- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] reboot: allow to specify reboot mode via sysfs
by Hongyu Li 18 Jan '22

18 Jan '22

From: Matteo Croce <mcroce(a)microsoft.com> mainline inclusion category: feature from mainline-v5.11 commit 2c622ed0eaa38b68d7440bedb8c6cdd138b5a860 bugzilla: https://gitee.com/openeuler/kernel/issues/I4BULZ CVE: NA -------------------------------- The kernel cmdline reboot= option offers some sort of control on how the reboot is issued. We don't always know in advance what type of reboot to perform. Sometimes a warm reboot is preferred to persist certain memory regions across the reboot. Others a cold one is needed to apply a future system update that makes a memory memory model change, like changing the base page size or resizing a persistent memory region. Or simply we want to enable reboot_force because we noticed that something bad happened. Add handles in sysfs to allow setting these reboot options, so they can be changed when the system is booted, other than at boot time. The handlers are under <sysfs>/kernel/reboot, can be read to get the current configuration and written to alter it. # cd /sys/kernel/reboot/ # grep . * cpu:0 force:0 mode:cold type:acpi # echo 2 >cpu # echo yes >force # echo soft >mode # echo bios >type # grep . * cpu:2 force:1 mode:soft type:bios Before setting anything, check for CAP_SYS_BOOT capability, so it's possible to allow an unpriviledged process to change these settings simply by relaxing the handles permissions, without opening them to the world. [natechancellor(a)gmail.com: fix variable assignments in type_store] Link: https://lkml.kernel.org/r/20201112035023.974748-1-natechancellor@gmail.com Link: https://github.com/ClangBuiltLinux/linux/issues/1197 Link: https://lkml.kernel.org/r/20201110202746.9690-1-mcroce@linux.microsoft.com Signed-off-by: Matteo Croce <mcroce(a)microsoft.com> Signed-off-by: Nathan Chancellor <natechancellor(a)gmail.com> Reviewed-by: Petr Mladek <pmladek(a)suse.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Guenter Roeck <linux(a)roeck-us.net> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Pavel Tatashin <pasha.tatashin(a)soleen.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: Tyler Hicks <tyhicks(a)linux.microsoft.com> Cc: Nathan Chancellor <natechancellor(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Li Hongyu <543306408(a)qq.com> --- Documentation/ABI/testing/sysfs-kernel-reboot | 32 +++ kernel/reboot.c | 206 ++++++++++++++++++ 2 files changed, 238 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-kernel-reboot diff --git a/Documentation/ABI/testing/sysfs-kernel-reboot b/Documentation/ABI/testing/sysfs-kernel-reboot new file mode 100644 index 000000000000..837330fb2511 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-reboot @@ -0,0 +1,32 @@ +What: /sys/kernel/reboot +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Interface to set the kernel reboot behavior, similarly to + what can be done via the reboot= cmdline option. + (see Documentation/admin-guide/kernel-parameters.txt) + +What: /sys/kernel/reboot/mode +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Reboot mode. Valid values are: cold warm hard soft gpio + +What: /sys/kernel/reboot/type +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Reboot type. Valid values are: bios acpi kbd triple efi pci + +What: /sys/kernel/reboot/cpu +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: CPU number to use to reboot. + +What: /sys/kernel/reboot/force +Date: November 2020 +KernelVersion: 5.11 +Contact: Matteo Croce <mcroce(a)microsoft.com> +Description: Don't wait for any other CPUs on reboot and + avoid anything that could hang. diff --git a/kernel/reboot.c b/kernel/reboot.c index aa3bfd6c673b..940cbb784e17 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -600,3 +600,209 @@ static int __init reboot_setup(char *str) return 1; } __setup("reboot=", reboot_setup); + +#ifdef CONFIG_SYSFS + +#define REBOOT_COLD_STR "cold" +#define REBOOT_WARM_STR "warm" +#define REBOOT_HARD_STR "hard" +#define REBOOT_SOFT_STR "soft" +#define REBOOT_GPIO_STR "gpio" +#define REBOOT_UNDEFINED_STR "undefined" + +#define BOOT_TRIPLE_STR "triple" +#define BOOT_KBD_STR "kbd" +#define