From 9a4b9708f1f2eaf5edd619df578cf3afec36eb82 Mon Sep 17 00:00:00 2001 From: Matti Linnanvuori Date: Thu, 8 Nov 2007 08:37:38 -0800 Subject: module: fix and elaborate comments Fix and elaborate comments. Signed-off-by: Matti Linnanvuori Signed-off-by: Rusty Russell --- kernel/module.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 3202c99500..91fe6958b6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -81,7 +81,8 @@ int unregister_module_notifier(struct notifier_block * nb) } EXPORT_SYMBOL(unregister_module_notifier); -/* We require a truly strong try_module_get() */ +/* We require a truly strong try_module_get(): 0 means failure due to + ongoing or failed initialization etc. */ static inline int strong_try_module_get(struct module *mod) { if (mod && mod->state == MODULE_STATE_COMING) @@ -952,7 +953,8 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs, ret = __find_symbol(name, &owner, &crc, !(mod->taints & TAINT_PROPRIETARY_MODULE)); if (ret) { - /* use_module can fail due to OOM, or module unloading */ + /* use_module can fail due to OOM, + or module initialization or unloading */ if (!check_version(sechdrs, versindex, name, mod, crc) || !use_module(mod, owner)) ret = 0; @@ -1369,7 +1371,7 @@ dup: return ret; } -/* Change all symbols so that sh_value encodes the pointer directly. */ +/* Change all symbols so that st_value encodes the pointer directly. */ static int simplify_symbols(Elf_Shdr *sechdrs, unsigned int symindex, const char *strtab, -- cgit v1.2.2 From 611cd55b155a89d9a0ce5f92a9cbabc5e284d0d4 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 19 Nov 2007 21:49:25 -0800 Subject: [IPVS]: Fix sysctl warnings about missing strategy Running the latest git code I get the following messages during boot: sysctl table check failed: /net/ipv4/vs/drop_entry .3.5.21.4 Missing strategy [...] sysctl table check failed: /net/ipv4/vs/drop_packet .3.5.21.5 Missing strategy [...] sysctl table check failed: /net/ipv4/vs/secure_tcp .3.5.21.6 Missing strategy [...] sysctl table check failed: /net/ipv4/vs/sync_threshold .3.5.21.24 Missing strategy I removed the binary sysctl handler for those messages and also removed the definitions in ip_vs.h. The alternative would be to implement a proper strategy handler, but syscall sysctl is deprecated. There are other sysctl definitions that are commented out or work with the default sysctl_data strategy. I did not touch these. Signed-off-by: Christian Borntraeger Acked-by: Simon Horman Signed-off-by: David S. Miller --- kernel/sysctl_check.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index 4abc6d2306..9e17497603 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -242,9 +242,6 @@ static struct trans_ctl_table trans_net_ipv4_vs_table[] = { { NET_IPV4_VS_AMEMTHRESH, "amemthresh" }, { NET_IPV4_VS_DEBUG_LEVEL, "debug_level" }, { NET_IPV4_VS_AMDROPRATE, "am_droprate" }, - { NET_IPV4_VS_DROP_ENTRY, "drop_entry" }, - { NET_IPV4_VS_DROP_PACKET, "drop_packet" }, - { NET_IPV4_VS_SECURE_TCP, "secure_tcp" }, { NET_IPV4_VS_TO_ES, "timeout_established" }, { NET_IPV4_VS_TO_SS, "timeout_synsent" }, { NET_IPV4_VS_TO_SR, "timeout_synrecv" }, @@ -260,7 +257,6 @@ static struct trans_ctl_table trans_net_ipv4_vs_table[] = { { NET_IPV4_VS_CACHE_BYPASS, "cache_bypass" }, { NET_IPV4_VS_EXPIRE_NODEST_CONN, "expire_nodest_conn" }, { NET_IPV4_VS_EXPIRE_QUIESCENT_TEMPLATE, "expire_quiescent_template" }, - { NET_IPV4_VS_SYNC_THRESHOLD, "sync_threshold" }, { NET_IPV4_VS_NAT_ICMP_SEND, "nat_icmp_send" }, { NET_IPV4_VS_LBLC_EXPIRE, "lblc_expiration" }, { NET_IPV4_VS_LBLCR_EXPIRE, "lblcr_expiration" }, -- cgit v1.2.2 From 9e103fa6bd53147e228e941256803a6b8927cdb9 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 19 Nov 2007 21:50:21 -0800 Subject: [IPVS]: Fix sysctl warnings about missing strategy in schedulers sysctl table check failed: /net/ipv4/vs/lblc_expiration .3.5.21.19 Missing strategy [...] sysctl table check failed: /net/ipv4/vs/lblcr_expiration .3.5.21.20 Missing strategy Switch these entried over to use CTL_UNNUMBERED as clearly the sys_syscal portion wasn't working. This is along the same lines as Christian Borntraeger's patch that fixes up entries with no stratergy in net/ipv4/ipvs/ip_vs_ctl.c Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- kernel/sysctl_check.