From 54bb6552bd9405dc7685653157a4ec260c77a71c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 9 Dec 2009 15:29:01 -0500 Subject: ima: initialize ima before inodes can be allocated ima wants to create an inode information struct (iint) when inodes are allocated. This means that at least the part of ima which does this allocation (the allocation is filled with information later) should before any inodes are created. To accomplish this we split the ima initialization routine placing the kmem cache allocator inside a security_initcall() function. Since this makes use of radix trees we also need to make sure that is initialized before security_initcall(). Signed-off-by: Eric Paris Acked-by: Mimi Zohar Signed-off-by: Al Viro --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index dac44a9..4cb47a1 100644 --- a/init/main.c +++ b/init/main.c @@ -657,9 +657,9 @@ asmlinkage void __init start_kernel(void) proc_caches_init(); buffer_init(); key_init(); + radix_tree_init(); security_init(); vfs_caches_init(totalram_pages); - radix_tree_init(); signals_init(); /* rootfs populating might need page-writeback */ page_writeback_init(); -- cgit v1.1 From 773e3eb7b81e5ba13b5155dfb3bb75b8ce37f8f9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:33 -0800 Subject: init: Move radix_tree_init() early Prepare for using radix trees in early_irq_init(). Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-30-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 4cb47a1..8451878 100644 --- a/init/main.c +++ b/init/main.c @@ -584,6 +584,7 @@ asmlinkage void __init start_kernel(void) local_irq_disable(); } rcu_init(); + radix_tree_init(); /* init some links before init_ISA_irqs() */ early_irq_init(); init_IRQ(); @@ -657,7 +658,6 @@ asmlinkage void __init start_kernel(void) proc_caches_init(); buffer_init(); key_init(); - radix_tree_init(); security_init(); vfs_caches_init(totalram_pages); signals_init(); -- cgit v1.1 From 2b633e3fac5efada088b57d31e65401f22bcc18f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:37 -0800 Subject: smp: Use nr_cpus= to set nr_cpu_ids early On x86, before prefill_possible_map(), nr_cpu_ids will be NR_CPUS aka CONFIG_NR_CPUS. Add nr_cpus= to set nr_cpu_ids. so we can simulate cpus <=8 are installed on normal config. -v2: accordging to Christoph, acpi_numa_init should use nr_cpu_ids in stead of NR_CPUS. -v3: add doc in kernel-parameters.txt according to Andrew. Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-34-git-send-email-yinghai@kernel.org> Acked-by: Linus Torvalds Signed-off-by: H. Peter Anvin Cc: Tony Luck --- init/main.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 8451878..05b5283 100644 --- a/init/main.c +++ b/init/main.c @@ -149,6 +149,20 @@ static int __init nosmp(char *str) early_param("nosmp", nosmp); +/* this is hard limit */ +static int __init nrcpus(char *str) +{ + int nr_cpus; + + get_option(&str, &nr_cpus); + if (nr_cpus > 0 && nr_cpus < nr_cpu_ids) + nr_cpu_ids = nr_cpus; + + return 0; +} + +early_param("nr_cpus", nrcpus); + static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); -- cgit v1.1 From d11c563dd20ff35da5652c3e1c989d9e10e1d6d0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:04:50 -0800 Subject: sched: Use lockdep-based checking on rcu_dereference() Update the rcu_dereference() usages to take advantage of the new lockdep-based checking. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com 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: <1266887105-1528-6-git-send-email-paulmck@linux.vnet.ibm.com> [ -v2: fix allmodconfig missing symbol export build failure on x86 ] Signed-off-by: Ingo Molnar --- init/main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 4cb47a1..c75dcd6 100644 --- a/init/main.c +++ b/init/main.c @@ -416,7 +416,9 @@ static noinline void __init_refok rest_init(void) kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND); numa_default_policy(); pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); + rcu_read_lock(); kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns); + rcu_read_unlock(); unlock_kernel(); /* -- cgit v1.1 From 2bd3a997befc226ab4b504f05c5cbba305f3e0e6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 2 Mar 2010 23:53:19 -0800 Subject: init: Open /dev/console from rootfs To avoid potential problems with an empty /dev open /dev/console from rootfs instead of waiting to mount our root filesystem and mounting it there. This effectively guarantees that there will be a device node, and it won't be on a filesystem that we will ever unmount, so there are no issues with leaving /dev/console open and pinning the filesystem. This is actually more effective than automatically mounting devtmpfs on /dev because it removes removes the occasionally problematic assumption that /dev/console exists from the boot code. With this patch I was able to throw busybox on my /boot partition (which has no /dev directory) and boot into userspace without problems. The only possible negative consequence I can think of is that someone out there deliberately used did not use a character device that is major 5 minor 2 for /dev/console. Does anyone know of a situation in which that could make sense? Signed-off-by: Eric W. Biederman Signed-off-by: Al Viro --- init/main.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 4cb47a1..106e02d 100644 --- a/init/main.c +++ b/init/main.c @@ -806,11 +806,6 @@ static noinline int init_post(void) system_state = SYSTEM_RUNNING; numa_default_policy(); - if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) - printk(KERN_WARNING "Warning: unable to open an initial console.\n"); - - (void) sys_dup(0); - (void) sys_dup(0); current->signal->flags |= SIGNAL_UNKILLABLE; @@ -873,6 +868,12 @@ static int __init kernel_init(void * unused) do_basic_setup(); + /* Open the /dev/console on the rootfs, this should never fail */ + if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + printk(KERN_WARNING "Warning: unable to open an initial console.\n"); + + (void) sys_dup(0); + (void) sys_dup(0); /* * check if there is an early userspace init. If yes, let it do all * the work -- cgit v1.1 From 452aa6999e6703ffbddd7f6ea124d3968915f3e3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 5 Mar 2010 13:42:13 -0800 Subject: mm/pm: force GFP_NOIO during suspend/hibernation and resume There are quite a few GFP_KERNEL memory allocations made during suspend/hibernation and resume that may cause the system to hang, because the I/O operations they depend on cannot be completed due to the underlying devices being suspended. Avoid this problem by clearing the __GFP_IO and __GFP_FS bits in gfp_allowed_mask before suspend/hibernation and restoring the original values of these bits in gfp_allowed_mask durig the subsequent resume. [akpm@linux-foundation.org: fix CONFIG_PM=n linkage] Signed-off-by: Rafael J. Wysocki Reported-by: Maxim Levitsky Cc: Sebastian Ott Cc: Benjamin Herrenschmidt Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 40aaa02..41d0f10 100644 --- a/init/main.c +++ b/init/main.c @@ -618,7 +618,7 @@ asmlinkage void __init start_kernel(void) local_irq_enable(); /* Interrupts are enabled now so all GFP allocations are safe. */ - set_gfp_allowed_mask(__GFP_BITS_MASK); + gfp_allowed_mask = __GFP_BITS_MASK; kmem_cache_init_late(); -- cgit v1.1 From 9a85b8d6049cbb0e7961df2069322fbc4192026a Mon Sep 17 00:00:00 2001 From: Andreas Mohr Date: Fri, 5 Mar 2010 13:42:39 -0800 Subject: init/main.c: improve usability in case of init binary failure - new Documentation/init.txt file describing various forms of failure trying to load the init binary after kernel bootup - extend the init/main.c init failure message to direct to Documentation/init.txt Signed-off-by: Andreas Mohr Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 41d0f10..b09a828 100644 --- a/init/main.c +++ b/init/main.c @@ -847,7 +847,8 @@ static noinline int init_post(void) run_init_process("/bin/init"); run_init_process("/bin/sh"); - panic("No init found. Try passing init= option to kernel."); + panic("No init found. Try passing init= option to kernel. " + "See Linux Documentation/init.txt for guidance."); } static int __init kernel_init(void * unused) -- cgit v1.1 From 7463e633c5f94792dcff1afefb0d2961318a9d09 Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Fri, 5 Mar 2010 13:42:46 -0800 Subject: init/main.c: make setup_max_cpus static for !SMP The only in tree external users of the symbol setup_max_cpus are in arch/x86/. The files ./kernel/alternative.c, ./kernel/visws_quirks.c, and ./mm/kmemcheck/kmemcheck.c are all guarded by CONFIG_SMP being defined. For this case the symbol is an unsigned int and declared as an extern in include/linux/smp.h. When CONFIG_SMP is not defined the symbol setup_max_cpus is a constant value that is only used in init/main.c. Make the symbol static for this case. Signed-off-by: H Hartley Sweeten Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index b09a828..a1ab78c 100644 --- a/init/main.c +++ b/init/main.c @@ -174,7 +174,7 @@ static int __init maxcpus(char *str) early_param("maxcpus", maxcpus); #else -const unsigned int setup_max_cpus = NR_CPUS; +static const unsigned int setup_max_cpus = NR_CPUS; #endif /* -- cgit v1.1 From 5ab116c9349ef52d6fbd2e2917a53f13194b048e Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Tue, 23 Mar 2010 13:35:34 -0700 Subject: cpuset: fix the problem that cpuset_mem_spread_node() returns an offline node cpuset_mem_spread_node() returns an offline node, and causes an oops. This patch fixes it by initializing task->mems_allowed to node_states[N_HIGH_MEMORY], and updating task->mems_allowed when doing memory hotplug. Signed-off-by: Miao Xie Acked-by: David Rientjes Reported-by: Nick Piggin Tested-by: Nick Piggin Cc: Paul Menage Cc: Li Zefan Cc: Ingo Molnar Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index a1ab78c..cbead27 100644 --- a/init/main.c +++ b/init/main.c @@ -858,7 +858,7 @@ static int __init kernel_init(void * unused) /* * init can allocate pages on any node */ - set_mems_allowed(node_possible_map); + set_mems_allowed(node_states[N_HIGH_MEMORY]); /* * init can run on any cpu. */ -- cgit v1.1 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 --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index cbead27..5c85402 100644 --- a/init/main.c +++ b/init/main.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include @@ -69,6 +68,7 @@ #include #include #include +#include #include #include -- cgit v1.1 From 67fc4e0cb931d6b4ccf21248e4199b154478ecea Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:21 -0500 Subject: kdb: core for kgdb back end (2 of 2) This patch contains the hooks and instrumentation into kernel which live outside the kernel/debug directory, which the kdb core will call to run commands like lsmod, dmesg, bt etc... CC: linux-arch@vger.kernel.org Signed-off-by: Jason Wessel Signed-off-by: Martin Hicks --- init/main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 5c85402..3727713 100644 --- a/init/main.c +++ b/init/main.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include #include @@ -675,6 +676,7 @@ asmlinkage void __init start_kernel(void) buffer_init(); key_init(); security_init(); + kdb_init(KDB_INIT_FULL); vfs_caches_init(totalram_pages); signals_init(); /* rootfs populating might need page-writeback */ -- cgit v1.1 From 0b4b3827db386ec6034a5aba1261025b039440c2 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 20 May 2010 21:04:29 -0500 Subject: x86, kgdb, init: Add early and late debug states The kernel debugger can operate well before mm_init(), but the x86 hardware breakpoint code which uses the perf api requires that the kernel allocators are initialized. This means the kernel debug core needs to provide an optional arch specific call back to allow the initialization functions to run after the kernel has been further initialized. The kdb shell already had a similar restriction with an early initialization and late initialization. The kdb_init() was moved into the debug core's version of the late init which is called dbg_late_init(); CC: kgdb-bugreport@lists.sourceforge.net Signed-off-by: Jason Wessel --- init/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 3727713..22881b5 100644 --- a/init/main.c +++ b/init/main.c @@ -62,7 +62,7 @@ #include #include #include -#include +#include #include #include #include @@ -676,7 +676,7 @@ asmlinkage void __init start_kernel(void) buffer_init(); key_init(); security_init(); - kdb_init(KDB_INIT_FULL); + dbg_late_init(); vfs_caches_init(totalram_pages); signals_init(); /* rootfs populating might need page-writeback */ -- cgit v1.1 From 1f522509c77a5dea8dc384b735314f03908a6415 Mon Sep 17 00:00:00 2001 From: Haicheng Li Date: Mon, 24 May 2010 14:32:51 -0700 Subject: mem-hotplug: avoid multiple zones sharing same boot strapping boot_pageset For each new populated zone of hotadded node, need to update its pagesets with dynamically allocated per_cpu_pageset struct for all possible CPUs: 1) Detach zone->pageset from the shared boot_pageset at end of __build_all_zonelists(). 2) Use mutex to protect zone->pageset when it's still shared in onlined_pages() Otherwises, multiple zones of different nodes would share same boot strapping boot_pageset for same CPU, which will finally cause below kernel panic: ------------[ cut here ]------------ kernel BUG at mm/page_alloc.c:1239! invalid opcode: 0000 [#1] SMP ... Call Trace: [] __alloc_pages_nodemask+0x131/0x7b0 [] alloc_pages_current+0x87/0xd0 [] __page_cache_alloc+0x67/0x70 [] __do_page_cache_readahead+0x120/0x260 [] ra_submit+0x21/0x30 [] ondemand_readahead+0x166/0x2c0 [] page_cache_async_readahead+0x80/0xa0 [] generic_file_aio_read+0x364/0x670 [] nfs_file_read+0xca/0x130 [] do_sync_read+0xfa/0x140 [] vfs_read+0xb5/0x1a0 [] sys_read+0x51/0x80 [] system_call_fastpath+0x16/0x1b RIP [] get_page_from_freelist+0x883/0x900 RSP ---[ end trace 4bda28328b9990db ] [akpm@linux-foundation.org: merge fix] Signed-off-by: Haicheng Li Signed-off-by: Wu Fengguang Reviewed-by: Andi Kleen Reviewed-by: Christoph Lameter Cc: Mel Gorman Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 22881b5..3bdb152 100644 --- a/init/main.c +++ b/init/main.c @@ -567,7 +567,7 @@ asmlinkage void __init start_kernel(void) setup_per_cpu_areas(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ - build_all_zonelists(); + build_all_zonelists(NULL); page_alloc_init(); printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line); -- cgit v1.1 From 75cbfb97a156dd3dabdc81295fb8144576332366 Mon Sep 17 00:00:00 2001 From: Thomas Renninger Date: Wed, 26 May 2010 17:03:33 +0200 Subject: ACPI: Do not try to set up acpi processor stuff on cores exceeding maxcpus= Patch is against latest Linus master branch and is expected to be safe bug fix. You get: ACPI: HARDWARE addr space,NOT supported yet for each ACPI defined CPU which status is active, but exceeds maxcpus= count. As these "not booted" CPUs do not run an idle routine and echo X >/proc/acpi/processor/*/throttling did not work I couldn't find a way to really access not onlined/booted machines. Still this should get fixed and /proc/acpi/processor/X dirs of cores exceeding maxcpus should not show up. I wonder whether this could get cleaned up by truncating possible cpu mask and nr_cpu_ids to setup_max_cpus early some day (and not exporting setup_max_cpus anymore then). But this needs touching of a lot other places... Signed-off-by: Thomas Renninger CC: travis@sgi.com CC: linux-acpi@vger.kernel.org CC: lenb@kernel.org Signed-off-by: Len Brown --- init/main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 3bdb152..ac2e4a5 100644 --- a/init/main.c +++ b/init/main.c @@ -125,7 +125,9 @@ static char *ramdisk_execute_command; #ifdef CONFIG_SMP /* Setup configured maximum number of CPUs to activate */ -unsigned int __initdata setup_max_cpus = NR_CPUS; +unsigned int setup_max_cpus = NR_CPUS; +EXPORT_SYMBOL(setup_max_cpus); + /* * Setup routine for controlling SMP activation -- cgit v1.1 From b433c3d4549ae74935b585115f076c6fb7bc48fe Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 28 Jun 2010 16:51:01 +0200 Subject: init, sched: Fix race between init and kthreadd Ilya reported that on a very slow machine he could reliably reproduce a race between forking init and kthreadd. We first fork init so that it obtains pid-1, however since the scheduler is already fully running at this point it can preempt and run the init thread before we spawn and set kthreadd_task. The init thread can then attempt spawning kthreads without kthreadd being present which results in an OOPS. Reported-by: Ilya Loginov Signed-off-by: Peter Zijlstra Acked-by: Linus Torvalds LKML-Reference: <1277736661.3561.110.camel@laptop> Signed-off-by: Ingo Molnar --- init/main.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 3bdb152..633442f 100644 --- a/init/main.c +++ b/init/main.c @@ -422,18 +422,26 @@ static void __init setup_command_line(char *command_line) * gcc-3.4 accidentally inlines this function, so use noinline. */ +static __initdata DECLARE_COMPLETION(kthreadd_done); + static noinline void __init_refok rest_init(void) __releases(kernel_lock) { int pid; rcu_scheduler_starting(); + /* + * We need to spawn init first so that it obtains pid-1, however + * the init task will end up wanting to create kthreads, which, if + * we schedule it before we create kthreadd, will OOPS. + */ kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND); numa_default_policy(); pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); rcu_read_lock(); kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns); rcu_read_unlock(); + complete(&kthreadd_done); unlock_kernel(); /* @@ -855,6 +863,10 @@ static noinline int init_post(void) static int __init kernel_init(void * unused) { + /* + * Wait until kthreadd is all set-up. + */ + wait_for_completion(&kthreadd_done); lock_kernel(); /* -- cgit v1.1 From 9715856922bf8475f5428c29b6f4a9eebc97d391 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Jun 2010 10:37:11 +0200 Subject: init: Fix comment Apparently "pid-1" confuses people... Requested-by: Randy Dunlap Signed-off-by: Peter Zijlstra Cc: torvalds@linux-foundation.org Cc: randy.dunlap@oracle.com Cc: Ilya Loginov LKML-Reference: <1277887031.1868.82.camel@laptop> Signed-off-by: Ingo Molnar --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init/main.c') diff --git a/init/main.c b/init/main.c index 633442f..1692df3 100644 --- a/init/main.c +++ b/init/main.c @@ -431,7 +431,7 @@ static noinline void __init_refok rest_init(void) rcu_scheduler_starting(); /* - * We need to spawn init first so that it obtains pid-1, however + * We need to spawn init first so that it obtains pid 1, however * the init task will end up wanting to create kthreads, which, if * we schedule it before we create kthreadd, will OOPS. */ -- cgit v1.1