BOOT_BIOS_STR "bios" +#define BOOT_ACPI_STR "acpi" +#define BOOT_EFI_STR "efi" +#define BOOT_CF9_FORCE_STR "cf9_force" +#define BOOT_CF9_SAFE_STR "cf9_safe" + +static ssize_t mode_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + const char *val; + + switch (reboot_mode) { + case REBOOT_COLD: + val = REBOOT_COLD_STR; + break; + case REBOOT_WARM: + val = REBOOT_WARM_STR; + break; + case REBOOT_HARD: + val = REBOOT_HARD_STR; + break; + case REBOOT_SOFT: + val = REBOOT_SOFT_STR; + break; + case REBOOT_GPIO: + val = REBOOT_GPIO_STR; + break; + default: + val = REBOOT_UNDEFINED_STR; + } + + return sprintf(buf, "%s\n", val); +} +static ssize_t mode_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + if (!strncmp(buf, REBOOT_COLD_STR, strlen(REBOOT_COLD_STR))) + reboot_mode = REBOOT_COLD; + else if (!strncmp(buf, REBOOT_WARM_STR, strlen(REBOOT_WARM_STR))) + reboot_mode = REBOOT_WARM; + else if (!strncmp(buf, REBOOT_HARD_STR, strlen(REBOOT_HARD_STR))) + reboot_mode = REBOOT_HARD; + else if (!strncmp(buf, REBOOT_SOFT_STR, strlen(REBOOT_SOFT_STR))) + reboot_mode = REBOOT_SOFT; + else if (!strncmp(buf, REBOOT_GPIO_STR, strlen(REBOOT_GPIO_STR))) + reboot_mode = REBOOT_GPIO; + else + return -EINVAL; + + return count; +} +static struct kobj_attribute reboot_mode_attr = __ATTR_RW(mode); + +static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + const char *val; + + switch (reboot_type) { + case BOOT_TRIPLE: + val = BOOT_TRIPLE_STR; + break; + case BOOT_KBD: + val = BOOT_KBD_STR; + break; + case BOOT_BIOS: + val = BOOT_BIOS_STR; + break; + case BOOT_ACPI: + val = BOOT_ACPI_STR; + break; + case BOOT_EFI: + val = BOOT_EFI_STR; + break; + case BOOT_CF9_FORCE: + val = BOOT_CF9_FORCE_STR; + break; + case BOOT_CF9_SAFE: + val = BOOT_CF9_SAFE_STR; + break; + default: + val = REBOOT_UNDEFINED_STR; + } + + return sprintf(buf, "%s\n", val); +} +static ssize_t type_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + if (!strncmp(buf, BOOT_TRIPLE_STR, strlen(BOOT_TRIPLE_STR))) + reboot_type = BOOT_TRIPLE; + else if (!strncmp(buf, BOOT_KBD_STR, strlen(BOOT_KBD_STR))) + reboot_type = BOOT_KBD; + else if (!strncmp(buf, BOOT_BIOS_STR, strlen(BOOT_BIOS_STR))) + reboot_type = BOOT_BIOS; + else if (!strncmp(buf, BOOT_ACPI_STR, strlen(BOOT_ACPI_STR))) + reboot_type = BOOT_ACPI; + else if (!strncmp(buf, BOOT_EFI_STR, strlen(BOOT_EFI_STR))) + reboot_type = BOOT_EFI; + else if (!strncmp(buf, BOOT_CF9_FORCE_STR, strlen(BOOT_CF9_FORCE_STR))) + reboot_type = BOOT_CF9_FORCE; + else if (!strncmp(buf, BOOT_CF9_SAFE_STR, strlen(BOOT_CF9_SAFE_STR))) + reboot_type = BOOT_CF9_SAFE; + else + return -EINVAL; + + return count; +} +static struct kobj_attribute reboot_type_attr = __ATTR_RW(type); + +static ssize_t cpu_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", reboot_cpu); +} +static ssize_t cpu_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned int cpunum; + int rc; + + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + rc = kstrtouint(buf, 0, &cpunum); + + if (rc) + return rc; + + if (cpunum >= num_possible_cpus()) + return -ERANGE; + + reboot_cpu = cpunum; + + return count; +} +static struct kobj_attribute reboot_cpu_attr = __ATTR_RW(cpu); + +static ssize_t force_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", reboot_force); +} +static ssize_t force_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + bool res; + + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + if (kstrtobool(buf, &res)) + return -EINVAL; + + reboot_force = res; + + return count; +} +static struct kobj_attribute reboot_force_attr = __ATTR_RW(force); + +static struct attribute *reboot_attrs[] = { + &reboot_mode_attr.attr, + &reboot_type_attr.attr, + &reboot_cpu_attr.attr, + &reboot_force_attr.attr, + NULL, +}; + +static const struct attribute_group reboot_attr_group = { + .attrs = reboot_attrs, +}; + +static int __init reboot_ksysfs_init(void) +{ + struct kobject *reboot_kobj; + int ret; + + reboot_kobj = kobject_create_and_add("reboot", kernel_kobj); + if (!reboot_kobj) + return -ENOMEM; + + ret = sysfs_create_group(reboot_kobj, &reboot_attr_group); + if (ret) { + kobject_put(reboot_kobj); + return ret; + } + + return 0; +} +late_initcall(reboot_ksysfs_init); + +#endif -- 2.17.1

