- Kernel - mailweb.openeuler.org

[PATCH openEuler-21.09 1/2] eulerfs: add the /proc/stat2 file
by Hongyu Li 13 Oct '21

13 Oct '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- The default way of calculating CPU utilization is to check which task is executed during the interval of two ticks. This leads to the inaccurate results of CPU utilization. This problem can be solved by counting the idle time via scheduler rather than the tick interval. We can record the time before executing idle process and calculate the execute time before quiting the idle process. The idle time of each CPU is given in the /proc/stat2 file. This way can give higher precision in accounting the CPU idle time compared with the /proc/stat. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++++ kernel/sched/idle.c | 38 ++++++++++++++++++ 5 files changed, 171 insertions(+) create mode 100644 fs/proc/stat2.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..33588a37579e 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/stat2 file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/stat2 file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..b0d5f2b347d7 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += stat2.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/stat2.c b/fs/proc/stat2.c new file mode 100644 index 000000000000..6036a946c71d --- /dev/null +++ b/fs/proc/stat2.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/proc/stat2.c + * + * Copyright (C) 2007 + * + * cpu idle time accouting + */ + +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "stat2" + +extern u64 cal_idle_sum_exec_runtime(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cal_idle_sum_exec_runtime(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 32 + 32 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..25218a8f822f 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -19,6 +19,8 @@ */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); +extern struct static_key_true proc_idle; + static int sched_clock_irqtime; void enable_sched_clock_irqtime(void) @@ -1078,3 +1080,35 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cal_idle_sum_exec_runtime(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + if (!static_branch_likely(&proc_idle)) + return 0ULL; + + if (rq->curr == rq->idle) { + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return idle; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle += delta_exec; + } + + return idle; +} + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..3714a1c0d57b 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -10,6 +10,8 @@ #include <trace/events/power.h> +DEFINE_STATIC_KEY_TRUE(proc_idle); + /* Linker adds these: start and end of __cpuidle functions */ extern char __cpuidle_text_start[], __cpuidle_text_end[]; @@ -424,8 +426,35 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + if (!static_branch_likely(&proc_idle)) + return; + + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } +#ifdef CONFIG_PROC_IDLE +static int __init init_proc_idle(char *str) +{ + if (!strcmp(str, "false")) + static_branch_disable(&proc_idle); + + return 1; +} +__setup("proc_idle=", init_proc_idle); +#endif static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); @@ -436,6 +465,15 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + if (static_branch_likely(&proc_idle)) { + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; + } +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

1 0

[PATCH openEuler-21.09 0/2] Improve the precisoin of accounuting CPU utilization rate
by Hongyu Li 13 Oct '21

13 Oct '21

The current way of calculating the CPU utilization rate is not accurate. The accounting system only works In the interval of two ticks. However, a process can give up the CPU before the tick ending. This can be fixed by counting the idel time via the scheduler. We can use the sum_exe_runtime of the idle process of each CPU to calculate the the CPU utilization rate. The idle time of each CPU is given in the /proc/stat2 file. An example of using this file is also attached. Hongyu Li (2): eulerfs: add the /proc/stat2 file tools: add a tool to calculate the CPU utilization rate fs/proc/Kconfig | 7 +++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 +++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++ kernel/sched/idle.c | 38 ++++++++++++++++ tools/accounting/Makefile | 2 +- tools/accounting/idle_cal.c | 91 +++++++++++++++++++++++++++++++++++++ 7 files changed, 263 insertions(+), 1 deletion(-) create mode 100644 fs/proc/stat2.c create mode 100644 tools/accounting/idle_cal.c -- 2.17.1

1 0

[PATCH openEuler-5.10 1/4] spraid: support Ramaxel raid controller
by Zheng Zengkai 13 Oct '21

13 Oct '21

From: Yanling Song <songyl(a)ramaxel.com> Ramaxel inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I494HF CVE: NA This initial commit contains Ramaxel's spraid module. The spraid controller has two modes: HBA mode and raid mode. Raid mode supports raid 0/1/5/6/10/50/60 mode. The spraid driver works under scsi sub system and transfers scsi commands to ramaxel raid chip. Signed-off-by: Yanling Song <songyl(a)ramaxel.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spraid/Kconfig | 11 + drivers/scsi/spraid/Makefile | 7 + drivers/scsi/spraid/spraid.h | 655 ++++++ drivers/scsi/spraid/spraid_main.c | 3616 +++++++++++++++++++++++++++++ 6 files changed, 4291 insertions(+) create mode 100644 drivers/scsi/spraid/Kconfig create mode 100644 drivers/scsi/spraid/Makefile create mode 100644 drivers/scsi/spraid/spraid.h create mode 100644 drivers/scsi/spraid/spraid_main.c diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 871f8ea7b928..0fbe4edeccd0 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -484,6 +484,7 @@ source "drivers/scsi/megaraid/Kconfig.megaraid" source "drivers/scsi/mpt3sas/Kconfig" source "drivers/scsi/smartpqi/Kconfig" source "drivers/scsi/ufs/Kconfig" +source "drivers/scsi/spraid/Kconfig" config SCSI_HPTIOP tristate "HighPoint RocketRAID 3xxx/4xxx Controller support" diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index ce61ba07fadd..78a3c832394c 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -97,6 +97,7 @@ obj-$(CONFIG_SCSI_ZALON) += zalon7xx.o obj-$(CONFIG_SCSI_DC395x) += dc395x.o obj-$(CONFIG_SCSI_AM53C974) += esp_scsi.o am53c974.o obj-$(CONFIG_CXLFLASH) += cxlflash/ +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid/ obj-$(CONFIG_MEGARAID_LEGACY) += megaraid.o obj-$(CONFIG_MEGARAID_NEWGEN) += megaraid/ obj-$(CONFIG_MEGARAID_SAS) += megaraid/ diff --git a/drivers/scsi/spraid/Kconfig b/drivers/scsi/spraid/Kconfig new file mode 100644 index 000000000000..83962efaab07 --- /dev/null +++ b/drivers/scsi/spraid/Kconfig @@ -0,0 +1,11 @@ +# +# Ramaxel driver configuration +# + +config RAMAXEL_SPRAID + tristate "Ramaxel spraid Adapter" + depends on PCI && SCSI + depends on ARM64 || X86_64 + default m + help + This driver supports Ramaxel spraid driver. diff --git a/drivers/scsi/spraid/Makefile b/drivers/scsi/spraid/Makefile new file mode 100644 index 000000000000..aadc2ffd37eb --- /dev/null +++ b/drivers/scsi/spraid/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the Ramaxel device drivers. +# + +obj-$(CONFIG_RAMAXEL_SPRAID) += spraid.o + +spraid-objs := spraid_main.o \ No newline at end of file diff --git a/drivers/scsi/spraid/spraid.h b/drivers/scsi/spraid/spraid.h new file mode 100644 index 000000000000..da46d8e1b4b6 --- /dev/null +++ b/drivers/scsi/spraid/spraid.h @@ -0,0 +1,655 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SPRAID_H_ +#define __SPRAID_H_ + +#define SPRAID_CAP_MQES(cap) ((cap) & 0xffff) +#define SPRAID_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define SPRAID_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) +#define SPRAID_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define SPRAID_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) +#define SPRAID_CAP_DMAMASK(cap) (((cap) >> 37) & 0xff) + +#define SPRAID_DEFAULT_MAX_CHANNEL 4 +#define SPRAID_DEFAULT_MAX_ID 240 +#define SPRAID_DEFAULT_MAX_LUN_PER_HOST 8 +#define MAX_SECTORS 2048 + +#define IO_SQE_SIZE sizeof(struct spraid_ioq_command) +#define ADMIN_SQE_SIZE sizeof(struct spraid_admin_command) +#define SQE_SIZE(qid) (((qid) > 0) ? IO_SQE_SIZE : ADMIN_SQE_SIZE) +#define CQ_SIZE(depth) ((depth) * sizeof(struct spraid_completion)) +#define SQ_SIZE(qid, depth) ((depth) * SQE_SIZE(qid)) + +#define SENSE_SIZE(depth) ((depth) * SCSI_SENSE_BUFFERSIZE) + +#define SPRAID_AQ_DEPTH 128 +#define SPRAID_NR_AEN_COMMANDS 1 +#define SPRAID_AQ_BLK_MQ_DEPTH (SPRAID_AQ_DEPTH - SPRAID_NR_AEN_COMMANDS) +#define SPRAID_AQ_MQ_TAG_DEPTH (SPRAID_AQ_BLK_MQ_DEPTH - 1) + +#define SPRAID_ADMIN_QUEUE_NUM 1 +#define SPRAID_PTCMDS_PERQ 1 +#define SPRAID_IO_BLK_MQ_DEPTH (hdev->shost->can_queue) +#define SPRAID_NR_IOQ_PTCMDS (SPRAID_PTCMDS_PERQ * hdev->shost->nr_hw_queues) + +#define FUA_MASK 0x08 +#define SPRAID_MINORS BIT(MINORBITS) + +#define COMMAND_IS_WRITE(cmd) ((cmd)->common.opcode & 1) + +#define SPRAID_IO_IOSQES 7 +#define SPRAID_IO_IOCQES 4 +#define PRP_ENTRY_SIZE 8 + +#define SMALL_POOL_SIZE 256 +#define MAX_SMALL_POOL_NUM 16 +#define MAX_CMD_PER_DEV 32 +#define MAX_CDB_LEN 32 + +#define SPRAID_UP_TO_MULTY4(x) (((x) + 4) & (~0x03)) + +#define CQE_STATUS_SUCCESS (0x0) + +#define PCI_VENDOR_ID_RAMAXEL_LOGIC 0x1E81 + +#define SPRAID_SERVER_DEVICE_HAB_DID 0x2100 +#define SPRAID_SERVER_DEVICE_RAID_DID 0x2200 + +#define IO_6_DEFAULT_TX_LEN 256 + +#define SPRAID_INT_PAGES 2 +#define SPRAID_INT_BYTES(hdev) (SPRAID_INT_PAGES * (hdev)->page_size) + +enum { + SPRAID_REQ_CANCELLED = (1 << 0), + SPRAID_REQ_USERCMD = (1 << 1), +}; + +enum { + SPRAID_SC_SUCCESS = 0x0, + SPRAID_SC_INVALID_OPCODE = 0x1, + SPRAID_SC_INVALID_FIELD = 0x2, + + SPRAID_SC_ABORT_LIMIT = 0x103, + SPRAID_SC_ABORT_MISSING = 0x104, + SPRAID_SC_ASYNC_LIMIT = 0x105, + + SPRAID_SC_DNR = 0x4000, +}; + +enum { + SPRAID_REG_CAP = 0x0000, + SPRAID_REG_CC = 0x0014, + SPRAID_REG_CSTS = 0x001c, + SPRAID_REG_AQA = 0x0024, + SPRAID_REG_ASQ = 0x0028, + SPRAID_REG_ACQ = 0x0030, + SPRAID_REG_DBS = 0x1000, +}; + +enum { + SPRAID_CC_ENABLE = 1 << 0, + SPRAID_CC_CSS_NVM = 0 << 4, + SPRAID_CC_MPS_SHIFT = 7, + SPRAID_CC_AMS_SHIFT = 11, + SPRAID_CC_SHN_SHIFT = 14, + SPRAID_CC_IOSQES_SHIFT = 16, + SPRAID_CC_IOCQES_SHIFT = 20, + SPRAID_CC_AMS_RR = 0 << SPRAID_CC_AMS_SHIFT, + SPRAID_CC_SHN_NONE = 0 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_IOSQES = SPRAID_IO_IOSQES << SPRAID_CC_IOSQES_SHIFT, + SPRAID_CC_IOCQES = SPRAID_IO_IOCQES << SPRAID_CC_IOCQES_SHIFT, + SPRAID_CC_SHN_NORMAL = 1 << SPRAID_CC_SHN_SHIFT, + SPRAID_CC_SHN_MASK = 3 << SPRAID_CC_SHN_SHIFT, + SPRAID_CSTS_CFS_SHIFT = 1, + SPRAID_CSTS_SHST_SHIFT = 2, + SPRAID_CSTS_PP_SHIFT = 5, + SPRAID_CSTS_RDY = 1 << 0, + SPRAID_CSTS_SHST_CMPLT = 2 << 2, + SPRAID_CSTS_SHST_MASK = 3 << 2, + SPRAID_CSTS_CFS_MASK = 1 << SPRAID_CSTS_CFS_SHIFT, + SPRAID_CSTS_PP_MASK = 1 << SPRAID_CSTS_PP_SHIFT, +}; + +enum { + SPRAID_ADMIN_DELETE_SQ = 0x00, + SPRAID_ADMIN_CREATE_SQ = 0x01, + SPRAID_ADMIN_DELETE_CQ = 0x04, + SPRAID_ADMIN_CREATE_CQ = 0x05, + SPRAID_ADMIN_ABORT_CMD = 0x08, + SPRAID_ADMIN_SET_FEATURES = 0x09, + SPRAID_ADMIN_ASYNC_EVENT = 0x0c, + SPRAID_ADMIN_GET_INFO = 0xc6, + SPRAID_ADMIN_RESET = 0xc8, +}; + +enum { + SPRAID_GET_INFO_CTRL = 0, + SPRAID_GET_INFO_DEV_LIST = 1, +}; + +enum { + SPRAID_RESET_TARGET = 0, + SPRAID_RESET_BUS = 1, +}; + +enum { + SPRAID_AEN_ERROR = 0, + SPRAID_AEN_NOTICE = 2, + SPRAID_AEN_VS = 7, +}; + +enum { + SPRAID_AEN_DEV_CHANGED = 0x00, + SPRAID_AEN_HOST_PROBING = 0x10, +}; + +enum { + SPRAID_AEN_TIMESYN = 0x07 +}; + +enum { + SPRAID_CMD_WRITE = 0x01, + SPRAID_CMD_READ = 0x02, + + SPRAID_CMD_NONIO_NONE = 0x80, + SPRAID_CMD_NONIO_TODEV = 0x81, + SPRAID_CMD_NONIO_FROMDEV = 0x82, +}; + +enum { + SPRAID_QUEUE_PHYS_CONTIG = (1 << 0), + SPRAID_CQ_IRQ_ENABLED = (1 << 1), + + SPRAID_FEAT_NUM_QUEUES = 0x07, + SPRAID_FEAT_ASYNC_EVENT = 0x0b, + SPRAID_FEAT_TIMESTAMP = 0x0e, +}; + +enum spraid_state { + SPRAID_NEW, + SPRAID_LIVE, + SPRAID_RESETTING, + SPRAID_DELETING, + SPRAID_DEAD, +}; + +struct spraid_completion { + __le32 result; + union { + struct { + __u8 sense_len; + __u8 resv[3]; + }; + __le32 result1; + }; + __le16 sq_head; + __le16 sq_id; + __u16 cmd_id; + __le16 status; +}; + +struct spraid_ctrl_info { + __le32 nd; + __le16 max_cmds; + __le16 max_channel; + __le32 max_tgt_id; + __le16 max_lun; + __le16 max_num_sge; + __le16 lun_num_in_boot; + __u8 mdts; + __u8 acl; + __u8 aerl; + __u8 card_type; + __u16 rsvd; + __u32 rtd3e; + __u8 sn[32]; + __u8 fr[16]; + __u8 rsvd1[4020]; +}; + +struct spraid_dev { + struct pci_dev *pdev; + struct device *dev; + struct Scsi_Host *shost; + struct spraid_queue *queues; + struct dma_pool *prp_page_pool; + struct dma_pool *prp_small_pool[MAX_SMALL_POOL_NUM]; + mempool_t *iod_mempool; + struct blk_mq_tag_set admin_tagset; + struct request_queue *admin_q; + void __iomem *bar; + u32 max_qid; + u32 num_vecs; + u32 queue_count; + u32 ioq_depth; + int db_stride; + u32 __iomem *dbs; + struct rw_semaphore devices_rwsem; + int numa_node; + u32 page_size; + u32 ctrl_config; + u32 online_queues; + u64 cap; + struct device ctrl_device; + struct cdev cdev; + int instance; + struct spraid_ctrl_info *ctrl_info; + struct spraid_dev_info *devices; + + struct spraid_ioq_ptcmd *ioq_ptcmds; + struct list_head ioq_pt_list; + spinlock_t ioq_pt_lock; + + struct work_struct aen_work; + struct work_struct scan_work; + struct work_struct timesyn_work; + struct work_struct reset_work; + + enum spraid_state state; + spinlock_t state_lock; +}; + +struct spraid_sgl_desc { + __le64 addr; + __le32 length; + __u8 rsvd[3]; + __u8 type; +}; + +union spraid_data_ptr { + struct { + __le64 prp1; + __le64 prp2; + }; + struct spraid_sgl_desc sgl; +}; + +struct spraid_admin_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le32 cdw2[4]; + union spraid_data_ptr dptr; + __le32 cdw10; + __le32 cdw11; + __le32 cdw12; + __le32 cdw13; + __le32 cdw14; + __le32 cdw15; +}; + +struct spraid_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[2]; + union spraid_data_ptr dptr; + __le32 fid; + __le32 dword11; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct spraid_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct spraid_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct spraid_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct spraid_get_info { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u32 rsvd2[4]; + union spraid_data_ptr dptr; + __u8 type; + __u8 rsvd10[3]; + __le32 cdw11; + __u32 rsvd12[4]; +}; + +enum { + SPRAID_CMD_FLAG_SGL_METABUF = (1 << 6), + SPRAID_CMD_FLAG_SGL_METASEG = (1 << 7), + SPRAID_CMD_FLAG_SGL_ALL = SPRAID_CMD_FLAG_SGL_METABUF | SPRAID_CMD_FLAG_SGL_METASEG, +}; + +enum spraid_cmd_state { + SPRAID_CMD_IDLE = 0, + SPRAID_CMD_IN_FLIGHT = 1, + SPRAID_CMD_COMPLETE = 2, + SPRAID_CMD_TIMEOUT = 3, + SPRAID_CMD_TMO_COMPLETE = 4, +}; + +struct spraid_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __le16 sqid; + __le16 cid; + __u32 rsvd11[5]; +}; + +struct spraid_reset_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __u64 rsvd2[4]; + __u8 type; + __u8 rsvd10[3]; + __u32 rsvd11[5]; +}; + +struct spraid_admin_command { + union { + struct spraid_admin_common_command common; + struct spraid_features features; + struct spraid_create_cq create_cq; + struct spraid_create_sq create_sq; + struct spraid_delete_queue delete_queue; + struct spraid_get_info get_info; + struct spraid_abort_cmd abort; + struct spraid_reset_cmd reset; + }; +}; + +struct spraid_ioq_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __le32 cdw3[3]; + union spraid_data_ptr dptr; + __le32 cdw10[6]; + __u8 cdb[32]; + __le64 sense_addr; + __le32 cdw26[6]; +}; + +struct spraid_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_len; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __le64 slba; + __le16 nlb; + __le16 control; + __u32 rsvd13[3]; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_scsi_nonio { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 hdid; + __le16 sense_len; + __u8 cdb_length; + __u8 rsvd2; + __u32 rsvd3[3]; + union spraid_data_ptr dptr; + __u32 rsvd10[5]; + __le32 buffer_len; + __u8 cdb[32]; + __le64 sense_addr; + __u32 rsvd26[6]; +}; + +struct spraid_ioq_command { + union { + struct spraid_ioq_common_command common; + struct spraid_rw_command rw; + struct spraid_scsi_nonio scsi_nonio; + }; +}; + +#define SPRAID_IOCTL_RESET_CMD _IOWR('N', 0x80, struct spraid_passthru_common_cmd) +#define SPRAID_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct spraid_passthru_common_cmd) + +struct spraid_passthru_common_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 data_len; + __u16 param_len; + } info_1; + __u32 cdw3; + }; + __u64 metadata; + + __u64 addr; + __u64 prp2; + + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +#define SPRAID_IOCTL_IOQ_CMD _IOWR('N', 0x42, struct spraid_ioq_passthru_cmd) + +struct spraid_ioq_passthru_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd0; + __u32 nsid; + union { + struct { + __u16 res_sense_len; + __u8 cdb_len; + __u8 rsvd0; + } info_0; + __u32 cdw2; + }; + union { + struct { + __u16 subopcode; + __u16 rsvd1; + } info_1; + __u32 cdw3; + }; + union { + struct { + __u16 rsvd; + __u16 param_len; + } info_2; + __u32 cdw4; + }; + __u32 cdw5; + __u64 addr; + __u64 prp2; + union { + struct { + __u16 eid; + __u16 sid; + } info_3; + __u32 cdw10; + }; + union { + struct { + __u16 did; + __u8 did_flag; + __u8 rsvd2; + } info_4; + __u32 cdw11; + }; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 