diff options
Diffstat (limited to 'init')
| -rw-r--r-- | init/Kconfig | 45 | ||||
| -rw-r--r-- | init/initramfs.c | 147 | ||||
| -rw-r--r-- | init/main.c | 42 |
3 files changed, 152 insertions, 82 deletions
diff --git a/init/Kconfig b/init/Kconfig index 4592bf7997c0..8b9ffe236e4f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -562,7 +562,6 @@ config BUILD_BIN2C config IKCONFIG tristate "Kernel .config support" - select BUILD_BIN2C ---help--- This option enables the complete Linux kernel ".config" file contents to be saved in the kernel. It provides documentation @@ -580,6 +579,16 @@ config IKCONFIG_PROC This option enables access to the kernel configuration file through /proc/config.gz. +config IKHEADERS_PROC + tristate "Enable kernel header artifacts through /proc/kheaders.tar.xz" + depends on PROC_FS + help + This option enables access to the kernel header and other artifacts that + are generated during the build process. These can be used to build eBPF + tracing programs, or similar programs. If you build the headers as a + module, a module called kheaders.ko is built which can be loaded on-demand + to get access to the headers. + config LOG_BUF_SHIFT int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" range 12 25 @@ -1171,9 +1180,6 @@ config LD_DEAD_CODE_DATA_ELIMINATION config SYSCTL bool -config ANON_INODES - bool - config HAVE_UID16 bool @@ -1378,14 +1384,12 @@ config HAVE_FUTEX_CMPXCHG config EPOLL bool "Enable eventpoll support" if EXPERT default y - select ANON_INODES help Disabling this option will cause the kernel to be built without support for epoll family of system calls. config SIGNALFD bool "Enable signalfd() system call" if EXPERT - select ANON_INODES default y help Enable the signalfd() system call that allows to receive signals @@ -1395,7 +1399,6 @@ config SIGNALFD config TIMERFD bool "Enable timerfd() system call" if EXPERT - select ANON_INODES default y help Enable the timerfd() system call that allows to receive timer @@ -1405,7 +1408,6 @@ config TIMERFD config EVENTFD bool "Enable eventfd() system call" if EXPERT - select ANON_INODES default y help Enable the eventfd() system call that allows to receive both @@ -1516,7 +1518,6 @@ config KALLSYMS_BASE_RELATIVE # syscall, maps, verifier config BPF_SYSCALL bool "Enable bpf() system call" - select ANON_INODES select BPF select IRQ_WORK default n @@ -1533,7 +1534,6 @@ config BPF_JIT_ALWAYS_ON config USERFAULTFD bool "Enable userfaultfd() system call" - select ANON_INODES depends on MMU help Enable the userfaultfd() system call that allows to intercept and @@ -1600,7 +1600,6 @@ config PERF_EVENTS bool "Kernel performance events and counters" default y if PROFILING depends on HAVE_PERF_EVENTS - select ANON_INODES select IRQ_WORK select SRCU help @@ -1753,6 +1752,30 @@ config SLAB_FREELIST_HARDENED sacrifies to harden the kernel slab allocator against common freelist exploit methods. +config SHUFFLE_PAGE_ALLOCATOR + bool "Page allocator randomization" + default SLAB_FREELIST_RANDOM && ACPI_NUMA + help + Randomization of the page allocator improves the average + utilization of a direct-mapped memory-side-cache. See section + 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI + 6.2a specification for an example of how a platform advertises + the presence of a memory-side-cache. There are also incidental + security benefits as it reduces the predictability of page + allocations to compliment SLAB_FREELIST_RANDOM, but the + default granularity of shuffling on the "MAX_ORDER - 1" i.e, + 10th order of pages is selected based on cache utilization + benefits on x86. + + While the randomization improves cache utilization it may + negatively impact workloads on platforms without a cache. For + this reason, by default, the randomization is enabled only + after runtime detection of a direct-mapped memory-side-cache. + Otherwise, the randomization may be force enabled with the + 'page_alloc.shuffle' kernel command line parameter. + + Say Y if unsure. + config SLUB_CPU_PARTIAL default y depends on SLUB && SMP diff --git a/init/initramfs.c b/init/initramfs.c index 4749e1115eef..178130fd61c2 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -513,42 +513,55 @@ static int __init retain_initrd_param(char *str) } __setup("retain_initrd", retain_initrd_param); +#ifdef CONFIG_ARCH_HAS_KEEPINITRD +static int __init keepinitrd_setup(char *__unused) +{ + do_retain_initrd = 1; + return 1; +} +__setup("keepinitrd", keepinitrd_setup); +#endif + extern char __initramfs_start[]; extern unsigned long __initramfs_size; #include <linux/initrd.h> #include <linux/kexec.h> -static void __init free_initrd(void) +void __weak free_initrd_mem(unsigned long start, unsigned long end) { + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, + "initrd"); +} + #ifdef CONFIG_KEXEC_CORE +static bool kexec_free_initrd(void) +{ unsigned long crashk_start = (unsigned long)__va(crashk_res.start); unsigned long crashk_end = (unsigned long)__va(crashk_res.end); -#endif - if (do_retain_initrd) - goto skip; -#ifdef CONFIG_KEXEC_CORE /* * If the initrd region is overlapped with crashkernel reserved region, * free only memory that is not part of crashkernel region. */ - if (initrd_start < crashk_end && initrd_end > crashk_start) { - /* - * Initialize initrd memory region since the kexec boot does - * not do. - */ - memset((void *)initrd_start, 0, initrd_end - initrd_start); - if (initrd_start < crashk_start) - free_initrd_mem(initrd_start, crashk_start); - if (initrd_end > crashk_end) - free_initrd_mem(crashk_end, initrd_end); - } else -#endif - free_initrd_mem(initrd_start, initrd_end); -skip: - initrd_start = 0; - initrd_end = 0; + if (initrd_start >= crashk_end || initrd_end <= crashk_start) + return false; + + /* + * Initialize initrd memory region since the kexec boot does not do. + */ + memset((void *)initrd_start, 0, initrd_end - initrd_start); + if (initrd_start < crashk_start) + free_initrd_mem(initrd_start, crashk_start); + if (initrd_end > crashk_end) + free_initrd_mem(crashk_end, initrd_end); + return true; +} +#else +static inline bool kexec_free_initrd(void) +{ + return false; } +#endif /* CONFIG_KEXEC_CORE */ #ifdef CONFIG_BLK_DEV_RAM #define BUF_SIZE 1024 @@ -597,7 +610,38 @@ static void __init clean_rootfs(void) ksys_close(fd); kfree(buf); } -#endif +#else +static inline void clean_rootfs(void) +{ +} +#endif /* CONFIG_BLK_DEV_RAM */ + +#ifdef CONFIG_BLK_DEV_RAM +static void populate_initrd_image(char *err) +{ + ssize_t written; + int fd; + + unpack_to_rootfs(__initramfs_start, __initramfs_size); + + printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", + err); + fd = ksys_open("/initrd.image", O_WRONLY | O_CREAT, 0700); + if (fd < 0) + return; + + written = xwrite(fd, (char *)initrd_start, initrd_end - initrd_start); + if (written != initrd_end - initrd_start) + pr_err("/initrd.image: incomplete write (%zd != %ld)\n", + written, initrd_end - initrd_start); + ksys_close(fd); +} +#else +static void populate_initrd_image(char *err) +{ + printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); +} +#endif /* CONFIG_BLK_DEV_RAM */ static int __init populate_rootfs(void) { @@ -605,46 +649,31 @@ static int __init populate_rootfs(void) char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size); if (err) panic("%s", err); /* Failed to decompress INTERNAL initramfs */ - /* If available load the bootloader supplied initrd */ - if (initrd_start && !IS_ENABLED(CONFIG_INITRAMFS_FORCE)) { -#ifdef CONFIG_BLK_DEV_RAM - int fd; + + if (!initrd_start || IS_ENABLED(CONFIG_INITRAMFS_FORCE)) + goto done; + + if (IS_ENABLED(CONFIG_BLK_DEV_RAM)) printk(KERN_INFO "Trying to unpack rootfs image as initramfs...\n"); - err = unpack_to_rootfs((char *)initrd_start, - initrd_end - initrd_start); - if (!err) { - free_initrd(); - goto done; - } else { - clean_rootfs(); - unpack_to_rootfs(__initramfs_start, __initramfs_size); - } - printk(KERN_INFO "rootfs image is not initramfs (%s)" - "; looks like an initrd\n", err); - fd = ksys_open("/initrd.image", - O_WRONLY|O_CREAT, 0700); - if (fd >= 0) { - ssize_t written = xwrite(fd, (char *)initrd_start, - initrd_end - initrd_start); - - if (written != initrd_end - initrd_start) - pr_err("/initrd.image: incomplete write (%zd != %ld)\n", - written, initrd_end - initrd_start); - - ksys_close(fd); - free_initrd(); - } - done: - /* empty statement */; -#else + else printk(KERN_INFO "Unpacking initramfs...