + mlx4_en_init_timestamp(mdev); + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { if (!dev->caps.comp_pool) { mdev->profile.prof[i].rx_ring_num = @@ -301,10 +305,6 @@ static void *mlx4_en_add(struct mlx4_dev *dev) mdev->pndev[i] = NULL; } - /* Initialize time stamp mechanism */ - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - mlx4_en_init_timestamp(mdev); - return mdev; err_mr: diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index d2e591955bdd..0095af50fb81 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -678,9 +678,6 @@ static void cp_tx (struct cp_private *cp) le32_to_cpu(txd->opts1) & 0xffff, PCI_DMA_TODEVICE); - bytes_compl += skb->len; - pkts_compl++; - if (status & LastFrag) { if (status & (TxError | TxFIFOUnder)) { netif_dbg(cp, tx_err, cp->dev, @@ -702,6 +699,8 @@ static void cp_tx (struct cp_private *cp) netif_dbg(cp, tx_done, cp->dev, "tx done, slot %d\n", tx_tail); } + bytes_compl += skb->len; + pkts_compl++; dev_kfree_skb_irq(skb); } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 3397cee89777..fb3f8dc1b8b1 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -3465,6 +3465,11 @@ static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp) rtl_writephy(tp, 0x14, 0x9065); rtl_writephy(tp, 0x14, 0x1065); + /* Check ALDPS bit, disable it if enabled */ + rtl_writephy(tp, 0x1f, 0x0a43); + if (rtl_readphy(tp, 0x10) & 0x0004) + rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0004); + rtl_writephy(tp, 0x1f, 0x0000); } diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 98eedb90cdc3..fc3e25ca7135 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -46,7 +46,8 @@ defined(CONFIG_MACH_LITTLETON) ||\ defined(CONFIG_MACH_ZYLONITE2) ||\ defined(CONFIG_ARCH_VIPER) ||\ - defined(CONFIG_MACH_STARGATE2) + defined(CONFIG_MACH_STARGATE2) ||\ + defined(CONFIG_ARCH_VERSATILE) #include @@ -154,6 +155,8 @@ static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg) #define SMC_outl(v, a, r) writel(v, (a) + (r)) #define SMC_insl(a, r, p, l) readsl((a) + (r), p, l) #define SMC_outsl(a, r, p, l) writesl((a) + (r), p, l) +#define SMC_insw(a, r, p, l) readsw((a) + (r), p, l) +#define SMC_outsw(a, r, p, l) writesw((a) + (r), p, l) #define SMC_IRQ_FLAGS (-1) /* from resource */ /* We actually can't write halfwords properly if not word aligned */ @@ -206,23 +209,6 @@ SMC_outw(u16 val, void __iomem *ioaddr, int reg) #define RPC_LSA_DEFAULT RPC_LED_TX_RX #define RPC_LSB_DEFAULT RPC_LED_100_10 -#elif defined(CONFIG_ARCH_VERSATILE) - -#define SMC_CAN_USE_8BIT 1 -#define SMC_CAN_USE_16BIT 1 -#define SMC_CAN_USE_32BIT 1 -#define SMC_NOWAIT 1 - -#define SMC_inb(a, r) readb((a) + (r)) -#define SMC_inw(a, r) readw((a) + (r)) -#define SMC_inl(a, r) readl((a) + (r)) -#define SMC_outb(v, a, r) writeb(v, (a) + (r)) -#define SMC_outw(v, a, r) writew(v, (a) + (r)) -#define SMC_outl(v, a, r) writel(v, (a) + (r)) -#define SMC_insl(a, r, p, l) readsl((a) + (r), p, l) -#define SMC_outsl(a, r, p, l) writesl((a) + (r), p, l) -#define SMC_IRQ_FLAGS (-1) /* from resource */ - #elif defined(CONFIG_MN10300) /* diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index d022bf936572..ad61d26a44f3 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -2172,16 +2172,13 @@ static int velocity_poll(struct napi_struct *napi, int budget) unsigned int rx_done; unsigned long flags; - spin_lock_irqsave(&vptr->lock, flags); /* * Do rx and tx twice for performance (taken from the VIA * out-of-tree driver). */ - rx_done = velocity_rx_srv(vptr, budget / 2); - velocity_tx_srv(vptr); - rx_done += velocity_rx_srv(vptr, budget - rx_done); + rx_done = velocity_rx_srv(vptr, budget); + spin_lock_irqsave(&vptr->lock, flags); velocity_tx_srv(vptr); - /* If budget not fully consumed, exit the polling mode */ if (rx_done < budget) { napi_complete(napi); @@ -2342,6 +2339,8 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu) if (ret < 0) goto out_free_tmp_vptr_1; + napi_disable(&vptr->napi); + spin_lock_irqsave(&vptr->lock, flags); netif_stop_queue(dev); @@ -2362,6 +2361,8 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu) velocity_give_many_rx_descs(vptr); + napi_enable(&vptr->napi); + mac_enable_int(vptr->mac_regs); netif_start_queue(dev); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 9dccb1edfd2a..dc76670c2f2a 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -628,6 +628,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, const struct iovec *iv, unsigned long total_len, size_t count, int noblock) { + int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN); struct sk_buff *skb; struct macvlan_dev *vlan; unsigned long len = total_len; @@ -670,6 +671,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN; + if (copylen > good_linear) + copylen = good_linear; linear = copylen; if (iov_pages(iv, vnet_hdr_len + copylen, count) <= MAX_SKB_FRAGS) @@ -678,7 +681,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (!zerocopy) { copylen = len; - linear = vnet_hdr.hdr_len; + if (vnet_hdr.hdr_len > good_linear) + linear = good_linear; + else + linear = vnet_hdr.hdr_len; } skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen, diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 5f66e30d9823..82ee6ed954cb 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -979,8 +979,6 @@ static int pppoe_recvmsg(struct kiocb *iocb, struct socket *sock, if (error < 0) goto end; - m->msg_namelen = 0; - if (skb) { total_len = min_t(size_t, total_len, skb->len); error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 50e43e64d51d..6327df255404 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1366,6 +1366,8 @@ static int team_user_linkup_option_get(struct team *team, return 0; } +static void __team_carrier_check(struct team *team); + static int team_user_linkup_option_set(struct team *team, struct team_gsetter_ctx *ctx) { @@ -1373,6 +1375,7 @@ static int team_user_linkup_option_set(struct team *team, port->user.linkup = ctx->data.bool_val; team_refresh_port_linkup(port); + __team_carrier_check(port->team); return 0; } @@ -1392,6 +1395,7 @@ static int team_user_linkup_en_option_set(struct team *team, port->user.linkup_enabled = ctx->data.bool_val; team_refresh_port_linkup(port); + __team_carrier_check(port->team); return 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7cb105c103fe..782e38bfc1ee 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -981,6 +981,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb; size_t len = total_len, align = NET_SKB_PAD, linear; struct virtio_net_hdr gso = { 0 }; + int good_linear; int offset = 0; int copylen; bool zerocopy = false; @@ -1021,12 +1022,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, return -EINVAL; } + good_linear = SKB_MAX_HEAD(align); + if (msg_control) { /* There are 256 bytes to be copied in skb, so there is * enough room for skb expand head in case it is used. * The rest of the buffer is mapped from userspace. */ copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN; + if (copylen > good_linear) + copylen = good_linear; linear = copylen; if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS) zerocopy = true; @@ -1034,7 +1039,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (!zerocopy) { copylen = len; - linear = gso.hdr_len; + if (gso.hdr_len > good_linear) + linear = good_linear; + else + linear = gso.hdr_len; } skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 90a429b7ebad..8494bb53ebdc 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -204,9 +204,6 @@ static void intr_complete (struct urb *urb) break; } - if (!netif_running (dev->net)) - return; - status = usb_submit_urb (urb, GFP_ATOMIC); if (status != 0) netif_err(dev, timer, dev->net, diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h index fa33b5edf931..e3eb95292a7f 100644 --- a/drivers/net/wireless/rt2x00/rt2800.h +++ b/drivers/net/wireless/rt2x00/rt2800.h @@ -52,6 +52,7 @@ * RF3322 2.4G 2T2R(RT3352/RT3371/RT3372/RT3391/RT3392) * RF3053 2.4G/5G 3T3R(RT3883/RT3563/RT3573/RT3593/RT3662) * RF5592 2.4G/5G 2T2R + * RF3070 2.4G 1T1R * RF5360 2.4G 1T1R * RF5370 2.4G 1T1R * RF5390 2.4G 1T1R @@ -70,6 +71,7 @@ #define RF3322 0x000c #define RF3053 0x000d #define RF5592 0x000f +#define RF3070 0x3070 #define RF3290 0x3290 #define RF5360 0x5360 #define RF5370 0x5370 diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 14007870302b..446eadeaaef6 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -3152,6 +3152,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, case RF3322: rt2800_config_channel_rf3322(rt2x00dev, conf, rf, info); break; + case RF3070: case RF5360: case RF5370: case RF5372: @@ -3166,7 +3167,8 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev, rt2800_config_channel_rf2xxx(rt2x00dev, conf, rf, info); } - if (rt2x00_rf(rt2x00dev, RF3290) || + if (rt2x00_rf(rt2x00dev, RF3070) || + rt2x00_rf(rt2x00dev, RF3290) || rt2x00_rf(rt2x00dev, RF3322) || rt2x00_rf(rt2x00dev, RF5360) || rt2x00_rf(rt2x00dev, RF5370) || @@ -4264,6 +4266,7 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_write(rt2x00dev, 7, rfcsr); break; case RF3053: + case RF3070: case RF3290: case RF5360: case RF5370: @@ -7024,6 +7027,7 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev) case RF3022: case RF3052: case RF3053: + case RF3070: case RF3290: case RF3320: case RF3322: @@ -7546,6 +7550,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) rt2x00_rf(rt2x00dev, RF2020) || rt2x00_rf(rt2x00dev, RF3021) || rt2x00_rf(rt2x00dev, RF3022) || + rt2x00_rf(rt2x00dev, RF3070) || rt2x00_rf(rt2x00dev, RF3290) || rt2x00_rf(rt2x00dev, RF3320) || rt2x00_rf(rt2x00dev, RF3322) || @@ -7674,6 +7679,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) case RF3320: case RF3052: case RF3053: + case RF3070: case RF3290: case RF5360: case RF5370: diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 900da4b243ad..625585034ef4 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -39,6 +39,7 @@ #include #include +#include #include #include diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c index ed0834e2b72e..ab69245f86dc 100644 --- a/drivers/usb/musb/davinci.c +++ b/drivers/usb/musb/davinci.c @@ -509,7 +509,7 @@ static u64 davinci_dmamask = DMA_BIT_MASK(32); static int davinci_probe(struct platform_device *pdev) { - struct resource musb_resources[2]; + struct resource musb_resources[3]; struct musb_hdrc_platform_data *pdata = dev_get_platdata(&pdev->dev); struct platform_device *musb; struct davinci_glue *glue; @@ -567,6 +567,15 @@ static int davinci_probe(struct platform_device *pdev) musb_resources[1].end = pdev->resource[1].end; musb_resources[1].flags = pdev->resource[1].flags; + /* + * For DM6467 3 resources are passed. A placeholder for the 3rd + * resource is always there, so it's safe to always copy it... + */ + musb_resources[2].name = pdev->resource[2].name; + musb_resources[2].start = pdev->resource[2].start; + musb_resources[2].end = pdev->resource[2].end; + musb_resources[2].flags = pdev->resource[2].flags; + ret = platform_device_add_resources(musb, musb_resources, ARRAY_SIZE(musb_resources)); if (ret) { diff --git a/drivers/usb/wusbcore/wa-xfer.c b/drivers/usb/wusbcore/wa-xfer.c index 6ad02f57c366..3dcf66f345e9 100644 --- a/drivers/usb/wusbcore/wa-xfer.c +++ b/drivers/usb/wusbcore/wa-xfer.c @@ -91,7 +91,8 @@ #include "wusbhc.h" enum { - WA_SEGS_MAX = 255, + /* [WUSB] section 8.3.3 allocates 7 bits for the segment index. */ + WA_SEGS_MAX = 128, }; enum wa_seg_status { @@ -446,7 +447,7 @@ static ssize_t __wa_xfer_setup_sizes(struct wa_xfer *xfer, } xfer->seg_size = (xfer->seg_size / maxpktsize) * maxpktsize; xfer->segs = DIV_ROUND_UP(urb->transfer_buffer_length, xfer->seg_size); - if (xfer->segs >= WA_SEGS_MAX) { + if (xfer->segs > WA_SEGS_MAX) { dev_err(dev, "BUG? ops, number of segments %d bigger than %d\n", (int)(urb->transfer_buffer_length / xfer->seg_size), WA_SEGS_MAX); diff --git a/drivers/video/kyro/fbdev.c b/drivers/video/kyro/fbdev.c index 6157f74ac600..ec7fc87fa5ab 100644 --- a/drivers/video/kyro/fbdev.c +++ b/drivers/video/kyro/fbdev.c @@ -625,15 +625,15 @@ static int kyrofb_ioctl(struct fb_info *info, } break; case KYRO_IOCTL_UVSTRIDE: - if (copy_to_user(argp, &deviceInfo.ulOverlayUVStride, sizeof(unsigned long))) + if (copy_to_user(argp, &deviceInfo.ulOverlayUVStride, sizeof(deviceInfo.ulOverlayUVStride))) return -EFAULT; break; case KYRO_IOCTL_STRIDE: - if (copy_to_user(argp, &deviceInfo.ulOverlayStride, sizeof(unsigned long))) + if (copy_to_user(argp, &deviceInfo.ulOverlayStride, sizeof(deviceInfo.ulOverlayStride))) return -EFAULT; break; case KYRO_IOCTL_OVERLAY_OFFSET: - if (copy_to_user(argp, &deviceInfo.ulOverlayOffset, sizeof(unsigned long))) + if (copy_to_user(argp, &deviceInfo.ulOverlayOffset, sizeof(deviceInfo.ulOverlayOffset))) return -EFAULT; break; } diff --git a/fs/aio.c b/fs/aio.c index 067e3d340c35..6efb7f6cb22e 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -36,10 +36,10 @@ #include #include #include -#include #include #include #include +#include #include #include @@ -80,6 +80,8 @@ struct kioctx { struct percpu_ref users; atomic_t dead; + struct percpu_ref reqs; + unsigned long user_id; struct __percpu kioctx_cpu *cpu; @@ -107,7 +109,6 @@ struct kioctx { struct page **ring_pages; long nr_pages; - struct rcu_head rcu_head; struct work_struct free_work; struct { @@ -152,12 +153,67 @@ unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio request static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; +static struct vfsmount *aio_mnt; + +static const struct file_operations aio_ring_fops; +static const struct address_space_operations aio_ctx_aops; + +static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) +{ + struct qstr this = QSTR_INIT("[aio]", 5); + struct file *file; + struct path path; + struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb); + if (IS_ERR(inode)) + return ERR_CAST(inode); + + inode->i_mapping->a_ops = &aio_ctx_aops; + inode->i_mapping->private_data = ctx; + inode->i_size = PAGE_SIZE * nr_pages; + + path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this); + if (!path.dentry) { + iput(inode); + return ERR_PTR(-ENOMEM); + } + path.mnt = mntget(aio_mnt); + + d_instantiate(path.dentry, inode); + file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops); + if (IS_ERR(file)) { + path_put(&path); + return file; + } + + file->f_flags = O_RDWR; + file->private_data = ctx; + return file; +} + +static struct dentry *aio_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + static const struct dentry_operations ops = { + .d_dname = simple_dname, + }; + return mount_pseudo(fs_type, "aio:", NULL, &ops, 0xa10a10a1); +} + /* aio_setup * Creates the slab caches used by the aio routines, panic on * failure as this is done early during the boot sequence. */ static int __init aio_setup(void) { + static struct file_system_type aio_fs = { + .name = "aio", + .mount = aio_mount, + .kill_sb = kill_anon_super, + }; + aio_mnt = kern_mount(&aio_fs); + if (IS_ERR(aio_mnt)) + panic("Failed to create aio fs mount."); + kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); @@ -195,8 +251,10 @@ static void aio_free_ring(struct kioctx *ctx) put_aio_ring_file(ctx); - if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) + if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) { kfree(ctx->ring_pages); + ctx->ring_pages = NULL; + } } static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) @@ -283,16 +341,12 @@ static int aio_setup_ring(struct kioctx *ctx) if (nr_pages < 0) return -EINVAL; - file = anon_inode_getfile_private("[aio]", &aio_ring_fops, ctx, O_RDWR); + file = aio_private_file(ctx, nr_pages); if (IS_ERR(file)) { ctx->aio_ring_file = NULL; return -EAGAIN; } - file->f_inode->i_mapping->a_ops = &aio_ctx_aops; - file->f_inode->i_mapping->private_data = ctx; - file->f_inode->i_size = PAGE_SIZE * (loff_t)nr_pages; - for (i = 0; i < nr_pages; i++) { struct page *page; page = find_or_create_page(file->f_inode->i_mapping, @@ -313,8 +367,10 @@ static int aio_setup_ring(struct kioctx *ctx) if (nr_pages > AIO_RING_PAGES) { ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); - if (!ctx->ring_pages) + if (!ctx->ring_pages) { + put_aio_ring_file(ctx); return -ENOMEM; + } } ctx->mmap_size = nr_pages * PAGE_SIZE; @@ -412,26 +468,34 @@ static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb) return cancel(kiocb); } -static void free_ioctx_rcu(struct rcu_head *head) +static void free_ioctx(struct work_struct *work) { - struct kioctx *ctx = container_of(head, struct kioctx, rcu_head); + struct kioctx *ctx = container_of(work, struct kioctx, free_work); + pr_debug("freeing %p\n", ctx); + + aio_free_ring(ctx); free_percpu(ctx->cpu); kmem_cache_free(kioctx_cachep, ctx); } +static void free_ioctx_reqs(struct percpu_ref *ref) +{ + struct kioctx *ctx = container_of(ref, struct kioctx, reqs); + + INIT_WORK(&ctx->free_work, free_ioctx); + schedule_work(&ctx->free_work); +} + /* * When this function runs, the kioctx has been removed from the "hash table" * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - * now it's safe to cancel any that need to be. */ -static void free_ioctx(struct work_struct *work) +static void free_ioctx_users(struct percpu_ref *ref) { - struct kioctx *ctx = container_of(work, struct kioctx, free_work); - struct aio_ring *ring; + struct kioctx *ctx = container_of(ref, struct kioctx, users); struct kiocb *req; - unsigned cpu, avail; - DEFINE_WAIT(wait); spin_lock_irq(&ctx->ctx_lock); @@ -445,54 +509,8 @@ static void free_ioctx(struct work_struct *work) spin_unlock_irq(&ctx->ctx_lock); - for_each_possible_cpu(cpu) { - struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu); - - atomic_add(kcpu->reqs_available, &ctx->reqs_available); - kcpu->reqs_available = 0; - } - - while (1) { - prepare_to_wait(&ctx->wait, &wait, TASK_UNINTERRUPTIBLE); - - ring = kmap_atomic(ctx->ring_pages[0]); - avail = (ring->head <= ring->tail) - ? ring->tail - ring->head - : ctx->nr_events - ring->head + ring->tail; - - atomic_add(avail, &ctx->reqs_available); - ring->head = ring->tail; - kunmap_atomic(ring); - - if (atomic_read(&ctx->reqs_available) >= ctx->nr_events - 1) - break; - - schedule(); - } - finish_wait(&ctx->wait, &wait); - - WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr_events - 1); - - aio_free_ring(ctx); - - pr_debug("freeing %p\n", ctx); - - /* - * Here the call_rcu() is between the wait_event() for reqs_active to - * hit 0, and freeing the ioctx. - * - * aio_complete() decrements reqs_active, but it has to touch the ioctx - * after to issue a wakeup so we use rcu. - */ - call_rcu(&ctx->rcu_head, free_ioctx_rcu); -} - -static void free_ioctx_ref(struct percpu_ref *ref) -{ - struct kioctx *ctx = container_of(ref, struct kioctx, users); - - INIT_WORK(&ctx->free_work, free_ioctx); - schedule_work(&ctx->free_work); + percpu_ref_kill(&ctx->reqs); + percpu_ref_put(&ctx->reqs); } static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) @@ -551,6 +569,16 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) } } +static void aio_nr_sub(unsigned nr) +{ + spin_lock(&aio_nr_lock); + if (WARN_ON(aio_nr - nr > aio_nr)) + aio_nr = 0; + else + aio_nr -= nr; + spin_unlock(&aio_nr_lock); +} + /* ioctx_alloc * Allocates and initializes an ioctx. Returns an ERR_PTR if it failed. */ @@ -588,8 +616,11 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) ctx->max_reqs = nr_events; - if (percpu_ref_init(&ctx->users, free_ioctx_ref)) - goto out_freectx; + if (percpu_ref_init(&ctx->users, free_ioctx_users)) + goto err; + + if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs)) + goto err; spin_lock_init(&ctx->ctx_lock); spin_lock_init(&ctx->completion_lock); @@ -600,10 +631,10 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) ctx->cpu = alloc_percpu(struct kioctx_cpu); if (!ctx->cpu) - goto out_freeref; + goto err; if (aio_setup_ring(ctx) < 0) - goto out_freepcpu; + goto err; atomic_set(&ctx->reqs_available, ctx->nr_events - 1); ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4); @@ -615,7 +646,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) if (aio_nr + nr_events > (aio_max_nr * 2UL) || aio_nr + nr_events < aio_nr) { spin_unlock(&aio_nr_lock); - goto out_cleanup; + err = -EAGAIN; + goto err_ctx; } aio_nr += ctx->max_reqs; spin_unlock(&aio_nr_lock); @@ -624,23 +656,20 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) err = ioctx_add_table(ctx, mm); if (err) - goto out_cleanup_put; + goto err_cleanup; pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", ctx, ctx->user_id, mm, ctx->nr_events); return ctx; -out_cleanup_put: - percpu_ref_put(&ctx->users); -out_cleanup: - err = -EAGAIN; +err_cleanup: + aio_nr_sub(ctx->max_reqs); +err_ctx: aio_free_ring(ctx); -out_freepcpu: +err: free_percpu(ctx->cpu); -out_freeref: + free_percpu(ctx->reqs.pcpu_count); free_percpu(ctx->users.pcpu_count); -out_freectx: - put_aio_ring_file(ctx); kmem_cache_free(kioctx_cachep, ctx); pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); @@ -675,10 +704,7 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) * -EAGAIN with no ioctxs actually in use (as far as userspace * could tell). */ - spin_lock(&aio_nr_lock); - BUG_ON(aio_nr - ctx->max_reqs > aio_nr); - aio_nr -= ctx->max_reqs; - spin_unlock(&aio_nr_lock); + aio_nr_sub(ctx->max_reqs); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); @@ -810,6 +836,8 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx) if (unlikely(!req)) goto out_put; + percpu_ref_get(&ctx->reqs); + req->ki_ctx = ctx; return req; out_put: @@ -879,12 +907,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2) return; } - /* - * Take rcu_read_lock() in case the kioctx is being destroyed, as we - * need to issue a wakeup after incrementing reqs_available. - */ - rcu_read_lock(); - if (iocb->ki_list.next) { unsigned long flags; @@ -959,7 +981,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); - rcu_read_unlock(); + percpu_ref_put(&ctx->reqs); } EXPORT_SYMBOL(aio_complete); @@ -1370,6 +1392,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, return 0; out_put_req: put_reqs_available(ctx, 1); + percpu_ref_put(&ctx->reqs); kiocb_free(req); return ret; } diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 85c961849953..22f9698a1214 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -24,7 +24,6 @@ static struct vfsmount *anon_inode_mnt __read_mostly; static struct inode *anon_inode_inode; -static const struct file_operations anon_inode_fops; /* * anon_inodefs_dname() is called from d_path(). @@ -39,51 +38,6 @@ static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; -/* - * nop .set_page_dirty method so that people can use .page_mkwrite on - * anon inodes. - */ -static int anon_set_page_dirty(struct page *page) -{ - return 0; -}; - -static const struct address_space_operations anon_aops = { - .set_page_dirty = anon_set_page_dirty, -}; - -/* - * A single inode exists for all anon_inode files. Contrary to pipes, - * anon_inode inodes have no associated per-instance data, so we need - * only allocate one of them. - */ -static struct inode *anon_inode_mkinode(struct super_block *s) -{ - struct inode *inode = new_inode_pseudo(s); - - if (!inode) - return ERR_PTR(-ENOMEM); - - inode->i_ino = get_next_ino(); - inode->i_fop = &anon_inode_fops; - - inode->i_mapping->a_ops = &anon_aops; - - /* - * Mark the inode dirty from the very