data_len; + __u32 cdw16; + __u32 cdw17; + __u32 cdw18; + __u32 cdw19; + __u32 cdw20; + __u32 cdw21; + __u32 cdw22; + __u32 cdw23; + __u64 sense_addr; + __u32 cdw26[4]; + __u32 timeout_ms; + __u32 result0; + __u32 result1; +}; + +struct spraid_ioq_ptcmd { + int qid; + int cid; + u32 result0; + u32 result1; + u16 status; + void *priv; + enum spraid_cmd_state state; + struct completion cmd_done; + struct list_head list; +}; + +struct spraid_admin_request { + struct spraid_admin_command *cmd; + u32 result0; + u32 result1; + u16 flags; + u16 status; +}; + +struct spraid_queue { + struct spraid_dev *hdev; + spinlock_t sq_lock; /* spinlock for lock handling */ + + spinlock_t cq_lock ____cacheline_aligned_in_smp; /* spinlock for lock handling */ + + void *sq_cmds; + + struct spraid_completion *cqes; + + dma_addr_t sq_dma_addr; + dma_addr_t cq_dma_addr; + u32 __iomem *q_db; + u8 cq_phase; + u8 sqes; + u16 qid; + u16 sq_tail; + u16 cq_head; + u16 last_cq_head; + u16 q_depth; + s16 cq_vector; + void *sense; + dma_addr_t sense_dma_addr; + struct dma_pool *prp_small_pool; +}; + +struct spraid_iod { + struct spraid_admin_request req; + struct spraid_queue *spraidq; + enum spraid_cmd_state state; + int npages; + u32 nsge; + u32 length; + bool use_sgl; + bool sg_drv_mgmt; + dma_addr_t first_dma; + void *sense; + dma_addr_t sense_dma; + struct scatterlist *sg; + struct scatterlist inline_sg[0]; +}; + +#define SPRAID_DEV_INFO_ATTR_BOOT(attr) ((attr) & 0x01) +#define SPRAID_DEV_INFO_ATTR_HDD(attr) ((attr) & 0x02) +#define SPRAID_DEV_INFO_ATTR_PT(attr) (((attr) & 0x22) == 0x02) +#define SPRAID_DEV_INFO_ATTR_RAWDISK(attr) ((attr) & 0x20) + +#define SPRAID_DEV_INFO_FLAG_VALID(flag) ((flag) & 0x01) +#define SPRAID_DEV_INFO_FLAG_CHANGE(flag) ((flag) & 0x02) + +struct spraid_dev_info { + __le32 hdid; + __le16 target; + __u8 channel; + __u8 lun; + __u8 attr; + __u8 flag; + __le16 max_io_kb; +}; + +#define MAX_DEV_ENTRY_PER_PAGE_4K 340 +struct spraid_dev_list { + __le32 dev_num; + __u32 rsvd0[3]; + struct spraid_dev_info devices[MAX_DEV_ENTRY_PER_PAGE_4K]; +}; + +struct spraid_sdev_hostdata { + u32 hdid; +}; + +#endif + diff --git a/drivers/scsi/spraid/spraid_main.c b/drivers/scsi/spraid/spraid_main.c new file mode 100644 index 000000000000..a0a75ecb0027 --- /dev/null +++ b/drivers/scsi/spraid/spraid_main.c @@ -0,0 +1,3616 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Linux spraid device driver + * Copyright(c) 2021 Ramaxel Memory Technology, Ltd + */ +#define pr_fmt(fmt) "spraid: " fmt + +#include <linux/sched/signal.h> +#include <linux/version.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/module.h> +#include <linux/ioport.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/cdev.h> +#include <linux/sysfs.h> +#include <linux/gfp.h> +#include <linux/types.h> +#include <linux/ratelimit.h> +#include <linux/once.h> +#include <linux/debugfs.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/blkdev.h> + +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_device.h> +#include <scsi/scsi_host.h> +#include <scsi/scsi_transport.h> +#include <scsi/scsi_dbg.h> + +#include "spraid.h" + +static u32 admin_tmout = 60; +module_param(admin_tmout, uint, 0644); +MODULE_PARM_DESC(admin_tmout, "admin commands timeout (seconds)"); + +static u32 scmd_tmout_pt = 30; +module_param(scmd_tmout_pt, uint, 0644); +MODULE_PARM_DESC(scmd_tmout_pt, "scsi commands timeout for passthrough(seconds)"); + +static u32 scmd_tmout_nonpt = 180; +module_param(scmd_tmout_nonpt, uint, 0644); +MODULE_PARM_DESC(scmd_tmout_nonpt, "scsi commands timeout for rawdisk&raid(seconds)"); + +static u32 wait_abl_tmout = 3; +module_param(wait_abl_tmout, uint, 0644); +MODULE_PARM_DESC(wait_abl_tmout, "wait abnormal io timeout(seconds)"); + +static bool use_sgl_force; +module_param(use_sgl_force, bool, 0644); +MODULE_PARM_DESC(use_sgl_force, "force IO use sgl format, default false"); + +static int ioq_depth_set(const char *val, const struct kernel_param *kp); +static const struct kernel_param_ops ioq_depth_ops = { + .set = ioq_depth_set, + .get = param_get_uint, +}; + +static u32 io_queue_depth = 1024; +module_param_cb(io_queue_depth, &ioq_depth_ops, &io_queue_depth, 0644); +MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2"); + +static int log_debug_switch_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + + return param_set_byte(val, kp); +} + +static const struct kernel_param_ops log_debug_switch_ops = { + .set = log_debug_switch_set, + .get = param_get_byte, +}; + +static unsigned char log_debug_switch; +module_param_cb(log_debug_switch, &log_debug_switch_ops, &log_debug_switch, 0644); +MODULE_PARM_DESC(log_debug_switch, "set log state, default non-zero for switch on"); + +static int small_pool_num_set(const char *val, const struct kernel_param *kp) +{ + u8 n = 0; + int ret; + + ret = kstrtou8(val, 10, &n); + if (ret != 0) + return -EINVAL; + if (n > MAX_SMALL_POOL_NUM) + n = MAX_SMALL_POOL_NUM; + if (n < 1) + n = 1; + *((u8 *)kp->arg) = n; + + return 0; +} + +static const struct kernel_param_ops small_pool_num_ops = { + .set = small_pool_num_set, + .get = param_get_byte, +}; + +static unsigned char small_pool_num = 4; +module_param_cb(small_pool_num, &small_pool_num_ops, &small_pool_num, 0644); +MODULE_PARM_DESC(small_pool_num, "set prp small pool num, default 4, MAX 16"); + +static void spraid_free_queue(struct spraid_queue *spraidq); +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result); +static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result); + +static DEFINE_IDA(spraid_instance_ida); +static dev_t spraid_chr_devt; +static struct class *spraid_class; + +#define SPRAID_CAP_TIMEOUT_UNIT_MS (HZ / 2) + +static struct workqueue_struct *spraid_wq; + +#define dev_log_dbg(dev, fmt, ...) do { \ + if (unlikely(log_debug_switch)) \ + dev_info(dev, "[%s] [%d] " fmt, \ + __func__, __LINE__, ##__VA_ARGS__); \ +} while (0) + +#define SPRAID_DRV_VERSION "1.0.0.0" + +#define ADMIN_TIMEOUT (admin_tmout * HZ) +#define ADMIN_ERR_TIMEOUT 32757 + +#define SPRAID_WAIT_ABNL_CMD_TIMEOUT (wait_abl_tmout * 2) + +#define SPRAID_DMA_MSK_BIT_MAX 64 + +enum FW_STAT_CODE { + FW_STAT_OK = 0, + FW_STAT_NEED_CHECK, + FW_STAT_ERROR, + FW_STAT_EP_PCIE_ERROR, + FW_STAT_NAC_DMA_ERROR, + FW_STAT_ABORTED, + FW_STAT_NEED_RETRY +}; + +static int ioq_depth_set(const char *val, const struct kernel_param *kp) +{ + int n = 0; + int ret; + + ret = kstrtoint(val, 10, &n); + if (ret != 0 || n < 2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static int spraid_remap_bar(struct spraid_dev *hdev, u32 size) +{ + struct pci_dev *pdev = hdev->pdev; + + if (size > pci_resource_len(pdev, 0)) { + dev_err(hdev->dev, "Input size[%u] exceed bar0 length[%llu]\n", + size, pci_resource_len(pdev, 0)); + return -ENOMEM; + } + + if (hdev->bar) + iounmap(hdev->bar); + + hdev->bar = ioremap(pci_resource_start(pdev, 0), size); + if (!hdev->bar) { + dev_err(hdev->dev, "ioremap for bar0 failed\n"); + return -ENOMEM; + } + hdev->dbs = hdev->bar + SPRAID_REG_DBS; + + return 0; +} + +static int spraid_dev_map(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret; + + ret = pci_request_mem_regions(pdev, "spraid"); + if (ret) { + dev_err(hdev->dev, "fail to request memory regions\n"); + return ret; + } + + ret = spraid_remap_bar(hdev, SPRAID_REG_DBS + 4096); + if (ret) { + pci_release_mem_regions(pdev); + return ret; + } + + return 0; +} + +static void spraid_dev_unmap(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + + if (hdev->bar) { + iounmap(hdev->bar); + hdev->bar = NULL; + } + pci_release_mem_regions(pdev); +} + +static int spraid_pci_enable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret = -ENOMEM; + u64 maskbit = SPRAID_DMA_MSK_BIT_MAX; + + if (pci_enable_device_mem(pdev)) { + dev_err(hdev->dev, "Enable pci device memory resources failed\n"); + return ret; + } + pci_set_master(pdev); + + if (readl(hdev->bar + SPRAID_REG_CSTS) == U32_MAX) { + ret = -ENODEV; + dev_err(hdev->dev, "Read csts register failed\n"); + goto disable; + } + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err(hdev->dev, "Allocate one IRQ for setup admin channel failed\n"); + goto disable; + } + + hdev->cap = lo_hi_readq(hdev->bar + SPRAID_REG_CAP); + hdev->ioq_depth = min_t(u32, SPRAID_CAP_MQES(hdev->cap) + 1, io_queue_depth); + hdev->db_stride = 1 << SPRAID_CAP_STRIDE(hdev->cap); + + maskbit = SPRAID_CAP_DMAMASK(hdev->cap); + if (maskbit < 32 || maskbit > SPRAID_DMA_MSK_BIT_MAX) { + dev_err(hdev->dev, "err, dma mask invalid[%llu], set to default\n", maskbit); + maskbit = SPRAID_DMA_MSK_BIT_MAX; + } + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(maskbit))) { + dev_err(hdev->dev, "set dma mask and coherent failed\n"); + goto disable; + } + + dev_info(hdev->dev, "set dma