2 1

[PATCH OLK-5.10] mm: introduce process_mrelease system call
by Wen Zhiwei 18 Jan '22

18 Jan '22

mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4FHN2?from=project-issue CVE: NA --------------------------- In modern systems it's not unusual to have a system component monitoring memory conditions of the system and tasked with keeping system memory pressure under control. One way to accomplish that is to kill non-essential processes to free up memory for more important ones. Examples of this are Facebook's OOM killer daemon called oomd and Android's low memory killer daemon called lmkd. For such system component it's important to be able to free memory quickly and efficiently. Unfortunately the time process takes to free up its memory after receiving a SIGKILL might vary based on the state of the process (uninterruptible sleep), size and OPP level of the core the process is running. A mechanism to free resources of the target process in a more predictable way would improve system's ability to control its memory pressure. Introduce process_mrelease system call that releases memory of a dying process from the context of the caller. This way the memory is freed in a more controllable way with CPU affinity and priority of the caller. The workload of freeing the memory will also be charged to the caller. The operation is allowed only on a dying process. Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Reviewed-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Acked-by: Christian Brauner <christian.brauner(a)ubuntu.com> Cc: David Rientjes <rientjes(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Roman Gushchin <guro(a)fb.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Oleg Nesterov <oleg(a)redhat.com> Cc: Jann Horn <jannh(a)google.com> Cc: Geert Uytterhoeven <geert(a)linux-m68k.org> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Christian Brauner <christian.brauner(a)ubuntu.com> Cc: Florian Weimer <fweimer(a)redhat.com> Cc: Jan Engelhardt <jengelh(a)inai.de> Cc: Tim Murray <timmurray(a)google.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Wen Zhiwei <wenzhiwei(a)kylinos.cn> --- arch/arm64/include/asm/unistd32.h | 3 +- arch/x86/entry/syscalls/syscall_64.tbl | 2 +- include/linux/syscalls.h | 3 ++ include/uapi/asm-generic/unistd.h | 5 +- kernel/sys_ni.c | 1 + mm/oom_kill.c | 72 +++++++++++++++++++++++++ tools/include/uapi/asm-generic/unistd.h | 4 +- 7 files changed, 86 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 107f08e03b9f..e1786b2e8551 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -889,7 +889,8 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) - +#define __NR_process_mrelease 441 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) /* * Please add new compat syscalls above this comment and update * __NR_compat_syscalls in asm/unistd.h. diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 379819244b91..6eec6496d72c 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -362,7 +362,7 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise - +441 common process_mrelease sys_process_mrelease # # Due to a historical design error, certain syscalls are numbered differently # in x32 as compared to native x86_64. These syscalls have numbers 512-547. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index aea0ce9f3b74..764bfcdbbcb0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -905,6 +905,9 @@ asmlinkage long sys_mincore(unsigned long start, size_t len, asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec, size_t vlen, int behavior, unsigned int flags); + +asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags); + asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 2056318988f7..e5f38ea960c4 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -859,9 +859,12 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_process_mrelease 441 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) #undef __NR_syscalls -#define __NR_syscalls 441 +#define __NR_syscalls 442 + /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index f27ac94d5fa7..6b8203edf531 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -281,6 +281,7 @@ COND_SYSCALL(munlockall); COND_SYSCALL(mincore); COND_SYSCALL(madvise); COND_SYSCALL(process_madvise); +COND_SYSCALL(process_mrelease); COND_SYSCALL(remap_file_pages); COND_SYSCALL(mbind); COND_SYSCALL_COMPAT(mbind); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index fb39b0902476..d169eb511518 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -43,6 +43,7 @@ #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> +#include <linux/syscalls.h> #include <asm/tlb.h> #include "internal.h" @@ -1186,3 +1187,74 @@ void pagefault_out_of_memory(void) out_of_memory(&oc); mutex_unlock(&oom_lock); } + +SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) +{ +#ifdef CONFIG_MMU + struct mm_struct *mm = NULL; + struct task_struct *task; + struct task_struct *p; + unsigned int f_flags; + bool reap = false; + struct pid *pid; + long ret = 0; + + if (flags) + return -EINVAL; + + pid = pidfd_get_pid(pidfd, &f_flags); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + task = get_pid_task(pid, PIDTYPE_TGID); + if (!task) { + ret = -ESRCH; + goto put_pid; + } + + /* + * Make sure to choose a thread which still has a reference to mm + * during the group exit + */ + p = find_lock_task_mm(task); + if (!p) { + ret = -ESRCH; + goto put_task; + } + + if (mmget_not_zero(p->mm)) { + mm = p->mm; + if (task_will_free_mem(p)) + reap = true; + else { + /* Error only if the work has not been done already */ + if (!test_bit(MMF_OOM_SKIP, &mm->flags)) + ret = -EINVAL; + } + } + task_unlock(p); + + if (!reap) + goto drop_mm; + + if (mmap_read_lock_killable(mm)) { + ret = -EINTR; + goto drop_mm; + } + if (!__oom_reap_task_mm(mm)) + ret = -EAGAIN; + mmap_read_unlock(mm); + +drop_mm: + if (mm) + mmput(mm); +put_task: + put_task_struct(task); +put_pid: + put_pid(pid); + return ret; +#else + return -ENOSYS; +#endif /* CONFIG_MMU */ +} + diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 2056318988f7..c252faa802d3 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_process_mrelease 441 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) #undef __NR_syscalls -#define __NR_syscalls 441 +#define __NR_syscalls 442 /* * 32 bit systems traditionally used different -- 2.30.0

2 1

[PATCH OLK-5.10] crypto:rmd320 rmd128 rmd256-remove RIPE-MD 320 128 256 hash algorithm
by Wen Zhiwei 18 Jan '22

