From b7aa0bf70c4afb9e38be25f5c0922498d0f8684c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Apr 2007 16:16:32 -0700 Subject: [NET]: convert network timestamps to ktime_t We currently use a special structure (struct skb_timeval) and plain 'struct timeval' to store packet timestamps in sk_buffs and struct sock. This has some drawbacks : - Fixed resolution of micro second. - Waste of space on 64bit platforms where sizeof(struct timeval)=16 I suggest using ktime_t that is a nice abstraction of high resolution time services, currently capable of nanosecond resolution. As sizeof(ktime_t) is 8 bytes, using ktime_t in 'struct sock' permits a 8 byte shrink of this structure on 64bit architectures. Some other structures also benefit from this size reduction (struct ipq in ipv4/ip_fragment.c, struct frag_queue in ipv6/reassembly.c, ...) Once this ktime infrastructure adopted, we can more easily provide nanosecond resolution on top of it. (ioctl SIOCGSTAMPNS and/or SO_TIMESTAMPNS/SCM_TIMESTAMPNS) Note : this patch includes a bug correction in compat_sock_get_timestamp() where a "err = 0;" was missing (so this syscall returned -ENOENT instead of 0) Signed-off-by: Eric Dumazet CC: Stephen Hemminger CC: John find Signed-off-by: David S. Miller --- kernel/time.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/time.c b/kernel/time.c index 2f47888e46c9..a1439f421d0b 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -469,6 +469,7 @@ struct timeval ns_to_timeval(const s64 nsec) return tv; } +EXPORT_SYMBOL(ns_to_timeval); /* * Convert jiffies to milliseconds and back. -- cgit v1.2.3 From 641b9e0e8b7f96425da6ce98f3361e3af0baee29 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 16 Mar 2007 01:18:42 -0700 Subject: [NET_SCHED]: Use ktime as clocksource Get rid of the manual clock source selection mess and use ktime. Also use a scalar representation, which allows to clean up pkt_sched.h a bit more and results in less ktime_to_ns() calls in most cases. The PSCHED_US2JIFFIE/PSCHED_JIFFIE2US macros are implemented quite inefficient by this patch, following patches will convert all qdiscs to hrtimers and get rid of them entirely. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- kernel/hrtimer.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index b74860aaf5f1..f5cfde8c9025 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -59,6 +59,7 @@ ktime_t ktime_get(void) return timespec_to_ktime(now); } +EXPORT_SYMBOL_GPL(ktime_get); /** * ktime_get_real - get the real (wall-) time in ktime_t format -- cgit v1.2.3 From 27a884dc3cb63b93c2b3b643f5b31eed5f8a4d26 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 19 Apr 2007 20:29:13 -0700 Subject: [SK_BUFF]: Convert skb->tail to sk_buff_data_t So that it is also an offset from skb->head, reduces its size from 8 to 4 bytes on 64bit architectures, allowing us to combine the 4 bytes hole left by the layer headers conversion, reducing struct sk_buff size to 256 bytes, i.e. 4 64byte cachelines, and since the sk_buff slab cache is SLAB_HWCACHE_ALIGN... :-) Many calculations that previously required that skb->{transport,network, mac}_header be first converted to a pointer now can be done directly, being meaningful as offsets or pointers. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- kernel/audit.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 76c9a11b72d6..ea8521417d13 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1073,7 +1073,7 @@ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, goto out; } va_copy(args2, args); - len = vsnprintf(skb->tail, avail, fmt, args); + len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args); if (len >= avail) { /* The printk buffer is 1024 bytes long, so if we get * here and AUDIT_BUFSIZ is at least 1024, then we can @@ -1082,7 +1082,7 @@ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); if (!avail) goto out; - len = vsnprintf(skb->tail, avail, fmt, args2); + len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); } if (len > 0) skb_put(skb, len); @@ -1143,7 +1143,7 @@ void audit_log_hex(struct audit_buffer *ab, const unsigned char *buf, return; } - ptr = skb->tail; + ptr = skb_tail_pointer(skb); for (i=0; i>4]; /* Upper nibble */ *ptr++ = hex[buf[i] & 0x0F]; /* Lower nibble */ @@ -1175,7 +1175,7 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen, if (!avail) return; } - ptr = skb->tail; + ptr = skb_tail_pointer(skb); *ptr++ = '"'; memcpy(ptr, string, slen); ptr += slen; -- cgit v1.2.3 From b529ccf2799c14346d1518e9bdf1f88f03643e99 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 25 Apr 2007 19:08:35 -0700 Subject: [NETLINK]: Introduce nlmsg_hdr() helper For the common "(struct nlmsghdr *)skb->data" sequence, so that we reduce the number of direct accesses to skb->data and for consistency with all the other cast skb member helpers. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- kernel/audit.c | 6 +++--- kernel/taskstats.