mask[%llu] success\n", maskbit); + + pci_enable_pcie_error_reporting(pdev); + pci_save_state(pdev); + + return 0; + +disable: + pci_disable_device(pdev); + return ret; +} + +static inline +struct spraid_admin_request *spraid_admin_req(struct request *req) +{ + return blk_mq_rq_to_pdu(req); +} + +static int spraid_npages_prp(u32 size, struct spraid_dev *hdev) +{ + u32 nprps = DIV_ROUND_UP(size + hdev->page_size, hdev->page_size); + + return DIV_ROUND_UP(PRP_ENTRY_SIZE * nprps, PAGE_SIZE - PRP_ENTRY_SIZE); +} + +static int spraid_npages_sgl(u32 nseg) +{ + return DIV_ROUND_UP(nseg * sizeof(struct spraid_sgl_desc), PAGE_SIZE); +} + +static void **spraid_iod_list(struct spraid_iod *iod) +{ + return (void **)(iod->inline_sg + (iod->sg_drv_mgmt ? iod->nsge : 0)); +} + +static u32 spraid_iod_ext_size(struct spraid_dev *hdev, u32 size, u32 nsge, + bool sg_drv_mgmt, bool use_sgl) +{ + size_t alloc_size, sg_size; + + if (use_sgl) + alloc_size = sizeof(__le64 *) * spraid_npages_sgl(nsge); + else + alloc_size = sizeof(__le64 *) * spraid_npages_prp(size, hdev); + + sg_size = sg_drv_mgmt ? (sizeof(struct scatterlist) * nsge) : 0; + return sg_size + alloc_size; +} + +static u32 spraid_cmd_size(struct spraid_dev *hdev, bool sg_drv_mgmt, bool use_sgl) +{ + u32 alloc_size = spraid_iod_ext_size(hdev, SPRAID_INT_BYTES(hdev), + SPRAID_INT_PAGES, sg_drv_mgmt, use_sgl); + + dev_info(hdev->dev, "sg_drv_mgmt: %s, use_sgl: %s, iod size: %lu, alloc_size: %u\n", + sg_drv_mgmt ? "true" : "false", use_sgl ? "true" : "false", + sizeof(struct spraid_iod), alloc_size); + + return sizeof(struct spraid_iod) + alloc_size; +} + +static int spraid_setup_prps(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + struct scatterlist *sg = iod->sg; + u64 dma_addr = sg_dma_address(sg); + int dma_len = sg_dma_len(sg); + __le64 *prp_list, *old_prp_list; + u32 page_size = hdev->page_size; + int offset = dma_addr & (page_size - 1); + void **list = spraid_iod_list(iod); + int length = iod->length; + struct dma_pool *pool; + dma_addr_t prp_dma; + int nprps, i; + + length -= (page_size - offset); + if (length <= 0) { + iod->first_dma = 0; + return 0; + } + + dma_len -= (page_size - offset); + if (dma_len) { + dma_addr += (page_size - offset); + } else { + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + if (length <= page_size) { + iod->first_dma = dma_addr; + return 0; + } + + nprps = DIV_ROUND_UP(length, page_size); + if (nprps <= (SMALL_POOL_SIZE / PRP_ENTRY_SIZE)) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, "Allocate first prp_list memory failed\n"); + iod->first_dma = dma_addr; + iod->npages = -1; + return -ENOMEM; + } + list[0] = prp_list; + iod->first_dma = prp_dma; + i = 0; + for (;;) { + if (i == page_size / PRP_ENTRY_SIZE) { + old_prp_list = prp_list; + + prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + if (!prp_list) { + dev_err_ratelimited(hdev->dev, "Allocate %dth prp_list memory failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = prp_list; + prp_list[0] = old_prp_list[i - 1]; + old_prp_list[i - 1] = cpu_to_le64(prp_dma); + i = 1; + } + prp_list[i++] = cpu_to_le64(dma_addr); + dma_len -= page_size; + dma_addr += page_size; + length -= page_size; + if (length <= 0) + break; + if (dma_len > 0) + continue; + if (unlikely(dma_len < 0)) + goto bad_sgl; + sg = sg_next(sg); + dma_addr = sg_dma_address(sg); + dma_len = sg_dma_len(sg); + } + + return 0; + +bad_sgl: + dev_err(hdev->dev, "Setup prps, invalid SGL for payload: %d nents: %d\n", + iod->length, iod->nsge); + return -EIO; +} + +#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct spraid_sgl_desc)) + +static void spraid_submit_cmd(struct spraid_queue *spraidq, const void *cmd) +{ + u32 sqes = SQE_SIZE(spraidq->qid); + unsigned long flags; + struct spraid_admin_common_command *acd = (struct spraid_admin_common_command *)cmd; + + spin_lock_irqsave(&spraidq->sq_lock, flags); + memcpy((spraidq->sq_cmds + sqes * spraidq->sq_tail), cmd, sqes); + if (++spraidq->sq_tail == spraidq->q_depth) + spraidq->sq_tail = 0; + + writel(spraidq->sq_tail, spraidq->q_db); + spin_unlock_irqrestore(&spraidq->sq_lock, flags); + + dev_log_dbg(spraidq->hdev->dev, "cid[%d], qid[%d], opcode[0x%x], flags[0x%x], hdid[%u]\n", + acd->command_id, spraidq->qid, acd->opcode, acd->flags, le32_to_cpu(acd->hdid)); +} + +static u32 spraid_mod64(u64 dividend, u32 divisor) +{ + u64 d; + u32 remainder; + + if (!divisor) + pr_err("DIVISOR is zero, in div fn\n"); + + d = dividend; + remainder = do_div(d, divisor); + return remainder; +} + +static inline bool spraid_is_rw_scmd(struct scsi_cmnd *scmd) +{ + switch (scmd->cmnd[0]) { + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case READ_32: + case WRITE_6: + case WRITE_10: + case WRITE_12: + case WRITE_16: + case WRITE_32: + return true; + default: + return false; + } +} + +static bool spraid_is_prp(struct spraid_dev *hdev, struct scsi_cmnd *scmd, u32 nsge) +{ + struct scatterlist *sg = scsi_sglist(scmd); + u32 page_size = hdev->page_size; + bool is_prp = true; + int i = 0; + + scsi_for_each_sg(scmd, sg, nsge, i) { + if (i != 0 && i != nsge - 1) { + if (spraid_mod64(sg_dma_len(sg), page_size) || + spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == 0) { + if ((spraid_mod64((sg_dma_address(sg) + sg_dma_len(sg)), page_size))) { + is_prp = false; + break; + } + } + + if (nsge > 1 && i == (nsge - 1)) { + if (spraid_mod64(sg_dma_address(sg), page_size)) { + is_prp = false; + break; + } + } + } + + return is_prp; +} + +enum { + SPRAID_SGL_FMT_DATA_DESC = 0x00, + SPRAID_SGL_FMT_SEG_DESC = 0x02, + SPRAID_SGL_FMT_LAST_SEG_DESC = 0x03, + SPRAID_KEY_SGL_FMT_DATA_DESC = 0x04, + SPRAID_TRANSPORT_SGL_DATA_DESC = 0x05 +}; + +static void spraid_sgl_set_data(struct spraid_sgl_desc *sge, struct scatterlist *sg) +{ + sge->addr = cpu_to_le64(sg_dma_address(sg)); + sge->length = cpu_to_le32(sg_dma_len(sg)); + sge->type = SPRAID_SGL_FMT_DATA_DESC << 4; +} + +static void spraid_sgl_set_seg(struct spraid_sgl_desc *sge, dma_addr_t dma_addr, int entries) +{ + sge->addr = cpu_to_le64(dma_addr); + if (entries <= SGES_PER_PAGE) { + sge->length = cpu_to_le32(entries * sizeof(*sge)); + sge->type = SPRAID_SGL_FMT_LAST_SEG_DESC << 4; + } else { + sge->length = cpu_to_le32(PAGE_SIZE); + sge->type = SPRAID_SGL_FMT_SEG_DESC << 4; + } +} + +static int spraid_setup_ioq_cmd_sgl(struct spraid_dev *hdev, + struct scsi_cmnd *scmd, struct spraid_ioq_command *ioq_cmd, + struct spraid_iod *iod) +{ + struct spraid_sgl_desc *sg_list, *link, *old_sg_list; + struct scatterlist *sg = scsi_sglist(scmd); + void **list = spraid_iod_list(iod); + struct dma_pool *pool; + int nsge = iod->nsge; + dma_addr_t sgl_dma; + int i = 0; + + ioq_cmd->common.flags |= SPRAID_CMD_FLAG_SGL_METABUF; + + if (nsge == 1) { + spraid_sgl_set_data(&ioq_cmd->common.dptr.sgl, sg); + return 0; + } + + if (nsge <= (SMALL_POOL_SIZE / sizeof(struct spraid_sgl_desc))) { + pool = iod->spraidq->prp_small_pool; + iod->npages = 0; + } else { + pool = hdev->prp_page_pool; + iod->npages = 1; + } + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, "Allocate first sgl_list failed\n"); + iod->npages = -1; + return -ENOMEM; + } + + list[0] = sg_list; + iod->first_dma = sgl_dma; + spraid_sgl_set_seg(&ioq_cmd->common.dptr.sgl, sgl_dma, nsge); + do { + if (i == SGES_PER_PAGE) { + old_sg_list = sg_list; + link = &old_sg_list[SGES_PER_PAGE - 1]; + + sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); + if (!sg_list) { + dev_err_ratelimited(hdev->dev, "Allocate %dth sgl_list failed\n", + iod->npages + 1); + return -ENOMEM; + } + list[iod->npages++] = sg_list; + + i = 0; + memcpy(&sg_list[i++], link, sizeof(*link)); + spraid_sgl_set_seg(link, sgl_dma, nsge); + } + + spraid_sgl_set_data(&sg_list[i++], sg); + sg = sg_next(sg); + } while (--nsge > 0); + + return 0; +} + +#define SPRAID_RW_FUA BIT(14) + +static void spraid_setup_rw_cmd(struct spraid_dev *hdev, + struct spraid_rw_command *rw, + struct scsi_cmnd *scmd) +{ + u32 start_lba_lo, start_lba_hi; + u32 datalength = 0; + u16 control = 0; + + start_lba_lo = 0; + start_lba_hi = 0; + + if (scmd->sc_data_direction == DMA_TO_DEVICE) { + rw->opcode = SPRAID_CMD_WRITE; + } else if (scmd->sc_data_direction == DMA_FROM_DEVICE) { + rw->opcode = SPRAID_CMD_READ; + } else { + dev_err(hdev->dev, "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } + + /* 6-byte READ(0x08) or WRITE(0x0A) cdb */ + if (scmd->cmd_len == 6) { + datalength = (u32)(scmd->cmnd[4] == 0 ? + IO_6_DEFAULT_TX_LEN : scmd->cmnd[4]); + start_lba_lo = ((u32)scmd->cmnd[1] << 16) | + ((u32)scmd->cmnd[2] << 8) | (u32)scmd->cmnd[3]; + + start_lba_lo &= 0x1FFFFF; + } + + /* 10-byte READ(0x28) or WRITE(0x2A) cdb */ + else if (scmd->cmd_len == 10) { + datalength = (u32)scmd->cmnd[8] | ((u32)scmd->cmnd[7] << 8); + start_lba_lo = ((u32)scmd->cmnd[2] << 