From 309ce156aa27f29338438011d292a8d6496623d3 Mon Sep 17 00:00:00 2001 From: Jayamohan Kallickal Date: Sat, 20 Feb 2010 08:02:10 +0530 Subject: [SCSI] libiscsi: Make iscsi_eh_target_reset start with session reset The iscsi_eh_target_reset has been modified to attempt target reset only. If it fails, then iscsi_eh_session_reset will be called. Signed-off-by: Mike Christie Signed-off-by: Jayamohan Kallickal Signed-off-by: James Bottomley --- include/scsi/libiscsi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index ff92b46f5153..ae5196aae1a5 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -338,7 +338,8 @@ struct iscsi_host { extern int iscsi_change_queue_depth(struct scsi_device *sdev, int depth, int reason); extern int iscsi_eh_abort(struct scsi_cmnd *sc); -extern int iscsi_eh_target_reset(struct scsi_cmnd *sc); +extern int iscsi_eh_recover_target(struct scsi_cmnd *sc); +extern int iscsi_eh_session_reset(struct scsi_cmnd *sc); extern int iscsi_eh_device_reset(struct scsi_cmnd *sc); extern int iscsi_queuecommand(struct scsi_cmnd *sc, void (*done)(struct scsi_cmnd *)); -- cgit v1.2.2 From 881245dcff29df992d8431392a41fb81549129f9 Mon Sep 17 00:00:00 2001 From: William Cohen Date: Tue, 9 Mar 2010 09:26:04 +0100 Subject: Add DocBook documentation for the block tracepoints. This patch adds a simple description of the various block tracepoints available in the kernel. Signed-off-by: William Cohen Acked-by: Randy Dunlap Signed-off-by: Jens Axboe --- include/trace/events/block.h | 164 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 164 insertions(+) (limited to 'include') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 5fb72733331e..d870a918559c 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -40,6 +40,16 @@ DECLARE_EVENT_CLASS(block_rq_with_error, __entry->nr_sector, __entry->errors) ); +/** + * block_rq_abort - abort block operation request + * @q: queue containing the block operation request + * @rq: block IO operation request + * + * Called immediately after pending block IO operation request @rq in + * queue @q is aborted. The fields in the operation request @rq + * can be examined to determine which device and sectors the pending + * operation would access. + */ DEFINE_EVENT(block_rq_with_error, block_rq_abort, TP_PROTO(struct request_queue *q, struct request *rq), @@ -47,6 +57,15 @@ DEFINE_EVENT(block_rq_with_error, block_rq_abort, TP_ARGS(q, rq) ); +/** + * block_rq_requeue - place block IO request back on a queue + * @q: queue holding operation + * @rq: block IO operation request + * + * The block operation request @rq is being placed back into queue + * @q. For some reason the request was not completed and needs to be + * put back in the queue. + */ DEFINE_EVENT(block_rq_with_error, block_rq_requeue, TP_PROTO(struct request_queue *q, struct request *rq), @@ -54,6 +73,17 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue, TP_ARGS(q, rq) ); +/** + * block_rq_complete - block IO operation completed by device driver + * @q: queue containing the block operation request + * @rq: block operations request + * + * The block_rq_complete tracepoint event indicates that some portion + * of operation request has been completed by the device driver. If + * the @rq->bio is %NULL, then there is absolutely no additional work to + * do for the request. If @rq->bio is non-NULL then there is + * additional work required to complete the request. + */ DEFINE_EVENT(block_rq_with_error, block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq), @@ -95,6 +125,16 @@ DECLARE_EVENT_CLASS(block_rq, __entry->nr_sector, __entry->comm) ); +/** + * block_rq_insert - insert block operation request into queue + * @q: target queue + * @rq: block IO operation request + * + * Called immediately before block operation request @rq is inserted + * into queue @q. The fields in the operation request @rq struct can + * be examined to determine which device and sectors the pending + * operation would access. + */ DEFINE_EVENT(block_rq, block_rq_insert, TP_PROTO(struct request_queue *q, struct request *rq), @@ -102,6 +142,14 @@ DEFINE_EVENT(block_rq, block_rq_insert, TP_ARGS(q, rq) ); +/** + * block_rq_issue - issue pending block IO request operation to device driver + * @q: queue holding operation + * @rq: block IO operation operation request + * + * Called when block operation request @rq from queue @q is sent to a + * device driver for processing. + */ DEFINE_EVENT(block_rq, block_rq_issue, TP_PROTO(struct request_queue *q, struct request *rq), @@ -109,6 +157,17 @@ DEFINE_EVENT(block_rq, block_rq_issue, TP_ARGS(q, rq) ); +/** + * block_bio_bounce - used bounce buffer when processing block operation + * @q: queue holding the block operation + * @bio: block operation + * + * A bounce buffer was used to handle the block operation @bio in @q. + * This occurs when hardware limitations prevent a direct transfer of + * data between the @bio data memory area and the IO device. Use of a + * bounce buffer requires extra copying of data and decreases + * performance. + */ TRACE_EVENT(block_bio_bounce, TP_PROTO(struct request_queue *q, struct bio *bio), @@ -138,6 +197,14 @@ TRACE_EVENT(block_bio_bounce, __entry->nr_sector, __entry->comm) ); +/** + * block_bio_complete - completed all work on the block operation + * @q: queue holding the block operation + * @bio: block operation completed + * + * This tracepoint indicates there is no further work to do on this + * block IO operation @bio. + */ TRACE_EVENT(block_bio_complete, TP_PROTO(struct request_queue *q, struct bio *bio), @@ -193,6 +260,14 @@ DECLARE_EVENT_CLASS(block_bio, __entry->nr_sector, __entry->comm) ); +/** + * block_bio_backmerge - merging block operation to the end of an existing operation + * @q: queue holding operation + * @bio: new block operation to merge + * + * Merging block request @bio to the end of an existing block request + * in queue @q. + */ DEFINE_EVENT(block_bio, block_bio_backmerge, TP_PROTO(struct request_queue *q, struct bio *bio), @@ -200,6 +275,14 @@ DEFINE_EVENT(block_bio, block_bio_backmerge, TP_ARGS(q, bio) ); +/** + * block_bio_frontmerge - merging block operation to the beginning of an existing operation + * @q: queue holding operation + * @bio: new block operation to merge + * + * Merging block IO operation @bio to the beginning of an existing block + * operation in queue @q. + */ DEFINE_EVENT(block_bio, block_bio_frontmerge, TP_PROTO(struct request_queue *q, struct bio *bio), @@ -207,6 +290,13 @@ DEFINE_EVENT(block_bio, block_bio_frontmerge, TP_ARGS(q, bio) ); +/** + * block_bio_queue - putting new block IO operation in queue + * @q: queue holding operation + * @bio: new block operation + * + * About to place the block IO operation @bio into queue @q. + */ DEFINE_EVENT(block_bio, block_bio_queue, TP_PROTO(struct request_queue *q, struct bio *bio), @@ -243,6 +333,15 @@ DECLARE_EVENT_CLASS(block_get_rq, __entry->nr_sector, __entry->comm) ); +/** + * block_getrq - get a free request entry in queue for block IO operations + * @q: queue for operations + * @bio: pending block IO operation + * @rw: low bit indicates a read (%0) or a write (%1) + * + * A request struct for queue @q has been allocated to handle the + * block IO operation @bio. + */ DEFINE_EVENT(block_get_rq, block_getrq, TP_PROTO(struct request_queue *q, struct bio *bio, int rw), @@ -250,6 +349,17 @@ DEFINE_EVENT(block_get_rq, block_getrq, TP_ARGS(q, bio, rw) ); +/** + * block_sleeprq - waiting to get a free request entry in queue for block IO operation + * @q: queue for operation + * @bio: pending block IO operation + * @rw: low bit indicates a read (%0) or a write (%1) + * + * In the case where a request struct cannot be provided for queue @q + * the process needs to wait for an request struct to become + * available. This tracepoint event is generated each time the + * process goes to sleep waiting for request struct become available. + */ DEFINE_EVENT(block_get_rq, block_sleeprq, TP_PROTO(struct request_queue *q, struct bio *bio, int rw), @@ -257,6 +367,14 @@ DEFINE_EVENT(block_get_rq, block_sleeprq, TP_ARGS(q, bio, rw) ); +/** + * block_plug - keep operations requests in request queue + * @q: request queue to plug + * + * Plug the request queue @q. Do not allow block operation requests + * to be sent to the device driver. Instead, accumulate requests in + * the queue to improve throughput performance of the block device. + */ TRACE_EVENT(block_plug, TP_PROTO(struct request_queue *q), @@ -293,6 +411,13 @@ DECLARE_EVENT_CLASS(block_unplug, TP_printk("[%s] %d", __entry->comm, __entry->nr_rq) ); +/** + * block_unplug_timer - timed release of operations requests in queue to device driver + * @q: request queue to unplug + * + * Unplug the request queue @q because a timer expired and allow block + * operation requests to be sent to the device driver. + */ DEFINE_EVENT(block_unplug, block_unplug_timer, TP_PROTO(struct request_queue *q), @@ -300,6 +425,13 @@ DEFINE_EVENT(block_unplug, block_unplug_timer, TP_ARGS(q) ); +/** + * block_unplug_io - release of operations requests in request queue + * @q: request queue to unplug + * + * Unplug request queue @q because device driver is scheduled to work + * on elements in the request queue. + */ DEFINE_EVENT(block_unplug, block_unplug_io, TP_PROTO(struct request_queue *q), @@ -307,6 +439,17 @@ DEFINE_EVENT(block_unplug, block_unplug_io, TP_ARGS(q) ); +/** + * block_split - split a single bio struct into two bio structs + * @q: queue containing the bio + * @bio: block operation being split + * @new_sector: The starting sector for the new bio + * + * The bio request @bio in request queue @q needs to be split into two + * bio requests. The newly created @bio request starts at + * @new_sector. This split may be required due to hardware limitation + * such as operation crossing device boundaries in a RAID system. + */ TRACE_EVENT(block_split, TP_PROTO(struct request_queue *q, struct bio *bio, @@ -337,6 +480,16 @@ TRACE_EVENT(block_split, __entry->comm) ); +/** + * block_remap - map request for a partition to the raw device + * @q: queue holding the operation + * @bio: revised operation + * @dev: device for the operation + * @from: original sector for the operation + * + * An operation for a partition on a block device has been mapped to the + * raw block device. + */ TRACE_EVENT(block_remap, TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev, @@ -370,6 +523,17 @@ TRACE_EVENT(block_remap, (unsigned long long)__entry->old_sector) ); +/** + * block_rq_remap - map request for a block operation request + * @q: queue holding the operation + * @rq: block IO operation request + * @dev: device for the operation + * @from: original sector for the operation + * + * The block operation request @rq in @q has been remapped. The block + * operation request @rq holds the current information and @from hold + * the original sector. + */ TRACE_EVENT(block_rq_remap, TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev, -- cgit v1.2.2 From 62bb2ac5cb6c2f813e151617525ec518e2d1c649 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 17 Feb 2010 21:27:26 +0100 Subject: mac80211: deprecate RX status noise The noise value as is won't be used, isn't filled by most drivers and doesn't really make a whole lot of sense on a per packet basis -- proper cfg80211 survey support in mac80211 will need to be different. Mark the struct member as deprecated so it will be removed from drivers. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 45d7d44d7cbe..936bc410d061 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -543,7 +543,7 @@ enum mac80211_rx_flags { * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* - * @noise: noise when receiving this frame, in dBm. + * @noise: noise when receiving this frame, in dBm (DEPRECATED). * @antenna: antenna used * @rate_idx: index of data rate into band's supported rates or MCS index if * HT rates are use (RX_FLAG_HT) @@ -554,7 +554,7 @@ struct ieee80211_rx_status { enum ieee80211_band band; int freq; int signal; - int noise; + int noise __deprecated; int antenna; int rate_idx; int flag; -- cgit v1.2.2 From 04e82ffb0f02e645f3dde5128ef39d425a8b3c6d Mon Sep 17 00:00:00 2001 From: Peter Huewe Date: Wed, 10 Mar 2010 11:55:05 +0900 Subject: serial: sh-sci: Fix build failure for non-sh architectures. This patch fixes a build failure for various arm based defconfigs [1][2][3] and maybe other architectures/configs. The build failure was introduced by the sh specific patch [4] "serial: sh-sci: Add DMA support" by Guennadi Liakhovetski Patch against linux-next of 20100309 References: [1] http://kisskb.ellerman.id.au/kisskb/buildresult/2248992/ [2] http://kisskb.ellerman.id.au/kisskb/buildresult/2248996/ [3] http://kisskb.ellerman.id.au/kisskb/buildresult/2248998/ [4] http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git;a=commit;h=73a19e4c0301908ce6346715fd08a74308451f5a Signed-off-by: Peter Huewe Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 1b177d29a7f0..193d4bfe42ff 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -2,7 +2,9 @@ #define __LINUX_SERIAL_SCI_H #include +#ifdef CONFIG_SERIAL_SH_SCI_DMA #include +#endif /* * Generic header for SuperH SCI(F) (used by sh/sh64/h8300 and related parts) @@ -30,8 +32,10 @@ struct plat_sci_port { upf_t flags; /* UPF_* flags */ char *clk; /* clock string */ struct device *dma_dev; +#ifdef CONFIG_SERIAL_SH_SCI_DMA enum sh_dmae_slave_chan_id dma_slave_tx; enum sh_dmae_slave_chan_id dma_slave_rx; +#endif }; #endif /* __LINUX_SERIAL_SCI_H */ -- cgit v1.2.2 From 3f6da3905398826d85731247e7fbcf53400c18bd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 5 Mar 2010 13:01:18 +0100 Subject: perf: Rework and fix the arch CPU-hotplug hooks Remove the hw_perf_event_*() hotplug hooks in favour of per PMU hotplug notifiers. This has the advantage of reducing the static weak interface as well as exposing all hotplug actions to the PMU. Use this to fix x86 hotplug usage where we did things in ONLINE which should have been done in UP_PREPARE or STARTING. Signed-off-by: Peter Zijlstra Cc: Paul Mundt Cc: paulus@samba.org Cc: eranian@google.com Cc: robert.richter@amd.com Cc: fweisbec@gmail.com Cc: Arnaldo Carvalho de Melo LKML-Reference: <20100305154128.736225361@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6f8cd7da1a01..80acbf3d5de1 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -936,5 +936,21 @@ static inline void perf_event_disable(struct perf_event *event) { } #define perf_output_put(handle, x) \ perf_output_copy((handle), &(x), sizeof(x)) +/* + * This has to have a higher priority than migration_notifier in sched.c. + */ +#define perf_cpu_notifier(fn) \ +do { \ + static struct notifier_block fn##_nb __cpuinitdata = \ + { .notifier_call = fn, .priority = 20 }; \ + fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_STARTING, \ + (void *)(unsigned long)smp_processor_id()); \ + fn(&fn##_nb, (unsigned long)CPU_ONLINE, \ + (void *)(unsigned long)smp_processor_id()); \ + register_cpu_notifier(&fn##_nb); \ +} while (0) + #endif /* __KERNEL__ */ #endif /* _LINUX_PERF_EVENT_H */ -- cgit v1.2.2 From 5331d7b84613b8325362dde53dc2bff2fb87d351 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 4 Mar 2010 21:15:56 +0100 Subject: perf: Introduce new perf_fetch_caller_regs() for hot regs snapshot Events that trigger overflows by interrupting a context can use get_irq_regs() or task_pt_regs() to retrieve the state when the event triggered. But this is not the case for some other class of events like trace events as tracepoints are executed in the same context than the code that triggered the event. It means we need a different api to capture the regs there, namely we need a hot snapshot to get the most important informations for perf: the instruction pointer to get the event origin, the frame pointer for the callchain, the code segment for user_mode() tests (we always use __KERNEL_CS as trace events always occur from the kernel) and the eflags for further purposes. v2: rename perf_save_regs to perf_fetch_caller_regs as per Masami's suggestion. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Arnaldo Carvalho de Melo Cc: Masami Hiramatsu Cc: Jason Baron Cc: Archs --- include/linux/perf_event.h | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 80acbf3d5de1..70cffd052c04 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -452,6 +452,7 @@ enum perf_callchain_context { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 @@ -847,6 +848,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) __perf_sw_event(event_id, nr, nmi, regs, addr); } +extern void +perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); + +/* + * Take a snapshot of the regs. Skip ip and frame pointer to + * the nth caller. We only need a few of the regs: + * - ip for PERF_SAMPLE_IP + * - cs for user_mode() tests + * - bp for callchains + * - eflags, for future purposes, just in case + */ +static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) +{ + unsigned long ip; + + memset(regs, 0, sizeof(*regs)); + + switch (skip) { + case 1 : + ip = CALLER_ADDR0; + break; + case 2 : + ip = CALLER_ADDR1; + break; + case 3 : + ip = CALLER_ADDR2; + break; + case 4: + ip = CALLER_ADDR3; + break; + /* No need to support further for now */ + default: + ip = 0; + } + + return perf_arch_fetch_caller_regs(regs, ip, skip); +} + extern void __perf_event_mmap(struct vm_area_struct *vma); static inline void perf_event_mmap(struct vm_area_struct *vma) @@ -880,7 +919,8 @@ static inline bool perf_paranoid_kernel(void) } extern void perf_event_init(void); -extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size); +extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, + int entry_size, struct pt_regs *regs); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags -- cgit v1.2.2 From c530665c31c0140b74ca7689e7f836177796e5bd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 3 Mar 2010 07:16:16 +0100 Subject: perf: Take a hot regs snapshot for trace events We are taking a wrong regs snapshot when a trace event triggers. Either we use get_irq_regs(), which gives us the interrupted registers if we are in an interrupt, or we use task_pt_regs() which gives us the state before we entered the kernel, assuming we are lucky enough to be no kernel thread, in which case task_pt_regs() returns the initial set of regs when the kernel thread was started. What we want is different. We need a hot snapshot of the regs, so that we can get the instruction pointer to record in the sample, the frame pointer for the callchain, and some other things. Let's use the new perf_fetch_caller_regs() for that. Comparison with perf record -e lock: -R -a -f -g Before: perf [kernel] [k] __do_softirq | --- __do_softirq | |--55.16%-- __open | --44.84%-- __write_nocancel After: perf [kernel] [k] perf_tp_event | --- perf_tp_event | |--41.07%-- lock_acquire | | | |--39.36%-- _raw_spin_lock | | | | | |--7.81%-- hrtimer_interrupt | | | smp_apic_timer_interrupt | | | apic_timer_interrupt The old case was producing unreliable callchains. Now having right frame and instruction pointers, we have the trace we want. Also syscalls and kprobe events already have the right regs, let's use them instead of wasting a retrieval. v2: Follow the rename perf_save_regs() -> perf_fetch_caller_regs() Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Arnaldo Carvalho de Melo Cc: Masami Hiramatsu Cc: Jason Baron Cc: Archs --- include/linux/ftrace_event.h | 7 +++++-- include/trace/ftrace.h | 6 +++++- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 6b7c444ab8f6..ac424f18ce63 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -187,6 +187,9 @@ do { \ #ifdef CONFIG_PERF_EVENTS struct perf_event; + +DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); + extern int ftrace_profile_enable(int event_id); extern void ftrace_profile_disable(int event_id); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, @@ -198,11 +201,11 @@ ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp, static inline void ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr, - u64 count, unsigned long irq_flags) + u64 count, unsigned long irq_flags, struct pt_regs *regs) { struct trace_entry *entry = raw_data; - perf_tp_event(entry->type, addr, count, raw_data, size); + perf_tp_event(entry->type, addr, count, raw_data, size, regs); perf_swevent_put_recursion_context(rctx); local_irq_restore(irq_flags); } diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 0804cd594803..f31bb8b9777c 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -764,6 +764,7 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ struct ftrace_raw_##call *entry; \ u64 __addr = 0, __count = 1; \ unsigned long irq_flags; \ + struct pt_regs *__regs; \ int __entry_size; \ int __data_size; \ int rctx; \ @@ -784,8 +785,11 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ \ { assign; } \ \ + __regs = &__get_cpu_var(perf_trace_regs); \ + perf_fetch_caller_regs(__regs, 2); \ + \ ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr, \ - __count, irq_flags); \ + __count, irq_flags, __regs); \ } #undef DEFINE_EVENT -- cgit v1.2.2 From 97d5a22005f38057b4bc0d95f81cd26510268794 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 5 Mar 2010 05:35:37 +0100 Subject: perf: Drop the obsolete profile naming for trace events Drop the obsolete "profile" naming used by perf for trace events. Perf can now do more than simple events counting, so generalize the API naming. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Masami Hiramatsu Cc: Jason Baron --- include/linux/ftrace_event.h | 16 ++++++++-------- include/linux/syscalls.h | 24 ++++++++++++------------ include/trace/ftrace.h | 38 +++++++++++++++++++------------------- include/trace/syscall.h | 8 ++++---- 4 files changed, 43 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index ac424f18ce63..c0f4b364c711 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -131,12 +131,12 @@ struct ftrace_event_call { void *mod; void *data; - int profile_count; - int (*profile_enable)(struct ftrace_event_call *); - void (*profile_disable)(struct ftrace_event_call *); + int perf_refcount; + int (*perf_event_enable)(struct ftrace_event_call *); + void (*perf_event_disable)(struct ftrace_event_call *); }; -#define FTRACE_MAX_PROFILE_SIZE 2048 +#define PERF_MAX_TRACE_SIZE 2048 #define MAX_FILTER_PRED 32 #define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ @@ -190,17 +190,17 @@ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -extern int ftrace_profile_enable(int event_id); -extern void ftrace_profile_disable(int event_id); +extern int perf_trace_enable(int event_id); +extern void perf_trace_disable(int event_id); extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); extern void * -ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp, +perf_trace_buf_prepare(int size, unsigned short type, int *rctxp, unsigned long *irq_flags); static inline void -ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr, +perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, u64 count, unsigned long irq_flags, struct pt_regs *regs) { struct trace_entry *entry = raw_data; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 8126f239edf0..51435bcc3460 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -101,18 +101,18 @@ struct perf_event_attr; #ifdef CONFIG_PERF_EVENTS -#define TRACE_SYS_ENTER_PROFILE_INIT(sname) \ - .profile_enable = prof_sysenter_enable, \ - .profile_disable = prof_sysenter_disable, +#define TRACE_SYS_ENTER_PERF_INIT(sname) \ + .perf_event_enable = perf_sysenter_enable, \ + .perf_event_disable = perf_sysenter_disable, -#define TRACE_SYS_EXIT_PROFILE_INIT(sname) \ - .profile_enable = prof_sysexit_enable, \ - .profile_disable = prof_sysexit_disable, +#define TRACE_SYS_EXIT_PERF_INIT(sname) \ + .perf_event_enable = perf_sysexit_enable, \ + .perf_event_disable = perf_sysexit_disable, #else -#define TRACE_SYS_ENTER_PROFILE(sname) -#define TRACE_SYS_ENTER_PROFILE_INIT(sname) -#define TRACE_SYS_EXIT_PROFILE(sname) -#define TRACE_SYS_EXIT_PROFILE_INIT(sname) +#define TRACE_SYS_ENTER_PERF(sname) +#define TRACE_SYS_ENTER_PERF_INIT(sname) +#define TRACE_SYS_EXIT_PERF(sname) +#define TRACE_SYS_EXIT_PERF_INIT(sname) #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_FTRACE_SYSCALLS @@ -149,7 +149,7 @@ struct perf_event_attr; .regfunc = reg_event_syscall_enter, \ .unregfunc = unreg_event_syscall_enter, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_ENTER_PROFILE_INIT(sname) \ + TRACE_SYS_ENTER_PERF_INIT(sname) \ } #define SYSCALL_TRACE_EXIT_EVENT(sname) \ @@ -171,7 +171,7 @@ struct perf_event_attr; .regfunc = reg_event_syscall_exit, \ .unregfunc = unreg_event_syscall_exit, \ .data = (void *)&__syscall_meta_##sname,\ - TRACE_SYS_EXIT_PROFILE_INIT(sname) \ + TRACE_SYS_EXIT_PERF_INIT(sname) \ } #define SYSCALL_METADATA(sname, nb) \ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index f31bb8b9777c..25ab56f75d65 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -401,18 +401,18 @@ static inline notrace int ftrace_get_offsets_##call( \ #undef DEFINE_EVENT #define DEFINE_EVENT(template, name, proto, args) \ \ -static void ftrace_profile_##name(proto); \ +static void perf_trace_##name(proto); \ \ static notrace int \ -ftrace_profile_enable_##name(struct ftrace_event_call *unused) \ +perf_trace_enable_##name(struct ftrace_event_call *unused) \ { \ - return register_trace_##name(ftrace_profile_##name); \ + return register_trace_##name(perf_trace_##name); \ } \ \ static notrace void \ -ftrace_profile_disable_##name(struct ftrace_event_call *unused) \ +perf_trace_disable_##name(struct ftrace_event_call *unused) \ { \ - unregister_trace_##name(ftrace_profile_##name); \ + unregister_trace_##name(perf_trace_##name); \ } #undef DEFINE_EVENT_PRINT @@ -507,12 +507,12 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused) \ #ifdef CONFIG_PERF_EVENTS -#define _TRACE_PROFILE_INIT(call) \ - .profile_enable = ftrace_profile_enable_##call, \ - .profile_disable = ftrace_profile_disable_##call, +#define _TRACE_PERF_INIT(call) \ + .perf_event_enable = perf_trace_enable_##call, \ + .perf_event_disable = perf_trace_disable_##call, #else -#define _TRACE_PROFILE_INIT(call) +#define _TRACE_PERF_INIT(call) #endif /* CONFIG_PERF_EVENTS */ #undef __entry @@ -638,7 +638,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ .unregfunc = ftrace_raw_unreg_event_##call, \ .print_fmt = print_fmt_##template, \ .define_fields = ftrace_define_fields_##template, \ - _TRACE_PROFILE_INIT(call) \ + _TRACE_PERF_INIT(call) \ } #undef DEFINE_EVENT_PRINT @@ -657,18 +657,18 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ .unregfunc = ftrace_raw_unreg_event_##call, \ .print_fmt = print_fmt_##call, \ .define_fields = ftrace_define_fields_##template, \ - _TRACE_PROFILE_INIT(call) \ + _TRACE_PERF_INIT(call) \ } #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* - * Define the insertion callback to profile events + * Define the insertion callback to perf events * * The job is very similar to ftrace_raw_event_ except that we don't * insert in the ring buffer but in a perf counter. * - * static void ftrace_profile_(proto) + * static void ftrace_perf_(proto) * { * struct ftrace_data_offsets_ __maybe_unused __data_offsets; * struct ftrace_event_call *event_call = &event_; @@ -757,7 +757,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace void \ -ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ +perf_trace_templ_##call(struct ftrace_event_call *event_call, \ proto) \ { \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ @@ -774,10 +774,10 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ sizeof(u64)); \ __entry_size -= sizeof(u32); \ \ - if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE, \ + if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE, \ "profile buffer not large enough")) \ return; \ - entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare( \ + entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare( \ __entry_size, event_call->id, &rctx, &irq_flags); \ if (!entry) \ return; \ @@ -788,17 +788,17 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \ __regs = &__get_cpu_var(perf_trace_regs); \ perf_fetch_caller_regs(__regs, 2); \ \ - ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr, \ + perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \ __count, irq_flags, __regs); \ } #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ -static notrace void ftrace_profile_##call(proto) \ +static notrace void perf_trace_##call(proto) \ { \ struct ftrace_event_call *event_call = &event_##call; \ \ - ftrace_profile_templ_##template(event_call, args); \ + perf_trace_templ_##template(event_call, args); \ } #undef DEFINE_EVENT_PRINT diff --git a/include/trace/syscall.h b/include/trace/syscall.h index 0387100752f0..e5e5f48dbfb3 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -47,10 +47,10 @@ enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags); #endif #ifdef CONFIG_PERF_EVENTS -int prof_sysenter_enable(struct ftrace_event_call *call); -void prof_sysenter_disable(struct ftrace_event_call *call); -int prof_sysexit_enable(struct ftrace_event_call *call); -void prof_sysexit_disable(struct ftrace_event_call *call); +int perf_sysenter_enable(struct ftrace_event_call *call); +void perf_sysenter_disable(struct ftrace_event_call *call); +int perf_sysexit_enable(struct ftrace_event_call *call); +void perf_sysexit_disable(struct ftrace_event_call *call); #endif #endif /* _TRACE_SYSCALL_H */ -- cgit v1.2.2 From 85cfabbcd10f8d112feee6e2ec64ee78033b6d3c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Mar 2010 13:06:56 +0100 Subject: perf, ppc: Fix compile error due to new cpu notifiers Fix: arch/powerpc/kernel/perf_event.c:1334: error: 'power_pmu_notifier' undeclared (first use in this function) arch/powerpc/kernel/perf_event.c:1334: error: (Each undeclared identifier is reported only once arch/powerpc/kernel/perf_event.c:1334: error: for each function it appears in.) arch/powerpc/kernel/perf_event.c:1334: error: implicit declaration of function 'power_pmu_notifier' arch/powerpc/kernel/perf_event.c:1334: error: implicit declaration of function 'register_cpu_notifier' Due to commit 3f6da390 (perf: Rework and fix the arch CPU-hotplug hooks). Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 70cffd052c04..95477038a72a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -453,6 +453,7 @@ enum perf_callchain_context { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 -- cgit v1.2.2 From cf14c2e987ba0a09a7b09be2ecd55af0bc9c17b4 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Tue, 2 Feb 2010 21:03:50 +0100 Subject: drbd: --dry-run option for drbdsetup net ( drbdadm -- --dry-run connect ) Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd.h | 2 +- include/linux/drbd_nl.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 78962272338a..4341b1a97a34 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -56,7 +56,7 @@ extern const char *drbd_buildtag(void); #define REL_VERSION "8.3.7" #define API_VERSION 88 #define PRO_VERSION_MIN 86 -#define PRO_VERSION_MAX 91 +#define PRO_VERSION_MAX 92 enum drbd_io_error_p { diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h index a4d82f895994..b41050e8cc2f 100644 --- a/include/linux/drbd_nl.h +++ b/include/linux/drbd_nl.h @@ -63,6 +63,7 @@ NL_PACKET(net_conf, 5, NL_BIT( 41, T_MAY_IGNORE, always_asbp) NL_BIT( 61, T_MAY_IGNORE, no_cork) NL_BIT( 62, T_MANDATORY, auto_sndbuf_size) + NL_BIT( 70, T_MANDATORY, dry_run) ) NL_PACKET(disconnect, 6, ) -- cgit v1.2.2 From 1f55243024087b56aef0b1e6d9c0ea89c76f0a6b Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Thu, 4 Mar 2010 15:51:01 +0100 Subject: drbd: Renamed overwrite_peer to primary_force Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd_nl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h index b41050e8cc2f..f7431a4ca608 100644 --- a/include/linux/drbd_nl.h +++ b/include/linux/drbd_nl.h @@ -12,7 +12,7 @@ #endif NL_PACKET(primary, 1, - NL_BIT( 1, T_MAY_IGNORE, overwrite_peer) + NL_BIT( 1, T_MAY_IGNORE, primary_force) ) NL_PACKET(secondary, 2, ) -- cgit v1.2.2 From f11c9c5c259cb2c3d698548dc3936f773ab1f5b9 Mon Sep 17 00:00:00 2001 From: Edward Shishkin Date: Thu, 11 Mar 2010 14:09:47 -0800 Subject: vfs: improve writeback_inodes_wb() Do not pin/unpin superblock for every inode in writeback_inodes_wb(), pin it for the whole group of inodes which belong to the same superblock and call writeback_sb_inodes() handler for them. Signed-off-by: Edward Shishkin Cc: Jens Axboe Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/writeback.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 76e8903cd204..36520ded3e06 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -34,6 +34,9 @@ struct writeback_control { enum writeback_sync_modes sync_mode; unsigned long *older_than_this; /* If !NULL, only write back inodes older than this */ + unsigned long wb_start; /* Time writeback_inodes_wb was + called. This is needed to avoid + extra jobs and livelock */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ -- cgit v1.2.2 From 80a05b9ffa7dc13f6693902dd8999a2b61a3a0d7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 Mar 2010 17:34:14 +0100 Subject: clockevents: Sanitize min_delta_ns adjustment and prevent overflows The current logic which handles clock events programming failures can increase min_delta_ns unlimited and even can cause overflows. Sanitize it by: - prevent zero increase when min_delta_ns == 1 - limiting min_delta_ns to a jiffie - bail out if the jiffie limit is hit - add retries stats for /proc/timer_list so we can gather data Reported-by: Uwe Kleine-Koenig Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 0cf725bdd2a1..fc53492b6ad7 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -73,6 +73,7 @@ enum clock_event_nofitiers { * @list: list head for the management code * @mode: operating mode assigned by the management code * @next_event: local storage for the next event in oneshot mode + * @retries: number of forced programming retries */ struct clock_event_device { const char *name; @@ -93,6 +94,7 @@ struct clock_event_device { struct list_head list; enum clock_event_mode mode; ktime_t next_event; + unsigned long retries; }; /* -- cgit v1.2.2 From 3f17522ce461a31e7ced6311b28fcf5b8a763316 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 12 Feb 2010 14:32:01 +0000 Subject: Video: ARM CLCD: Better fix for swapped IENB and CNTL registers On PL111, as found on Realview and other platforms, these registers are always arranged as CNTL then IENB. On PL110, these registers are IENB then CNTL, except on Versatile platforms. Re-arrange the handling of these register swaps so that PL111 always gets it right without resorting to ifdefs, leaving the only case needing special handling being PL110 on Versatile. Fill out amba/clcd.h with the PL110/PL111 register definition differences in case someone tries to use the PL110 specific definitions on PL111. Signed-off-by: Russell King --- include/linux/amba/clcd.h | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h index 29c0448265cf..ca16c3801a1e 100644 --- a/include/linux/amba/clcd.h +++ b/include/linux/amba/clcd.h @@ -21,22 +21,21 @@ #define CLCD_UBAS 0x00000010 #define CLCD_LBAS 0x00000014 -#if !defined(CONFIG_ARCH_VERSATILE) && !defined(CONFIG_ARCH_REALVIEW) -#define CLCD_IENB 0x00000018 -#define CLCD_CNTL 0x0000001c -#else -/* - * Someone rearranged these two registers on the Versatile - * platform... - */ -#define CLCD_IENB 0x0000001c -#define CLCD_CNTL 0x00000018 -#endif - -#define CLCD_STAT 0x00000020 -#define CLCD_INTR 0x00000024 -#define CLCD_UCUR 0x00000028 -#define CLCD_LCUR 0x0000002C +#define CLCD_PL110_IENB 0x00000018 +#define CLCD_PL110_CNTL 0x0000001c +#define CLCD_PL110_STAT 0x00000020 +#define CLCD_PL110_INTR 0x00000024 +#define CLCD_PL110_UCUR 0x00000028 +#define CLCD_PL110_LCUR 0x0000002C + +#define CLCD_PL111_CNTL 0x00000018 +#define CLCD_PL111_IENB 0x0000001c +#define CLCD_PL111_RIS 0x00000020 +#define CLCD_PL111_MIS 0x00000024 +#define CLCD_PL111_ICR 0x00000028 +#define CLCD_PL111_UCUR 0x0000002c +#define CLCD_PL111_LCUR 0x00000030 + #define CLCD_PALL 0x00000200 #define CLCD_PALETTE 0x00000200 @@ -147,6 +146,8 @@ struct clcd_fb { struct clcd_board *board; void *board_data; void __iomem *regs; + u16 off_ienb; + u16 off_cntl; u32 clcd_cntl; u32 cmap[16]; }; -- cgit v1.2.2 From 338e2b1d571e4873908b199c90d6a31f65137fe3 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 3 Mar 2010 13:39:13 -0500 Subject: drm/radeon: add new RS880 pci id This should go to 2.6.33 stable as well. Signed-off-by: Alex Deucher Cc: stable@kernel.org Signed-off-by: Dave Airlie --- include/drm/drm_pciids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 676104b7818c..04a6ebc27b96 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -410,6 +410,7 @@ {0x1002, 0x9712, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9713, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9714, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9715, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0, 0, 0} #define r128_PCI_IDS \ -- cgit v1.2.2 From 72e942dd846f98e2d35aad5436d77a878ef05c5e Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 9 Mar 2010 06:33:26 +0000 Subject: drm/ttm: use drm calloc large and free large Now that the drm core can do this, lets just use it, split the code out so TTM doesn't have to drag all of drmP.h in. Signed-off-by: Dave Airlie --- include/drm/drmP.h | 34 +-------------------- include/drm/drm_mem_util.h | 65 +++++++++++++++++++++++++++++++++++++++++ include/drm/ttm/ttm_bo_driver.h | 1 - 3 files changed, 66 insertions(+), 34 deletions(-) create mode 100644 include/drm/drm_mem_util.h (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 4a3c4e441027..de2f82efb15f 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1545,39 +1545,7 @@ static __inline__ void drm_core_dropmap(struct drm_local_map *map) { } - -static __inline__ void *drm_calloc_large(size_t nmemb, size_t size) -{ - if (size != 0 && nmemb > ULONG_MAX / size) - return NULL; - - if (size * nmemb <= PAGE_SIZE) - return kcalloc(nmemb, size, GFP_KERNEL); - - return __vmalloc(size * nmemb, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); -} - -/* Modeled after cairo's malloc_ab, it's like calloc but without the zeroing. */ -static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size) -{ - if (size != 0 && nmemb > ULONG_MAX / size) - return NULL; - - if (size * nmemb <= PAGE_SIZE) - return kmalloc(nmemb * size, GFP_KERNEL); - - return __vmalloc(size * nmemb, - GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL); -} - -static __inline void drm_free_large(void *ptr) -{ - if (!is_vmalloc_addr(ptr)) - return kfree(ptr); - - vfree(ptr); -} +#include "drm_mem_util.h" /*@}*/ #endif /* __KERNEL__ */ diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h new file mode 100644 index 000000000000..6bd325fedc87 --- /dev/null +++ b/include/drm/drm_mem_util.h @@ -0,0 +1,65 @@ +/* + * Copyright © 2008 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + * Authors: + * Jesse Barnes + * + */ +#ifndef _DRM_MEM_UTIL_H_ +#define _DRM_MEM_UTIL_H_ + +#include + +static __inline__ void *drm_calloc_large(size_t nmemb, size_t size) +{ + if (size != 0 && nmemb > ULONG_MAX / size) + return NULL; + + if (size * nmemb <= PAGE_SIZE) + return kcalloc(nmemb, size, GFP_KERNEL); + + return __vmalloc(size * nmemb, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); +} + +/* Modeled after cairo's malloc_ab, it's like calloc but without the zeroing. */ +static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size) +{ + if (size != 0 && nmemb > ULONG_MAX / size) + return NULL; + + if (size * nmemb <= PAGE_SIZE) + return kmalloc(nmemb * size, GFP_KERNEL); + + return __vmalloc(size * nmemb, + GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL); +} + +static __inline void drm_free_large(void *ptr) +{ + if (!is_vmalloc_addr(ptr)) + return kfree(ptr); + + vfree(ptr); +} + +#endif diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index e3f1b4a4b601..e929c27ede22 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -115,7 +115,6 @@ struct ttm_backend { struct ttm_backend_func *func; }; -#define TTM_PAGE_FLAG_VMALLOC (1 << 0) #define TTM_PAGE_FLAG_USER (1 << 1) #define TTM_PAGE_FLAG_USER_DIRTY (1 << 2) #define TTM_PAGE_FLAG_WRITE (1 << 3) -- cgit v1.2.2 From 2cda2728aa1c8c006418a24f867b25e5eb7a32e2 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 15 Mar 2010 12:46:51 +0100 Subject: block: Fix overrun in lcm() and move it to lib lcm() was defined to take integer-sized arguments. The supplied arguments are multiplied, however, causing us to overflow given sufficiently large input. That in turn led to incorrect optimal I/O size reporting in some cases (RAID over RAID). Switch lcm() over to unsigned long similar to gcd() and move the function from blk-settings.c to lib. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/lcm.h | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 include/linux/lcm.h (limited to 'include') diff --git a/include/linux/lcm.h b/include/linux/lcm.h new file mode 100644 index 000000000000..7bf01d779b45 --- /dev/null +++ b/include/linux/lcm.h @@ -0,0 +1,8 @@ +#ifndef _LCM_H +#define _LCM_H + +#include + +unsigned long lcm(unsigned long a, unsigned long b) __attribute_const__; + +#endif /* _LCM_H */ -- cgit v1.2.2 From ee714f2dd33e726346e34f5cda12543162f4753e Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 10 Mar 2010 00:48:32 -0500 Subject: block: Finalize conversion of block limits functions Remove compatibility wrappers and update remaining drivers. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ebd22dbed861..41551c9341b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -921,26 +921,7 @@ extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); - -/* Temporary compatibility wrapper */ -static inline void blk_queue_max_sectors(struct request_queue *q, unsigned int max) -{ - blk_queue_max_hw_sectors(q, max); -} - extern void blk_queue_max_segments(struct request_queue *, unsigned short); - -static inline void blk_queue_max_phys_segments(struct request_queue *q, unsigned short max) -{ - blk_queue_max_segments(q, max); -} - -static inline void blk_queue_max_hw_segments(struct request_queue *q, unsigned short max) -{ - blk_queue_max_segments(q, max); -} - - extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1030,11 +1011,6 @@ static inline int sb_issue_discard(struct super_block *sb, extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -#define MAX_PHYS_SEGMENTS 128 -#define MAX_HW_SEGMENTS 128 -#define SAFE_MAX_SECTORS 255 -#define MAX_SEGMENT_SIZE 65536 - enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, -- cgit v1.2.2 From 97fedbbe1046b3118f49df249840ca21041eefe4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 16 Mar 2010 08:55:32 +0100 Subject: Remove GENHD_FL_DRIVERFS This flag is not used, so best discarded. Signed-off-by: NeilBrown -- Hi Jens, I came across this recently - these are the only two occurances of "GENHD_FL_DRIVERFS" in the kernel, so it cannot be needed. NeilBrown Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 56b50514ab25..5f2f4c4d8fb0 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -109,7 +109,7 @@ struct hd_struct { }; #define GENHD_FL_REMOVABLE 1 -#define GENHD_FL_DRIVERFS 2 +/* 2 is unused */ #define GENHD_FL_MEDIA_CHANGE_NOTIFY 4 #define GENHD_FL_CD 8 #define GENHD_FL_UP 16 -- cgit v1.2.2 From e3818b8dce2a934cd1521dbc4827e5238d8f45d8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 15 Mar 2010 17:03:43 -0700 Subject: rcu: Make rcu_read_lock_bh_held() allow for disabled BH Disabling BH can stand in for rcu_read_lock_bh(), and this patch updates rcu_read_lock_bh_held() to allow for this. In order to avoid include-file hell, this function is moved out of line to kernel/rcupdate.c. This fixes a false positive RCU warning. Reported-by: Arnd Bergmann Reported-by: Eric Dumazet Signed-off-by: Paul E. McKenney Acked-by: Lai Jiangshan Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <20100316000343.GA25857@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 3024050c82a1..e1bdc4bfd275 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -123,22 +123,11 @@ static inline int rcu_read_lock_held(void) return lock_is_held(&rcu_lock_map); } -/** - * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? - * - * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in - * an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING, - * this assumes we are in an RCU-bh read-side critical section unless it can - * prove otherwise. - * - * Check rcu_scheduler_active to prevent false positives during boot. +/* + * rcu_read_lock_bh_held() is defined out of line to avoid #include-file + * hell. */ -static inline int rcu_read_lock_bh_held(void) -{ - if (!debug_lockdep_rcu_enabled()) - return 1; - return lock_is_held(&rcu_bh_lock_map); -} +extern int rcu_read_lock_bh_held(void); /** * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section? -- cgit v1.2.2 From 7f5b774275df8c76a959eae7488128b637fcbfc8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 16 Mar 2010 17:00:29 +0800 Subject: rcu: Fix tracepoints & lockdep false positive tracepoint.h uses rcu_dereference(), which triggers this warning: [ 0.701161] =================================================== [ 0.702211] [ INFO: suspicious rcu_dereference_check() usage. ] [ 0.702716] --------------------------------------------------- [ 0.703203] include/trace/events/workqueue.h:68 invoked rcu_dereference_check() without protection! [ 0.703971] [ 0.703990] other info that might help us debug this: [ 0.703993] [ 0.705590] [ 0.705604] rcu_scheduler_active = 1, debug_locks = 0 [ 0.706712] 1 lock held by swapper/1: [ 0.707229] #0: (cpu_add_remove_lock){+.+.+.}, at: [] cpu_maps_update_begin+0x14/0x20 [ 0.710097] [ 0.710106] stack backtrace: [ 0.712602] Pid: 1, comm: swapper Not tainted 2.6.34-rc1-tip-01613-g72662bb #168 [ 0.713231] Call Trace: [ 0.713997] [] lockdep_rcu_dereference+0x9d/0xb0 [ 0.714746] [] create_workqueue_thread+0x107/0x110 [ 0.715353] [] ? worker_thread+0x0/0x340 [ 0.715845] [] __create_workqueue_key+0x138/0x240 [ 0.716427] [] ? cpu_maps_update_done+0x12/0x20 [ 0.717012] [] init_workqueues+0x6f/0x80 [ 0.717530] [] kernel_init+0x102/0x1f0 [ 0.717570] [] ? kernel_init+0x0/0x1f0 [ 0.718944] [] kernel_thread_helper+0x6/0x10 Signed-off-by: Lai Jiangshan Cc: Paul E. McKenney Cc: Mathieu Desnoyers Cc: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <4B9F48AD.4000404@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index f59604ed0ec6..78b4bd3be496 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -49,7 +49,7 @@ struct tracepoint { void **it_func; \ \ rcu_read_lock_sched_notrace(); \ - it_func = rcu_dereference((tp)->funcs); \ + it_func = rcu_dereference_sched((tp)->funcs); \ if (it_func) { \ do { \ ((void(*)(proto))(*it_func))(args); \ -- cgit v1.2.2 From e7fb9c4ad351a8da7c09e182bd2e7ccd043daf08 Mon Sep 17 00:00:00 2001 From: Alberto Panizzo Date: Fri, 18 Dec 2009 16:42:11 +0100 Subject: backlight: Add Epson L4F00242T03 LCD driver The Epson LCD L4F00242T03 is mounted on the Freescale i.MX31 PDK board. Based upon Marek Vasut work in l4f00242t03.c, this driver provides basic init and power on/off functionality for this device through the sysfs lcd interface. Unfortunately Datasheet for this device are not available and all the control sequences sent to the display were copied from the freescale driver that in the i.MX31 Linux BSP. As in the i.MX31PDK board the core and io suppliers are voltage regulators, that functionality is embedded here, but not strict. Signed-off-by: Alberto Panizzo Signed-off-by: Richard Purdie --- include/linux/spi/l4f00242t03.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/spi/l4f00242t03.h (limited to 'include') diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h new file mode 100644 index 000000000000..aee1dbda4edc --- /dev/null +++ b/include/linux/spi/l4f00242t03.h @@ -0,0 +1,31 @@ +/* + * l4f00242t03.h -- Platform glue for Epson L4F00242T03 LCD + * + * Copyright (c) 2009 Alberto Panizzo + * Based on Marek Vasut work in lms283gf05.h + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ + +#ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_ +#define _INCLUDE_LINUX_SPI_L4F00242T03_H_ + +struct l4f00242t03_pdata { + unsigned int reset_gpio; + unsigned int data_enable_gpio; + const char *io_supply; /* will be set to 1.8 V */ + const char *core_supply; /* will be set to 2.8 V */ +}; + +#endif /* _INCLUDE_LINUX_SPI_L4F00242T03_H_ */ -- cgit v1.2.2 From b4144e4f6e3b448d322095ca08af393682a69e33 Mon Sep 17 00:00:00 2001 From: Richard Purdie Date: Mon, 18 Jan 2010 14:16:07 +0000 Subject: backlight: Revert some const qualifiers 9905a43b2d563e6f89e4c63c4278ada03f2ebb14 went a little to far with const qualifiers as there are legitiment cases where the function pointers can change (machine specific setup code for example). Signed-off-by: Richard Purdie --- include/linux/backlight.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 8c4f884db6b4..ee377d791996 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -36,18 +36,18 @@ struct backlight_device; struct fb_info; struct backlight_ops { - const unsigned int options; + unsigned int options; #define BL_CORE_SUSPENDRESUME (1 << 0) /* Notify the backlight driver some property has changed */ - int (* const update_status)(struct backlight_device *); + int (*update_status)(struct backlight_device *); /* Return the current backlight brightness (accounting for power, fb_blank etc.) */ - int (* const get_brightness)(struct backlight_device *); + int (*get_brightness)(struct backlight_device *); /* Check if given framebuffer device is the one bound to this backlight; return 0 if not, !=0 if it is. If NULL, backlight always matches the fb. */ - int (* const check_fb)(struct fb_info *); + int (*check_fb)(struct fb_info *); }; /* This structure defines all the properties of a backlight */ -- cgit v1.2.2 From 57e148b6a975980944f4466ccb669b1d02dfc6a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bruno=20Pr=C3=A9mont?= Date: Sun, 21 Feb 2010 00:20:01 +0100 Subject: backlight: Add backlight_device parameter to check_fb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit check_fb from backlight_ops lacks a reference to the backlight_device that's being referred to. Add this parameter so a backlight_device can be mapped to a single framebuffer, especially if the same driver handles multiple devices on a single system. Signed-off-by: Bruno Prémont Signed-off-by: Richard Purdie --- include/linux/backlight.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index ee377d791996..21cd866d24cd 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -47,7 +47,7 @@ struct backlight_ops { int (*get_brightness)(struct backlight_device *); /* Check if given framebuffer device is the one bound to this backlight; return 0 if not, !=0 if it is. If NULL, backlight always matches the fb. */ - int (*check_fb)(struct fb_info *); + int (*check_fb)(struct backlight_device *, struct fb_info *); }; /* This structure defines all the properties of a backlight */ -- cgit v1.2.2 From a19a6ee6cad2b20292a774c2f56ba8039b0fac9c Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Wed, 17 Feb 2010 16:39:44 -0500 Subject: backlight: Allow properties to be passed at registration Values such as max_brightness should be set before backlights are registered, but the current API doesn't allow that. Add a parameter to backlight_device_register and update drivers to ensure that they set this correctly. Signed-off-by: Matthew Garrett Signed-off-by: Richard Purdie --- include/linux/backlight.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 21cd866d24cd..4a3d52e545e1 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -103,7 +103,8 @@ static inline void backlight_update_status(struct backlight_device *bd) } extern struct backlight_device *backlight_device_register(const char *name, - struct device *dev, void *devdata, const struct backlight_ops *ops); + struct device *dev, void *devdata, const struct backlight_ops *ops, + const struct backlight_properties *props); extern void backlight_device_unregister(struct backlight_device *bd); extern void backlight_force_update(struct backlight_device *bd, enum backlight_update_reason reason); -- cgit v1.2.2 From bc32df00894f0e1dbf583cc3dab210d2969b078a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 15 Mar 2010 00:35:03 -0400 Subject: memory hotplug: allow setting of phys_device /sys/devices/system/memory/memoryX/phys_device is supposed to contain the number of the physical device that the corresponding piece of memory belongs to. In case a physical device should be replaced or taken offline for whatever reason it is necessary to set all corresponding memory pieces offline. The current implementation always sets phys_device to '0' and there is no way or hook to change that. Seems like there was a plan to implement that but it wasn't finished for whatever reason. So add a weak function which architectures can override to actually set the phys_device from within add_memory_block(). Signed-off-by: Heiko Carstens Cc: Dave Hansen Cc: Gerald Schaefer Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/memory.h b/include/linux/memory.h index 1adfe779eb99..85582e1bcee9 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -36,6 +36,8 @@ struct memory_block { struct sys_device sysdev; }; +int arch_get_memory_phys_device(unsigned long start_pfn); + /* These states are exposed to userspace as text strings in sysfs */ #define MEM_ONLINE (1<<0) /* exposed to userspace */ #define MEM_GOING_OFFLINE (1<<1) /* exposed to userspace */ -- cgit v1.2.2 From 1976152fd8e706135deed6cf333e347c08416056 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 18 Mar 2010 07:30:31 -0600 Subject: of: Fix comparison of "compatible" properties Commit 7c7b60cb87547b1664a4385c187f029bf514a737 "of: put default string compare and #a/s-cell values into common header" Breaks various things on powerpc due to using strncasecmp instead of strcasecmp for comparing against "compatible" strings. This causes things like the 4xx PCI code to fail miserably due to the partial matches in code like this: for_each_compatible_node(np, NULL, "ibm,plb-pcix") ppc4xx_probe_pcix_bridge(np); for_each_compatible_node(np, NULL, "ibm,plb-pci") ppc4xx_probe_pci_bridge(np); It's not quite right to do partial name match. Entries in a compatible list are meant to be matched whole. If a device is compatible with both "foo" and "foo1", then the device should have both strings in its "compatible" property. This patch reverts powerpc and microblaze us to use strcasecmp. Signed-off-by: Benjamin Herrenschmidt (for patch description) Signed-off-by: Grant Likely Acked-by: David S. Miller Acked-by: Michal Simek --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index f6d9cbc39c9c..a367e19bb3af 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -127,7 +127,7 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) /* Default string compare functions, Allow arch asm/prom.h to override */ #if !defined(of_compat_cmp) -#define of_compat_cmp(s1, s2, l) strncasecmp((s1), (s2), (l)) +#define of_compat_cmp(s1, s2, l) strcasecmp((s1), (s2)) #define of_prop_cmp(s1, s2) strcmp((s1), (s2)) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) #endif -- cgit v1.2.2 From 0cff810f54b3b52075c27f7a7021d5b195264b6c Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 18 Mar 2010 12:25:33 -0700 Subject: rcu: Fix local_irq_disable() CONFIG_PROVE_RCU=y false positives It is documented that local_irq_disable() also delimits RCU_SCHED read-site critical sections. See the document of synchronize_sched() or Documentation/RCU/whatisRCU.txt. So we have to test irqs_disabled() in rcu_read_lock_sched_held(). Otherwise rcu-lockdep brings incorrect complaint. Signed-off-by: Lai Jiangshan Signed-off-by: Paul E. McKenney Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: eric.dumazet@gmail.com LKML-Reference: <1268940334-10892-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e1bdc4bfd275..872a98e13d6a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -149,7 +149,7 @@ static inline int rcu_read_lock_sched_held(void) return 1; if (debug_locks) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); - return lockdep_opinion || preempt_count() != 0; + return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); } #else /* #ifdef CONFIG_PREEMPT */ static inline int rcu_read_lock_sched_held(void) @@ -180,7 +180,7 @@ static inline int rcu_read_lock_bh_held(void) #ifdef CONFIG_PREEMPT static inline int rcu_read_lock_sched_held(void) { - return !rcu_scheduler_active || preempt_count() != 0; + return !rcu_scheduler_active || preempt_count() != 0 || irqs_disabled(); } #else /* #ifdef CONFIG_PREEMPT */ static inline int rcu_read_lock_sched_held(void) -- cgit v1.2.2 From 1e94d72feab025b8f7c55d07020602f82f3a97dd Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Thu, 18 Mar 2010 17:45:44 -0700 Subject: rps: Fixed build with CONFIG_SMP not enabled. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index de1a52bcb9e0..726ecd1af535 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1341,7 +1341,9 @@ struct softnet_data { struct sk_buff *completion_queue; /* Elements below can be accessed between CPUs for RPS */ +#ifdef CONFIG_SMP struct call_single_data csd ____cacheline_aligned_in_smp; +#endif struct sk_buff_head input_pkt_queue; struct napi_struct backlog; }; -- cgit v1.2.2 From 93d9b7d7a85cfb4e1711d5226eba73586dd4919f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 10 Mar 2010 10:28:56 +0000 Subject: net: rename notifier defines for netdev type change Since generally there could be more netdevices changing type other than bonding, making this event type name "bonding-unrelated" Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/notifier.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index fee6c2f68075..f3635fc6e942 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -199,8 +199,8 @@ static inline int notifier_to_errno(int ret) #define NETDEV_FEAT_CHANGE 0x000B #define NETDEV_BONDING_FAILOVER 0x000C #define NETDEV_PRE_UP 0x000D -#define NETDEV_BONDING_OLDTYPE 0x000E -#define NETDEV_BONDING_NEWTYPE 0x000F +#define NETDEV_PRE_TYPE_CHANGE 0x000E +#define NETDEV_POST_TYPE_CHANGE 0x000F #define NETDEV_POST_INIT 0x0010 #define NETDEV_UNREGISTER_BATCH 0x0011 -- cgit v1.2.2 From 3ca5b4042ecae5e73c59de62e4ac0db31c10e0f8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 10 Mar 2010 10:29:35 +0000 Subject: bonding: check return value of nofitier when changing type This patch adds the possibility to refuse the bonding type change for other subsystems (such as for example bridge, vlan, etc.) Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 726ecd1af535..813bed723f58 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2005,7 +2005,7 @@ extern void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct extern int dev_set_promiscuity(struct net_device *dev, int inc); extern int dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); -extern void netdev_bonding_change(struct net_device *dev, +extern int netdev_bonding_change(struct net_device *dev, unsigned long event); extern void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ -- cgit v1.2.2 From 0641e4fbf2f824faee00ea74c459a088d94905fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Mar 2010 21:16:45 -0700 Subject: net: Potential null skb->dev dereference When doing "ifenslave -d bond0 eth0", there is chance to get NULL dereference in netif_receive_skb(), because dev->master suddenly becomes NULL after we tested it. We should use ACCESS_ONCE() to avoid this (or rcu_dereference()) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c79a88be7c33..fa8b47637997 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2059,12 +2059,12 @@ static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and * ARP on active-backup slaves with arp_validate enabled. */ -static inline int skb_bond_should_drop(struct sk_buff *skb) +static inline int skb_bond_should_drop(struct sk_buff *skb, + struct net_device *master) { - struct net_device *dev = skb->dev; - struct net_device *master = dev->master; - if (master) { + struct net_device *dev = skb->dev; + if (master->priv_flags & IFF_MASTER_ARPMON) dev->last_rx = jiffies; -- cgit v1.2.2 From 181fdde3b4268cb7b4af76ba6337e7ec8accbb36 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Fri, 19 Mar 2010 08:58:16 +0100 Subject: block: remove 16 bytes of padding from struct request on 64bits Remove alignment padding to shrink struct request from 336 to 320 bytes so needing one fewer cacheline and therefore removing 48 bytes from struct request_queue. Signed-off-by: Richard Kennedy Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 41551c9341b6..6690e8bae7bb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -158,7 +158,6 @@ enum rq_flag_bits { struct request { struct list_head queuelist; struct call_single_data csd; - int cpu; struct request_queue *q; @@ -166,9 +165,11 @@ struct request { enum rq_cmd_type_bits cmd_type; unsigned long atomic_flags; + int cpu; + /* the following two fields are internal, NEVER access directly */ - sector_t __sector; /* sector cursor */ unsigned int __data_len; /* total data len */ + sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; @@ -201,20 +202,20 @@ struct request { unsigned short ioprio; + int ref_count; + void *special; /* opaque pointer available for LLD use */ char *buffer; /* kaddr of the current segment if available */ int tag; int errors; - int ref_count; - /* * when request is used as a packet command carrier */ - unsigned short cmd_len; unsigned char __cmd[BLK_MAX_CDB]; unsigned char *cmd; + unsigned short cmd_len; unsigned int extra_len; /* length of alignment and padding */ unsigned int sense_len; -- cgit v1.2.2 From 87a6aca504d65f242589583e04df5e74b5eae1fe Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 15 Mar 2010 17:14:15 -0700 Subject: Revert "tty: Add a new VT mode which is like VT_PROCESS but doesn't require a VT_RELDISP ioctl call" This reverts commit eec9fe7d1ab4a0dfac4cb43047a7657fffd0002f. Ari writes as the reason this should be reverted: The problems with this patch include: 1. There's at least one subtlety I overlooked - switching between X servers (i.e. from one X VT to another) still requires the cooperation of both X servers. I was assuming that KMS eliminated this. 2. It hasn't been tested at all (no X server patch exists which uses the new mode). As he was the original author of the patch, I'll revert it. Cc: Ari Entlich Cc: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/vt.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vt.h b/include/linux/vt.h index 778b7b2a47d4..d5dd0bc408fd 100644 --- a/include/linux/vt.h +++ b/include/linux/vt.h @@ -27,7 +27,7 @@ struct vt_mode { #define VT_SETMODE 0x5602 /* set mode of active vt */ #define VT_AUTO 0x00 /* auto vt switching */ #define VT_PROCESS 0x01 /* process controls switching */ -#define VT_PROCESS_AUTO 0x02 /* process is notified of switching */ +#define VT_ACKACQ 0x02 /* acknowledge switch */ struct vt_stat { unsigned short v_active; /* active vt */ @@ -38,7 +38,6 @@ struct vt_stat { #define VT_SENDSIG 0x5604 /* signal to send to bitmask of vts */ #define VT_RELDISP 0x5605 /* release display */ -#define VT_ACKACQ 0x02 /* acknowledge switch */ #define VT_ACTIVATE 0x5606 /* make vt active */ #define VT_WAITACTIVE 0x5607 /* wait for vt active */ -- cgit v1.2.2 From 352fa6ad16b89f8ffd1a93b4419b1a8f2259feab Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 2 Mar 2010 22:24:19 +0000 Subject: tty: Take a 256 byte padding into account when buffering below sub-page units The TTY layer takes some care to ensure that only sub-page allocations are made with interrupts disabled. It does this by setting a goal of "TTY_BUFFER_PAGE" to allocate. Unfortunately, while TTY_BUFFER_PAGE takes the size of tty_buffer into account, it fails to account that tty_buffer_find() rounds the buffer size out to the next 256 byte boundary before adding on the size of the tty_buffer. This patch adjusts the TTY_BUFFER_PAGE calculation to take into account the size of the tty_buffer and the padding. Once applied, tty_buffer_alloc() should not require high-order allocations. Signed-off-by: Mel Gorman Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/tty.h b/include/linux/tty.h index 568369a86306..593228a520e1 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -70,12 +70,13 @@ struct tty_buffer { /* * We default to dicing tty buffer allocations to this many characters - * in order to avoid multiple page allocations. We assume tty_buffer itself - * is under 256 bytes. See tty_buffer_find for the allocation logic this - * must match + * in order to avoid multiple page allocations. We know the size of + * tty_buffer itself but it must also be taken into account that the + * the buffer is 256 byte aligned. See tty_buffer_find for the allocation + * logic this must match */ -#define TTY_BUFFER_PAGE ((PAGE_SIZE - 256) / 2) +#define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF) struct tty_bufhead { -- cgit v1.2.2 From 336cee42dd52824e360ab419eab4e8888eb054ec Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Mon, 8 Mar 2010 21:50:11 -0600 Subject: tty_port,usb-console: Fix usb serial console open/close regression Commit e1108a63e10d344284011cccc06328b2cd3e5da3 ("usb_serial: Use the shutdown() operation") breaks the ability to use a usb console starting in 2.6.33. This was observed when using console=ttyUSB0,115200 as a boot argument with an FTDI device. The error is: ftdi_sio ttyUSB0: ftdi_submit_read_urb - failed submitting read urb, error -22 The handling of the ASYNCB_INITIALIZED changed in 2.6.32 such that in tty_port_shutdown() it always clears the flag if it is set. The fix is to add a variable to the tty_port struct to indicate when the tty port is a console. CC: Alan Cox CC: Alan Stern CC: Oliver Neukum CC: Andrew Morton Signed-off-by: Jason Wessel Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/tty.h b/include/linux/tty.h index 593228a520e1..4409967db0c4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -224,6 +224,7 @@ struct tty_port { wait_queue_head_t close_wait; /* Close waiters */ wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ + unsigned char console:1; /* port is a console */ struct mutex mutex; /* Locking */ struct mutex buf_mutex; /* Buffer alloc lock */ unsigned char *xmit_buf; /* Optional buffer */ -- cgit v1.2.2 From f09a15e6e69884cedec4d1c022089a973aa01f1e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 16 Mar 2010 12:55:44 -0700 Subject: USB: Fix usb_fill_int_urb for SuperSpeed devices USB 3 and Wireless USB specify a logarithmic encoding of the endpoint interval that matches the USB 2 specification. usb_fill_int_urb() didn't know that and was filling in the interval as if it was USB 1.1. Fix usb_fill_int_urb() for SuperSpeed devices, but leave the wireless case alone, because David Vrabel wants to keep the old encoding. Update the struct urb kernel doc to note that SuperSpeed URBs must have urb->interval specified in microframes. Add a missing break statement in the usb_submit_urb() interrupt URB checking, since wireless USB and SuperSpeed USB encode urb->interval differently. This allows xHCI roothubs to actually register with khubd. Signed-off-by: Matthew Wilcox Signed-off-by: Sarah Sharp Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 8c9f053111bb..ce1323c4e47c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1055,7 +1055,8 @@ typedef void (*usb_complete_t)(struct urb *); * @number_of_packets: Lists the number of ISO transfer buffers. * @interval: Specifies the polling interval for interrupt or isochronous * transfers. The units are frames (milliseconds) for full and low - * speed devices, and microframes (1/8 millisecond) for highspeed ones. + * speed devices, and microframes (1/8 millisecond) for highspeed + * and SuperSpeed devices. * @error_count: Returns the number of ISO transfers that reported errors. * @context: For use in completion functions. This normally points to * request-specific driver context. @@ -1286,9 +1287,16 @@ static inline void usb_fill_bulk_urb(struct urb *urb, * * Initializes a interrupt urb with the proper information needed to submit * it to a device. - * Note that high speed interrupt endpoints use a logarithmic encoding of - * the endpoint interval, and express polling intervals in microframes - * (eight per millisecond) rather than in frames (one per millisecond). + * + * Note that High Speed and SuperSpeed interrupt endpoints use a logarithmic + * encoding of the endpoint interval, and express polling intervals in + * microframes (eight per millisecond) rather than in frames (one per + * millisecond). + * + * Wireless USB also uses the logarithmic encoding, but specifies it in units of + * 128us instead of 125us. For Wireless USB devices, the interval is passed + * through to the host controller, rather than being translated into microframe + * units. */ static inline void usb_fill_int_urb(struct urb *urb, struct usb_device *dev, @@ -1305,7 +1313,7 @@ static inline void usb_fill_int_urb(struct urb *urb, urb->transfer_buffer_length = buffer_length; urb->complete = complete_fn; urb->context = context; - if (dev->speed == USB_SPEED_HIGH) + if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) urb->interval = 1 << (interval - 1); else urb->interval = interval; -- cgit v1.2.2 From f5d410f2ea7ba340f11815a56e05b9fa9421c421 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 16 Mar 2010 13:30:44 +0000 Subject: netlink: fix unaligned access in nla_get_be64() This patch fixes a unaligned access in nla_get_be64() that was introduced by myself in a17c859849402315613a0015ac8fbf101acf0cc1. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netlink.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index f82e463c875a..4fc05b58503e 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -945,7 +945,11 @@ static inline u64 nla_get_u64(const struct nlattr *nla) */ static inline __be64 nla_get_be64(const struct nlattr *nla) { - return *(__be64 *) nla_data(nla); + __be64 tmp; + + nla_memcpy(&tmp, nla, sizeof(tmp)); + + return tmp; } /** -- cgit v1.2.2 From 1a50307ba1826e4da0024e64b245ce4eadf7688a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 18 Mar 2010 14:24:42 +0000 Subject: netlink: fix NETLINK_RECV_NO_ENOBUFS in netlink_set_err() Currently, ENOBUFS errors are reported to the socket via netlink_set_err() even if NETLINK_RECV_NO_ENOBUFS is set. However, that should not happen. This fixes this problem and it changes the prototype of netlink_set_err() to return the number of sockets that have set the NETLINK_RECV_NO_ENOBUFS socket option. This return value is used in the next patch in these bugfix series. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index fde27c017326..6eaca5e1e8ca 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -188,7 +188,7 @@ extern int netlink_has_listeners(struct sock *sk, unsigned int group); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, __u32 group, gfp_t allocation); -extern void netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); +extern int netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); -- cgit v1.2.2 From 37b7ef7203240b3aba577bb1ff6765fe15225976 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 16 Mar 2010 13:30:21 +0000 Subject: netfilter: ctnetlink: fix reliable event delivery if message building fails This patch fixes a bug that allows to lose events when reliable event delivery mode is used, ie. if NETLINK_BROADCAST_SEND_ERROR and NETLINK_RECV_NO_ENOBUFS socket options are set. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 53923868c9bd..361d6b5630ee 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -76,7 +76,7 @@ extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); extern int nfnetlink_has_listeners(struct net *net, unsigned int group); extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo, gfp_t flags); -extern void nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error); +extern int nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error); extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags); extern void nfnl_lock(void); -- cgit v1.2.2 From 372e6c8f1f7b2bb68f9992d2e664925c73552a1d Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:09 +0000 Subject: ipv6: convert temporary address list to list macros Use list macros instead of open coded linked list. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/if_inet6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 545d8b059bef..09d906460a43 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -58,7 +58,7 @@ struct inet6_ifaddr { struct inet6_ifaddr *if_next; /* next addr in inet6_dev */ #ifdef CONFIG_IPV6_PRIVACY - struct inet6_ifaddr *tmp_next; /* next addr in tempaddr_lst */ + struct list_head tmp_list; struct inet6_ifaddr *ifpub; int regen_count; #endif @@ -175,7 +175,7 @@ struct inet6_dev { #ifdef CONFIG_IPV6_PRIVACY u8 rndid[8]; struct timer_list regen_timer; - struct inet6_ifaddr *tempaddr_list; + struct list_head tempaddr_list; #endif struct neigh_parms *nd_parms; -- cgit v1.2.2 From c2e21293c054817c42eb5fa9c613d2ad51954136 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:10 +0000 Subject: ipv6: convert addrconf list to hlist Using hash list macros, simplifies code and helps later RCU. This patch includes some initialization that is not strictly necessary, since an empty hlist node/list is all zero; and list is in BSS and node is allocated with kzalloc. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/if_inet6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 09d906460a43..498401541519 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -54,7 +54,7 @@ struct inet6_ifaddr { struct inet6_dev *idev; struct rt6_info *rt; - struct inet6_ifaddr *lst_next; /* next addr in addr_lst */ + struct hlist_node addr_lst; struct inet6_ifaddr *if_next; /* next addr in inet6_dev */ #ifdef CONFIG_IPV6_PRIVACY -- cgit v1.2.2 From 5c578aedcb21d79eeb4e9cf04ca5b276ac82614c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:11 +0000 Subject: IPv6: convert addrconf hash list to RCU Convert from reader/writer lock to RCU and spinlock for addrconf hash list. Adds an additional helper macro for hlist_for_each_entry_continue_rcu to handle the continue case. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/rculist.h | 13 +++++++++++++ include/net/if_inet6.h | 1 + 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 2c9b46cff3d7..004908b104d5 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -428,5 +428,18 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) +/** + * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_continue_rcu(tpos, pos, member) \ + for (pos = rcu_dereference((pos)->next); \ + pos && ({ prefetch(pos->next); 1; }) && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ + pos = rcu_dereference(pos->next)) + + #endif /* __KERNEL__ */ #endif diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 498401541519..22a00b1d2c38 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -64,6 +64,7 @@ struct inet6_ifaddr { #endif int dead; + struct rcu_head rcu; }; struct ip6_sf_socklist { -- cgit v1.2.2 From 502a2ffd7376ae27cfde6172257db0ff9d8cfec2 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:13 +0000 Subject: ipv6: convert idev_list to list macros Convert to list macro's for the list of addresses per interface in IPv6. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/if_inet6.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 22a00b1d2c38..13f9fc086d54 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -55,7 +55,7 @@ struct inet6_ifaddr { struct rt6_info *rt; struct hlist_node addr_lst; - struct inet6_ifaddr *if_next; /* next addr in inet6_dev */ + struct list_head if_list; #ifdef CONFIG_IPV6_PRIVACY struct list_head tmp_list; @@ -152,9 +152,9 @@ struct ipv6_devstat { }; struct inet6_dev { - struct net_device *dev; + struct net_device *dev; - struct inet6_ifaddr *addr_list; + struct list_head addr_list; struct ifmcaddr6 *mc_list; struct ifmcaddr6 *mc_tomb; -- cgit v1.2.2 From aef7d97cc604309b66f6f45cce02cd734934cd4e Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 21 Mar 2010 05:27:45 +0100 Subject: Bluetooth: Convert debug files to actually use debugfs instead of sysfs Some of the debug files ended up wrongly in sysfs, because at that point of time, debugfs didn't exist. Convert these files to use debugfs and also seq_file. This patch converts all of these files at once and then removes the exported symbol for the Bluetooth sysfs class. Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 04a6908e38d2..ff77e8f882f1 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -176,6 +176,6 @@ extern void hci_sock_cleanup(void); extern int bt_sysfs_init(void); extern void bt_sysfs_cleanup(void); -extern struct class *bt_class; +extern struct dentry *bt_debugfs; #endif /* __BLUETOOTH_H */ -- cgit v1.2.2 From 755d0e77ac9c8d125388922dc33434ed5b2ebe80 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Mar 2010 04:42:24 +0000 Subject: net: rtnetlink: ignore NETDEV_PRE_TYPE_CHANGE in rtnetlink_event() Ignore the new NETDEV_PRE_TYPE_CHANGE event in rtnetlink_event() since there have been no changes userspace needs to be notified of. Also add a comment to the netdev notifier event definitions to remind people to update the exclusion list when adding new event types. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/notifier.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index f3635fc6e942..9c5d3fad01f3 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -182,7 +182,10 @@ static inline int notifier_to_errno(int ret) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ -/* netdevice notifier chain */ +/* netdevice notifier chain. Please remember to update the rtnetlink + * notification exclusion list in rtnetlink_event() when adding new + * types. + */ #define NETDEV_UP 0x0001 /* For now you can't veto a device up/down */ #define NETDEV_DOWN 0x0002 #define NETDEV_REBOOT 0x0003 /* Tell a protocol stack a network interface -- cgit v1.2.2 From 32a806c194ea112cfab00f558482dd97bee5e44e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 19 Mar 2010 04:00:23 +0000 Subject: bonding: flush unicast and multicast lists when changing type After the type change, addresses in unicast and multicast lists wouldn't make sense, not to mention possible different lenghts. So flush both lists here. Note "dev_addr_discard" will be very soon replaced by "dev_mc_flush" (once mc_list conversion will be done). Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9fc6ee8e7508..c96c41e08e37 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1994,10 +1994,12 @@ extern int dev_unicast_delete(struct net_device *dev, void *addr); extern int dev_unicast_add(struct net_device *dev, void *addr); extern int dev_unicast_sync(struct net_device *to, struct net_device *from); extern void dev_unicast_unsync(struct net_device *to, struct net_device *from); +extern void dev_unicast_flush(struct net_device *dev); extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all); extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); extern int dev_mc_sync(struct net_device *to, struct net_device *from); extern void dev_mc_unsync(struct net_device *to, struct net_device *from); +extern void dev_addr_discard(struct net_device *dev); extern int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all); extern int __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly); extern int __dev_addr_sync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count); -- cgit v1.2.2 From 907cdda5205b012eec7513f66713749b293188c9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Mar 2010 05:37:18 +0000 Subject: tcp: Add SNMP counter for DEFER_ACCEPT Its currently hard to diagnose when ACK frames are dropped because an application set TCP_DEFER_ACCEPT on its listening socket. See http://bugzilla.kernel.org/show_bug.cgi?id=15507 This patch adds a SNMP value, named TCPDeferAcceptDrop netstat -s | grep TCPDeferAcceptDrop TCPDeferAcceptDrop: 0 This counter is incremented every time we drop a pure ACK frame received by a socket in SYN_RECV state because its SYNACK retrans count is lower than defer_accept value. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/snmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 4435d1084755..d2a9aa3c6c88 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -227,6 +227,7 @@ enum LINUX_MIB_SACKSHIFTFALLBACK, LINUX_MIB_TCPBACKLOGDROP, LINUX_MIB_TCPMINTTLDROP, /* RFC 5082 */ + LINUX_MIB_TCPDEFERACCEPTDROP, __LINUX_MIB_MAX }; -- cgit v1.2.2 From ec733b15a3ef0b5759141a177f8044a2f40c41e7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Mar 2010 20:36:06 +0000 Subject: net: snmp mib cleanup There is no point to align or pad mibs to cache lines, they are per cpu allocated with a 8 bytes alignment anyway. This wastes space for no gain. This patch removes __SNMP_MIB_ALIGN__ Since SNMP mibs contain "unsigned long" fields only, we can relax the allocation alignment from "unsigned long long" to "unsigned long" Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 2 +- include/net/snmp.h | 29 +++++++---------------------- 2 files changed, 8 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 78740ec57d5d..59151557406c 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -268,7 +268,7 @@ enum { #define SCTP_MIB_MAX __SCTP_MIB_MAX struct sctp_mib { unsigned long mibs[SCTP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* Print debugging messages. */ diff --git a/include/net/snmp.h b/include/net/snmp.h index 692ee0061dc4..884fdbb74b23 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -52,26 +52,11 @@ struct snmp_mib { * count on the 20Gb/s + networks people expect in a few years time! */ -/* - * The rule for padding: - * Best is power of two because then the right structure can be found by a - * simple shift. The structure should be always cache line aligned. - * gcc needs n=alignto(cachelinesize, popcnt(sizeof(bla_mib))) shift/add - * instructions to emulate multiply in case it is not power-of-two. - * Currently n is always <=3 for all sizes so simple cache line alignment - * is enough. - * - * The best solution would be a global CPU local area , especially on 64 - * and 128byte cacheline machine it makes a *lot* of sense -AK - */ - -#define __SNMP_MIB_ALIGN__ ____cacheline_aligned - /* IPstats */ #define IPSTATS_MIB_MAX __IPSTATS_MIB_MAX struct ipstats_mib { unsigned long mibs[IPSTATS_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* ICMP */ #define ICMP_MIB_DUMMY __ICMP_MIB_MAX @@ -79,36 +64,36 @@ struct ipstats_mib { struct icmp_mib { unsigned long mibs[ICMP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; #define ICMPMSG_MIB_MAX __ICMPMSG_MIB_MAX struct icmpmsg_mib { unsigned long mibs[ICMPMSG_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* ICMP6 (IPv6-ICMP) */ #define ICMP6_MIB_MAX __ICMP6_MIB_MAX struct icmpv6_mib { unsigned long mibs[ICMP6_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; #define ICMP6MSG_MIB_MAX __ICMP6MSG_MIB_MAX struct icmpv6msg_mib { unsigned long mibs[ICMP6MSG_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* TCP */ #define TCP_MIB_MAX __TCP_MIB_MAX struct tcp_mib { unsigned long mibs[TCP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* UDP */ #define UDP_MIB_MAX __UDP_MIB_MAX struct udp_mib { unsigned long mibs[UDP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* Linux */ #define LINUX_MIB_MAX __LINUX_MIB_MAX -- cgit v1.2.2 From 9bf35c8dddd56f7f247a27346f74f5adc18071f4 Mon Sep 17 00:00:00 2001 From: Paulius Zaleckas Date: Sun, 21 Mar 2010 21:19:02 -0700 Subject: if_tunnel.h: add missing ams/byteorder.h include When compiling userspace application which includes if_tunnel.h and uses GRE_* defines you will get undefined reference to __cpu_to_be16. Fix this by adding missing #include Cc: stable@kernel.org Signed-off-by: Paulius Zaleckas Signed-off-by: David S. Miller --- include/linux/if_tunnel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 1822d635be6b..16b92d008bed 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -2,6 +2,7 @@ #define _IF_TUNNEL_H_ #include +#include #ifdef __KERNEL__ #include -- cgit v1.2.2 From c9acb42ef1904d15d0fb315061cefbe638f67f3a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 19 Mar 2010 15:36:22 -0400 Subject: SUNRPC: Fix a use after free bug with the NFSv4.1 backchannel The ->release_request() callback was designed to allow the transport layer to do housekeeping after the RPC call is done. It cannot be used to free the request itself, and doing so leads to a use-after-free bug in xprt_release(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index d7152b451e21..7c91260c44a9 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -36,7 +36,6 @@ struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, int max_reqs); -void bc_release_request(struct rpc_task *); int bc_send(struct rpc_rqst *req); /* @@ -59,6 +58,10 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) { return 0; } + +static inline void xprt_free_bc_request(struct rpc_rqst *req) +{ +} #endif /* CONFIG_NFS_V4_1 */ #endif /* _LINUX_SUNRPC_BC_XPRT_H */ -- cgit v1.2.2 From ae6be51ed01d6c4aaf249a207b4434bc7785853b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 22 Mar 2010 13:12:33 -0700 Subject: Fix up prototype for sys_ipc breakage Commit 45575f5a426c ("ppc64 sys_ipc breakage in 2.6.34-rc2") fixed the definition of the sys_ipc() helper, but didn't fix the prototype in Reported-and-tested-by: Andreas Schwab Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f994ae58a002..057929b0a651 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -688,7 +688,7 @@ asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); asmlinkage long sys_shmget(key_t key, size_t size, int flag); asmlinkage long sys_shmdt(char __user *shmaddr); asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); -asmlinkage long sys_ipc(unsigned int call, int first, int second, +asmlinkage long sys_ipc(unsigned int call, int first, unsigned long second, unsigned long third, void __user *ptr, long fifth); asmlinkage long sys_mq_open(const char __user *name, int oflag, mode_t mode, struct mq_attr __user *attr); -- cgit v1.2.2 From 66f1207bce10fd80ee8ce99b67d617644612f05e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 11 Mar 2010 17:01:09 -0700 Subject: resources: add interfaces that return conflict information request_resource() and insert_resource() only return success or failure, which no information about what existing resource conflicted with the proposed new reservation. This patch adds request_resource_conflict() and insert_resource_conflict(), which return the conflicting resource. Callers may use this for better error messages or to adjust the new resource and retry the request. Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 71ab79da7e7f..26fad187d661 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -112,12 +112,14 @@ struct resource_list { extern struct resource ioport_resource; extern struct resource iomem_resource; +extern struct resource *request_resource_conflict(struct resource *root, struct resource *new); extern int request_resource(struct resource *root, struct resource *new); extern int release_resource(struct resource *new); void release_child_resources(struct resource *new); extern void reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name); +extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new); extern int insert_resource(struct resource *parent, struct resource *new); extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new); extern int allocate_resource(struct resource *root, struct resource *new, -- cgit v1.2.2 From f6e0bb56d43d1f3b2ad54d51b65c07ef3bdead16 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 18 Mar 2010 18:29:32 -0700 Subject: include/linux/wireless.h: Add IW_HANDLER macro to initialize array entry Copied the idea from orinoco Signed-off-by: Joe Perches Signed-off-by: John W. Linville --- include/linux/wireless.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 5b4c6c772a9b..0955b67616d2 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -346,6 +346,8 @@ #define SIOCIWFIRST 0x8B00 #define SIOCIWLAST SIOCIWLASTPRIV /* 0x8BFF */ #define IW_IOCTL_IDX(cmd) ((cmd) - SIOCIWFIRST) +#define IW_HANDLER(id, func) \ + [IW_IOCTL_IDX(id)] = func /* Odd : get (world access), even : set (root access) */ #define IW_IS_SET(cmd) (!((cmd) & 0x1)) -- cgit v1.2.2 From 2ae2332ed11687325096e68e326ec57f0294cff9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 18 Mar 2010 18:29:33 -0700 Subject: wireless.h: Use SIOCIWFIRST not SIOCSIWCOMMIT for range check These two #defines use the same value, but SIOCIWFIRST makes more sense in this use. Signed-off-by: Joe Perches Signed-off-by: John W. Linville --- include/linux/wireless.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 0955b67616d2..e6827eedf18b 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -650,7 +650,7 @@ * 32 bit bitmasks. Note : 32 bits = 0x20 = 2^5. */ #define IW_EVENT_CAPA_BASE(cmd) ((cmd >= SIOCIWFIRSTPRIV) ? \ (cmd - SIOCIWFIRSTPRIV + 0x60) : \ - (cmd - SIOCSIWCOMMIT)) + (cmd - SIOCIWFIRST)) #define IW_EVENT_CAPA_INDEX(cmd) (IW_EVENT_CAPA_BASE(cmd) >> 5) #define IW_EVENT_CAPA_MASK(cmd) (1 << (IW_EVENT_CAPA_BASE(cmd) & 0x1F)) /* Event capability constants - event autogenerated by the kernel -- cgit v1.2.2 From 1e4dcd012423b6a28f968a55886d2b27896a1586 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Fri, 19 Mar 2010 07:14:53 +0200 Subject: mac80211: Add support for connection monitor in hardware This patch is based on a RFC patch by Kalle Valo. The wl1271 has a feature which handles the connection monitor logic in hardware, basically sending periodically nullfunc frames and reporting to the host if AP is lost, after attempting to recover by sending probe-requests to the AP. Add support to mac80211 by adding a new flag IEEE80211_HW_CONNECTION_MONITOR which prevents conn_mon_timer from triggering during idle periods, and prevents sending probe-requests to the AP if beacon-loss is indicated by the hardware. Cc: Kalle Valo Signed-off-by: Juuso Oikarinen Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 936bc410d061..d14226f29ffc 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -954,6 +954,11 @@ enum ieee80211_tkip_key_type { * Hardware can provide ack status reports of Tx frames to * the stack. * + * @IEEE80211_HW_CONNECTION_MONITOR: + * The hardware performs its own connection monitoring, including + * periodic keep-alives to the AP and probing the AP on beacon loss. + * When this flag is set, signaling beacon-loss will cause an immediate + * change to disassociated state. */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -975,6 +980,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS = 1<<16, IEEE80211_HW_SUPPORTS_UAPSD = 1<<17, IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, + IEEE80211_HW_CONNECTION_MONITOR = 1<<19, }; /** @@ -2364,12 +2370,26 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * When beacon filtering is enabled with IEEE80211_HW_BEACON_FILTERING and - * IEEE80211_CONF_PS is set, the driver needs to inform whenever the + * When beacon filtering is enabled with %IEEE80211_HW_BEACON_FILTERING and + * %IEEE80211_CONF_PS is set, the driver needs to inform whenever the * hardware is not receiving beacons with this function. */ void ieee80211_beacon_loss(struct ieee80211_vif *vif); +/** + * ieee80211_connection_loss - inform hardware has lost connection to the AP + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * When beacon filtering is enabled with %IEEE80211_HW_BEACON_FILTERING, and + * %IEEE80211_CONF_PS and %IEEE80211_HW_CONNECTION_MONITOR are set, the driver + * needs to inform if the connection to the AP has been lost. + * + * This function will cause immediate change to disassociated state, + * without connection recovery attempts. + */ +void ieee80211_connection_loss(struct ieee80211_vif *vif); + /* Rate control API */ /** -- cgit v1.2.2 From 8a6d9b149f105f8bdfa8e42dd9753e45a1887a16 Mon Sep 17 00:00:00 2001 From: Ferenc Wagner Date: Wed, 24 Mar 2010 08:20:03 +0100 Subject: i2o: Remove the dangerous kobj_to_i2o_device macro This macro worked only when applied to variables named 'kobj'. While this could have been fixed by simply renaming the macro argument, a more type-safe replacement by an inline function would be preferred. However, nobody uses this macro, so it's simpler to just remove it. Signed-off-by: Ferenc Wagner Signed-off-by: Jens Axboe --- include/linux/i2o.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 87018dc5527d..9e7a12d6385d 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -782,7 +782,6 @@ extern int i2o_exec_lct_get(struct i2o_controller *); #define to_i2o_driver(drv) container_of(drv,struct i2o_driver, driver) #define to_i2o_device(dev) container_of(dev, struct i2o_device, device) #define to_i2o_controller(dev) container_of(dev, struct i2o_controller, device) -#define kobj_to_i2o_device(kobj) to_i2o_device(container_of(kobj, struct device, kobj)) /** * i2o_out_to_virt - Turn an I2O message to a virtual address -- cgit v1.2.2 From d7646f7632549124fe70fec8af834c7c1246f365 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 15 Mar 2010 21:46:34 +0100 Subject: pcmcia: use dev_pm_ops for class pcmcia_socket_class Instead of requiring PCMCIA socket drivers to call various functions during their (bus) resume and suspend functions, register an own dev_pm_ops for this class. This fixes several suspend/resume bugs seen on db1xxx-ss, and probably on some other socket drivers, too. With regard to the asymmetry with only _noirq suspend, but split up resume, please see bug 14334 and commit 9905d1b411946fb3 . Signed-off-by: Dominik Brodowski --- include/pcmcia/ss.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h index 32896a773910..2e488b60bc76 100644 --- a/include/pcmcia/ss.h +++ b/include/pcmcia/ss.h @@ -277,12 +277,6 @@ extern struct pccard_resource_ops pccard_nonstatic_ops; #endif -/* socket drivers are expected to use these callbacks in their .drv struct */ -extern int pcmcia_socket_dev_suspend(struct device *dev); -extern void pcmcia_socket_dev_early_resume(struct device *dev); -extern void pcmcia_socket_dev_late_resume(struct device *dev); -extern int pcmcia_socket_dev_resume(struct device *dev); - /* socket drivers use this callback in their IRQ handler */ extern void pcmcia_parse_events(struct pcmcia_socket *socket, unsigned int events); -- cgit v1.2.2 From 222e82ac9ffbd3b80ab1b0b1d2c8c60ddb47d69d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 24 Mar 2010 14:38:37 +0100 Subject: acpi: Support IBM SMBus CMI devices On some old IBM workstations and desktop computers, the BIOS presents in the DSDT an SMBus object that is missing the HID identifier that the i2c-scmi driver looks for. Modify the ACPI device scan code to insert the missing HID if it finds an IBM system with such an object. Affected machines: IntelliStation Z20/Z30. Note that the i2c-i801 driver no longer works on these machines because of ACPI resource conflicts. Signed-off-by: Darrick J. Wong Signed-off-by: Jean Delvare --- include/acpi/acpi_drivers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h index 3a4767c01c5f..4f7b44866b76 100644 --- a/include/acpi/acpi_drivers.h +++ b/include/acpi/acpi_drivers.h @@ -65,6 +65,8 @@ #define ACPI_VIDEO_HID "LNXVIDEO" #define ACPI_BAY_HID "LNXIOBAY" #define ACPI_DOCK_HID "LNXDOCK" +/* Quirk for broken IBM BIOSes */ +#define ACPI_SMBUS_IBM_HID "SMBUSIBM" /* * For fixed hardware buttons, we fabricate acpi_devices with HID -- cgit v1.2.2 From 03e6d819c2cb2cc8ce5642669a0a7c72336ee7a2 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 23 Mar 2010 20:40:50 +0000 Subject: skbuff: remove unused dma_head & dma_maps fields The dma map fields in the skb_shared_info structure no longer has any users and can be dropped since it is making the skb_shared_info unecessarily larger. Running slabtop show that we were using 4K slabs for the skb->head on x86_64 w/ an allocation size of 1522. It turns out that the dma_head and dma_maps array made skb_shared large enough that we had crossed over the 2k boundary with standard frames and as such we were using 4k blocks of memory for all skbs. Signed-off-by: Alexander Duyck Signed-off-by: Jeff Kirsher Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 03f816a9b659..124f90cd5a38 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -190,9 +190,6 @@ struct skb_shared_info { atomic_t dataref; unsigned short nr_frags; unsigned short gso_size; -#ifdef CONFIG_HAS_DMA - dma_addr_t dma_head; -#endif /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; unsigned short gso_type; @@ -201,9 +198,6 @@ struct skb_shared_info { struct sk_buff *frag_list; struct skb_shared_hwtstamps hwtstamps; skb_frag_t frags[MAX_SKB_FRAGS]; -#ifdef CONFIG_HAS_DMA - dma_addr_t dma_maps[MAX_SKB_FRAGS]; -#endif /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ void * destructor_arg; -- cgit v1.2.2 From d6dc1a386358979e12366d1f35eeb68fc181e101 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Tue, 23 Mar 2010 09:02:33 +0200 Subject: cfg80211: Add connection quality monitoring support to nl80211 Add support for basic configuration of a connection quality monitoring to the nl80211 interface, and basic support for notifying about triggered monitoring events. Via this interface a user-space connection manager may configure and receive pre-warning events of deteriorating WLAN connection quality, and start preparing for roaming in advance, before the connection is already lost. An example usage of such a trigger is starting scanning for nearby AP's in an attempt to find one with better connection quality, and associate to it before the connection characteristics of the existing connection become too bad or the association is even lost, leading in a prolonged delay in connectivity. The interface currently supports only RSSI, but it could be later extended to include other parameters, such as signal-to-noise ratio, if need for that arises. Signed-off-by: Juuso Oikarinen Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ include/net/cfg80211.h | 19 +++++++++++++++++++ 2 files changed, 65 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 28ba20fda3e2..89947597b9ce 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -323,6 +323,12 @@ * the TX command and %NL80211_ATTR_FRAME includes the contents of the * frame. %NL80211_ATTR_ACK flag is included if the recipient acknowledged * the frame. + * @NL80211_CMD_SET_CQM: Connection quality monitor configuration. This command + * is used to configure connection quality monitoring notification trigger + * levels. + * @NL80211_CMD_NOTIFY_CQM: Connection quality monitor notification. This + * command is used as an event to indicate the that a trigger level was + * reached. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -419,6 +425,9 @@ enum nl80211_commands { NL80211_CMD_SET_POWER_SAVE, NL80211_CMD_GET_POWER_SAVE, + NL80211_CMD_SET_CQM, + NL80211_CMD_NOTIFY_CQM, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -691,6 +700,9 @@ enum nl80211_commands { * @NL80211_ATTR_ACK: Flag attribute indicating that the frame was * acknowledged by the recipient. * + * @NL80211_ATTR_CQM: connection quality monitor configuration in a + * nested attribute with %NL80211_ATTR_CQM_* sub-attributes. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -842,6 +854,8 @@ enum nl80211_attrs { NL80211_ATTR_PS_STATE, + NL80211_ATTR_CQM, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1583,4 +1597,36 @@ enum nl80211_ps_state { NL80211_PS_ENABLED, }; +/** + * enum nl80211_attr_cqm - connection quality monitor attributes + * @__NL80211_ATTR_CQM_INVALID: invalid + * @NL80211_ATTR_CQM_RSSI_THOLD: RSSI threshold in dBm (zero to disable) + * @NL80211_ATTR_CQM_RSSI_HYST: RSSI hysteresis in dBm + * @NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT: RSSI threshold event + * @__NL80211_ATTR_CQM_AFTER_LAST: internal + * @NL80211_ATTR_CQM_MAX: highest key attribute + */ +enum nl80211_attr_cqm { + __NL80211_ATTR_CQM_INVALID, + NL80211_ATTR_CQM_RSSI_THOLD, + NL80211_ATTR_CQM_RSSI_HYST, + NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, + + /* keep last */ + __NL80211_ATTR_CQM_AFTER_LAST, + NL80211_ATTR_CQM_MAX = __NL80211_ATTR_CQM_AFTER_LAST - 1 +}; + +/** + * enum nl80211_cqm_rssi_threshold_event - RSSI threshold event + * @NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW - The RSSI level is lower than the + * configured threshold + * @NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH - The RSSI is higher than the + * configured threshold + */ +enum nl80211_cqm_rssi_threshold_event { + NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW, + NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 3d134a1fb96b..868cfd3b9724 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1007,6 +1007,7 @@ struct cfg80211_pmksa { * RSN IE. It allows for faster roaming between WPA2 BSSIDs. * @del_pmksa: Delete a cached PMKID. * @flush_pmksa: Flush all cached PMKIDs. + * @set_cqm_rssi_config: Configure connection quality monitor RSSI threshold. * */ struct cfg80211_ops { @@ -1152,6 +1153,10 @@ struct cfg80211_ops { int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); + + int (*set_cqm_rssi_config)(struct wiphy *wiphy, + struct net_device *dev, + s32 rssi_thold, u32 rssi_hyst); }; /* @@ -2337,4 +2342,18 @@ bool cfg80211_rx_action(struct net_device *dev, int freq, const u8 *buf, void cfg80211_action_tx_status(struct net_device *dev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp); + +/** + * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event + * @dev: network device + * @rssi_event: the triggered RSSI event + * @gfp: context flags + * + * This function is called when a configured connection quality monitoring + * rssi threshold reached event occurs. + */ +void cfg80211_cqm_rssi_notify(struct net_device *dev, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp); + #endif /* __NET_CFG80211_H */ -- cgit v1.2.2 From a97c13c34509be460dea23c86f31c02daa2428b5 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Tue, 23 Mar 2010 09:02:34 +0200 Subject: mac80211: Add support for connection quality monitoring Add support for the set_cqm_config op. This op function configures the requested connection quality monitor rssi threshold and rssi hysteresis values to the hardware if the hardware supports IEEE80211_HW_SUPPORTS_CQM. For unsupported hardware, currently -EOPNOTSUPP is returned, so the mac80211 is currently not doing connection quality monitoring on the host. This could be added later, if needed. Signed-off-by: Juuso Oikarinen Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d14226f29ffc..1a8f50af49a0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -144,6 +144,7 @@ struct ieee80211_low_level_stats { * new beacon (beaconing modes) * @BSS_CHANGED_BEACON_ENABLED: Beaconing should be * enabled/disabled (beaconing modes) + * @BSS_CHANGED_CQM: Connection quality monitor config changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -156,6 +157,7 @@ enum ieee80211_bss_change { BSS_CHANGED_BSSID = 1<<7, BSS_CHANGED_BEACON = 1<<8, BSS_CHANGED_BEACON_ENABLED = 1<<9, + BSS_CHANGED_CQM = 1<<10, }; /** @@ -185,6 +187,9 @@ enum ieee80211_bss_change { * @enable_beacon: whether beaconing should be enabled or not * @ht_operation_mode: HT operation mode (like in &struct ieee80211_ht_info). * This field is only valid when the channel type is one of the HT types. + * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value + * implies disabled + * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis */ struct ieee80211_bss_conf { const u8 *bssid; @@ -202,6 +207,8 @@ struct ieee80211_bss_conf { u64 timestamp; u32 basic_rates; u16 ht_operation_mode; + s32 cqm_rssi_thold; + u32 cqm_rssi_hyst; }; /** @@ -959,6 +966,12 @@ enum ieee80211_tkip_key_type { * periodic keep-alives to the AP and probing the AP on beacon loss. * When this flag is set, signaling beacon-loss will cause an immediate * change to disassociated state. + * + * @IEEE80211_HW_SUPPORTS_CQM_RSSI: + * Hardware can do connection quality monitoring - i.e. it can monitor + * connection quality related parameters, such as the RSSI level and + * provide notifications if configured trigger levels are reached. + * */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -981,6 +994,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_UAPSD = 1<<17, IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, IEEE80211_HW_CONNECTION_MONITOR = 1<<19, + IEEE80211_HW_SUPPORTS_CQM_RSSI = 1<<20, }; /** @@ -2390,6 +2404,22 @@ void ieee80211_beacon_loss(struct ieee80211_vif *vif); */ void ieee80211_connection_loss(struct ieee80211_vif *vif); +/** + * ieee80211_cqm_rssi_notify - inform a configured connection quality monitoring + * rssi threshold triggered + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @rssi_event: the RSSI trigger event type + * @gfp: context flags + * + * When the %IEEE80211_HW_SUPPORTS_CQM_RSSI is set, and a connection quality + * monitoring is configured with an rssi threshold, the driver will inform + * whenever the rssi level reaches the threshold. + */ +void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp); + /* Rate control API */ /** -- cgit v1.2.2 From 4ac5541bdaea4d8e93710c58775cfa48ac82e09b Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Wed, 24 Mar 2010 10:11:14 +0200 Subject: cfg80211: Improve connection quality maintenance docs in nl80211.h In nl80211.h, be a little more elaborate in the docs for the definitions NL80211_ATTR_CQM_RSSI_THOLD and NL80211_ATTR_CQM_RSSI_HYST. Reported-by: Luis R. Rodriguez Signed-off-by: Juuso Oikarinen Signed-off-by: John W. Linville --- include/linux/nl80211.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 89947597b9ce..daf6a3432b92 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1600,8 +1600,12 @@ enum nl80211_ps_state { /** * enum nl80211_attr_cqm - connection quality monitor attributes * @__NL80211_ATTR_CQM_INVALID: invalid - * @NL80211_ATTR_CQM_RSSI_THOLD: RSSI threshold in dBm (zero to disable) - * @NL80211_ATTR_CQM_RSSI_HYST: RSSI hysteresis in dBm + * @NL80211_ATTR_CQM_RSSI_THOLD: RSSI threshold in dBm. This value specifies + * the threshold for the RSSI level at which an event will be sent. Zero + * to disable. + * @NL80211_ATTR_CQM_RSSI_HYST: RSSI hysteresis in dBm. This value specifies + * the minimum amount the RSSI level must change after an event before a + * new event may be issued (to reduce effects of RSSI oscillation). * @NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT: RSSI threshold event * @__NL80211_ATTR_CQM_AFTER_LAST: internal * @NL80211_ATTR_CQM_MAX: highest key attribute -- cgit v1.2.2 From 4c87684d32e8f95715d53039dcd2d998dc63d1eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=A4rdeman?= Date: Tue, 23 Mar 2010 13:35:22 -0700 Subject: kfifo: fix KFIFO_INIT in include/linux/kfifo.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit include/linux/kfifo.h first defines and then undefines __kfifo_initializer which is used by INIT_KFIFO (which is also a macro, so building a module which uses INIT_KFIFO will fail). Signed-off-by: David Härdeman Acked-by: Stefani Seibold Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index bc0fc795bd35..ece0b1c33816 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -102,8 +102,6 @@ union { \ unsigned char name##kfifo_buffer[size]; \ struct kfifo name = __kfifo_initializer(size, name##kfifo_buffer) -#undef __kfifo_initializer - extern void kfifo_init(struct kfifo *fifo, void *buffer, unsigned int size); extern __must_check int kfifo_alloc(struct kfifo *fifo, unsigned int size, -- cgit v1.2.2 From 6cb4aff0a77cc0e6bae9475d62205319e3ebbf3f Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 23 Mar 2010 13:35:38 -0700 Subject: reiserfs: fix oops while creating privroot with selinux enabled Commit 57fe60df ("reiserfs: add atomic addition of selinux attributes during inode creation") contains a bug that will cause it to oops when mounting a file system that didn't previously contain extended attributes on a system using security.* xattrs. The issue is that while creating the privroot during mount reiserfs_security_init calls reiserfs_xattr_jcreate_nblocks which dereferences the xattr root. The xattr root doesn't exist, so we get an oops. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=15309 Signed-off-by: Jeff Mahoney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_xattr.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 99928dce37ea..7fa02b4af838 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -70,6 +70,11 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, void reiserfs_security_free(struct reiserfs_security_handle *sec); #endif +static inline int reiserfs_xattrs_initialized(struct super_block *sb) +{ + return REISERFS_SB(sb)->priv_root != NULL; +} + #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header)) static inline loff_t reiserfs_xattr_nblocks(struct inode *inode, loff_t size) { -- cgit v1.2.2 From 7198f3c9b13c7aa1e5d9f7ff74c0ea303174feff Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 23 Mar 2010 13:35:40 -0700 Subject: mmc: fix incorrect interpretation of card type bits In the extended CSD register the CARD_TYPE is an 8-bit value of which the upper 6 bits were reserved in JEDEC specifications prior to version 4.4. In version 4.4 two of the reserved bits were designated for identifying support for the newly added High-Speed Dual Data Rate. Unfortunately the mmc_read_ext_csd() function required that the reserved bits be zero instead of ignoring them as it should. This patch makes mmc_read_ext_csd() ignore the CARD_TYPE bits that are reserved or not yet supported. It also stops the function jumping to the end as though an error occurred, when it is only warns that the CARD_TYPE bits (that it does interpret) are invalid. Signed-off-by: Adrian Hunter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/mmc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index c02c8db73701..8a49cbf0376d 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -268,6 +268,7 @@ struct _mmc_csd { #define EXT_CSD_CARD_TYPE_26 (1<<0) /* Card can run at 26MHz */ #define EXT_CSD_CARD_TYPE_52 (1<<1) /* Card can run at 52MHz */ +#define EXT_CSD_CARD_TYPE_MASK 0x3 /* Mask out reserved and DDR bits */ #define EXT_CSD_BUS_WIDTH_1 0 /* Card is in 1 bit mode */ #define EXT_CSD_BUS_WIDTH_4 1 /* Card is in 4 bit mode */ -- cgit v1.2.2 From 90fddabf5818367c6bd1fe1b256a10e01827862f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 24 Mar 2010 09:43:00 +0000 Subject: Document Linux's circular buffering capabilities Document the circular buffering capabilities available in Linux. Signed-off-by: David Howells Signed-off-by: Paul E. McKenney Reviewed-by: Randy Dunlap Reviewed-by: Stefan Richter Signed-off-by: Linus Torvalds --- include/linux/circ_buf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/circ_buf.h b/include/linux/circ_buf.h index a2ed0591fb19..90f2471dc6f2 100644 --- a/include/linux/circ_buf.h +++ b/include/linux/circ_buf.h @@ -1,3 +1,7 @@ +/* + * See Documentation/circular-buffers.txt for more information. + */ + #ifndef _LINUX_CIRC_BUF_H #define _LINUX_CIRC_BUF_H 1 -- cgit v1.2.2 From 9c13886665c43600bd0af4b38e33c654e648e078 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 25 Mar 2010 11:17:26 +0100 Subject: netfilter: ip6table_raw: fix table priority The order of the IPv6 raw table is currently reversed, that makes impossible to use the NOTRACK target in IPv6: for example if someone enters ip6tables -t raw -A PREROUTING -p tcp --dport 80 -j NOTRACK and if we receive fragmented packets then the first fragment will be untracked and thus skip nf_ct_frag6_gather (and conntrack), while all subsequent fragments enter nf_ct_frag6_gather and reassembly will never successfully be finished. Singed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter_ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index d654873aa25a..1f7e300094cd 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -59,6 +59,7 @@ enum nf_ip6_hook_priorities { NF_IP6_PRI_FIRST = INT_MIN, NF_IP6_PRI_CONNTRACK_DEFRAG = -400, + NF_IP6_PRI_RAW = -300, NF_IP6_PRI_SELINUX_FIRST = -225, NF_IP6_PRI_CONNTRACK = -200, NF_IP6_PRI_MANGLE = -150, -- cgit v1.2.2 From df3345457a7a174dfb5872a070af80d456985038 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 Mar 2010 19:13:54 +0000 Subject: rps: add CONFIG_RPS RPS currently depends on SMP and SYSFS Adding a CONFIG_RPS makes sense in case this requirement changes in the future. This patch saves about 1500 bytes of kernel text in case SMP is on but SYSFS is off. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c96c41e08e37..53c272f2a734 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -531,6 +531,7 @@ struct netdev_queue { unsigned long tx_dropped; } ____cacheline_aligned_in_smp; +#ifdef CONFIG_RPS /* * This structure holds an RPS map which can be of variable length. The * map is an array of CPUs. @@ -549,6 +550,7 @@ struct netdev_rx_queue { struct netdev_rx_queue *first; atomic_t count; } ____cacheline_aligned_in_smp; +#endif /* * This structure defines the management hooks for network devices. @@ -897,12 +899,14 @@ struct net_device { unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ +#ifdef CONFIG_RPS struct kset *queues_kset; struct netdev_rx_queue *_rx; /* Number of RX queues allocated at alloc_netdev_mq() time */ unsigned int num_rx_queues; +#endif struct netdev_queue rx_queue; -- cgit v1.2.2 From 5a7aadfe2fcb0f69e2acc1fbefe22a096e792fc9 Mon Sep 17 00:00:00 2001 From: Matt Helsley Date: Fri, 26 Mar 2010 23:51:44 +0100 Subject: Freezer: Fix buggy resume test for tasks frozen with cgroup freezer When the cgroup freezer is used to freeze tasks we do not want to thaw those tasks during resume. Currently we test the cgroup freezer state of the resuming tasks to see if the cgroup is FROZEN. If so then we don't thaw the task. However, the FREEZING state also indicates that the task should remain frozen. This also avoids a problem pointed out by Oren Ladaan: the freezer state transition from FREEZING to FROZEN is updated lazily when userspace reads or writes the freezer.state file in the cgroup filesystem. This means that resume will thaw tasks in cgroups which should be in the FROZEN state if there is no read/write of the freezer.state file to trigger this transition before suspend. NOTE: Another "simple" solution would be to always update the cgroup freezer state during resume. However it's a bad choice for several reasons: Updating the cgroup freezer state is somewhat expensive because it requires walking all the tasks in the cgroup and checking if they are each frozen. Worse, this could easily make resume run in N^2 time where N is the number of tasks in the cgroup. Finally, updating the freezer state from this code path requires trickier locking because of the way locks must be ordered. Instead of updating the freezer state we rely on the fact that lazy updates only manage the transition from FREEZING to FROZEN. We know that a cgroup with the FREEZING state may actually be FROZEN so test for that state too. This makes sense in the resume path even for partially-frozen cgroups -- those that really are FREEZING but not FROZEN. Reported-by: Oren Ladaan Signed-off-by: Matt Helsley Cc: stable@kernel.org Signed-off-by: Rafael J. Wysocki --- include/linux/freezer.