- Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] block: don't get gendisk if queue has not been registered
by Li Lingfeng 01 Sep '23

01 Sep '23

hulk inclusion category: bugfix bugzilla: 189153, https://gitee.com/openeuler/kernel/issues/I7XTQH CVE: NA ---------------------------------------- Creating and using dm device at same time may trigger null-ptr-deref or deadlock. Some resources have not been initialized after calling add_disk in the process of creating dm device, which means users can get device and use some uninitialized resources. Using uninitialized resources may trigger null-ptr-deref directly. What's more, IO can't be finished by waiting specific resources to be initialized and the resources can't be initialized since IO is inflight, which triggers deadlock. Don't get gendisk if queue has not been registered to fix this. Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- block/blk-sysfs.c | 4 ++-- block/blk-throttle.c | 2 +- fs/block_dev.c | 6 ++++++ include/linux/blkdev.h | 2 +- 4 files changed, 10 insertions(+), 4 deletions(-) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 1b00c8f5c9d6..1c4d795bbdc4 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -976,7 +976,7 @@ int blk_register_queue(struct gendisk *disk) blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); wbt_enable_default(q); blk_throtl_register_queue(q); - blk_queue_flag_set(QUEUE_FLAG_THROTL_INIT_DONE, q); + blk_queue_flag_set(QUEUE_FLAG_REGISTER_DONE, q); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&q->kobj, KOBJ_ADD); @@ -1025,7 +1025,7 @@ void blk_unregister_queue(struct gendisk *disk) if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags)) return; - blk_queue_flag_clear(QUEUE_FLAG_THROTL_INIT_DONE, q); + blk_queue_flag_clear(QUEUE_FLAG_REGISTER_DONE, q); /* * Since sysfs_remove_dir() prevents adding new directory entries * before removal of existing entries starts, protect against diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 1c5ac48a9de8..598191286557 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1493,7 +1493,7 @@ static void tg_conf_updated(struct throtl_grp *tg, u64 *old_limits, bool global) static inline int throtl_check_init_done(struct request_queue *q) { - if (test_bit(QUEUE_FLAG_THROTL_INIT_DONE, &q->queue_flags)) + if (test_bit(QUEUE_FLAG_REGISTER_DONE, &q->queue_flags)) return 0; return blk_queue_dying(q) ? -ENODEV : -EBUSY; diff --git a/fs/block_dev.c b/fs/block_dev.c index d8a10f477558..e072d1ef16ef 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1173,6 +1173,12 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) if (!disk) return NULL; + + if (!test_bit(QUEUE_FLAG_REGISTER_DONE, &disk->queue->queue_flags)) { + put_disk_and_module(disk); + return NULL; + } + /* * Now that we hold gendisk reference we make sure bdev we looked up is * not stale. If it is, it means device got removed and created before diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 41d235ee579a..c848f4205729 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -713,7 +713,7 @@ struct request_queue { #define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ -#define QUEUE_FLAG_THROTL_INIT_DONE 8 /* io throttle can be online */ +#define QUEUE_FLAG_REGISTER_DONE 8 /* blkdev can be opened */ #define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ -- 2.31.1

2 1

[PATCH OLK-5.10 00/19] x86/speculation: Add force option to GDS mitigation
by Zeng Heng 01 Sep '23