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index ea8521417d13..80a7457dadbf 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -151,7 +151,7 @@ struct audit_buffer { static void audit_set_pid(struct audit_buffer *ab, pid_t pid) { - struct nlmsghdr *nlh = (struct nlmsghdr *)ab->skb->data; + struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); nlh->nlmsg_pid = pid; } @@ -750,7 +750,7 @@ static void audit_receive_skb(struct sk_buff *skb) u32 rlen; while (skb->len >= NLMSG_SPACE(0)) { - nlh = (struct nlmsghdr *)skb->data; + nlh = nlmsg_hdr(skb); if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) return; rlen = NLMSG_ALIGN(nlh->nlmsg_len); @@ -1268,7 +1268,7 @@ void audit_log_end(struct audit_buffer *ab) audit_log_lost("rate limit exceeded"); } else { if (audit_pid) { - struct nlmsghdr *nlh = (struct nlmsghdr *)ab->skb->data; + struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); nlh->nlmsg_len = ab->skb->len - NLMSG_SPACE(0); skb_queue_tail(&audit_skb_queue, ab->skb); ab->skb = NULL; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 4c3476fa058d..ad7d2392cb0e 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -102,7 +102,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, */ static int send_reply(struct sk_buff *skb, pid_t pid) { - struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data); + struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); int rc; @@ -121,7 +121,7 @@ static int send_reply(struct sk_buff *skb, pid_t pid) static void send_cpu_listeners(struct sk_buff *skb, struct listener_list *listeners) { - struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data); + struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); struct listener *s, *tmp; struct sk_buff *skb_next, *skb_cur = skb; void *reply = genlmsg_data(genlhdr); -- cgit v1.2.3 From 85795d64eddd4546375f5ee37bedd88cb5bc4ece Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sat, 24 Mar 2007 21:35:33 -0700 Subject: [TCP] tcp_probe: improvements for net-2.6.22 Change tcp_probe to use ktime (needed to add one export). Add option to only get events when cwnd changes - from Doug Leith Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- kernel/time.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/time.c b/kernel/time.c index a1439f421d0b..ba18ec4899bd 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -452,6 +452,7 @@ struct timespec ns_to_timespec(const s64 nsec) return ts; } +EXPORT_SYMBOL(ns_to_timespec); /** * ns_to_timeval - Convert nanoseconds to timeval -- cgit v1.2.3 From af65bdfce98d7965fbe93a48b8128444a2eea024 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 20 Apr 2007 14:14:21 -0700 Subject: [NETLINK]: Switch cb_lock spinlock to mutex and allow to override it Switch cb_lock to mutex and allow netlink kernel users to override it with a subsystem specific mutex for consistent locking in dump callbacks. All netlink_dump_start users have been audited not to rely on any side-effects of the previously used spinlock. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- kernel/audit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 80a7457dadbf..4e9d20829681 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -795,7 +795,7 @@ static int __init audit_init(void) printk(KERN_INFO "audit: initializing netlink socket (%s)\n", audit_default ? "enabled" : "disabled"); audit_sock = netlink_kernel_create(NETLINK_AUDIT, 0, audit_receive, - THIS_MODULE); + NULL, THIS_MODULE); if (!audit_sock) audit_panic("cannot initialize netlink socket"); else -- cgit v1.2.3 From e19dff1fdd99a25819af74cf0710e147fff4fd3a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 26 Apr 2007 15:46:56 -0700 Subject: [AF_RXRPC]: Make it possible to merely try to cancel timers from a module Export try_to_del_timer_sync() for use by the AF_RXRPC module. Signed-off-by: David Howells Signed-off-by: David S. Miller --- kernel/timer.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/timer.c b/kernel/timer.c index dd6c2c1c561b..b22bd39740dd 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -505,6 +505,8 @@ out: return ret; } +EXPORT_SYMBOL(try_to_del_timer_sync); + /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated -- cgit v1.2.3 From 39bc89fd4019b164002adaacef92c4140e37955a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 25 Apr 2007 20:50:03 -0700 Subject: make SysRq-T show all tasks again show_state() (SysRq-T) developed the buggy habbit of not showing TASK_RUNNING tasks. This was due to the mistaken belief that state_filter == -1 would be a pass-through filter - while in reality it did not let TASK_RUNNING == 0 p->state values through. Fix this by restoring the original '!state_filter means all tasks' special-case i had in the original version. Test-built and test-booted on i686, SysRq-T now works as intended. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index b9a683730148..960d7c5fca39 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4746,7 +4746,7 @@ void show_state_filter(unsigned long state_filter) * console might take alot of time: */ touch_nmi_watchdog(); - if (p->state & state_filter) + if (!state_filter || (p->state & state_filter)) show_task(p); } while_each_thread(g, p); -- cgit v1.2.3