beginning, - * that way it will never be moved to the dirty - * list because mark_inode_dirty() will think - * that it already _is_ on the dirty list. - */ - inode->i_state = I_DIRTY; - inode->i_mode = S_IRUSR | S_IWUSR; - inode->i_uid = current_fsuid(); - inode->i_gid = current_fsgid(); - inode->i_flags |= S_PRIVATE; - inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - return inode; -} - static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { @@ -92,7 +46,7 @@ static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type, &anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC); if (!IS_ERR(root)) { struct super_block *s = root->d_sb; - anon_inode_inode = anon_inode_mkinode(s); + anon_inode_inode = alloc_anon_inode(s); if (IS_ERR(anon_inode_inode)) { dput(root); deactivate_locked_super(s); @@ -134,7 +88,7 @@ struct file *anon_inode_getfile_private(const char *name, if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); - inode = anon_inode_mkinode(anon_inode_mnt->mnt_sb); + inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) { file = ERR_PTR(-ENOMEM); goto err_module; diff --git a/fs/libfs.c b/fs/libfs.c index 3a3a9b53bf5a..193e0c29fb94 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -993,3 +993,46 @@ EXPORT_SYMBOL_GPL(simple_attr_open); EXPORT_SYMBOL_GPL(simple_attr_release); EXPORT_SYMBOL_GPL(simple_attr_read); EXPORT_SYMBOL_GPL(simple_attr_write); + +/* + * nop .set_page_dirty method so that people can use .page_mkwrite on + * anon inodes. + */ +static int anon_set_page_dirty(struct page *page) +{ + return 0; +}; + +/* + * A single inode exists for all anon_inode files. Contrary to pipes, + * anon_inode inodes have no associated per-instance data, so we need + * only allocate one of them. + */ +struct inode *alloc_anon_inode(struct super_block *s) +{ + static const struct address_space_operations anon_aops = { + .set_page_dirty = anon_set_page_dirty, + }; + struct inode *inode = new_inode_pseudo(s); + + if (!inode) + return ERR_PTR(-ENOMEM); + + inode->i_ino = get_next_ino(); + inode->i_mapping->a_ops = &anon_aops; + + /* + * Mark the inode dirty from the very beginning, + * that way it will never be moved to the dirty + * list because mark_inode_dirty() will think + * that it already _is_ on the dirty list. + */ + inode->i_state = I_DIRTY; + inode->i_mode = S_IRUSR | S_IWUSR; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); + inode->i_flags |= S_PRIVATE; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + return inode; +} +EXPORT_SYMBOL(alloc_anon_inode); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 668e8f4ccf5e..2e1e6c33841d 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1717,6 +1717,12 @@ xfs_file_ioctl( if (mp->m_flags & XFS_MOUNT_RDONLY) return -XFS_ERROR(EROFS); + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (mp->m_flags & XFS_MOUNT_RDONLY) + return -XFS_ERROR(EROFS); + if (copy_from_user(&eofb, arg, sizeof(eofb))) return -XFS_ERROR(EFAULT); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f40547ba191..fefa7b00ba42 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2562,6 +2562,7 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping, extern int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); +extern struct inode *alloc_anon_inode(struct super_block *); extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); diff --git a/include/linux/net.h b/include/linux/net.h index 4f27575ce1d6..8bd9d926b3cf 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -163,6 +163,14 @@ struct proto_ops { #endif int (*sendmsg) (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len); + /* Notes for implementing recvmsg: + * =============================== + * msg->msg_namelen should get updated by the recvmsg handlers + * iff msg_name != NULL. It is by default 0 to prevent + * returning uninitialized memory to user space. The recvfrom + * handlers can assume that msg.msg_name is either NULL or has + * a minimum size of sizeof(struct sockaddr_storage). + */ int (*recvmsg) (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len, int flags); diff --git a/include/linux/random.h b/include/linux/random.h index 6312dd9ba449..bf9085e89fb5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -50,9 +50,9 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) { u32 i = (seed >> 32) ^ (seed << 10) ^ seed; - state->s1 = __seed(i, 1); - state->s2 = __seed(i, 7); - state->s3 = __seed(i, 15); + state->s1 = __seed(i, 2); + state->s2 = __seed(i, 8); + state->s3 = __seed(i, 16); } #ifdef CONFIG_ARCH_RANDOM diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c2d89335f637..f66f346dd164 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -333,11 +333,6 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif -#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \ - defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE) -#define NET_SKBUFF_NF_DEFRAG_NEEDED 1 -#endif - /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -370,7 +365,6 @@ typedef unsigned char *sk_buff_data_t; * @protocol: Packet protocol from driver * @destructor: Destruct function * @nfct: Associated connection, if any - * @nfct_reasm: netfilter conntrack re-assembly pointer * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index @@ -459,9 +453,6 @@ struct sk_buff { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack *nfct; #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED - struct sk_buff *nfct_reasm; -#endif #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif @@ -2605,18 +2596,6 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct) atomic_inc(&nfct->use); } #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED -static inline void nf_conntrack_get_reasm(struct sk_buff *skb) -{ - if (skb) - atomic_inc(&skb->users); -} -static inline void nf_conntrack_put_reasm(struct sk_buff *skb) -{ - if (skb) - kfree_skb(skb); -} -#endif #ifdef CONFIG_BRIDGE_NETFILTER static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) { @@ -2635,10 +2614,6 @@ static inline void nf_reset(struct sk_buff *skb) nf_conntrack_put(skb->nfct); skb->nfct = NULL; #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED - nf_conntrack_put_reasm(skb->nfct_reasm); - skb->nfct_reasm = NULL; -#endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); skb->nf_bridge = NULL; @@ -2660,10 +2635,6 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) nf_conntrack_get(src->nfct); dst->nfctinfo = src->nfctinfo; #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED - dst->nfct_reasm = src->nfct_reasm; - nf_conntrack_get_reasm(src->nfct_reasm); -#endif #ifdef CONFIG_BRIDGE_NETFILTER dst->nf_bridge = src->nf_bridge; nf_bridge_get(src->nf_bridge); @@ -2675,9 +2646,6 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(dst->nfct); #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED - nf_conntrack_put_reasm(dst->nfct_reasm); -#endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(dst->nf_bridge); #endif diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 1855f0a22add..c557c6d096de 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -39,6 +39,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, + NUMA_HUGE_PTE_UPDATES, NUMA_HINT_FAULTS, NUMA_HINT_FAULTS_LOCAL, NUMA_PAGE_MIGRATE, diff --git a/include/net/ip.h b/include/net/ip.h index 5e5268807a1c..301f10c9b563 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -464,7 +464,7 @@ extern int compat_ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); -extern int ip_recv_error(struct sock *sk, struct msghdr *msg, int len); +extern int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); extern void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); extern void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9c4d37ec45a1..772252ddc115 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -109,7 +109,6 @@ extern int ip_vs_conn_tab_size; struct ip_vs_iphdr { __u32 len; /* IPv4 simply where L4 starts IPv6 where L4 Transport Header starts */ - __u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */ __u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/ __s16 protocol; __s32 flags; @@ -117,34 +116,12 @@ struct ip_vs_iphdr { union nf_inet_addr daddr; }; -/* Dependency to module: nf_defrag_ipv6 */ -#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE) -static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb) -{ - return skb->nfct_reasm; -} -static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, - int len, void *buffer, - const struct ip_vs_iphdr *ipvsh) -{ - if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb))) - return skb_header_pointer(skb_nfct_reasm(skb), - ipvsh->thoff_reasm, len, buffer); - - return skb_header_pointer(skb, offset, len, buffer); -} -#else -static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb) -{ - return NULL; -} static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, int len, void *buffer, const struct ip_vs_iphdr *ipvsh) { return skb_header_pointer(skb, offset, len, buffer); } -#endif static inline void ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr) @@ -171,19 +148,12 @@ ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) (struct ipv6hdr *)skb_network_header(skb); iphdr->saddr.in6 = iph->saddr; iphdr->daddr.in6 = iph->daddr; - /* ipv6_find_hdr() updates len, flags, thoff_reasm */ - iphdr->thoff_reasm = 0; + /* ipv6_find_hdr() updates len, flags */ iphdr->len = 0; iphdr->flags = 0; iphdr->protocol = ipv6_find_hdr(skb, &iphdr->len, -1, &iphdr->fragoffs, &iphdr->flags); - /* get proto from re-assembled packet and it's offset */ - if (skb_nfct_reasm(skb)) - iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb), - &iphdr->thoff_reasm, - -1, NULL, NULL); - } else #endif { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index bbf1c8fb8511..1f96efd30816 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -802,8 +802,10 @@ extern int compat_ipv6_getsockopt(struct sock *sk, extern int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); -extern int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len); -extern int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len); +extern int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); +extern int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); extern void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); extern void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index fd79c9a1779d..17920d847b40 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -6,10 +6,7 @@ extern void nf_defrag_ipv6_enable(void); extern int nf_ct_frag6_init(void); extern void nf_ct_frag6_cleanup(void); extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user); -extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, - struct net_device *in, - struct net_device *out, - int (*okfn)(struct sk_buff *)); +extern void nf_ct_frag6_consume_orig(struct sk_buff *skb); struct inet_frags_ctl; diff --git a/include/net/ping.h b/include/net/ping.h index 5db0224b73ac..2b496e9f9ebd 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -31,7 +31,8 @@ /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { - int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len); + int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); int (*ip6_datagram_recv_ctl)(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); int (*icmpv6_err_convert)(u8 type, u8 code, int *err); diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 9b829134d422..66f925d3c07b 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -759,13 +759,14 @@ enum { TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */ - TCA_FQ_FLOW_DEFAULT_RATE,/* for sockets with unspecified sk_rate, - * use the