diff options
Diffstat (limited to 'init')
| -rw-r--r-- | init/Kconfig | 190 | ||||
| -rw-r--r-- | init/do_mounts.c | 9 | ||||
| -rw-r--r-- | init/initramfs.c | 34 | ||||
| -rw-r--r-- | init/main.c | 34 | ||||
| -rw-r--r-- | init/version.c | 5 |
5 files changed, 177 insertions, 95 deletions
diff --git a/init/Kconfig b/init/Kconfig index 80a6907f91c5..9afb971497f4 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -477,7 +477,7 @@ config TREE_RCU thousands of CPUs. It also scales down nicely to smaller systems. -config TREE_PREEMPT_RCU +config PREEMPT_RCU bool "Preemptible tree-based hierarchical RCU" depends on PREEMPT select IRQ_WORK @@ -501,14 +501,18 @@ config TINY_RCU endchoice -config PREEMPT_RCU - def_bool TREE_PREEMPT_RCU +config TASKS_RCU + bool "Task_based RCU implementation using voluntary context switch" + default n help - This option enables preemptible-RCU code that is common between - TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU. + This option enables a task-based RCU implementation that uses + only voluntary context switch (not preemption!), idle, and + user-mode execution as quiescent states. + + If unsure, say N. config RCU_STALL_COMMON - def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) + def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE ) help This option enables RCU CPU stall code that is common between the TINY and TREE variants of RCU. The purpose is to allow @@ -566,7 +570,7 @@ config RCU_FANOUT int "Tree-based hierarchical RCU fanout value" range 2 64 if 64BIT range 2 32 if !64BIT - depends on TREE_RCU || TREE_PREEMPT_RCU + depends on TREE_RCU || PREEMPT_RCU default 64 if 64BIT default 32 if !64BIT help @@ -586,7 +590,7 @@ config RCU_FANOUT_LEAF int "Tree-based hierarchical RCU leaf-level fanout value" range 2 RCU_FANOUT if 64BIT range 2 RCU_FANOUT if !64BIT - depends on TREE_RCU || TREE_PREEMPT_RCU + depends on TREE_RCU || PREEMPT_RCU default 16 help This option controls the leaf-level fanout of hierarchical @@ -611,7 +615,7 @@ config RCU_FANOUT_LEAF config RCU_FANOUT_EXACT bool "Disable tree-based hierarchical RCU auto-balancing" - depends on TREE_RCU || TREE_PREEMPT_RCU + depends on TREE_RCU || PREEMPT_RCU default n help This option forces use of the exact RCU_FANOUT value specified, @@ -642,11 +646,11 @@ config RCU_FAST_NO_HZ Say N if you are unsure. config TREE_RCU_TRACE - def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU ) + def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU ) select DEBUG_FS help This option provides tracing for the TREE_RCU and - TREE_PREEMPT_RCU implementations, permitting Makefile to + PREEMPT_RCU implementations, permitting Makefile to trivially select kernel/rcutree_trace.c. config RCU_BOOST @@ -662,30 +666,31 @@ config RCU_BOOST Say Y here if you are working with real-time apps or heavy loads Say N here if you are unsure. -config RCU_BOOST_PRIO - int "Real-time priority to boost RCU readers to" +config RCU_KTHREAD_PRIO + int "Real-time priority to use for RCU worker threads" range 1 99 depends on RCU_BOOST default 1 help - This option specifies the real-time priority to which long-term - preempted RCU readers are to be boosted. If you are working - with a real-time application that has one or more CPU-bound - threads running at a real-time priority level, you should set - RCU_BOOST_PRIO to a priority higher then the highest-priority - real-time CPU-bound thread. The default RCU_BOOST_PRIO value - of 1 is appropriate in the common case, which is real-time + This option specifies the SCHED_FIFO priority value that will be + assigned to the rcuc/n and rcub/n threads and is also the value + used for RCU_BOOST (if enabled). If you are working with a + real-time application that has one or more CPU-bound threads + running at a real-time priority level, you should set + RCU_KTHREAD_PRIO to a priority higher than the highest-priority + real-time CPU-bound application thread. The default RCU_KTHREAD_PRIO + value of 1 is appropriate in the