01 Sep '23

Borislav Petkov (1): x86/cpu: Init AP exception handling from cpu_init_secondary() Daniel Sneddon (3): x86/speculation: Add force option to GDS mitigation x86/speculation: Add Kconfig option for GDS KVM: Add GDS_NO support to KVM Dave Hansen (1): Documentation/x86: Fix backwards on/off logic about YMM support Juergen Gross (2): x86/xen: Fix secondary processors' FPU initialization x86/mm: fix poking_init() for Xen PV guests Peter Zijlstra (3): x86/mm: Use mm_alloc() in poking_init() mm: Move mm_cachep initialization to mm_init() x86/mm: Initialize text poking earlier Thomas Gleixner (9): init: Provide arch_cpu_finalize_init() x86/cpu: Switch to arch_cpu_finalize_init() ARM: cpu: Switch to arch_cpu_finalize_init() init: Remove check_bugs() leftovers init: Invoke arch_cpu_finalize_init() earlier init, x86: Move mem_encrypt_init() into arch_cpu_finalize_init() x86/fpu: Remove cpuinfo argument from init functions x86/fpu: Mark init functions __init x86/fpu: Move FPU initialization into arch_cpu_finalize_init() .../hw-vuln/gather_data_sampling.rst | 18 ++- .../admin-guide/kernel-parameters.txt | 8 +- arch/Kconfig | 3 + arch/alpha/include/asm/bugs.h | 20 ---- arch/arm/Kconfig | 1 + arch/arm/include/asm/bugs.h | 4 - arch/arm/kernel/bugs.c | 3 +- arch/parisc/include/asm/bugs.h | 20 ---- arch/powerpc/include/asm/bugs.h | 15 --- arch/x86/Kconfig | 20 ++++ arch/x86/include/asm/bugs.h | 2 - arch/x86/include/asm/fpu/api.h | 2 +- arch/x86/include/asm/mem_encrypt.h | 7 +- arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/cpu/bugs.c | 82 ++++++-------- arch/x86/kernel/cpu/common.c | 104 +++++++++++++++--- arch/x86/kernel/cpu/cpu.h | 1 + arch/x86/kernel/fpu/init.c | 8 +- arch/x86/kernel/smpboot.c | 3 +- arch/x86/kernel/traps.c | 4 +- arch/x86/kvm/x86.c | 7 +- arch/x86/mm/init.c | 7 +- arch/x86/xen/smp_pv.c | 2 + arch/xtensa/include/asm/bugs.h | 18 --- include/asm-generic/bugs.h | 11 -- include/linux/cpu.h | 6 + include/linux/sched/task.h | 2 +- init/main.c | 21 +--- kernel/fork.c | 37 +++---- 29 files changed, 222 insertions(+), 215 deletions(-) delete mode 100644 arch/alpha/include/asm/bugs.h delete mode 100644 arch/parisc/include/asm/bugs.h delete mode 100644 arch/powerpc/include/asm/bugs.h delete mode 100644 arch/xtensa/include/asm/bugs.h delete mode 100644 include/asm-generic/bugs.h -- 2.25.1

2 20

[PATCH openEuler-1.0-LTS] fuse: revalidate: don't invalidate if interrupted
by ZhaoLong Wang 31 Aug '23

31 Aug '23

From: Miklos Szeredi <mszeredi(a)redhat.com> stable inclusion from stable-v4.19.201 commit 00260209e140aae7f1a274b27e29fa6b4e986f95 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7XMB3 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit a9d1c4c6df0e568207907c04aed9e7beb1294c42 upstream. If the LOOKUP request triggered from fuse_dentry_revalidate() is interrupted, then the dentry will be invalidated, possibly resulting in submounts being unmounted. Reported-by: Xu Rongbo <xurongbo(a)baidu.com> Closes: https://lore.kernel.org/all/CAJfpegswN_CJJ6C3RZiaK6rpFmNyWmXfaEpnQUJ42KCwNF… Fixes: 9e6268db496a ("[PATCH] FUSE - read-write operations") Cc: <stable(a)vger.kernel.org> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/fuse/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b468ccb296c3..6068955995da 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -232,7 +232,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) spin_unlock(&fc->lock); } kfree(forget); - if (ret == -ENOMEM) + if (ret == -ENOMEM || ret == -EINTR) goto out; if (ret || fuse_invalid_attr(&outarg.attr) || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) -- 2.34.3

2 1

[PATCH OLK-5.10 0/2] zs_malloc: return ERR_PTR on failure
by Jinjiang Tu 31 Aug '23

31 Aug '23

1. zs_malloc() returns error code instead of 0 when error happens. 2. check parameter handle in zs_free(). Hui Zhu (1): zsmalloc: zs_malloc: return ERR_PTR on failure Sergey Senozhatsky (1): mm/zsmalloc: do not attempt to free IS_ERR handle drivers/block/zram/zram_drv.c | 10 +++++----- mm/zsmalloc.c | 15 +++++++++------ 2 files changed, 14 insertions(+), 11 deletions(-) -- 2.25.1