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index 9e17497603..cffb4adf13 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -258,8 +258,6 @@ static struct trans_ctl_table trans_net_ipv4_vs_table[] = { { NET_IPV4_VS_EXPIRE_NODEST_CONN, "expire_nodest_conn" }, { NET_IPV4_VS_EXPIRE_QUIESCENT_TEMPLATE, "expire_quiescent_template" }, { NET_IPV4_VS_NAT_ICMP_SEND, "nat_icmp_send" }, - { NET_IPV4_VS_LBLC_EXPIRE, "lblc_expiration" }, - { NET_IPV4_VS_LBLCR_EXPIRE, "lblcr_expiration" }, {} }; -- cgit v1.2.2 From 9055fa1f3ded5ad858a55ae18439ed55227ee7eb Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 19 Nov 2007 21:51:13 -0800 Subject: [IPVS]: Move remaining sysctl handlers over to CTL_UNNUMBERED Switch the remaining IPVS sysctl entries over to to use CTL_UNNUMBERED, I stronly doubt that anyone is using the sys_sysctl interface to these variables. Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- kernel/sysctl_check.c | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index cffb4adf13..fdfca0dd99 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -237,30 +237,6 @@ static struct trans_ctl_table trans_net_ipv4_conf_table[] = { {} }; - -static struct trans_ctl_table trans_net_ipv4_vs_table[] = { - { NET_IPV4_VS_AMEMTHRESH, "amemthresh" }, - { NET_IPV4_VS_DEBUG_LEVEL, "debug_level" }, - { NET_IPV4_VS_AMDROPRATE, "am_droprate" }, - { NET_IPV4_VS_TO_ES, "timeout_established" }, - { NET_IPV4_VS_TO_SS, "timeout_synsent" }, - { NET_IPV4_VS_TO_SR, "timeout_synrecv" }, - { NET_IPV4_VS_TO_FW, "timeout_finwait" }, - { NET_IPV4_VS_TO_TW, "timeout_timewait" }, - { NET_IPV4_VS_TO_CL, "timeout_close" }, - { NET_IPV4_VS_TO_CW, "timeout_closewait" }, - { NET_IPV4_VS_TO_LA, "timeout_lastack" }, - { NET_IPV4_VS_TO_LI, "timeout_listen" }, - { NET_IPV4_VS_TO_SA, "timeout_synack" }, - { NET_IPV4_VS_TO_UDP, "timeout_udp" }, - { NET_IPV4_VS_TO_ICMP, "timeout_icmp" }, - { NET_IPV4_VS_CACHE_BYPASS, "cache_bypass" }, - { NET_IPV4_VS_EXPIRE_NODEST_CONN, "expire_nodest_conn" }, - { NET_IPV4_VS_EXPIRE_QUIESCENT_TEMPLATE, "expire_quiescent_template" }, - { NET_IPV4_VS_NAT_ICMP_SEND, "nat_icmp_send" }, - {} -}; - static struct trans_ctl_table trans_net_neigh_vars_table[] = { { NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" }, { NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" }, @@ -335,7 +311,6 @@ static struct trans_ctl_table trans_net_ipv4_table[] = { { NET_IPV4_ROUTE, "route", trans_net_ipv4_route_table }, /* NET_IPV4_FIB_HASH unused */ { NET_IPV4_NETFILTER, "netfilter", trans_net_ipv4_netfilter_table }, - { NET_IPV4_VS, "vs", trans_net_ipv4_vs_table }, { NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" }, { NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" }, -- cgit v1.2.2 From 43ebbf119a9670d8f08b9e57968e109c770f8636 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 20 Nov 2007 11:13:33 +0100 Subject: [S390] cmm: remove unused binary sysctls. Remove binary sysctls that never worked due to missing strategy functions. Cc: Christian Borntraeger Signed-off-by: Heiko Carstens Signed-off-by: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Martin Schwidefsky --- kernel/sysctl_check.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index 4abc6d2306..cde6d780b0 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -140,9 +140,6 @@ static struct trans_ctl_table trans_vm_table[] = { { VM_PANIC_ON_OOM, "panic_on_oom" }, { VM_VDSO_ENABLED, "vdso_enabled" }, { VM_MIN_SLAB, "min_slab_ratio" }, - { VM_CMM_PAGES, "cmm_pages" }, - { VM_CMM_TIMED_PAGES, "cmm_timed_pages" }, - { VM_CMM_TIMEOUT, "cmm_timeout" }, {} }; -- cgit v1.2.2 From 37e3a6ac5a30468021a2f366e497d455bbcb5d21 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 20 Nov 2007 11:13:34 +0100 Subject: [S390] appldata: remove unused binary sysctls. Remove binary sysctls that never worked due to missing strategy functions. Cc: "Eric W. Biederman" Cc: Christian Borntraeger Cc: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- kernel/sysctl_check.