18 Jan '22

mainlin inclusion category: performance bugzilla: NA CVE: NA ----------------------------------------------------------- RIPE-MD 256 is never referenced anywhere in the kernel, and unlikely to be depended upon by userspace via AF_ALG. So let's remove it Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Wen Zhiwei <wenzhiwei(a)kylinos.cn> --- crypto/tcrypt.c | 42 +----------------------------------------- 1 file changed, 1 insertion(+), 41 deletions(-) diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index 8609174e036e..c8b0d31631f5 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -71,7 +71,7 @@ static const char *check[] = { "blowfish", "twofish", "serpent", "sha384", "sha512", "md4", "aes", "cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea", "khazad", "wp512", "wp384", "wp256", "tnepres", "xeta", "fcrypt", - "camellia", "seed", "salsa20", "rmd128", "rmd160", "rmd256", "rmd320", + "camellia", "seed", "salsa20", "rmd160", "lzo", "lzo-rle", "cts", "sha3-224", "sha3-256", "sha3-384", "sha3-512", "streebog256", "streebog512", NULL @@ -1860,22 +1860,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) ret += tcrypt_test("cts(cbc(aes))"); break; - case 39: - ret += tcrypt_test("rmd128"); - break; - case 40: ret += tcrypt_test("rmd160"); break; - case 41: - ret += tcrypt_test("rmd256"); - break; - - case 42: - ret += tcrypt_test("rmd320"); - break; - case 43: ret += tcrypt_test("ecb(seed)"); break; @@ -1948,10 +1936,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) ret += tcrypt_test("xcbc(aes)"); break; - case 107: - ret += tcrypt_test("hmac(rmd128)"); - break; - case 108: ret += tcrypt_test("hmac(rmd160)"); break; @@ -2402,22 +2386,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) test_hash_speed("sha224", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; fallthrough; - case 314: - test_hash_speed("rmd128", sec, generic_hash_speed_template); - if (mode > 300 && mode < 400) break; - fallthrough; case 315: test_hash_speed("rmd160", sec, generic_hash_speed_template); if (mode > 300 && mode < 400) break; fallthrough; - case 316: - test_hash_speed("rmd256", sec, generic_hash_speed_template); - if (mode > 300 && mode < 400) break; - fallthrough; - case 317: - test_hash_speed("rmd320", sec, generic_hash_speed_template); - if (mode > 300 && mode < 400) break; - fallthrough; case 318: klen = 16; test_hash_speed("ghash", sec, generic_hash_speed_template); @@ -2526,22 +2498,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb) test_ahash_speed("sha224", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; fallthrough; - case 414: - test_ahash_speed("rmd128", sec, generic_hash_speed_template); - if (mode > 400 && mode < 500) break; - fallthrough; case 415: test_ahash_speed("rmd160", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; fallthrough; - case 416: - test_ahash_speed("rmd256", sec, generic_hash_speed_template); - if (mode > 400 && mode < 500) break; - fallthrough; - case 417: - test_ahash_speed("rmd320", sec, generic_hash_speed_template); - if (mode > 400 && mode < 500) break; - fallthrough; case 418: test_ahash_speed("sha3-224", sec, generic_hash_speed_template); if (mode > 400 && mode < 500) break; -- 2.30.0

2 1

[PATCH OLK-5.10 0/2] change arm64 and x86 configs
by Chao Liu 18 Jan '22

18 Jan '22

change arm64 and x86 configs openEuler inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4OFDI CVE: NA -------------------------------- Chao Liu (2): change arm64 configs change x86 configs arch/arm64/configs/openeuler_defconfig | 287 ++++++++----- arch/x86/configs/openeuler_defconfig | 540 +++++++++---------------- 2 files changed, 374 insertions(+), 453 deletions(-) -- 2.27.0

1 2

[PATCH openEuler-1.0-LTS] ip_gre: validate csum_start only on pull
by Yang Yingliang 18 Jan '22

18 Jan '22

From: Willem de Bruijn <willemb(a)google.com> mainline inclusion from mainline-v5.14 commit 8a0ed250f911da31a2aef52101bc707846a800ff category: bugfix bugzilla: NA CVE: CVE-2021-39633 ------------------------------------------------- The GRE tunnel device can pull existing outer headers in ipge_xmit. This is a rare path, apparently unique to this device. The below commit ensured that pulling does not move skb->data beyond csum_start. But it has a false positive if ip_summed is not CHECKSUM_PARTIAL and thus csum_start is irrelevant. Refine to exclude this. At the same time simplify and strengthen the test. Simplify, by moving the check next to the offending pull, making it more self documenting and removing an unnecessary branch from other code paths. Strengthen, by also ensuring that the transport header is correct and therefore the inner headers will be after skb_reset_inner_headers. The transport header is set to csum_start in skb_partial_csum_set. Link: https://lore.kernel.org/netdev/YS+h%2FtqCJJiQei+W@shredder/ Fixes: 1d011c4803c7 ("ip_gre: add validation for csum_start") Reported-by: Ido Schimmel <idosch(a)idosch.org> Suggested-by: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Willem de Bruijn <willemb(a)google.com> Reviewed-by: Alexander Duyck <alexanderduyck(a)fb.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Huang Guobin <huangguobin4(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/ipv4/ip_gre.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a8a37d1128201..0c431fd4b1200 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -449,8 +449,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, static int gre_handle_offloads(struct sk_buff *skb, bool csum) { - if (csum && skb_checksum_start(skb) < skb->data) - return -EINVAL; return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } @@ -682,15 +680,20 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { + const int pull_len = tunnel->hlen + sizeof(struct iphdr); + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; + if (pull_len > skb_transport_offset(skb)) + goto free_skb; + /* Pull skb since ip_tunnel_xmit() needs skb->data pointing * to gre header. */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + skb_pull(skb, pull_len); skb_reset_mac_header(skb); } else { if (skb_cow_head(skb, dev->needed_headroom)) -- 2.25.1