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 5a361f85cfec..da7e52b099f3 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -64,9 +64,12 @@ extern bool freeze_task(struct task_struct *p, bool sig_only); extern void cancel_freezing(struct task_struct *p); #ifdef CONFIG_CGROUP_FREEZER -extern int cgroup_frozen(struct task_struct *task); +extern int cgroup_freezing_or_frozen(struct task_struct *task); #else /* !CONFIG_CGROUP_FREEZER */ -static inline int cgroup_frozen(struct task_struct *task) { return 0; } +static inline int cgroup_freezing_or_frozen(struct task_struct *task) +{ + return 0; +} #endif /* !CONFIG_CGROUP_FREEZER */ /* -- cgit v1.2.2 From 71c5c1595c04852d6fbf3c4882b47b30b61a4d32 Mon Sep 17 00:00:00 2001 From: Brandon L Black Date: Fri, 26 Mar 2010 16:18:03 +0000 Subject: net: Add MSG_WAITFORONE flag to recvmmsg Add new flag MSG_WAITFORONE for the recvmmsg() syscall. When this flag is specified for a blocking socket, recvmmsg() will only block until at least 1 packet is available. The default behavior is to block until all vlen packets are available. This flag has no effect on non-blocking sockets or when used in combination with MSG_DONTWAIT. Signed-off-by: Brandon L Black Acked-by: Ulrich Drepper Acked-by: Eric Dumazet Acked-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7b3aae2052a6..354cc5617f8b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -255,6 +255,7 @@ struct ucred { #define MSG_ERRQUEUE 0x2000 /* Fetch message from error queue */ #define MSG_NOSIGNAL 0x4000 /* Do not generate SIGPIPE */ #define MSG_MORE 0x8000 /* Sender will send more */ +#define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_EOF MSG_FIN -- cgit v1.2.2 From 0c0dbfecbf217b47d0b508afb59b8b3639582a4c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 27 Mar 2010 19:23:46 -0700 Subject: decnet: Remove unused FIB metric macros. Unlike the ipv4 side, these are completely unused. Signed-off-by: David S. Miller --- include/net/dn_fib.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index 52da6c3dd50d..bbcde3238e58 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -50,10 +50,6 @@ struct dn_fib_info { __le16 fib_prefsrc; __u32 fib_priority; __u32 fib_metrics[RTAX_MAX]; -#define dn_fib_mtu fib_metrics[RTAX_MTU-1] -#define dn_fib_window fib_metrics[RTAX_WINDOW-1] -#define dn_fib_rtt fib_metrics[RTAX_RTT-1] -#define dn_fib_advmss fib_metrics[RTAX_ADVMSS-1] int fib_nhs; int fib_power; struct dn_fib_nh fib_nh[0]; -- cgit v1.2.2 From 259354deaaf03d49a02dbb9975d6ec2a54675672 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 10 Mar 2010 18:56:10 +0900 Subject: module: encapsulate percpu handling better and record percpu_size Better encapsulate module static percpu area handling so that code outsidef of CONFIG_SMP ifdef doesn't deal with mod->percpu directly and add mod->percpu_size and record percpu_size in it. Both percpu fields are compiled out on UP. While at it, mark mod->percpu w/ __percpu. This is to prepare for is_module_percpu_address(). Signed-off-by: Tejun Heo Acked-by: Rusty Russell --- include/linux/module.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 5e869ffd34aa..87d247ac6761 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -330,8 +330,11 @@ struct module struct module_notes_attrs *notes_attrs; #endif +#ifdef CONFIG_SMP /* Per-cpu data. */ - void *percpu; + void __percpu *percpu; + unsigned int percpu_size; +#endif /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ -- cgit v1.2.2 From 10fad5e46f6c7bdfb01b1a012380a38e3c6ab346 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 10 Mar 2010 18:57:54 +0900 Subject: percpu, module: implement and use is_kernel/module_percpu_address() lockdep has custom code to check whether a pointer belongs to static percpu area which is somewhat broken. Implement proper is_kernel/module_percpu_address() and replace the custom code. On UP, percpu variables are regular static variables and can't be distinguished from them. Always return %false on UP. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Ingo Molnar --- include/linux/module.h | 1 + include/linux/percpu.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 87d247ac6761..f0e2659f4e3e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -395,6 +395,7 @@ static inline int module_is_live(struct module *mod) struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); +bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); static inline int within_module_core(unsigned long addr, struct module *mod) diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a93e5bfdccb8..11d5f834b54a 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -137,6 +137,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); extern void __percpu *__alloc_percpu(size_t size, size_t align); extern void free_percpu(void __percpu *__pdata); +extern bool is_kernel_percpu_address(unsigned long addr); extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA @@ -163,6 +164,12 @@ static inline void free_percpu(void __percpu *p) kfree(p); } +/* can't distinguish from other static vars, always false */ +static inline bool is_kernel_percpu_address(unsigned long addr) +{ + return false; +} + static inline phys_addr_t per_cpu_ptr_to_phys(void *addr) { return __pa(addr); -- cgit v1.2.2 From a53f4f9efaeb1d87cfae066346979d4d70e1abe9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 29 Mar 2010 13:08:52 +0100 Subject: SLOW_WORK: CONFIG_SLOW_WORK_PROC should be CONFIG_SLOW_WORK_DEBUG CONFIG_SLOW_WORK_PROC was changed to CONFIG_SLOW_WORK_DEBUG, but not in all instances. Change the remaining instances. This makes the debugfs file display the time mark and the owner's description again. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/fscache-cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 7be0c6fbe880..c57db27ac861 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -105,7 +105,7 @@ struct fscache_operation { /* operation releaser */ fscache_operation_release_t release; -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG const char *name; /* operation name */ const char *state; /* operation state */ #define fscache_set_op_name(OP, N) do { (OP)->name = (N); } while(0) -- cgit v1.2.2 From c36207a4624f15020f2918324405c1c88a5d4cbc Mon Sep 17 00:00:00 2001 From: viresh kumar Date: Mon, 29 Mar 2010 05:28:32 +0100 Subject: ARM: 5999/1: Including device.h and resource.h header files in linux/amba/bus.h linux/amba/bus.h have dependencies on linux/device.h and linux/resource.h, but it doesn't include them. We get compilation errors in our files which include bus.h but doesn't include device.h and resource.h. This patch includes device.h and resource.h in linux/amba/bus.h file. Signed-off-by: Viresh Kumar Acked-by: Linux Walleij Signed-off-by: Russell King --- include/linux/amba/bus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6816be6c3f77..8b1038607831 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -14,6 +14,9 @@ #ifndef ASMARM_AMBA_H #define ASMARM_AMBA_H +#include +#include + #define AMBA_NR_IRQS 2 struct amba_device { -- cgit v1.2.2 From 367d6acceaacff1adc44f121543effb9c060e575 Mon Sep 17 00:00:00 2001 From: viresh kumar Date: Mon, 29 Mar 2010 05:29:56 +0100 Subject: ARM: 6003/1: removing compilation warning from pl061.h pl061.h is using u8 type. including in pl061.h to avoid warning. Signed-off-by: Viresh Kumar Acked-by: Baruch Siach Signed-off-by: Russell King --- include/linux/amba/pl061.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/amba/pl061.h b/include/linux/amba/pl061.h index b4fbd9862606..5ddd9ad4b19c 100644 --- a/include/linux/amba/pl061.h +++ b/include/linux/amba/pl061.h @@ -1,3 +1,5 @@ +#include + /* platform data for the PL061 GPIO driver */ struct pl061_platform_data { -- cgit v1.2.2 From de329820e920cd9cfbc2127cad26a37026260cce Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 Mar 2010 14:30:19 -0700 Subject: ext3: fix broken handling of EXT3_STATE_NEW In commit 9df93939b735 ("ext3: Use bitops to read/modify EXT3_I(inode)->i_state") ext3 changed its internal 'i_state' variable to use bitops for its state handling. However, unline the same ext4 change, it didn't actually change the name of the field when it changed the semantics of it. As a result, an old use of 'i_state' remained in fs/ext3/ialloc.c that initialized the field to EXT3_STATE_NEW. And that does not work _at_all_ when we're now working with individually named bits rather than values that get masked. So the code tried to mark the state to be new, but in actual fact set the field to EXT3_STATE_JDATA. Which makes no sense at all, and screws up all the code that checks whether the inode was newly allocated. In particular, it made the xattr code unhappy, and caused various random behavior, like apparently https://bugzilla.redhat.com/show_bug.cgi?id=577911 So fix the initialization, and rename the field to match ext4 so that we don't have this happen again. Cc: James Morris Cc: Stephen Smalley Cc: Daniel J Walsh Cc: Eric Paris Cc: Jan Kara Signed-off-by: Linus Torvalds --- include/linux/ext3_fs.h | 6 +++--- include/linux/ext3_fs_i.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index cac84b006667..5f494b465097 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -565,17 +565,17 @@ enum { static inline int ext3_test_inode_state(struct inode *inode, int bit) { - return test_bit(bit, &EXT3_I(inode)->i_state); + return test_bit(bit, &EXT3_I(inode)->i_state_flags); } static inline void ext3_set_inode_state(struct inode *inode, int bit) { - set_bit(bit, &EXT3_I(inode)->i_state); + set_bit(bit, &EXT3_I(inode)->i_state_flags); } static inline void ext3_clear_inode_state(struct inode *inode, int bit) { - clear_bit(bit, &EXT3_I(inode)->i_state); + clear_bit(bit, &EXT3_I(inode)->i_state_flags); } #else /* Assume that user mode programs are passing in an ext3fs superblock, not diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h index 7679acdb519a..f42c098aed8d 100644 --- a/include/linux/ext3_fs_i.h +++ b/include/linux/ext3_fs_i.h @@ -87,7 +87,7 @@ struct ext3_inode_info { * near to their parent directory's inode. */ __u32 i_block_group; - unsigned long i_state; /* Dynamic state flags for ext3 */ + unsigned long i_state_flags; /* Dynamic state flags for ext3 */ /* block reservation info */ struct ext3_block_alloc_info *i_block_alloc_info; -- cgit v1.2.2 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- include/drm/drmP.h | 1 + include/linux/delayacct.h | 1 + include/linux/fsnotify.h | 1 + include/linux/gameport.h | 1 + include/linux/io-mapping.h | 1 + include/linux/jbd.h | 1 + include/linux/jbd2.h | 1 + include/linux/security.h | 2 +- include/linux/spi/spi.h | 1 + include/linux/taskstats_kern.h | 1 + include/linux/usb/gadget.h | 2 ++ include/linux/wimax/debug.h | 1 + include/net/ax25.h | 1 + include/net/fib_rules.h | 1 + include/net/ipx.h | 1 + include/net/iucv/iucv.h | 1 + include/net/netfilter/nf_conntrack_extend.h | 2 ++ include/net/netlabel.h | 1 + include/net/netrom.h | 1 + include/net/sock.h | 1 + include/net/x25.h | 1 + include/net/xfrm.h | 1 + include/scsi/libsas.h | 1 + include/xen/xenbus.h | 1 + 24 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 4a3c4e441027..cca2845bca55 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -55,6 +55,7 @@ #include #include #include +#include #if defined(__alpha__) || defined(__powerpc__) #include /* For pte_wrprotect */ #endif diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 5076fe0c8a96..6cee17c22313 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -18,6 +18,7 @@ #define _LINUX_DELAYACCT_H #include +#include /* * Per-task flags relevant to delay accounting diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index df8fd9a3b214..01755909ce81 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -15,6 +15,7 @@ #include #include #include +#include /* * fsnotify_d_instantiate - instantiate a dentry for inode diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 48e68da097f6..361d1cc288d0 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -16,6 +16,7 @@ #include #include #include +#include struct gameport { diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 97eb928b4924..25085ddd955f 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -19,6 +19,7 @@ #define _LINUX_IO_MAPPING_H #include +#include #include #include #include diff --git a/include/linux/jbd.h b/include/linux/jbd.h index f3aa59cb675d..516a2a27e87a 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -31,6 +31,7 @@ #include #include #include +#include #define journal_oom_retry 1 diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1ec876358180..a4d2e9f7088a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -30,6 +30,7 @@ #include #include #include +#include #endif #define journal_oom_retry 1 diff --git a/include/linux/security.h b/include/linux/security.h index 233d20b52c1b..3158dd982d27 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include /* Maximum number of letters for an LSM name string */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 97b60b37f445..af56071b06f9 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -21,6 +21,7 @@ #include #include +#include /* * INTERFACES between SPI master-side drivers and SPI infrastructure. diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index b6523c1427ce..58de6edf751f 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -9,6 +9,7 @@ #include #include +#include #ifdef CONFIG_TASKSTATS extern struct kmem_cache *taskstats_cache; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index bbf45d500b6d..f4b7ca516cdd 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -15,6 +15,8 @@ #ifndef __LINUX_USB_GADGET_H #define __LINUX_USB_GADGET_H +#include + struct usb_ep; /** diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index db8096e88533..57031b4d12f2 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -155,6 +155,7 @@ #include #include +#include /* Backend stuff */ diff --git a/include/net/ax25.h b/include/net/ax25.h index 717e2192d521..206d22297ac3 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #define AX25_T1CLAMPLO 1 diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index c07ac9650ebc..c49086d2bc7d 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -2,6 +2,7 @@ #define __NET_FIB_RULES_H #include +#include #include #include #include diff --git a/include/net/ipx.h b/include/net/ipx.h index a14121dd1932..ef51a668ba19 100644 --- a/include/net/ipx.h +++ b/include/net/ipx.h @@ -13,6 +13,7 @@ #include #include #include +#include struct ipx_address { __be32 net; diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 5e310c8d8e2f..205a3360156e 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -28,6 +28,7 @@ */ #include +#include #include /* diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 2d2a1f9a61d8..32d15bd6efa3 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -1,6 +1,8 @@ #ifndef _NF_CONNTRACK_EXTEND_H #define _NF_CONNTRACK_EXTEND_H +#include + #include enum nf_ct_ext_id { diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 60ebbc1fef46..9db401a8b4d9 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -31,6 +31,7 @@ #define _NETLABEL_H #include +#include #include #include #include diff --git a/include/net/netrom.h b/include/net/netrom.h index ab170a60e7d3..f0793c1cb5f8 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -9,6 +9,7 @@ #include #include +#include #include #define NR_NETWORK_LEN 15 diff --git a/include/net/sock.h b/include/net/sock.h index 092b0551e77f..b4603cd54fcd 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -51,6 +51,7 @@ #include /* struct sk_buff */ #include #include +#include #include #include diff --git a/include/net/x25.h b/include/net/x25.h index 9baa07dc7d17..15ef9624ab75 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -10,6 +10,7 @@ #ifndef _X25_H #define _X25_H #include +#include #include #define X25_ADDR_LEN 16 diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d74e080ba6c9..ac52f33f3e4a 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 9eaa3f05f954..3b586859669c 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -36,6 +36,7 @@ #include #include #include +#include struct block_device; diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b9763badbd77..43e2d7d33976 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.2 From de380b55f92986c1a84198149cb71b7228d15fbd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:06:43 +0900 Subject: percpu: don't implicitly include slab.h from percpu.h percpu.h has always been including slab.h to get k[mz]alloc/free() for UP inline implementation. percpu.h being used by very low level headers including module.h and sched.h, this meant that a lot files unintentionally got slab.h inclusion. Lee Schermerhorn was trying to make topology.h use percpu.h and got bitten by this implicit inclusion. The right thing to do is break this ultimately unnecessary dependency. The previous patch added explicit inclusion of either gfp.h or slab.h to the source files using them. This patch updates percpu.h such that slab.h is no longer included from percpu.h. Signed-off-by: Tejun Heo Reviewed-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- include/linux/percpu.h | 30 +++++------------------------- 1 file changed, 5 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a93e5bfdccb8..c7845130bfdf 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -2,10 +2,10 @@ #define __LINUX_PERCPU_H #include -#include /* For kmalloc() */ #include #include #include +#include #include @@ -135,9 +135,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, #define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))) extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); -extern void __percpu *__alloc_percpu(size_t size, size_t align); -extern void free_percpu(void __percpu *__pdata); -extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA extern void __init setup_per_cpu_areas(void); @@ -147,27 +144,6 @@ extern void __init setup_per_cpu_areas(void); #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) -static inline void __percpu *__alloc_percpu(size_t size, size_t align) -{ - /* - * Can't easily make larger alignment work with kmalloc. WARN - * on it. Larger alignment should only be used for module - * percpu sections on SMP for which this path isn't used. - */ - WARN_ON_ONCE(align > SMP_CACHE_BYTES); - return kzalloc(size, GFP_KERNEL); -} - -static inline void free_percpu(void __percpu *p) -{ - kfree(p); -} - -static inline phys_addr_t per_cpu_ptr_to_phys(void *addr) -{ - return __pa(addr); -} - static inline void __init setup_per_cpu_areas(void) { } static inline void *pcpu_lpage_remapped(void *kaddr) @@ -177,6 +153,10 @@ static inline void *pcpu_lpage_remapped(void *kaddr) #endif /* CONFIG_SMP */ +extern void __percpu *__alloc_percpu(size_t size, size_t align); +extern void free_percpu(void __percpu *__pdata); +extern phys_addr_t per_cpu_ptr_to_phys(void *addr); + #define alloc_percpu(type) \ (typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type)) -- cgit v1.2.2 From 70596b612c04694806a31dd389bd796c035085fa Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Tue, 30 Mar 2010 13:56:19 +0000 Subject: net-caif: add CAIF protocol definitions Add CAIF definitions to existing header files. Files: if_arp.h, if_ether.h, socket.h. Types: ARPHRD_CAIF, ETH_P_CAIF, AF_CAIF, PF_CAIF, SOL_CAIF, N_CAIF Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/linux/if_arp.h | 1 + include/linux/if_ether.h | 1 + include/linux/socket.h | 5 ++++- 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index e80b7f88f7c6..6d722f41ee7c 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -90,6 +90,7 @@ #define ARPHRD_PHONET 820 /* PhoNet media type */ #define ARPHRD_PHONET_PIPE 821 /* PhoNet pipe header */ +#define ARPHRD_CAIF 822 /* CAIF media type */ #define ARPHRD_VOID 0xFFFF /* Void type, nothing is known */ #define ARPHRD_NONE 0xFFFE /* zero header length */ diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 299b4121f914..bed7a4682b90 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -109,6 +109,7 @@ #define ETH_P_TRAILER 0x001C /* Trailer switch tagging */ #define ETH_P_PHONET 0x00F5 /* Nokia Phonet frames */ #define ETH_P_IEEE802154 0x00F6 /* IEEE802.15.4 frame */ +#define ETH_P_CAIF 0x00F7 /* ST-Ericsson CAIF protocol */ /* * This is an Ethernet frame header. diff --git a/include/linux/socket.h b/include/linux/socket.h index 7b3aae2052a6..960659bd8f78 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -189,7 +189,8 @@ struct ucred { #define AF_ISDN 34 /* mISDN sockets */ #define AF_PHONET 35 /* Phonet sockets */ #define AF_IEEE802154 36 /* IEEE802154 sockets */ -#define AF_MAX 37 /* For now.. */ +#define AF_CAIF 37 /* CAIF sockets */ +#define AF_MAX 38 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -229,6 +230,7 @@ struct ucred { #define PF_ISDN AF_ISDN #define PF_PHONET AF_PHONET #define PF_IEEE802154 AF_IEEE802154 +#define PF_CAIF AF_CAIF #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -300,6 +302,7 @@ struct ucred { #define SOL_PNPIPE 275 #define SOL_RDS 276 #define SOL_IUCV 277 +#define SOL_CAIF 278 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.2 From f671c54207d8a47129f35a84569fdfda614d2439 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Tue, 30 Mar 2010 13:56:20 +0000 Subject: net-caif: add CAIF socket and configuration headers Add CAIF types for Socket Address, Socket Options, and configuration parameters for the GPRS IP network interface. Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/linux/caif/caif_socket.h | 164 +++++++++++++++++++++++++++++++++++++++ include/linux/caif/if_caif.h | 34 ++++++++ 2 files changed, 198 insertions(+) create mode 100644 include/linux/caif/caif_socket.h create mode 100644 include/linux/caif/if_caif.h (limited to 'include') diff --git a/include/linux/caif/caif_socket.h b/include/linux/caif/caif_socket.h new file mode 100644 index 000000000000..8e5c8444a3f4 --- /dev/null +++ b/include/linux/caif/caif_socket.h @@ -0,0 +1,164 @@ +/* linux/caif_socket.h + * CAIF Definitions for CAIF socket and network layer + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef _LINUX_CAIF_SOCKET_H +#define _LINUX_CAIF_SOCKET_H + +#include + +#ifdef __KERNEL__ +#include +#else +#include +#endif + + +/** + * enum caif_link_selector - Physical Link Selection. + * @CAIF_LINK_HIGH_BANDW: Physical interface for high-bandwidth + * traffic. + * @CAIF_LINK_LOW_LATENCY: Physical interface for low-latency + * traffic. + * + * CAIF Link Layers can register their link properties. + * This enum is used for choosing between CAIF Link Layers when + * setting up CAIF Channels when multiple CAIF Link Layers exists. + */ +enum caif_link_selector { + CAIF_LINK_HIGH_BANDW, + CAIF_LINK_LOW_LATENCY +}; + +/** + * enum caif_channel_priority - CAIF channel priorities. + * + * @CAIF_PRIO_MIN: Min priority for a channel. + * @CAIF_PRIO_LOW: Low-priority channel. + * @CAIF_PRIO_NORMAL: Normal/default priority level. + * @CAIF_PRIO_HIGH: High priority level + * @CAIF_PRIO_MAX: Max priority for channel + * + * Priority can be set on CAIF Channels in order to + * prioritize between traffic on different CAIF Channels. + * These priority levels are recommended, but the priority value + * is not restricted to the values defined in this enum, any value + * between CAIF_PRIO_MIN and CAIF_PRIO_MAX could be used. + */ +enum caif_channel_priority { + CAIF_PRIO_MIN = 0x01, + CAIF_PRIO_LOW = 0x04, + CAIF_PRIO_NORMAL = 0x0f, + CAIF_PRIO_HIGH = 0x14, + CAIF_PRIO_MAX = 0x1F +}; + +/** + * enum caif_protocol_type - CAIF Channel type. + * @CAIFPROTO_AT: Classic AT channel. + * @CAIFPROTO_DATAGRAM: Datagram channel. + * @CAIFPROTO_DATAGRAM_LOOP: Datagram loopback channel, used for testing. + * @CAIFPROTO_UTIL: Utility (Psock) channel. + * @CAIFPROTO_RFM: Remote File Manager + * + * This enum defines the CAIF Channel type to be used. This defines + * the service to connect to on the modem. + */ +enum caif_protocol_type { + CAIFPROTO_AT, + CAIFPROTO_DATAGRAM, + CAIFPROTO_DATAGRAM_LOOP, + CAIFPROTO_UTIL, + CAIFPROTO_RFM, + _CAIFPROTO_MAX +}; +#define CAIFPROTO_MAX _CAIFPROTO_MAX + +/** + * enum caif_at_type - AT Service Endpoint + * @CAIF_ATTYPE_PLAIN: Connects to a plain vanilla AT channel. + */ +enum caif_at_type { + CAIF_ATTYPE_PLAIN = 2 +}; + +/** + * struct sockaddr_caif - the sockaddr structure for CAIF sockets. + * @u: Union of address data 'switched' by family. + * : + * @u.at: Applies when family = CAIFPROTO_AT. + * + * @u.at.type: Type of AT link to set up (enum caif_at_type). + * + * @u.util: Applies when family = CAIFPROTO_UTIL + * + * @u.util.service: Utility service name. + * + * @u.dgm: Applies when family = CAIFPROTO_DATAGRAM + * + * @u.dgm.connection_id: Datagram connection id. + * + * @u.dgm.nsapi: NSAPI of the PDP-Context. + * + * @u.rfm: Applies when family = CAIFPROTO_RFM + * + * @u.rfm.connection_id: Connection ID for RFM. + * + * @u.rfm.volume: Volume to mount. + * + * Description: + * This structure holds the connect parameters used for setting up a + * CAIF Channel. It defines the service to connect to on the modem. + */ +struct sockaddr_caif { + sa_family_t family; + union { + struct { + __u8 type; /* type: enum caif_at_type */ + } at; /* CAIFPROTO_AT */ + struct { + char service[16]; + } util; /* CAIFPROTO_UTIL */ + union { + __u32 connection_id; + __u8 nsapi; + } dgm; /* CAIFPROTO_DATAGRAM(_LOOP)*/ + struct { + __u32 connection_id; + char volume[16]; + } rfm; /* CAIFPROTO_RFM */ + } u; +}; + +/** + * enum caif_socket_opts - CAIF option values for getsockopt and setsockopt. + * + * @CAIFSO_LINK_SELECT: Selector used if multiple CAIF Link layers are + * available. Either a high bandwidth + * link can be selected (CAIF_LINK_HIGH_BANDW) or + * or a low latency link (CAIF_LINK_LOW_LATENCY). + * This option is of type __u32. + * Alternatively SO_BINDTODEVICE can be used. + * + * @CAIFSO_REQ_PARAM: Used to set the request parameters for a + * utility channel. (maximum 256 bytes). This + * option must be set before connecting. + * + * @CAIFSO_RSP_PARAM: Gets the response parameters for a utility + * channel. (maximum 256 bytes). This option + * is valid after a successful connect. + * + * + * This enum defines the CAIF Socket options to be used on a socket + * + */ +enum caif_socket_opts { + CAIFSO_LINK_SELECT = 127, + CAIFSO_REQ_PARAM = 128, + CAIFSO_RSP_PARAM = 129, +}; + +#endif /* _LINUX_CAIF_SOCKET_H */ diff --git a/include/linux/caif/if_caif.h b/include/linux/caif/if_caif.h new file mode 100644 index 000000000000..5e7eed4edf51 --- /dev/null +++ b/include/linux/caif/if_caif.h @@ -0,0 +1,34 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef IF_CAIF_H_ +#define IF_CAIF_H_ +#include +#include +#include + +/** + * enum ifla_caif - CAIF NetlinkRT parameters. + * @IFLA_CAIF_IPV4_CONNID: Connection ID for IPv4 PDP Context. + * The type of attribute is NLA_U32. + * @IFLA_CAIF_IPV6_CONNID: Connection ID for IPv6 PDP Context. + * The type of attribute is NLA_U32. + * @IFLA_CAIF_LOOPBACK: If different from zero, device is doing loopback + * The type of attribute is NLA_U8. + * + * When using RT Netlink to create, destroy or configure a CAIF IP interface, + * enum ifla_caif is used to specify the configuration attributes. + */ +enum ifla_caif { + __IFLA_CAIF_UNSPEC, + IFLA_CAIF_IPV4_CONNID, + IFLA_CAIF_IPV6_CONNID, + IFLA_CAIF_LOOPBACK, + __IFLA_CAIF_MAX +}; +#define IFLA_CAIF_MAX (__IFLA_CAIF_MAX-1) + +#endif /*IF_CAIF_H_*/ -- cgit v1.2.2 From 09009f30de188c847d72039e6250bfea56a0f887 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Tue, 30 Mar 2010 13:56:21 +0000 Subject: net-caif: add CAIF core protocol stack header files Add include files for the CAIF Core protocol stack. caif_layer.h - Defines the structure of the CAIF protocol layers cfcnfg.h - CAIF Configuration Module for services and link layers cfctrl.h - CAIF Control Protocol Layer cffrml.h - CAIF Framing Layer cfmuxl.h - CAIF Muxing Layer cfpkt.h - CAIF Packet layer (skb helper functions) cfserl.h - CAIF Serial Layer cfsrvl.h - CAIF Service Layer Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/caif_layer.h | 283 ++++++++++++++++++++++++++++++++++++++++++ include/net/caif/cfcnfg.h | 133 ++++++++++++++++++++ include/net/caif/cfctrl.h | 138 ++++++++++++++++++++ include/net/caif/cffrml.h | 16 +++ include/net/caif/cfmuxl.h | 22 ++++ include/net/caif/cfpkt.h | 274 ++++++++++++++++++++++++++++++++++++++++ include/net/caif/cfserl.h | 12 ++ include/net/caif/cfsrvl.h | 34 +++++ 8 files changed, 912 insertions(+) create mode 100644 include/net/caif/caif_layer.h create mode 100644 include/net/caif/cfcnfg.h create mode 100644 include/net/caif/cfctrl.h create mode 100644 include/net/caif/cffrml.h create mode 100644 include/net/caif/cfmuxl.h create mode 100644 include/net/caif/cfpkt.h create mode 100644 include/net/caif/cfserl.h create mode 100644 include/net/caif/cfsrvl.h (limited to 'include') diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h new file mode 100644 index 000000000000..25c472f0e5b8 --- /dev/null +++ b/include/net/caif/caif_layer.h @@ -0,0 +1,283 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland / sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CAIF_LAYER_H_ +#define CAIF_LAYER_H_ + +#include + +struct cflayer; +struct cfpkt; +struct cfpktq; +struct caif_payload_info; +struct caif_packet_funcs; + +#define CAIF_MAX_FRAMESIZE 4096 +#define CAIF_MAX_PAYLOAD_SIZE (4096 - 64) +#define CAIF_NEEDED_HEADROOM (10) +#define CAIF_NEEDED_TAILROOM (2) + +#define CAIF_LAYER_NAME_SZ 16 +#define CAIF_SUCCESS 1 +#define CAIF_FAILURE 0 + +/** + * caif_assert() - Assert function for CAIF. + * @assert: expression to evaluate. + * + * This function will print a error message and a do WARN_ON if the + * assertion failes. Normally this will do a stack up at the current location. + */ +#define caif_assert(assert) \ +do { \ + if (!(assert)) { \ + pr_err("caif:Assert detected:'%s'\n", #assert); \ + WARN_ON(!(assert)); \ + } \ +} while (0) + + +/** + * enum caif_ctrlcmd - CAIF Stack Control Signaling sent in layer.ctrlcmd(). + * + * @CAIF_CTRLCMD_FLOW_OFF_IND: Flow Control is OFF, transmit function + * should stop sending data + * + * @CAIF_CTRLCMD_FLOW_ON_IND: Flow Control is ON, transmit function + * can start sending data + * + * @CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND: Remote end modem has decided to close + * down channel + * + * @CAIF_CTRLCMD_INIT_RSP: Called initially when the layer below + * has finished initialization + * + * @CAIF_CTRLCMD_DEINIT_RSP: Called when de-initialization is + * complete + * + * @CAIF_CTRLCMD_INIT_FAIL_RSP: Called if initialization fails + * + * @_CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND: CAIF Link layer temporarily cannot + * send more packets. + * @_CAIF_CTRLCMD_PHYIF_FLOW_ON_IND: Called if CAIF Link layer is able + * to send packets again. + * @_CAIF_CTRLCMD_PHYIF_DOWN_IND: Called if CAIF Link layer is going + * down. + * + * These commands are sent upwards in the CAIF stack to the CAIF Client. + * They are used for signaling originating from the modem or CAIF Link Layer. + * These are either responses (*_RSP) or events (*_IND). + */ +enum caif_ctrlcmd { + CAIF_CTRLCMD_FLOW_OFF_IND, + CAIF_CTRLCMD_FLOW_ON_IND, + CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND, + CAIF_CTRLCMD_INIT_RSP, + CAIF_CTRLCMD_DEINIT_RSP, + CAIF_CTRLCMD_INIT_FAIL_RSP, + _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, + _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND, + _CAIF_CTRLCMD_PHYIF_DOWN_IND, +}; + +/** + * enum caif_modemcmd - Modem Control Signaling, sent from CAIF Client + * to the CAIF Link Layer or modem. + * + * @CAIF_MODEMCMD_FLOW_ON_REQ: Flow Control is ON, transmit function + * can start sending data. + * + * @CAIF_MODEMCMD_FLOW_OFF_REQ: Flow Control is OFF, transmit function + * should stop sending data. + * + * @_CAIF_MODEMCMD_PHYIF_USEFULL: Notify physical layer that it is in use + * + * @_CAIF_MODEMCMD_PHYIF_USELESS: Notify physical layer that it is + * no longer in use. + * + * These are requests sent 'downwards' in the stack. + * Flow ON, OFF can be indicated to the modem. + */ +enum caif_modemcmd { + CAIF_MODEMCMD_FLOW_ON_REQ = 0, + CAIF_MODEMCMD_FLOW_OFF_REQ = 1, + _CAIF_MODEMCMD_PHYIF_USEFULL = 3, + _CAIF_MODEMCMD_PHYIF_USELESS = 4 +}; + +/** + * enum caif_direction - CAIF Packet Direction. + * Indicate if a packet is to be sent out or to be received in. + * @CAIF_DIR_IN: Incoming packet received. + * @CAIF_DIR_OUT: Outgoing packet to be transmitted. + */ +enum caif_direction { + CAIF_DIR_IN = 0, + CAIF_DIR_OUT = 1 +}; + +/** + * struct cflayer - CAIF Stack layer. + * Defines the framework for the CAIF Core Stack. + * @up: Pointer up to the layer above. + * @dn: Pointer down to the layer below. + * @node: List node used when layer participate in a list. + * @receive: Packet receive function. + * @transmit: Packet transmit funciton. + * @ctrlcmd: Used for control signalling upwards in the stack. + * @modemcmd: Used for control signaling downwards in the stack. + * @prio: Priority of this layer. + * @id: The identity of this layer + * @type: The type of this layer + * @name: Name of the layer. + * + * This structure defines the layered structure in CAIF. + * + * It defines CAIF layering structure, used by all CAIF Layers and the + * layers interfacing CAIF. + * + * In order to integrate with CAIF an adaptation layer on top of the CAIF stack + * and PHY layer below the CAIF stack + * must be implemented. These layer must follow the design principles below. + * + * Principles for layering of protocol layers: + * - All layers must use this structure. If embedding it, then place this + * structure first in the layer specific structure. + * + * - Each layer should not depend on any others layer private data. + * + * - In order to send data upwards do + * layer->up->receive(layer->up, packet); + * + * - In order to send data downwards do + * layer->dn->transmit(layer->dn, info, packet); + */ +struct cflayer { + struct cflayer *up; + struct cflayer *dn; + struct list_head node; + + /* + * receive() - Receive Function. + * Contract: Each layer must implement a receive function passing the + * CAIF packets upwards in the stack. + * Packet handling rules: + * - The CAIF packet (cfpkt) cannot be accessed after + * passing it to the next layer using up->receive(). + * - If parsing of the packet fails, the packet must be + * destroyed and -1 returned from the function. + * - If parsing succeeds (and above layers return OK) then + * the function must return a value > 0. + * + * Returns result < 0 indicates an error, 0 or positive value + * indicates success. + * + * @layr: Pointer to the current layer the receive function is + * implemented for (this pointer). + * @cfpkt: Pointer to CaifPacket to be handled. + */ + int (*receive)(struct cflayer *layr, struct cfpkt *cfpkt); + + /* + * transmit() - Transmit Function. + * Contract: Each layer must implement a transmit function passing the + * CAIF packet downwards in the stack. + * Packet handling rules: + * - The CAIF packet (cfpkt) ownership is passed to the + * transmit function. This means that the the packet + * cannot be accessed after passing it to the below + * layer using dn->transmit(). + * + * - If transmit fails, however, the ownership is returned + * to thecaller. The caller of "dn->transmit()" must + * destroy or resend packet. + * + * - Return value less than zero means error, zero or + * greater than zero means OK. + * + * result < 0 indicates an error, 0 or positive value + * indicate success. + * + * @layr: Pointer to the current layer the receive function + * isimplemented for (this pointer). + * @cfpkt: Pointer to CaifPacket to be handled. + */ + int (*transmit) (struct cflayer *layr, struct cfpkt *cfpkt); + + /* + * cttrlcmd() - Control Function upwards in CAIF Stack. + * Used for signaling responses (CAIF_CTRLCMD_*_RSP) + * and asynchronous events from the modem (CAIF_CTRLCMD_*_IND) + * + * @layr: Pointer to the current layer the receive function + * is implemented for (this pointer). + * @ctrl: Control Command. + */ + void (*ctrlcmd) (struct cflayer *layr, enum caif_ctrlcmd ctrl, + int phyid); + + /* + * modemctrl() - Control Function used for controlling the modem. + * Used to signal down-wards in the CAIF stack. + * Returns 0 on success, < 0 upon failure. + * + * @layr: Pointer to the current layer the receive function + * is implemented for (this pointer). + * @ctrl: Control Command. + */ + int (*modemcmd) (struct cflayer *layr, enum caif_modemcmd ctrl); + + unsigned short prio; + unsigned int id; + unsigned int type; + char name[CAIF_LAYER_NAME_SZ]; +}; + +/** + * layer_set_up() - Set the up pointer for a specified layer. + * @layr: Layer where up pointer shall be set. + * @above: Layer above. + */ +#define layer_set_up(layr, above) ((layr)->up = (struct cflayer *)(above)) + +/** + * layer_set_dn() - Set the down pointer for a specified layer. + * @layr: Layer where down pointer shall be set. + * @below: Layer below. + */ +#define layer_set_dn(layr, below) ((layr)->dn = (struct cflayer *)(below)) + +/** + * struct dev_info - Physical Device info information about physical layer. + * @dev: Pointer to native physical device. + * @id: Physical ID of the physical connection used by the + * logical CAIF connection. Used by service layers to + * identify their physical id to Caif MUX (CFMUXL)so + * that the MUX can add the correct physical ID to the + * packet. + */ +struct dev_info { + void *dev; + unsigned int id; +}; + +/** + * struct caif_payload_info - Payload information embedded in packet (sk_buff). + * + * @dev_info: Information about the receiving device. + * + * @hdr_len: Header length, used to align pay load on 32bit boundary. + * + * @channel_id: Channel ID of the logical CAIF connection. + * Used by mux to insert channel id into the caif packet. + */ +struct caif_payload_info { + struct dev_info *dev_info; + unsigned short hdr_len; + unsigned short channel_id; +}; + +#endif /* CAIF_LAYER_H_ */ diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h new file mode 100644 index 000000000000..366082c5d435 --- /dev/null +++ b/include/net/caif/cfcnfg.h @@ -0,0 +1,133 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFCNFG_H_ +#define CFCNFG_H_ +#include +#include +#include + +struct cfcnfg; + +/** + * enum cfcnfg_phy_type - Types of physical layers defined in CAIF Stack + * + * @CFPHYTYPE_FRAG: Fragmented frames physical interface. + * @CFPHYTYPE_CAIF: Generic CAIF physical interface + */ +enum cfcnfg_phy_type { + CFPHYTYPE_FRAG = 1, + CFPHYTYPE_CAIF, + CFPHYTYPE_MAX +}; + +/** + * enum cfcnfg_phy_preference - Physical preference HW Abstraction + * + * @CFPHYPREF_UNSPECIFIED: Default physical interface + * + * @CFPHYPREF_LOW_LAT: Default physical interface for low-latency + * traffic + * @CFPHYPREF_HIGH_BW: Default physical interface for high-bandwidth + * traffic + * @CFPHYPREF_LOOP: TEST only Loopback interface simulating modem + * responses. + * + */ +enum cfcnfg_phy_preference { + CFPHYPREF_UNSPECIFIED, + CFPHYPREF_LOW_LAT, + CFPHYPREF_HIGH_BW, + CFPHYPREF_LOOP +}; + +/** + * cfcnfg_create() - Create the CAIF configuration object. + */ +struct cfcnfg *cfcnfg_create(void); + +/** + * cfcnfg_remove() - Remove the CFCNFG object + * @cfg: config object + */ +void cfcnfg_remove(struct cfcnfg *cfg); + +/** + * cfcnfg_add_phy_layer() - Adds a physical layer to the CAIF stack. + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @phy_type: Specifies the type of physical interface, e.g. + * CFPHYTYPE_FRAG. + * @dev: Pointer to link layer device + * @phy_layer: Specify the physical layer. The transmit function + * MUST be set in the structure. + * @phyid: The assigned physical ID for this layer, used in + * cfcnfg_add_adapt_layer to specify PHY for the link. + * @pref: The phy (link layer) preference. + * @fcs: Specify if checksum is used in CAIF Framing Layer. + * @stx: Specify if Start Of Frame eXtention is used. + */ + +void +cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, + void *dev, struct cflayer *phy_layer, u16 *phyid, + enum cfcnfg_phy_preference pref, + bool fcs, bool stx); + +/** + * cfcnfg_del_phy_layer - Deletes an phy layer from the CAIF stack. + * + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @phy_layer: Adaptation layer to be removed. + */ +int cfcnfg_del_phy_layer(struct cfcnfg *cnfg, struct cflayer *phy_layer); + +/** + * cfcnfg_del_adapt_layer - Deletes an adaptation layer from the CAIF stack. + * + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @adap_layer: Adaptation layer to be removed. + */ +int cfcnfg_del_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer); + +/** + * cfcnfg_add_adaptation_layer - Add an adaptation layer to the CAIF stack. + * + * The adaptation Layer is where the interface to application or higher-level + * driver functionality is implemented. + * + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @param: Link setup parameters. + * @adap_layer: Specify the adaptation layer; the receive and + * flow-control functions MUST be set in the structure. + * + */ +int +cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, + struct cfctrl_link_param *param, + struct cflayer *adap_layer); + +/** + * cfcnfg_get_phyid() - Get physical ID, given type. + * Returns one of the physical interfaces matching the given type. + * Zero if no match is found. + * @cnfg: Configuration object + * @phy_pref: Caif Link Layer preference + */ +struct dev_info *cfcnfg_get_phyid(struct cfcnfg *cnfg, + enum cfcnfg_phy_preference phy_pref); + +/** + * cfcnfg_get_named() - Get the Physical Identifier of CAIF Link Layer + * @cnfg: Configuration object + * @name: Name of the Physical Layer (Caif Link Layer) + */ +int cfcnfg_get_named(struct cfcnfg *cnfg, char *name); + +#endif /* CFCNFG_H_ */ diff --git a/include/net/caif/cfctrl.h b/include/net/caif/cfctrl.h new file mode 100644 index 000000000000..dee25b86caa0 --- /dev/null +++ b/include/net/caif/cfctrl.h @@ -0,0 +1,138 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFCTRL_H_ +#define CFCTRL_H_ +#include +#include + +/* CAIF Control packet commands */ +enum cfctrl_cmd { + CFCTRL_CMD_LINK_SETUP = 0, + CFCTRL_CMD_LINK_DESTROY = 1, + CFCTRL_CMD_LINK_ERR = 2, + CFCTRL_CMD_ENUM = 3, + CFCTRL_CMD_SLEEP = 4, + CFCTRL_CMD_WAKE = 5, + CFCTRL_CMD_LINK_RECONF = 6, + CFCTRL_CMD_START_REASON = 7, + CFCTRL_CMD_RADIO_SET = 8, + CFCTRL_CMD_MODEM_SET = 9, + CFCTRL_CMD_MASK = 0xf +}; + +/* Channel types */ +enum cfctrl_srv { + CFCTRL_SRV_DECM = 0, + CFCTRL_SRV_VEI = 1, + CFCTRL_SRV_VIDEO = 2, + CFCTRL_SRV_DBG = 3, + CFCTRL_SRV_DATAGRAM = 4, + CFCTRL_SRV_RFM = 5, + CFCTRL_SRV_UTIL = 6, + CFCTRL_SRV_MASK = 0xf +}; + +#define CFCTRL_RSP_BIT 0x20 +#define CFCTRL_ERR_BIT 0x10 + +struct cfctrl_rsp { + void (*linksetup_rsp)(struct cflayer *layer, u8 linkid, + enum cfctrl_srv serv, u8 phyid, + struct cflayer *adapt_layer); + void (*linkdestroy_rsp)(struct cflayer *layer, u8 linkid, + struct cflayer *client_layer); + void (*linkerror_ind)(void); + void (*enum_rsp)(void); + void (*sleep_rsp)(void); + void (*wake_rsp)(void); + void (*restart_rsp)(void); + void (*radioset_rsp)(void); + void (*reject_rsp)(struct cflayer *layer, u8 linkid, + struct cflayer *client_layer);; +}; + +/* Link Setup Parameters for CAIF-Links. */ +struct cfctrl_link_param { + enum cfctrl_srv linktype;/* (T3,T0) Type of Channel */ + u8 priority; /* (P4,P0) Priority of the channel */ + u8 phyid; /* (U2-U0) Physical interface to connect */ + u8 endpoint; /* (E1,E0) Endpoint for data channels */ + u8 chtype; /* (H1,H0) Channel-Type, applies to + * VEI, DEBUG */ + union { + struct { + u8 connid; /* (D7,D0) Video LinkId */ + } video; + + struct { + u32 connid; /* (N31,Ngit0) Connection ID used + * for Datagram */ + } datagram; + + struct { + u32 connid; /* Connection ID used for RFM */ + char volume[20]; /* Volume to mount for RFM */ + } rfm; /* Configuration for RFM */ + + struct { + u16 fifosize_kb; /* Psock FIFO size in KB */ + u16 fifosize_bufs; /* Psock # signal buffers */ + char name[16]; /* Name of the PSOCK service */ + u8 params[255]; /* Link setup Parameters> */ + u16 paramlen; /* Length of Link Setup + * Parameters */ + } utility; /* Configuration for Utility Links (Psock) */ + } u; +}; + +/* This structure is used internally in CFCTRL */ +struct cfctrl_request_info { + int sequence_no; + enum cfctrl_cmd cmd; + u8 channel_id; + struct cfctrl_link_param param; + struct cfctrl_request_info *next; + struct cflayer *client_layer; +}; + +struct cfctrl { + struct cfsrvl serv; + struct cfctrl_rsp res; + atomic_t req_seq_no; + atomic_t rsp_seq_no; + struct cfctrl_request_info *first_req; + /* Protects from simultaneous access to first_req list */ + spinlock_t info_list_lock; +#ifndef CAIF_NO_LOOP + u8 loop_linkid; + int loop_linkused[256]; + /* Protects simultaneous access to loop_linkid and loop_linkused */ + spinlock_t loop_linkid_lock; +#endif + +}; + +void cfctrl_enum_req(struct cflayer *cfctrl, u8 physlinkid); +void cfctrl_linkup_request(struct cflayer *cfctrl, + struct cfctrl_link_param *param, + struct cflayer *user_layer); +int cfctrl_linkdown_req(struct cflayer *cfctrl, u8 linkid, + struct cflayer *client); +void cfctrl_sleep_req(struct cflayer *cfctrl); +void cfctrl_wake_req(struct cflayer *cfctrl); +void cfctrl_getstartreason_req(struct cflayer *cfctrl); +struct cflayer *cfctrl_create(void); +void cfctrl_set_dnlayer(struct cflayer *this, struct cflayer *dn); +void cfctrl_set_uplayer(struct cflayer *this, struct cflayer *up); +struct cfctrl_rsp *cfctrl_get_respfuncs(struct cflayer *layer); +bool cfctrl_req_eq(struct cfctrl_request_info *r1, + struct cfctrl_request_info *r2); +void cfctrl_insert_req(struct cfctrl *ctrl, + struct cfctrl_request_info *req); +struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, + struct cfctrl_request_info *req); +#endif /* CFCTRL_H_ */ diff --git a/include/net/caif/cffrml.h b/include/net/caif/cffrml.h new file mode 100644 index 000000000000..3f14d2e1ce61 --- /dev/null +++ b/include/net/caif/cffrml.h @@ -0,0 +1,16 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFFRML_H_ +#define CFFRML_H_ +#include + +struct cffrml; +struct cflayer *cffrml_create(u16 phyid, bool DoFCS); +void cffrml_set_uplayer(struct cflayer *this, struct cflayer *up); +void cffrml_set_dnlayer(struct cflayer *this, struct cflayer *dn); + +#endif /* CFFRML_H_ */ diff --git a/include/net/caif/cfmuxl.h b/include/net/caif/cfmuxl.h new file mode 100644 index 000000000000..4e1b4f33423e --- /dev/null +++ b/include/net/caif/cfmuxl.h @@ -0,0 +1,22 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFMUXL_H_ +#define CFMUXL_H_ +#include + +struct cfsrvl; +struct cffrml; + +struct cflayer *cfmuxl_create(void); +int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid); +struct cflayer *cfmuxl_remove_dnlayer(struct cflayer *layr, u8 phyid); +int cfmuxl_set_dnlayer(struct cflayer *layr, struct cflayer *up, u8 phyid); +struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 linkid); +bool cfmuxl_is_phy_inuse(struct cflayer *layr, u8 phyid); +u8 cfmuxl_get_phyid(struct cflayer *layr, u8 channel_id); + +#endif /* CFMUXL_H_ */ diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h new file mode 100644 index 000000000000..fbc681beff52 --- /dev/null +++ b/include/net/caif/cfpkt.h @@ -0,0 +1,274 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFPKT_H_ +#define CFPKT_H_ +#include +#include +struct cfpkt; + +/* Create a CAIF packet. + * len: Length of packet to be created + * @return New packet. + */ +struct cfpkt *cfpkt_create(u16 len); + +/* Create a CAIF packet. + * data Data to copy. + * len Length of packet to be created + * @return New packet. + */ +struct cfpkt *cfpkt_create_uplink(const unsigned char *data, unsigned int len); +/* + * Destroy a CAIF Packet. + * pkt Packet to be destoyed. + */ +void cfpkt_destroy(struct cfpkt *pkt); + +/* + * Extract header from packet. + * + * pkt Packet to extract header data from. + * data Pointer to copy the header data into. + * len Length of head data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len); + +/* + * Peek header from packet. + * Reads data from packet without changing packet. + * + * pkt Packet to extract header data from. + * data Pointer to copy the header data into. + * len Length of head data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_peek_head(struct cfpkt *pkt, void *data, u16 len); + +/* + * Extract header from trailer (end of packet). + * + * pkt Packet to extract header data from. + * data Pointer to copy the trailer data into. + * len Length of header data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_extr_trail(struct cfpkt *pkt, void *data, u16 len); + +/* + * Add header to packet. + * + * + * pkt Packet to add header data to. + * data Pointer to data to copy into the header. + * len Length of header data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_add_head(struct cfpkt *pkt, const void *data, u16 len); + +/* + * Add trailer to packet. + * + * + * pkt Packet to add trailer data to. + * data Pointer to data to copy into the trailer. + * len Length of trailer data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_add_trail(struct cfpkt *pkt, const void *data, u16 len); + +/* + * Pad trailer on packet. + * Moves data pointer in packet, no content copied. + * + * pkt Packet in which to pad trailer. + * len Length of padding to add. + * @return zero on success and error code upon failure + */ +int cfpkt_pad_trail(struct cfpkt *pkt, u16 len); + +/* + * Add a single byte to packet body (tail). + * + * pkt Packet in which to add byte. + * data Byte to add. + * @return zero on success and error code upon failure + */ +int cfpkt_addbdy(struct cfpkt *pkt, const u8 data); + +/* + * Add a data to packet body (tail). + * + * pkt Packet in which to add data. + * data Pointer to data to copy into the packet body. + * len Length of data to add. + * @return zero on success and error code upon failure + */ +int cfpkt_add_body(struct cfpkt *pkt, const void *data, u16 len); + +/* + * Checks whether there are more data to process in packet. + * pkt Packet to check. + * @return true if more data are available in packet false otherwise + */ +bool cfpkt_more(struct cfpkt *pkt); + +/* + * Checks whether the packet is erroneous, + * i.e. if it has been attempted to extract more data than available in packet + * or writing more data than has been allocated in cfpkt_create(). + * pkt Packet to check. + * @return true on error false otherwise + */ +bool cfpkt_erroneous(struct cfpkt *pkt); + +/* + * Get the packet length. + * pkt Packet to get length from. + * @return Number of bytes in packet. + */ +u16 cfpkt_getlen(struct cfpkt *pkt); + +/* + * Set the packet length, by adjusting the trailer pointer according to length. + * pkt Packet to set length. + * len Packet length. + * @return Number of bytes in packet. + */ +int cfpkt_setlen(struct cfpkt *pkt, u16 len); + +/* + * cfpkt_append - Appends a packet's data to another packet. + * dstpkt: Packet to append data into, WILL BE FREED BY THIS FUNCTION + * addpkt: Packet to be appended and automatically released, + * WILL BE FREED BY THIS FUNCTION. + * expectlen: Packet's expected total length. This should be considered + * as a hint. + * NB: Input packets will be destroyed after appending and cannot be used + * after calling this function. + * @return The new appended packet. + */ +struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, struct cfpkt *addpkt, + u16 expectlen); + +/* + * cfpkt_split - Split a packet into two packets at the specified split point. + * pkt: Packet to be split (will contain the first part of the data on exit) + * pos: Position to split packet in two parts. + * @return The new packet, containing the second part of the data. + */ +struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos); + +/* + * Iteration function, iterates the packet buffers from start to end. + * + * Checksum iteration function used to iterate buffers + * (we may have packets consisting of a chain of buffers) + * pkt: Packet to calculate checksum for + * iter_func: Function pointer to iteration function + * chks: Checksum calculated so far. + * buf: Pointer to the buffer to checksum + * len: Length of buf. + * data: Initial checksum value. + * @return Checksum of buffer. + */ + +u16 cfpkt_iterate(struct cfpkt *pkt, + u16 (*iter_func)(u16 chks, void *buf, u16 len), + u16 data); + +/* Append by giving user access to packet buffer + * cfpkt Packet to append to + * buf Buffer inside pkt that user shall copy data into + * buflen Length of buffer and number of bytes added to packet + * @return 0 on error, 1 on success + */ +int cfpkt_raw_append(struct cfpkt *cfpkt, void **buf, unsigned int buflen); + +/* Extract by giving user access to packet buffer + * cfpkt Packet to extract from + * buf Buffer inside pkt that user shall copy data from + * buflen Length of buffer and number of bytes removed from packet + * @return 0 on error, 1 on success + */ +int cfpkt_raw_extract(struct cfpkt *cfpkt, void **buf, unsigned int buflen); + +/* Map from a "native" packet (e.g. Linux Socket Buffer) to a CAIF packet. + * dir - Direction indicating whether this packet is to be sent or received. + * nativepkt - The native packet to be transformed to a CAIF packet + * @return The mapped CAIF Packet CFPKT. + */ +struct cfpkt *cfpkt_fromnative(enum caif_direction dir, void *nativepkt); + +/* Map from a CAIF packet to a "native" packet (e.g. Linux Socket Buffer). + * pkt - The CAIF packet to be transformed into a "native" packet. + * @return The native packet transformed from a CAIF packet. + */ +void *cfpkt_tonative(struct cfpkt *pkt); + +/* + * Insert a packet in the packet queue. + * pktq Packet queue to insert into + * pkt Packet to be inserted in queue + * prio Priority of packet + */ +void cfpkt_queue(struct cfpktq *pktq, struct cfpkt *pkt, + unsigned short prio); + +/* + * Remove a packet from the packet queue. + * pktq Packet queue to fetch packets from. + * @return Dequeued packet. + */ +struct cfpkt *cfpkt_dequeue(struct cfpktq *pktq); + +/* + * Peek into a packet from the packet queue. + * pktq Packet queue to fetch packets from. + * @return Peeked packet. + */ +struct cfpkt *cfpkt_qpeek(struct cfpktq *pktq); + +/* + * Initiates the packet queue. + * @return Pointer to new packet queue. + */ +struct cfpktq *cfpktq_create(void); + +/* + * Get the number of packets in the queue. + * pktq Packet queue to fetch count from. + * @return Number of packets in queue. + */ +int cfpkt_qcount(struct cfpktq *pktq); + +/* + * Put content of packet into buffer for debuging purposes. + * pkt Packet to copy data from + * buf Buffer to copy data into + * buflen Length of data to copy + * @return Pointer to copied data + */ +char *cfpkt_log_pkt(struct cfpkt *pkt, char *buf, int buflen); + +/* + * Clones a packet and releases the original packet. + * This is used for taking ownership of a packet e.g queueing. + * pkt Packet to clone and release. + * @return Cloned packet. + */ +struct cfpkt *cfpkt_clone_release(struct cfpkt *pkt); + + +/* + * Returns packet information for a packet. + * pkt Packet to get info from; + * @return Packet information + */ +struct caif_payload_info *cfpkt_info(struct cfpkt *pkt); +/*! @} */ +#endif /* CFPKT_H_ */ diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h new file mode 100644 index 000000000000..b8374321b362 --- /dev/null +++ b/include/net/caif/cfserl.h @@ -0,0 +1,12 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFSERL_H_ +#define CFSERL_H_ +#include + +struct cflayer *cfserl_create(int type, int instance, bool use_stx); +#endif /* CFSERL_H_ */ diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h new file mode 100644 index 000000000000..b2a12db20cd2 --- /dev/null +++ b/include/net/caif/cfsrvl.h @@ -0,0 +1,34 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFSRVL_H_ +#define CFSRVL_H_ +#include +#include +#include +struct cfsrvl { + struct cflayer layer; + bool open; + bool phy_flow_on; + bool modem_flow_on; + struct dev_info dev_info; +}; + +struct cflayer *cfvei_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfdgml_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfutill_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfvidl_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfrfml_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfdbgl_create(u8 linkid, struct dev_info *dev_info); +bool cfsrvl_phyid_match(struct cflayer *layer, int phyid); +void cfservl_destroy(struct cflayer *layer); +void cfsrvl_init(struct cfsrvl *service, + u8 channel_id, + struct dev_info *dev_info); +bool cfsrvl_ready(struct cfsrvl *service, int *err); +u8 cfsrvl_getphyid(struct cflayer *layer); + +#endif /* CFSRVL_H_ */ -- cgit v1.2.2 From 2721c5b9dd2a56a9710021c00146bb26ba8dd7b3 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Tue, 30 Mar 2010 13:56:22 +0000 Subject: net-caif: add CAIF Link layer device header files Header files for CAIF Link layer net-device, and link-layer registration. Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/caif_dev.h | 90 ++++++++++++++++++++++++++++++++++++++++++ include/net/caif/caif_device.h | 55 ++++++++++++++++++++++++++ 2 files changed, 145 insertions(+) create mode 100644 include/net/caif/caif_dev.h create mode 100644 include/net/caif/caif_device.h (limited to 'include') diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h new file mode 100644 index 000000000000..42a7c7867849 --- /dev/null +++ b/include/net/caif/caif_dev.h @@ -0,0 +1,90 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CAIF_DEV_H_ +#define CAIF_DEV_H_ + +#include +#include +#include +#include + +/** + * struct caif_param - CAIF parameters. + * @size: Length of data + * @data: Binary Data Blob + */ +struct caif_param { + u16 size; + u8 data[256]; +}; + +/** + * caif_connect_request - Request data for CAIF channel setup. + * @sockaddr: Socket address to connect. + * @priority: Priority of the connection. + * @link_selector: Link selector (high bandwidth or low latency) + * @link_name: Name of the CAIF Link Layer to use. + * + * This struct is used when connecting a CAIF channel. + * It contains all CAIF channel configuration options. + */ +struct caif_connect_request { + int protocol; + struct sockaddr_caif sockaddr; + enum caif_channel_priority priority; + enum caif_link_selector link_selector; + char link_name[16]; + struct caif_param param; +}; + +/** + * caif_connect_client - Connect a client to CAIF Core Stack. + * @config: Channel setup parameters, specifying what address + * to connect on the Modem. + * @client_layer: User implementation of client layer. This layer + * MUST have receive and control callback functions + * implemented. + * + * This function connects a CAIF channel. The Client must implement + * the struct cflayer. This layer represents the Client layer and holds + * receive functions and control callback functions. Control callback + * function will receive information about connect/disconnect responses, + * flow control etc (see enum caif_control). + * E.g. CAIF Socket will call this function for each socket it connects + * and have one client_layer instance for each socket. + */ +int caif_connect_client(struct caif_connect_request *config, + struct cflayer *client_layer); + +/** + * caif_disconnect_client - Disconnects a client from the CAIF stack. + * + * @client_layer: Client layer to be removed. + */ +int caif_disconnect_client(struct cflayer *client_layer); + +/** + * connect_req_to_link_param - Translate configuration parameters + * from socket format to internal format. + * @cnfg: Pointer to configuration handler + * @con_req: Configuration parameters supplied in function + * caif_connect_client + * @channel_setup_param: Parameters supplied to the CAIF Core stack for + * setting up channels. + * + */ +int connect_req_to_link_param(struct cfcnfg *cnfg, + struct caif_connect_request *con_req, + struct cfctrl_link_param *channel_setup_param); + +/** + * get_caif_conf() - Get the configuration handler. + */ +struct cfcnfg *get_caif_conf(void); + + +#endif /* CAIF_DEV_H_ */ diff --git a/include/net/caif/caif_device.h b/include/net/caif/caif_device.h new file mode 100644 index 000000000000..d02f044adb8a --- /dev/null +++ b/include/net/caif/caif_device.h @@ -0,0 +1,55 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CAIF_DEVICE_H_ +#define CAIF_DEVICE_H_ +#include +#include +#include +#include +#include + +/** + * struct caif_dev_common - data shared between CAIF drivers and stack. + * @flowctrl: Flow Control callback function. This function is + * supplied by CAIF Core Stack and is used by CAIF + * Link Layer to send flow-stop to CAIF Core. + * The flow information will be distributed to all + * clients of CAIF. + * + * @link_select: Profile of device, either high-bandwidth or + * low-latency. This member is set by CAIF Link + * Layer Device in order to indicate if this device + * is a high bandwidth or low latency device. + * + * @use_frag: CAIF Frames may be fragmented. + * Is set by CAIF Link Layer in order to indicate if the + * interface receives fragmented frames that must be + * assembled by CAIF Core Layer. + * + * @use_fcs: Indicate if Frame CheckSum (fcs) is used. + * Is set if the physical interface is + * using Frame Checksum on the CAIF Frames. + * + * @use_stx: Indicate STart of frame eXtension (stx) in use. + * Is set if the CAIF Link Layer expects + * CAIF Frames to start with the STX byte. + * + * This structure is shared between the CAIF drivers and the CAIF stack. + * It is used by the device to register its behavior. + * CAIF Core layer must set the member flowctrl in order to supply + * CAIF Link Layer with the flow control function. + * + */ + struct caif_dev_common { + void (*flowctrl)(struct net_device *net, int on); + enum caif_link_selector link_select; + int use_frag; + int use_fcs; + int use_stx; +}; + +#endif /* CAIF_DEVICE_H_ */ -- cgit v1.2.2 From 9b27105b4a44c54bf91ecd7d0315034ae75684f7 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Tue, 30 Mar 2010 13:56:30 +0000 Subject: net-caif-driver: add CAIF serial driver (ldisc) Add CAIF Serial driver. This driver is implemented as a line discipline. caif_serial uses the following module parameters: ser_use_stx - specifies if STart of frame eXtension is in use. ser_loop - sets the interface in loopback mode. Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tty.h b/include/linux/tty.h index 568369a86306..71c7e9c96b23 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -23,7 +23,7 @@ */ #define NR_UNIX98_PTY_DEFAULT 4096 /* Default maximum for Unix98 ptys */ #define NR_UNIX98_PTY_MAX (1 << MINORBITS) /* Absolute limit */ -#define NR_LDISCS 20 +#define NR_LDISCS 21 /* line disciplines */ #define N_TTY 0 @@ -46,8 +46,8 @@ #define N_GIGASET_M101 16 /* Siemens Gigaset M101 serial DECT adapter */ #define N_SLCAN 17 /* Serial / USB serial CAN Adaptors */ #define N_PPS 18 /* Pulse per Second */ - #define N_V253 19 /* Codec control over voice modem */ +#define N_CAIF 20 /* CAIF protocol for talking to modems */ /* * This character is the same as _POSIX_VDISABLE: it cannot be used as -- cgit v1.2.2 From d5e50daf92df8afcb701fd717b301985691e802f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 31 Mar 2010 11:33:42 +0900 Subject: module: add stub for is_module_percpu_address Fix build for CONFIG_MODULES not enabled by providing a stub for is_module_percpu_address(). kernel/lockdep.c:605: error: implicit declaration of function 'is_module_percpu_address' Signed-off-by: Randy Dunlap Signed-off-by: Tejun Heo --- include/linux/module.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index f0e2659f4e3e..8bd399a00343 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -567,6 +567,11 @@ static inline bool is_module_address(unsigned long addr) return false; } +static inline bool is_module_percpu_address(unsigned long addr) +{ + return false; +} + static inline bool is_module_text_address(unsigned long addr) { return false; -- cgit v1.2.2 From d57b8fb8a8f94bdf467a4435be7d8bbebf87fe2a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?YOSHIFUJI=20Hideaki=20/=20=E5=90=89=E8=97=A4=E8=8B=B1?= =?UTF-8?q?=E6=98=8E?= Date: Mon, 29 Mar 2010 06:00:05 +0000 Subject: ipv6: Use __fls() instead of fls() in __ipv6_addr_diff(). Because we have ensured that the argument is non-zero, it is better to use __fls() and generate better code. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e72fb10ce573..033ddd4652a5 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -422,7 +422,7 @@ static inline int __ipv6_addr_diff(const void *token1, const void *token2, int a for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) - return i * 32 + 32 - fls(ntohl(xb)); + return i * 32 + 31 - __fls(ntohl(xb)); } /* -- cgit v1.2.2 From b00fabb4020d17bda4bea59507e09fadf573088d Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 29 Mar 2010 14:47:27 +0000 Subject: netdev: ethtool RXHASH flag This adds ethtool and device feature flag to allow control of receive hashing offload. Signed-off-by: Stephen Hemminger Acked-by: Jeff Garzik Signed-off-by: David S. Miller --- include/linux/ethtool.h | 1 + include/linux/netdevice.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b33f316bb92e..b391969a0dd9 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -310,6 +310,7 @@ struct ethtool_perm_addr { enum ethtool_flags { ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */ ETH_FLAG_NTUPLE = (1 << 27), /* N-tuple filters enabled */ + ETH_FLAG_RXHASH = (1 << 28), }; /* The following structures are for supporting RX network flow diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 53c272f2a734..b5670ab5107c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -785,6 +785,7 @@ struct net_device { #define NETIF_F_SCTP_CSUM (1 << 25) /* SCTP checksum offload */ #define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/ #define NETIF_F_NTUPLE (1 << 27) /* N-tuple filters supported */ +#define NETIF_F_RXHASH (1 << 28) /* Receive hashing offload */ /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 -- cgit v1.2.2 From e446630c960946b5c1762e4eadb618becef599e7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 29 Mar 2010 08:57:56 +0000 Subject: Add hotplug support to mcp251x driver Chip model can now be selected directly by matching the modalias name (instead of filling the .model field in platform_data), and allows the module to be auto-loaded. Previous behaviour is of course still supported. Convert the two in-tree users to this feature (icontrol & zeus). Tested on an Zeus platform (mcp2515). Signed-off-by: Marc Zyngier Acked-by: Christian Pellegrin Cc: Edwin Peer Acked-by: Wolfgang Grandegger Signed-off-by: David S. Miller --- include/linux/can/platform/mcp251x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h index 1448177d86d5..dba28268e651 100644 --- a/include/linux/can/platform/mcp251x.h +++ b/include/linux/can/platform/mcp251x.h @@ -26,8 +26,8 @@ struct mcp251x_platform_data { unsigned long oscillator_frequency; int model; -#define CAN_MCP251X_MCP2510 0 -#define CAN_MCP251X_MCP2515 1 +#define CAN_MCP251X_MCP2510 0x2510 +#define CAN_MCP251X_MCP2515 0x2515 int (*board_specific_setup)(struct spi_device *spi); int (*transceiver_enable)(int enable); int (*power_enable) (int enable); -- cgit v1.2.2 From e3cf8b3f7b9eefbe1d39b160726d6e5c2cbb4c5d Mon Sep 17 00:00:00 2001 From: Zhu Yi Date: Mon, 29 Mar 2010 17:35:07 +0800 Subject: mac80211: support paged rx SKBs Mac80211 drivers can now pass paged SKBs to mac80211 via ieee80211_rx{_irqsafe}. The implementation currently use skb_linearize() in a few places i.e. management frame handling, software decryption, defragmentation and A-MSDU process. We will optimize them one by one later. Signed-off-by: Zhu Yi Cc: Kalle Valo Cc: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1a8f50af49a0..ecaae10426f9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1822,7 +1822,10 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw); * ieee80211_rx - receive frame * * Use this function to hand received frames to mac80211. The receive - * buffer in @skb must start with an IEEE 802.11 header. + * buffer in @skb must start with an IEEE 802.11 header. In case of a + * paged @skb is used, the driver is recommended to put the ieee80211 + * header of the frame on the linear part of the @skb to avoid memory + * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to -- cgit v1.2.2 From e1b3ec1a2a336c328c336cfa5485a5f0484cc90d Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Mon, 29 Mar 2010 12:18:34 +0200 Subject: mac80211: explicitly disable/enable QoS Add interface to disable/enable QoS (aka WMM or WME). Currently drivers enable it explicitly when ->conf_tx method is called, and newer disable. Disabling is needed for some APs, which do not support QoS, such we should send QoS frames to them. Signed-off-by: Stanislaw Gruszka Signed-off-by: John W. Linville --- include/net/mac80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ecaae10426f9..dcf3c5f23c96 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -587,11 +587,15 @@ struct ieee80211_rx_status { * may turn the device off as much as possible. Typically, this flag will * be set when an interface is set UP but not associated or scanning, but * it can also be unset in that case when monitor interfaces are active. + * @IEEE80211_CONF_QOS: Enable 802.11e QoS also know as WMM (Wireless + * Multimedia). On some drivers (iwlwifi is one of know) we have + * to enable/disable QoS explicitly. */ enum ieee80211_conf_flags { IEEE80211_CONF_MONITOR = (1<<0), IEEE80211_CONF_PS = (1<<1), IEEE80211_CONF_IDLE = (1<<2), + IEEE80211_CONF_QOS = (1<<3), }; @@ -616,6 +620,7 @@ enum ieee80211_conf_changed { IEEE80211_CONF_CHANGE_CHANNEL = BIT(6), IEEE80211_CONF_CHANGE_RETRY_LIMITS = BIT(7), IEEE80211_CONF_CHANGE_IDLE = BIT(8), + IEEE80211_CONF_CHANGE_QOS = BIT(9), }; /** -- cgit v1.2.2 From f9ea3eb44218b0e12a190f222400f8d56136915f Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 18 Mar 2010 18:29:34 -0700 Subject: include/net/iw_handler.h: Use SIOCIWFIRST not SIOCSIWCOMMIT in comment to match use in IW_IOCTL_IDX macro Signed-off-by: Joe Perches Signed-off-by: John W. Linville --- include/net/iw_handler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index b2b98f3fa265..3afdb21cc31d 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -323,7 +323,7 @@ typedef int (*iw_handler)(struct net_device *dev, struct iw_request_info *info, struct iw_handler_def { /* Array of handlers for standard ioctls - * We will call dev->wireless_handlers->standard[ioctl - SIOCSIWCOMMIT] + * We will call dev->wireless_handlers->standard[ioctl - SIOCIWFIRST] */ const iw_handler * standard; /* Number of handlers defined (more precisely, index of the -- cgit v1.2.2 From e49a5bd38159dfb1928fd25b173bc9de4bbadb21 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 22 Mar 2010 19:40:03 +0100 Subject: perf: Use hot regs with software sched switch/migrate events Scheduler's task migration events don't work because they always pass NULL regs perf_sw_event(). The event hence gets filtered in perf_swevent_add(). Scheduler's context switches events use task_pt_regs() to get the context when the event occured which is a wrong thing to do as this won't give us the place in the kernel where we went to sleep but the place where we left userspace. The result is even more wrong if we switch from a kernel thread. Use the hot regs snapshot for both events as they belong to the non-interrupt/exception based events family. Unlike page faults or so that provide the regs matching the exact origin of the event, we need to save the current context. This makes the task migration event working and fix the context switch callchains and origin ip. Example: perf record -a -e cs Before: 10.91% ksoftirqd/0 0 [k] 0000000000000000 | --- (nil) perf_callchain perf_prepare_sample __perf_event_overflow perf_swevent_overflow perf_swevent_add perf_swevent_ctx_event do_perf_sw_event __perf_sw_event perf_event_task_sched_out schedule run_ksoftirqd kthread kernel_thread_helper After: 23.77% hald-addon-stor [kernel.kallsyms] [k] schedule | --- schedule | |--60.00%-- schedule_timeout | wait_for_common | wait_for_completion | blk_execute_rq | scsi_execute | scsi_execute_req | sr_test_unit_ready | | | |--66.67%-- sr_media_change | | media_changed | | cdrom_media_changed | | sr_block_media_changed | | check_disk_change | | cdrom_open v2: Always build perf_arch_fetch_caller_regs() now that software events need that too. They don't need it from modules, unlike trace events, so we keep the EXPORT_SYMBOL in trace_event_perf.c Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Ingo Molnar Cc: David Miller --- include/linux/perf_event.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 95477038a72a..c8e375440403 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -842,13 +842,6 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); -static inline void -perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) -{ - if (atomic_read(&perf_swevent_enabled[event_id])) - __perf_sw_event(event_id, nr, nmi, regs, addr); -} - extern void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); @@ -887,6 +880,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) return perf_arch_fetch_caller_regs(regs, ip, skip); } +static inline void +perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) +{ + if (atomic_read(&perf_swevent_enabled[event_id])) { + struct pt_regs hot_regs; + + if (!regs) { + perf_fetch_caller_regs(&hot_regs, 1); + regs = &hot_regs; + } + __perf_sw_event(event_id, nr, nmi, regs, addr); + } +} + extern void __perf_event_mmap(struct vm_area_struct *vma); static inline void perf_event_mmap(struct vm_area_struct *vma) -- cgit v1.2.2 From 6072f7491f5ef391a575e18a1165e72a3eef1601 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 31 Mar 2010 20:11:59 +0000 Subject: ide: Requeue request after DMA timeout I noticed that my KVM virtual machines were experiencing IDE issues resulting in processes stuck on waiting for buffers to complete. The root cause is of course race conditions in the ancient qemu backend that I'm using. However, the fact that the guest isn't recovering is a bug. I've tracked it down to the change made last year to dequeue requests at the start rather than at the end in the IDE layer. commit 8f6205cd572fece673da0255d74843680f67f879 Author: Tejun Heo Date: Fri May 8 11:53:59 2009 +0900 ide: dequeue in-flight request The problem is that the function ide_dma_timeout_retry does not requeue the current request, causing one request to be lost for each DMA timeout. This patch fixes this by requeueing the request. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index 97e6ab435184..3239d1c10acb 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1169,6 +1169,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(unsigned long); extern irqreturn_t ide_intr(int irq, void *dev_id); extern void do_ide_request(struct request_queue *); +extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); -- cgit v1.2.2 From 042be38e6106ed70b42d096ab4a1ed4187e510e6 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 1 Apr 2010 14:32:43 -0700 Subject: ibft, x86: Change reserve_ibft_region() to find_ibft_region() This allows arch code could decide the way to reserve the ibft. And we should reserve ibft as early as possible, instead of BOOTMEM stage, in case the table is in RAM range and is not reserved by BIOS (this will often be the case.) Move to just after find_smp_config(). Also when CONFIG_NO_BOOTMEM=y, We will not have reserve_bootmem() anymore. -v2: fix typo about ibft pointed by Konrad Rzeszutek Wilk Signed-off-by: Yinghai Lu LKML-Reference: <4BB510FB.80601@kernel.org> Cc: Pekka Enberg Cc: Peter Jones Cc: Konrad Rzeszutek Wilk CC: Jan Beulich Signed-off-by: H. Peter Anvin --- include/linux/iscsi_ibft.