24) | + ((u32)scmd->cmnd[3] << 16) | + ((u32)scmd->cmnd[4] << 8) | (u32)scmd->cmnd[5]; + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + /* 12-byte READ(0xA8) or WRITE(0xAA) cdb */ + else if (scmd->cmd_len == 12) { + datalength = ((u32)scmd->cmnd[6] << 24) | + ((u32)scmd->cmnd[7] << 16) | + ((u32)scmd->cmnd[8] << 8) | (u32)scmd->cmnd[9]; + start_lba_lo = ((u32)scmd->cmnd[2] << 24) | + ((u32)scmd->cmnd[3] << 16) | + ((u32)scmd->cmnd[4] << 8) | (u32)scmd->cmnd[5]; + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 16-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 16) { + datalength = ((u32)scmd->cmnd[10] << 24) | + ((u32)scmd->cmnd[11] << 16) | + ((u32)scmd->cmnd[12] << 8) | (u32)scmd->cmnd[13]; + start_lba_lo = ((u32)scmd->cmnd[6] << 24) | + ((u32)scmd->cmnd[7] << 16) | + ((u32)scmd->cmnd[8] << 8) | (u32)scmd->cmnd[9]; + start_lba_hi = ((u32)scmd->cmnd[2] << 24) | + ((u32)scmd->cmnd[3] << 16) | + ((u32)scmd->cmnd[4] << 8) | (u32)scmd->cmnd[5]; + + if (scmd->cmnd[1] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + /* 32-byte READ(0x88) or WRITE(0x8A) cdb */ + else if (scmd->cmd_len == 32) { + datalength = ((u32)scmd->cmnd[28] << 24) | + ((u32)scmd->cmnd[29] << 16) | + ((u32)scmd->cmnd[30] << 8) | (u32)scmd->cmnd[31]; + start_lba_lo = ((u32)scmd->cmnd[16] << 24) | + ((u32)scmd->cmnd[17] << 16) | + ((u32)scmd->cmnd[18] << 8) | (u32)scmd->cmnd[19]; + start_lba_hi = ((u32)scmd->cmnd[12] << 24) | + ((u32)scmd->cmnd[13] << 16) | + ((u32)scmd->cmnd[14] << 8) | (u32)scmd->cmnd[15]; + + if (scmd->cmnd[10] & FUA_MASK) + control |= SPRAID_RW_FUA; + } + + if (unlikely(datalength > U16_MAX || datalength == 0)) { + dev_err(hdev->dev, "Invalid IO for illegal transfer data length: %u\n", + datalength); + WARN_ON(1); + } + + rw->slba = cpu_to_le64(((u64)start_lba_hi << 32) | start_lba_lo); + /* 0base for nlb */ + rw->nlb = cpu_to_le16((u16)(datalength - 1)); + rw->control = cpu_to_le16(control); +} + +static void spraid_setup_nonio_cmd(struct spraid_dev *hdev, + struct spraid_scsi_nonio *scsi_nonio, struct scsi_cmnd *scmd) +{ + scsi_nonio->buffer_len = cpu_to_le32(scsi_bufflen(scmd)); + + switch (scmd->sc_data_direction) { + case DMA_NONE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_NONE; + break; + case DMA_TO_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_TODEV; + break; + case DMA_FROM_DEVICE: + scsi_nonio->opcode = SPRAID_CMD_NONIO_FROMDEV; + break; + default: + dev_err(hdev->dev, "Invalid IO for unsupported data direction: %d\n", + scmd->sc_data_direction); + WARN_ON(1); + } +} + +static void spraid_setup_ioq_cmd(struct spraid_dev *hdev, + struct spraid_ioq_command *ioq_cmd, struct scsi_cmnd *scmd) +{ + memcpy(ioq_cmd->common.cdb, scmd->cmnd, scmd->cmd_len); + ioq_cmd->common.cdb_len = scmd->cmd_len; + + if (spraid_is_rw_scmd(scmd)) + spraid_setup_rw_cmd(hdev, &ioq_cmd->rw, scmd); + else + spraid_setup_nonio_cmd(hdev, &ioq_cmd->scsi_nonio, scmd); +} + +static int spraid_init_iod(struct spraid_dev *hdev, + struct spraid_iod *iod, struct spraid_ioq_command *ioq_cmd, + struct scsi_cmnd *scmd) +{ + if (unlikely(!iod->sense)) { + dev_err(hdev->dev, "Allocate sense data buffer failed\n"); + return -ENOMEM; + } + ioq_cmd->common.sense_addr = cpu_to_le64(iod->sense_dma); + ioq_cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + + iod->nsge = 0; + iod->npages = -1; + iod->use_sgl = 0; + iod->sg_drv_mgmt = false; + WRITE_ONCE(iod->state, SPRAID_CMD_IDLE); + + return 0; +} + +static void spraid_free_iod_res(struct spraid_dev *hdev, struct spraid_iod *iod) +{ + const int last_prp = hdev->page_size / sizeof(__le64) - 1; + dma_addr_t dma_addr, next_dma_addr; + struct spraid_sgl_desc *sg_list; + __le64 *prp_list; + void *addr; + int i; + + dma_addr = iod->first_dma; + if (iod->npages == 0) + dma_pool_free(iod->spraidq->prp_small_pool, spraid_iod_list(iod)[0], dma_addr); + + for (i = 0; i < iod->npages; i++) { + addr = spraid_iod_list(iod)[i]; + + if (iod->use_sgl) { + sg_list = addr; + next_dma_addr = + le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr); + } else { + prp_list = addr; + next_dma_addr = le64_to_cpu(prp_list[last_prp]); + } + + dma_pool_free(hdev->prp_page_pool, addr, dma_addr); + dma_addr = next_dma_addr; + } + + if (iod->sg_drv_mgmt && iod->sg != iod->inline_sg) { + iod->sg_drv_mgmt = false; + mempool_free(iod->sg, hdev->iod_mempool); + } + + iod->sense = NULL; + iod->npages = -1; +} + +static int spraid_io_map_data(struct spraid_dev *hdev, struct spraid_iod *iod, + struct scsi_cmnd *scmd, struct spraid_ioq_command *ioq_cmd) +{ + int ret; + + iod->nsge = scsi_dma_map(scmd); + + /* No data to DMA, it may be scsi no-rw command */ + if (unlikely(iod->nsge == 0)) + return 0; + + iod->length = scsi_bufflen(scmd); + iod->sg = scsi_sglist(scmd); + iod->use_sgl = !spraid_is_prp(hdev, scmd, iod->nsge); + + if (iod->use_sgl) { + ret = spraid_setup_ioq_cmd_sgl(hdev, scmd, ioq_cmd, iod); + } else { + ret = spraid_setup_prps(hdev, iod); + ioq_cmd->common.dptr.prp1 = + cpu_to_le64(sg_dma_address(iod->sg)); + ioq_cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + } + + if (ret) + scsi_dma_unmap(scmd); + + return ret; +} + +static void spraid_map_status(struct spraid_iod *iod, struct scsi_cmnd *scmd, + struct spraid_completion *cqe) +{ + scsi_set_resid(scmd, 0); + + switch ((le16_to_cpu(cqe->status) >> 1) & 0x7f) { + case FW_STAT_OK: + set_host_byte(scmd, DID_OK); + break; + case FW_STAT_NEED_CHECK: + set_host_byte(scmd, DID_OK); + scmd->result |= le16_to_cpu(cqe->status) >> 8; + if (scmd->result & SAM_STAT_CHECK_CONDITION) { + memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); + memcpy(scmd->sense_buffer, iod->sense, SCSI_SENSE_BUFFERSIZE); + set_driver_byte(scmd, DRIVER_SENSE); + } + break; + case FW_STAT_ABORTED: + set_host_byte(scmd, DID_ABORT); + break; + case FW_STAT_NEED_RETRY: + set_host_byte(scmd, DID_REQUEUE); + break; + default: + set_host_byte(scmd, DID_BAD_TARGET); + break; + } +} + +static inline void spraid_get_tag_from_scmd(struct scsi_cmnd *scmd, u16 *qid, u16 *cid) +{ + u32 tag = blk_mq_unique_tag(scmd->request); + + *qid = blk_mq_unique_tag_to_hwq(tag) + 1; + *cid = blk_mq_unique_tag_to_tag(tag); +} + +static int spraid_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_dev *hdev = shost_priv(shost); + struct scsi_device *sdev = scmd->device; + struct spraid_sdev_hostdata *hostdata; + struct spraid_ioq_command ioq_cmd; + struct spraid_queue *ioq; + unsigned long elapsed; + u16 hwq, cid; + int ret; + + if (unlikely(!scmd)) { + dev_err(hdev->dev, "err, scmd is null, return 0\n"); + return 0; + } + + if (unlikely(hdev->state != SPRAID_LIVE)) { + set_host_byte(scmd, DID_NO_CONNECT); + scmd->scsi_done(scmd); + dev_err(hdev->dev, "[%s] err, hdev state is not live\n", __func__); + return 0; + } + + if (log_debug_switch) + scsi_print_command(scmd); + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + hostdata = sdev->hostdata; + ioq = &hdev->queues[hwq]; + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.rw.hdid = cpu_to_le32(hostdata->hdid); + ioq_cmd.rw.command_id = cid; + + spraid_setup_ioq_cmd(hdev, &ioq_cmd, scmd); + + ret = cid * SCSI_SENSE_BUFFERSIZE; + iod->sense = ioq->sense + ret; + iod->sense_dma = ioq->sense_dma_addr + ret; + + ret = spraid_init_iod(hdev, iod, &ioq_cmd, scmd); + if (unlikely(ret)) + return SCSI_MLQUEUE_HOST_BUSY; + + iod->spraidq = ioq; + ret = spraid_io_map_data(hdev, iod, scmd, &ioq_cmd); + if (unlikely(ret)) { + dev_err(hdev->dev, "spraid_io_map_data Err.\n"); + set_host_byte(scmd, DID_ERROR); + scmd->scsi_done(scmd); + ret = 0; + goto deinit_iod; + } + + WRITE_ONCE(iod->state, SPRAID_CMD_IN_FLIGHT); + spraid_submit_cmd(ioq, &ioq_cmd); + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, "cid[%d], qid[%d] submit IO cost %3ld.