1 0

[PATCH openEuler-5.10 01/82] clocksource/arm_arch_timer: Add build-time guards for unhandled register accesses
by Zheng Zengkai 17 Jan '22

17 Jan '22

From: Marc Zyngier <maz(a)kernel.org> mainline inclusion from mainline-v5.16-rc1 commit 4775bc63f880 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4QCBG CVE: NA -------------------------- As we are about to change the registers that are used by the driver, start by adding build-time checks to ensure that we always handle all registers and access modes. Suggested-by: Mark Rutland <mark.rutland(a)arm.com> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Link: https://lore.kernel.org/r/20211017124225.3018098-2-maz@kernel.org Signed-off-by: Daniel Lezcano <daniel.lezcano(a)linaro.org> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/arm/include/asm/arch_timer.h | 12 ++++++++++++ arch/arm64/include/asm/arch_timer.h | 13 ++++++++++++- drivers/clocksource/arm_arch_timer.c | 8 ++++++++ 3 files changed, 32 insertions(+), 1 deletion(-) diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h index 99175812d903..a5d27cff28fa 100644 --- a/arch/arm/include/asm/arch_timer.h +++ b/arch/arm/include/asm/arch_timer.h @@ -34,6 +34,8 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) case ARCH_TIMER_REG_TVAL: asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val)); break; + default: + BUILD_BUG(); } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { @@ -43,7 +45,11 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) case ARCH_TIMER_REG_TVAL: asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val)); break; + default: + BUILD_BUG(); } + } else { + BUILD_BUG(); } isb(); @@ -62,6 +68,8 @@ u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) case ARCH_TIMER_REG_TVAL: asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val)); break; + default: + BUILD_BUG(); } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { @@ -71,7 +79,11 @@ u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) case ARCH_TIMER_REG_TVAL: asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val)); break; + default: + BUILD_BUG(); } + } else { + BUILD_BUG(); } return val; diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index ce37c14f9417..7dfb7c6261bb 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -112,6 +112,8 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) case ARCH_TIMER_REG_TVAL: write_sysreg(val, cntp_tval_el0); break; + default: + BUILD_BUG(); } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { @@ -121,7 +123,11 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) case ARCH_TIMER_REG_TVAL: write_sysreg(val, cntv_tval_el0); break; + default: + BUILD_BUG(); } + } else { + BUILD_BUG(); } isb(); @@ -136,6 +142,8 @@ u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) return read_sysreg(cntp_ctl_el0); case ARCH_TIMER_REG_TVAL: return arch_timer_reg_read_stable(cntp_tval_el0); + default: + BUILD_BUG(); } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { @@ -143,10 +151,13 @@ u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) return read_sysreg(cntv_ctl_el0); case ARCH_TIMER_REG_TVAL: return arch_timer_reg_read_stable(cntv_tval_el0); + default: + BUILD_BUG(); } } - BUG(); + BUILD_BUG(); + unreachable(); } static inline u32 arch_timer_get_cntfrq(void) diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 3ea1c22314f9..f3c65e5181ec 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -103,6 +103,8 @@ void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val, case ARCH_TIMER_REG_TVAL: writel_relaxed(val, timer->base + CNTP_TVAL); break; + default: + BUILD_BUG(); } } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); @@ -113,6 +115,8 @@ void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val, case ARCH_TIMER_REG_TVAL: writel_relaxed(val, timer->base + CNTV_TVAL); break; + default: + BUILD_BUG(); } } else { arch_timer_reg_write_cp15(access, reg, val); @@ -134,6 +138,8 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg, case ARCH_TIMER_REG_TVAL: val = readl_relaxed(timer->base + CNTP_TVAL); break; + default: + BUILD_BUG(); } } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) { struct arch_timer *timer = to_arch_timer(clk); @@ -144,6 +150,8 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg, case ARCH_TIMER_REG_TVAL: val = readl_relaxed(timer->base + CNTV_TVAL); break; + default: + BUILD_BUG(); } } else { val = arch_timer_reg_read_cp15(access, reg); -- 2.20.1