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iscsi_ibft.h b/include/linux/iscsi_ibft.h index 6092487e2950..d2e4042f8f5e 100644 --- a/include/linux/iscsi_ibft.h +++ b/include/linux/iscsi_ibft.h @@ -42,9 +42,13 @@ extern struct ibft_table_header *ibft_addr; * mapped address is set in the ibft_addr variable. */ #ifdef CONFIG_ISCSI_IBFT_FIND -extern void __init reserve_ibft_region(void); +unsigned long find_ibft_region(unsigned long *sizep); #else -static inline void reserve_ibft_region(void) { } +static inline unsigned long find_ibft_region(unsigned long *sizep) +{ + *sizep = 0; + return 0; +} #endif #endif /* ISCSI_IBFT_H */ -- cgit v1.2.2 From 5d944c640b4ae5f37c537acf491c2f0eb89fa0d6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Mar 2010 07:06:04 +0000 Subject: gen_estimator: deadlock fix One of my test machine got a deadlock during "tc" sessions, adding/deleting classes & filters, using traffic estimators. After some analysis, I believe we have a potential use after free case in est_timer() : spin_lock(e->stats_lock); << HERE >> read_lock(&est_lock); if (e->bstats == NULL) << TEST >> goto skip; Test is done a bit late, because after estimator is killed, and before rcu grace period elapsed, we might already have freed/reuse memory where e->stats_locks points to (some qdisc->q.lock) A possible fix is to respect a rcu grace period at Qdisc dismantle time. On 64bit, sizeof(struct Qdisc) is exactly 192 bytes. Adding 16 bytes to it (for struct rcu_head) is a problem because it might change performance, given QDISC_ALIGNTO is 32 bytes. This is why I also change QDISC_ALIGNTO to 64 bytes, to satisfy most current alignment requirements. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 +- include/net/sch_generic.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index b6cdc33b39c1..9d4d87cc970e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -12,7 +12,7 @@ struct qdisc_walker { int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *); }; -#define QDISC_ALIGNTO 32 +#define QDISC_ALIGNTO 64 #define QDISC_ALIGN(len) (((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1)) static inline void *qdisc_priv(struct Qdisc *q) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 67dc08eaaa45..03ca5d826757 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -73,6 +73,7 @@ struct Qdisc { struct sk_buff_head q; struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; + struct rcu_head rcu_head; }; struct Qdisc_class_ops { -- cgit v1.2.2 From bd2c77a0a749589b45f2697ea446a4438d078f9b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?YOSHIFUJI=20Hideaki=20/=20=E5=90=89=E8=97=A4=E8=8B=B1?= =?UTF-8?q?=E6=98=8E?= Date: Wed, 31 Mar 2010 22:24:22 +0000 Subject: ipv6 fib: Make rt6_info{} more cache-line aware. The head element of rt6_info{} is dst_entry{}, and IPv6 specific elements follow. Because elements at the end of dst_entry{} are frequently updated, it is not good to put frequently-used static elements, such as rt6i_idev, rt6i_dst or rt6i_flags in the same cache line. On the other hand, fib6_table, rt6i_node or rt6i_gateway are rarely used, so it is okay to stay in the same cache line. Let's rearrange rt6_info{}. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 86f46c49e318..4b1dc1161c37 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -88,34 +88,37 @@ struct rt6_info { struct dst_entry dst; } u; - struct inet6_dev *rt6i_idev; - #define rt6i_dev u.dst.dev #define rt6i_nexthop u.dst.neighbour #define rt6i_expires u.dst.expires + /* + * Tail elements of dst_entry (__refcnt etc.) + * and these elements (rarely used in hot path) are in + * the same cache line. + */ + struct fib6_table *rt6i_table; struct fib6_node *rt6i_node; struct in6_addr rt6i_gateway; - - u32 rt6i_flags; - u32 rt6i_metric; - atomic_t rt6i_ref; - /* more non-fragment space at head required */ - unsigned short rt6i_nfheader_len; - - u8 rt6i_protocol; + atomic_t rt6i_ref; - struct fib6_table *rt6i_table; + /* These are in a separate cache line. */ + struct rt6key rt6i_dst ____cacheline_aligned_in_smp; + u32 rt6i_flags; + struct rt6key rt6i_src; + u32 rt6i_metric; - struct rt6key rt6i_dst; + struct inet6_dev *rt6i_idev; #ifdef CONFIG_XFRM u32 rt6i_flow_cache_genid; #endif + /* more non-fragment space at head required */ + unsigned short rt6i_nfheader_len; - struct rt6key rt6i_src; + u8 rt6i_protocol; }; static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) -- cgit v1.2.2 From 8626d3b4328061f5b82b11ae1d6918a0c3602f42 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 2 Apr 2010 01:05:27 +0000 Subject: phylib: Support phy module autoloading We don't use the normal hotplug mechanism because it doesn't work. It will load the module some time after the device appears, but that's not good enough for us -- we need the driver loaded _immediately_ because otherwise the NIC driver may just abort and then the phy 'device' goes away. [bwh: s/phy/mdio/ in module alias, kerneldoc for struct mdio_device_id] Signed-off-by: David Woodhouse Signed-off-by: Ben Hutchings Acked-by: Andy Fleming Signed-off-by: David S. Miller --- include/linux/mod_devicetable.h | 26 ++++++++++++++++++++++++++ include/linux/phy.h | 1 + 2 files changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index f58e9d836f32..55f1f9c9506c 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -474,4 +474,30 @@ struct platform_device_id { __attribute__((aligned(sizeof(kernel_ulong_t)))); }; +#define MDIO_MODULE_PREFIX "mdio:" + +#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d" +#define MDIO_ID_ARGS(_id) \ + (_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \ + ((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \ + ((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \ + ((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \ + ((_id)>>15) & 1, ((_id)>>14) & 1, ((_id)>>13) & 1, ((_id)>>12) & 1, \ + ((_id)>>11) & 1, ((_id)>>10) & 1, ((_id)>>9) & 1, ((_id)>>8) & 1, \ + ((_id)>>7) & 1, ((_id)>>6) & 1, ((_id)>>5) & 1, ((_id)>>4) & 1, \ + ((_id)>>3) & 1, ((_id)>>2) & 1, ((_id)>>1) & 1, (_id) & 1 + +/** + * struct mdio_device_id - identifies PHY devices on an MDIO/MII bus + * @phy_id: The result of + * (mdio_read(&MII_PHYSID1) << 16 | mdio_read(&PHYSID2)) & @phy_id_mask + * for this PHY type + * @phy_id_mask: Defines the significant bits of @phy_id. A value of 0 + * is used to terminate an array of struct mdio_device_id. + */ +struct mdio_device_id { + __u32 phy_id; + __u32 phy_id_mask; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/phy.h b/include/linux/phy.h index d9bce4b526b4..987e111f7b11 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -24,6 +24,7 @@ #include #include #include +#include #include -- cgit v1.2.2 From a748ee2426817a95b1f03012d8f339c45c722ae1 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Apr 2010 21:22:09 +0000 Subject: net: move address list functions to a separate file +little renaming of unicast functions to be smooth with multicast ones Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b5670ab5107c..60f0c83192fe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1991,15 +1991,20 @@ extern int dev_addr_add_multiple(struct net_device *to_dev, extern int dev_addr_del_multiple(struct net_device *to_dev, struct net_device *from_dev, unsigned char addr_type); +extern void dev_addr_flush(struct net_device *dev); +extern int dev_addr_init(struct net_device *dev); + +/* Functions used for unicast addresses handling */ +extern int dev_uc_add(struct net_device *dev, unsigned char *addr); +extern int dev_uc_del(struct net_device *dev, unsigned char *addr); +extern int dev_uc_sync(struct net_device *to, struct net_device *from); +extern void dev_uc_unsync(struct net_device *to, struct net_device *from); +extern void dev_uc_flush(struct net_device *dev); +extern void dev_uc_init(struct net_device *dev); /* Functions used for secondary unicast and multicast support */ extern void dev_set_rx_mode(struct net_device *dev); extern void __dev_set_rx_mode(struct net_device *dev); -extern int dev_unicast_delete(struct net_device *dev, void *addr); -extern int dev_unicast_add(struct net_device *dev, void *addr); -extern int dev_unicast_sync(struct net_device *to, struct net_device *from); -extern void dev_unicast_unsync(struct net_device *to, struct net_device *from); -extern void dev_unicast_flush(struct net_device *dev); extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all); extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); extern int dev_mc_sync(struct net_device *to, struct net_device *from); -- cgit v1.2.2 From 22bedad3ce112d5ca1eaf043d4990fa2ed698c87 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Apr 2010 21:22:57 +0000 Subject: net: convert multicast list to list_head Converts the list and the core manipulating with it to be the same as uc_list. +uses two functions for adding/removing mc address (normal and "global" variant) instead of a function parameter. +removes dev_mcast.c completely. +exposes netdev_hw_addr_list_* macros along with __hw_addr_* functions for manipulation with lists on a sandbox (used in bonding and 80211 drivers) Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 82 ++++++++++++++++++++++++----------------------- include/net/mac80211.h | 2 +- 2 files changed, 43 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 60f0c83192fe..a343a21ba8b9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -228,25 +228,6 @@ struct netif_rx_stats { DECLARE_PER_CPU(struct netif_rx_stats, netdev_rx_stat); -struct dev_addr_list { - struct dev_addr_list *next; - u8 da_addr[MAX_ADDR_LEN]; - u8 da_addrlen; - u8 da_synced; - int da_users; - int da_gusers; -}; - -/* - * We tag multicasts with these structures. - */ - -#define dev_mc_list dev_addr_list -#define dmi_addr da_addr -#define dmi_addrlen da_addrlen -#define dmi_users da_users -#define dmi_gusers da_gusers - struct netdev_hw_addr { struct list_head list; unsigned char addr[MAX_ADDR_LEN]; @@ -255,8 +236,10 @@ struct netdev_hw_addr { #define NETDEV_HW_ADDR_T_SAN 2 #define NETDEV_HW_ADDR_T_SLAVE 3 #define NETDEV_HW_ADDR_T_UNICAST 4 +#define NETDEV_HW_ADDR_T_MULTICAST 5 int refcount; bool synced; + bool global_use; struct rcu_head rcu_head; }; @@ -265,16 +248,20 @@ struct netdev_hw_addr_list { int count; }; -#define netdev_uc_count(dev) ((dev)->uc.count) -#define netdev_uc_empty(dev) ((dev)->uc.count == 0) -#define netdev_for_each_uc_addr(ha, dev) \ - list_for_each_entry(ha, &dev->uc.list, list) +#define netdev_hw_addr_list_count(l) ((l)->count) +#define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0) +#define netdev_hw_addr_list_for_each(ha, l) \ + list_for_each_entry(ha, &(l)->list, list) -#define netdev_mc_count(dev) ((dev)->mc_count) -#define netdev_mc_empty(dev) (netdev_mc_count(dev) == 0) +#define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc) +#define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) +#define netdev_for_each_uc_addr(ha, dev) \ + netdev_hw_addr_list_for_each(ha, &(dev)->uc) +#define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) +#define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(mclist, dev) \ - for (mclist = dev->mc_list; mclist; mclist = mclist->next) + netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { struct hh_cache *hh_next; /* Next entry */ @@ -862,12 +849,10 @@ struct net_device { unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ - struct netdev_hw_addr_list uc; /* Secondary unicast - mac addresses */ - int uc_promisc; spinlock_t addr_list_lock; - struct dev_addr_list *mc_list; /* Multicast mac addresses */ - int mc_count; /* Number of installed mcasts */ + struct netdev_hw_addr_list uc; /* Unicast mac addresses */ + struct netdev_hw_addr_list mc; /* Multicast mac addresses */ + int uc_promisc; unsigned int promiscuity; unsigned int allmulti; @@ -1980,6 +1965,22 @@ extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, extern int register_netdev(struct net_device *dev); extern void unregister_netdev(struct net_device *dev); +/* General hardware address lists handling functions */ +extern int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type); +extern void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type); +extern int __hw_addr_sync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); +extern void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); +extern void __hw_addr_flush(struct netdev_hw_addr_list *list); +extern void __hw_addr_init(struct netdev_hw_addr_list *list); + /* Functions used for device addresses handling */ extern int dev_addr_add(struct net_device *dev, unsigned char *addr, unsigned char addr_type); @@ -2002,18 +2003,19 @@ extern void dev_uc_unsync(struct net_device *to, struct net_device *from); extern void dev_uc_flush(struct net_device *dev); extern void dev_uc_init(struct net_device *dev); +/* Functions used for multicast addresses handling */ +extern int dev_mc_add(struct net_device *dev, unsigned char *addr); +extern int dev_mc_add_global(struct net_device *dev, unsigned char *addr); +extern int dev_mc_del(struct net_device *dev, unsigned char *addr); +extern int dev_mc_del_global(struct net_device *dev, unsigned char *addr); +extern int dev_mc_sync(struct net_device *to, struct net_device *from); +extern void dev_mc_unsync(struct net_device *to, struct net_device *from); +extern void dev_mc_flush(struct net_device *dev); +extern void dev_mc_init(struct net_device *dev); + /* Functions used for secondary unicast and multicast support */ extern void dev_set_rx_mode(struct net_device *dev); extern void __dev_set_rx_mode(struct net_device *dev); -extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all); -extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); -extern int dev_mc_sync(struct net_device *to, struct net_device *from); -extern void dev_mc_unsync(struct net_device *to, struct net_device *from); -extern void dev_addr_discard(struct net_device *dev); -extern int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all); -extern int __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly); -extern int __dev_addr_sync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count); -extern void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count); extern int dev_set_promiscuity(struct net_device *dev, int inc); extern int dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1a8f50af49a0..20823d04e03c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1626,7 +1626,7 @@ struct ieee80211_ops { struct ieee80211_bss_conf *info, u32 changed); u64 (*prepare_multicast)(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mc_list); + struct netdev_hw_addr_list *mc_list); void (*configure_filter)(struct ieee80211_hw *hw, unsigned int changed_flags, unsigned int *total_flags, -- cgit v1.2.2 From fd558d186df2c13a22455373858bae634a4795af Mon Sep 17 00:00:00 2001 From: James Chapman Date: Fri, 2 Apr 2010 06:18:33 +0000 Subject: l2tp: Split pppol2tp patch into separate l2tp and ppp parts This patch splits the pppol2tp driver into separate L2TP and PPP parts to prepare for L2TPv3 support. In L2TPv3, protocols other than PPP can be carried, so this split creates a common L2TP core that will handle the common L2TP bits which protocol support modules such as PPP will use. Note that the existing pppol2tp module is split into l2tp_core and l2tp_ppp by this change. There are no feature changes here. Internally, however, there are significant changes, mostly to handle the separation of PPP-specific data from the L2TP session and to provide hooks in the core for modules like PPP to access. Signed-off-by: James Chapman Reviewed-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/if_pppol2tp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h index c58baea4a25b..1a1fb6e5d933 100644 --- a/include/linux/if_pppol2tp.h +++ b/include/linux/if_pppol2tp.h @@ -2,7 +2,7 @@ * Linux PPP over L2TP (PPPoL2TP) Socket Implementation (RFC 2661) * * This file supplies definitions required by the PPP over L2TP driver - * (pppol2tp.c). All version information wrt this file is located in pppol2tp.c + * (l2tp_ppp.c). All version information wrt this file is located in l2tp_ppp.c * * License: * This program is free software; you can redistribute it and/or -- cgit v1.2.2 From 63f96072f9ba430aa348bc987c3d5a4f48bae301 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Fri, 2 Apr 2010 06:18:39 +0000 Subject: ppp: Add ppp_dev_name() exported function ppp_dev_name() gives PPP users visibility of a ppp channel's device name. This can be used by L2TP drivers to dump the assigned PPP interface name. Signed-off-by: James Chapman Reviewed-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/ppp_channel.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h index 0d3fa63e90ea..bff98ec1bfed 100644 --- a/include/linux/ppp_channel.h +++ b/include/linux/ppp_channel.h @@ -72,6 +72,9 @@ extern int ppp_channel_index(struct ppp_channel *); /* Get the unit number associated with a channel, or -1 if none */ extern int ppp_unit_number(struct ppp_channel *); +/* Get the device name associated with a channel, or NULL if none */ +extern char *ppp_dev_name(struct ppp_channel *); + /* * SMP locking notes: * The channel code must ensure that when it calls ppp_unregister_channel, -- cgit v1.2.2 From e0d4435f93905f517003cfa7328a36ea19788147 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Fri, 2 Apr 2010 06:18:54 +0000 Subject: l2tp: Update PPP-over-L2TP driver to work over L2TPv3 This patch makes changes to the L2TP PPP code for L2TPv3. The existing code has some assumptions about the L2TP header which are broken by L2TPv3. Also the sockaddr_pppol2tp structure of the original code is too small to support the increased size of the L2TPv3 tunnel and session id, so a new sockaddr_pppol2tpv3 structure is needed. In the socket calls, the size of this structure is used to tell if the operation is for L2TPv2 or L2TPv3. Signed-off-by: James Chapman Reviewed-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/if_pppol2tp.h | 14 ++++++++++++++ include/linux/if_pppox.h | 9 +++++++++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h index 1a1fb6e5d933..184bc5566207 100644 --- a/include/linux/if_pppol2tp.h +++ b/include/linux/if_pppol2tp.h @@ -35,6 +35,20 @@ struct pppol2tp_addr { __u16 d_tunnel, d_session; /* For sending outgoing packets */ }; +/* The L2TPv3 protocol changes tunnel and session ids from 16 to 32 + * bits. So we need a different sockaddr structure. + */ +struct pppol2tpv3_addr { + pid_t pid; /* pid that owns the fd. + * 0 => current */ + int fd; /* FD of UDP or IP socket to use */ + + struct sockaddr_in addr; /* IP address and port to send to */ + + __u32 s_tunnel, s_session; /* For matching incoming packets */ + __u32 d_tunnel, d_session; /* For sending outgoing packets */ +}; + /* Socket options: * DEBUG - bitmask of debug message categories * SENDSEQ - 0 => don't send packets with sequence numbers diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 90b5fae5d714..a6577af0c4e6 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -72,6 +72,15 @@ struct sockaddr_pppol2tp { struct pppol2tp_addr pppol2tp; }__attribute__ ((packed)); +/* The L2TPv3 protocol changes tunnel and session ids from 16 to 32 + * bits. So we need a different sockaddr structure. + */ +struct sockaddr_pppol2tpv3 { + sa_family_t sa_family; /* address family, AF_PPPOX */ + unsigned int sa_protocol; /* protocol identifier */ + struct pppol2tpv3_addr pppol2tp; +} __attribute__ ((packed)); + /********************************************************************* * * ioctl interface for defining forwarding of connections -- cgit v1.2.2 From 0d76751fad7739014485ba5bd388d4f1b4fd4143 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Fri, 2 Apr 2010 06:19:00 +0000 Subject: l2tp: Add L2TPv3 IP encapsulation (no UDP) support This patch adds a new L2TPIP socket family and modifies the core to handle the case where there is no UDP header in the L2TP packet. L2TP/IP uses IP protocol 115. Since L2TP/UDP and L2TP/IP packets differ in layout, the datapath packet handling code needs changes too. Userspace uses an L2TPIP socket instead of a UDP socket when IP encapsulation is required. We can't use raw sockets for this because the semantics of raw sockets don't lend themselves to the socket-per-tunnel model - we need to Signed-off-by: David S. Miller --- include/linux/l2tp.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/l2tp.h (limited to 'include') diff --git a/include/linux/l2tp.h b/include/linux/l2tp.h new file mode 100644 index 000000000000..deff7bca4e05 --- /dev/null +++ b/include/linux/l2tp.h @@ -0,0 +1,38 @@ +/* + * L2TP-over-IP socket for L2TPv3. + * + * Author: James Chapman + */ + +#ifndef _LINUX_L2TP_H_ +#define _LINUX_L2TP_H_ + +#include +#ifdef __KERNEL__ +#include +#include +#endif + +#define IPPROTO_L2TP 115 + +/** + * struct sockaddr_l2tpip - the sockaddr structure for L2TP-over-IP sockets + * @l2tp_family: address family number AF_L2TPIP. + * @l2tp_addr: protocol specific address information + * @l2tp_conn_id: connection id of tunnel + */ +struct sockaddr_l2tpip { + /* The first fields must match struct sockaddr_in */ + sa_family_t l2tp_family; /* AF_INET */ + __be16 l2tp_unused; /* INET port number (unused) */ + struct in_addr l2tp_addr; /* Internet address */ + + __u32 l2tp_conn_id; /* Connection ID of tunnel */ + + /* Pad to size of `struct sockaddr'. */ + unsigned char __pad[sizeof(struct sockaddr) - sizeof(sa_family_t) - + sizeof(__be16) - sizeof(struct in_addr) - + sizeof(__u32)]; +}; + +#endif -- cgit v1.2.2 From f408e0ce40270559ef80f231843c93baa9947bc5 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Fri, 2 Apr 2010 06:19:05 +0000 Subject: netlink: Export genl_lock() API for use by modules This lets kernel modules which use genl netlink APIs serialize netlink processing. Signed-off-by: James Chapman Reviewed-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/genetlink.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index b834ef6d59fa..61549b26ad6f 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -80,4 +80,12 @@ enum { #define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1) +#ifdef __KERNEL__ + +/* All generic netlink requests are serialized by a global lock. */ +extern void genl_lock(void); +extern void genl_unlock(void); + +#endif /* __KERNEL__ */ + #endif /* __LINUX_GENERIC_NETLINK_H */ -- cgit v1.2.2 From 309795f4bec2d69cd507a631f82065c2198a0825 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Fri, 2 Apr 2010 06:19:10 +0000 Subject: l2tp: Add netlink control API for L2TP In L2TPv3, we need to create/delete/modify/query L2TP tunnel and session contexts. The number of parameters is significant. So let's use netlink. Userspace uses this API to control L2TP tunnel/session contexts in the kernel. The previous pppol2tp driver was managed using [gs]etsockopt(). This API is retained for backwards compatibility. Unlike L2TPv2 which carries only PPP frames, L2TPv3 can carry raw ethernet frames or other frame types and these do not always have an associated socket family. Therefore, we need a way to use L2TP sessions that doesn't require a socket type for each supported frame type. Hence netlink is used. Signed-off-by: James Chapman Reviewed-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/l2tp.h | 125 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 125 insertions(+) (limited to 'include') diff --git a/include/linux/l2tp.h b/include/linux/l2tp.h index deff7bca4e05..4bdb31df8e72 100644 --- a/include/linux/l2tp.h +++ b/include/linux/l2tp.h @@ -11,6 +11,8 @@ #ifdef __KERNEL__ #include #include +#else +#include #endif #define IPPROTO_L2TP 115 @@ -21,6 +23,7 @@ * @l2tp_addr: protocol specific address information * @l2tp_conn_id: connection id of tunnel */ +#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */ struct sockaddr_l2tpip { /* The first fields must match struct sockaddr_in */ sa_family_t l2tp_family; /* AF_INET */ @@ -35,4 +38,126 @@ struct sockaddr_l2tpip { sizeof(__u32)]; }; +/***************************************************************************** + * NETLINK_GENERIC netlink family. + *****************************************************************************/ + +/* + * Commands. + * Valid TLVs of each command are:- + * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum, vlanid + * TUNNEL_DELETE - CONN_ID + * TUNNEL_MODIFY - CONN_ID, udpcsum + * TUNNEL_GETSTATS - CONN_ID, (stats) + * TUNNEL_GET - CONN_ID, (...) + * SESSION_CREATE - SESSION_ID, PW_TYPE, offset, data_seq, cookie, peer_cookie, offset, l2spec + * SESSION_DELETE - SESSION_ID + * SESSION_MODIFY - SESSION_ID, data_seq + * SESSION_GET - SESSION_ID, (...) + * SESSION_GETSTATS - SESSION_ID, (stats) + * + */ +enum { + L2TP_CMD_NOOP, + L2TP_CMD_TUNNEL_CREATE, + L2TP_CMD_TUNNEL_DELETE, + L2TP_CMD_TUNNEL_MODIFY, + L2TP_CMD_TUNNEL_GET, + L2TP_CMD_SESSION_CREATE, + L2TP_CMD_SESSION_DELETE, + L2TP_CMD_SESSION_MODIFY, + L2TP_CMD_SESSION_GET, + __L2TP_CMD_MAX, +}; + +#define L2TP_CMD_MAX (__L2TP_CMD_MAX - 1) + +/* + * ATTR types defined for L2TP + */ +enum { + L2TP_ATTR_NONE, /* no data */ + L2TP_ATTR_PW_TYPE, /* u16, enum l2tp_pwtype */ + L2TP_ATTR_ENCAP_TYPE, /* u16, enum l2tp_encap_type */ + L2TP_ATTR_OFFSET, /* u16 */ + L2TP_ATTR_DATA_SEQ, /* u16 */ + L2TP_ATTR_L2SPEC_TYPE, /* u8, enum l2tp_l2spec_type */ + L2TP_ATTR_L2SPEC_LEN, /* u8, enum l2tp_l2spec_type */ + L2TP_ATTR_PROTO_VERSION, /* u8 */ + L2TP_ATTR_IFNAME, /* string */ + L2TP_ATTR_CONN_ID, /* u32 */ + L2TP_ATTR_PEER_CONN_ID, /* u32 */ + L2TP_ATTR_SESSION_ID, /* u32 */ + L2TP_ATTR_PEER_SESSION_ID, /* u32 */ + L2TP_ATTR_UDP_CSUM, /* u8 */ + L2TP_ATTR_VLAN_ID, /* u16 */ + L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ + L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ + L2TP_ATTR_DEBUG, /* u32 */ + L2TP_ATTR_RECV_SEQ, /* u8 */ + L2TP_ATTR_SEND_SEQ, /* u8 */ + L2TP_ATTR_LNS_MODE, /* u8 */ + L2TP_ATTR_USING_IPSEC, /* u8 */ + L2TP_ATTR_RECV_TIMEOUT, /* msec */ + L2TP_ATTR_FD, /* int */ + L2TP_ATTR_IP_SADDR, /* u32 */ + L2TP_ATTR_IP_DADDR, /* u32 */ + L2TP_ATTR_UDP_SPORT, /* u16 */ + L2TP_ATTR_UDP_DPORT, /* u16 */ + L2TP_ATTR_MTU, /* u16 */ + L2TP_ATTR_MRU, /* u16 */ + L2TP_ATTR_STATS, /* nested */ + __L2TP_ATTR_MAX, +}; + +#define L2TP_ATTR_MAX (__L2TP_ATTR_MAX - 1) + +/* Nested in L2TP_ATTR_STATS */ +enum { + L2TP_ATTR_STATS_NONE, /* no data */ + L2TP_ATTR_TX_PACKETS, /* u64 */ + L2TP_ATTR_TX_BYTES, /* u64 */ + L2TP_ATTR_TX_ERRORS, /* u64 */ + L2TP_ATTR_RX_PACKETS, /* u64 */ + L2TP_ATTR_RX_BYTES, /* u64 */ + L2TP_ATTR_RX_SEQ_DISCARDS, /* u64 */ + L2TP_ATTR_RX_OOS_PACKETS, /* u64 */ + L2TP_ATTR_RX_ERRORS, /* u64 */ + __L2TP_ATTR_STATS_MAX, +}; + +#define L2TP_ATTR_STATS_MAX (__L2TP_ATTR_STATS_MAX - 1) + +enum l2tp_pwtype { + L2TP_PWTYPE_NONE = 0x0000, + L2TP_PWTYPE_ETH_VLAN = 0x0004, + L2TP_PWTYPE_ETH = 0x0005, + L2TP_PWTYPE_PPP = 0x0007, + L2TP_PWTYPE_PPP_AC = 0x0008, + L2TP_PWTYPE_IP = 0x000b, + __L2TP_PWTYPE_MAX +}; + +enum l2tp_l2spec_type { + L2TP_L2SPECTYPE_NONE, + L2TP_L2SPECTYPE_DEFAULT, +}; + +enum l2tp_encap_type { + L2TP_ENCAPTYPE_UDP, + L2TP_ENCAPTYPE_IP, +}; + +enum l2tp_seqmode { + L2TP_SEQ_NONE = 0, + L2TP_SEQ_IP = 1, + L2TP_SEQ_ALL = 2, +}; + +/* + * NETLINK_GENERIC related info + */ +#define L2TP_GENL_NAME "l2tp" +#define L2TP_GENL_VERSION 0x1 + #endif -- cgit v1.2.2 From 1f8438a853667d48055ad38384c63e94b32c6578 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 3 Apr 2010 15:09:04 -0700 Subject: icmp: Account for ICMP out errors When ip_append() fails because of socket limit or memory shortage, increment ICMP_MIB_OUTERRORS counter, so that "netstat -s" can report these errors. LANG=C netstat -s | grep "ICMP messages failed" 0 ICMP messages failed For IPV6, implement ICMP6_MIB_OUTERRORS counter as well. # grep Icmp6OutErrors /proc/net/dev_snmp6/* /proc/net/dev_snmp6/eth0:Icmp6OutErrors 0 /proc/net/dev_snmp6/lo:Icmp6OutErrors 0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/snmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index d2a9aa3c6c88..52797714ade7 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -100,6 +100,7 @@ enum ICMP6_MIB_INMSGS, /* InMsgs */ ICMP6_MIB_INERRORS, /* InErrors */ ICMP6_MIB_OUTMSGS, /* OutMsgs */ + ICMP6_MIB_OUTERRORS, /* OutErrors */ __ICMP6_MIB_MAX }; -- cgit v1.2.2 From f11947c7c5b8abffd328739996dfdffef2b3e03f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 2 Apr 2010 14:29:23 +0300 Subject: ALSA: i2c: cleanup: change parameter to pointer We actually pass an array of 7 chars not 5. This silences a smatch warning. Signed-off-by: Dan Carpenter Signed-off-by: Takashi Iwai --- include/sound/ak4113.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h index 8988edae1609..2609048c1d44 100644 --- a/include/sound/ak4113.h +++ b/include/sound/ak4113.h @@ -307,7 +307,7 @@ struct ak4113 { int snd_ak4113_create(struct snd_card *card, ak4113_read_t *read, ak4113_write_t *write, - const unsigned char pgm[AK4113_WRITABLE_REGS], + const unsigned char *pgm, void *private_data, struct ak4113 **r_ak4113); void snd_ak4113_reg_write(struct ak4113 *ak4113, unsigned char reg, unsigned char mask, unsigned char val); -- cgit v1.2.2 From 6d96d3ab7aea5f0e75205a0c97f8d1fdf82c5287 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 29 Mar 2010 18:13:59 -0500 Subject: 9p: Make sure we are able to clunk the cached fid on umount dcache prune happen on umount. So we cannot mark the client satus disconnect. That will prevent a 9p call to the server Signed-off-by: Aneesh Kumar K.V Signed-off-by: Eric Van Hensbergen --- include/net/9p/client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/9p/client.h b/include/net/9p/client.h index f076dfa75ae8..4f3760afc20f 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -54,6 +54,7 @@ enum p9_proto_versions{ enum p9_trans_status { Connected, + BeginDisconnect, Disconnected, Hung, }; @@ -198,6 +199,7 @@ int p9_client_version(struct p9_client *); struct p9_client *p9_client_create(const char *dev_name, char *options); void p9_client_destroy(struct p9_client *clnt); void p9_client_disconnect(struct p9_client *clnt); +void p9_client_begin_disconnect(struct p9_client *clnt); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, char *uname, u32 n_uname, char *aname); struct p9_fid *p9_client_auth(struct p9_client *clnt, char *uname, -- cgit v1.2.2 From 5f712b2b73a9fc87fcc52124cfe8adefaa0c92f5 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 22 Mar 2010 10:11:15 +0100 Subject: ALSA: ASoC: move dma_data from snd_soc_dai to snd_soc_pcm_stream This fixes a memory corruption when ASoC devices are used in full-duplex mode. Specifically for pxa-ssp code, where this pointer is dynamically allocated for each direction and destroyed upon each stream start. All other platforms are fixed blindly, I couldn't even compile-test them. Sorry for any breakage I may have caused. [Note that this is a backported version for 2.6.34. Upstream commit is fd23b7dee] Signed-off-by: Daniel Mack Reported-by: Sven Neumann Reported-by: Michael Hirsch Acked-by: Liam Girdwood Signed-off-by: Mark Brown --- include/sound/soc-dai.h | 18 +++++++++++++++++- include/sound/soc.h | 1 + 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 061f16d4c878..0a0b019d41ad 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -219,7 +219,6 @@ struct snd_soc_dai { struct snd_soc_codec *codec; unsigned int active; unsigned char pop_wait:1; - void *dma_data; /* DAI private data */ void *private_data; @@ -230,4 +229,21 @@ struct snd_soc_dai { struct list_head list; }; +static inline void *snd_soc_dai_get_dma_data(const struct snd_soc_dai *dai, + const struct snd_pcm_substream *ss) +{ + return (ss->stream == SNDRV_PCM_STREAM_PLAYBACK) ? + dai->playback.dma_data : dai->capture.dma_data; +} + +static inline void snd_soc_dai_set_dma_data(struct snd_soc_dai *dai, + const struct snd_pcm_substream *ss, + void *data) +{ + if (ss->stream == SNDRV_PCM_STREAM_PLAYBACK) + dai->playback.dma_data = data; + else + dai->capture.dma_data = data; +} + #endif diff --git a/include/sound/soc.h b/include/sound/soc.h index 5d234a8c2506..a57fbfcd4c8f 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -375,6 +375,7 @@ struct snd_soc_pcm_stream { unsigned int channels_min; /* min channels */ unsigned int channels_max; /* max channels */ unsigned int active:1; /* stream is in use */ + void *dma_data; /* used by platform code */ }; /* SoC audio ops */ -- cgit v1.2.2 From 5fbfb18d7a5b846946d52c4a10e3aaa213ec31b6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 1 Apr 2010 19:09:40 +1100 Subject: Fix up possibly racy module refcounting Module refcounting is implemented with a per-cpu counter for speed. However there is a race when tallying the counter where a reference may be taken by one CPU and released by another. Reference count summation may then see the decrement without having seen the previous increment, leading to lower than expected count. A module which never has its actual reference drop below 1 may return a reference count of 0 due to this race. Module removal generally runs under stop_machine, which prevents this race causing bugs due to removal of in-use modules. However there are other real bugs in module.c code and driver code (module_refcount is exported) where the callers do not run under stop_machine. Fix this by maintaining running per-cpu counters for the number of module refcount increments and the number of refcount decrements. The increments are tallied after the decrements, so any decrement seen will always have its corresponding increment counted. The final refcount is the difference of the total increments and decrements, preventing a low-refcount from being returned. Signed-off-by: Nick Piggin Acked-by: Rusty Russell Signed-off-by: Linus Torvalds --- include/linux/module.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 8bd399a00343..515d53ae6a79 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -368,7 +368,8 @@ struct module void (*exit)(void); struct module_ref { - int count; + unsigned int incs; + unsigned int decs; } __percpu *refptr; #endif @@ -463,9 +464,9 @@ static inline void __module_get(struct module *module) { if (module) { preempt_disable(); - __this_cpu_inc(module->refptr->count); + __this_cpu_inc(module->refptr->incs); trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); + __this_cpu_read(module->refptr->incs)); preempt_enable(); } } @@ -478,11 +479,10 @@ static inline int try_module_get(struct module *module) preempt_disable(); if (likely(module_is_live(module))) { - __this_cpu_inc(module->refptr->count); + __this_cpu_inc(module->refptr->incs); trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); - } - else + __this_cpu_read(module->refptr->incs)); + } else ret = 0; preempt_enable(); -- cgit v1.2.2 From 445d211b0da4e9a6e6d576edff85085c2aaf53df Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Apr 2010 10:33:13 +0900 Subject: libata: unlock HPA if device shrunk Some BIOSes don't configure HPA during boot but do so while resuming. This causes harddrives to shrink during resume making libata detach and reattach them. This can be worked around by unlocking HPA if old size equals native size. Add ATA_DFLAG_UNLOCK_HPA so that HPA unlocking can be controlled per-device and update ata_dev_revalidate() such that it sets ATA_DFLAG_UNLOCK_HPA and fails with -EIO when the above condition is detected. This patch fixes the following bug. https://bugzilla.kernel.org/show_bug.cgi?id=15396 Signed-off-by: Tejun Heo Reported-by: Oleksandr Yermolenko Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index f8ea71e6d0e2..b2f2003b92e5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -146,6 +146,7 @@ enum { ATA_DFLAG_SLEEPING = (1 << 15), /* device is sleeping */ ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ + ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), -- cgit v1.2.2 From 8a64c0f6b7ec7f758c4ef445e49f479e27fa2236 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Tue, 6 Apr 2010 10:52:44 +0200 Subject: libertas/sdio: 8686: set ECSI bit for 1-bit transfers When operating in 1-bit mode, SDAT1 is used as dedicated interrupt line. However, the 8686 will only drive this line when the ECSI bit is set in the CCCR_IF register. Thanks to Alagu Sankar for pointing me in the right direction. Signed-off-by: Daniel Mack Cc: Alagu Sankar Cc: Volker Ernst Cc: Dan Williams Cc: John W. Linville Cc: Holger Schurig Cc: Bing Zhao Cc: libertas-dev@lists.infradead.org Cc: linux-wireless@vger.kernel.org Cc: linux-mmc@vger.kernel.org Acked-by: Dan Williams Signed-off-by: John W. Linville --- include/linux/mmc/sdio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h index 47ba464f5170..118f0295a575 100644 --- a/include/linux/mmc/sdio.h +++ b/include/linux/mmc/sdio.h @@ -94,6 +94,8 @@ #define SDIO_BUS_WIDTH_1BIT 0x00 #define SDIO_BUS_WIDTH_4BIT 0x02 +#define SDIO_BUS_ECSI 0x20 /* Enable continuous SPI interrupt */ +#define SDIO_BUS_SCSI 0x40 /* Support continuous SPI interrupt */ #define SDIO_BUS_CD_DISABLE 0x80 /* disable pull-up on DAT3 (pin 1) */ -- cgit v1.2.2 From c6537d6742985da1fbf12ae26cde6a096fd35b5c Mon Sep 17 00:00:00 2001 From: Jon Paul Maloy Date: Tue, 6 Apr 2010 11:40:52 +0000 Subject: TIPC: Updated topology subscription protocol according to latest spec This patch makes it explicit in the API that all fields in subscriptions and events exchanged with the Topology Server must be in network byte order. It also ensures that all fields of a subscription are compared when cancelling a subscription, in order to avoid inadvertent cancelling of the wrong subscription. Finally, the tipc module version is updated to 2.0.0, to reflect the API change. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- include/linux/tipc.h | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/tipc.h b/include/linux/tipc.h index 3d92396639de..9536d8aeadf1 100644 --- a/include/linux/tipc.h +++ b/include/linux/tipc.h @@ -127,23 +127,17 @@ static inline unsigned int tipc_node(__u32 addr) * TIPC topology subscription service definitions */ -#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ -#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ -#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ -#if 0 -/* The following filter options are not currently implemented */ -#define TIPC_SUB_NO_BIND_EVTS 0x04 /* filter out "publish" events */ -#define TIPC_SUB_NO_UNBIND_EVTS 0x08 /* filter out "withdraw" events */ -#define TIPC_SUB_SINGLE_EVT 0x10 /* expire after first event */ -#endif +#define TIPC_SUB_SERVICE 0x00 /* Filter for service availability */ +#define TIPC_SUB_PORTS 0x01 /* Filter for port availability */ +#define TIPC_SUB_CANCEL 0x04 /* Cancel a subscription */ #define TIPC_WAIT_FOREVER ~0 /* timeout for permanent subscription */ struct tipc_subscr { - struct tipc_name_seq seq; /* name sequence of interest */ - __u32 timeout; /* subscription duration (in ms) */ - __u32 filter; /* bitmask of filter options */ - char usr_handle[8]; /* available for subscriber use */ + struct tipc_name_seq seq; /* NBO. Name sequence of interest */ + __u32 timeout; /* NBO. Subscription duration (in ms) */ + __u32 filter; /* NBO. Bitmask of filter options */ + char usr_handle[8]; /* Opaque. Available for subscriber use */ }; #define TIPC_PUBLISHED 1 /* publication event */ @@ -151,11 +145,11 @@ struct tipc_subscr { #define TIPC_SUBSCR_TIMEOUT 3 /* subscription timeout event */ struct tipc_event { - __u32 event; /* event type */ - __u32 found_lower; /* matching name seq instances */ - __u32 found_upper; /* " " " " */ - struct tipc_portid port; /* associated port */ - struct tipc_subscr s; /* associated subscription */ + __u32 event; /* NBO. Event type, as defined above */ + __u32 found_lower; /* NBO. Matching name seq instances */ + __u32 found_upper; /* " " " " " */ + struct tipc_portid port; /* NBO. Associated port */ + struct tipc_subscr s; /* Original, associated subscription */ }; /* -- cgit v1.2.2 From fe1a5f031e76bd8761a7803d75b95ee96e84a574 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timo=20Ter=C3=A4s?= Date: Wed, 7 Apr 2010 00:30:04 +0000 Subject: flow: virtualize flow cache entry methods This allows to validate the cached object before returning it. It also allows to destruct object properly, if the last reference was held in flow cache. This is also a prepartion for caching bundles in the flow cache. In return for virtualizing the methods, we save on: - not having to regenerate the whole flow cache on policy removal: each flow matching a killed policy gets refreshed as the getter function notices it smartly. - we do not have to call flow_cache_flush from policy gc, since the flow cache now properly deletes the object if it had any references Signed-off-by: Timo Teras Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/flow.h | 23 +++++++++++++++++++---- include/net/xfrm.h | 2 ++ 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 809970b7dfee..bb08692a20b0 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -86,11 +86,26 @@ struct flowi { struct net; struct sock; -typedef int (*flow_resolve_t)(struct net *net, struct flowi *key, u16 family, - u8 dir, void **objp, atomic_t **obj_refp); +struct flow_cache_ops; + +struct flow_cache_object { + const struct flow_cache_ops *ops; +}; + +struct flow_cache_ops { + struct flow_cache_object *(*get)(struct flow_cache_object *); + int (*check)(struct flow_cache_object *); + void (*delete)(struct flow_cache_object *); +}; + +typedef struct flow_cache_object *(*flow_resolve_t)( + struct net *net, struct flowi *key, u16 family, + u8 dir, struct flow_cache_object *oldobj, void *ctx); + +extern struct flow_cache_object *flow_cache_lookup( + struct net *net, struct flowi *key, u16 family, + u8 dir, flow_resolve_t resolver, void *ctx); -extern void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, - u8 dir, flow_resolve_t resolver); extern void flow_cache_flush(void); extern atomic_t flow_cache_genid; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d74e080ba6c9..35396e2dd1dc 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -481,6 +482,7 @@ struct xfrm_policy { atomic_t refcnt; struct timer_list timer; + struct flow_cache_object flo; u32 priority; u32 index; struct xfrm_mark mark; -- cgit v1.2.2 From 80c802f3073e84c956846e921e8a0b02dfa3755f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timo=20Ter=C3=A4s?= Date: Wed, 7 Apr 2010 00:30:05 +0000 Subject: xfrm: cache bundles instead of policies for outgoing flows __xfrm_lookup() is called for each packet transmitted out of system. The xfrm_find_bundle() does a linear search which can kill system performance depending on how many bundles are required per policy. This modifies __xfrm_lookup() to store bundles directly in the flow cache. If we did not get a hit, we just create a new bundle instead of doing slow search. This means that we can now get multiple xfrm_dst's for same flow (on per-cpu basis). Signed-off-by: Timo Teras Signed-off-by: David S. Miller --- include/net/xfrm.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 35396e2dd1dc..625dd61ccbba 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -267,7 +267,6 @@ struct xfrm_policy_afinfo { xfrm_address_t *saddr, xfrm_address_t *daddr); int (*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr); - struct dst_entry *(*find_bundle)(struct flowi *fl, struct xfrm_policy *policy); void (*decode_session)(struct sk_buff *skb, struct flowi *fl, int reverse); @@ -483,13 +482,13 @@ struct xfrm_policy { struct timer_list timer; struct flow_cache_object flo; + atomic_t genid; u32 priority; u32 index; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; struct xfrm_lifetime_cur curlft; - struct dst_entry *bundles; struct xfrm_policy_walk_entry walk; u8 type; u8 action; @@ -879,11 +878,15 @@ struct xfrm_dst { struct rt6_info rt6; } u; struct dst_entry *route; + struct flow_cache_object flo; + struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; + int num_pols, num_xfrms; #ifdef CONFIG_XFRM_SUB_POLICY struct flowi *origin; struct xfrm_selector *partner; #endif - u32 genid; + u32 xfrm_genid; + u32 policy_genid; u32 route_mtu_cached; u32 child_mtu_cached; u32 route_cookie; @@ -893,6 +896,7 @@ struct xfrm_dst { #ifdef CONFIG_XFRM static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) { + xfrm_pols_put(xdst->pols, xdst->num_pols); dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); -- cgit v1.2.2 From b01d0942c2b7a3026d2b7d38b5773d3d00420e06 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 6 Apr 2010 14:34:41 -0700 Subject: bitops: remove temporary for_each_bit() Migration has been completed so remove this now. There's one straggler in linux-next's drivers/mtd/sm_ftl.c. A patch has been sent. Cc: Akinobu Mita Cc: Stephen Rothwell Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index b79389879238..b796eab5ca75 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -21,9 +21,6 @@ (bit) < (size); \ (bit) = find_next_bit((addr), (size), (bit) + 1)) -/* Temporary */ -#define for_each_bit(bit, addr, size) for_each_set_bit(bit, addr, size) - static __inline__ int get_bitmask_order(unsigned int count) { int order; -- cgit v1.2.2 From 530cd330dc3865e3107304a6e84fdc332aa72f7d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=A4rdeman?= Date: Tue, 6 Apr 2010 14:34:43 -0700 Subject: include/linux/kfifo.h: fix INIT_KFIFO() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DECLARE_KFIFO creates a union with a struct kfifo and a buffer array with size [size + sizeof(struct kfifo)]. INIT_KFIFO then sets the buffer pointer in struct kfifo to point to the beginning of the buffer array which means that the first call to kfifo_in will overwrite members of the struct kfifo. Signed-off-by: David Härdeman Acked-by: Stefani Seibold Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index ece0b1c33816..e117b1aee69c 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -86,7 +86,8 @@ union { \ */ #define INIT_KFIFO(name) \ name = __kfifo_initializer(sizeof(name##kfifo_buffer) - \ - sizeof(struct kfifo), name##kfifo_buffer) + sizeof(struct kfifo), \ + name##kfifo_buffer + sizeof(struct kfifo)) /** * DEFINE_KFIFO - macro to define and initialize a kfifo -- cgit v1.2.2 From 55ab3a1ff843e3f0e24d2da44e71bffa5d853010 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 6 Apr 2010 14:34:58 -0700 Subject: raw: fsync method is now required Commit 148f948ba877f4d3cdef036b1ff6d9f68986706a (vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode) broke the raw driver. We now call through generic_file_aio_write -> generic_write_sync -> vfs_fsync_range. vfs_fsync_range has: if (!fop || !fop->fsync) { ret = -EINVAL; goto out; } But drivers/char/raw.c doesn't set an fsync method. We have two options: fix it or remove the raw driver completely. I'm happy to do either, the fact this has been broken for so long suggests it is rarely used. The patch below adds an fsync method to the raw driver. My knowledge of the block layer is pretty sketchy so this could do with a once over. If we instead decide to remove the raw driver, this patch might still be useful as a backport to 2.6.33 and 2.6.32. Signed-off-by: Anton Blanchard Reviewed-by: Jan Kara Cc: Christoph Hellwig Cc: Alexander Viro Cc: Jens Axboe Reviewed-by: Jeff Moyer Tested-by: Jeff Moyer Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 10b8dedcd18b..5d9c7e27c5a4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2212,6 +2212,7 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); +extern int block_fsync(struct file *filp, struct dentry *dentry, int datasync); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, -- cgit v1.2.2 From b1dd3b2843b3b73b7fc2ee47d96310cd1c051371 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 6 Apr 2010 14:35:00 -0700 Subject: vfs: rename block_fsync() to blkdev_fsync() Requested by hch, for consistency now it is exported. Cc: Alexander Viro Cc: Anton Blanchard Cc: Christoph Hellwig Cc: Jan Kara Cc: Jeff Moyer Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5d9c7e27c5a4..39d57bc6cc71 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2212,7 +2212,7 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); -extern int block_fsync(struct file *filp, struct dentry *dentry, int datasync); +extern int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, -- cgit v1.2.2 From bb1dc0bacb8ddd7ba6a5906c678a5a5a110cf695 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Tue, 6 Apr 2010 14:35:02 -0700 Subject: kernel.h: fix wrong usage of __ratelimit() When __ratelimit() returns 1 this means that we can go ahead. Signed-off-by: Yong Zhang Cc: Ingo Molnar Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7f0707463360..9365227dbaf6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -426,7 +426,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) .burst = DEFAULT_RATELIMIT_BURST, \ }; \ \ - if (!__ratelimit(&_rs)) \ + if (__ratelimit(&_rs)) \ printk(fmt, ##__VA_ARGS__); \ }) #else -- cgit v1.2.2 From 116354d177ba2da37e91cf884e3d11e67f825efd Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 6 Apr 2010 14:35:04 -0700 Subject: pagemap: fix pfn calculation for hugepage When we look into pagemap using page-types with option -p, the value of pfn for hugepages looks wrong (see below.) This is because pte was evaluated only once for one vma although it should be updated for each hugepage. This patch fixes it. $ page-types -p 3277 -Nl -b huge voffset offset len flags 7f21e8a00 11e400 1 ___U___________H_G________________ 7f21e8a01 11e401 1ff ________________TG________________ ^^^ 7f21e8c00 11e400 1 ___U___________H_G________________ 7f21e8c01 11e401 1ff ________________TG________________ ^^^ One hugepage contains 1 head page and 511 tail pages in x86_64 and each two lines represent each hugepage. Voffset and offset mean virtual address and physical address in the page unit, respectively. The different hugepages should not have the same offset value. With this patch applied: $ page-types -p 3386 -Nl -b huge voffset offset len flags 7fec7a600 112c00 1 ___UD__________H_G________________ 7fec7a601 112c01 1ff ________________TG________________ ^^^ 7fec7a800 113200 1 ___UD__________H_G________________ 7fec7a801 113201 1ff ________________TG________________ ^^^ OK More info: - This patch modifies walk_page_range()'s hugepage walker. But the change only affects pagemap_read(), which is the only caller of hugepage callback. - Without this patch, hugetlb_entry() callback is called per vma, that doesn't match the natural expectation from its name. - With this patch, hugetlb_entry() is called per hugepte entry and the callback can become much simpler. Signed-off-by: Naoya Horiguchi Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Matt Mackall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index e70f21beb4b4..462acaf36f3a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -783,8 +783,8 @@ struct mm_walk { int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); - int (*hugetlb_entry)(pte_t *, unsigned long, unsigned long, - struct mm_walk *); + int (*hugetlb_entry)(pte_t *, unsigned long, + unsigned long, unsigned long, struct mm_walk *); struct mm_struct *mm; void *private; }; -- cgit v1.2.2 From 8725d5416213a145ccc9c236dbd26830ba409e00 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 6 Apr 2010 14:35:05 -0700 Subject: memcg: fix race in file_mapped accounting Presently, memcg's FILE_MAPPED accounting has following race with move_account (happens at rmdir()). increment page->mapcount (rmap.c) mem_cgroup_update_file_mapped() move_account() lock_page_cgroup() check page_mapped() if page_mapped(page)>1 { FILE_MAPPED -1 from old memcg FILE_MAPPED +1 to old memcg } ..... overwrite pc->mem_cgroup unlock_page_cgroup() lock_page_cgroup() FILE_MAPPED + 1 to pc->mem_cgroup unlock_page_cgroup() Then, old memcg (-1 file mapped) new memcg (+2 file mapped) This happens because move_account see page_mapped() which is not guarded by lock_page_cgroup(). This patch adds FILE_MAPPED flag to page_cgroup and move account information based on it. Now, all checks are synchronous with lock_page_cgroup(). Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Balbir Singh Reviewed-by: Daisuke Nishimura Cc: Andrea Righi Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 30b08136fdf3..aef22ae2af47 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -39,6 +39,7 @@ enum { PCG_CACHE, /* charged as cache */ PCG_USED, /* this object is in use. */ PCG_ACCT_LRU, /* page has been accounted for */ + PCG_FILE_MAPPED, /* page is accounted as "mapped" */ }; #define TESTPCGFLAG(uname, lname) \ @@ -73,6 +74,11 @@ CLEARPCGFLAG(AcctLRU, ACCT_LRU) TESTPCGFLAG(AcctLRU, ACCT_LRU) TESTCLEARPCGFLAG(AcctLRU, ACCT_LRU) + +SETPCGFLAG(FileMapped, FILE_MAPPED) +CLEARPCGFLAG(FileMapped, FILE_MAPPED) +TESTPCGFLAG(FileMapped, FILE_MAPPED) + static inline int page_cgroup_nid(struct page_cgroup *pc) { return page_to_nid(pc->page); -- cgit v1.2.2 From d5cdfacb35ed886271d1ccfffbded98d3447da17 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sun, 4 Apr 2010 09:37:19 +0300 Subject: cfg80211: Add local-state-change-only auth/deauth/disassoc cfg80211 is quite strict on allowing authentication and association commands only in certain states. In order to meet these requirements, user space applications may need to clear authentication or association state in some cases. Currently, this can be done with deauth/disassoc command, but that ends up sending out Deauthentication or Disassociation frame unnecessarily. Add a new nl80211 attribute to allow this sending of the frame be skipped, but with all other deauth/disassoc operations being completed. Similar state change is also needed for IEEE 802.11r FT protocol in the FT-over-DS case which does not use Authentication frame exchange in a transition to another BSS. For this to work with cfg80211, an authentication entry needs to be created for the target BSS without sending out an Authentication frame. The nl80211 authentication command can be used for this purpose, too, with the new attribute to indicate that the command is only for changing local state. This enables wpa_supplicant to complete FT-over-DS transition successfully. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/nl80211.h | 8 ++++++++ include/net/cfg80211.h | 11 +++++++++++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index daf6a3432b92..2ea3edeee7aa 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -703,6 +703,12 @@ enum nl80211_commands { * @NL80211_ATTR_CQM: connection quality monitor configuration in a * nested attribute with %NL80211_ATTR_CQM_* sub-attributes. * + * @NL80211_ATTR_LOCAL_STATE_CHANGE: Flag attribute to indicate that a command + * is requesting a local authentication/association state change without + * invoking actual management frame exchange. This can be used with + * NL80211_CMD_AUTHENTICATE, NL80211_CMD_DEAUTHENTICATE, + * NL80211_CMD_DISASSOCIATE. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -856,6 +862,8 @@ enum nl80211_attrs { NL80211_ATTR_CQM, + NL80211_ATTR_LOCAL_STATE_CHANGE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 868cfd3b9724..37cebd3aa0f7 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -704,6 +704,10 @@ struct cfg80211_crypto_settings { * @key_len: length of WEP key for shared key authentication * @key_idx: index of WEP key for shared key authentication * @key: WEP key for shared key authentication + * @local_state_change: This is a request for a local state only, i.e., no + * Authentication frame is to be transmitted and authentication state is + * to be changed without having to wait for a response from the peer STA + * (AP). */ struct cfg80211_auth_request { struct cfg80211_bss *bss; @@ -712,6 +716,7 @@ struct cfg80211_auth_request { enum nl80211_auth_type auth_type; const u8 *key; u8 key_len, key_idx; + bool local_state_change; }; /** @@ -744,12 +749,15 @@ struct cfg80211_assoc_request { * @ie: Extra IEs to add to Deauthentication frame or %NULL * @ie_len: Length of ie buffer in octets * @reason_code: The reason code for the deauthentication + * @local_state_change: This is a request for a local state only, i.e., no + * Deauthentication frame is to be transmitted. */ struct cfg80211_deauth_request { struct cfg80211_bss *bss; const u8 *ie; size_t ie_len; u16 reason_code; + bool local_state_change; }; /** @@ -762,12 +770,15 @@ struct cfg80211_deauth_request { * @ie: Extra IEs to add to Disassociation frame or %NULL * @ie_len: Length of ie buffer in octets * @reason_code: The reason code for the disassociation + * @local_state_change: This is a request for a local state only, i.e., no + * Disassociation frame is to be transmitted. */ struct cfg80211_disassoc_request { struct cfg80211_bss *bss; const u8 *ie; size_t ie_len; u16 reason_code; + bool local_state_change; }; /** -- cgit v1.2.2 From 098a607091426e79178b9a6c318d993fea131791 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Apr 2010 11:18:47 +0200 Subject: mac80211: clean up/fix aggregation code The aggregation code has a number of quirks, like inventing an unneeded WLAN_BACK_TIMER value and leaking memory under certain circumstances during station destruction. Fix these issues by using the regular aggregation session teardown code and blocking new aggregation sessions, all before the station is really destructed. As a side effect, this gets rid of the long code block to destroy aggregation safely. Additionally, rename tid_state_rx which can only have the values IDLE and OPERATIONAL to tid_active_rx to make it easier to understand that there is no bitwise stuff going on on the RX side -- the TX side remains because it needs to keep track of the driver and peer states. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 19984958ab7b..e9e03b02cb08 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1324,7 +1324,6 @@ enum ieee80211_back_actioncode { enum ieee80211_back_parties { WLAN_BACK_RECIPIENT = 0, WLAN_BACK_INITIATOR = 1, - WLAN_BACK_TIMER = 2, }; /* SA Query action */ -- cgit v1.2.2 From 18e225f257663c59ff9d4482f07ffd06361fc2ec Mon Sep 17 00:00:00 2001 From: Pavel Roskin Date: Wed, 7 Apr 2010 16:40:09 -0700 Subject: net: fix definition of netdev_for_each_mc_addr() The first argument should be called ha, not mclist. All callers use the name "ha", but if they used a different name, there would be a compile error. Signed-off-by: Pavel Roskin Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a343a21ba8b9..d1a21b576a40 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -260,7 +260,7 @@ struct netdev_hw_addr_list { #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) -#define netdev_for_each_mc_addr(mclist, dev) \ +#define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { -- cgit v1.2.2 From b7a413015d2986edf020fba765c906cc9cbcbfc9 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 31 Mar 2010 21:56:42 +0300 Subject: virtio: disable multiport console support. Move MULTIPORT feature and related config changes out of exported headers, and disable the feature at runtime. At this point, it seems less risky to keep code around until we can enable it than rip it out completely. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio_console.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include') diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index ae4f039515b4..92228a8fbcbc 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -12,37 +12,14 @@ /* Feature bits */ #define VIRTIO_CONSOLE_F_SIZE 0 /* Does host provide console size? */ -#define VIRTIO_CONSOLE_F_MULTIPORT 1 /* Does host provide multiple ports? */ struct virtio_console_config { /* colums of the screens */ __u16 cols; /* rows of the screens */ __u16 rows; - /* max. number of ports this device can hold */ - __u32 max_nr_ports; - /* number of ports added so far */ - __u32 nr_ports; } __attribute__((packed)); -/* - * A message that's passed between the Host and the Guest for a - * particular port. - */ -struct virtio_console_control { - __u32 id; /* Port number */ - __u16 event; /* The kind of control event (see below) */ - __u16 value; /* Extra information for the key */ -}; - -/* Some events for control messages */ -#define VIRTIO_CONSOLE_PORT_READY 0 -#define VIRTIO_CONSOLE_CONSOLE_PORT 1 -#define VIRTIO_CONSOLE_RESIZE 2 -#define VIRTIO_CONSOLE_PORT_OPEN 3 -#define VIRTIO_CONSOLE_PORT_NAME 4 -#define VIRTIO_CONSOLE_PORT_REMOVE 5 - #ifdef __KERNEL__ int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int)); #endif /* __KERNEL__ */ -- cgit v1.2.2 From f5eb917b861828da18dc28854308068c66d1449a Mon Sep 17 00:00:00 2001 From: John Hughes Date: Wed, 7 Apr 2010 21:29:25 -0700 Subject: x25: Patch to fix bug 15678 - x25 accesses fields beyond end of packet. Here is a patch to stop X.25 examining fields beyond the end of the packet. For example, when a simple CALL ACCEPTED was received: 10 10 0f x25_parse_facilities was attempting to decode the FACILITIES field, but this packet contains no facilities field. Signed-off-by: John Hughes Signed-off-by: David S. Miller --- include/net/x25.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/x25.h b/include/net/x25.h index 9baa07dc7d17..33f67fb78586 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -182,6 +182,10 @@ extern int sysctl_x25_clear_request_timeout; extern int sysctl_x25_ack_holdback_timeout; extern int sysctl_x25_forward; +extern int x25_parse_address_block(struct sk_buff *skb, + struct x25_address *called_addr, + struct x25_address *calling_addr); + extern int x25_addr_ntoa(unsigned char *, struct x25_address *, struct x25_address *); extern int x25_addr_aton(unsigned char *, struct x25_address *, -- cgit v1.2.2 From 97f8aefbbfb5aa5c9944e5fa8149f1fdaf71c7b6 Mon Sep 17 00:00:00 2001 From: chavey Date: Wed, 7 Apr 2010 21:54:42 -0700 Subject: net: fix ethtool coding style errors and warnings Fix coding style errors and warnings output while running checkpatch.pl on the files net/core/ethtool.c and include/linux/ethtool.h Signed-off-by: chavey Signed-off-by: David S. Miller --- include/linux/ethtool.h | 115 ++++++++++++++++++++++++++---------------------- 1 file changed, 62 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b391969a0dd9..276b40a16835 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -491,12 +491,12 @@ void ethtool_ntuple_flush(struct net_device *dev); * get_ufo: Report whether UDP fragmentation offload is enabled * set_ufo: Turn UDP fragmentation offload on or off * self_test: Run specified self-tests - * get_strings: Return a set of strings that describe the requested objects + * get_strings: Return a set of strings that describe the requested objects * phys_id: Identify the device * get_stats: Return statistics about the device * get_flags: get 32-bit flags bitmap * set_flags: set 32-bit flags bitmap - * + * * Description: * * get_settings: @@ -532,14 +532,20 @@ struct ethtool_ops { int (*nway_reset)(struct net_device *); u32 (*get_link)(struct net_device *); int (*get_eeprom_len)(struct net_device *); - int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); - int (*set_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); + int (*get_eeprom)(struct net_device *, + struct ethtool_eeprom *, u8 *); + int (*set_eeprom)(struct net_device *, + struct ethtool_eeprom *, u8 *); int (*get_coalesce)(struct net_device *, struct ethtool_coalesce *); int (*set_coalesce)(struct net_device *, struct ethtool_coalesce *); - void (*get_ringparam)(struct net_device *, struct ethtool_ringparam *); - int (*set_ringparam)(struct net_device *, struct ethtool_ringparam *); - void (*get_pauseparam)(struct net_device *, struct ethtool_pauseparam*); - int (*set_pauseparam)(struct net_device *, struct ethtool_pauseparam*); + void (*get_ringparam)(struct net_device *, + struct ethtool_ringparam *); + int (*set_ringparam)(struct net_device *, + struct ethtool_ringparam *); + void (*get_pauseparam)(struct net_device *, + struct ethtool_pauseparam*); + int (*set_pauseparam)(struct net_device *, + struct ethtool_pauseparam*); u32 (*get_rx_csum)(struct net_device *); int (*set_rx_csum)(struct net_device *, u32); u32 (*get_tx_csum)(struct net_device *); @@ -551,21 +557,24 @@ struct ethtool_ops { void (*self_test)(struct net_device *, struct ethtool_test *, u64 *); void (*get_strings)(struct net_device *, u32 stringset, u8 *); int (*phys_id)(struct net_device *, u32); - void (*get_ethtool_stats)(struct net_device *, struct ethtool_stats *, u64 *); + void (*get_ethtool_stats)(struct net_device *, + struct ethtool_stats *, u64 *); int (*begin)(struct net_device *); void (*complete)(struct net_device *); - u32 (*get_ufo)(struct net_device *); - int (*set_ufo)(struct net_device *, u32); - u32 (*get_flags)(struct net_device *); - int (*set_flags)(struct net_device *, u32); - u32 (*get_priv_flags)(struct net_device *); - int (*set_priv_flags)(struct net_device *, u32); + u32 (*get_ufo)(struct net_device *); + int (*set_ufo)(struct net_device *, u32); + u32 (*get_flags)(struct net_device *); + int (*set_flags)(struct net_device *, u32); + u32 (*get_priv_flags)(struct net_device *); + int (*set_priv_flags)(struct net_device *, u32); int (*get_sset_count)(struct net_device *, int); - int (*get_rxnfc)(struct net_device *, struct ethtool_rxnfc *, void *); + int (*get_rxnfc)(struct net_device *, + struct ethtool_rxnfc *, void *); int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); - int (*flash_device)(struct net_device *, struct ethtool_flash *); + int (*flash_device)(struct net_device *, struct ethtool_flash *); int (*reset)(struct net_device *, u32 *); - int (*set_rx_ntuple)(struct net_device *, struct ethtool_rx_ntuple *); + int (*set_rx_ntuple)(struct net_device *, + struct ethtool_rx_ntuple *); int (*get_rx_ntuple)(struct net_device *, u32 stringset, void *); }; #endif /* __KERNEL__ */ @@ -577,29 +586,29 @@ struct ethtool_ops { #define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ #define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ #define ETHTOOL_SWOL 0x00000006 /* Set wake-on-lan options. */ -#define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ -#define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ +#define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ +#define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ #define ETHTOOL_NWAY_RST 0x00000009 /* Restart autonegotiation. */ #define ETHTOOL_GLINK 0x0000000a /* Get link status (ethtool_value) */ -#define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ -#define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ +#define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ +#define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ #define ETHTOOL_GCOALESCE 0x0000000e /* Get coalesce config */ #define ETHTOOL_SCOALESCE 0x0000000f /* Set coalesce config. */ #define ETHTOOL_GRINGPARAM 0x00000010 /* Get ring parameters */ #define ETHTOOL_SRINGPARAM 0x00000011 /* Set ring parameters. */ #define ETHTOOL_GPAUSEPARAM 0x00000012 /* Get pause parameters */ #define ETHTOOL_SPAUSEPARAM 0x00000013 /* Set pause parameters. */ -#define ETHTOOL_GRXCSUM 0x00000014 /* Get RX hw csum enable (ethtool_value) */ -#define ETHTOOL_SRXCSUM 0x00000015 /* Set RX hw csum enable (ethtool_value) */ -#define ETHTOOL_GTXCSUM 0x00000016 /* Get TX hw csum enable (ethtool_value) */ -#define ETHTOOL_STXCSUM 0x00000017 /* Set TX hw csum enable (ethtool_value) */ +#define ETHTOOL_GRXCSUM 0x00000014 /* Get RX hw csum enable (ethtool_value) */ +#define ETHTOOL_SRXCSUM 0x00000015 /* Set RX hw csum enable (ethtool_value) */ +#define ETHTOOL_GTXCSUM 0x00000016 /* Get TX hw csum enable (ethtool_value) */ +#define ETHTOOL_STXCSUM 0x00000017 /* Set TX hw csum enable (ethtool_value) */ #define ETHTOOL_GSG 0x00000018 /* Get scatter-gather enable * (ethtool_value) */ #define ETHTOOL_SSG 0x00000019 /* Set scatter-gather enable * (ethtool_value). */ #define ETHTOOL_TEST 0x0000001a /* execute NIC self-test. */ #define ETHTOOL_GSTRINGS 0x0000001b /* get specified string set */ -#define ETHTOOL_PHYS_ID 0x0000001c /* identify the NIC */ +#define ETHTOOL_PHYS_ID 0x0000001c /* identify the NIC */ #define ETHTOOL_GSTATS 0x0000001d /* get NIC-specific statistics */ #define ETHTOOL_GTSO 0x0000001e /* Get TSO enable (ethtool_value) */ #define ETHTOOL_STSO 0x0000001f /* Set TSO enable (ethtool_value) */ @@ -610,24 +619,24 @@ struct ethtool_ops { #define ETHTOOL_SGSO 0x00000024 /* Set GSO enable (ethtool_value) */ #define ETHTOOL_GFLAGS 0x00000025 /* Get flags bitmap(ethtool_value) */ #define ETHTOOL_SFLAGS 0x00000026 /* Set flags bitmap(ethtool_value) */ -#define ETHTOOL_GPFLAGS 0x00000027 /* Get driver-private flags bitmap */ -#define ETHTOOL_SPFLAGS 0x00000028 /* Set driver-private flags bitmap */ +#define ETHTOOL_GPFLAGS 0x00000027 /* Get driver-private flags bitmap */ +#define ETHTOOL_SPFLAGS 0x00000028 /* Set driver-private flags bitmap */ -#define ETHTOOL_GRXFH 0x00000029 /* Get RX flow hash configuration */ -#define ETHTOOL_SRXFH 0x0000002a /* Set RX flow hash configuration */ +#define ETHTOOL_GRXFH 0x00000029 /* Get RX flow hash configuration */ +#define ETHTOOL_SRXFH 0x0000002a /* Set RX flow hash configuration */ #define ETHTOOL_GGRO 0x0000002b /* Get GRO enable (ethtool_value) */ #define ETHTOOL_SGRO 0x0000002c /* Set GRO enable (ethtool_value) */ -#define ETHTOOL_GRXRINGS 0x0000002d /* Get RX rings available for LB */ -#define ETHTOOL_GRXCLSRLCNT 0x0000002e /* Get RX class rule count */ -#define ETHTOOL_GRXCLSRULE 0x0000002f /* Get RX classification rule */ -#define ETHTOOL_GRXCLSRLALL 0x00000030 /* Get all RX classification rule */ -#define ETHTOOL_SRXCLSRLDEL 0x00000031 /* Delete RX classification rule */ -#define ETHTOOL_SRXCLSRLINS 0x00000032 /* Insert RX classification rule */ -#define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ -#define ETHTOOL_RESET 0x00000034 /* Reset hardware */ -#define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ -#define ETHTOOL_GRXNTUPLE 0x00000036 /* Get n-tuple filters from device */ -#define ETHTOOL_GSSET_INFO 0x00000037 /* Get string set info */ +#define ETHTOOL_GRXRINGS 0x0000002d /* Get RX rings available for LB */ +#define ETHTOOL_GRXCLSRLCNT 0x0000002e /* Get RX class rule count */ +#define ETHTOOL_GRXCLSRULE 0x0000002f /* Get RX classification rule */ +#define ETHTOOL_GRXCLSRLALL 0x00000030 /* Get all RX classification rule */ +#define ETHTOOL_SRXCLSRLDEL 0x00000031 /* Delete RX classification rule */ +#define ETHTOOL_SRXCLSRLINS 0x00000032 /* Insert RX classification rule */ +#define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ +#define ETHTOOL_RESET 0x00000034 /* Reset hardware */ +#define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ +#define ETHTOOL_GRXNTUPLE 0x00000036 /* Get n-tuple filters from device */ +#define ETHTOOL_GSSET_INFO 0x00000037 /* Get string set info */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET @@ -636,18 +645,18 @@ struct ethtool_ops { /* Indicates what features are supported by the interface. */ #define SUPPORTED_10baseT_Half (1 << 0) #define SUPPORTED_10baseT_Full (1 << 1) -#define SUPPORTED_100baseT_Half (1 << 2) -#define SUPPORTED_100baseT_Full (1 << 3) +#define SUPPORTED_100baseT_Half (1 << 2) +#define SUPPORTED_100baseT_Full (1 << 3) #define SUPPORTED_1000baseT_Half (1 << 4) #define SUPPORTED_1000baseT_Full (1 << 5) #define SUPPORTED_Autoneg (1 << 6) #define SUPPORTED_TP (1 << 7) #define SUPPORTED_AUI (1 << 8) #define SUPPORTED_MII (1 << 9) -#define SUPPORTED_FIBRE (1 << 10) +#define SUPPORTED_FIBRE (1 << 10) #define SUPPORTED_BNC (1 << 11) #define SUPPORTED_10000baseT_Full (1 << 12) -#define SUPPORTED_Pause (1 << 13) +#define SUPPORTED_Pause (1 << 13) #define SUPPORTED_Asym_Pause (1 << 14) #define SUPPORTED_2500baseX_Full (1 << 15) #define SUPPORTED_Backplane (1 << 16) @@ -657,8 +666,8 @@ struct ethtool_ops { #define SUPPORTED_10000baseR_FEC (1 << 20) /* Indicates what features are advertised by the interface. */ -#define ADVERTISED_10baseT_Half (1 << 0) -#define ADVERTISED_10baseT_Full (1 << 1) +#define ADVERTISED_10baseT_Half (1 << 0) +#define ADVERTISED_10baseT_Full (1 << 1) #define ADVERTISED_100baseT_Half (1 << 2) #define ADVERTISED_100baseT_Full (1 << 3) #define ADVERTISED_1000baseT_Half (1 << 4) @@ -697,12 +706,12 @@ struct ethtool_ops { #define DUPLEX_FULL 0x01 /* Which connector port. */ -#define PORT_TP 0x00 +#define PORT_TP 0x00 #define PORT_AUI 0x01 #define PORT_MII 0x02 #define PORT_FIBRE 0x03 #define PORT_BNC 0x04 -#define PORT_DA 0x05 +#define PORT_DA 0x05 #define PORT_NONE 0xef #define PORT_OTHER 0xff @@ -716,7 +725,7 @@ struct ethtool_ops { /* Enable or disable autonegotiation. If this is set to enable, * the forced link modes above are completely ignored. */ -#define AUTONEG_DISABLE 0x00 +#define AUTONEG_DISABLE 0x00 #define AUTONEG_ENABLE 0x01 /* Mode MDI or MDI-X */ @@ -747,8 +756,8 @@ struct ethtool_ops { #define AH_V6_FLOW 0x0b #define ESP_V6_FLOW 0x0c #define IP_USER_FLOW 0x0d -#define IPV4_FLOW 0x10 -#define IPV6_FLOW 0x11 +#define IPV4_FLOW 0x10 +#define IPV6_FLOW 0x11 /* L3-L4 network traffic flow hash options */ #define RXH_L2DA (1 << 1) -- cgit v1.2.2 From 45c4d015a92f72ec47acd0c7557abdc0c8a6499d Mon Sep 17 00:00:00 2001 From: Mark Lord Date: Wed, 7 Apr 2010 13:52:08 -0400 Subject: libata: Fix accesses at LBA28 boundary (old bug, but nasty) (v2) Most drives from Seagate, Hitachi, and possibly other brands, do not allow LBA28 access to sector number 0x0fffffff (2^28 - 1). So instead use LBA48 for such accesses. This bug could bite a lot of systems, especially when the user has taken care to align partitions to 4KB boundaries. On misaligned systems, it is less likely to be encountered, since a 4KB read would end at 0x10000000 rather than at 0x0fffffff. Signed-off-by: Mark Lord Signed-off-by: Jeff Garzik --- include/linux/ata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index b4c85e2adef5..700c5b9b3583 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -1025,8 +1025,8 @@ static inline int ata_ok(u8 status) static inline int lba_28_ok(u64 block, u32 n_block) { - /* check the ending block number */ - return ((block + n_block) < ((u64)1 << 28)) && (n_block <= 256); + /* check the ending block number: must be LESS THAN 0x0fffffff */ + return ((block + n_block) < ((1 << 28) - 1)) && (n_block <= 256); } static inline int lba_48_ok(u64 block, u32 n_block) -- cgit v1.2.2 From e4077e018b5ead3de9951fc01d8bf12eeeeeefed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timo=20Ter=C3=A4s?= Date: Thu, 8 Apr 2010 11:27:42 -0700 Subject: xfrm: Fix crashes in xfrm_lookup() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit From: Timo Teräs Happens because CONFIG_XFRM_SUB_POLICY is not enabled, and one of the helper functions I used did unexpected things in that case. Signed-off-by: David S. Miller --- include/net/xfrm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 625dd61ccbba..cccb049991a9 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -735,19 +735,12 @@ static inline void xfrm_pol_put(struct xfrm_policy *policy) xfrm_policy_destroy(policy); } -#ifdef CONFIG_XFRM_SUB_POLICY static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) { int i; for (i = npols - 1; i >= 0; --i) xfrm_pol_put(pols[i]); } -#else -static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) -{ - xfrm_pol_put(pols[0]); -} -#endif extern void __xfrm_state_destroy(struct xfrm_state *); -- cgit v1.2.2 From 97ad9139fd68b5c71f44d28d3f9788d89cfd4916 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Mon, 29 Mar 2010 11:00:21 -0700 Subject: mac80211: Moved mesh action codes to a more visible location Grouped mesh action codes together with the other action codes in ieee80211.h. Signed-off-by: Javier Cardona Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e9e03b02cb08..1252ba1fbff5 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1211,6 +1211,8 @@ enum ieee80211_category { WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, WLAN_CATEGORY_WMM = 17, + WLAN_CATEGORY_MESH_PLINK = 30, /* Pending ANA approval */ + WLAN_CATEGORY_MESH_PATH_SEL = 32, /* Pending ANA approval */ WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126, WLAN_CATEGORY_VENDOR_SPECIFIC = 127, }; -- cgit v1.2.2 From fc1c183353a113c71675fecd0485e5aa0fe68d72 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Wed, 7 Apr 2010 19:23:40 +0300 Subject: slab: Generify kernel pointer validation As suggested by Linus, introduce a kern_ptr_validate() helper that does some sanity checks to make sure a pointer is a valid kernel pointer. This is a preparational step for fixing SLUB kmem_ptr_validate(). Cc: Andrew Morton Cc: Christoph Lameter Cc: David Rientjes Cc: Ingo Molnar Cc: Matt Mackall Cc: Nick Piggin Signed-off-by: Pekka Enberg Signed-off-by: Linus Torvalds --- include/linux/slab.