2 3

[PATCH v2 openEuler-23.09 0/2] openeuler_defconfig: Enable SDEI Watchdog
by Wupeng Ma 31 Aug '23

31 Aug '23

From: Ma Wupeng <mawupeng1(a)huawei.com> Tweak gmem related configs 1. Remove select config GMEM_DEV for gmem. 2. Enable gmem related configs. Changelog since v1: 1. add license for gmem_dev. Ma Wupeng (2): mm: gmem: Remove select config GMEM_DEV for gmem openeuler_defconfig: Enable gmem related configs arch/arm64/configs/openeuler_defconfig | 2 ++ arch/x86/configs/openeuler_defconfig | 2 ++ drivers/char/gmem_dev.c | 1 + mm/Kconfig | 1 - 4 files changed, 5 insertions(+), 1 deletion(-) -- 2.25.1

2 3

[PATCH v6 openEuler-23.09 00/25] backport etmem feature from OLK-5.10
by liubo 31 Aug '23

31 Aug '23

This patch set is used to backport etmem feature patches to version 23.09. etmem is a tiered memory extension technology that uses DRAM+memory compression/high-performance storage media to form tiered memory storage. Memory data is tiered, and cold data is migrated from memory media to high-performance storage media to release memory space and reduce memory costs. v5 -> v6 - Change the value of sysctl_hugetlb_* to static and delete unnecessary external declarations. v4 -> v5 - fix some review comment during https://gitee.com/openeuler/kernel/pulls/1772 patch v3 -> v4 - fix the commit message format error v2 -> v3 - fix the build problem in riscv64 arch. v1 -> v2 - some cleanup fix Kemeng Shi (11): etmem: add ioctl for mm idle scan etmem: x86: support scan hugetlb of vm etmem_scan: x86: support scan 4 level ept under 5 level host page table etmem scan: fix memleak in vm_idle_read etmem: fix concurrent access to export file operations etmem: fix potential UAF when walk ept page table etmem_scan: release CPU after scan walk_step size etmem_scan: add pte_hole callback acpi/numa: memorize node type from SRAT table hugepage: add sysctl for hugepage alloc and mig x86: hugepage: use nt copy hugepage to AEP in x86 liubo (14): memig: add memig-scan feature to openEuler memig: add memig-swap feature to openEuler memig: fix compile error when CONFIG_NUMA is turned off etmem: Modify the memig feature name to etmem move ETMEM feature CONFIG to mm/Kconfig and add architecture dependency etmem: etmem scan module Replace WARN_ONCE() with debug_printk for "nothing read" add ETMEM feature CONFIG to mm/Kconfig config: enable CONFIG_ETMEM by default etmem: add CONFIG_ETMEM macro definition for etmem feature etmem: add original kernel swap enabled options etmem: add swapcache reclaim to etmem etmem: Add a scan flag to support specified page swap-out etmem: fix the div 0 problem in swapcache reclaim process etmem: fix some problem during backport etmem patches arch/arm64/configs/openeuler_defconfig | 3 + arch/x86/configs/openeuler_defconfig | 3 + arch/x86/include/asm/page_64.h | 7 + arch/x86/lib/Makefile | 1 + arch/x86/lib/copy_highpages.c | 107 ++ arch/x86/lib/copy_page_64.S | 73 ++ drivers/acpi/numa/srat.c | 5 + fs/proc/Makefile | 2 + fs/proc/base.c | 8 + fs/proc/etmem_scan.c | 1382 ++++++++++++++++++++++++ fs/proc/etmem_scan.h | 149 +++ fs/proc/etmem_swap.c | 282 +++++ fs/proc/internal.h | 4 + fs/proc/task_mmu.c | 194 ++++ include/linux/highmem.h | 17 + include/linux/list.h | 17 + include/linux/mm.h | 4 + include/linux/mm_types.h | 17 +- include/linux/numa.h | 12 + include/linux/swap.h | 39 + include/uapi/asm-generic/mman-common.h | 4 + mm/Kconfig | 25 + mm/Makefile | 1 + mm/etmem.c | 383 +++++++ mm/huge_memory.c | 1 + mm/hugetlb.c | 27 +- mm/internal.h | 1 - mm/madvise.c | 17 +- mm/page_alloc.c | 13 + mm/pagewalk.c | 1 + mm/swap_state.c | 3 + mm/util.c | 11 +- mm/vmscan.c | 18 + virt/kvm/kvm_main.c | 6 + 34 files changed, 2824 insertions(+), 13 deletions(-) create mode 100644 arch/x86/lib/copy_highpages.c create mode 100644 fs/proc/etmem_scan.c create mode 100644 fs/proc/etmem_scan.h create mode 100644 fs/proc/etmem_swap.c create mode 100644 mm/etmem.c -- 2.27.0

