From 4446a36ff8c74ac3b32feb009b651048e129c6af Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 12 May 2008 21:21:05 +0200 Subject: rcu: add call_rcu_sched() Fourth cut of patch to provide the call_rcu_sched(). This is again to synchronize_sched() as call_rcu() is to synchronize_rcu(). Should be fine for experimental and -rt use, but not ready for inclusion. With some luck, I will be able to tell Andrew to come out of hiding on the next round. Passes multi-day rcutorture sessions with concurrent CPU hotplugging. Fixes since the first version include a bug that could result in indefinite blocking (spotted by Gautham Shenoy), better resiliency against CPU-hotplug operations, and other minor fixes. Fixes since the second version include reworking grace-period detection to avoid deadlocks that could happen when running concurrently with CPU hotplug, adding Mathieu's fix to avoid the softlockup messages, as well as Mathieu's fix to allow use earlier in boot. Fixes since the third version include a wrong-CPU bug spotted by Andrew, getting rid of the obsolete synchronize_kernel API that somehow snuck back in, merging spin_unlock() and local_irq_restore() in a few places, commenting the code that checks for quiescent states based on interrupting from user-mode execution or the idle loop, removing some inline attributes, and some code-style changes. Known/suspected shortcomings: o I still do not entirely trust the sleep/wakeup logic. Next step will be to use a private snapshot of the CPU online mask in rcu_sched_grace_period() -- if the CPU wasn't there at the start of the grace period, we don't need to hear from it. And the bit about accounting for changes in online CPUs inside of rcu_sched_grace_period() is ugly anyway. o It might be good for rcu_sched_grace_period() to invoke resched_cpu() when a given CPU wasn't responding quickly, but resched_cpu() is declared static... This patch also fixes a long-standing bug in the earlier preemptable-RCU implementation of synchronize_rcu() that could result in loss of concurrent external changes to a task's CPU affinity mask. I still cannot remember who reported this... Signed-off-by: Paul E. McKenney Signed-off-by: Mathieu Desnoyers Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- init/main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index f7fb20021d48..a9cc3e0803de 100644 --- a/init/main.c +++ b/init/main.c @@ -758,6 +758,7 @@ static void __init do_initcalls(void) */ static void __init do_basic_setup(void) { + rcu_init_sched(); /* needed by module_init stage. */ /* drivers will send hotplug events */ init_workqueues(); usermodehelper_init(); -- cgit v1.2.3 From 3da757daf86e498872855f0b5e101f763ba79499 Mon Sep 17 00:00:00 2001 From: Alok Kataria Date: Fri, 20 Jun 2008 15:06:33 -0700 Subject: x86: use cpu_khz for loops_per_jiffy calculation On the x86 platform we can use the value of tsc_khz computed during tsc calibration to calculate the loops_per_jiffy value. Its very important to keep the error in lpj values to minimum as any error in that may result in kernel panic in check_timer. In virtualization environment, On a highly overloaded host the guest delay calibration may sometimes result in errors beyond the ~50% that timer_irq_works can handle, resulting in the guest panicking. Does some formating changes to lpj_setup code to now have a single printk to print the bogomips value. We do this only for the boot processor because the AP's can have different base frequencies or the BIOS might boot a AP at a different frequency. Signed-off-by: Alok N Kataria Cc: Arjan van de Ven Cc: Daniel Hecht Cc: Tim Mann Cc: Zach Amsden Cc: Sahil Rihan Signed-off-by: Ingo Molnar --- init/calibrate.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) (limited to 'init') diff --git a/init/calibrate.c b/init/calibrate.c index ecb3822d4f70..86286974dada 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -8,7 +8,9 @@ #include #include #include +#include +unsigned long lpj_tsc; unsigned long preset_lpj; static int __init lpj_setup(char *str) { @@ -108,6 +110,10 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;} * This is the number of bits of precision for the loops_per_jiffy. Each * bit takes on average 1.5/HZ seconds. This (like the original) is a little * better than 1% + * For the boot cpu we can skip the delay calibration and assign it a value + * calculated based on the tsc frequency. + * For the rest of the CPUs we cannot assume that the tsc frequency is same as + * the cpu frequency, hence do the calibration for those. */ #define LPS_PREC 8 @@ -118,20 +124,20 @@ void __cpuinit calibrate_delay(void) if (preset_lpj) { loops_per_jiffy = preset_lpj; - printk("Calibrating delay loop (skipped)... " - "%lu.%02lu BogoMIPS preset\n", - loops_per_jiffy/(500000/HZ), - (loops_per_jiffy/(5000/HZ)) % 100); + printk(KERN_INFO + "Calibrating delay loop (skipped) preset value.. "); + } else if ((smp_processor_id() == 0) && lpj_tsc) { + loops_per_jiffy = lpj_tsc; + printk(KERN_INFO + "Calibrating delay loop (skipped), " + "using tsc calculated value.. "); } else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) { - printk("Calibrating delay using timer specific routine.. "); - printk("%lu.%02lu BogoMIPS (lpj=%lu)\n", - loops_per_jiffy/(500000/HZ), - (loops_per_jiffy/(5000/HZ)) % 100, - loops_per_jiffy); + printk(KERN_INFO + "Calibrating delay using timer specific routine.. "); } else { loops_per_jiffy = (1<<12); - printk(KERN_DEBUG "Calibrating delay loop... "); + printk(KERN_INFO "Calibrating delay loop... "); while ((loops_per_jiffy <<= 1) != 0) { /* wait for "start of" clock tick */ ticks = jiffies; @@ -161,12 +167,8 @@ void __cpuinit calibrate_delay(void) if (jiffies != ticks) /* longer than 1 tick */ loops_per_jiffy &= ~loopbit; } - - /* Round the value and print it */ - printk("%lu.%02lu BogoMIPS (lpj=%lu)\n", - loops_per_jiffy/(500000/HZ), - (loops_per_jiffy/(5000/HZ)) % 100, - loops_per_jiffy); } - + printk(KERN_INFO "%lu.%02lu BogoMIPS (lpj=%lu)\n", + loops_per_jiffy/(500000/HZ), + (loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy); } -- cgit v1.2.3 From f3f3149f35b9195ef4b761b1353fc0766b5f53be Mon Sep 17 00:00:00 2001 From: Alok Kataria Date: Mon, 23 Jun 2008 18:21:56 -0700 Subject: x86: use cpu_khz for loops_per_jiffy calculation, cleanup As suggested by Ingo, remove all references to tsc from init/calibrate.c TSC is x86 specific, and using tsc in variable names in a generic file should be avoided. lpj_tsc is now called lpj_fine, since it is related to fine tuning of lpj value. Also tsc_rate_* is called timer_rate_* Signed-off-by: Alok N Kataria Cc: Arjan van de Ven Cc: Daniel Hecht Cc: Tim Mann Cc: Zach Amsden Cc: Sahil Rihan Signed-off-by: Ingo Molnar --- init/calibrate.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) (limited to 'init') diff --git a/init/calibrate.c b/init/calibrate.c index 86286974dada..7963e3fc51d9 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -10,7 +10,7 @@ #include #include -unsigned long lpj_tsc; +unsigned long lpj_fine; unsigned long preset_lpj; static int __init lpj_setup(char *str) { @@ -35,9 +35,9 @@ static unsigned long __cpuinit calibrate_delay_direct(void) unsigned long pre_start, start, post_start; unsigned long pre_end, end, post_end; unsigned long start_jiffies; - unsigned long tsc_rate_min, tsc_rate_max; - unsigned long good_tsc_sum = 0; - unsigned long good_tsc_count = 0; + unsigned long timer_rate_min, timer_rate_max; + unsigned long good_timer_sum = 0; + unsigned long good_timer_count = 0; int i; if (read_current_timer(&pre_start) < 0 ) @@ -81,22 +81,24 @@ static unsigned long __cpuinit calibrate_delay_direct(void) } read_current_timer(&post_end); - tsc_rate_max = (post_end - pre_start) / DELAY_CALIBRATION_TICKS; - tsc_rate_min = (pre_end - post_start) / DELAY_CALIBRATION_TICKS; + timer_rate_max = (post_end - pre_start) / + DELAY_CALIBRATION_TICKS; + timer_rate_min = (pre_end - post_start) / + DELAY_CALIBRATION_TICKS; /* - * If the upper limit and lower limit of the tsc_rate is + * If the upper limit and lower limit of the timer_rate is * >= 12.5% apart, redo calibration. */ if (pre_start != 0 && pre_end != 0 && - (tsc_rate_max - tsc_rate_min) < (tsc_rate_max >> 3)) { - good_tsc_count++; - good_tsc_sum += tsc_rate_max; + (timer_rate_max - timer_rate_min) < (timer_rate_max >> 3)) { + good_timer_count++; + good_timer_sum += timer_rate_max; } } - if (good_tsc_count) - return (good_tsc_sum/good_tsc_count); + if (good_timer_count) + return (good_timer_sum/good_timer_count); printk(KERN_WARNING "calibrate_delay_direct() failed to get a good " "estimate for loops_per_jiffy.\nProbably due to long platform interrupts. Consider using \"lpj=\" boot option.\n"); @@ -111,8 +113,8 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;} * bit takes on average 1.5/HZ seconds. This (like the original) is a little * better than 1% * For the boot cpu we can skip the delay calibration and assign it a value - * calculated based on the tsc frequency. - * For the rest of the CPUs we cannot assume that the tsc frequency is same as + * calculated based on the timer frequency. + * For the rest of the CPUs we cannot assume that the timer frequency is same as * the cpu frequency, hence do the calibration for those. */ #define LPS_PREC 8 @@ -126,11 +128,11 @@ void __cpuinit calibrate_delay(void) loops_per_jiffy = preset_lpj; printk(KERN_INFO "Calibrating delay loop (skipped) preset value.. "); - } else if ((smp_processor_id() == 0) && lpj_tsc) { - loops_per_jiffy = lpj_tsc; + } else if ((smp_processor_id() == 0) && lpj_fine) { + loops_per_jiffy = lpj_fine; printk(KERN_INFO "Calibrating delay loop (skipped), " - "using tsc calculated value.. "); + "value calculated using timer frequency.. "); } else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) { printk(KERN_INFO "Calibrating delay using timer specific routine.. "); -- cgit v1.2.3 From 3d4422332711ef48ef0f132f1fcbfcbd56c7f3d1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 26 Jun 2008 11:21:34 +0200 Subject: Add generic helpers for arch IPI function calls This adds kernel/smp.c which contains helpers for IPI function calls. In addition to supporting the existing smp_call_function() in a more efficient manner, it also adds a more scalable variant called smp_call_function_single() for calling a given function on a single CPU only. The core of this is based on the x86-64 patch from Nick Piggin, lots of changes since then. "Alan D. Brunelle" has contributed lots of fixes and suggestions as well. Also thanks to Paul E. McKenney for reviewing RCU usage and getting rid of the data allocation fallback deadlock. Acked-by: Ingo Molnar Reviewed-by: Paul E. McKenney Signed-off-by: Jens Axboe --- init/main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index f7fb20021d48..1efcccff1bdb 100644 --- a/init/main.c +++ b/init/main.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -779,6 +780,7 @@ static void __init do_pre_smp_initcalls(void) { extern int spawn_ksoftirqd(void); + init_call_single_data(); migration_init(); spawn_ksoftirqd(); if (!nosoftlockup) -- cgit v1.2.3 From 2d62f488585405bc9108c47cb06957397cfd1059 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 31 Jan 2008 17:25:00 +0200 Subject: do_mounts: allow UBI root device name Similarly to MTD devices, allow UBI devices. Signed-off-by: Adrian Hunter --- init/do_mounts.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index 660c1e50c91b..a1de1bf3d6b9 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -372,7 +372,8 @@ void __init prepare_namespace(void) if (saved_root_name[0]) { root_device_name = saved_root_name; - if (!strncmp(root_device_name, "mtd", 3)) { + if (!strncmp(root_device_name, "mtd", 3) || + !strncmp(root_device_name, "ubi", 3)) { mount_block_root(root_device_name, root_mountflags); goto out; } -- cgit v1.2.3 From e761b7725234276a802322549cee5255305a0930 Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Tue, 15 Jul 2008 04:43:49 -0700 Subject: cpu hotplug, sched: Introduce cpu_active_map and redo sched domain managment (take 2) This is based on Linus' idea of creating cpu_active_map that prevents scheduler load balancer from migrating tasks to the cpu that is going down. It allows us to simplify domain management code and avoid unecessary domain rebuilds during cpu hotplug event handling. Please ignore the cpusets part for now. It needs some more work in order to avoid crazy lock nesting. Although I did simplfy and unify domain reinitialization logic. We now simply call partition_sched_domains() in all the cases. This means that we're using exact same code paths as in cpusets case and hence the test below cover cpusets too. Cpuset changes to make rebuild_sched_domains() callable from various contexts are in the separate patch (right next after this one). This not only boots but also easily handles while true; do make clean; make -j 8; done and while true; do on-off-cpu 1; done at the same time. (on-off-cpu 1 simple does echo 0/1 > /sys/.../cpu1/online thing). Suprisingly the box (dual-core Core2) is quite usable. In fact I'm typing this on right now in gnome-terminal and things are moving just fine. Also this is running with most of the debug features enabled (lockdep, mutex, etc) no BUG_ONs or lockdep complaints so far. I believe I addressed all of the Dmitry's comments for original Linus' version. I changed both fair and rt balancer to mask out non-active cpus. And replaced cpu_is_offline() with !cpu_active() in the main scheduler code where it made sense (to me). Signed-off-by: Max Krasnyanskiy Acked-by: Linus Torvalds Acked-by: Peter Zijlstra Acked-by: Gregory Haskins Cc: dmitry.adamushko@gmail.com Cc: pj@sgi.com Signed-off-by: Ingo Molnar --- init/main.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index edeace036fd9..dd25259530ea 100644 --- a/init/main.c +++ b/init/main.c @@ -415,6 +415,13 @@ static void __init smp_init(void) { unsigned int cpu; + /* + * Set up the current CPU as possible to migrate to. + * The other ones will be done by cpu_up/cpu_down() + */ + cpu = smp_processor_id(); + cpu_set(cpu, cpu_active_map); + /* FIXME: This should be done in userspace --RR */ for_each_present_cpu(cpu) { if (num_online_cpus() >= setup_max_cpus) -- cgit v1.2.3 From fb6624ebd912e3d6907ca6490248e73368223da9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 17 Jul 2008 21:16:36 +0200 Subject: initrd: Fix virtual/physical mix-up in overwrite test On recent kernels, I get the following error when using an initrd: | initrd overwritten (0x00b78000 < 0x07668000) - disabling it. My Amiga 4000 has 12 MiB of RAM at physical address 0x07400000 (virtual 0x00000000). The initrd is located at the end of RAM: 0x00b78000 - 0x00c00000 (virtual). The overwrite test compares the (virtual) initrd location to the (physical) first available memory location, which fails. This patch converts initrd_start to a page frame number, so it can safely be compared with min_low_pfn. Before the introduction of discontiguous memory support on m68k (12d810c1b8c2b913d48e629e2b5c01d105029839), min_low_pfn was just left untouched by the m68k-specific code (zero, I guess), and everything worked fine. Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- init/main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index edeace036fd9..756eca4b821a 100644 --- a/init/main.c +++ b/init/main.c @@ -630,9 +630,10 @@ asmlinkage void __init start_kernel(void) #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start && !initrd_below_start_ok && - initrd_start < min_low_pfn << PAGE_SHIFT) { + page_to_pfn(virt_to_page(initrd_start)) < min_low_pfn) { printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - " - "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT); + "disabling it.\n", + page_to_pfn(virt_to_page(initrd_start)), min_low_pfn); initrd_start = 0; } #endif -- cgit v1.2.3 From f7f5b67557eac1131ba6532522e3c50eced34238 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Tue, 22 Jul 2008 19:24:26 -0500 Subject: Shrink struct module: CONFIG_UNUSED_SYMBOLS ifdefs module.c and module.h conatains code for finding exported symbols which are declared with EXPORT_UNUSED_SYMBOL, and this code is compiled in even if CONFIG_UNUSED_SYMBOLS is not set and thus there can be no EXPORT_UNUSED_SYMBOLs in modules anyway (because EXPORT_UNUSED_SYMBOL(x) are compiled out to nothing then). This patch adds required #ifdefs. Signed-off-by: Denys Vlasenko Signed-off-by: Rusty Russell --- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 6199d1120900..c8578f9ee31d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -856,8 +856,8 @@ config MODULE_UNLOAD help Without this option you will not be able to unload any modules (note that some modules may not be unloadable - anyway), which makes your kernel slightly smaller and - simpler. If unsure, say Y. + anyway), which makes your kernel smaller, faster + and simpler. If unsure, say Y. config MODULE_FORCE_UNLOAD bool "Forced module unloading" -- cgit v1.2.3 From baabaae98125fbd1a8dc258aa95333c01cd9e206 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Jul 2008 19:00:16 +0200 Subject: make CONFIG_KMOD invisible ... as preparation for removing it completely, make it an invisible bool defaulting to yes. Signed-off-by: Johannes Berg Signed-off-by: Rusty Russell --- init/Kconfig | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index c8578f9ee31d..a50bdfed2df7 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -893,16 +893,11 @@ config MODULE_SRCVERSION_ALL will be created for all modules. If unsure, say N. config KMOD - bool "Automatic kernel module loading" + def_bool y depends on MODULES help - Normally when you have selected some parts of the kernel to - be created as kernel modules, you must load them (using the - "modprobe" command) before you can use them. If you say Y - here, some parts of the kernel will be able to load modules - automatically: when a part of the kernel needs a module, it - runs modprobe with the appropriate arguments, thereby - loading the module if it is available. If unsure, say Y. + This is being removed soon. These days, CONFIG_MODULES + implies CONFIG_KMOD, so use that instead. config STOP_MACHINE bool -- cgit v1.2.3