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 488446289cab..49d1247cd6d9 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -106,6 +106,7 @@ int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); unsigned int kmem_cache_size(struct kmem_cache *); const char *kmem_cache_name(struct kmem_cache *); +int kern_ptr_validate(const void *ptr, unsigned long size); int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr); /* -- cgit v1.2.2 From ce82653d6cfcc95ba88c25908664878459fb1b8d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 6 Apr 2010 22:36:20 +0100 Subject: radix_tree_tag_get() is not as safe as the docs make out [ver #2] radix_tree_tag_get() is not safe to use concurrently with radix_tree_tag_set() or radix_tree_tag_clear(). The problem is that the double tag_get() in radix_tree_tag_get(): if (!tag_get(node, tag, offset)) saw_unset_tag = 1; if (height == 1) { int ret = tag_get(node, tag, offset); may see the value change due to the action of set/clear. RCU is no protection against this as no pointers are being changed, no nodes are being replaced according to a COW protocol - set/clear alter the node directly. The documentation in linux/radix-tree.h, however, says that radix_tree_tag_get() is an exception to the rule that "any function modifying the tree or tags (...) must exclude other modifications, and exclude any functions reading the tree". The problem is that the next statement in radix_tree_tag_get() checks that the tag doesn't vary over time: BUG_ON(ret && saw_unset_tag); This has been seen happening in FS-Cache: https://www.redhat.com/archives/linux-cachefs/2010-April/msg00013.html To this end, remove the BUG_ON() from radix_tree_tag_get() and note in various comments that the value of the tag may change whilst the RCU read lock is held, and thus that the return value of radix_tree_tag_get() may not be relied upon unless radix_tree_tag_set/clear() and radix_tree_delete() are excluded from running concurrently with it. Reported-by: Romain DEGEZ Signed-off-by: David Howells Acked-by: Nick Piggin Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index c5da74918096..55ca73cf25e5 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -121,6 +121,13 @@ do { \ * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * + * Note that the value returned by radix_tree_tag_get() may not be relied upon + * if only the RCU read lock is held. Functions to set/clear tags and to + * delete nodes running concurrently with it may affect its result such that + * two consecutive reads in the same locked section may return different + * values. If reliability is required, modification functions must also be + * excluded from concurrency. + * * radix_tree_tagged is able to be called without locking or RCU. */ -- cgit v1.2.2 From bb29624614c2afe2873ee8ee97cf09df42701694 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 11 Apr 2010 02:15:55 +0000 Subject: inet: Remove unused send_check length argument inet: Remove unused send_check length argument This patch removes the unused length argument from the send_check function in struct inet_connection_sock_af_ops. Signed-off-by: Herbert Xu Tested-by: Yinghai Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 +-- include/net/tcp.h | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 696d6e4ce68a..52c8b8b8a0b9 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -37,8 +37,7 @@ struct tcp_congestion_ops; */ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sk_buff *skb, int ipfragok); - void (*send_check)(struct sock *sk, int len, - struct sk_buff *skb); + void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/tcp.h b/include/net/tcp.h index 75be5a28815d..70c5159f4b36 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -423,7 +423,7 @@ extern u8 *tcp_parse_md5sig_option(struct tcphdr *th); * TCP v4 functions exported for the inet6 API */ -extern void tcp_v4_send_check(struct sock *sk, int len, +extern void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); extern int tcp_v4_conn_request(struct sock *sk, -- cgit v1.2.2 From ed85b565b825566da34e55eee9ad150ed93fdda0 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 7 Apr 2010 22:41:28 +0000 Subject: packet: support for TX time stamps on RAW sockets Enable the SO_TIMESTAMPING socket infrastructure for raw packet sockets. We introduce PACKET_TX_TIMESTAMP for the control message cmsg_type. Similar support for UDP and CAN sockets was added in commit 51f31cabe3ce5345b51e4a4f82138b38c4d5dc91 Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/if_packet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index aa57a5f993fc..6ac23ef1801a 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -47,6 +47,7 @@ struct sockaddr_ll { #define PACKET_TX_RING 13 #define PACKET_LOSS 14 #define PACKET_VNET_HDR 15 +#define PACKET_TX_TIMESTAMP 16 struct tpacket_stats { unsigned int tp_packets; -- cgit v1.2.2 From b6c6712a42ca3f9fa7f4a3d7c40e3a9dd1fd9e03 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Apr 2010 23:03:29 +0000 Subject: net: sk_dst_cache RCUification With latest CONFIG_PROVE_RCU stuff, I felt more comfortable to make this work. sk->sk_dst_cache is currently protected by a rwlock (sk_dst_lock) This rwlock is readlocked for a very small amount of time, and dst entries are already freed after RCU grace period. This calls for RCU again :) This patch converts sk_dst_lock to a spinlock, and use RCU for readers. __sk_dst_get() is supposed to be called with rcu_read_lock() or if socket locked by user, so use appropriate rcu_dereference_check() condition (rcu_read_lock_held() || sock_owned_by_user(sk)) This patch avoids two atomic ops per tx packet on UDP connected sockets, for example, and permits sk_dst_lock to be much less dirtied. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 15 --------------- include/net/ip6_route.h | 4 ++-- include/net/sock.h | 47 ++++++++++++++++++++++++++++++----------------- 3 files changed, 32 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index ce078cda6b74..aac5a5fcfda9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -225,21 +225,6 @@ static inline void dst_confirm(struct dst_entry *dst) neigh_confirm(dst->neighbour); } -static inline void dst_negative_advice(struct dst_entry **dst_p, - struct sock *sk) -{ - struct dst_entry * dst = *dst_p; - if (dst && dst->ops->negative_advice) { - *dst_p = dst->ops->negative_advice(dst); - - if (dst != *dst_p) { - extern void sk_reset_txq(struct sock *sk); - - sk_reset_txq(sk); - } - } -} - static inline void dst_link_failure(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 68f67836e146..278312c95f96 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -152,9 +152,9 @@ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, struct in6_addr *daddr, struct in6_addr *saddr) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __ip6_dst_store(sk, dst, daddr, saddr); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } static inline int ipv6_unicast_destination(struct sk_buff *skb) diff --git a/include/net/sock.h b/include/net/sock.h index b4603cd54fcd..56df440a950b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -262,7 +262,7 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; #endif - rwlock_t sk_dst_lock; + spinlock_t sk_dst_lock; atomic_t sk_rmem_alloc; atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; @@ -1192,7 +1192,8 @@ extern unsigned long sock_i_ino(struct sock *sk); static inline struct dst_entry * __sk_dst_get(struct sock *sk) { - return sk->sk_dst_cache; + return rcu_dereference_check(sk->sk_dst_cache, rcu_read_lock_held() || + sock_owned_by_user(sk)); } static inline struct dst_entry * @@ -1200,50 +1201,62 @@ sk_dst_get(struct sock *sk) { struct dst_entry *dst; - read_lock(&sk->sk_dst_lock); - dst = sk->sk_dst_cache; + rcu_read_lock(); + dst = rcu_dereference(sk->sk_dst_cache); if (dst) dst_hold(dst); - read_unlock(&sk->sk_dst_lock); + rcu_read_unlock(); return dst; } +extern void sk_reset_txq(struct sock *sk); + +static inline void dst_negative_advice(struct sock *sk) +{ + struct dst_entry *ndst, *dst = __sk_dst_get(sk); + + if (dst && dst->ops->negative_advice) { + ndst = dst->ops->negative_advice(dst); + + if (ndst != dst) { + rcu_assign_pointer(sk->sk_dst_cache, ndst); + sk_reset_txq(sk); + } + } +} + static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = dst; + old_dst = rcu_dereference_check(sk->sk_dst_cache, + lockdep_is_held(&sk->sk_dst_lock)); + rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __sk_dst_set(sk, dst); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } static inline void __sk_dst_reset(struct sock *sk) { - struct dst_entry *old_dst; - - sk_tx_queue_clear(sk); - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = NULL; - dst_release(old_dst); + __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __sk_dst_reset(sk); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); -- cgit v1.2.2 From cd58950a5345f006a318f178705b9250aa54425c Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 9 Apr 2010 10:01:37 +0000 Subject: skbuff: remove unused dev_consume_skb macro definition dev_consume_skb and kfree_skb_clean have no users and in the case of kfree_skb_clean could cause potential build issues since I cannot find where it is defined. Based on the patch in which it was introduced it appears to have been a bit of leftover code from an earlier version of the patch in which kfree_skb_clean was dropped in favor of consume_skb. Signed-off-by: Alexander Duyck Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf42f194616e..38501d20650c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -470,7 +470,6 @@ extern int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); extern int skb_pad(struct sk_buff *skb, int pad); #define dev_kfree_skb(a) consume_skb(a) -#define dev_consume_skb(a) kfree_skb_clean(a) extern void skb_over_panic(struct sk_buff *skb, int len, void *here); extern void skb_under_panic(struct sk_buff *skb, int len, -- cgit v1.2.2 From 829e0015431537176e38812f88fffe1d3250083e Mon Sep 17 00:00:00 2001 From: "Hans J. Koch" Date: Tue, 13 Apr 2010 00:03:25 +0000 Subject: Fix some #includes in CAN drivers (rebased for net-next-2.6) In the current implementation, CAN drivers need to #include _before_ they #include , which is both ugly and unnecessary. Fix this by including in and remove the #include lines from drivers. Signed-off-by: Hans J. Koch Signed-off-by: David S. Miller --- include/linux/can/dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 6e5a7f00223d..cc0bb4961669 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -14,6 +14,7 @@ #ifndef CAN_DEV_H #define CAN_DEV_H +#include #include #include -- cgit v1.2.2 From acbbc07145b919248c410e1852b953d385be5c97 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 11 Apr 2010 06:56:11 +0000 Subject: net: uninline skb_bond_should_drop() skb_bond_should_drop() is too big to be inlined. This patch reduces kernel text size, and its compilation time as well (shrinking include/linux/netdevice.h) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 48 ++++------------------------------------------- 1 file changed, 4 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d1a21b576a40..470f7c951afb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2089,54 +2089,14 @@ static inline void netif_set_gso_max_size(struct net_device *dev, dev->gso_max_size = size; } -static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, - struct net_device *master) -{ - if (skb->pkt_type == PACKET_HOST) { - u16 *dest = (u16 *) eth_hdr(skb)->h_dest; - - memcpy(dest, master->dev_addr, ETH_ALEN); - } -} +extern int __skb_bond_should_drop(struct sk_buff *skb, + struct net_device *master); -/* On bonding slaves other than the currently active slave, suppress - * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and - * ARP on active-backup slaves with arp_validate enabled. - */ static inline int skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) { - if (master) { - struct net_device *dev = skb->dev; - - if (master->priv_flags & IFF_MASTER_ARPMON) - dev->last_rx = jiffies; - - if ((master->priv_flags & IFF_MASTER_ALB) && master->br_port) { - /* Do address unmangle. The local destination address - * will be always the one master has. Provides the right - * functionality in a bridge. - */ - skb_bond_set_mac_by_master(skb, master); - } - - if (dev->priv_flags & IFF_SLAVE_INACTIVE) { - if ((dev->priv_flags & IFF_SLAVE_NEEDARP) && - skb->protocol == __cpu_to_be16(ETH_P_ARP)) - return 0; - - if (master->priv_flags & IFF_MASTER_ALB) { - if (skb->pkt_type != PACKET_BROADCAST && - skb->pkt_type != PACKET_MULTICAST) - return 0; - } - if (master->priv_flags & IFF_MASTER_8023AD && - skb->protocol == __cpu_to_be16(ETH_P_SLOW)) - return 0; - - return 1; - } - } + if (master) + return __skb_bond_should_drop(skb, master); return 0; } -- cgit v1.2.2 From d8a566beaa75c6ad5e38cdccf0ea5294323e7866 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:15 +0000 Subject: net: fib_rules: consolidate IPv4 and DECnet ->default_pref() functions. Both functions are equivalent, consolidate them since a following patch needs a third implementation for multicast routing. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/fib_rules.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index c49086d2bc7d..52bd9e6c9141 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -114,4 +114,5 @@ extern int fib_rules_lookup(struct fib_rules_ops *, extern int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); +extern u32 fib_default_rule_pref(struct fib_rules_ops *ops); #endif -- cgit v1.2.2 From 0f87b1dd01b51dc3c789f7a212656a4a87eee1bd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:17 +0000 Subject: net: fib_rules: decouple address families from real address families Decouple the address family values used for fib_rules from the real address families in socket.h. This allows to use fib_rules for code that is not a real address family without increasing AF_MAX/NPROTO. Values up to 127 are reserved for real address families and map directly to the corresponding AF value, values starting from 128 are for other uses. rtnetlink is changed to invoke the AF_UNSPEC dumpit/doit handlers for these families. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 51da65b68b85..405e41139a4d 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -15,6 +15,13 @@ /* try to find source address in routing lookups */ #define FIB_RULE_FIND_SADDR 0x00010000 +/* fib_rules families. values up to 127 are reserved for real address + * families, values above 128 may be used arbitrarily. + */ +#define FIB_RULES_IPV4 AF_INET +#define FIB_RULES_IPV6 AF_INET6 +#define FIB_RULES_DECNET AF_DECnet + struct fib_rule_hdr { __u8 family; __u8 dst_len; -- cgit v1.2.2 From f74e49b5613206fb18468bdc9509a1db746aa01b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:18 +0000 Subject: ipv4: raw: move struct raw_sock and raw_sk() to include/net/raw.h A following patch will use struct raw_sock to store state for ipmr, so having the definitions in icmp.h doesn't fit very well anymore. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/icmp.h | 11 ----------- include/net/raw.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/icmp.h b/include/net/icmp.h index 15b3dfe9fce8..6e991e0d0d6f 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -48,15 +48,4 @@ extern void icmp_out_count(struct net *net, unsigned char type); /* Move into dst.h ? */ extern int xrlim_allow(struct dst_entry *dst, int timeout); -struct raw_sock { - /* inet_sock has to be the first member */ - struct inet_sock inet; - struct icmp_filter filter; -}; - -static inline struct raw_sock *raw_sk(const struct sock *sk) -{ - return (struct raw_sock *)sk; -} - #endif /* _ICMP_H */ diff --git a/include/net/raw.h b/include/net/raw.h index 6c14a656357a..67cc64369432 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -19,6 +19,7 @@ #include +#include extern struct proto raw_prot; @@ -56,4 +57,15 @@ int raw_seq_open(struct inode *ino, struct file *file, void raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); +struct raw_sock { + /* inet_sock has to be the first member */ + struct inet_sock inet; + struct icmp_filter filter; +}; + +static inline struct raw_sock *raw_sk(const struct sock *sk) +{ + return (struct raw_sock *)sk; +} + #endif /* _RAW_H */ -- cgit v1.2.2 From e258beb22f4d3ea3dc88586ffc9c990d0eb03380 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:19 +0000 Subject: ipv4: ipmr: move unres_queue and timer to per-namespace data The unres_queue is currently shared between all namespaces. Following patches will additionally allow to create multiple multicast routing tables in each namespace. Having a single shared queue for all these users seems to excessive, move the queue and the cleanup timer to the per-namespace data to unshare it. As a side-effect, this fixes a bug in the seq file iteration functions: the first entry returned is always from the current namespace, entries returned after that may belong to any namespace. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2764994c9136..b15e518f952a 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -60,6 +60,8 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MROUTE struct sock *mroute_sk; + struct timer_list ipmr_expire_timer; + struct mfc_cache *mfc_unres_queue; struct mfc_cache **mfc_cache_array; struct vif_device *vif_table; int maxvif; -- cgit v1.2.2 From d658f8a0e63b6476148162aa7a3ffffc58dcad52 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:20 +0000 Subject: ipv4: ipmr: remove net pointer from struct mfc_cache Now that cache entries in unres_queue don't need to be distinguished by their network namespace pointer anymore, we can remove it from struct mfc_cache add pass the namespace as function argument to the functions that need it. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/mroute.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index c5f3d53548e2..de7780a6dd32 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -192,9 +192,6 @@ struct vif_device { struct mfc_cache { struct mfc_cache *next; /* Next entry on cache line */ -#ifdef CONFIG_NET_NS - struct net *mfc_net; -#endif __be32 mfc_mcastgrp; /* Group the entry belongs to */ __be32 mfc_origin; /* Source of packet */ vifi_t mfc_parent; /* Source interface */ @@ -217,18 +214,6 @@ struct mfc_cache { } mfc_un; }; -static inline -struct net *mfc_net(const struct mfc_cache *mfc) -{ - return read_pnet(&mfc->mfc_net); -} - -static inline -void mfc_net_set(struct mfc_cache *mfc, struct net *net) -{ - write_pnet(&mfc->mfc_net, hold_net(net)); -} - #define MFC_STATIC 1 #define MFC_NOTIFY 2 -- cgit v1.2.2 From 862465f2e7e90975e7bf0ecfbb171dd3adedd950 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:21 +0000 Subject: ipv4: ipmr: convert struct mfc_cache to struct list_head Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/mroute.h | 2 +- include/net/netns/ipv4.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index de7780a6dd32..7ff6c77d6008 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -191,7 +191,7 @@ struct vif_device { #define VIFF_STATIC 0x8000 struct mfc_cache { - struct mfc_cache *next; /* Next entry on cache line */ + struct list_head list; __be32 mfc_mcastgrp; /* Group the entry belongs to */ __be32 mfc_origin; /* Source of packet */ vifi_t mfc_parent; /* Source interface */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index b15e518f952a..5d06429968d5 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -61,8 +61,8 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MROUTE struct sock *mroute_sk; struct timer_list ipmr_expire_timer; - struct mfc_cache *mfc_unres_queue; - struct mfc_cache **mfc_cache_array; + struct list_head mfc_unres_queue; + struct list_head *mfc_cache_array; struct vif_device *vif_table; int maxvif; atomic_t cache_resolve_queue_len; -- cgit v1.2.2 From 0c12295a741d3186987f96f518cfbdaf01abb087 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:22 +0000 Subject: ipv4: ipmr: move mroute data into seperate structure Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 5d06429968d5..72e762ab3e5d 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -59,18 +59,7 @@ struct netns_ipv4 { atomic_t rt_genid; #ifdef CONFIG_IP_MROUTE - struct sock *mroute_sk; - struct timer_list ipmr_expire_timer; - struct list_head mfc_unres_queue; - struct list_head *mfc_cache_array; - struct vif_device *vif_table; - int maxvif; - atomic_t cache_resolve_queue_len; - int mroute_do_assert; - int mroute_do_pim; -#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) - int mroute_reg_vif_num; -#endif + struct mr_table *mrt; #endif }; #endif -- cgit v1.2.2 From f0ad0860d01e47a3ffd220564c5c653b3afbe962 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:23 +0000 Subject: ipv4: ipmr: support multiple tables This patch adds support for multiple independant multicast routing instances, named "tables". Userspace multicast routing daemons can bind to a specific table instance by issuing a setsockopt call using a new option MRT_TABLE. The table number is stored in the raw socket data and affects all following ipmr setsockopt(), getsockopt() and ioctl() calls. By default, a single table (RT_TABLE_DEFAULT) is created with a default routing rule pointing to it. Newly created pimreg devices have the table number appended ("pimregX"), with the exception of devices created in the default table, which are named just "pimreg" for compatibility reasons. Packets are directed to a specific table instance using routing rules, similar to how regular routing rules work. Currently iif, oif and mark are supported as keys, source and destination addresses could be supported additionally. Example usage: - bind pimd/xorp/... to a specific table: uint32_t table = 123; setsockopt(fd, IPPROTO_IP, MRT_TABLE, &table, sizeof(table)); - create routing rules directing packets to the new table: # ip mrule add iif eth0 lookup 123 # ip mrule add oif eth0 lookup 123 Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 1 + include/linux/mroute.h | 3 ++- include/net/netns/ipv4.h | 5 +++++ include/net/raw.h | 1 + 4 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 405e41139a4d..04a397619ebe 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -21,6 +21,7 @@ #define FIB_RULES_IPV4 AF_INET #define FIB_RULES_IPV6 AF_INET6 #define FIB_RULES_DECNET AF_DECnet +#define FIB_RULES_IPMR 128 struct fib_rule_hdr { __u8 family; diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 7ff6c77d6008..fa04b246c9ae 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -27,7 +27,8 @@ #define MRT_DEL_MFC (MRT_BASE+5) /* Delete a multicast forwarding entry */ #define MRT_VERSION (MRT_BASE+6) /* Get the kernel multicast version */ #define MRT_ASSERT (MRT_BASE+7) /* Activate PIM assert mode */ -#define MRT_PIM (MRT_BASE+8) /* enable PIM code */ +#define MRT_PIM (MRT_BASE+8) /* enable PIM code */ +#define MRT_TABLE (MRT_BASE+9) /* Specify mroute table ID */ #define SIOCGETVIFCNT SIOCPROTOPRIVATE /* IP protocol privates */ #define SIOCGETSGCNT (SIOCPROTOPRIVATE+1) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 72e762ab3e5d..ae07feec6446 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -59,7 +59,12 @@ struct netns_ipv4 { atomic_t rt_genid; #ifdef CONFIG_IP_MROUTE +#ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES struct mr_table *mrt; +#else + struct list_head mr_tables; + struct fib_rules_ops *mr_rules_ops; +#endif #endif }; #endif diff --git a/include/net/raw.h b/include/net/raw.h index 67cc64369432..43c57502659b 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -61,6 +61,7 @@ struct raw_sock { /* inet_sock has to be the first member */ struct inet_sock inet; struct icmp_filter filter; + u32 ipmr_table; }; static inline struct raw_sock *raw_sk(const struct sock *sk) -- cgit v1.2.2 From e326e8503dfc73e4f79d488a78ee3d7cde10081f Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Tue, 13 Apr 2010 20:21:14 +0000 Subject: stmmac: new descriptor field for the driver's platform The new enh_desc is used for selecting the enhanced descriptors structure. There are several scenarios; some chips (mac10/100 or gmac) want to use the enhanced descriptors; others want the normal ones. For example, on ST platforms: MAC10/100 uses the normal desc structure and the GMAC uses the enhanced one. It can be useful to get this information from the platform. This could also be decided at run-time looking at the chip's ID number; but it could happen that chips with the same ID want to use different descriptor structure. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 32bfd1a8a48d..632ff7c03280 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -33,6 +33,7 @@ struct plat_stmmacenet_data { int bus_id; int pbl; int has_gmac; + int enh_desc; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(unsigned long ioaddr); #ifdef CONFIG_STM_DRIVERS -- cgit v1.2.2 From fd793d8905720595caede6bd26c5df6c0ecd37f8 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 15 Apr 2010 00:16:59 -0700 Subject: net: CONFIG_SMP should be CONFIG_RPS Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 470f7c951afb..55c2086e1f06 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1331,7 +1331,7 @@ struct softnet_data { struct sk_buff *completion_queue; /* Elements below can be accessed between CPUs for RPS */ -#ifdef CONFIG_SMP +#ifdef CONFIG_RPS struct call_single_data csd ____cacheline_aligned_in_smp; #endif struct sk_buff_head input_pkt_queue; -- cgit v1.2.2 From 4e15ed4d930297c127d280ca1d0c785be870def4 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Thu, 15 Apr 2010 16:43:08 +0000 Subject: net: replace ipfragok with skb->local_df As Herbert Xu said: we should be able to simply replace ipfragok with skb->local_df. commit f88037(sctp: Drop ipfargok in sctp_xmit function) has droped ipfragok and set local_df value properly. The patch kills the ipfragok parameter of .queue_xmit(). Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 2 +- include/net/inet_connection_sock.h | 2 +- include/net/ip.h | 2 +- include/net/ipv6.h | 3 +-- 4 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index f13ddc2543b1..aae08f686633 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -38,5 +38,5 @@ extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk, extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); -extern int inet6_csk_xmit(struct sk_buff *skb, int ipfragok); +extern int inet6_csk_xmit(struct sk_buff *skb); #endif /* _INET6_CONNECTION_SOCK_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 52c8b8b8a0b9..b6d3b55da19b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -36,7 +36,7 @@ struct tcp_congestion_ops; * (i.e. things that depend on the address family) */ struct inet_connection_sock_af_ops { - int (*queue_xmit)(struct sk_buff *skb, int ipfragok); + int (*queue_xmit)(struct sk_buff *skb); void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); int (*conn_request)(struct sock *sk, struct sk_buff *skb); diff --git a/include/net/ip.h b/include/net/ip.h index 503994a38ed1..a84ceb692687 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -101,7 +101,7 @@ extern int ip_do_nat(struct sk_buff *skb); extern void ip_send_check(struct iphdr *ip); extern int __ip_local_out(struct sk_buff *skb); extern int ip_local_out(struct sk_buff *skb); -extern int ip_queue_xmit(struct sk_buff *skb, int ipfragok); +extern int ip_queue_xmit(struct sk_buff *skb); extern void ip_init(void); extern int ip_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 033ddd4652a5..b1d8db90b214 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -482,8 +482,7 @@ extern int ip6_rcv_finish(struct sk_buff *skb); extern int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct ipv6_txoptions *opt, - int ipfragok); + struct ipv6_txoptions *opt); extern int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, -- cgit v1.2.2 From fec5e652e58fa6017b2c9e06466cb2a6538de5b4 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 16 Apr 2010 16:01:27 -0700 Subject: rfs: Receive Flow Steering This patch implements receive flow steering (RFS). RFS steers received packets for layer 3 and 4 processing to the CPU where the application for the corresponding flow is running. RFS is an extension of Receive Packet Steering (RPS). The basic idea of RFS is that when an application calls recvmsg (or sendmsg) the application's running CPU is stored in a hash table that is indexed by the connection's rxhash which is stored in the socket structure. The rxhash is passed in skb's received on the connection from netif_receive_skb. For each received packet, the associated rxhash is used to look up the CPU in the hash table, if a valid CPU is set then the packet is steered to that CPU using the RPS mechanisms. The convolution of the simple approach is that it would potentially allow OOO packets. If threads are thrashing around CPUs or multiple threads are trying to read from the same sockets, a quickly changing CPU value in the hash table could cause rampant OOO packets-- we consider this a non-starter. To avoid OOO packets, this solution implements two types of hash tables: rps_sock_flow_table and rps_dev_flow_table. rps_sock_table is a global hash table. Each entry is just a CPU number and it is populated in recvmsg and sendmsg as described above. This table contains the "desired" CPUs for flows. rps_dev_flow_table is specific to each device queue. Each entry contains a CPU and a tail queue counter. The CPU is the "current" CPU for a matching flow. The tail queue counter holds the value of a tail queue counter for the associated CPU's backlog queue at the time of last enqueue for a flow matching the entry. Each backlog queue has a queue head counter which is incremented on dequeue, and so a queue tail counter is computed as queue head count + queue length. When a packet is enqueued on a backlog queue, the current value of the queue tail counter is saved in the hash entry of the rps_dev_flow_table. And now the trick: when selecting the CPU for RPS (get_rps_cpu) the rps_sock_flow table and the rps_dev_flow table for the RX queue are consulted. When the desired CPU for the flow (found in the rps_sock_flow table) does not match the current CPU (found in the rps_dev_flow table), the current CPU is changed to the desired CPU if one of the following is true: - The current CPU is unset (equal to RPS_NO_CPU) - Current CPU is offline - The current CPU's queue head counter >= queue tail counter in the rps_dev_flow table. This checks if the queue tail has advanced beyond the last packet that was enqueued using this table entry. This guarantees that all packets queued using this entry have been dequeued, thus preserving in order delivery. Making each queue have its own rps_dev_flow table has two advantages: 1) the tail queue counters will be written on each receive, so keeping the table local to interrupting CPU s good for locality. 2) this allows lockless access to the table-- the CPU number and queue tail counter need to be accessed together under mutual exclusion from netif_receive_skb, we assume that this is only called from device napi_poll which is non-reentrant. This patch implements RFS for TCP and connected UDP sockets. It should be usable for other flow oriented protocols. There are two configuration parameters for RFS. The "rps_flow_entries" kernel init parameter sets the number of entries in the rps_sock_flow_table, the per rxqueue sysfs entry "rps_flow_cnt" contains the number of entries in the rps_dev_flow table for the rxqueue. Both are rounded to power of two. The obvious benefit of RFS (over just RPS) is that it achieves CPU locality between the receive processing for a flow and the applications processing; this can result in increased performance (higher pps, lower latency). The benefits of RFS are dependent on cache hierarchy, application load, and other factors. On simple benchmarks, we don't necessarily see improvement and sometimes see degradation. However, for more complex benchmarks and for applications where cache pressure is much higher this technique seems to perform very well. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. The RPC test is an request/response test similar in structure to netperf RR test ith 100 threads on each host, but does more work in userspace that netperf. e1000e on 8 core Intel No RFS or RPS 104K tps at 30% CPU No RFS (best RPS config): 290K tps at 63% CPU RFS 303K tps at 61% CPU RPC test tps CPU% 50/90/99% usec latency Latency StdDev No RFS/RPS 103K 48% 757/900/3185 4472.35 RPS only: 174K 73% 415/993/2468 491.66 RFS 223K 73% 379/651/1382 315.61 Signed-off-by: Tom Herbert Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 69 ++++++++++++++++++++++++++++++++++++++++++++++- include/net/inet_sock.h | 38 ++++++++++++++++++++++++++ 2 files changed, 106 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 55c2086e1f06..649a0252686e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -530,14 +530,73 @@ struct rps_map { }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) +/* + * The rps_dev_flow structure contains the mapping of a flow to a CPU and the + * tail pointer for that CPU's input queue at the time of last enqueue. + */ +struct rps_dev_flow { + u16 cpu; + u16 fill; + unsigned int last_qtail; +}; + +/* + * The rps_dev_flow_table structure contains a table of flow mappings. + */ +struct rps_dev_flow_table { + unsigned int mask; + struct rcu_head rcu; + struct work_struct free_work; + struct rps_dev_flow flows[0]; +}; +#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ + (_num * sizeof(struct rps_dev_flow))) + +/* + * The rps_sock_flow_table contains mappings of flows to the last CPU + * on which they were processed by the application (set in recvmsg). + */ +struct rps_sock_flow_table { + unsigned int mask; + u16 ents[0]; +}; +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \ + (_num * sizeof(u16))) + +#define RPS_NO_CPU 0xffff + +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + if (table && hash) { + unsigned int cpu, index = hash & table->mask; + + /* We only give a hint, preemption can change cpu under us */ + cpu = raw_smp_processor_id(); + + if (table->ents[index] != cpu) + table->ents[index] = cpu; + } +} + +static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + if (table && hash) + table->ents[hash & table->mask] = RPS_NO_CPU; +} + +extern struct rps_sock_flow_table *rps_sock_flow_table; + /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { struct rps_map *rps_map; + struct rps_dev_flow_table *rps_flow_table; struct kobject kobj; struct netdev_rx_queue *first; atomic_t count; } ____cacheline_aligned_in_smp; -#endif +#endif /* CONFIG_RPS */ /* * This structure defines the management hooks for network devices. @@ -1333,11 +1392,19 @@ struct softnet_data { /* Elements below can be accessed between CPUs for RPS */ #ifdef CONFIG_RPS struct call_single_data csd ____cacheline_aligned_in_smp; + unsigned int input_queue_head; #endif struct sk_buff_head input_pkt_queue; struct napi_struct backlog; }; +static inline void incr_input_queue_head(struct softnet_data *queue) +{ +#ifdef CONFIG_RPS + queue->input_queue_head++; +#endif +} + DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); #define HAVE_NETIF_QUEUE diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 83fd34437cf1..b487bc1b99ab 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -101,6 +102,7 @@ struct rtable; * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts + * @rxhash - flow hash received from netif layer * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? @@ -124,6 +126,9 @@ struct inet_sock { __u16 cmsg_flags; __be16 inet_sport; __u16 inet_id; +#ifdef CONFIG_RPS + __u32 rxhash; +#endif struct ip_options *opt; __u8 tos; @@ -219,4 +224,37 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; } +static inline void inet_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_record_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); + rcu_read_unlock(); +#endif +} + +static inline void inet_rps_reset_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_reset_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); + rcu_read_unlock(); +#endif +} + +static inline void inet_rps_save_rxhash(const struct sock *sk, u32 rxhash) +{ +#ifdef CONFIG_RPS + if (unlikely(inet_sk(sk)->rxhash != rxhash)) { + inet_rps_reset_flow(sk); + inet_sk(sk)->rxhash = rxhash; + } +#endif +} #endif /* _INET_SOCK_H */ -- cgit v1.2.2 From 88751275b8e867d756e4f86ae92afe0232de129f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Apr 2010 05:07:33 +0000 Subject: rps: shortcut net_rps_action() net_rps_action() is a bit expensive on NR_CPUS=64..4096 kernels, even if RPS is not active. Tom Herbert used two bitmasks to hold information needed to send IPI, but a single LIFO list seems more appropriate. Move all RPS logic into net_rps_action() to cleanup net_rx_action() code (remove two ifdefs) Move rps_remote_softirq_cpus into softnet_data to share its first cache line, filling an existing hole. In a future patch, we could call net_rps_action() from process_backlog() to make sure we send IPI before handling this cpu backlog. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 649a0252686e..83ab3da149ad 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1381,17 +1381,20 @@ static inline int unregister_gifconf(unsigned int family) } /* - * Incoming packets are placed on per-cpu queues so that - * no locking is needed. + * Incoming packets are placed on per-cpu queues */ struct softnet_data { struct Qdisc *output_queue; struct list_head poll_list; struct sk_buff *completion_queue; - /* Elements below can be accessed between CPUs for RPS */ #ifdef CONFIG_RPS + struct softnet_data *rps_ipi_list; + + /* Elements below can be accessed between CPUs for RPS */ struct call_single_data csd ____cacheline_aligned_in_smp; + struct softnet_data *rps_ipi_next; + unsigned int cpu; unsigned int input_queue_head; #endif struct sk_buff_head input_pkt_queue; -- cgit v1.2.2 From e36fa2f7e92f25aab2e3d787dcfe3590817f19d3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Apr 2010 21:17:14 +0000 Subject: rps: cleanups struct softnet_data holds many queues, so consistent use "sd" name instead of "queue" is better. Adds a rps_ipi_queued() helper to cleanup enqueue_to_backlog() Adds a _and_irq_disable suffix to net_rps_action() name, as David suggested. incr_input_queue_head() becomes input_queue_head_incr() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 83ab3da149ad..3c5ed5f5274e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1401,10 +1401,10 @@ struct softnet_data { struct napi_struct backlog; }; -static inline void incr_input_queue_head(struct softnet_data *queue) +static inline void input_queue_head_incr(struct softnet_data *sd) { #ifdef CONFIG_RPS - queue->input_queue_head++; + sd->input_queue_head++; #endif } -- cgit v1.2.2