following rate - */ + TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */ TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */ TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */ + + TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */ + __TCA_FQ_MAX }; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index bb2215174f05..af8d1d4f3d55 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -475,6 +475,7 @@ static void sync_cmos_clock(struct work_struct *work) * called as close as possible to 500 ms before the new second starts. * This code is run on a timer. If the clock is set, that timer * may not expire at the correct time. Thus, we adjust... + * We want the clock to be within a couple of ticks from the target. */ if (!ntp_synced()) { /* @@ -485,7 +486,7 @@ static void sync_cmos_clock(struct work_struct *work) } getnstimeofday(&now); - if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) { + if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { struct timespec adjust = now; fail = -ENODEV; diff --git a/lib/random32.c b/lib/random32.c index 52280d5526be..01e8890d1089 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -141,7 +141,7 @@ void prandom_seed(u32 entropy) */ for_each_possible_cpu (i) { struct rnd_state *state = &per_cpu(net_rand_state, i); - state->s1 = __seed(state->s1 ^ entropy, 1); + state->s1 = __seed(state->s1 ^ entropy, 2); } } EXPORT_SYMBOL(prandom_seed); @@ -158,9 +158,9 @@ static int __init prandom_init(void) struct rnd_state *state = &per_cpu(net_rand_state,i); #define LCG(x) ((x) * 69069) /* super-duper LCG */ - state->s1 = __seed(LCG(i + jiffies), 1); - state->s2 = __seed(LCG(state->s1), 7); - state->s3 = __seed(LCG(state->s2), 15); + state->s1 = __seed(LCG(i + jiffies), 2); + state->s2 = __seed(LCG(state->s1), 8); + state->s3 = __seed(LCG(state->s2), 16); /* "warm it up" */ prandom_u32_state(state); @@ -187,9 +187,9 @@ static int __init prandom_reseed(void) u32 seeds[3]; get_random_bytes(&seeds, sizeof(seeds)); - state->s1 = __seed(seeds[0], 1); - state->s2 = __seed(seeds[1], 7); - state->s3 = __seed(seeds[2], 15); + state->s1 = __seed(seeds[0], 2); + state->s2 = __seed(seeds[1], 8); + state->s3 = __seed(seeds[2], 16); /* mix it in */ prandom_u32_state(state); diff --git a/mm/mprotect.c b/mm/mprotect.c index 412ba2b7326a..6c3f56f19275 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -138,6 +138,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pmd_t *pmd; unsigned long next; unsigned long pages = 0; + unsigned long nr_huge_updates = 0; bool all_same_node; pmd = pmd_offset(pud, addr); @@ -148,7 +149,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, split_huge_page_pmd(vma, addr, pmd); else if (change_huge_pmd(vma, pmd, addr, newprot, prot_numa)) { - pages++; + pages += HPAGE_PMD_NR; + nr_huge_updates++; continue; } /* fall through */ @@ -168,6 +170,9 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, change_pmd_protnuma(vma->vm_mm, addr, pmd); } while (pmd++, addr = next, addr != end); + if (nr_huge_updates) + count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates); + return pages; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 9bb314577911..5a442a723d79 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -812,6 +812,7 @@ const char * const vmstat_text[] = { #ifdef CONFIG_NUMA_BALANCING "numa_pte_updates", + "numa_huge_pte_updates", "numa_hint_faults", "numa_hint_faults_local", "numa_pages_migrated", diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 7fee50d637f9..7d424ac6e760 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1735,7 +1735,6 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr size_t size, int flags) { struct sock *sk = sock->sk; - struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name; struct ddpehdr *ddp; int copied = 0; int offset = 0; @@ -1764,14 +1763,13 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr } err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied); - if (!err) { - if (sat) { - sat->sat_family = AF_APPLETALK; - sat->sat_port = ddp->deh_sport; - sat->sat_addr.s_node = ddp->deh_snode; - sat->sat_addr.s_net = ddp->deh_snet; - } - msg->msg_namelen = sizeof(*sat); + if (!err && msg->msg_name) { + struct sockaddr_at *sat = msg->msg_name; + sat->sat_family = AF_APPLETALK; + sat->sat_port = ddp->deh_sport; + sat->sat_addr.s_node = ddp->deh_snode; + sat->sat_addr.s_net = ddp->deh_snet; + msg->msg_namelen = sizeof(*sat); } skb_free_datagram(sk, skb); /* Free the datagram. */ diff --git a/net/atm/common.c b/net/atm/common.c index 737bef59ce89..7b491006eaf4 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -531,8 +531,6 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sk_buff *skb; int copied, error = -EINVAL; - msg->msg_namelen = 0; - if (sock->state != SS_CONNECTED) return -ENOTCONN; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 4b4d2b779ec1..78c474f8f615 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1636,11 +1636,11 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock, skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - if (msg->msg_namelen != 0) { - struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name; + if (msg->msg_name) { ax25_digi digi; ax25_address src; const unsigned char *mac = skb_mac_header(skb); + struct sockaddr_ax25 *sax = msg->msg_name; memset(sax, 0, sizeof(struct full_sockaddr_ax25)); ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL, diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 9096137c889c..6629cdc134dc 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -221,8 +221,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & (MSG_OOB)) return -EOPNOTSUPP; - msg->msg_namelen = 0; - skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -287,8 +285,6 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & MSG_OOB) return -EOPNOTSUPP; - msg->msg_namelen = 0; - BT_DBG("sk %p size %zu", sk, size); lock_sock(sk); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 9bd7d959e384..fa4bf6631425 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -752,8 +752,6 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 30b3721dc6d7..c1c6028e389a 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -608,7 +608,6 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { rfcomm_dlc_accept(d); - msg->msg_namelen = 0; return 0; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 96bd388d93a4..d021e441b6e6 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -715,7 +715,6 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock, test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sco_conn_defer_accept(pi->conn->hcon, pi->setting); sk->sk_state = BT_CONFIG; - msg->msg_namelen = 0; release_sock(sk); return 0; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index c41d5fbb91d0..547504ccba69 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -172,6 +172,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_fdb_delete_by_port(br, NULL, 1); + del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 05a41c7ec304..d6be3edb7a43 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -286,8 +286,6 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, if (m->msg_flags&MSG_OOB) goto read_error; - m->msg_namelen = 0; - skb = skb_recv_datagram(sk, flags, 0 , &ret); if (!skb) goto read_error; @@ -361,8 +359,6 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags&MSG_OOB) goto out; - msg->msg_namelen = 0; - /* * Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg diff --git a/net/compat.c b/net/compat.c index 89032580bd1d..dd32e34c1e2c 100644 --- a/net/compat.c +++ b/net/compat.c @@ -72,7 +72,7 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) - return -EINVAL; + kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); @@ -93,7 +93,8 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, if (err < 0) return err; } - kern_msg->msg_name = kern_address; + if (kern_msg->msg_name) + kern_msg->msg_name = kern_address; } else kern_msg->msg_name = NULL; diff --git a/net/core/dev.c b/net/core/dev.c index 3430b1ed12e5..3d1387461279 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1691,13 +1691,9 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } - skb->protocol = eth_type_trans(skb, dev); - /* eth_type_trans() can set pkt_type. - * call skb_scrub_packet() after it to clear pkt_type _after_ calling - * eth_type_trans(). - */ skb_scrub_packet(skb, true); + skb->protocol = eth_type_trans(skb, dev); return netif_rx(skb); } @@ -4819,7 +4815,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; - if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags) + if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 2e654138433c..f409e0bd35c0 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -460,7 +460,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (frh->action && (frh->action != rule->action)) continue; - if (frh->table && (frh_get_table(frh, tb) != rule->table)) + if (frh_get_table(frh, tb) && + (frh_get_table(frh, tb) != rule->table)) continue; if (tb[FRA_PRIORITY] && diff --git a/net/core/iovec.c b/net/core/iovec.c index b77eeecc0011..7d84ea1fbb20 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -48,7 +48,8 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a if (err < 0) return err; } - m->msg_name = address; + if (m->msg_name) + m->msg_name = address; } else { m->msg_name = NULL; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 261357a66300..a797fff7f222 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2527,6 +2527,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, if (x) { int ret; __u8 *eth; + struct iphdr *iph; + nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); @@ -2548,6 +2550,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, eth = (__u8 *) skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 12); *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); } } return 1; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d81cff119f73..c28c7fed0d0b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -580,9 +580,6 @@ static void skb_release_head_state(struct sk_buff *skb) #if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb->nfct); #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED - nf_conntrack_put_reasm(skb->nfct_reasm); -#endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); #endif @@ -2758,6 +2755,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *fskb = skb_shinfo(skb)->frag_list; + skb_frag_t *skb_frag = skb_shinfo(skb)->frags; unsigned int mss = skb_shinfo(skb)->gso_size; unsigned int doffset = skb->data - skb_mac_header(skb); unsigned int offset = doffset; @@ -2797,16 +2795,38 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (hsize > len || !sg) hsize = len; - if (!hsize && i >= nfrags) { - BUG_ON(fskb->len != len); + if (!hsize && i >= nfrags && skb_headlen(fskb) && + (skb_headlen(fskb) == len || sg)) { + BUG_ON(skb_headlen(fskb) > len); + + i = 0; + nfrags = skb_shinfo(fskb)->nr_frags; + skb_frag = skb_shinfo(fskb)->frags; + pos += skb_headlen(fskb); + + while (pos < offset + len) { + BUG_ON(i >= nfrags); + + size = skb_frag_size(skb_frag); + if (pos + size > offset + len) + break; + + i++; + pos += size; + skb_frag++; + } - pos += len; nskb = skb_clone(fskb, GFP_ATOMIC); fskb = fskb->next; if (unlikely(!nskb)) goto err; + if (unlikely(pskb_trim(nskb, len))) { + kfree_skb(nskb); + goto err; + } + hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); @@ -2850,7 +2870,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) nskb->data - tnl_hlen, doffset + tnl_hlen); - if (fskb != skb_shinfo(skb)->frag_list) + if (nskb->len == len + doffset) goto perform_csum_check; if (!sg) { @@ -2868,8 +2888,28 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; - while (pos < offset + len && i < nfrags) { - *frag = skb_shinfo(skb)->frags[i]; + while (pos < offset + len) { + if (i >= nfrags) { + BUG_ON(skb_headlen(fskb)); + + i = 0; + nfrags = skb_shinfo(fskb)->nr_frags; + skb_frag = skb_shinfo(fskb)->frags; + + BUG_ON(!nfrags); + + fskb = fskb->next; + } + + if (unlikely(skb_shinfo(nskb)->nr_frags >= + MAX_SKB_FRAGS)) { + net_warn_ratelimited( + "skb_segment: too many frags: %u %u\n", + pos, mss); + goto err; + } + + *frag = *skb_frag; __skb_frag_ref(frag); size = skb_frag_size(frag); @@ -2882,6 +2922,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (pos + size <= offset + len) { i++; + skb_frag++; pos += size; } else { skb_frag_size_sub(frag, pos + size - (offset + len)); @@ -2891,25 +2932,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) frag++; } - if (pos < offset + len) { - struct sk_buff *fskb2 = fskb; - - BUG_ON(pos + fskb->len != offset + len); - - pos += fskb->len; - fskb = fskb->next; - - if (fskb2->next) { - fskb2 = skb_clone(fskb2, GFP_ATOMIC); - if (!fskb2) - goto err; - } else - skb_get(fskb2); - - SKB_FRAG_ASSERT(nskb); - skb_shinfo(nskb)->frag_list = fskb2; - } - skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index ff41b4d60d30..008f33703a33 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -957,7 +957,7 @@ lowpan_process_data(struct sk_buff *skb) * Traffic class carried in-line * ECN + DSCP (1 byte), Flow Label is elided */ - case 1: /* 10b */ + case 2: /* 10b */ if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; @@ -968,7 +968,7 @@ lowpan_process_data(struct sk_buff *skb) * Flow Label carried in-line * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided */ - case 2: /* 01b */ + case 1: /* 01b */ if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 581a59504bd5..1865fdf5a5a5 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -315,9 +315,8 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, if (saddr) { saddr->family = AF_IEEE802154; saddr->addr = mac_cb(skb)->sa; - } - if (addr_len) *addr_len = sizeof(*saddr); + } if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index b28e863fe0a7..19e36376d2a0 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -57,7 +57,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); goto out; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d9c4f113d709..23e6ab0a2dc0 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -368,7 +368,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf /* * Handle MSG_ERRQUEUE */ -int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; struct sk_buff *skb, *skb2; @@ -405,6 +405,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 63a6d6d6b875..254f11c24aa5 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -454,6 +454,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); + if (tunnel->dev->type == ARPHRD_ETHER) { skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -461,8 +463,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, skb->dev = tunnel->dev; } - skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); - gro_cells_receive(&tunnel->gro_cells, skb); return 0; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 6e87f853d033..26847e189c04 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -190,6 +190,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (!rt->dst.xfrm || rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { dev->stats.tx_carrier_errors++; + ip_rt_put(rt); goto tx_error_icmp; } tdev = rt->dst.dev; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index d7d9882d4cae..c482f7c7dd32 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -769,7 +769,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -827,8 +827,6 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, { struct inet_sock *isk = inet_sk(sk); int family = sk->sk_family; - struct sockaddr_in *sin; - struct sockaddr_in6 *sin6; struct sk_buff *skb; int copied, err; @@ -838,19 +836,13 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (addr_len) { - if (family == AF_INET) - *addr_len = sizeof(*sin); - else if (family == AF_INET6 && addr_len) - *addr_len = sizeof(*sin6); - } - if (flags & MSG_ERRQUEUE) { if (family == AF_INET) { - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { - return pingv6_ops.ipv6_recv_error(sk, msg, len); + return pingv6_ops.ipv6_recv_error(sk, msg, len, + addr_len); #endif } } @@ -874,11 +866,15 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* Copy the address and add cmsg data. */ if (family == AF_INET) { - sin = (struct sockaddr_in *) msg->msg_name; - sin->sin_family = AF_INET; - sin->sin_port = 0 /* skb->h.uh->source */; - sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + + if (sin) { + sin->sin_family = AF_INET; + sin->sin_port = 0 /* skb->h.uh->source */; + sin->sin_addr.s_addr = ip_hdr(skb)->saddr; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); + } if (isk->cmsg_flags) ip_cmsg_recv(msg, skb); @@ -887,17 +883,21 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } else if (family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *ip6 = ipv6_hdr(skb); - sin6 = (struct sockaddr_in6 *) msg->msg_name; - sin6->sin6_family = AF_INET6; - sin6->sin6_port = 0; - sin6->sin6_addr = ip6->saddr; - - sin6->sin6_flowinfo = 0; - if (np->sndflow) - sin6->sin6_flowinfo = ip6_flowinfo(ip6); - - sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + struct sockaddr_in6 *sin6 = + (struct sockaddr_in6 *)msg->msg_name; + + if (sin6) { + sin6->sin6_family = AF_INET6; + sin6->sin6_port = 0; + sin6->sin6_addr = ip6->saddr; + sin6->sin6_flowinfo = 0; + if (np->sndflow) + sin6->sin6_flowinfo = ip6_flowinfo(ip6); + sin6->sin6_scope_id = + ipv6_iface_scope_id(&sin6->sin6_addr, + IP6CB(skb)->iif); + *addr_len = sizeof(*sin6); + } if (inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 193db03540ad..7d3db7838e62 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -694,11 +694,8 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); - if (flags & MSG_ERRQUEUE) { - err = ip_recv_error(sk, msg, len); + err = ip_recv_error(sk, msg, len, addr_len); goto out; } @@ -724,6 +721,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6011615e810d..62290b5124c8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1772,8 +1772,12 @@ local_input: rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } - if (do_cache) - rt_cache_route(&FIB_RES_NH(res), rth); + if (do_cache) { + if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) { + rth->dst.flags |= DST_NOCACHE; + rt_add_uncached_list(rth); + } + } skb_dst_set(skb, &rth->dst); err = 0; goto out; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6e5617b9f9db..be5246e1d5b6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -806,12 +806,6 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, xmit_size_goal = min_t(u32, gso_size, sk->sk_gso_max_size - 1 - hlen); - /* TSQ : try to have at least two segments in flight - * (one in NIC TX ring, another in Qdisc) - */ - xmit_size_goal = min_t(u32, xmit_size_goal, - sysctl_tcp_limit_output_bytes >> 1); - xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); /* We try hard to avoid divides here */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b14266bb91eb..5031f68b545d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -177,7 +177,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); return err; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 52f3c6b971d2..310711433358 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -659,10 +659,13 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost) { + struct dst_entry *dst = __sk_dst_get(sk); struct tcp_metrics_block *tm; + if (!dst) + return; rcu_read_lock(); - tm = tcp_get_metrics(sk, __sk_dst_get(sk), true); + tm = tcp_get_metrics(sk, dst, true); if (tm) { struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 533c58a5cfb7..910ab81bc0dd 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -272,33 +272,32 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff * { const struct iphdr *iph = skb_gro_network_header(skb); __wsum wsum; - __sum16 sum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = skb->csum; switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + 0); + + /* fall through */ + case CHECKSUM_COMPLETE: if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr, - skb->csum)) { + wsum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } -flush: + NAPI_GRO_CB(skb)->flush = 1; return NULL; - - case CHECKSUM_NONE: - wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb_gro_len(skb), IPPROTO_TCP, 0); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; } +skip_csum: return tcp_gro_receive(head, skb); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d46f2143305c..e912634b2f05 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1875,8 +1875,12 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, * - better RTT estimation and ACK scheduling * - faster recovery * - high rates + * Alas, some drivers / subsystems require a fair amount + * of queued bytes to ensure line rate. + * One example is wifi aggregation (802.11 AMPDU) */ - limit = max(skb->truesize, sk->sk_pacing_rate >> 10); + limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes, + sk->sk_pacing_rate >> 10); if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); @@ -3108,7 +3112,6 @@ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; - tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq; tcp_xmit_probe_skb(sk, 0); } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0ca44df51ee9..5e2c2f1a075d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -973,7 +973,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -1072,6 +1072,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, struct udp_sock *up = udp_sk(sk); int ret; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + if (!up->pending) { struct msghdr msg = { .msg_flags = flags|MSG_MORE }; @@ -1209,14 +1212,8 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int is_udplite = IS_UDPLITE(sk); bool slow; - /* - * Check any passed addresses - */ - if (addr_len) - *addr_len = sizeof(*sin); - if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -1276,6 +1273,7 @@ try_again: sin->sin_port = udp_hdr(skb)->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index ccde54248c8c..adf998322bd2 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -104,10 +104,14 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) const struct iphdr *iph = ip_hdr(skb); u8 *xprth = skb_network_header(skb) + iph->ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; - fl4->flowi4_oif = skb_dst(skb)->dev->ifindex; + fl4->flowi4_oif = reverse ? skb->skb_iif : oif; if (!ip_is_fragment(iph)) { switch (iph->protocol) { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7c96100b021e..8132b4457b20 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -965,10 +965,10 @@ out: #ifdef CONFIG_SYSCTL sysctl_fail: - ipv6_packet_cleanup(); + pingv6_exit(); #endif pingv6_fail: - pingv6_exit(); + ipv6_packet_cleanup(); ipv6_packet_fail: tcpv6_exit(); tcpv6_fail: diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 48b6bd2a9a14..c66c6df6e881 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) /* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) &sin->sin6_addr); sin->sin6_scope_id = 0; } + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); @@ -377,6 +378,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; + sin->sin6_port = 0; if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) @@ -423,7 +425,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -457,6 +460,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; + *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 46e88433ec7d..f0ccdb787100 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -453,8 +453,10 @@ static int mem_check(struct sock *sk) if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; + rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) count++; + rcu_read_unlock_bh(); if (room <= 0 || ((count >= FL_MAX_PER_SOCK || diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 91fb4e8212f5..b6fa35e7425c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -116,8 +116,8 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_unlock_bh(); - IP6_INC_STATS_BH(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } @@ -125,7 +125,8 @@ static int ip6_finish_output2(struct sk_buff *skb) static int ip6_finish_output(struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb))) + dst_allfrag(skb_dst(skb)) || + (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(skb, ip6_finish_output2); else return ip6_finish_output2(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 583b77e2f69b..c1e11b5d6ccc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1635,6 +1635,15 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], return ip6_tnl_update(t, &p); } +static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6_tnl_get_size(const struct net_device *dev) { return @@ -1699,6 +1708,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = { .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, + .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, }; @@ -1715,9 +1725,9 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .priority = 1, }; -static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) { - struct net *net = dev_net(ip6n->fb_tnl_dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; @@ -1785,10 +1795,8 @@ err_alloc_dev: static void __net_exit ip6_tnl_exit_net(struct net *net) { - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - rtnl_lock(); - ip6_tnl_destroy_tunnels(ip6n); + ip6_tnl_destroy_tunnels(net); rtnl_unlock(); } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index d6e4dd8b58df..83ab37cc8e6a 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -169,63 +169,13 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int __ipv6_conntrack_in(struct net *net, - unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm = skb->nfct_reasm; - const struct nf_conn_help *help; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - - /* This packet is fragmented and has reassembled packet. */ - if (reasm) { - /* Reassembled packet isn't parsed yet ? */ - if (!reasm->nfct) { - unsigned int ret; - - ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm); - if (ret != NF_ACCEPT) - return ret; - } - - /* Conntrack helpers need the entire reassembled packet in the - * POST_ROUTING hook. In case of unconfirmed connections NAT - * might reassign a helper, so the entire packet is also - * required. - */ - ct = nf_ct_get(reasm, &ctinfo); - if (ct != NULL && !nf_ct_is_untracked(ct)) { - help = nfct_help(ct); - if ((help && help->helper) || !nf_ct_is_confirmed(ct)) { - nf_conntrack_get_reasm(reasm); - NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, - (struct net_device *)in, - (struct net_device *)out, - okfn, NF_IP6_PRI_CONNTRACK + 1); - return NF_DROP_ERR(-ECANCELED); - } - } - - nf_conntrack_get(reasm->nfct); - skb->nfct = reasm->nfct; - skb->nfctinfo = reasm->nfctinfo; - return NF_ACCEPT; - } - - return nf_conntrack_in(net, PF_INET6, hooknum, skb); -} - static unsigned int ipv6_conntrack_in(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(in), PF_INET6, hooknum, skb); } static unsigned int ipv6_conntrack_local(unsigned int hooknum, @@ -239,7 +189,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(out), PF_INET6, hooknum, skb); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index dffdc1a389c5..253566a8d55b 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -621,31 +621,16 @@ ret_orig: return skb; } -void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, - struct net_device *in, struct net_device *out, - int (*okfn)(struct sk_buff *)) +void nf_ct_frag6_consume_orig(struct sk_buff *skb) { struct sk_buff *s, *s2; - unsigned int ret = 0; for (s = NFCT_FRAG6_CB(skb)->orig; s;) { - nf_conntrack_put_reasm(s->nfct_reasm); - nf_conntrack_get_reasm(skb); - s->nfct_reasm = skb; - s2 = s->next; s->next = NULL; - - if (ret != -ECANCELED) - ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, - in, out, okfn, - NF_IP6_PRI_CONNTRACK_DEFRAG + 1); - else - kfree_skb(s); - + consume_skb(s); s = s2; } - nf_conntrack_put_reasm(skb); } static int nf_ct_net_init(struct net *net) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index aacd121fe8c5..581dd9ede0de 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (reasm == skb) return NF_ACCEPT; - nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, - (struct net_device *)out, okfn); + nf_ct_frag6_consume_orig(reasm); + + NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, + (struct net_device *) in, (struct net_device *) out, + okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); return NF_STOLEN; } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 18f19df4189f..7856e962a3e6 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -57,7 +57,8 @@ static struct inet_protosw pingv6_protosw = { /* Compatibility glue so we can support IPv6 when it's compiled as a module */ -static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { return -EAFNOSUPPORT; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a4ed2416399e..430067cb9210 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -466,14 +466,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_OOB) return -EOPNOTSUPP; - if (addr_len) - *addr_len=sizeof(*sin6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -507,6 +504,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); + *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 04e17b3309fb..77308af056bc 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -731,8 +731,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, prefix = &prefix_buf; } - rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, - dev->ifindex); + if (rinfo->prefix_len == 0) + rt = rt6_get_dflt_router(gwaddr, dev); + else + rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, + gwaddr, dev->ifindex); if (rt && !lifetime) { ip6_del_rt(rt); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 19269453a8ea..b43388452bf8 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1594,6 +1594,15 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { #endif }; +static void ipip6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + if (dev != sitn->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, @@ -1605,6 +1614,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = { .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, + .dellink = ipip6_dellink, }; static struct xfrm_tunnel sit_handler __read_mostly = { @@ -1619,9 +1629,10 @@ static struct xfrm_tunnel ipip_handler __read_mostly = { .priority = 2, }; -static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) +static void __net_exit sit_destroy_tunnels(struct net *net, + struct list_head *head) { - struct net *net = dev_net(sitn->fb_tunnel_dev); + struct sit_net *sitn = net_generic(net, sit_net_id); struct net_device *dev, *aux; int prio; @@ -1696,11 +1707,10 @@ err_alloc_dev: static void __net_exit sit_exit_net(struct net *net) { - struct sit_net *sitn = net_generic(net, sit_net_id); LIST_HEAD(list); rtnl_lock(); - sit_destroy_tunnels(sitn, &list); + sit_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 2ec6bf6a0aa0..a7a2384b30f5 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -37,34 +37,32 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, { const struct ipv6hdr *iph = skb_gro_network_header(skb); __wsum wsum; - __sum16 sum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = skb->csum; switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + wsum); + + /* fall through */ + case CHECKSUM_COMPLETE: if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { + wsum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; break; } -flush: + NAPI_GRO_CB(skb)->flush = 1; return NULL; - - case CHECKSUM_NONE: - wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), - IPPROTO_TCP, 0)); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; } +skip_csum: return tcp_gro_receive(head, skb); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 18786098fd41..3d2758d4494e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -374,14 +374,11 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int is_udp4; bool slow; - if (addr_len) - *addr_len = sizeof(struct sockaddr_in6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -462,7 +459,7 @@ try_again: ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); } - + *addr_len = sizeof(*sin6); } if (is_udp4) { if (inet->cmsg_flags) diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 60559511bd9c..34c6fff3ae84 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -88,7 +88,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); - if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) { + if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 08ed2772b7aa..550b195bb2fc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -135,10 +135,14 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u8 nexthdr = nh[IP6CB(skb)->nhoff]; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; - fl6->flowi6_oif = skb_dst(skb)->dev->ifindex; + fl6->flowi6_oif = reverse ? skb->skb_iif : oif; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 7a1e0fc1bd4d..e096025b477f 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1823,8 +1823,6 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, if (skb->tstamp.tv64) sk->sk_stamp = skb->tstamp; - msg->msg_namelen = sizeof(*sipx); - if (sipx) { sipx->sipx_family = AF_IPX; sipx->sipx_port = ipx->ipx_source.sock; @@ -1832,6 +1830,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, sipx->sipx_network = IPX_SKB_CB(skb)->ipx_source_net; sipx->sipx_type = ipx->ipx_type; sipx->sipx_zero = 0; + msg->msg_namelen = sizeof(*sipx); } rc = copied; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 0578d4fa00a9..a5e62ef57155 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1385,8 +1385,6 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __func__); - msg->msg_namelen = 0; - skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); if (!skb) @@ -1451,8 +1449,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); - msg->msg_namelen = 0; - do { int chunk; struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 168aff5e60de..c4b7218058b6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1324,8 +1324,6 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, int err = 0; u32 offset; - msg->msg_namelen = 0; - if ((sk->sk_state == IUCV_DISCONN) && skb_queue_empty(&iucv->backlog_skb_q) && skb_queue_empty(&sk->sk_receive_queue) && diff --git a/net/key/af_key.c b/net/key/af_key.c index 911ef03bf8fb..545f047868ad 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3616,7 +3616,6 @@ static int pfkey_recvmsg(struct kiocb *kiocb, if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT)) goto out; - msg->msg_namelen = 0; skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 571db8dd2292..da1a1cee1a08 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -518,9 +518,6 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); - skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; @@ -543,6 +540,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index b8a6039314e8..e6e8408c9e36 