common case, which is real-time applications that do not have any CPU-bound threads. Some real-time applications might not have a single real-time thread that saturates a given CPU, but instead might have multiple real-time threads that, taken together, fully utilize - that CPU. In this case, you should set RCU_BOOST_PRIO to + that CPU. In this case, you should set RCU_KTHREAD_PRIO to a priority higher than the lowest-priority thread that is conspiring to prevent the CPU from running any non-real-time tasks. For example, if one thread at priority 10 and another thread at priority 5 are between themselves fully consuming - the CPU time on a given CPU, then RCU_BOOST_PRIO should be + the CPU time on a given CPU, then RCU_KTHREAD_PRIO should be set to priority 6 or higher. Specify the real-time priority, or take the default if unsure. @@ -705,7 +710,7 @@ config RCU_BOOST_DELAY config RCU_NOCB_CPU bool "Offload RCU callback processing from boot-selected CPUs" - depends on TREE_RCU || TREE_PREEMPT_RCU + depends on TREE_RCU || PREEMPT_RCU default n help Use this option to reduce OS jitter for aggressive HPC or @@ -729,6 +734,7 @@ config RCU_NOCB_CPU choice prompt "Build-forced no-CBs CPUs" default RCU_NOCB_CPU_NONE + depends on RCU_NOCB_CPU help This option allows no-CBs CPUs (whose RCU callbacks are invoked from kthreads rather than from softirq context) to be specified @@ -737,7 +743,6 @@ choice config RCU_NOCB_CPU_NONE bool "No build_forced no-CBs CPUs" - depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL help This option does not force any of the CPUs to be no-CBs CPUs. Only CPUs designated by the rcu_nocbs= boot parameter will be @@ -751,7 +756,6 @@ config RCU_NOCB_CPU_NONE config RCU_NOCB_CPU_ZERO bool "CPU 0 is a build_forced no-CBs CPU" - depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL help This option forces CPU 0 to be a no-CBs CPU, so that its RCU callbacks are invoked by a per-CPU kthread whose name begins @@ -766,7 +770,6 @@ config RCU_NOCB_CPU_ZERO config RCU_NOCB_CPU_ALL bool "All CPUs are build_forced no-CBs CPUs" - depends on RCU_NOCB_CPU help This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs= boot parameter will be ignored. All CPUs' RCU callbacks will @@ -828,6 +831,7 @@ config LOG_BUF_SHIFT config LOG_CPU_MAX_BUF_SHIFT int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)" + depends on SMP range 0 21 default 12 if !BASE_SMALL default 0 if BASE_SMALL @@ -889,25 +893,6 @@ config ARCH_SUPPORTS_INT128 config ARCH_WANT_NUMA_VARIABLE_LOCALITY bool -# -# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE -config ARCH_WANTS_PROT_NUMA_PROT_NONE - bool - -config ARCH_USES_NUMA_PROT_NONE - bool - default y - depends on ARCH_WANTS_PROT_NUMA_PROT_NONE - depends on NUMA_BALANCING - -config NUMA_BALANCING_DEFAULT_ENABLED - bool "Automatically enable NUMA aware memory/task placement" - default y - depends on NUMA_BALANCING - help - If set, automatic NUMA balancing will be enabled if running on a NUMA - machine. - config NUMA_BALANCING bool "Memory placement aware NUMA scheduler" depends on ARCH_SUPPORTS_NUMA_BALANCING @@ -920,6 +905,14 @@ config NUMA_BALANCING This system will be inactive on UMA systems. +config NUMA_BALANCING_DEFAULT_ENABLED + bool "Automatically enable NUMA aware memory/task placement" + default y + depends on NUMA_BALANCING + help + If set, automatic NUMA balancing will be enabled if running on a NUMA + machine. + menuconfig CGROUPS boolean "Control Group support" select KERNFS @@ -979,32 +972,17 @@ config CGROUP_CPUACCT Provides a simple Resource Controller for monitoring the total CPU consumed by the tasks in a cgroup. -config RESOURCE_COUNTERS - bool "Resource counters" - help - This option enables controller independent resource accounting - infrastructure that works with cgroups. +config PAGE_COUNTER + bool config MEMCG bool "Memory Resource Controller for Control Groups" - depends on RESOURCE_COUNTERS + select PAGE_COUNTER select EVENTFD help Provides a memory resource