1 81

[PATCH OLK-5.10 v3 1/3] arm64: Add memmap parameter for pmem
by Zhuling 17 Jan '22

17 Jan '22

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4O31I?from=project-issue CVE: NA Add "!" in memmap parameter, use memmap(memmap=nn[KMG]!ss[KMG]) reserve memory for pmem which register persistent memory in arm64. Signed-off-by: Zhuling <zhuling8(a)huawei.com> --- Documentation/admin-guide/kernel-parameters.txt | 9 +++++++-- arch/arm64/mm/init.c | 8 ++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 64be32b..1953570 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2829,10 +2829,15 @@ will be eaten. memmap=nn[KMG]!ss[KMG] - [KNL,X86] Mark specific memory as protected. + [KNL,X86,ARM64] Mark specific memory as protected. Region of memory to be used, from ss to ss+nn. - The memory region may be marked as e820 type 12 (0xc) + [X86]The memory region may be marked as e820 type 12 (0xc) and is NVDIMM or ADR memory. + [ARM64]Reserve memory for persistent storage when the kernel + restart or update. the data in PMEM will not be lost and can + be loaded faster + Example: + memmap=100K!0x1a0000000 memmap=<size>%<offset>-<oldtype>+<newtype> [KNL,ACPI] Convert memory within the specified region diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 6ebfabd..b9eb312 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -56,6 +56,8 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); +phys_addr_t start_at, mem_size; + #ifdef CONFIG_PIN_MEMORY struct resource pin_memory_resource = { .name = "Pin memory", @@ -111,6 +113,8 @@ static void __init reserve_pin_memory_res(void) */ phys_addr_t arm64_dma_phys_limit __ro_after_init; +static unsigned long long pmem_size, pmem_start; + #ifndef CONFIG_KEXEC_CORE static void __init reserve_crashkernel(void) { @@ -442,6 +446,10 @@ static int __init parse_memmap_one(char *p) start_at = memparse(p + 1, &p); memblock_reserve(start_at, mem_size); memblock_mark_memmap(start_at, mem_size); + } else if (*p == '!') { + start_at = memparse(p+1, &p); + pmem_start = start_at; + pmem_size = mem_size; } else pr_info("Unrecognized memmap option, please check the parameter.\n"); -- 2.9.5

3 7

[PATCH openEuler-1.0-LTS 1/2] hugetlbfs: extend the definition of hugepages parameter to support node allocation
by Yang Yingliang 17 Jan '22