%3ld seconds\n", + cid, hwq, elapsed / HZ, elapsed % HZ); + return 0; + +deinit_iod: + spraid_free_iod_res(hdev, iod); + return ret; +} + +static int spraid_match_dev(struct spraid_dev *hdev, u16 idx, struct scsi_device *sdev) +{ + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[idx].flag)) { + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + dev_info(hdev->dev, "Match device success, channel:target:lun[%d:%d:%d]\n", + hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + return 1; + } + } + + return 0; +} + +static int spraid_slave_alloc(struct scsi_device *sdev) +{ + struct spraid_sdev_hostdata *hostdata; + struct spraid_dev *hdev; + u16 idx; + + hdev = shost_priv(sdev->host); + hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL); + if (!hostdata) { + dev_err(hdev->dev, "Alloc scsi host data memory failed\n"); + return -ENOMEM; + } + + down_read(&hdev->devices_rwsem); + for (idx = 0; idx < le32_to_cpu(hdev->ctrl_info->nd); idx++) { + if (spraid_match_dev(hdev, idx, sdev)) + goto scan_host; + } + up_read(&hdev->devices_rwsem); + + kfree(hostdata); + return -ENXIO; + +scan_host: + hostdata->hdid = le32_to_cpu(hdev->devices[idx].hdid); + sdev->hostdata = hostdata; + up_read(&hdev->devices_rwsem); + return 0; +} + +static void spraid_slave_destroy(struct scsi_device *sdev) +{ + kfree(sdev->hostdata); + sdev->hostdata = NULL; +} + +static int spraid_slave_configure(struct scsi_device *sdev) +{ + u16 idx; + unsigned int timeout = scmd_tmout_nonpt * HZ; + struct spraid_dev *hdev = shost_priv(sdev->host); + struct spraid_sdev_hostdata *hostdata = sdev->hostdata; + u32 max_sec = sdev->host->max_sectors; + + if (!hostdata) { + idx = hostdata->hdid - 1; + if (sdev->channel == hdev->devices[idx].channel && + sdev->id == le16_to_cpu(hdev->devices[idx].target) && + sdev->lun < hdev->devices[idx].lun) { + if (SPRAID_DEV_INFO_ATTR_PT(hdev->devices[idx].attr)) + timeout = scmd_tmout_pt * HZ; + else + timeout = scmd_tmout_nonpt * HZ; + max_sec = le16_to_cpu(hdev->devices[idx].max_io_kb) << 1; + } else { + dev_err(hdev->dev, "[%s] err, sdev->channel:id:lun[%d:%d:%lld];" + "devices[%d], channel:target:lun[%d:%d:%d]\n", + __func__, sdev->channel, sdev->id, sdev->lun, + idx, hdev->devices[idx].channel, + hdev->devices[idx].target, + hdev->devices[idx].lun); + } + } else { + dev_err(hdev->dev, "[%s] err, sdev->hostdata is null\n", __func__); + } + + blk_queue_rq_timeout(sdev->request_queue, timeout); + sdev->eh_timeout = timeout; + + if ((max_sec == 0) || (max_sec > sdev->host->max_sectors)) + max_sec = sdev->host->max_sectors; + blk_queue_max_hw_sectors(sdev->request_queue, max_sec); + + dev_info(hdev->dev, "[%s] sdev->channel:id:lun[%d:%d:%lld], scmd_timeout[%d]s, maxsec[%d]\n", + __func__, sdev->channel, sdev->id, sdev->lun, timeout / HZ, max_sec); + + return 0; +} + +static void spraid_shost_init(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u8 domain, bus; + u32 dev_func; + + domain = pci_domain_nr(pdev->bus); + bus = pdev->bus->number; + dev_func = pdev->devfn; + + hdev->shost->nr_hw_queues = hdev->online_queues - 1; + hdev->shost->can_queue = (hdev->ioq_depth - SPRAID_PTCMDS_PERQ); + + hdev->shost->sg_tablesize = le16_to_cpu(hdev->ctrl_info->max_num_sge); + /* 512B per sector */ + hdev->shost->max_sectors = (1U << ((hdev->ctrl_info->mdts) * 1U) << 12) / 512; + hdev->shost->cmd_per_lun = MAX_CMD_PER_DEV; + hdev->shost->max_channel = le16_to_cpu(hdev->ctrl_info->max_channel) - 1; + hdev->shost->max_id = le32_to_cpu(hdev->ctrl_info->max_tgt_id); + hdev->shost->max_lun = le16_to_cpu(hdev->ctrl_info->max_lun); + + hdev->shost->this_id = -1; + hdev->shost->unique_id = (domain << 16) | (bus << 8) | dev_func; + hdev->shost->max_cmd_len = MAX_CDB_LEN; + hdev->shost->hostt->cmd_size = max(spraid_cmd_size(hdev, false, true), + spraid_cmd_size(hdev, false, false)); +} + +static inline void spraid_host_deinit(struct spraid_dev *hdev) +{ + ida_free(&spraid_instance_ida, hdev->instance); +} + +static int spraid_alloc_queue(struct spraid_dev *hdev, u16 qid, u16 depth) +{ + struct spraid_queue *spraidq = &hdev->queues[qid]; + int ret = 0; + + if (hdev->queue_count > qid) { + dev_info(hdev->dev, "[%s] warn: queue[%d] is exist\n", __func__, qid); + return 0; + } + + spraidq->cqes = dma_alloc_coherent(hdev->dev, CQ_SIZE(depth), + &spraidq->cq_dma_addr, GFP_KERNEL | __GFP_ZERO); + if (!spraidq->cqes) + return -ENOMEM; + + spraidq->sq_cmds = dma_alloc_coherent(hdev->dev, SQ_SIZE(qid, depth), + &spraidq->sq_dma_addr, GFP_KERNEL); + if (!spraidq->sq_cmds) { + ret = -ENOMEM; + goto free_cqes; + } + + spin_lock_init(&spraidq->sq_lock); + spin_lock_init(&spraidq->cq_lock); + spraidq->hdev = hdev; + spraidq->q_depth = depth; + spraidq->qid = qid; + spraidq->cq_vector = -1; + hdev->queue_count++; + + /* alloc sense buffer */ + spraidq->sense = dma_alloc_coherent(hdev->dev, SENSE_SIZE(depth), + &spraidq->sense_dma_addr, GFP_KERNEL | __GFP_ZERO); + if (!spraidq->sense) { + ret = -ENOMEM; + goto free_sq_cmds; + } + + return 0; + +free_sq_cmds: + dma_free_coherent(hdev->dev, SQ_SIZE(qid, depth), (void *)spraidq->sq_cmds, + spraidq->sq_dma_addr); +free_cqes: + dma_free_coherent(hdev->dev, CQ_SIZE(depth), (void *)spraidq->cqes, + spraidq->cq_dma_addr); + return ret; +} + +static int spraid_wait_ready(struct spraid_dev *hdev, u64 cap, bool enabled) +{ + unsigned long timeout = + ((SPRAID_CAP_TIMEOUT(cap) + 1) * SPRAID_CAP_TIMEOUT_UNIT_MS) + jiffies; + u32 bit = enabled ? SPRAID_CSTS_RDY : 0; + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY) != bit) { + usleep_range(1000, 2000); + if (fatal_signal_pending(current)) + return -EINTR; + + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, "Device not ready; aborting %s\n", + enabled ? "initialisation" : "reset"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_shutdown_ctrl(struct spraid_dev *hdev) +{ + unsigned long timeout = hdev->ctrl_info->rtd3e + jiffies; + + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config |= SPRAID_CC_SHN_NORMAL; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + while ((readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_SHST_MASK) != + SPRAID_CSTS_SHST_CMPLT) { + msleep(100); + if (fatal_signal_pending(current)) + return -EINTR; + if (time_after(jiffies, timeout)) { + dev_err(hdev->dev, "Device shutdown incomplete; abort shutdown\n"); + return -ENODEV; + } + } + return 0; +} + +static int spraid_disable_ctrl(struct spraid_dev *hdev) +{ + hdev->ctrl_config &= ~SPRAID_CC_SHN_MASK; + hdev->ctrl_config &= ~SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, hdev->cap, false); +} + +static int spraid_enable_ctrl(struct spraid_dev *hdev) +{ + u64 cap = hdev->cap; + u32 dev_page_min = SPRAID_CAP_MPSMIN(cap) + 12; + u32 page_shift = PAGE_SHIFT; + + if (page_shift < dev_page_min) { + dev_err(hdev->dev, "Minimum device page size[%u], too large for host[%u]\n", + 1U << dev_page_min, 1U << page_shift); + return -ENODEV; + } + + page_shift = min_t(unsigned int, SPRAID_CAP_MPSMAX(cap) + 12, PAGE_SHIFT); + hdev->page_size = 1U << page_shift; + + hdev->ctrl_config = SPRAID_CC_CSS_NVM; + hdev->ctrl_config |= (page_shift - 12) << SPRAID_CC_MPS_SHIFT; + hdev->ctrl_config |= SPRAID_CC_AMS_RR | SPRAID_CC_SHN_NONE; + hdev->ctrl_config |= SPRAID_CC_IOSQES | SPRAID_CC_IOCQES; + hdev->ctrl_config |= SPRAID_CC_ENABLE; + writel(hdev->ctrl_config, hdev->bar + SPRAID_REG_CC); + + return spraid_wait_ready(hdev, cap, true); +} + +static void spraid_init_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + + memset((void *)spraidq->cqes, 0, CQ_SIZE(spraidq->q_depth)); + + spraidq->sq_tail = 0; + spraidq->cq_head = 0; + spraidq->cq_phase = 1; + spraidq->q_db = &hdev->dbs[qid * 2 * hdev->db_stride]; + spraidq->prp_small_pool = hdev->prp_small_pool[qid % small_pool_num]; + hdev->online_queues++; +} + +static inline bool spraid_cqe_pending(struct spraid_queue *spraidq) +{ + return (le16_to_cpu(spraidq->cqes[spraidq->cq_head].status) & 1) == + spraidq->cq_phase; +} + +static void spraid_complete_ioq_cmnd(struct spraid_queue *ioq, struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + unsigned long elapsed; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) { + dev_warn(hdev->dev, "Invalid id %d completed on queue %d\n", + cqe->cmd_id, ioq->qid); + return; + } + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + elapsed = jiffies - scmd->jiffies_at_alloc; + dev_log_dbg(hdev->dev, "cid[%d], qid[%d] finish IO cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + + if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_COMPLETE) != + SPRAID_CMD_IN_FLIGHT) { + dev_warn(hdev->dev, "cid[%d], qid[%d] enters abnormal handler, cost %3ld.