2 26

[PATCH openEuler-23.09 0/2] Tweak gmem related configs
by Wupeng Ma 31 Aug '23

31 Aug '23

From: Ma Wupeng <mawupeng1(a)huawei.com> 1. Remove select config GMEM_DEV for gmem. 2. Enable gmem related configs. Ma Wupeng (2): mm: gmem: Remove select config GMEM_DEV for gmem openeuler_defconfig: Enable gmem related configs arch/arm64/configs/openeuler_defconfig | 2 ++ arch/x86/configs/openeuler_defconfig | 2 ++ mm/Kconfig | 1 - 3 files changed, 4 insertions(+), 1 deletion(-) -- 2.25.1

2 3

[PATCH v5 openEuler-23.09 00/25] backport etmem feature from OLK-5.10
by liubo 31 Aug '23

31 Aug '23

This patch set is used to backport etmem feature patches to version 23.09. etmem is a tiered memory extension technology that uses DRAM+memory compression/high-performance storage media to form tiered memory storage. Memory data is tiered, and cold data is migrated from memory media to high-performance storage media to release memory space and reduce memory costs. v4 -> v5 - fix some review comment during https://gitee.com/openeuler/kernel/pulls/1772 patch v3 -> v4 - fix the commit message format error v2 -> v3 - fix the build problem in riscv64 arch. v1 -> v2 - some cleanup fix Kemeng Shi (11): etmem: add ioctl for mm idle scan etmem: x86: support scan hugetlb of vm etmem_scan: x86: support scan 4 level ept under 5 level host page table etmem scan: fix memleak in vm_idle_read etmem: fix concurrent access to export file operations etmem: fix potential UAF when walk ept page table etmem_scan: release CPU after scan walk_step size etmem_scan: add pte_hole callback acpi/numa: memorize node type from SRAT table hugepage: add sysctl for hugepage alloc and mig x86: hugepage: use nt copy hugepage to AEP in x86 liubo (14): memig: add memig-scan feature to openEuler memig: add memig-swap feature to openEuler memig: fix compile error when CONFIG_NUMA is turned off etmem: Modify the memig feature name to etmem move ETMEM feature CONFIG to mm/Kconfig and add architecture dependency etmem: etmem scan module Replace WARN_ONCE() with debug_printk for "nothing read" add ETMEM feature CONFIG to mm/Kconfig config: enable CONFIG_ETMEM by default etmem: add CONFIG_ETMEM macro definition for etmem feature etmem: add original kernel swap enabled options etmem: add swapcache reclaim to etmem etmem: Add a scan flag to support specified page swap-out etmem: fix the div 0 problem in swapcache reclaim process etmem: fix some problem during backport etmem patches arch/arm64/configs/openeuler_defconfig | 3 + arch/x86/configs/openeuler_defconfig | 3 + arch/x86/include/asm/page_64.h | 7 + arch/x86/lib/Makefile | 1 + arch/x86/lib/copy_highpages.c | 107 ++ arch/x86/lib/copy_page_64.S | 73 ++ drivers/acpi/numa/srat.c | 5 + fs/proc/Makefile | 2 + fs/proc/base.c | 8 + fs/proc/etmem_scan.c | 1382 ++++++++++++++++++++++++ fs/proc/etmem_scan.h | 149 +++ fs/proc/etmem_swap.c | 282 +++++ fs/proc/internal.h | 4 + fs/proc/task_mmu.c | 194 ++++ include/linux/highmem.h | 17 + include/linux/hugetlb.h | 6 + include/linux/list.h | 17 + include/linux/mm.h | 4 + include/linux/mm_types.h | 17 +- include/linux/numa.h | 12 + include/linux/swap.h | 39 + include/uapi/asm-generic/mman-common.h | 4 + mm/Kconfig | 25 + mm/Makefile | 1 + mm/etmem.c | 383 +++++++ mm/huge_memory.c | 1 + mm/hugetlb.c | 27 +- mm/internal.h | 1 - mm/madvise.c | 17 +- mm/page_alloc.c | 13 + mm/pagewalk.c | 1 + mm/swap_state.c | 3 + mm/util.c | 11 +- mm/vmscan.c | 19 + virt/kvm/kvm_main.c | 6 + 35 files changed, 2831 insertions(+), 13 deletions(-) create mode 100644 arch/x86/lib/copy_highpages.c create mode 100644 fs/proc/etmem_scan.c create mode 100644 fs/proc/etmem_scan.h create mode 100644 fs/proc/etmem_swap.c create mode 100644 mm/etmem.c -- 2.27.0