17 Jan '22

From: Zhenguo Yao <yaozhenguo1(a)gmail.com> mainline inclusion from mainline-v5.16-rc1 commit b5389086ad7be0453c55e0069a89856d1fbdf605 category: feature bugzilla: 186043 CVE: NA -------------------------------- We can specify the number of hugepages to allocate at boot. But the hugepages is balanced in all nodes at present. In some scenarios, we only need hugepages in one node. For example: DPDK needs hugepages which are in the same node as NIC. If DPDK needs four hugepages of 1G size in node1 and system has 16 numa nodes we must reserve 64 hugepages on the kernel cmdline. But only four hugepages are used. The others should be free after boot. If the system memory is low(for example: 64G), it will be an impossible task. So extend the hugepages parameter to support specifying hugepages on a specific node. For example add following parameter: hugepagesz=1G hugepages=0:1,1:3 It will allocate 1 hugepage in node0 and 3 hugepages in node1. Link: https://lkml.kernel.org/r/20211005054729.86457-1-yaozhenguo1@gmail.com Signed-off-by: Zhenguo Yao <yaozhenguo1(a)gmail.com> Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Zhenguo Yao <yaozhenguo1(a)gmail.com> Cc: Dan Carpenter <dan.carpenter(a)oracle.com> Cc: Nathan Chancellor <nathan(a)kernel.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Benjamin Herrenschmidt <benh(a)kernel.crashing.org> Cc: Paul Mackerras <paulus(a)samba.org> Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Conflicts: Documentation/admin-guide/kernel-parameters.txt Documentation/admin-guide/mm/hugetlbpage.rst arch/powerpc/mm/hugetlbpage.c include/linux/hugetlb.h mm/hugetlb.c Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kefeng Wang<wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- .../admin-guide/kernel-parameters.txt | 5 + arch/powerpc/mm/hugetlbpage.c | 9 +- include/linux/hugetlb.h | 6 +- mm/hugetlb.c | 142 +++++++++++++++--- 4 files changed, 137 insertions(+), 25 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 420f7317aa6af..5623a9d1cf813 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1402,6 +1402,11 @@ registers. Default set by CONFIG_HPET_MMAP_DEFAULT. hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot. + If using node format, the number of pages to allocate + per-node can be specified. + Format: <integer> or (node format) + <node>:<integer>[,<node>:<integer>] + hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages. On x86-64 and powerpc, this option can be specified multiple times interleaved with hugepages= to reserve diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index cef0b7ee10246..163b0ef7d156e 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -241,17 +241,22 @@ int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) m->hstate = hstate; return 1; } + +bool __init hugetlb_node_alloc_supported(void) +{ + return false; +} #endif -int __init alloc_bootmem_huge_page(struct hstate *h) +int __init alloc_bootmem_huge_page(struct hstate *h, int nid) { #ifdef CONFIG_PPC_BOOK3S_64 if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) return pseries_alloc_bootmem_huge_page(h); #endif - return __alloc_bootmem_huge_page(h); + return __alloc_bootmem_huge_page(h, nid); } #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 561e7679fadc4..588f9f2a44fce 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -347,6 +347,7 @@ struct hstate { unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; @@ -409,8 +410,9 @@ int hugetlb_insert_hugepage(struct vm_area_struct *vma, unsigned long addr, struct page *hpage, pgprot_t prot); /* arch callback */ -int __init __alloc_bootmem_huge_page(struct hstate *h); -int __init alloc_bootmem_huge_page(struct hstate *h); +int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); +int __init alloc_bootmem_huge_page(struct hstate *h, int nid); +bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b2ed9174bfd73..8286a6f8cb050 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -56,6 +56,7 @@ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static unsigned long __initdata default_hstate_size; static bool __initdata parsed_valid_hugepagesz = true; +static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; int enable_charge_mighp __read_mostly; /* @@ -2241,33 +2242,39 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, return ERR_PTR(-ENOSPC); } -int alloc_bootmem_huge_page(struct hstate *h) +int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); -int __alloc_bootmem_huge_page(struct hstate *h) +int __alloc_bootmem_huge_page(struct hstate *h, int nid) { - struct huge_bootmem_page *m; + struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; + if (nid >= nr_online_nodes) + return 0; + /* do node specific alloc */ + if (nid != NUMA_NO_NODE) { + m = memblock_virt_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + if (!m) + return 0; + goto found; + } + /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { - void *addr; - - addr = memblock_virt_alloc_try_nid_raw( + m = memblock_virt_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, BOOTMEM_ALLOC_ACCESSIBLE, node); - if (addr) { - /* - * Use the beginning of the huge page to store the - * huge_bootmem_page struct (until gather_bootmem - * puts them into the mem_map). - */ - m = addr; - goto found; - } + /* + * Use the beginning of the huge page to store the + * huge_bootmem_page struct (until gather_bootmem + * puts them into the mem_map). + */ + if (!m) + return 0; + goto found; } - return 0; found: - BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); @@ -2310,12 +2317,55 @@ static void __init gather_bootmem_prealloc(void) cond_resched(); } } +static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) +{ + unsigned long i; + char buf[32]; + + for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { + if (hstate_is_gigantic(h)) { + if (!alloc_bootmem_huge_page(h, nid)) + break; + } else { + struct page *page; + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + + page = alloc_fresh_huge_page(h, gfp_mask, nid, + &node_states[N_MEMORY], NULL); + if (!page) + break; + put_page(page); /* free it into the hugepage allocator */ + } + cond_resched(); + } + if (i == h->max_huge_pages_node[nid]) + return; + + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", + h->max_huge_pages_node[nid], buf, nid, i); + h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); + h->max_huge_pages_node[nid] = i; +} static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; nodemask_t *node_alloc_noretry; + bool node_specific_alloc = false; + + /* do node specific alloc */ + for (i = 0; i < nr_online_nodes; i++) { + if (h->max_huge_pages_node[i] > 0) { + hugetlb_hstate_alloc_pages_onenode(h, i); + node_specific_alloc = true; + } + } + + if (node_specific_alloc) + return; + /* below will do all node balanced alloc */ if (!hstate_is_gigantic(h)) { /* * Bit mask controlling how hard we retry per-node allocations. @@ -2336,7 +2386,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { - if (!alloc_bootmem_huge_page(h)) + if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; } else if (!alloc_pool_huge_page(h, &node_states[N_MEMORY], @@ -2991,8 +3041,13 @@ static int __init hugetlb_init(void) } default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size)); if (default_hstate_max_huge_pages) { - if (!default_hstate.max_huge_pages) + if (!default_hstate.max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; + + for (i = 0; i < nr_online_nodes; i++) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; + } } hugetlb_init_hstates(); @@ -3052,10 +3107,19 @@ void __init hugetlb_add_hstate(unsigned int order) parsed_hstate = h; } +bool __init __weak hugetlb_node_alloc_supported(void) +{ + return true; +} + static int __init hugetlb_nrpages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; + int node = NUMA_NO_NODE; + int count; + unsigned long tmp; + char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("hugepages = %s preceded by " @@ -3077,8 +3141,40 @@ static int __init hugetlb_nrpages_setup(char *s) return 1; } - if (sscanf(s, "%lu", mhp) <= 0) - *mhp = 0; + while (*p) { + count = 0; + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + /* Parameter is node format */ + if (p[count] == ':') { + if (!hugetlb_node_alloc_supported()) { + pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); + return 0; + } + node = tmp; + p += count + 1; + if (node < 0 || node >= nr_online_nodes) + goto invalid; + /* Parse hugepages */ + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + if (!hugetlb_max_hstate) + default_hugepages_in_node[node] = tmp; + else + parsed_hstate->max_huge_pages_node[node] = tmp; + *mhp += tmp; + /* Go to parse next node*/ + if (p[count] == ',') + p += count + 1; + else + break; + } else { + if (p != s) + goto invalid; + *mhp = tmp; + break; + } + } /* * Global state is always initialized later in hugetlb_init. @@ -3091,6 +3187,10 @@ static int __init hugetlb_nrpages_setup(char *s) last_mhp = mhp; return 1; + +invalid: + pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); + return 0; } __setup("hugepages=", hugetlb_nrpages_setup); -- 2.25.1

