From ab84d31e15502fb626169ba2663381e34bf965b2 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Thu, 21 Jul 2011 09:43:28 -0700 Subject: sched: Introduce primitives to account for CFS bandwidth tracking In this patch we introduce the notion of CFS bandwidth, partitioned into globally unassigned bandwidth, and locally claimed bandwidth. - The global bandwidth is per task_group, it represents a pool of unclaimed bandwidth that cfs_rqs can allocate from. - The local bandwidth is tracked per-cfs_rq, this represents allotments from the global pool bandwidth assigned to a specific cpu. Bandwidth is managed via cgroupfs, adding two new interfaces to the cpu subsystem: - cpu.cfs_period_us : the bandwidth period in usecs - cpu.cfs_quota_us : the cpu bandwidth (in usecs) that this tg will be allowed to consume over period above. Signed-off-by: Paul Turner Signed-off-by: Nikhil Rao Signed-off-by: Bharata B Rao Reviewed-by: Hidetoshi Seto Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110721184756.972636699@google.com Signed-off-by: Ingo Molnar --- init/Kconfig | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index d627783..d19b3a7 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -715,6 +715,18 @@ config FAIR_GROUP_SCHED depends on CGROUP_SCHED default CGROUP_SCHED +config CFS_BANDWIDTH + bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" + depends on EXPERIMENTAL + depends on FAIR_GROUP_SCHED + default n + help + This option allows users to define CPU bandwidth rates (limits) for + tasks running within the fair group scheduler. Groups with no limit + set are considered to be unconstrained and will run with no + restriction. + See tip/Documentation/scheduler/sched-bwc.txt for more information. + config RT_GROUP_SCHED bool "Group scheduling for SCHED_RR/FIFO" depends on EXPERIMENTAL -- cgit v1.1 From 8008e129dc90ff4f7a56cb033d6bd042afe3ed52 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 8 Jun 2011 16:31:33 -0700 Subject: rcu: Drive configuration directly from SMP and PREEMPT This commit eliminates the possibility of running TREE_PREEMPT_RCU when SMP=n and of running TINY_RCU when PREEMPT=y. People who really want these combinations can hand-edit init/Kconfig, but eliminating them as choices for production systems reduces the amount of testing required. It will also allow cutting out a few #ifdefs. Note that running TREE_RCU and TINY_RCU on single-CPU systems using SMP-built kernels is still supported. Signed-off-by: Paul E. McKenney --- init/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index d627783..dc7e27b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -391,7 +391,7 @@ config TREE_RCU config TREE_PREEMPT_RCU bool "Preemptible tree-based hierarchical RCU" - depends on PREEMPT + depends on PREEMPT && SMP help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -401,7 +401,7 @@ config TREE_PREEMPT_RCU config TINY_RCU bool "UP-only small-memory-footprint RCU" - depends on !SMP + depends on !PREEMPT && !SMP help This option selects the RCU implementation that is designed for UP systems from which real-time response @@ -410,7 +410,7 @@ config TINY_RCU config TINY_PREEMPT_RCU bool "Preemptible UP-only small-memory-footprint RCU" - depends on !SMP && PREEMPT + depends on PREEMPT && !SMP help This option selects the RCU implementation that is designed for real-time UP systems. This option greatly reduces the -- cgit v1.1 From 97ce2c88f9ad42e3c60a9beb9fca87abf3639faa Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 12 Oct 2011 16:17:54 -0700 Subject: jump-label: initialize jump-label subsystem much earlier Initialize jump_labels much, much earlier, so they're available for use during system setup. Signed-off-by: Jeremy Fitzhardinge Acked-by: Peter Zijlstra --- init/main.