\n"); - err = unpack_to_rootfs((char *)initrd_start, - initrd_end - initrd_start); - if (err) - printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); - free_initrd(); -#endif + + err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start); + if (err) { + clean_rootfs(); + populate_initrd_image(err); } + +done: + /* + * If the initrd region is overlapped with crashkernel reserved region, + * free only memory that is not part of crashkernel region. + */ + if (!do_retain_initrd && initrd_start && !kexec_free_initrd()) + free_initrd_mem(initrd_start, initrd_end); + initrd_start = 0; + initrd_end = 0; + flush_delayed_fput(); return 0; } diff --git a/init/main.c b/init/main.c index 598e278b46f7..5a2c69b4d7b3 100644 --- a/init/main.c +++ b/init/main.c @@ -504,6 +504,10 @@ void __init __weak thread_stack_cache_init(void) void __init __weak mem_encrypt_init(void) { } +void __init __weak poking_init(void) { } + +void __init __weak pgd_cache_init(void) { } + bool initcall_debug; core_param(initcall_debug, initcall_debug, bool, 0644); @@ -535,6 +539,7 @@ static void __init mm_init(void) init_espfix_bsp(); /* Should be run after espfix64 is set up. */ pti_init(); + pgd_cache_init(); } void __init __weak arch_call_rest_init(void) @@ -564,13 +569,6 @@ asmlinkage __visible void __init start_kernel(void) page_address_init(); pr_notice("%s", linux_banner); setup_arch(&command_line); - /* - * Set up the the initial canary and entropy after arch - * and after adding latent and command line entropy. - */ - add_latent_entropy(); - add_device_randomness(command_line, strlen(command_line)); - boot_init_stack_canary(); mm_init_cpumask(&init_mm); setup_command_line(command_line); setup_nr_cpu_ids(); @@ -582,6 +580,8 @@ asmlinkage __visible void __init start_kernel(void) page_alloc_init(); pr_notice("Kernel command line: %s\n", boot_command_line); + /* parameters may set static keys */ + jump_label_init(); parse_early_param(); after_dashes = parse_args("Booting kernel", static_command_line, __start___param, @@ -591,8 +591,6 @@ asmlinkage __visible void __init start_kernel(void) parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, NULL, set_init_arg); - jump_label_init(); - /* * These use large bootmem allocations and must precede * kmem_cache_init() @@ -655,6 +653,20 @@ asmlinkage __visible void __init start_kernel(void) hrtimers_init(); softirq_init(); timekeeping_init(); + + /* + * For best initial stack canary entropy, prepare it after: + * - setup_arch() for any UEFI RNG entropy and boot cmdline access + * - timekeeping_init() for ktime entropy used in rand_initialize() + * - rand_initialize() to get any arch-specific entropy like RDRAND + * - add_latent_entropy() to get any latent entropy + * - adding command line entropy + */ + rand_initialize(); + add_latent_entropy(); + add_device_randomness(command_line, strlen(command_line)); + boot_init_stack_canary(); + time_init(); printk_safe_init(); perf_event_init(); @@ -737,6 +749,7 @@ asmlinkage __visible void __init start_kernel(void) taskstats_init_early(); delayacct_init(); + poking_init(); check_bugs(); acpi_subsystem_init(); @@ -840,7 +853,7 @@ trace_initcall_start_cb(void *data, initcall_t fn) { ktime_t *calltime = (ktime_t *)data; - printk(KERN_DEBUG "calling %pF @ %i\n", fn, task_pid_nr(current)); + printk(KERN_DEBUG "calling %pS @ %i\n", fn, task_pid_nr(current)); *calltime = ktime_get(); } @@ -854,7 +867,7 @@ trace_initcall_finish_cb(void *data, initcall_t fn, int ret) rettime = ktime_get(); delta = ktime_sub(rettime, *calltime); duration = (unsigned long long) ktime_to_ns(delta) >> 10; - printk(KERN_DEBUG "initcall %pF returned %d after %lld usecs\n", + printk(KERN_DEBUG "initcall %pS returned %d after %lld usecs\n", fn, ret, duration); } @@ -911,7 +924,7 @@ int __init_or_module do_one_initcall(initcall_t fn) strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf)); local_irq_enable(); } - WARN(msgbuf[0], "initcall %pF returned with %s\n", fn, msgbuf); + WARN(msgbuf[0], "initcall %pS returned with %s\n", fn, msgbuf); add_latent_entropy(); return ret; @@ -1061,6 +1074,11 @@ static inline void mark_readonly(void) } #endif +void __weak free_initmem(void) +{ + free_initmem_default(POISON_FREE_INITMEM); +} + static int __ref kernel_init(void *unused) { int ret; |