controller that manages both anonymous memory and page cache. (See Documentation/cgroups/memory.txt) - Note that setting this option increases fixed memory overhead - associated with each page of memory in the system. By this, - 8(16)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory - usage tracking struct at boot. Total amount of this is printed out - at boot. - - Only enable when you're ok with these trade offs and really - 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 controller) - config MEMCG_SWAP bool "Memory Resource Controller Swap Extension" depends on MEMCG && SWAP @@ -1055,7 +1033,8 @@ config MEMCG_KMEM config CGROUP_HUGETLB bool "HugeTLB Resource Controller for Control Groups" - depends on RESOURCE_COUNTERS && HUGETLB_PAGE + depends on HUGETLB_PAGE + select PAGE_COUNTER default n help Provides a cgroup Resource Controller for HugeTLB pages. @@ -1301,6 +1280,22 @@ source "usr/Kconfig" endif +config INIT_FALLBACK + bool "Fall back to defaults if init= parameter is bad" + default y + help + If enabled, the kernel will try the default init binaries if an + explicit request from the init= parameter fails. + + This can have unexpected effects. For example, booting + with init=/sbin/kiosk_app will run /sbin/init or even /bin/sh + if /sbin/kiosk_app cannot be executed. + + The default value of Y is consistent with historical behavior. + Selecting N is likely to be more appropriate for most uses, + especially on kiosks and on kernels that are intended to be + run under the control of a script. + config CC_OPTIMIZE_FOR_SIZE bool "Optimize for size" help @@ -1341,6 +1336,10 @@ config SYSCTL_ARCH_UNALIGN_ALLOW config HAVE_PCSPKR_PLATFORM bool +# interpreter that classic socket filters depend on +config BPF + bool + menuconfig EXPERT bool "Configure standard kernel features (expert users)" # Unhide debug options, to make the on-by-default options visible @@ -1521,6 +1520,16 @@ config EVENTFD If unsure, say Y. +# syscall, maps, verifier +config BPF_SYSCALL + bool "Enable bpf() system call" if EXPERT + select ANON_INODES + select BPF + default n + help + Enable the bpf() system call that allows to manipulate eBPF + programs and maps via file descriptors. + config SHMEM bool "Use full shmem filesystem" if EXPERT default y @@ -1540,6 +1549,16 @@ config AIO by some high performance threaded applications. Disabling this option saves about 7k. +config ADVISE_SYSCALLS + bool "Enable madvise/fadvise syscalls" if EXPERT + default y + help + This option enables the madvise and fadvise syscalls, used by + applications to advise the kernel about their future memory or file + usage, improving performance. If building an embedded system where no + applications use these syscalls, you can disable this option to save + space. + config PCI_QUIRKS default y bool "Enable PCI quirk workarounds" if EXPERT @@ -1909,6 +1928,49 @@ config MODULE_SIG_HASH default "sha384" if MODULE_SIG_SHA384 default "sha512" if MODULE_SIG_SHA512 +config MODULE_COMPRESS + bool "Compress modules on installation" + depends on MODULES + help + This option compresses the kernel modules when 'make + modules_install' is run. + + The modules will be compressed either using gzip or xz depend on the + choice made in "Compression algorithm". + + module-init-tools has support for gzip format while kmod handle gzip + and xz compressed modules. + + When a kernel module is installed from outside of the main kernel + source and uses the Kbuild system for installing modules then that + kernel module will also be compressed when it is installed. + + This option provides little benefit when the modules are to be used inside + an initrd or initramfs, it generally is more efficient to compress the whole + initrd or initramfs instead. + + This is fully compatible with signed modules while the signed module is + compressed. module-init-tools or kmod handles decompression and provide to + other layer the uncompressed but signed payload. + +choice + prompt "Compression