2 26

[PATCH v3 openEuler-23.09 00/46] ima: Add IMA digest lists extension
by Zhou Shuiqing 31 Aug '23

31 Aug '23

This patchset supports IMA digest lists for the kernel. v2: -remove unused variable in ima_main.c v3: -modify patch header information David Howells (4): PGPLIB: PGP definitions (RFC 4880) PGPLIB: Basic packet parser KEYS: Provide PGP key description autogeneration KEYS: Provide a function to load keys from a PGP keyring blob Mimi Zohar (1): initramfs: add file metadata Roberto Sassu (32): initramfs: read metadata from special file METADATA!!! gen_init_cpio: add support for file metadata init: Add kernel option to force usage of tmpfs for rootfs ima: Add enforce-evm and log-evm modes to strictly check EVM status ima: Generalize ima_read_policy() ima: Generalize ima_write_policy() and raise uploaded data size limit ima: Generalize policy file operations ima: Use ima_show_htable_value to show violations and hash table data ima: Add parser of compact digest list ima: Prevent usage of digest lists not measured or appraised ima: Introduce new securityfs files ima: Introduce new hook DIGEST_LIST_CHECK ima: Load all digest lists from a directory at boot time ima: Add support for measurement with digest lists ima: Add support for appraisal with digest lists evm: Add support for digest lists of metadata ima: Introduce exec_tcb policy ima: Introduce appraise_exec_tcb policy ima: Introduce appraise_exec_immutable policy ima: Add Documentation/security/IMA-digest-lists.txt mpi: introduce mpi_key_length() rsa: add parser of raw format KEYS: PGP data parser KEYS: Introduce load_pgp_public_keyring() certs: Introduce search_trusted_key() ima: Search key in the built-in keyrings ima: Allow direct upload of digest lists to securityfs ima: Add parser keyword to the policy evm: Extend evm= with x509. allow_metadata_writes and complete values ima: Execute parser to upload digest lists not recognizable by the kernel evm: Propagate choice of HMAC algorithm in evm_crypto.c config: add digest list options for arm64 and x86 Zhang Tianxing (5): ima: fix a memory leak in ima_del_digest_data_entry ima: Add max size for IMA digest database ima: don't allow control characters in policy path ima: fix CONFIG_IMA_DIGEST_DB_MEGABYTES in openeuler_defconfig ima: fix db size overflow and Kconfig issues Zheng Zengkai (1): Revert "evm: Refuse EVM_ALLOW_METADATA_WRITES only if an HMAC key is loaded" Zhou Shuiqing (2): ima: Allow choice of file hash algorithm for measurement and audit ima: Add meta_immutable appraisal type shenxiangwei (1): ima: bugfix for digest lists importing Documentation/ABI/testing/evm | 4 +- .../admin-guide/kernel-parameters.txt | 49 +- Documentation/security/IMA-digest-lists.txt | 259 ++++++++++ arch/arm64/configs/openeuler_defconfig | 11 + arch/x86/configs/openeuler_defconfig | 31 +- certs/Kconfig | 7 + certs/Makefile | 7 + certs/system_certificates.S | 18 + certs/system_keyring.c | 44 ++ crypto/asymmetric_keys/Kconfig | 25 + crypto/asymmetric_keys/Makefile | 10 + crypto/asymmetric_keys/pgp_library.c | 281 +++++++++++ crypto/asymmetric_keys/pgp_parser.h | 23 + crypto/asymmetric_keys/pgp_preload.c | 119 +++++ crypto/asymmetric_keys/pgp_public_key.c | 383 +++++++++++++++ crypto/rsa.c | 14 +- crypto/rsa_helper.c | 69 +++ include/crypto/internal/rsa.h | 6 + include/linux/initramfs.h | 21 + include/linux/kernel_read_file.h | 1 + include/linux/mpi.h | 2 + include/linux/pgp.h | 220 +++++++++ include/linux/pgplib.h | 48 ++ include/linux/verification.h | 4 + init/do_mounts.c | 11 +- init/initramfs.c | 138 +++++- lib/mpi/mpicoder.c | 33 +- security/integrity/digsig_asymmetric.c | 10 + security/integrity/evm/Kconfig | 32 ++ security/integrity/evm/evm.h | 1 + security/integrity/evm/evm_crypto.c | 24 +- security/integrity/evm/evm_main.c | 103 +++- security/integrity/evm/evm_secfs.c | 2 +- security/integrity/iint.c | 2 + security/integrity/ima/Kconfig | 49 ++ security/integrity/ima/Makefile | 1 + security/integrity/ima/ima.h | 39 +- security/integrity/ima/ima_api.c | 42 +- security/integrity/ima/ima_appraise.c | 117 ++++- security/integrity/ima/ima_digest_list.c | 465 ++++++++++++++++++ security/integrity/ima/ima_digest_list.h | 54 ++ security/integrity/ima/ima_fs.c | 294 ++++++++--- security/integrity/ima/ima_init.c | 2 +- security/integrity/ima/ima_main.c | 125 ++++- security/integrity/ima/ima_policy.c | 117 ++++- security/integrity/integrity.h | 47 +- usr/Kconfig | 8 + usr/Makefile | 4 +- usr/gen_init_cpio.c | 136 ++++- usr/gen_initramfs.sh | 7 +- 50 files changed, 3300 insertions(+), 219 deletions(-) create mode 100644 Documentation/security/IMA-digest-lists.txt create mode 100644 crypto/asymmetric_keys/pgp_library.c create mode 100644 crypto/asymmetric_keys/pgp_parser.h create mode 100644 crypto/asymmetric_keys/pgp_preload.c create mode 100644 crypto/asymmetric_keys/pgp_public_key.c create mode 100644 include/linux/initramfs.h create mode 100644 include/linux/pgp.h create mode 100644 include/linux/pgplib.h create mode 100644 security/integrity/ima/ima_digest_list.c create mode 100644 security/integrity/ima/ima_digest_list.h -- 2.33.0

1 46

[PATCH openEuler-1.0-LTS] sched: Add 'affinity_preferred_nodes' for smart grid
by Hui Tang 31 Aug '23