1 1

回复:答复: openEuler kernel技术分享第十七期 & 双周例会
by Zhengyuan Liu 17 Jan '22

17 Jan '22

你好 rdma这个议题什么气候开始呢 ---------- 该邮件从移动设备发送 --------------原始邮件-------------- 发件人："tangjiayuan "<tangjiayuan(a)huawei.com>; 发送时间：2022年1月17日(星期一) 下午3:10 收件人："kernel(a)openeuler.org" <kernel(a)openeuler.org>;"kernel-discuss(a)openeuler.org" <kernel-discuss(a)openeuler.org>; 抄送："xie xiuqi "<xiexiuqi(a)huawei.com>;"chengjian (D) "<cj.chengjian(a)huawei.com>;"qiulaibin "<qiulaibin(a)huawei.com>; 主题：答复: openEuler kernel技术分享第十七期 & 双周例会 ----------------------------------- Kernel SIG增加一个议题：希望在内核态支持RDMA通信 -----邮件原件----- 发件人: openEuler conference [mailto:public@openeuler.org] 发送时间: 2021年12月27日 10:20 收件人: kernel(a)openeuler.org; tc(a)openeuler.org; dev(a)openeuler.org; kernel-discuss(a)openeuler.org 主题: openEuler kernel技术分享第十七期 & 双周例会您好！ Kernel SIG 邀请您参加 2021-12-31 14:00 召开的ZOOM会议(自动录制) 会议主题：openEuler kernel技术分享第十七期 & 双周例会会议内容： 14:10-15:30 openEuler kernel 技术分享第17期 - cgroup介绍会议链接：https://us06web.zoom.us/j/83118407147?pwd=elVzMVhGc2YzaDQ1TGorN2tPa1NhZz09 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the ZOOM conference(auto recording) will be held at 2021-12-31 14:00, The subject of the conference is openEuler kernel技术分享第十七期 & 双周例会, Summary: 14:10-15:30 openEuler kernel 技术分享第17期 - cgroup介绍 You can join the meeting at https://us06web.zoom.us/j/83118407147?pwd=elVzMVhGc2YzaDQ1TGorN2tPa1NhZz09. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/ _______________________________________________ Kernel-discuss mailing list -- kernel-discuss(a)openeuler.org To unsubscribe send an email to kernel-discuss-leave(a)openeuler.org _______________________________________________ Kernel mailing list -- kernel(a)openeuler.org To unsubscribe send an email to kernel-leave(a)openeuler.org

1 0

[PATCH openEuler-1.0-LTS 1/2] share pool: use rwsem to protect sp group exit
by Yang Yingliang 17 Jan '22

17 Jan '22

From: Guo Mengqi <guomengqi3(a)huawei.com> ascend inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4ODMN CVE: NA ------------------------------------------------- Fix following situation: when the last process in a group exits, and a second process tries to add to this group. The second process may get a invalid spg. However the group's use_count is increased by 1, which caused the first process failed to free the group when it exits. And then second process called sp_group_drop --> free_sp_group and cause a double request of rwsem. Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index 428742f5d4044..c79ea4bb06026 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -711,20 +711,25 @@ static void free_new_spg_id(bool new, int spg_id) free_sp_group_id(spg_id); } -static void free_sp_group(struct sp_group *spg) +static void free_sp_group_locked(struct sp_group *spg) { fput(spg->file); fput(spg->file_hugetlb); free_spg_stat(spg->id); - down_write(&sp_group_sem); idr_remove(&sp_group_idr, spg->id); - up_write(&sp_group_sem); free_sp_group_id((unsigned int)spg->id); kfree(spg); system_group_count--; WARN(system_group_count < 0, "unexpected group count\n"); } +static void free_sp_group(struct sp_group *spg) +{ + down_write(&sp_group_sem); + free_sp_group_locked(spg); + up_write(&sp_group_sem); +} + static void sp_group_drop(struct sp_group *spg) { if (atomic_dec_and_test(&spg->use_count)) @@ -4460,14 +4465,15 @@ void sp_group_post_exit(struct mm_struct *mm) sp_proc_stat_drop(stat); } - /* lockless traverse */ + down_write(&sp_group_sem); list_for_each_entry_safe(spg_node, tmp, &master->node_list, group_node) { spg = spg_node->spg; /* match with refcount inc in sp_group_add_task */ - sp_group_drop(spg); + if (atomic_dec_and_test(&spg->use_count)) + free_sp_group_locked(spg); kfree(spg_node); } - + up_write(&sp_group_sem); kfree(master); } -- 2.25.1

1 1