algorithm" + depends on MODULE_COMPRESS + default MODULE_COMPRESS_GZIP + help + This determines which sort of compression will be used during + 'make modules_install'. + + GZIP (default) and XZ are supported. + +config MODULE_COMPRESS_GZIP + bool "GZIP" + +config MODULE_COMPRESS_XZ + bool "XZ" + +endchoice + endif # MODULES config INIT_ALL_POSSIBLE diff --git a/init/do_mounts.c b/init/do_mounts.c index 82f22885c87e..eb410083e8e0 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -182,7 +182,8 @@ done: /* * Convert a name into device number. We accept the following variants: * - * 1) device number in hexadecimal represents itself + * 1) <hex_major><hex_minor> device number in hexadecimal represents itself + * no leading 0x, for example b302. * 2) /dev/nfs represents Root_NFS (0xff) * 3) /dev/<disk_name> represents the device number of disk * 4) /dev/<disk_name><decimal> represents the device number @@ -394,8 +395,6 @@ retry: case 0: goto out; case -EACCES: - flags |= MS_RDONLY; - goto retry; case -EINVAL: continue; } @@ -418,6 +417,10 @@ retry: #endif panic("VFS: Unable to mount root fs on %s", b); } + if (!(flags & MS_RDONLY)) { + flags |= MS_RDONLY; + goto retry; + } printk("List of all partitions:\n"); printk_all_partitions(); diff --git a/init/initramfs.c b/init/initramfs.c index bece48c3461e..ad1bd7787bbb 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -197,14 +197,14 @@ static __initdata enum state { } state, next_state; static __initdata char *victim; -static unsigned long count __initdata; +static unsigned long byte_count __initdata; static __initdata loff_t this_header, next_header; static inline void __init eat(unsigned n) { victim += n; this_header += n; - count -= n; + byte_count -= n; } static __initdata char *vcollected; @@ -214,7 +214,7 @@ static __initdata char *collect; static void __init read_into(char *buf, unsigned size, enum state next) { - if (count >= size) { + if (byte_count >= size) { collected = victim; eat(size); state = next; @@ -237,8 +237,8 @@ static int __init do_start(void) static int __init do_collect(void) { unsigned long n = remains; - if (count < n) - n = count; + if (byte_count < n) + n = byte_count; memcpy(collect, victim, n); eat(n); collect += n; @@ -280,8 +280,8 @@ static int __init do_header(void) static int __init do_skip(void) { - if (this_header + count < next_header) { - eat(count); + if (this_header + byte_count < next_header) { + eat(byte_count); return 1; } else { eat(next_header - this_header); @@ -292,9 +292,9 @@ static int __init do_skip(void) static int __init do_reset(void) { - while(count && *victim == '\0') + while (byte_count && *victim == '\0') eat(1); - if (count && (this_header & 3)) + if (byte_count && (this_header & 3)) error("broken padding"); return 1; } @@ -309,11 +309,11 @@ static int __init maybe_link(void) return 0; } -static void __init clean_path(char *path, umode_t mode) +static void __init clean_path(char *path, umode_t fmode) { struct stat st; - if (!sys_newlstat(path, &st) && (st.st_mode^mode) & S_IFMT) { + if (!sys_newlstat(path, &st) && (st.st_mode ^ fmode) & S_IFMT) { if (S_ISDIR(st.st_mode)) sys_rmdir(path); else @@ -368,7 +368,7 @@ static int __init do_name(void) static int __init do_copy(void) { - if (count >= body_len) { + if (byte_count >= body_len) { if (xwrite(wfd, victim, body_len) != body_len) error("write error"); sys_close(wfd); @@ -378,10 +378,10 @@ static int __init do_copy(void) state = SkipIt; return 0; } else { - if (xwrite(wfd, victim, count) != count) + if (xwrite(wfd, victim, byte_count) != byte_count) error("write error"); - body_len -= count; - eat(count); + body_len -= byte_count; + eat(byte_count); return 1; } } @@ -411,12 +411,12 @@ static __initdata int (*actions[])(void) = { static long __init write_buffer(char *buf, unsigned long len) { - count = len; + byte_count = len; victim = buf; while (!actions[state]()) ; - return len - count; + return len - byte_count; } static long __init flush_buffer(void *bufv, unsigned long len) diff --git a/init/main.c b/init/main.c index bb1aed928f21..61b993767db5 100644 --- a/init/main.c +++ b/init/main.c @@ -51,7 +51,7 @@ #include <linux/mempolicy.h> #include <linux/key.h> #include <linux/buffer_head.h> -#include <linux/page_cgroup.h> +#include <linux/page_ext.h> #include <linux/debug_locks.h> #include <linux/debugobjects.h> #include <linux/lockdep.h> @@ -78,6 +78,8 @@ #include <linux/context_tracking.h> #include <linux/random.h> #include <linux/list.h> +#include <linux/integrity.h> +#include <linux/proc_ns.h> #include <asm/io.h> #include <asm/bugs.h> @@ -486,10 +488,10 @@ void __init __weak thread_info_cache_init(void) static void __init mm_init(void) { /* - * page_cgroup requires contiguous pages, + * page_ext requires contiguous pages, * bigger than MAX_ORDER unless SPARSEMEM. */ - page_cgroup_init_flatmem(); + page_ext_init_flatmem(); mem_init(); kmem_cache_init(); percpu_init_late(); @@ -501,13 +503,13 @@ asmlinkage __visible void __init start_kernel(void) { char *command_line; char *after_dashes; - extern const struct kernel_param __start___param[], __stop___param[]; /* * Need to run as early as possible, to initialize the * lockdep hash: */ lockdep_init(); + set_task_stack_end_magic(&init_task); smp_setup_processor_id(); debug_objects_early_init(); @@ -544,7 +546,7 @@ asmlinkage __visible void __init start_kernel(void) static_command_line, __start___param, __stop___param - __start___param, -1, -1, &unknown_bootoption); - if (after_dashes) + if (!IS_ERR_OR_NULL(after_dashes)) parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, set_init_arg); @@ -577,13 +579,17 @@ asmlinkage __visible void __init start_kernel(void) local_irq_disable(); idr_init_cache(); rcu_init(); - tick_nohz_init(); + + /* trace_printk() and trace points may be used after this */ + trace_init(); + context_tracking_init(); radix_tree_init(); /* init some links before init_ISA_irqs() */ early_irq_init(); init_IRQ(); tick_init(); + rcu_init_nohz(); init_timers(); hrtimers_init(); softirq_init(); @@ -627,7 +633,7 @@ asmlinkage __visible void __init start_kernel(void) initrd_start = 0; } #endif - page_cgroup_init(); + page_ext_init(); debug_objects_mem_init(); kmemleak_init(); setup_per_cpu_pageset(); @@ -660,6 +666,7 @@ asmlinkage __visible void __init start_kernel(void) /* rootfs populating might need page-writeback */ page_writeback_init(); proc_root_init(); + nsfs_init(); cgroup_init(); cpuset_init(); taskstats_init_early(); @@ -843,7 +850,6 @@ static char *initcall_level_names[] __initdata = { static void __init do_initcall_level(int level) { - extern const struct kernel_param __start___param[], __stop___param[]; initcall_t *fn; strcpy(initcall_command_line, saved_command_line); @@ -960,8 +966,13 @@ static int __ref kernel_init(void *unused) ret = run_init_process(execute_command); if (!ret) return 0; +#ifndef CONFIG_INIT_FALLBACK + panic("Requested init %s failed (error %d).", + execute_command, ret); +#else pr_err("Failed to execute %s (error %d). Attempting defaults...\n", - execute_command, ret); + execute_command, ret); +#endif } if (!try_to_run_init_process("/sbin/init") || !try_to_run_init_process("/etc/init") || @@ -1027,8 +1038,11 @@ static noinline void __init kernel_init_freeable(void) * Ok, we have completed the initial bootup, and * we're essentially up and running. Get rid of the * initmem segments and start the user-mode stuff.. + * + * rootfs is available now, try loading the public keys + * and default modules */ - /* rootfs is available now, try loading default modules */ + integrity_load_keys(); load_default_modules(); } diff --git a/init/version.c b/init/version.c index 1a4718e500fe..fe41a63efed6 100644 --- a/init/version.c +++ b/init/version.c @@ -35,7 +35,10 @@ struct uts_namespace init_uts_ns = { .domainname = UTS_DOMAINNAME, }, .user_ns = &init_user_ns, - .proc_inum = PROC_UTS_INIT_INO, + .ns.inum = PROC_UTS_INIT_INO, +#ifdef CONFIG_UTS_NS + .ns.ops = &utsns_operations, +#endif }; EXPORT_SYMBOL_GPL(init_uts_ns); |