31 Aug '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7G6SW CVE: NA ------------------------------- Add sysctl 'affinity_preferred_nodes' to set preferred nodes. For example: echo 0,3 > /proc/sys/kernel/affinity_preferred_nodes The preferred nodes is preferentially selected to init affinity domain if util is lower than 85%. If the util is higher than 85% and less than 15% higher than the non-preferred node, the node is also preferentially selected. Signed-off-by: Hui Tang <tanghui20(a)huawei.com> --- include/linux/sched/sysctl.h | 4 + kernel/sched/fair.c | 177 +++++++++++++++++------------------ kernel/sched/sched.h | 1 + kernel/sysctl.c | 7 ++ 4 files changed, 98 insertions(+), 91 deletions(-) diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index ad472760e97d7..8475ee46727ac 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -38,6 +38,10 @@ extern int sysctl_sched_util_low_pct; #ifdef CONFIG_QOS_SCHED_SMART_GRID extern int sysctl_affinity_adjust_delay_ms; +extern unsigned long *smart_grid_preferred_nodemask_bits; +extern int proc_cpu_affinity_domain_nodemask(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); #endif enum sched_tunable_scaling { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e9afb1e6ca4ca..571123e2a23a6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5296,6 +5296,9 @@ static unsigned long weighted_cpuload(struct rq *rq); static inline bool prefer_cpus_valid(struct task_struct *p); int sysctl_affinity_adjust_delay_ms = 5000; +nodemask_t smart_grid_preferred_nodemask; +unsigned long *smart_grid_preferred_nodemask_bits = + nodes_addr(smart_grid_preferred_nodemask); struct static_key __smart_grid_used; @@ -5494,90 +5497,6 @@ void stop_auto_affinity(struct auto_affinity *auto_affi) mutex_unlock(&smart_grid_used_mutex); } -static struct sched_group *sd_find_idlest_group(struct sched_domain *sd) -{ - struct sched_group *idlest = NULL, *group = sd->groups; - unsigned long min_runnable_load = ULONG_MAX; - unsigned long min_avg_load = ULONG_MAX; - int imbalance_scale = 100 + (sd->imbalance_pct-100)/2; - unsigned long imbalance = scale_load_down(NICE_0_LOAD) * - (sd->imbalance_pct-100) / 100; - - do { - unsigned long load, avg_load, runnable_load; - int i; - - avg_load = 0; - runnable_load = 0; - - for_each_cpu(i, sched_group_span(group)) { - load = target_load(i, 0); - runnable_load += load; - avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); - } - - avg_load = (avg_load * SCHED_CAPACITY_SCALE) / - group->sgc->capacity; - runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) / - group->sgc->capacity; - - if (min_runnable_load > (runnable_load + imbalance)) { - min_runnable_load = runnable_load; - min_avg_load = avg_load; - idlest = group; - } else if ((runnable_load < (min_runnable_load + imbalance)) && - (100*min_avg_load > imbalance_scale*avg_load)) { - min_avg_load = avg_load; - idlest = group; - } - } while (group = group->next, group != sd->groups); - - return idlest ? idlest : group; -} - -static int group_find_idlest_cpu(struct sched_group *group) -{ - int least_loaded_cpu = cpumask_first(sched_group_span(group)); - unsigned long load, min_load = ULONG_MAX; - unsigned int min_exit_latency = UINT_MAX; - u64 latest_idle_timestamp = 0; - int shallowest_idle_cpu = -1; - int i; - - if (group->group_weight == 1) - return least_loaded_cpu; - - for_each_cpu(i, sched_group_span(group)) { - if (sched_idle_cpu(i)) - return i; - - if (available_idle_cpu(i)) { - struct rq *rq = cpu_rq(i); - struct cpuidle_state *idle = idle_get_state(rq); - - if (idle && idle->exit_latency < min_exit_latency) { - min_exit_latency = idle->exit_latency; - latest_idle_timestamp = rq->idle_stamp; - shallowest_idle_cpu = i; - } else if ((!idle || - idle->exit_latency == min_exit_latency) && - rq->idle_stamp > latest_idle_timestamp) { - latest_idle_timestamp = rq->idle_stamp; - shallowest_idle_cpu = i; - } - } else if (shallowest_idle_cpu == -1) { - load = weighted_cpuload(cpu_rq(i)); - if (load < min_load) { - min_load = load; - least_loaded_cpu = i; - } - } - } - - return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : - least_loaded_cpu; -} - void free_affinity_domains(struct affinity_domain *ad) { int i; @@ -5612,14 +5531,72 @@ static int init_affinity_domains_orig(struct affinity_domain *ad) return -ENOMEM; } +struct nid_stats { + unsigned long util; + unsigned long compute_capacity; +}; + +static inline void update_nid_stats(struct nid_stats *ns, int nid) +{ + int cpu; + + memset(ns, 0, sizeof(*ns)); + for_each_cpu(cpu, cpumask_of_node(nid)) { + ns->compute_capacity += capacity_of(cpu); + ns->util += cpu_util(cpu); + } +} + +static int find_idlest_nid(void) +{ + int nid, imbalance_pct, is_prefer; + unsigned long long util_min = UINT_MAX; + int idlest_is_prefer = 0; + struct nid_stats ns; + int idlest_nid = 0; + + for_each_online_node(nid) { + if (!cpumask_intersects(cpumask_of_node(nid), + housekeeping_cpumask(HK_FLAG_DOMAIN))) + continue; + + update_nid_stats(&ns, nid); + + if (node_isset(nid, smart_grid_preferred_nodemask)) { + if (ns.util * 100 < + ns.compute_capacity * sysctl_sched_util_low_pct) { + idlest_nid = nid; + break; + } + is_prefer = 1; + } else { + is_prefer = 0; + } + + if (is_prefer && !idlest_is_prefer) + imbalance_pct = 117; // higher 15% + else if (!is_prefer && idlest_is_prefer) + imbalance_pct = 85; // lower 15% + else + imbalance_pct = 100; + + if (ns.util * 100 < util_min * imbalance_pct) { + util_min = ns.util * 100 / imbalance_pct; + idlest_nid = nid; + idlest_is_prefer = is_prefer; + } + } + + return idlest_nid; +} + static int init_affinity_domains(struct affinity_domain *ad) { - struct sched_domain *sd = NULL, *tmp; - struct sched_group *idlest = NULL; + struct sched_domain *tmp; + int cpu, idlest_nid; int ret = -ENOMEM; int dcount = 0; int i = 0; - int cpu; for (i = 0; i < AD_LEVEL_MAX; i++) { ad->domains[i] = kmalloc(sizeof(cpumask_t), GFP_KERNEL); @@ -5631,18 +5608,18 @@ static int init_affinity_domains(struct affinity_domain *ad) cpu = cpumask_first_and(cpu_active_mask, housekeeping_cpumask(HK_FLAG_DOMAIN)); for_each_domain(cpu, tmp) { - sd = tmp; dcount++; } - if (!sd || dcount > AD_LEVEL_MAX) { + if (dcount > AD_LEVEL_MAX) { rcu_read_unlock(); ret = -EINVAL; goto err; } - idlest = sd_find_idlest_group(sd); - cpu = group_find_idlest_cpu(idlest); + idlest_nid = find_idlest_nid(); + cpu = cpumask_first_and(cpumask_of_node(idlest_nid), + housekeeping_cpumask(HK_FLAG_DOMAIN)); i = 0; for_each_domain(cpu, tmp) { cpumask_copy(ad->domains[i], sched_domain_span(tmp)); @@ -5711,6 +5688,24 @@ static void destroy_auto_affinity(struct task_group *tg) kfree(tg->auto_affinity); tg->auto_affinity = NULL; } + +int proc_cpu_affinity_domain_nodemask(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int err; + + mutex_lock(&smart_grid_used_mutex); + + err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); + if (!err && write) + nodes_and(smart_grid_preferred_nodemask, + smart_grid_preferred_nodemask, + node_online_map); + + mutex_unlock(&smart_grid_used_mutex); + return err; +} #else static void destroy_auto_affinity(struct task_group *tg) {} diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1d882a2b8d5fe..ef3f5c84e8b95 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -509,6 +509,7 @@ extern void sched_offline_group(struct task_group *tg); extern void sched_move_task(struct task_struct *tsk); #ifdef CONFIG_QOS_SCHED_SMART_GRID +extern nodemask_t smart_grid_preferred_nodemask; extern void start_auto_affinity(struct auto_affinity *auto_affi); extern void stop_auto_affinity(struct auto_affinity *auto_affi); extern int init_auto_affinity(struct task_group *tg); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c7064f67f4a53..b0656ef92a2df 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1347,6 +1347,13 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &hundred_thousand, }, + { + .procname = "affinity_preferred_nodes", + .data = &smart_grid_preferred_nodemask_bits, + .maxlen = MAX_NUMNODES, + .mode = 0644, + .proc_handler = proc_cpu_affinity_domain_nodemask, + }, #endif { } }; -- 2.17.1

2 1