%3ld seconds\n", + cqe->cmd_id, ioq->qid, elapsed / HZ, elapsed % HZ); + WRITE_ONCE(iod->state, SPRAID_CMD_TMO_COMPLETE); + + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + + return; + } + + spraid_map_status(iod, scmd, cqe); + if (iod->nsge) { + iod->nsge = 0; + scsi_dma_unmap(scmd); + } + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); +} + +static inline void spraid_end_admin_request(struct request *req, __le16 status, + __le32 result0, __le32 result1) +{ + struct spraid_admin_request *rq = spraid_admin_req(req); + + rq->status = le16_to_cpu(status) >> 1; + rq->result0 = le32_to_cpu(result0); + rq->result1 = le32_to_cpu(result1); + blk_mq_complete_request(req); +} + +static void spraid_complete_adminq_cmnd(struct spraid_queue *adminq, struct spraid_completion *cqe) +{ + struct blk_mq_tags *tags = adminq->hdev->admin_tagset.tags[0]; + struct request *req; + + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req)) { + dev_warn(adminq->hdev->dev, "Invalid id %d completed on queue %d\n", + cqe->cmd_id, le16_to_cpu(cqe->sq_id)); + return; + } + spraid_end_admin_request(req, cqe->status, cqe->result, cqe->result1); +} + +static void spraid_complete_aen(struct spraid_queue *spraidq, struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = spraidq->hdev; + u32 result = le32_to_cpu(cqe->result); + + dev_info(hdev->dev, "rcv aen, status[%x], result[%x]\n", + le16_to_cpu(cqe->status) >> 1, result); + + if ((le16_to_cpu(cqe->status) >> 1) != SPRAID_SC_SUCCESS) + return; + switch (result & 0x7) { + case SPRAID_AEN_NOTICE: + spraid_handle_aen_notice(hdev, result); + break; + case SPRAID_AEN_VS: + spraid_handle_aen_vs(hdev, result); + break; + default: + dev_warn(hdev->dev, "Unsupported async event type: %u\n", + result & 0x7); + break; + } + queue_work(spraid_wq, &hdev->aen_work); +} + +static void spraid_put_ioq_ptcmd(struct spraid_dev *hdev, struct spraid_ioq_ptcmd *cmd); + +static void spraid_complete_ioq_sync_cmnd(struct spraid_queue *ioq, struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct spraid_ioq_ptcmd *ptcmd; + + ptcmd = hdev->ioq_ptcmds + (ioq->qid - 1) * SPRAID_PTCMDS_PERQ + + cqe->cmd_id - SPRAID_IO_BLK_MQ_DEPTH; + + ptcmd->status = le16_to_cpu(cqe->status) >> 1; + ptcmd->result0 = le32_to_cpu(cqe->result); + ptcmd->result1 = le32_to_cpu(cqe->result1); + + complete(&ptcmd->cmd_done); + + spraid_put_ioq_ptcmd(hdev, ptcmd); +} + +static inline void spraid_handle_cqe(struct spraid_queue *spraidq, u16 idx) +{ + struct spraid_completion *cqe = &spraidq->cqes[idx]; + struct spraid_dev *hdev = spraidq->hdev; + + if (unlikely(cqe->cmd_id >= spraidq->q_depth)) { + dev_err(hdev->dev, "Invalid command id[%d] completed on queue %d\n", + cqe->cmd_id, cqe->sq_id); + return; + } + + dev_log_dbg(hdev->dev, "cid[%d], qid[%d], result[0x%x], sq_id[%d], status[0x%x]\n", + cqe->cmd_id, spraidq->qid, le32_to_cpu(cqe->result), + le16_to_cpu(cqe->sq_id), le16_to_cpu(cqe->status)); + + if (unlikely(spraidq->qid == 0 && cqe->cmd_id >= SPRAID_AQ_BLK_MQ_DEPTH)) { + spraid_complete_aen(spraidq, cqe); + return; + } + + if (unlikely(spraidq->qid && cqe->cmd_id >= SPRAID_IO_BLK_MQ_DEPTH)) { + spraid_complete_ioq_sync_cmnd(spraidq, cqe); + return; + } + + if (spraidq->qid) + spraid_complete_ioq_cmnd(spraidq, cqe); + else + spraid_complete_adminq_cmnd(spraidq, cqe); +} + +static void spraid_complete_cqes(struct spraid_queue *spraidq, u16 start, u16 end) +{ + while (start != end) { + spraid_handle_cqe(spraidq, start); + if (++start == spraidq->q_depth) + start = 0; + } +} + +static inline void spraid_update_cq_head(struct spraid_queue *spraidq) +{ + if (++spraidq->cq_head == spraidq->q_depth) { + spraidq->cq_head = 0; + spraidq->cq_phase = !spraidq->cq_phase; + } +} + +static inline bool spraid_process_cq(struct spraid_queue *spraidq, u16 *start, u16 *end, int tag) +{ + bool found = false; + + *start = spraidq->cq_head; + while (!found && spraid_cqe_pending(spraidq)) { + if (spraidq->cqes[spraidq->cq_head].cmd_id == tag) + found = true; + spraid_update_cq_head(spraidq); + } + *end = spraidq->cq_head; + + if (*start != *end) + writel(spraidq->cq_head, spraidq->q_db + spraidq->hdev->db_stride); + + return found; +} + +static bool spraid_poll_cq(struct spraid_queue *spraidq, int cid) +{ + u16 start, end; + bool found; + + if (!spraid_cqe_pending(spraidq)) + return 0; + + spin_lock_irq(&spraidq->cq_lock); + found = spraid_process_cq(spraidq, &start, &end, cid); + spin_unlock_irq(&spraidq->cq_lock); + + spraid_complete_cqes(spraidq, start, end); + return found; +} + +static irqreturn_t spraid_irq(int irq, void *data) +{ + struct spraid_queue *spraidq = data; + irqreturn_t ret = IRQ_NONE; + u16 start, end; + + spin_lock(&spraidq->cq_lock); + if (spraidq->cq_head != spraidq->last_cq_head) + ret = IRQ_HANDLED; + + spraid_process_cq(spraidq, &start, &end, -1); + spraidq->last_cq_head = spraidq->cq_head; + spin_unlock(&spraidq->cq_lock); + + if (start != end) { + spraid_complete_cqes(spraidq, start, end); + ret = IRQ_HANDLED; + } + return ret; +} + +static int spraid_setup_admin_queue(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u32 aqa; + int ret; + + dev_info(hdev->dev, "[%s] start disable ctrl\n", __func__); + + ret = spraid_disable_ctrl(hdev); + if (ret) + return ret; + + ret = spraid_alloc_queue(hdev, 0, SPRAID_AQ_DEPTH); + if (ret) + return ret; + + aqa = adminq->q_depth - 1; + aqa |= aqa << 16; + writel(aqa, hdev->bar + SPRAID_REG_AQA); + lo_hi_writeq(adminq->sq_dma_addr, hdev->bar + SPRAID_REG_ASQ); + lo_hi_writeq(adminq->cq_dma_addr, hdev->bar + SPRAID_REG_ACQ); + + dev_info(hdev->dev, "[%s] start enable ctrl\n", __func__); + + ret = spraid_enable_ctrl(hdev); + if (ret) { + ret = -ENODEV; + goto free_queue; + } + + adminq->cq_vector = 0; + spraid_init_queue(adminq, 0); + ret = pci_request_irq(hdev->pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", hdev->instance, adminq->qid); + + if (ret) { + adminq->cq_vector = -1; + hdev->online_queues--; + goto free_queue; + } + + dev_info(hdev->dev, "[%s] success, queuecount:[%d], onlinequeue:[%d]\n", + __func__, hdev->queue_count, hdev->online_queues); + + return 0; + +free_queue: + spraid_free_queue(adminq); + return ret; +} + +static u32 spraid_bar_size(struct spraid_dev *hdev, u32 nr_ioqs) +{ + return (SPRAID_REG_DBS + ((nr_ioqs + 1) * 8 * hdev->db_stride)); +} + +static inline void spraid_clear_spraid_request(struct request *req) +{ + if (!(req->rq_flags & RQF_DONTPREP)) { + spraid_admin_req(req)->flags = 0; + req->rq_flags |= RQF_DONTPREP; + } +} + +static struct request *spraid_alloc_admin_request(struct request_queue *q, + struct spraid_admin_command *cmd, + blk_mq_req_flags_t flags) +{ + u32 op = COMMAND_IS_WRITE(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN; + struct request *req; + + req = blk_mq_alloc_request(q, op, flags); + if (IS_ERR(req)) + return req; + req->cmd_flags |= REQ_FAILFAST_DRIVER; + spraid_clear_spraid_request(req); + spraid_admin_req(req)->cmd = cmd; + + return req; +} + +static int spraid_submit_admin_sync_cmd(struct request_queue *q, + struct spraid_admin_command *cmd, + u32 *result, void *buffer, + u32 bufflen, u32 timeout, int at_head, blk_mq_req_flags_t flags) +{ + struct request *req; + int ret; + + req = spraid_alloc_admin_request(q, cmd, flags); + if (IS_ERR(req)) + return PTR_ERR(req); + + req->timeout = timeout ? timeout : ADMIN_TIMEOUT; + if (buffer && bufflen) { + ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); + if (ret) + goto out; + } + blk_execute_rq(req->q, NULL, req, at_head); + + if (result) + *result = spraid_admin_req(req)->result0; + + if (spraid_admin_req(req)->flags & SPRAID_REQ_CANCELLED) + ret = -EINTR; + else + ret = spraid_admin_req(req)->status; + +out: + blk_mq_free_request(req); + return ret; +} + +static int spraid_create_cq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq, u16 cq_vector) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG | SPRAID_CQ_IRQ_ENABLED; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_cq.opcode = SPRAID_ADMIN_CREATE_CQ; + admin_cmd.create_cq.prp1 = cpu_to_le64(spraidq->cq_dma_addr); + admin_cmd.create_cq.cqid = cpu_to_le16(qid); + admin_cmd.create_cq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_cq.cq_flags = cpu_to_le16(flags); + admin_cmd.create_cq.irq_vector = cpu_to_le16(cq_vector); + + return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, + NULL, 0, 0, 0, 0); +} + +static int spraid_create_sq(struct spraid_dev *hdev, u16 qid, + struct spraid_queue *spraidq) +{ + struct spraid_admin_command admin_cmd; + int flags = SPRAID_QUEUE_PHYS_CONTIG; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.create_sq.opcode = SPRAID_ADMIN_CREATE_SQ; + admin_cmd.create_sq.prp1 = cpu_to_le64(spraidq->sq_dma_addr); + admin_cmd.create_sq.sqid = cpu_to_le16(qid); + admin_cmd.create_sq.qsize = cpu_to_le16(spraidq->q_depth - 1); + admin_cmd.create_sq.sq_flags = cpu_to_le16(flags); + admin_cmd.create_sq.cqid = cpu_to_le16(qid); + + return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, + NULL, 0, 0, 0, 0); +} + +static void spraid_free_queue(struct spraid_queue *spraidq) +{ + struct spraid_dev *hdev = spraidq->hdev; + + hdev->queue_count--; + dma_free_coherent(hdev->dev, CQ_SIZE(spraidq->q_depth), + (void *)spraidq->cqes, spraidq->cq_dma_addr); + dma_free_coherent(hdev->dev, SQ_SIZE(spraidq->qid, spraidq->q_depth), + spraidq->sq_cmds, spraidq->sq_dma_addr); + dma_free_coherent(hdev->dev, SENSE_SIZE(spraidq->q_depth), + spraidq->sense, spraidq->sense_dma_addr); +} + +static void spraid_free_admin_queue(struct spraid_dev *hdev) +{ + spraid_free_queue(&hdev->queues[0]); +} + +static void spraid_free_io_queues(struct spraid_dev *hdev) +{ + int i; + + for (i = hdev->queue_count - 1; i >= 1; i--) + spraid_free_queue(&hdev->queues[i]); +} + +static int spraid_delete_queue(struct spraid_dev *hdev, u8 op, u16 id) +{ + struct spraid_admin_command admin_cmd; + int ret; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.delete_queue.opcode = op; + admin_cmd.delete_queue.qid = cpu_to_le16(id); + + ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, + NULL, 0, 0, 0, 0); + + if (ret) + dev_err(hdev->dev, "Delete %s:[%d] failed\n", + (op == SPRAID_ADMIN_DELETE_CQ) ? "cq" : "sq", id); + + return ret; +} + +static int spraid_delete_cq(struct spraid_dev *hdev, u16 cqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_CQ, cqid); +} + +static int spraid_delete_sq(struct spraid_dev *hdev, u16 sqid) +{ + return spraid_delete_queue(hdev, SPRAID_ADMIN_DELETE_SQ, sqid); +} + +static int spraid_create_queue(struct spraid_queue *spraidq, u16 qid) +{ + struct spraid_dev *hdev = spraidq->hdev; + u16 cq_vector; + int ret; + + cq_vector = (hdev->num_vecs == 1) ? 