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index 2a9b88a..29d8d84 100644 --- a/init/main.c +++ b/init/main.c @@ -515,6 +515,9 @@ asmlinkage void __init start_kernel(void) parse_args("Booting kernel", static_command_line, __start___param, __stop___param - __start___param, &unknown_bootoption); + + jump_label_init(); + /* * These use large bootmem allocations and must precede * kmem_cache_init() -- cgit v1.1 From b1e4d20cbf2ef8e27515da032b95fdcbb5b06bf1 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Mon, 10 Oct 2011 00:03:37 +0200 Subject: params: make dashes and underscores in parameter names truly equal The user may use "foo-bar" for a kernel parameter defined as "foo_bar". Make sure it works the other way around too. Apply the equality of dashes and underscores on early_params and __setup params as well. The example given in Documentation/kernel-parameters.txt indicates that this is the intended behaviour. With the patch the kernel accepts "log-buf-len=1M" as expected. https://bugzilla.redhat.com/show_bug.cgi?id=744545 Signed-off-by: Michal Schmidt Signed-off-by: Rusty Russell (neatened implementations) --- 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 03b408d..63f5f6f 100644 --- a/init/main.c +++ b/init/main.c @@ -163,7 +163,7 @@ static int __init obsolete_checksetup(char *line) p = __setup_start; do { int n = strlen(p->str); - if (!strncmp(line, p->str, n)) { + if (parameqn(line, p->str, n)) { if (p->early) { /* Already done in parse_early_param? * (Needs exact match on param part). @@ -392,7 +392,7 @@ static int __init do_early_param(char *param, char *val) const struct obs_kernel_param *p; for (p = __setup_start; p < __setup_end; p++) { - if ((p->early && strcmp(param, p->str) == 0) || + if ((p->early && parameq(param, p->str)) || (strcmp(param, "console") == 0 && strcmp(p->str, "earlycon") == 0) ) { -- cgit v1.1 From f919b9235f930e649b374a50009c6c268bd9a073 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Wed, 2 Nov 2011 13:37:47 -0700 Subject: init/do_mounts_rd.c: fix ramdisk identification for padded cramfs When a cramfs ramdisk padded with 512 bytes is given to the kernel, the current identify_ramdisk_image function fails to identify it. Tested with a padded cramfs image on an ARM based board. Signed-off-by: Neil Armstrong Cc: Namhyung Kim Cc: Davidlohr Bueso Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 fe9acb0..887629e 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -120,6 +120,20 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) } /* + * Read 512 bytes further to check if cramfs is padded + */ + sys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0); + sys_read(fd, buf, size); + + if (cramfsb->magic == CRAMFS_MAGIC) { + printk(KERN_NOTICE + "RAMDISK: cramfs filesystem found at block %d\n", + start_block); + nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS; + goto done; + } + + /* * Read block 1 to test for minix and ext2 superblock */ sys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0); -- cgit v1.1 From 79975f1327850ef198ada994c2fc44b7d1ea8935 Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Wed, 2 Nov 2011 13:38:59 -0700 Subject: init: add root=PARTUUID=UUID/PARTNROFF=%d support Expand root=PARTUUID=UUID syntax to support selecting a root partition by integer offset from a known, unique partition. This approach provides similar properties to specifying a device and partition number, but using the UUID as the unique path prior to evaluating the offset. For example, root=PARTUUID=99DE9194-FC15-4223-9192-FC243948F88B/PARTNROFF=1 selects the partition with UUID 99DE.. then select the next partition. This change is motivated by a particular usecase in Chromium OS where the bootloader can easily determine what partition it is on (by UUID) but doesn't perform general partition table walking. That said, support for this model provides a direct mechanism for the user to modify the root partition to boot without specifically needing to extract each UUID or update the bootloader explicitly when the root partition UUID is changed (if it is recreated to be larger, for instance). Pinning to a /boot-style partition UUID allows the arbitrary root partition reconfiguration/modifications with slightly less ambiguity than just [dev][partition] and less stringency than the specific root partition UUID. [sfr@canb.auug.org.au: fix init sections warning] Signed-off-by: Will Drewry Cc: Kay Sievers Cc: Randy Dunlap Cc: Namhyung Kim Cc: Trond Myklebust Cc: Jens Axboe Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/do_mounts.c | 48 +++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 43 insertions(+), 5 deletions(-) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index c0851a8..0f6e1d9 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -28,7 +28,7 @@ int __initdata rd_doload; /* 1 = load RAM disk, 0 = don't load */ int root_mountflags = MS_RDONLY | MS_SILENT; static char * __initdata root_device_name; static char __initdata saved_root_name[64]; -static int __initdata root_wait; +static int root_wait; dev_t ROOT_DEV; @@ -85,12 +85,15 @@ no_match: /** * devt_from_partuuid - looks up the dev_t of a partition by its UUID - * @uuid: 36 byte char array containing a hex ascii UUID + * @uuid: min 36 byte char array containing a hex ascii UUID * * The function will return the first partition which contains a matching * UUID value in its partition_meta_info struct. This does not search * by filesystem UUIDs. * + * If @uuid is followed by a "/PARTNROFF=%d", then the number will be + * extracted and used as an offset from the partition identified by the UUID. + * * Returns the matching dev_t on success or 0 on failure. */ static dev_t devt_from_partuuid(char *uuid_str) @@ -98,6 +101,28 @@ static dev_t devt_from_partuuid(char *uuid_str) dev_t res = 0; struct device *dev = NULL; u8 uuid[16]; + struct gendisk *disk; + struct hd_struct *part; + int offset = 0; + + if (strlen(uuid_str) < 36) + goto done; + + /* Check for optional partition number offset attributes. */ + if (uuid_str[36]) { + char c = 0; + /* Explicitly fail on poor PARTUUID syntax. */ + if (sscanf(&uuid_str[36], + "/PARTNROFF=%d%c", &offset, &c) != 1) { + printk(KERN_ERR "VFS: PARTUUID= is invalid.\n" + "Expected PARTUUID=[/PARTNROFF=%%d]\n"); + if (root_wait) + printk(KERN_ERR + "Disabling rootwait; root= is invalid.\n"); + root_wait = 0; + goto done; + } + } /* Pack the requested UUID in the expected format. */ part_pack_uuid(uuid_str, uuid); @@ -107,8 +132,21 @@ static dev_t devt_from_partuuid(char *uuid_str) goto done; res = dev->devt; - put_device(dev); + /* Attempt to find the partition by offset. */ + if (!offset) + goto no_offset; + + res = 0; + disk = part_to_disk(dev_to_part(dev)); + part = disk_get_part(disk, dev_to_part(dev)->partno + offset); + if (part) { + res = part_devt(part); + put_device(part_to_dev(part)); + } + +no_offset: + put_device(dev); done: return res; } @@ -126,6 +164,8 @@ done: * used when disk name of partitioned disk ends on a digit. * 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the * unique id of a partition if the partition table provides it. + * 7) PARTUUID=/PARTNROFF= to select a partition in relation to + * a partition with a known unique id. * * If name doesn't have fall into the categories above, we return (0,0). * block_class is used to check if something is a disk name. If the disk @@ -143,8 +183,6 @@ dev_t name_to_dev_t(char *name) #ifdef CONFIG_BLOCK if (strncmp(name, "PARTUUID=", 9) == 0) { name += 9; - if (strlen(name) != 36) - goto fail; res = devt_from_partuuid(name); if (!res) goto fail; -- cgit v1.1 From c736de60aed869df8a9aba512cdaf89e32545b00 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Wed, 2 Nov 2011 13:39:25 -0700 Subject: sysctl: make CONFIG_SYSCTL_SYSCALL default to n When I tried to send a patch to remove it, Andi told me we still need to keep compabitlies for old libc, so we can't remove this completely. Then just make it default to n and remove the doc from feature-removal-schedule.txt. Signed-off-by: WANG Cong Cc: Eric Biederman Cc: Andi Kleen Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 31ba0fd..43298f9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -947,7 +947,7 @@ config UID16 config SYSCTL_SYSCALL bool "Sysctl syscall support" if EXPERT depends on PROC_SYSCTL - default y + default n select SYSCTL ---help--- sys_sysctl uses binary paths that have been found challenging @@ -959,7 +959,7 @@ config SYSCTL_SYSCALL trying to save some space it is probably safe to disable this, making your kernel marginally smaller. - If unsure say Y here. + If unsure say N here. config KALLSYMS bool "Load all symbols for debugging/ksymoops" if EXPERT -- cgit v1.1