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index cde6d780b0..8f5baac1eb 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -1216,16 +1216,6 @@ static struct trans_ctl_table trans_arlan_table[] = { {} }; -static struct trans_ctl_table trans_appldata_table[] = { - { CTL_APPLDATA_TIMER, "timer" }, - { CTL_APPLDATA_INTERVAL, "interval" }, - { CTL_APPLDATA_OS, "os" }, - { CTL_APPLDATA_NET_SUM, "net_sum" }, - { CTL_APPLDATA_MEM, "mem" }, - {} - -}; - static struct trans_ctl_table trans_s390dbf_table[] = { { 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" }, { 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" }, @@ -1270,7 +1260,6 @@ static struct trans_ctl_table trans_root_table[] = { { CTL_ABI, "abi" }, /* CTL_CPU not used */ { CTL_ARLAN, "arlan", trans_arlan_table }, - { CTL_APPLDATA, "appldata", trans_appldata_table }, { CTL_S390DBF, "s390dbf", trans_s390dbf_table }, { CTL_SUNRPC, "sunrpc", trans_sunrpc_table }, { CTL_PM, "pm", trans_pm_table }, -- cgit v1.2.2 From 52bfb36050c8529d9031d2c2513b281a360922ec Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 26 Nov 2007 20:42:19 +0100 Subject: time: add ADJ_OFFSET_SS_READ Michael Kerrisk reported that a long standing bug in the adjtimex() system call causes glibc's adjtime(3) function to deliver the wrong results if 'delta' is NULL. add the ADJ_OFFSET_SS_READ API detail, which will be used by glibc to fix this API compatibility bug. Also see: http://bugzilla.kernel.org/show_bug.cgi?id=6761 [ mingo@elte.hu: added patch description and made it backwards compatible ] NOTE: the new flag is defined 0xa001 so that it returns -EINVAL on older kernels - this way glibc can use it safely. Suggested by Ulrich Drepper. Acked-by: Ulrich Drepper Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- kernel/time/ntp.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 14a2ecf2b3..e64efaf957 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -249,10 +249,12 @@ int do_adjtimex(struct timex *txc) /* Now we validate the data before disabling interrupts */ - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) + if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) { /* singleshot must not be used with any other mode bits */ - if (txc->modes != ADJ_OFFSET_SINGLESHOT) + if (txc->modes != ADJ_OFFSET_SINGLESHOT && + txc->modes != ADJ_OFFSET_SS_READ) return -EINVAL; + } if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET)) /* adjustment Offset limited to +- .512 seconds */ @@ -372,7 +374,8 @@ int do_adjtimex(struct timex *txc) leave: if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0) result = TIME_ERROR; - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) + if ((txc->modes == ADJ_OFFSET_SINGLESHOT) || + (txc->modes == ADJ_OFFSET_SS_READ)) txc->offset = save_adjust; else txc->offset = ((long)shift_right(time_offset, SHIFT_UPDATE)) * -- cgit v1.2.2 From 5e8869bb699d50be5c0733edfc71cfcd5b43e10a Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 26 Nov 2007 21:21:49 +0100 Subject: sched: don't forget to unlock uids_mutex on error paths The commit commit 5cb350baf580017da38199625b7365b1763d7180 Author: Dhaval Giani Date: Mon Oct 15 17:00:14 2007 +0200 sched: group scheduling, sysfs tunables introduced the uids_mutex and the helpers to lock/unlock it. Unfortunately, the error paths of alloc_uid() were not patched to unlock it. Signed-off-by: Pavel Emelyanov Acked-by: Dhaval Giani Signed-off-by: Ingo Molnar --- kernel/user.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/user.c b/kernel/user.c index 0f3aa02341..8320a87f3e 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -337,8 +337,11 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid) struct user_struct *new; new = kmem_cache_alloc(uid_cachep, GFP_KERNEL); - if (!new) + if (!new) { + uids_mutex_unlock(); return NULL; + } + new->uid = uid; atomic_set(&new->__count, 1); atomic_set(&new->processes, 0); @@ -355,6 +358,7 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid) if (alloc_uid_keyring(new, current) < 0) { kmem_cache_free(uid_cachep, new); + uids_mutex_unlock(); return NULL; } @@ -362,6 +366,7 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid) key_put(new->uid_keyring); key_put(new->session_keyring); kmem_cache_free(uid_cachep, new); + uids_mutex_unlock(); return NULL; } -- cgit v1.2.2 From bcbe4a076609e15ea84cbebd9cd8f317ed70ce92 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 26 Nov 2007 21:21:49 +0100 Subject: sched: fix kernel/acct.c comment fix kernel/acct.c comment. noticed by Lin Tan. Comment suggested by Olaf Kirch. also see: http://bugzilla.kernel.org/show_bug.cgi?id=8220 Reported-by: tammy000@gmail.com Signed-off-by: Ingo Molnar --- kernel/acct.