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -665,7 +665,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, *addr_len = sizeof(*lsa); if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 8c46b271064a..44441c0c5037 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -197,8 +197,6 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock, if (sk->sk_state & PPPOX_BOUND) goto end; - msg->msg_namelen = 0; - err = 0; skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 6cba486353e8..7b01b9f5846c 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -720,8 +720,6 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, int target; /* Read at least this many bytes */ long timeo; - msg->msg_namelen = 0; - lock_sock(sk); copied = -ENOTCONN; if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN)) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 74fd00c27210..3581736446d5 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1139,12 +1139,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iph_skb(af, skb, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (!iph.fragoffs && skb_nfct_reasm(skb)) { - struct sk_buff *reasm = skb_nfct_reasm(skb); - /* Save fw mark for coming frags */ - reasm->ipvs_property = 1; - reasm->mark = skb->mark; - } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(skb, &related, @@ -1614,12 +1608,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (!iph.fragoffs && skb_nfct_reasm(skb)) { - struct sk_buff *reasm = skb_nfct_reasm(skb); - /* Save fw mark for coming frags. */ - reasm->ipvs_property = 1; - reasm->mark = skb->mark; - } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum, @@ -1671,9 +1659,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, 0, "ip_vs_in: packet continues traversal as normal"); - if (iph.fragoffs && !skb_nfct_reasm(skb)) { + if (iph.fragoffs) { /* Fragment that couldn't be mapped to a conn entry - * and don't have any pointer to a reasm skb * is missing module nf_defrag_ipv6 */ IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); @@ -1756,38 +1743,6 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 /* - * AF_INET6 fragment handling - * Copy info from first fragment, to the rest of them. - */ -static unsigned int -ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm = skb_nfct_reasm(skb); - struct net *net; - - /* Skip if not a "replay" from nf_ct_frag6_output or first fragment. - * ipvs_property is set when checking first fragment - * in ip_vs_in() and ip_vs_out(). - */ - if (reasm) - IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property); - if (!reasm || !reasm->ipvs_property) - return NF_ACCEPT; - - net = skb_net(skb); - if (!net_ipvs(net)->enable) - return NF_ACCEPT; - - /* Copy stored fw mark, saved in ip_vs_{in,out} */ - skb->mark = reasm->mark; - - return NF_ACCEPT; -} - -/* * AF_INET6 handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ @@ -1924,14 +1879,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .priority = 100, }, #ifdef CONFIG_IP_VS_IPV6 - /* After mangle & nat fetch 2:nd fragment and following */ - { - .hook = ip_vs_preroute_frag6, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_NAT_DST + 1, - }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index 9ef22bdce9f1..bed5f7042529 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -65,7 +65,6 @@ static int get_callid(const char *dptr, unsigned int dataoff, static int ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) { - struct sk_buff *reasm = skb_nfct_reasm(skb); struct ip_vs_iphdr iph; unsigned int dataoff, datalen, matchoff, matchlen; const char *dptr; @@ -79,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) /* todo: IPv6 fragments: * I think this only should be done for the first fragment. /HS */ - if (reasm) { - skb = reasm; - dataoff = iph.thoff_reasm + sizeof(struct udphdr); - } else - dataoff = iph.len + sizeof(struct udphdr); + dataoff = iph.len + sizeof(struct udphdr); if (dataoff >= skb->len) return -EINVAL; - /* todo: Check if this will mess-up the reasm skb !!! /HS */ retc = skb_linearize(skb); if (retc < 0) return retc; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8df7f64c6db3..613563555515 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2335,8 +2335,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, } #endif - msg->msg_namelen = 0; - copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 698814bfa7ad..53c19a35fc6d 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1179,10 +1179,9 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, sax->sax25_family = AF_NETROM; skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call, AX25_ADDR_LEN); + msg->msg_namelen = sizeof(*sax); } - msg->msg_namelen = sizeof(*sax); - skb_free_datagram(sk, skb); release_sock(sk); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index d308402b67d8..824c6056bf82 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -807,8 +807,6 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, pr_debug("%p %zu\n", sk, len); - msg->msg_namelen = 0; - lock_sock(sk); if (sk->sk_state == LLCP_CLOSED && diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 313bf1bc848a..5d11f4ac3ecb 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -241,8 +241,6 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return rc; - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2e8286b47c28..ba2548bd85bf 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -244,11 +244,15 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po); static void register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); + if (!po->running) { - if (po->fanout) + if (po->fanout) { __fanout_link(sk, po); - else + } else { dev_add_pack(&po->prot_hook); + rcu_assign_pointer(po->cached_dev, po->prot_hook.dev); + } + sock_hold(sk); po->running = 1; } @@ -266,10 +270,13 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) struct packet_sock *po = pkt_sk(sk); po->running = 0; - if (po->fanout) + if (po->fanout) { __fanout_unlink(sk, po); - else + } else { __dev_remove_pack(&po->prot_hook); + RCU_INIT_POINTER(po->cached_dev, NULL); + } + __sock_put(sk); if (sync) { @@ -432,9 +439,9 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po, pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; - spin_lock(&rb_queue->lock); + spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; - spin_unlock(&rb_queue->lock); + spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } @@ -2052,12 +2059,24 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, return tp_len; } +static struct net_device *packet_cached_dev_get(struct packet_sock *po) +{ + struct net_device *dev; + + rcu_read_lock(); + dev = rcu_dereference(po->cached_dev); + if (dev) + dev_hold(dev); + rcu_read_unlock(); + + return dev; +} + static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb; struct net_device *dev; __be16 proto; - bool need_rls_dev = false; int err, reserve = 0; void *ph; struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; @@ -2070,7 +2089,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) mutex_lock(&po->pg_vec_lock); if (saddr == NULL) { - dev = po->prot_hook.dev; + dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; } else { @@ -2084,19 +2103,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); - need_rls_dev = true; } err = -ENXIO; if (unlikely(dev == NULL)) goto out; - - reserve = dev->hard_header_len; - err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; + reserve = dev->hard_header_len; + size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2173,8 +2190,7 @@ out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: - if (need_rls_dev) - dev_put(dev); + dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; @@ -2212,7 +2228,6 @@ static int packet_snd(struct socket *sock, struct sk_buff *skb; struct net_device *dev; __be16 proto; - bool need_rls_dev = false; unsigned char *addr; int err, reserve = 0; struct virtio_net_hdr vnet_hdr = { 0 }; @@ -2228,7 +2243,7 @@ static int packet_snd(struct socket *sock, */ if (saddr == NULL) { - dev = po->prot_hook.dev; + dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; } else { @@ -2240,19 +2255,17 @@ static int packet_snd(struct socket *sock, proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); - need_rls_dev = true; } err = -ENXIO; - if (dev == NULL) + if (unlikely(dev == NULL)) goto out_unlock; - if (sock->type == SOCK_RAW) - reserve = dev->hard_header_len; - err = -ENETDOWN; - if (!(dev->flags & IFF_UP)) + if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; + if (sock->type == SOCK_RAW) + reserve = dev->hard_header_len; if (po->has_vnet_hdr) { vnet_hdr_len = sizeof(vnet_hdr); @@ -2386,15 +2399,14 @@ static int packet_snd(struct socket *sock, if (err > 0 && (err = net_xmit_errno(err)) != 0) goto out_unlock; - if (need_rls_dev) - dev_put(dev); + dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: - if (dev && need_rls_dev) + if (dev) dev_put(dev); out: return err; @@ -2614,6 +2626,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po = pkt_sk(sk); sk->sk_family = PF_PACKET; po->num = proto; + RCU_INIT_POINTER(po->cached_dev, NULL); sk->sk_destruct = packet_sock_destruct; sk_refcnt_debug_inc(sk); @@ -2660,7 +2673,6 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; - struct sockaddr_ll *sll; int vnet_hdr_len = 0; err = -EINVAL; @@ -2744,22 +2756,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, goto out_free; } - /* - * If the address length field is there to be filled in, we fill - * it in now. + /* You lose any data beyond the buffer you gave. If it worries + * a user program they can ask the device for its MTU + * anyway. */ - - sll = &PACKET_SKB_CB(skb)->sa.ll; - if (sock->type == SOCK_PACKET) - msg->msg_namelen = sizeof(struct sockaddr_pkt); - else - msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); - - /* - * You lose any data beyond the buffer you gave. If it worries a - * user program they can ask the device for its MTU anyway. - */ - copied = skb->len; if (copied > len) { copied = len; @@ -2772,9 +2772,20 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, sock_recv_ts_and_drops(msg, sk, skb); - if (msg->msg_name) + if (msg->msg_name) { + /* If the address length field is there to be filled + * in, we fill it in now. + */ + if (sock->type == SOCK_PACKET) { + msg->msg_namelen = sizeof(struct sockaddr_pkt); + } else { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + msg->msg_namelen = sll->sll_halen + + offsetof(struct sockaddr_ll, sll_addr); + } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, msg->msg_namelen); + } if (pkt_sk(sk)->auxdata) { struct tpacket_auxdata aux; diff --git a/net/packet/internal.h b/net/packet/internal.h index c4e4b4561207..1035fa2d909c 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -113,6 +113,7 @@ struct packet_sock { unsigned int tp_loss:1; unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; + struct net_device __rcu *cached_dev; struct packet_type prot_hook ____cacheline_aligned_in_smp; }; diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 12c30f3e643e..38946b26e471 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -139,9 +139,6 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, MSG_CMSG_COMPAT)) goto out_nofree; - if (addr_len) - *addr_len = sizeof(sa); - skb = skb_recv_datagram(sk, flags, noblock, &rval); if (skb == NULL) goto out_nofree; @@ -162,8 +159,10 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, rval = (flags & MSG_TRUNC) ? skb->len : copylen; - if (msg->msg_name != NULL) - memcpy(msg->msg_name, &sa, sizeof(struct sockaddr_pn)); + if (msg->msg_name != NULL) { + memcpy(msg->msg_name, &sa, sizeof(sa)); + *addr_len = sizeof(sa); + } out: skb_free_datagram(sk, skb); diff --git a/net/rds/recv.c b/net/rds/recv.c index 9f0f17cf6bf9..de339b24ca14 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -410,8 +410,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo); - msg->msg_namelen = 0; - if (msg_flags & MSG_OOB) goto out; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index e98fcfbe6007..33af77246bfe 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1216,7 +1216,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); - struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name; size_t copied; unsigned char *asmptr; struct sk_buff *skb; @@ -1252,8 +1251,11 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - if (srose != NULL) { - memset(srose, 0, msg->msg_namelen); + if (msg->msg_name) { + struct sockaddr_rose *srose; + + memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose)); + srose = msg->msg_name; srose->srose_family = AF_ROSE; srose->srose_addr = rose->dest_addr; srose->srose_call = rose->dest_call; diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 4b48687c3890..898492a8d61b 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -143,10 +143,13 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, /* copy the peer address and timestamp */ if (!continue_call) { - if (msg->msg_name && msg->msg_namelen > 0) + if (msg->msg_name) { + size_t len = + sizeof(call->conn->trans->peer->srx); memcpy(msg->msg_name, - &call->conn->trans->peer->srx, - sizeof(call->conn->trans->peer->srx)); + &call->conn->trans->peer->srx, len); + msg->msg_namelen = len; + } sock_recv_ts_and_drops(msg, &rx->sk, skb); } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a9dfdda9ed1d..2e55f8189502 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -88,7 +88,7 @@ struct fq_sched_data { struct fq_flow internal; /* for non classified or high prio packets */ u32 quantum; u32 initial_quantum; - u32 flow_default_rate;/* rate per flow : bytes per second */ + u32 flow_refill_delay; u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ struct rb_root *fq_root; @@ -115,6 +115,7 @@ static struct fq_flow detached, throttled; static void fq_flow_set_detached(struct fq_flow *f) { f->next = &detached; + f->age = jiffies; } static bool fq_flow_is_detached(const struct fq_flow *f) @@ -209,21 +210,15 @@ static void fq_gc(struct fq_sched_data *q, } } -static const u8 prio2band[TC_PRIO_MAX + 1] = { - 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 -}; - static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) { struct rb_node **p, *parent; struct sock *sk = skb->sk; struct rb_root *root; struct fq_flow *f; - int band; /* warning: no starvation prevention... */ - band = prio2band[skb->priority & TC_PRIO_MAX]; - if (unlikely(band == 0)) + if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL)) return &q->internal; if (unlikely(!sk)) { @@ -372,17 +367,20 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch) } f->qlen++; - flow_queue_add(f, skb); if (skb_is_retransmit(skb)) q->stat_tcp_retrans++; sch->qstats.backlog += qdisc_pkt_len(skb); if (fq_flow_is_detached(f)) { fq_flow_add_tail(&q->new_flows, f); - if (q->quantum > f->credit) - f->credit = q->quantum; + if (time_after(jiffies, f->age + q->flow_refill_delay)) + f->credit = max_t(u32, f->credit, q->quantum); q->inactive_flows--; qdisc_unthrottled(sch); } + + /* Note: this overwrites f->age */ + flow_queue_add(f, skb); + if (unlikely(f == &q->internal)) { q->stat_internal_packets++; qdisc_unthrottled(sch); @@ -460,7 +458,6 @@ begin: fq_flow_add_tail(&q->old_flows, f); } else { fq_flow_set_detached(f); - f->age = jiffies; q->inactive_flows++; } goto begin; @@ -614,6 +611,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_DEFAULT_RATE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, + [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, }; static int fq_change(struct Qdisc *sch, struct nlattr *opt) @@ -655,7 +653,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); if (tb[TCA_FQ_FLOW_DEFAULT_RATE]) - q->flow_default_rate = nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]); + pr_warn_ratelimited("sch_fq: defrate %u ignored.\n", + nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE])); if (tb[TCA_FQ_FLOW_MAX_RATE]) q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); @@ -669,6 +668,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) err = -EINVAL; } + if (tb[TCA_FQ_FLOW_REFILL_DELAY]) { + u32 usecs_delay = nla_get_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]) ; + + q->flow_refill_delay = usecs_to_jiffies(usecs_delay); + } + if (!err) err = fq_resize(q, fq_log); @@ -704,7 +709,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) q->flow_plimit = 100; q->quantum = 2 * psched_mtu(qdisc_dev(sch)); q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); - q->flow_default_rate = 0; + q->flow_refill_delay = msecs_to_jiffies(40); q->flow_max_rate = ~0U; q->rate_enable = 1; q->new_flows.first = NULL; @@ -731,15 +736,16 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) if (opts == NULL) goto nla_put_failure; - /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore, - * do not bother giving its value - */ + /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */ + if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) || nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) || nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) || nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) || + nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, + jiffies_to_usecs(q->flow_refill_delay)) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 1aaf1b6e51a2..6ddda282f9c7 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -21,6 +21,7 @@ #include #include #include +#include /* Simple Token Bucket Filter. @@ -117,6 +118,22 @@ struct tbf_sched_data { }; +/* + * Return length of individual segments of a gso packet, + * including all headers (MAC, IP, TCP/UDP) + */ +static unsigned int skb_gso_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); + return hdr_len + shinfo->gso_size; +} + /* GSO packet is too big, segment it so that tbf can transmit * each segment in time */ @@ -136,12 +153,8 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) while (segs) { nskb = segs->next; segs->next = NULL; - if (likely(segs->len <= q->max_size)) { - qdisc_skb_cb(segs)->pkt_len = segs->len; - ret = qdisc_enqueue(segs, q->qdisc); - } else { - ret = qdisc_reshape_fail(skb, sch); - } + qdisc_skb_cb(segs)->pkt_len = segs->len; + ret = qdisc_enqueue(segs, q->qdisc); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) sch->qstats.drops++; @@ -163,7 +176,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb)) + if (skb_is_gso(skb) && skb_gso_seglen(skb) <= q->max_size) return tbf_segment(skb, sch); return qdisc_reshape_fail(skb, sch); } @@ -316,6 +329,11 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) if (max_size < 0) goto done; + if (max_size < psched_mtu(qdisc_dev(sch))) + pr_warn_ratelimited("sch_tbf: burst %u is lower than device %s mtu (%u) !\n", + max_size, qdisc_dev(sch)->name, + psched_mtu(qdisc_dev(sch))); + if (q->qdisc != &noop_qdisc) { err = fifo_set_limit(q->qdisc, qopt->limit); if (err) diff --git a/net/socket.c b/net/socket.c index c226aceee65b..e83c416708af 100644 --- a/net/socket.c +++ b/net/socket.c @@ -221,12 +221,13 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, int err; int len; + BUG_ON(klen > sizeof(struct sockaddr_storage)); err = get_user(len, ulen); if (err) return err; if (len > klen) len = klen; - if (len < 0 || len > sizeof(struct sockaddr_storage)) + if (len < 0) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) @@ -1840,8 +1841,10 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, msg.msg_iov = &iov; iov.iov_len = size; iov.iov_base = ubuf; - msg.msg_name = (struct sockaddr *)&address; - msg.msg_namelen = sizeof(address); + /* Save some cycles and don't copy the address if not needed */ + msg.msg_name = addr ? (struct sockaddr *)&address : NULL; + /* We assume all kernel code knows the size of sockaddr_storage */ + msg.msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, size, flags); @@ -1970,7 +1973,7 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) return -EFAULT; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) - return -EINVAL; + kmsg->msg_namelen = sizeof(struct sockaddr_storage); return 0; } @@ -2221,16 +2224,14 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, goto out; } - /* - * Save the user-mode address (verify_iovec will change the - * kernel msghdr to use the kernel address space) + /* Save the user-mode address (verify_iovec will change the + * kernel msghdr to use the kernel address space) */ - uaddr = (__force void __user *)msg_sys->msg_name; uaddr_len = COMPAT_NAMELEN(msg); - if (MSG_CMSG_COMPAT & flags) { + if (MSG_CMSG_COMPAT & flags) err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE); - } else + else err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE); if (err < 0) goto out_freeiov; @@ -2239,6 +2240,9 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + /* We assume all kernel code knows the size of sockaddr_storage */ + msg_sys->msg_namelen = 0; + if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 6cc7ddd2fb7c..dffdbeac18ca 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -984,9 +984,6 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, goto exit; } - /* will be updated in set_orig_addr() if needed */ - m->msg_namelen = 0; - timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); restart: @@ -1095,9 +1092,6 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, goto exit; } - /* will be updated in set_orig_addr() if needed */ - m->msg_namelen = 0; - target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len); timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c1f403bed683..01625ccc3ae6 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1754,7 +1754,6 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { struct unix_sock *u = unix_sk(sk); - msg->msg_namelen = 0; if (u->addr) { msg->msg_namelen = u->addr->len; memcpy(msg->msg_name, u->addr->name, u->addr->len); @@ -1778,8 +1777,6 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags&MSG_OOB) goto out; - msg->msg_namelen = 0; - err = mutex_lock_interruptible(&u->readlock); if (err) { err = sock_intr_errno(sock_rcvtimeo(sk, noblock)); @@ -1924,8 +1921,6 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, target = sock_rcvlowat(sk, flags&MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT); - msg->msg_namelen = 0; - /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 545c08b8a1d4..5adfd94c5b85 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1662,8 +1662,6 @@ vsock_stream_recvmsg(struct kiocb *kiocb, vsk = vsock_sk(sk); err = 0; - msg->msg_namelen = 0; - lock_sock(sk); if (sk->sk_state != SS_CONNECTED) { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 9d6986634e0b..687360da62d9 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1746,8 +1746,6 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, if (flags & MSG_OOB || flags & MSG_ERRQUEUE) return -EOPNOTSUPP; - msg->msg_namelen = 0; - /* Retrieve the head sk_buff from the socket's receive queue. */ err = 0; skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 45a3ab5612c1..7622789d3750 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1340,10 +1340,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, if (sx25) { sx25->sx25_family = AF_X25; sx25->sx25_addr = x25->dest_addr; + msg->msg_namelen = sizeof(*sx25); } - msg->msg_namelen = sizeof(struct sockaddr_x25); - x25_check_rbuf(sk); rc = copied; out_free_dgram: