From 98a79d6a50181ca1ecf7400eda01d5dc1bc0dbf0 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 13 Dec 2008 21:19:41 +1030 Subject: cpumask: centralize cpu_online_map and cpu_possible_map Impact: cleanup Each SMP arch defines these themselves. Move them to a central location. Twists: 1) Some archs (m32, parisc, s390) set possible_map to all 1, so we add a CONFIG_INIT_ALL_POSSIBLE for this rather than break them. 2) mips and sparc32 '#define cpu_possible_map phys_cpu_present_map'. Those archs simply have phys_cpu_present_map replaced everywhere. 3) Alpha defined cpu_possible_map to cpu_present_map; this is tricky so I just manipulate them both in sync. 4) IA64, cris and m32r have gratuitous 'extern cpumask_t cpu_possible_map' declarations. Signed-off-by: Rusty Russell Reviewed-by: Grant Grundler Tested-by: Tony Luck Acked-by: Ingo Molnar Cc: Mike Travis Cc: ink@jurassic.park.msu.ru Cc: rmk@arm.linux.org.uk Cc: starvik@axis.com Cc: tony.luck@intel.com Cc: takata@linux-m32r.org Cc: ralf@linux-mips.org Cc: grundler@parisc-linux.org Cc: paulus@samba.org Cc: schwidefsky@de.ibm.com Cc: lethal@linux-sh.org Cc: wli@holomorphy.com Cc: davem@davemloft.net Cc: jdike@addtoit.com Cc: mingo@redhat.com --- init/Kconfig | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index f763762d544a..7656623f5006 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -916,6 +916,15 @@ config KMOD endif # MODULES +config INIT_ALL_POSSIBLE + bool + help + Back when each arch used to define their own cpu_online_map and + cpu_possible_map, some of them chose to initialize cpu_possible_map + with all 1s, and others with all 0s. When they were centralised, + it was better to provide this option than to break all the archs + and have several arch maintainers persuing me down dark alleys. + config STOP_MACHINE bool default y -- cgit v1.2.3 From 13a0c3c269b223f60abfac8a9811d77111a8b4ba Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 26 Dec 2008 02:05:47 -0800 Subject: sparseirq: work around compiler optimizing away __weak functions Impact: fix panic on null pointer with sparseirq Some GCC versions seem to inline the weak global function, when that function is empty. Work it around, by making the functions return a (dummy) integer. Signed-off-by: Yinghai Signed-off-by: Ingo Molnar --- arch/x86/kernel/io_apic.c | 8 ++++++-- include/linux/irq.h | 6 +++--- init/main.c | 7 ++++--- kernel/irq/handle.c | 7 ++++--- 4 files changed, 17 insertions(+), 11 deletions(-) (limited to 'init') diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index 2fe543f58ac8..976039377846 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -170,7 +170,7 @@ static struct irq_cfg irq_cfgx[NR_IRQS] = { [15] = { .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, }, }; -void __init arch_early_irq_init(void) +int __init arch_early_irq_init(void) { struct irq_cfg *cfg; struct irq_desc *desc; @@ -184,6 +184,8 @@ void __init arch_early_irq_init(void) desc = irq_to_desc(i); desc->chip_data = &cfg[i]; } + + return 0; } #ifdef CONFIG_SPARSE_IRQ @@ -212,7 +214,7 @@ static struct irq_cfg *get_one_free_irq_cfg(int cpu) return cfg; } -void arch_init_chip_data(struct irq_desc *desc, int cpu) +int arch_init_chip_data(struct irq_desc *desc, int cpu) { struct irq_cfg *cfg; @@ -224,6 +226,8 @@ void arch_init_chip_data(struct irq_desc *desc, int cpu) BUG_ON(1); } } + + return 0; } #ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC diff --git a/include/linux/irq.h b/include/linux/irq.h index 69da275c0ebd..0e40af4bac40 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -193,9 +193,9 @@ struct irq_desc { const char *name; } ____cacheline_internodealigned_in_smp; -extern void early_irq_init(void); -extern void arch_early_irq_init(void); -extern void arch_init_chip_data(struct irq_desc *desc, int cpu); +extern int early_irq_init(void); +extern int arch_early_irq_init(void); +extern int arch_init_chip_data(struct irq_desc *desc, int cpu); extern void arch_init_copy_chip_data(struct irq_desc *old_desc, struct irq_desc *desc, int cpu); extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc); diff --git a/init/main.c b/init/main.c index c1f999a3cf31..c314aa15370e 100644 --- a/init/main.c +++ b/init/main.c @@ -539,13 +539,14 @@ void __init __weak thread_info_cache_init(void) { } -void __init __weak arch_early_irq_init(void) +int __init __weak arch_early_irq_init(void) { + return 0; } -void __init __weak early_irq_init(void) +int __init __weak early_irq_init(void) { - arch_early_irq_init(); + return arch_early_irq_init(); } asmlinkage void __init start_kernel(void) diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 893da67b7781..0bef3ecb7a0e 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -86,8 +86,9 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) desc->kstat_irqs = (unsigned int *)ptr; } -void __attribute__((weak)) arch_init_chip_data(struct irq_desc *desc, int cpu) +int __weak arch_init_chip_data(struct irq_desc *desc, int cpu) { + return 0; } static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) @@ -132,7 +133,7 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm /* FIXME: use bootmem alloc ...*/ static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS]; -void __init early_irq_init(void) +int __init early_irq_init(void) { struct irq_desc *desc; int legacy_count; @@ -151,7 +152,7 @@ void __init early_irq_init(void) for (i = legacy_count; i < NR_IRQS; i++) irq_desc_ptrs[i] = NULL; - arch_early_irq_init(); + return arch_early_irq_init(); } struct irq_desc *irq_to_desc(unsigned int irq) -- cgit v1.2.3 From 43a256322ac1fc105c181b3cade3b9bfc0b63ca1 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 28 Dec 2008 16:01:13 -0800 Subject: sparseirq: move __weak symbols into separate compilation unit GCC has a bug with __weak alias functions: if the functions are in the same compilation unit as their call site, GCC can decide to inline them - and thus rob the linker of the opportunity to override the weak alias with the real thing. So move all the IRQ handling related __weak symbols to kernel/irq/chip.c. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 6 ++++++ include/linux/irq.h | 3 --- init/main.c | 10 ---------- kernel/irq/manage.c | 9 --------- kernel/softirq.c | 20 ++++++++++++++++++++ 5 files changed, 26 insertions(+), 22 deletions(-) (limited to 'init') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 777f89e00b4a..d9a370325ae2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -467,4 +467,10 @@ static inline void init_irq_proc(void) int show_interrupts(struct seq_file *p, void *v); +struct irq_desc; + +extern int early_irq_init(void); +extern int arch_early_irq_init(void); +extern int arch_init_chip_data(struct irq_desc *desc, int cpu); + #endif diff --git a/include/linux/irq.h b/include/linux/irq.h index 0e40af4bac40..d64a6d49bdef 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -193,9 +193,6 @@ struct irq_desc { const char *name; } ____cacheline_internodealigned_in_smp; -extern int early_irq_init(void); -extern int arch_early_irq_init(void); -extern int arch_init_chip_data(struct irq_desc *desc, int cpu); extern void arch_init_copy_chip_data(struct irq_desc *old_desc, struct irq_desc *desc, int cpu); extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc); diff --git a/init/main.c b/init/main.c index c314aa15370e..2c183abbf61c 100644 --- a/init/main.c +++ b/init/main.c @@ -539,16 +539,6 @@ void __init __weak thread_info_cache_init(void) { } -int __init __weak arch_early_irq_init(void) -{ - return 0; -} - -int __init __weak early_irq_init(void) -{ - return arch_early_irq_init(); -} - asmlinkage void __init start_kernel(void) { char * command_line; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c2741b02ad38..46953a06f4a8 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -261,15 +261,6 @@ void enable_irq(unsigned int irq) } EXPORT_SYMBOL(enable_irq); -/* - * [ Not in kernel/irq/handle.c, so that GCC does not - * inline the __weak alias: ] - */ -int __weak arch_init_chip_data(struct irq_desc *desc, int cpu) -{ - return 0; -} - static int set_irq_wake_real(unsigned int irq, unsigned int on) { struct irq_desc *desc = irq_to_desc(irq); diff --git a/kernel/softirq.c b/kernel/softirq.c index e7c69a720d69..daf46358d2dd 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -797,3 +797,23 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait) } EXPORT_SYMBOL(on_each_cpu); #endif + +/* + * [ These __weak aliases are kept in a separate compilation unit, so that + * GCC does not inline them incorrectly. ] + */ + +int __init __weak early_irq_init(void) +{ + return 0; +} + +int __init __weak arch_early_irq_init(void) +{ + return 0; +} + +int __weak arch_init_chip_data(struct irq_desc *desc, int cpu) +{ + return 0; +} -- cgit v1.2.3 From 915441b601e6662e79f6c958e7be307967a96977 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 1 Jan 2009 10:12:15 +1030 Subject: cpumask: Use accessors code in core Impact: use new API cpu_*_map are going away in favour of cpu_*_mask, but const pointers. So we have accessors where we really do want to frob them. Archs will also need the (trivial) conversion before we can finally remove cpu_*_map. Signed-off-by: Rusty Russell Signed-off-by: Mike Travis --- init/main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 2a7ce0f8e453..84d3732c0ce5 100644 --- a/init/main.c +++ b/init/main.c @@ -527,9 +527,9 @@ static void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ - cpu_set(cpu, cpu_online_map); - cpu_set(cpu, cpu_present_map); - cpu_set(cpu, cpu_possible_map); + set_cpu_online(cpu, true); + set_cpu_present(cpu, true); + set_cpu_possible(cpu, true); } void __init __weak smp_setup_processor_id(void) -- cgit v1.2.3 From e0c0ba736547e81c4f986ce192307c549d214167 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 1 Jan 2009 10:12:19 +1030 Subject: cpumask: Use find_last_bit() Impact: cleanup There's one obvious place to use it: to find the highest possible cpu. Signed-off-by: Rusty Russell --- init/main.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 84d3732c0ce5..546ebd2f44ba 100644 --- a/init/main.c +++ b/init/main.c @@ -380,12 +380,7 @@ EXPORT_SYMBOL(nr_cpu_ids); /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ static void __init setup_nr_cpu_ids(void) { - int cpu, highest_cpu = 0; - - for_each_possible_cpu(cpu) - highest_cpu = cpu; - - nr_cpu_ids = highest_cpu + 1; + nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; } #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA -- cgit v1.2.3 From 609e5b71d0eca163df017ecfcf917b149875e744 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 2 Jan 2009 16:16:16 +0100 Subject: kbuild: Remove gcc 4.1.0 quirk from init/main.c Impact: cleanup We now have a cleaner check for gcc 4.1.0/4.1.1 trouble in include/linux/compiler-gcc4.h, so remove the 4.1.0 quirk from init/main.c. Reported-by: Bartlomiej Zolnierkiewicz Signed-off-by: Ingo Molnar Acked-by: Sam Ravnborg Signed-off-by: Linus Torvalds --- init/main.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index f5e64f20d2b0..ad8f9f53f8d1 100644 --- a/init/main.c +++ b/init/main.c @@ -75,15 +75,6 @@ #include #endif -/* - * This is one of the first .c files built. Error out early if we have compiler - * trouble. - */ - -#if __GNUC__ == 4 && __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ == 0 -#warning gcc-4.1.0 is known to miscompile the kernel. A different compiler version is recommended. -#endif - static int kernel_init(void *); extern void init_IRQ(void); -- cgit v1.2.3 From a327ca2c2674c5a9a0073421df19bfc362698136 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Jul 2008 19:00:26 +0200 Subject: remove CONFIG_KMOD Now that nothing depends on it any more, remove CONFIG_KMOD. Signed-off-by: Johannes Berg Signed-off-by: Rusty Russell --- init/Kconfig | 6 ------ 1 file changed, 6 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index f6281711166d..52847eec7398 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -916,12 +916,6 @@ config MODULE_SRCVERSION_ALL the version). With this option, such a "srcversion" field will be created for all modules. If unsure, say N. -config KMOD - def_bool y - help - This is being removed soon. These days, CONFIG_MODULES - implies CONFIG_KMOD, so use that instead. - endif # MODULES config INIT_ALL_POSSIBLE -- cgit v1.2.3 From b8fed87d3265d21d6f90e34934d93f70cb1e5cc1 Mon Sep 17 00:00:00 2001 From: Phillip Lougher Date: Mon, 5 Jan 2009 08:46:28 +0000 Subject: Squashfs: initrd support Signed-off-by: Phillip Lougher --- init/do_mounts_rd.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'init') diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index a7c748fa977a..0f0f0cf3ba9a 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -9,6 +9,7 @@ #include #include "do_mounts.h" +#include "../fs/squashfs/squashfs_fs.h" int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */ @@ -41,6 +42,7 @@ static int __init crd_load(int in_fd, int out_fd); * ext2 * romfs * cramfs + * squashfs * gzip */ static int __init @@ -51,6 +53,7 @@ identify_ramdisk_image(int fd, int start_block) struct ext2_super_block *ext2sb; struct romfs_super_block *romfsb; struct cramfs_super *cramfsb; + struct squashfs_super_block *squashfsb; int nblocks = -1; unsigned char *buf; @@ -62,6 +65,7 @@ identify_ramdisk_image(int fd, int start_block) ext2sb = (struct ext2_super_block *) buf; romfsb = (struct romfs_super_block *) buf; cramfsb = (struct cramfs_super *) buf; + squashfsb = (struct squashfs_super_block *) buf; memset(buf, 0xe5, size); /* @@ -99,6 +103,16 @@ identify_ramdisk_image(int fd, int start_block) goto done; } + /* squashfs is at block zero too */ + if (le32_to_cpu(squashfsb->s_magic) == SQUASHFS_MAGIC) { + printk(KERN_NOTICE + "RAMDISK: squashfs filesystem found at block %d\n", + start_block); + nblocks = (le64_to_cpu(squashfsb->bytes_used) + BLOCK_SIZE - 1) + >> BLOCK_SIZE_BITS; + goto done; + } + /* * Read block 1 to test for minix and ext2 superblock */ -- cgit v1.2.3 From 24d431d06aeeda2b12cc925c6e1693c45ae5088b Mon Sep 17 00:00:00 2001 From: Ron Lee Date: Thu, 27 Nov 2008 02:31:57 +1030 Subject: trivial: add missing printk loglevel in start_kernel Add missing printk loglevel in start_kernel Signed-off-by: Ron Lee Signed-off-by: Jiri Kosina --- init/main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index cd168ebc5924..798fe450e708 100644 --- a/init/main.c +++ b/init/main.c @@ -602,7 +602,8 @@ asmlinkage void __init start_kernel(void) sched_clock_init(); profile_init(); if (!irqs_disabled()) - printk("start_kernel(): bug: interrupts were enabled early\n"); + printk(KERN_CRIT "start_kernel(): bug: interrupts were " + "enabled early\n"); early_boot_irqs_on(); local_irq_enable(); -- cgit v1.2.3 From fce3e804cfad49208fd2ff9db4bcb57481409e1d Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sat, 1 Nov 2008 14:03:00 +0100 Subject: sysfs: clarify SYSFS_DEPRECATED help text This should make the help text of SYSFS_DEPRECATED more clear, that this is _not_ about (what some people think it is) suppressing a few symlinks and variables, but a different sysfs _layout_ with new features. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- init/Kconfig | 44 +++++++++++++++++++++++++++----------------- 1 file changed, 27 insertions(+), 17 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 52847eec7398..d9d3dbabdb18 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -423,27 +423,37 @@ config SYSFS_DEPRECATED bool config SYSFS_DEPRECATED_V2 - bool "Create deprecated sysfs files" + bool "Create deprecated sysfs layout for older userspace tools" depends on SYSFS default y select SYSFS_DEPRECATED help - This option creates deprecated symlinks such as the - "device"-link, the :-link, and the - "bus"-link. It may also add deprecated key in the - uevent environment. - None of these features or values should be used today, as - they export driver core implementation details to userspace - or export properties which can't be kept stable across kernel - releases. - - If enabled, this option will also move any device structures - that belong to a class, back into the /sys/class hierarchy, in - order to support older versions of udev and some userspace - programs. - - If you are using a distro with the most recent userspace - packages, it should be safe to say N here. + This option switches the layout of sysfs to the deprecated + version. + + The current sysfs layout features a unified device tree at + /sys/devices/, which is able to express a hierarchy between + class devices. If the deprecated option is set to Y, the + unified device tree is split into a bus device tree at + /sys/devices/ and several individual class device trees at + /sys/class/. The class and bus devices will be connected by + ":" and the "device" links. The "block" + class devices, will not show up in /sys/class/block/. Some + subsystems will suppress the creation of some devices which + depend on the unified device tree. + + This option is not a pure compatibility option that can + be safely enabled on newer distributions. It will change the + layout of sysfs to the non-extensible deprecated version, + and disable some features, which can not be exported without + confusing older userspace tools. Since 2007/2008 all major + distributions do not enable this option, and ship no tools which + depend on the deprecated layout or this option. + + If you are using a new kernel on an older distribution, or use + older userspace tools, you might need to say Y here. Do not say Y, + if the original kernel, that came with your distribution, has + this option set to N. config PROC_PID_CPUSET bool "Include legacy /proc//cpuset file" -- cgit v1.2.3 From 853ac43ab194f5051b27a55060215d696dc9480d Mon Sep 17 00:00:00 2001 From: Matt Mackall Date: Tue, 6 Jan 2009 14:40:20 -0800 Subject: shmem: unify regular and tiny shmem tiny-shmem shares most of its 130 lines of code with shmem and tends to break when particular bits of shmem get modified. Unifying saves code and makes keeping these two in sync much easier. before: 14367 392 24 14783 39bf mm/shmem.o 396 72 8 476 1dc mm/tiny-shmem.o after: 14367 392 24 14783 39bf mm/shmem.o 412 72 8 492 1ec mm/shmem.o tiny Signed-off-by: Matt Mackall Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 4 -- mm/Makefile | 4 +- mm/shmem.c | 81 +++++++++++++++++++++++++++++----- mm/tiny-shmem.c | 134 -------------------------------------------------------- 4 files changed, 72 insertions(+), 151 deletions(-) delete mode 100644 mm/tiny-shmem.c (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 52847eec7398..315a6114bf87 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -838,10 +838,6 @@ config RT_MUTEXES boolean select PLIST -config TINY_SHMEM - default !SHMEM - bool - config BASE_SMALL int default 0 if BASE_FULL diff --git a/mm/Makefile b/mm/Makefile index 51c27709cc7c..72255be57f89 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -9,7 +9,7 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o pdflush.o \ - readahead.o swap.o truncate.o vmscan.o \ + readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o $(mmu-y) @@ -21,9 +21,7 @@ obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o -obj-$(CONFIG_SHMEM) += shmem.o obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o -obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o obj-$(CONFIG_SLOB) += slob.o obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_SLAB) += slab.o diff --git a/mm/shmem.c b/mm/shmem.c index 24f18fdee6e3..5941f9801363 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -14,31 +14,39 @@ * Copyright (c) 2004, Luke Kenneth Casson Leighton * Copyright (c) 2004 Red Hat, Inc., James Morris * + * tiny-shmem: + * Copyright (c) 2004, 2008 Matt Mackall + * * This file is released under the GPL. */ +#include +#include +#include +#include +#include +#include +#include +#include + +static struct vfsmount *shm_mnt; + +#ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ -#include -#include -#include #include #include #include -#include #include -#include -#include #include #include #include #include #include -#include #include #include #include @@ -2485,7 +2493,6 @@ static struct file_system_type tmpfs_fs_type = { .get_sb = shmem_get_sb, .kill_sb = kill_litter_super, }; -static struct vfsmount *shm_mnt; static int __init init_tmpfs(void) { @@ -2524,7 +2531,51 @@ out4: shm_mnt = ERR_PTR(error); return error; } -module_init(init_tmpfs) + +#else /* !CONFIG_SHMEM */ + +/* + * tiny-shmem: simple shmemfs and tmpfs using ramfs code + * + * This is intended for small system where the benefits of the full + * shmem code (swap-backed and resource-limited) are outweighed by + * their complexity. On systems without swap this code should be + * effectively equivalent, but much lighter weight. + */ + +#include + +static struct file_system_type tmpfs_fs_type = { + .name = "tmpfs", + .get_sb = ramfs_get_sb, + .kill_sb = kill_litter_super, +}; + +static int __init init_tmpfs(void) +{ + BUG_ON(register_filesystem(&tmpfs_fs_type) != 0); + + shm_mnt = kern_mount(&tmpfs_fs_type); + BUG_ON(IS_ERR(shm_mnt)); + + return 0; +} + +int shmem_unuse(swp_entry_t entry, struct page *page) +{ + return 0; +} + +#define shmem_file_operations ramfs_file_operations +#define shmem_vm_ops generic_file_vm_ops +#define shmem_get_inode ramfs_get_inode +#define shmem_acct_size(a, b) 0 +#define shmem_unacct_size(a, b) do {} while (0) +#define SHMEM_MAX_BYTES LLONG_MAX + +#endif /* CONFIG_SHMEM */ + +/* common code */ /** * shmem_file_setup - get an unlinked file living in tmpfs @@ -2568,12 +2619,20 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) if (!inode) goto close_file; +#ifdef CONFIG_SHMEM SHMEM_I(inode)->flags = flags & VM_ACCOUNT; +#endif d_instantiate(dentry, inode); inode->i_size = size; inode->i_nlink = 0; /* It is unlinked */ init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ, - &shmem_file_operations); + &shmem_file_operations); + +#ifndef CONFIG_MMU + error = ramfs_nommu_expand_for_mapping(inode, size); + if (error) + goto close_file; +#endif return file; close_file: @@ -2605,3 +2664,5 @@ int shmem_zero_setup(struct vm_area_struct *vma) vma->vm_ops = &shmem_vm_ops; return 0; } + +module_init(init_tmpfs) diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c deleted file mode 100644 index 3e67d575ee6e..000000000000 --- a/mm/tiny-shmem.c +++ /dev/null @@ -1,134 +0,0 @@ -/* - * tiny-shmem.c: simple shmemfs and tmpfs using ramfs code - * - * Matt Mackall January, 2004 - * derived from mm/shmem.c and fs/ramfs/inode.c - * - * This is intended for small system where the benefits of the full - * shmem code (swap-backed and resource-limited) are outweighed by - * their complexity. On systems without swap this code should be - * effectively equivalent, but much lighter weight. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static struct file_system_type tmpfs_fs_type = { - .name = "tmpfs", - .get_sb = ramfs_get_sb, - .kill_sb = kill_litter_super, -}; - -static struct vfsmount *shm_mnt; - -static int __init init_tmpfs(void) -{ - BUG_ON(register_filesystem(&tmpfs_fs_type) != 0); - - shm_mnt = kern_mount(&tmpfs_fs_type); - BUG_ON(IS_ERR(shm_mnt)); - - return 0; -} -module_init(init_tmpfs) - -/** - * shmem_file_setup - get an unlinked file living in tmpfs - * @name: name for dentry (to be seen in /proc//maps - * @size: size to be set for the file - * @flags: vm_flags - */ -struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) -{ - int error; - struct file *file; - struct inode *inode; - struct dentry *dentry, *root; - struct qstr this; - - if (IS_ERR(shm_mnt)) - return (void *)shm_mnt; - - error = -ENOMEM; - this.name = name; - this.len = strlen(name); - this.hash = 0; /* will go */ - root = shm_mnt->mnt_root; - dentry = d_alloc(root, &this); - if (!dentry) - goto put_memory; - - error = -ENFILE; - file = get_empty_filp(); - if (!file) - goto put_dentry; - - error = -ENOSPC; - inode = ramfs_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0); - if (!inode) - goto close_file; - - d_instantiate(dentry, inode); - inode->i_size = size; - inode->i_nlink = 0; /* It is unlinked */ - init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ, - &ramfs_file_operations); - -#ifndef CONFIG_MMU - error = ramfs_nommu_expand_for_mapping(inode, size); - if (error) - goto close_file; -#endif - return file; - -close_file: - put_filp(file); -put_dentry: - dput(dentry); -put_memory: - return ERR_PTR(error); -} -EXPORT_SYMBOL_GPL(shmem_file_setup); - -/** - * shmem_zero_setup - setup a shared anonymous mapping - * @vma: the vma to be mmapped is prepared by do_mmap_pgoff - */ -int shmem_zero_setup(struct vm_area_struct *vma) -{ - struct file *file; - loff_t size = vma->vm_end - vma->vm_start; - - file = shmem_file_setup("dev/zero", size, vma->vm_flags); - if (IS_ERR(file)) - return PTR_ERR(file); - - if (vma->vm_file) - fput(vma->vm_file); - vma->vm_file = file; - vma->vm_ops = &generic_file_vm_ops; - return 0; -} - -int shmem_unuse(swp_entry_t entry, struct page *page) -{ - return 0; -} - -#ifndef CONFIG_MMU -unsigned long shmem_get_unmapped_area(struct file *file, - unsigned long addr, - unsigned long len, - unsigned long pgoff, - unsigned long flags) -{ - return ramfs_nommu_get_unmapped_area(file, addr, len, pgoff, flags); -} -#endif -- cgit v1.2.3 From f99ebf0a86de13f77bc4ee349de96db9f2f67f2e Mon Sep 17 00:00:00 2001 From: Rakib Mullick Date: Tue, 6 Jan 2009 14:40:38 -0800 Subject: init: properly placing noinline keyword checkpatch warns about 'static void noinline'. It wants `static noinline void'. Both are permissible, but the kernel consistently uses `static inline' and `static noinline', and consistency is good. Hence let's keep the checkpatch warning and fix up this code site. [akpm@linux-foundation.org: rewrote changelog] Signed-off-by: Md.Rakib H. Mullick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index cd168ebc5924..90926dadc20d 100644 --- a/init/main.c +++ b/init/main.c @@ -447,7 +447,7 @@ static void __init setup_command_line(char *command_line) * gcc-3.4 accidentally inlines this function, so use noinline. */ -static void noinline __init_refok rest_init(void) +static noinline void __init_refok rest_init(void) __releases(kernel_lock) { int pid; @@ -786,7 +786,7 @@ static void run_init_process(char *init_filename) /* This is a non __init function. Force it to be noinline otherwise gcc * makes it inline to init() and it becomes part of init.text section */ -static int noinline init_post(void) +static noinline int init_post(void) { free_initmem(); unlock_kernel(); -- cgit v1.2.3 From bca1033b092a6fab2ed00036e8a7f6e2df5d99a2 Mon Sep 17 00:00:00 2001 From: Marton Balint Date: Tue, 6 Jan 2009 14:40:43 -0800 Subject: do_mounts: add device info to mount message In the past, I used the root=... command line parameter to specify the root filesystem to the kernel. Now it seems that specifying it is not necessary. The kernel detects the root filesystem even if the kernel command line is empty. My root fs is on a raid1 device by the way, and I am not using initrd for the boot process. If the kernel detects the root filesystem somehow, I think it should print out the result of this detection, otherwise I will not know which device has the root filesystem. Or is there an easy way to get this information on a running system? I had a quick look at the /proc and /sys filesystems, but haven't found anything useful there. Signed-off-by: Marton Balint Cc: Christoph Hellwig Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/do_mounts.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index d055b1914c3d..5efca73b39f9 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -220,10 +220,10 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data) sys_chdir("/root"); ROOT_DEV = current->fs->pwd.mnt->mnt_sb->s_dev; - printk("VFS: Mounted root (%s filesystem)%s.\n", + printk("VFS: Mounted root (%s filesystem)%s on device %u:%u.\n", current->fs->pwd.mnt->mnt_sb->s_type->name, current->fs->pwd.mnt->mnt_sb->s_flags & MS_RDONLY ? - " readonly" : ""); + " readonly" : "", MAJOR(ROOT_DEV), MINOR(ROOT_DEV)); return 0; } -- cgit v1.2.3 From f1883f86dea84fe47a71a39fc1afccc005915ed8 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 6 Jan 2009 14:40:45 -0800 Subject: Remove remaining unwinder code Signed-off-by: Alexey Dobriyan Cc: Gabor Gombas Cc: Jan Beulich Cc: Andi Kleen Cc: Ingo Molnar , Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/unwind.h | 13 --------- arch/x86/kernel/traps.c | 2 -- include/linux/module.h | 3 -- include/linux/unwind.h | 68 ------------------------------------------- init/main.c | 3 -- kernel/module.c | 15 ---------- lib/fault-inject.c | 1 - 7 files changed, 105 deletions(-) delete mode 100644 arch/x86/include/asm/unwind.h delete mode 100644 include/linux/unwind.h (limited to 'init') diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h deleted file mode 100644 index 8b064bd9c553..000000000000 --- a/arch/x86/include/asm/unwind.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef _ASM_X86_UNWIND_H -#define _ASM_X86_UNWIND_H - -#define UNW_PC(frame) ((void)(frame), 0UL) -#define UNW_SP(frame) ((void)(frame), 0UL) -#define UNW_FP(frame) ((void)(frame), 0UL) - -static inline int arch_unw_user_mode(const void *info) -{ - return 0; -} - -#endif /* _ASM_X86_UNWIND_H */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ce6650eb64e9..c9a666cdd3db 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -51,7 +50,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/module.h b/include/linux/module.h index 3bfed013350b..03cb93d1865a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -294,9 +294,6 @@ struct module /* The size of the executable code in each section. */ unsigned int init_text_size, core_text_size; - /* The handle returned from unwind_add_table. */ - void *unwind_info; - /* Arch-specific module values */ struct mod_arch_specific arch; diff --git a/include/linux/unwind.h b/include/linux/unwind.h deleted file mode 100644 index 7760860fa170..000000000000 --- a/include/linux/unwind.h +++ /dev/null @@ -1,68 +0,0 @@ -#ifndef _LINUX_UNWIND_H -#define _LINUX_UNWIND_H - -/* - * Copyright (C) 2002-2006 Novell, Inc. - * Jan Beulich - * This code is released under version 2 of the GNU GPL. - * - * A simple API for unwinding kernel stacks. This is used for - * debugging and error reporting purposes. The kernel doesn't need - * full-blown stack unwinding with all the bells and whistles, so there - * is not much point in implementing the full Dwarf2 unwind API. - */ - -struct module; - -struct unwind_frame_info {}; - -static inline void unwind_init(void) {} -static inline void unwind_setup(void) {} - -#ifdef CONFIG_MODULES - -static inline void *unwind_add_table(struct module *mod, - const void *table_start, - unsigned long table_size) -{ - return NULL; -} - -static inline void unwind_remove_table(void *handle, int init_only) -{ -} - -#endif - -static inline int unwind_init_frame_info(struct unwind_frame_info *info, - struct task_struct *tsk, - const struct pt_regs *regs) -{ - return -ENOSYS; -} - -static inline int unwind_init_blocked(struct unwind_frame_info *info, - struct task_struct *tsk) -{ - return -ENOSYS; -} - -static inline int unwind_init_running(struct unwind_frame_info *info, - asmlinkage int (*cb)(struct unwind_frame_info *, - void *arg), - void *arg) -{ - return -ENOSYS; -} - -static inline int unwind(struct unwind_frame_info *info) -{ - return -ENOSYS; -} - -static inline int unwind_to_user(struct unwind_frame_info *info) -{ - return -ENOSYS; -} - -#endif /* _LINUX_UNWIND_H */ diff --git a/init/main.c b/init/main.c index 90926dadc20d..e119dd28dd7d 100644 --- a/init/main.c +++ b/init/main.c @@ -50,7 +50,6 @@ #include #include #include -#include #include #include #include @@ -537,7 +536,6 @@ asmlinkage void __init start_kernel(void) * Need to run as early as possible, to initialize the * lockdep hash: */ - unwind_init(); lockdep_init(); debug_objects_early_init(); cgroup_init_early(); @@ -559,7 +557,6 @@ asmlinkage void __init start_kernel(void) setup_arch(&command_line); mm_init_owner(&init_mm, &init_task); setup_command_line(command_line); - unwind_setup(); setup_per_cpu_areas(); setup_nr_cpu_ids(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ diff --git a/kernel/module.c b/kernel/module.c index f47cce910f25..34b56cf06615 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -43,7 +43,6 @@ #include #include #include -#include #include #include #include @@ -1449,8 +1448,6 @@ static void free_module(struct module *mod) remove_sect_attrs(mod); mod_kobject_remove(mod); - unwind_remove_table(mod->unwind_info, 0); - /* Arch-specific cleanup. */ module_arch_cleanup(mod); @@ -1867,7 +1864,6 @@ static noinline struct module *load_module(void __user *umod, unsigned int symindex = 0; unsigned int strindex = 0; unsigned int modindex, versindex, infoindex, pcpuindex; - unsigned int unwindex = 0; unsigned int num_kp, num_mcount; struct kernel_param *kp; struct module *mod; @@ -1957,9 +1953,6 @@ static noinline struct module *load_module(void __user *umod, versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); -#ifdef ARCH_UNWIND_SECTION_NAME - unwindex = find_sec(hdr, sechdrs, secstrings, ARCH_UNWIND_SECTION_NAME); -#endif /* Don't keep modinfo and version sections. */ sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; @@ -1969,8 +1962,6 @@ static noinline struct module *load_module(void __user *umod, sechdrs[symindex].sh_flags |= SHF_ALLOC; sechdrs[strindex].sh_flags |= SHF_ALLOC; #endif - if (unwindex) - sechdrs[unwindex].sh_flags |= SHF_ALLOC; /* Check module struct version now, before we try to use module. */ if (!check_modstruct_version(sechdrs, versindex, mod)) { @@ -2267,11 +2258,6 @@ static noinline struct module *load_module(void __user *umod, add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - /* Size of section 0 is 0, so this works well if no unwind info. */ - mod->unwind_info = unwind_add_table(mod, - (void *)sechdrs[unwindex].sh_addr, - sechdrs[unwindex].sh_size); - /* Get rid of temporary copy */ vfree(hdr); @@ -2370,7 +2356,6 @@ sys_init_module(void __user *umod, mutex_lock(&module_mutex); /* Drop initial reference. */ module_put(mod); - unwind_remove_table(mod->unwind_info, 1); module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; diff --git a/lib/fault-inject.c b/lib/fault-inject.c index a50a311554cc..f97af55bdd96 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -6,7 +6,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From ff083c8372f6312bb3a8c7f7b748920aeeb210c9 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Tue, 6 Jan 2009 14:40:53 -0800 Subject: autodetect_raid: add missing __init marking The function autodetect_raid is only used by __init functions, and it refers to __initdata, so it needs __init markings. Fixes this error: The function autodetect_raid() references the variable __initdata raid_noautodetect. This is often because autodetect_raid lacks a __initdata annotation or the annotation of raid_noautodetect is wrong. Signed-off-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/do_mounts_md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index d6da5cdd3c38..ff95e3192884 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -271,7 +271,7 @@ static int __init raid_setup(char *str) __setup("raid=", raid_setup); __setup("md=", md_setup); -static void autodetect_raid(void) +static void __init autodetect_raid(void) { int fd; -- cgit v1.2.3 From d2e3192b6e372a441c18bc8cb32f89ef38f105b7 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 6 Jan 2009 14:41:10 -0800 Subject: init/main.c: mark late_time_init as __initdata Signed-off-by: Jan Beulich Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index e119dd28dd7d..b5a892c68375 100644 --- a/init/main.c +++ b/init/main.c @@ -107,7 +107,7 @@ EXPORT_SYMBOL(system_state); extern void time_init(void); /* Default late time init is NULL. archs can override this later. */ -void (*late_time_init)(void); +void (*__initdata late_time_init)(void); extern void softirq_init(void); /* Untouched command line saved by arch-specific code. */ -- cgit v1.2.3 From 22a9d645677feefd402befd02edd59b122289ef1 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 7 Jan 2009 08:45:46 -0800 Subject: async: Asynchronous function calls to speed up kernel boot Right now, most of the kernel boot is strictly synchronous, such that various hardware delays are done sequentially. In order to make the kernel boot faster, this patch introduces infrastructure to allow doing some of the initialization steps asynchronously, which will hide significant portions of the hardware delays in practice. In order to not change device order and other similar observables, this patch does NOT do full parallel initialization. Rather, it operates more in the way an out of order CPU does; the work may be done out of order and asynchronous, but the observable effects (instruction retiring for the CPU) are still done in the original sequence. Signed-off-by: Arjan van de Ven --- include/linux/async.h | 25 ++++ init/do_mounts.c | 2 + init/main.c | 5 +- kernel/Makefile | 3 +- kernel/async.c | 321 +++++++++++++++++++++++++++++++++++++++++++++++++ kernel/irq/autoprobe.c | 5 + kernel/module.c | 2 + 7 files changed, 361 insertions(+), 2 deletions(-) create mode 100644 include/linux/async.h create mode 100644 kernel/async.c (limited to 'init') diff --git a/include/linux/async.h b/include/linux/async.h new file mode 100644 index 000000000000..c4ecacd0b327 --- /dev/null +++ b/include/linux/async.h @@ -0,0 +1,25 @@ +/* + * async.h: Asynchronous function calls for boot performance + * + * (C) Copyright 2009 Intel Corporation + * Author: Arjan van de Ven + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include +#include + +typedef u64 async_cookie_t; +typedef void (async_func_ptr) (void *data, async_cookie_t cookie); + +extern async_cookie_t async_schedule(async_func_ptr *ptr, void *data); +extern async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *list); +extern void async_synchronize_full(void); +extern void async_synchronize_full_special(struct list_head *list); +extern void async_synchronize_cookie(async_cookie_t cookie); +extern void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *list); + diff --git a/init/do_mounts.c b/init/do_mounts.c index 5efca73b39f9..708105e163df 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -372,6 +373,7 @@ void __init prepare_namespace(void) /* wait for the known devices to complete their probing */ while (driver_probe_done() != 0) msleep(100); + async_synchronize_full(); md_run_setup(); diff --git a/init/main.c b/init/main.c index b5a892c68375..f66715d8a853 100644 --- a/init/main.c +++ b/init/main.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include @@ -684,7 +685,7 @@ asmlinkage void __init start_kernel(void) rest_init(); } -static int initcall_debug; +int initcall_debug; core_param(initcall_debug, initcall_debug, bool, 0644); int do_one_initcall(initcall_t fn) @@ -785,6 +786,8 @@ static void run_init_process(char *init_filename) */ static noinline int init_post(void) { + /* need to finish all async __init code before freeing the memory */ + async_synchronize_full(); free_initmem(); unlock_kernel(); mark_rodata_ro(); diff --git a/kernel/Makefile b/kernel/Makefile index e1c5bf3365c0..2921d90ce32f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -9,7 +9,8 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ - notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o + notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ + async.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files diff --git a/kernel/async.c b/kernel/async.c new file mode 100644 index 000000000000..afaa8a653d5a --- /dev/null +++ b/kernel/async.c @@ -0,0 +1,321 @@ +/* + * async.c: Asynchronous function calls for boot performance + * + * (C) Copyright 2009 Intel Corporation + * Author: Arjan van de Ven + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + + +/* + +Goals and Theory of Operation + +The primary goal of this feature is to reduce the kernel boot time, +by doing various independent hardware delays and discovery operations +decoupled and not strictly serialized. + +More specifically, the asynchronous function call concept allows +certain operations (primarily during system boot) to happen +asynchronously, out of order, while these operations still +have their externally visible parts happen sequentially and in-order. +(not unlike how out-of-order CPUs retire their instructions in order) + +Key to the asynchronous function call implementation is the concept of +a "sequence cookie" (which, although it has an abstracted type, can be +thought of as a monotonically incrementing number). + +The async core will assign each scheduled event such a sequence cookie and +pass this to the called functions. + +The asynchronously called function should before doing a globally visible +operation, such as registering device numbers, call the +async_synchronize_cookie() function and pass in its own cookie. The +async_synchronize_cookie() function will make sure that all asynchronous +operations that were scheduled prior to the operation corresponding with the +cookie have completed. + +Subsystem/driver initialization code that scheduled asynchronous probe +functions, but which shares global resources with other drivers/subsystems +that do not use the asynchronous call feature, need to do a full +synchronization with the async_synchronize_full() function, before returning +from their init function. This is to maintain strict ordering between the +asynchronous and synchronous parts of the kernel. + +*/ + +#include +#include +#include +#include +#include +#include +#include + +static async_cookie_t next_cookie = 1; + +#define MAX_THREADS 256 +#define MAX_WORK 32768 + +static LIST_HEAD(async_pending); +static LIST_HEAD(async_running); +static DEFINE_SPINLOCK(async_lock); + +struct async_entry { + struct list_head list; + async_cookie_t cookie; + async_func_ptr *func; + void *data; + struct list_head *running; +}; + +static DECLARE_WAIT_QUEUE_HEAD(async_done); +static DECLARE_WAIT_QUEUE_HEAD(async_new); + +static atomic_t entry_count; +static atomic_t thread_count; + +extern int initcall_debug; + + +/* + * MUST be called with the lock held! + */ +static async_cookie_t __lowest_in_progress(struct list_head *running) +{ + struct async_entry *entry; + if (!list_empty(&async_pending)) { + entry = list_first_entry(&async_pending, + struct async_entry, list); + return entry->cookie; + } else if (!list_empty(running)) { + entry = list_first_entry(running, + struct async_entry, list); + return entry->cookie; + } else { + /* nothing in progress... next_cookie is "infinity" */ + return next_cookie; + } + +} +/* + * pick the first pending entry and run it + */ +static void run_one_entry(void) +{ + unsigned long flags; + struct async_entry *entry; + ktime_t calltime, delta, rettime; + + /* 1) pick one task from the pending queue */ + + spin_lock_irqsave(&async_lock, flags); + if (list_empty(&async_pending)) + goto out; + entry = list_first_entry(&async_pending, struct async_entry, list); + + /* 2) move it to the running queue */ + list_del(&entry->list); + list_add_tail(&entry->list, &async_running); + spin_unlock_irqrestore(&async_lock, flags); + + /* 3) run it (and print duration)*/ + if (initcall_debug) { + printk("calling %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current)); + calltime = ktime_get(); + } + entry->func(entry->data, entry->cookie); + if (initcall_debug) { + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie, + entry->func, ktime_to_ns(delta) >> 10); + } + + /* 4) remove it from the running queue */ + spin_lock_irqsave(&async_lock, flags); + list_del(&entry->list); + + /* 5) free the entry */ + kfree(entry); + atomic_dec(&entry_count); + + spin_unlock_irqrestore(&async_lock, flags); + + /* 6) wake up any waiters. */ + wake_up(&async_done); + return; + +out: + spin_unlock_irqrestore(&async_lock, flags); +} + + +static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running) +{ + struct async_entry *entry; + unsigned long flags; + async_cookie_t newcookie; + + + /* allow irq-off callers */ + entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); + + /* + * If we're out of memory or if there's too much work + * pending already, we execute synchronously. + */ + if (!entry || atomic_read(&entry_count) > MAX_WORK) { + kfree(entry); + spin_lock_irqsave(&async_lock, flags); + newcookie = next_cookie++; + spin_unlock_irqrestore(&async_lock, flags); + + /* low on memory.. run synchronously */ + ptr(data, newcookie); + return newcookie; + } + entry->func = ptr; + entry->data = data; + entry->running = running; + + spin_lock_irqsave(&async_lock, flags); + newcookie = entry->cookie = next_cookie++; + list_add_tail(&entry->list, &async_pending); + atomic_inc(&entry_count); + spin_unlock_irqrestore(&async_lock, flags); + wake_up(&async_new); + return newcookie; +} + +async_cookie_t async_schedule(async_func_ptr *ptr, void *data) +{ + return __async_schedule(ptr, data, &async_pending); +} +EXPORT_SYMBOL_GPL(async_schedule); + +async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running) +{ + return __async_schedule(ptr, data, running); +} +EXPORT_SYMBOL_GPL(async_schedule_special); + +void async_synchronize_full(void) +{ + async_synchronize_cookie(next_cookie); +} +EXPORT_SYMBOL_GPL(async_synchronize_full); + +void async_synchronize_full_special(struct list_head *list) +{ + async_synchronize_cookie_special(next_cookie, list); +} +EXPORT_SYMBOL_GPL(async_synchronize_full_special); + +void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running) +{ + ktime_t starttime, delta, endtime; + + if (initcall_debug) { + printk("async_waiting @ %i\n", task_pid_nr(current)); + starttime = ktime_get(); + } + + wait_event(async_done, __lowest_in_progress(running) >= cookie); + + if (initcall_debug) { + endtime = ktime_get(); + delta = ktime_sub(endtime, starttime); + + printk("async_continuing @ %i after %lli usec\n", + task_pid_nr(current), ktime_to_ns(delta) >> 10); + } +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); + +void async_synchronize_cookie(async_cookie_t cookie) +{ + async_synchronize_cookie_special(cookie, &async_running); +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie); + + +static int async_thread(void *unused) +{ + DECLARE_WAITQUEUE(wq, current); + add_wait_queue(&async_new, &wq); + + while (!kthread_should_stop()) { + int ret = HZ; + set_current_state(TASK_INTERRUPTIBLE); + /* + * check the list head without lock.. false positives + * are dealt with inside run_one_entry() while holding + * the lock. + */ + rmb(); + if (!list_empty(&async_pending)) + run_one_entry(); + else + ret = schedule_timeout(HZ); + + if (ret == 0) { + /* + * we timed out, this means we as thread are redundant. + * we sign off and die, but we to avoid any races there + * is a last-straw check to see if work snuck in. + */ + atomic_dec(&thread_count); + wmb(); /* manager must see our departure first */ + if (list_empty(&async_pending)) + break; + /* + * woops work came in between us timing out and us + * signing off; we need to stay alive and keep working. + */ + atomic_inc(&thread_count); + } + } + remove_wait_queue(&async_new, &wq); + + return 0; +} + +static int async_manager_thread(void *unused) +{ + DECLARE_WAITQUEUE(wq, current); + add_wait_queue(&async_new, &wq); + + while (!kthread_should_stop()) { + int tc, ec; + + set_current_state(TASK_INTERRUPTIBLE); + + tc = atomic_read(&thread_count); + rmb(); + ec = atomic_read(&entry_count); + + while (tc < ec && tc < MAX_THREADS) { + kthread_run(async_thread, NULL, "async/%i", tc); + atomic_inc(&thread_count); + tc++; + } + + schedule(); + } + remove_wait_queue(&async_new, &wq); + + return 0; +} + +static int __init async_init(void) +{ + kthread_run(async_manager_thread, NULL, "async/mgr"); + return 0; +} + +core_initcall(async_init); diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index cc0f7321b8ce..1de9700f416e 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internals.h" @@ -34,6 +35,10 @@ unsigned long probe_irq_on(void) unsigned int status; int i; + /* + * quiesce the kernel, or at least the asynchronous portion + */ + async_synchronize_full(); mutex_lock(&probing_active); /* * something may have generated an irq long ago and we want to diff --git a/kernel/module.c b/kernel/module.c index 496dcb57b608..c9332c90d5a0 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -50,6 +50,7 @@ #include #include #include +#include #if 0 #define DEBUGP printk @@ -816,6 +817,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags) mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + async_synchronize_full(); mutex_lock(&module_mutex); /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); -- cgit v1.2.3 From cb6ff208076b5f434db1b8c983429269d719cef5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 8 Jan 2009 12:04:48 +0000 Subject: NOMMU: Support XIP on initramfs Support XIP on files unpacked from the initramfs image on NOMMU systems. This simply requires the length of the file to be preset so that the ramfs fs can attempt to garner sufficient contiguous storage to store the file (NOMMU mmap can only map contiguous RAM). All the other bits to do XIP on initramfs files are present: (1) ramfs's truncate attempts to allocate a contiguous run of pages when a file is truncated upwards from nothing. (2) ramfs sets BDI on its files to indicate direct mapping is possible, and that its files can be mapped for read, write and exec. (3) NOMMU mmap() will use the above bits to determine that it can do XIP. Possibly this needs better controls, because it will _always_ try and do XIP. One disadvantage of this very simplistic approach is that sufficient space will be allocated to store the whole file, and not just the bit that would be XIP'd. To deal with this, though, the initramfs unpacker would have to be able to parse the file contents. Signed-off-by: David Howells Acked-by: Paul Mundt --- init/initramfs.c | 1 + 1 file changed, 1 insertion(+) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index 4f5ba75aaa7c..d9c941c0c3ca 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -317,6 +317,7 @@ static int __init do_name(void) if (wfd >= 0) { sys_fchown(wfd, uid, gid); sys_fchmod(wfd, mode); + sys_ftruncate(wfd, body_len); vcollected = kstrdup(collected, GFP_KERNEL); state = CopyFile; } -- cgit v1.2.3 From 5cdc38f98596662620b822a4e13f797c3f2f65e0 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:07:30 -0800 Subject: cgroups: make cgroup config a submenu Making CGROUP related configs be a sub-menu. This patch make CGROUP related configs be a sub-menu and makes 1st level configs of "General Setup" shorter. including following additional changes - add help comment about CGROUPS and GROUP_SCHED. - moved MM_OWNER config to the bottom. (for good indent in menuconfig) Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Daisuke Nishimura Cc: Balbir Singh Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 123 ++++++++++++++++++++++++++++++++--------------------------- 1 file changed, 67 insertions(+), 56 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index e7893b1d3e42..6fcd192aa60d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -271,59 +271,6 @@ config LOG_BUF_SHIFT 13 => 8 KB 12 => 4 KB -config CGROUPS - bool "Control Group support" - help - This option will let you use process cgroup subsystems - such as Cpusets - - Say N if unsure. - -config CGROUP_DEBUG - bool "Example debug cgroup subsystem" - depends on CGROUPS - default n - help - This option enables a simple cgroup subsystem that - exports useful debugging information about the cgroups - framework - - Say N if unsure - -config CGROUP_NS - bool "Namespace cgroup subsystem" - depends on CGROUPS - help - Provides a simple namespace cgroup subsystem to - provide hierarchical naming of sets of namespaces, - for instance virtual servers and checkpoint/restart - jobs. - -config CGROUP_FREEZER - bool "control group freezer subsystem" - depends on CGROUPS - help - Provides a way to freeze and unfreeze all tasks in a - cgroup. - -config CGROUP_DEVICE - bool "Device controller for cgroups" - depends on CGROUPS && EXPERIMENTAL - help - Provides a cgroup implementing whitelists for devices which - a process in the cgroup can mknod or open. - -config CPUSETS - bool "Cpuset support" - depends on SMP && CGROUPS - help - This option will let you create and manage CPUSETs which - allow dynamically partitioning a system into sets of CPUs and - Memory Nodes and assigning tasks to run only within those sets. - This is primarily useful on large SMP or NUMA systems. - - Say N if unsure. - # # Architectures with an unreliable sched_clock() should select this: # @@ -337,6 +284,8 @@ config GROUP_SCHED help This feature lets CPU scheduler recognize task groups and control CPU bandwidth allocation to such task groups. + In order to create a group from arbitrary set of processes, use + CONFIG_CGROUPS. (See Control Group support.) config FAIR_GROUP_SCHED bool "Group scheduling for SCHED_OTHER" @@ -379,6 +328,66 @@ config CGROUP_SCHED endchoice +menu "Control Group support" +config CGROUPS + bool "Control Group support" + help + This option add support for grouping sets of processes together, for + use with process control subsystems such as Cpusets, CFS, memory + controls or device isolation. + See + - Documentation/cpusets.txt (Cpusets) + - Documentation/scheduler/sched-design-CFS.txt (CFS) + - Documentation/cgroups/ (features for grouping, isolation) + - Documentation/controllers/ (features for resource control) + + Say N if unsure. + +config CGROUP_DEBUG + bool "Example debug cgroup subsystem" + depends on CGROUPS + default n + help + This option enables a simple cgroup subsystem that + exports useful debugging information about the cgroups + framework + + Say N if unsure + +config CGROUP_NS + bool "Namespace cgroup subsystem" + depends on CGROUPS + help + Provides a simple namespace cgroup subsystem to + provide hierarchical naming of sets of namespaces, + for instance virtual servers and checkpoint/restart + jobs. + +config CGROUP_FREEZER + bool "control group freezer subsystem" + depends on CGROUPS + help + Provides a way to freeze and unfreeze all tasks in a + cgroup. + +config CGROUP_DEVICE + bool "Device controller for cgroups" + depends on CGROUPS && EXPERIMENTAL + help + Provides a cgroup implementing whitelists for devices which + a process in the cgroup can mknod or open. + +config CPUSETS + bool "Cpuset support" + depends on SMP && CGROUPS + help + This option will let you create and manage CPUSETs which + allow dynamically partitioning a system into sets of CPUs and + Memory Nodes and assigning tasks to run only within those sets. + This is primarily useful on large SMP or NUMA systems. + + Say N if unsure. + config CGROUP_CPUACCT bool "Simple CPU accounting cgroup subsystem" depends on CGROUPS @@ -393,9 +402,6 @@ config RESOURCE_COUNTERS infrastructure that works with cgroups depends on CGROUPS -config MM_OWNER - bool - config CGROUP_MEM_RES_CTLR bool "Memory Resource Controller for Control Groups" depends on CGROUPS && RESOURCE_COUNTERS @@ -419,6 +425,11 @@ config CGROUP_MEM_RES_CTLR This config option also selects MM_OWNER config option, which could in turn add some fork/exit overhead. +config MM_OWNER + bool + +endmenu + config SYSFS_DEPRECATED bool -- cgit v1.2.3 From c9d5409f8d46fd0d18b4a4481d9caa04076d87fc Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:07:35 -0800 Subject: memcg: fix a typo in Kconfig s/contoller/controller/ Signed-of-by: Li Zefan Cc: Paul Menage Acked-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 6fcd192aa60d..7cbe1f43ca22 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -420,7 +420,7 @@ config CGROUP_MEM_RES_CTLR sure you need the memory resource controller. Even when you enable this, you can set "cgroup_disable=memory" at your boot option to disable memory resource controller and you can avoid overheads. - (and lose benefits of memory resource contoller) + (and lose benefits of memory resource controller) This config option also selects MM_OWNER config option, which could in turn add some fork/exit overhead. -- cgit v1.2.3 From c077719be8e9e6b55702117513d1b5f41d80404a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 7 Jan 2009 18:07:57 -0800 Subject: memcg: mem+swap controller Kconfig Config and control variable for mem+swap controller. This patch adds CONFIG_CGROUP_MEM_RES_CTLR_SWAP (memory resource controller swap extension.) For accounting swap, it's obvious that we have to use additional memory to remember "who uses swap". This adds more overhead. So, it's better to offer "choice" to users. This patch adds 2 choices. This patch adds 2 parameters to enable swap extension or not. - CONFIG - boot option Reviewed-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 3 +++ include/linux/memcontrol.h | 3 +++ init/Kconfig | 17 +++++++++++++++++ mm/memcontrol.c | 34 ++++++++++++++++++++++++++++++++++ 4 files changed, 57 insertions(+) (limited to 'init') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 532eacbbed62..fb849020aea9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1562,6 +1562,9 @@ and is between 256 and 4096 characters. It is defined in the file nosoftlockup [KNL] Disable the soft-lockup detector. + noswapaccount [KNL] Disable accounting of swap in memory resource + controller. (See Documentation/controllers/memory.txt) + nosync [HW,M68K] Disables sync negotiation for all devices. notsc [BUGS=X86-32] Disable Time Stamp Counter diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b095f5f6ecf7..41b46cc9d1f1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -77,6 +77,9 @@ extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone, int priority, enum lru_list lru); +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +extern int do_swap_account; +#endif #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct mem_cgroup; diff --git a/init/Kconfig b/init/Kconfig index 7cbe1f43ca22..a724a149bf3f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -428,6 +428,23 @@ config CGROUP_MEM_RES_CTLR config MM_OWNER bool +config CGROUP_MEM_RES_CTLR_SWAP + bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)" + depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL + help + Add swap management feature to memory resource controller. When you + enable this, you can limit mem+swap usage per cgroup. In other words, + when you disable this, memory resource controller has no cares to + usage of swap...a process can exhaust all of the swap. This extension + is useful when you want to avoid exhaustion swap but this itself + adds more overheads and consumes memory for remembering information. + Especially if you use 32bit system or small memory system, please + be careful about enabling this. When memory resource controller + is disabled by boot option, this will be automatically disabled and + there will be no overhead from this. Even when you set this config=y, + if boot option "noswapaccount" is set, swap will not be accounted. + + endmenu config SYSFS_DEPRECATED diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7288e9d85ca7..59dd8c116372 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -41,6 +41,15 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */ +int do_swap_account __read_mostly; +static int really_do_swap_account __initdata = 1; /* for remember boot option*/ +#else +#define do_swap_account (0) +#endif + + /* * Statistics for memory cgroup. */ @@ -1404,6 +1413,18 @@ static void mem_cgroup_free(struct mem_cgroup *mem) } +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +static void __init enable_swap_cgroup(void) +{ + if (!mem_cgroup_subsys.disabled && really_do_swap_account) + do_swap_account = 1; +} +#else +static void __init enable_swap_cgroup(void) +{ +} +#endif + static struct cgroup_subsys_state * mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { @@ -1419,6 +1440,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; + /* root ? */ + if (cont->parent == NULL) + enable_swap_cgroup(); return &mem->css; free_out: @@ -1490,3 +1514,13 @@ struct cgroup_subsys mem_cgroup_subsys = { .attach = mem_cgroup_move_task, .early_init = 0, }; + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP + +static int __init disable_swap_account(char *s) +{ + really_do_swap_account = 0; + return 1; +} +__setup("noswapaccount", disable_swap_account); +#endif -- cgit v1.2.3