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/acct.c b/kernel/acct.c index fce53d8df8..cf19547cc9 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -413,7 +413,7 @@ static u32 encode_float(u64 value) * The acct_process() call is the workhorse of the process * accounting system. The struct acct is built here and then written * into the accounting file. This function should only be called from - * do_exit(). + * do_exit() or when switching to a different output file. */ /* -- cgit v1.2.2 From 722aab0c3bbd7648d66790515c14d95d10a15bf3 Mon Sep 17 00:00:00 2001 From: Zou Nan hai Date: Mon, 26 Nov 2007 21:21:49 +0100 Subject: sched: fix minimum granularity tunings increase the default minimum granularity some more - this gives us more performance in aim7 benchmarks. also correct some comments: we scale with ilog(ncpus) + 1. Signed-off-by: Zou Nan hai Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index ee00da284b..2f16e15c02 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -22,7 +22,7 @@ /* * Targeted preemption latency for CPU-bound tasks: - * (default: 20ms * ilog(ncpus), units: nanoseconds) + * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds) * * NOTE: this latency value is not the same as the concept of * 'timeslice length' - timeslices in CFS are of variable length @@ -36,14 +36,14 @@ unsigned int sysctl_sched_latency = 20000000ULL; /* * Minimal preemption granularity for CPU-bound tasks: - * (default: 1 msec * ilog(ncpus), units: nanoseconds) + * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_min_granularity = 1000000ULL; +unsigned int sysctl_sched_min_granularity = 4000000ULL; /* * is kept at sysctl_sched_latency / sysctl_sched_min_granularity */ -static unsigned int sched_nr_latency = 20; +static unsigned int sched_nr_latency = 5; /* * After fork, child runs first. (default) If set to 0 then @@ -61,7 +61,7 @@ unsigned int __read_mostly sysctl_sched_compat_yield; /* * SCHED_BATCH wake-up granularity. - * (default: 10 msec * ilog(ncpus), units: nanoseconds) + * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still @@ -71,7 +71,7 @@ unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL; /* * SCHED_OTHER wake-up granularity. - * (default: 10 msec * ilog(ncpus), units: nanoseconds) + * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still -- cgit v1.2.2 From f7b9329e556a8bdb9e07292cddbbe484c7a2b8c5 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 26 Nov 2007 21:21:49 +0100 Subject: sched: bump version of kernel/sched_debug.c bump version of kernel/sched_debug.c and remove CFS version information from it. Signed-off-by: Ingo Molnar --- kernel/sched_debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index ca198a797b..5d0d623a54 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -199,7 +199,7 @@ static int sched_debug_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Sched Debug Version: v0.06-v22, %s %.*s\n", + SEQ_printf(m, "Sched Debug Version: v0.07, %s %.*s\n", init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); -- cgit v1.2.2 From d3938204468dccae16be0099a2abf53db4ed0505 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 28 Nov 2007 15:52:56 +0100 Subject: softlockup: fix false positives on CONFIG_NOHZ David Miller reported soft lockup false-positives that trigger on NOHZ due to CPUs idling for more than 10 seconds. The solution is touch the softlockup watchdog when we return from idle. (by definition we are not 'locked up' when we were idle) http://bugzilla.kernel.org/show_bug.cgi?id=9409 Reported-by: David Miller Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/time/tick-sched.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 27a2338deb..cb89fa8db1 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -133,6 +133,8 @@ void tick_nohz_update_jiffies(void) if (!ts->tick_stopped) return; + touch_softlockup_watchdog(); + cpu_clear(cpu, nohz_cpu_mask); now = ktime_get(); -- cgit v1.2.2 From 9a4e715914f07e56cbfa6f2b544a68365d51c3ef Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 28 Nov 2007 15:52:56 +0100 Subject: sched: clean up sd_alloc_ctl_cpu_table() definition clean up sd_alloc_ctl_cpu_table() definition. Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 38933cafea..89cb2dac8b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5466,7 +5466,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) return table; } -static ctl_table * sd_alloc_ctl_cpu_table(int cpu) +static ctl_table *sd_alloc_ctl_cpu_table(int cpu) { struct ctl_table *entry, *table; struct sched_domain *sd; -- cgit v1.2.2 From deaf2227ddf657a260e923db44b6f0974d9bb782 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 28 Nov 2007 15:52:56 +0100 Subject: sched: clean up, move __sched_text_start/end to sched.h move __sched_text_start/end to sched.h. No code changed: text data bss dec hex filename 26582 2310 28 28920 70f8 sched.o.before 26582 2310 28 28920 70f8 sched.o.after Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 89cb2dac8b..98dcdf272d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6708,9 +6708,6 @@ void __init sched_init_smp(void) int in_sched_functions(unsigned long addr) { - /* Linker adds these: start and end of __sched functions */ - extern char __sched_text_start[], __sched_text_end[]; - return in_lock_functions(addr) || (addr >= (unsigned long)__sched_text_start && addr < (unsigned long)__sched_text_end); -- cgit v1.2.2 From c1a89740da168d3431f2f4e7c3b03daacbb55be1 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 28 Nov 2007 15:52:56 +0100 Subject: sched: clean up overlong line in kernel/sched_debug.c clean up overlong line in kernel/sched_debug.c. Signed-off-by: Ingo Molnar --- kernel/sched_debug.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 5d0d623a54..d30467b47d 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -327,10 +327,12 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) avg_atom = -1LL; avg_per_cpu = p->se.sum_exec_runtime; - if (p->se.nr_migrations) - avg_per_cpu = div64_64(avg_per_cpu, p->se.nr_migrations); - else + if (p->se.nr_migrations) { + avg_per_cpu = div64_64(avg_per_cpu, + p->se.nr_migrations); + } else { avg_per_cpu = -1LL; + } __PN(avg_atom); __PN(avg_per_cpu); -- cgit v1.2.2 From f95e0d1c2ad668c77aa4b272c076faf3aa0d631c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 28 Nov 2007 15:52:56 +0100 Subject: sched: clean up kernel/sched_stat.h clean up kernel/sched_stat.h. Signed-off-by: Ingo Molnar --- kernel/sched_stats.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 630178e53b..5b32433e7e 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -52,7 +52,8 @@ static int show_schedstat(struct seq_file *seq, void *v) sd->lb_nobusyq[itype], sd->lb_nobusyg[itype]); } - seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u %u\n", + seq_printf(seq, + " %u %u %u %u %u %u %u %u %u %u %u %u\n", sd->alb_count, sd->alb_failed, sd->alb_pushed, sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed, sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed, -- cgit v1.2.2 From c895078355b6b6e05c60aa205892526dd3390f0a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 28 Nov 2007 16:21:24 -0800 Subject: wait_task_stopped(): don't use task_pid_nr_ns() lockless wait_task_stopped(WNOWAIT) does task_pid_nr_ns() without tasklist/rcu lock, we can read an already freed memory. Use the cached pid_t value. Signed-off-by: Oleg Nesterov Looks-good-to: Roland McGrath Acked-by: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index cd0f1d4137..0a4a382ecf 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1357,7 +1357,7 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, int __user *stat_addr, struct rusage __user *ru) { int retval, exit_code; - struct pid_namespace *ns; + pid_t pid; if (!p->exit_code) return 0; @@ -1376,12 +1376,11 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, * keep holding onto the tasklist_lock while we call getrusage and * possibly take page faults for user memory. */ - ns = current->nsproxy->pid_ns; + pid = task_pid_nr_ns(p, current->nsproxy->pid_ns); get_task_struct(p); read_unlock(&tasklist_lock); if (unlikely(noreap)) { - pid_t pid = task_pid_nr_ns(p, ns); uid_t uid = p->uid; int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED; @@ -1451,11 +1450,11 @@ bail_ref: if (!retval && infop) retval = put_user(exit_code, &infop->si_status); if (!retval && infop) - retval = put_user(task_pid_nr_ns(p, ns), &infop->si_pid); + retval = put_user(pid, &infop->si_pid); if (!retval && infop) retval = put_user(p->uid, &infop->si_uid); if (!retval) - retval = task_pid_nr_ns(p, ns); + retval = pid; put_task_struct(p); BUG_ON(!retval); -- cgit v1.2.2 From 32df81cbd5b41d281cc3d7e7ff6a98ac6201e197 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 28 Nov 2007 16:21:38 -0800 Subject: Isolate the UTS namespace's domainname and hostname back Commit 7d69a1f4a72b18876c99c697692b78339d491568 ("remove CONFIG_UTS_NS and CONFIG_IPC_NS") by Cedric Le Goater accidentally removed the code that prevented the uts->hostname and uts->domainname values from being overwritten from another namespace. In other words, setting hostname/domainname via sysfs (echo xxx > /proc/sys/kernel/(host|domain)name) cased the new value to be set in init UTS namespace only. Return the isolation back. Signed-off-by: Pavel Emelyanov Acked-by: Cedric Le Goater Acked-by: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/utsname_sysctl.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index c76c06466b..fe3a56c225 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -18,6 +18,10 @@ static void *get_uts(ctl_table *table, int write) { char *which = table->data; + struct uts_namespace *uts_ns; + + uts_ns = current->nsproxy->uts_ns; + which = (which - (char *)&init_uts_ns) + (char *)uts_ns; if (!write) down_read(&uts_sem); -- cgit v1.2.2 From 9e6c1e633355b69803094ecbac4cecc96e00965c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 28 Nov 2007 16:22:04 -0800 Subject: FRV: fix the extern declaration of kallsyms_num_syms Fix the extern declaration of kallsyms_num_syms to indicate that the symbol does not reside in the small-data storage space, and so may not be accessed relative to the small data base register. Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kallsyms.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 474219a419..2fc2581050 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -32,9 +32,14 @@ /* These will be re-linked against their real values during the second link stage */ extern const unsigned long kallsyms_addresses[] __attribute__((weak)); -extern const unsigned long kallsyms_num_syms __attribute__((weak)); extern const u8 kallsyms_names[] __attribute__((weak)); +/* tell the compiler that the count isn't in the small data section if the arch + * has one (eg: FRV) + */ +extern const unsigned long kallsyms_num_syms +__attribute__((weak, section(".rodata"))); + extern const u8 kallsyms_token_table[] __attribute__((weak)); extern const u16 kallsyms_token_index[] __attribute__((weak)); -- cgit v1.2.2 From e6ceb32aa25fc33f21af84cc7a32fe289b3e860c Mon Sep 17 00:00:00 2001 From: Scott James Remnant Date: Wed, 28 Nov 2007 16:22:07 -0800 Subject: wait_task_stopped(): pass correct exit_code to wait_noreap_copyout() In wait_task_stopped() exit_code already contains the right value for the si_status member of siginfo, and this is simply set in the non WNOWAIT case. If you call waitid() with a stopped or traced process, you'll get the signal in siginfo.si_status as expected -- however if you call waitid(WNOWAIT) at the same time, you'll get the signal << 8 | 0x7f Pass it unchanged to wait_noreap_copyout(); we would only need to shift it and add 0x7f if we were returning it in the user status field and that isn't used for any function that permits WNOWAIT. Signed-off-by: Scott James Remnant Signed-off-by: Oleg Nesterov Cc: Roland McGrath Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index 0a4a382ecf..549c0558ba 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1388,7 +1388,7 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, if (unlikely(!exit_code) || unlikely(p->exit_state)) goto bail_ref; return wait_noreap_copyout(p, pid, uid, - why, (exit_code << 8) | 0x7f, + why, exit_code, infop, ru); } -- cgit v1.2.2