0 : qid; + ret = spraid_create_cq(hdev, qid, spraidq, cq_vector); + if (ret) + return ret; + + ret = spraid_create_sq(hdev, qid, spraidq); + if (ret) + goto delete_cq; + + spraid_init_queue(spraidq, qid); + spraidq->cq_vector = cq_vector; + + ret = pci_request_irq(hdev->pdev, cq_vector, spraid_irq, NULL, + spraidq, "spraid%d_q%d", hdev->instance, qid); + + if (ret) { + dev_err(hdev->dev, "Request queue[%d] irq failed\n", qid); + goto delete_sq; + } + + return 0; + +delete_sq: + spraidq->cq_vector = -1; + hdev->online_queues--; + spraid_delete_sq(hdev, qid); +delete_cq: + spraid_delete_cq(hdev, qid); + + return ret; +} + +static int spraid_create_io_queues(struct spraid_dev *hdev) +{ + u32 i, max; + int ret = 0; + + max = min(hdev->max_qid, hdev->queue_count - 1); + for (i = hdev->online_queues; i <= max; i++) { + ret = spraid_create_queue(&hdev->queues[i], i); + if (ret) { + dev_err(hdev->dev, "Create queue[%d] failed\n", i); + break; + } + } + + dev_info(hdev->dev, "[%s] queue_count[%d], online_queue[%d]", + __func__, hdev->queue_count, hdev->online_queues); + + return ret >= 0 ? 0 : ret; +} + +static int spraid_set_features(struct spraid_dev *hdev, u32 fid, u32 dword11, void *buffer, + size_t buflen, u32 *result) +{ + struct spraid_admin_command admin_cmd; + u32 res; + int ret; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.features.opcode = SPRAID_ADMIN_SET_FEATURES; + admin_cmd.features.fid = cpu_to_le32(fid); + admin_cmd.features.dword11 = cpu_to_le32(dword11); + + ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, &res, + buffer, buflen, 0, 0, 0); + + if (!ret && result) + *result = res; + + return ret; +} + +static int spraid_configure_timestamp(struct spraid_dev *hdev) +{ + __le64 ts; + int ret; + + ts = cpu_to_le64(ktime_to_ms(ktime_get_real())); + ret = spraid_set_features(hdev, SPRAID_FEAT_TIMESTAMP, 0, &ts, sizeof(ts), NULL); + + if (ret) + dev_err(hdev->dev, "set timestamp failed: %d\n", ret); + return ret; +} + +static int spraid_set_queue_cnt(struct spraid_dev *hdev, u32 *cnt) +{ + u32 q_cnt = (*cnt - 1) | ((*cnt - 1) << 16); + u32 nr_ioqs, result; + int status; + + status = spraid_set_features(hdev, SPRAID_FEAT_NUM_QUEUES, q_cnt, NULL, 0, &result); + if (status) { + dev_err(hdev->dev, "Set queue count failed, status: %d\n", + status); + return -EIO; + } + + nr_ioqs = min(result & 0xffff, result >> 16) + 1; + *cnt = min(*cnt, nr_ioqs); + if (*cnt == 0) { + dev_err(hdev->dev, "Illegal queue count: zero\n"); + return -EIO; + } + return 0; +} + +static int spraid_setup_io_queues(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct pci_dev *pdev = hdev->pdev; + u32 nr_ioqs = num_online_cpus(); + u32 i, size; + int ret; + + struct irq_affinity affd = { + .pre_vectors = 1 + }; + + ret = spraid_set_queue_cnt(hdev, &nr_ioqs); + if (ret < 0) + return ret; + + size = spraid_bar_size(hdev, nr_ioqs); + ret = spraid_remap_bar(hdev, size); + if (ret) + return -ENOMEM; + + adminq->q_db = hdev->dbs; + + pci_free_irq(pdev, 0, adminq); + pci_free_irq_vectors(pdev); + + ret = pci_alloc_irq_vectors_affinity(pdev, 1, (nr_ioqs + 1), + PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); + if (ret <= 0) + return -EIO; + + hdev->num_vecs = ret; + + hdev->max_qid = max(ret - 1, 1); + + ret = pci_request_irq(pdev, adminq->cq_vector, spraid_irq, NULL, + adminq, "spraid%d_q%d", hdev->instance, adminq->qid); + if (ret) { + dev_err(hdev->dev, "Request admin irq failed\n"); + adminq->cq_vector = -1; + return ret; + } + + for (i = hdev->queue_count; i <= hdev->max_qid; i++) { + ret = spraid_alloc_queue(hdev, i, hdev->ioq_depth); + if (ret) + break; + } + dev_info(hdev->dev, "[%s] max_qid: %d, queue_count: %d, online_queue: %d, ioq_depth: %d\n", + __func__, hdev->max_qid, hdev->queue_count, + hdev->online_queues, hdev->ioq_depth); + + return spraid_create_io_queues(hdev); +} + +static void spraid_delete_io_queues(struct spraid_dev *hdev) +{ + u16 queues = hdev->online_queues - 1; + u8 opcode = SPRAID_ADMIN_DELETE_SQ; + u16 i, pass; + + if (!pci_device_is_present(hdev->pdev)) { + dev_err(hdev->dev, "pci_device is not present, skip disable io queues\n"); + return; + } + + if (hdev->online_queues < 2) { + dev_err(hdev->dev, "[%s] err, io queue has been delete\n", __func__); + return; + } + + for (pass = 0; pass < 2; pass++) { + for (i = queues; i > 0; i--) + if (spraid_delete_queue(hdev, opcode, i)) + break; + + opcode = SPRAID_ADMIN_DELETE_CQ; + } +} + +static void spraid_remove_io_queues(struct spraid_dev *hdev) +{ + spraid_delete_io_queues(hdev); + spraid_free_io_queues(hdev); +} + +static void spraid_pci_disable(struct spraid_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + u32 i; + + for (i = 0; i < hdev->online_queues; i++) + pci_free_irq(pdev, hdev->queues[i].cq_vector, &hdev->queues[i]); + pci_free_irq_vectors(pdev); + if (pci_is_enabled(pdev)) { + pci_disable_pcie_error_reporting(pdev); + pci_disable_device(pdev); + } + hdev->online_queues = 0; +} + +static void spraid_disable_admin_queue(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] err, admin queue has been delete\n", __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + + spraid_complete_cqes(adminq, start, end); + spraid_free_admin_queue(hdev); +} + +static int spraid_create_dma_pools(struct spraid_dev *hdev) +{ + int i; + char poolname[20] = { 0 }; + + hdev->prp_page_pool = dma_pool_create("prp list page", hdev->dev, + PAGE_SIZE, PAGE_SIZE, 0); + + if (!hdev->prp_page_pool) { + dev_err(hdev->dev, "create prp_page_pool failed\n"); + return -ENOMEM; + } + + for (i = 0; i < small_pool_num; i++) { + sprintf(poolname, "prp_list_256_%d", i); + hdev->prp_small_pool[i] = dma_pool_create(poolname, hdev->dev, SMALL_POOL_SIZE, + SMALL_POOL_SIZE, 0); + + if (!hdev->prp_small_pool[i]) { + dev_err(hdev->dev, "create prp_small_pool %d failed\n", i); + goto destroy_prp_small_pool; + } + } + + return 0; + +destroy_prp_small_pool: + while (i > 0) + dma_pool_destroy(hdev->prp_small_pool[--i]); + dma_pool_destroy(hdev->prp_page_pool); + + return -ENOMEM; +} + +static void spraid_destroy_dma_pools(struct spraid_dev *hdev) +{ + int i; + + for (i = 0; i < small_pool_num; i++) + dma_pool_destroy(hdev->prp_small_pool[i]); + dma_pool_destroy(hdev->prp_page_pool); +} + +static int spraid_get_dev_list(struct spraid_dev *hdev, struct spraid_dev_info *devices) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + struct spraid_admin_command admin_cmd; + struct spraid_dev_list *list_buf; + u32 i, idx, hdid, ndev; + int ret = 0; + + list_buf = kmalloc(sizeof(*list_buf), GFP_KERNEL); + if (!list_buf) + return -ENOMEM; + + for (idx = 0; idx < nd;) { + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_DEV_LIST; + admin_cmd.get_info.cdw11 = cpu_to_le32(idx); + + ret = spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, list_buf, + sizeof(*list_buf), 0, 0, 0); + + if (ret) { + dev_err(hdev->dev, "Get device list failed, nd: %u, idx: %u, ret: %d\n", + nd, idx, ret); + goto out; + } + ndev = le32_to_cpu(list_buf->dev_num); + + dev_info(hdev->dev, "ndev numbers: %u\n", ndev); + + for (i = 0; i < ndev; i++) { + hdid = le32_to_cpu(list_buf->devices[i].hdid); + dev_info(hdev->dev, "list_buf->devices[%d], hdid: %u target: %d, channel: %d, lun: %d, attr[%x]\n", + i, hdid, + le16_to_cpu(list_buf->devices[i].target), + list_buf->devices[i].channel, + list_buf->devices[i].lun, + list_buf->devices[i].attr); + if (hdid > nd || hdid == 0) { + dev_err(hdev->dev, "err, hdid[%d] invalid\n", hdid); + continue; + } + memcpy(&devices[hdid - 1], &list_buf->devices[i], + sizeof(struct spraid_dev_info)); + } + idx += ndev; + + if (idx < MAX_DEV_ENTRY_PER_PAGE_4K) + break; + } + +out: + kfree(list_buf); + return ret; +} + +static void spraid_send_aen(struct spraid_dev *hdev) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = SPRAID_ADMIN_ASYNC_EVENT; + admin_cmd.common.command_id = SPRAID_AQ_BLK_MQ_DEPTH; + + spraid_submit_cmd(adminq, &admin_cmd); + dev_info(hdev->dev, "send aen, cid[%d]\n", SPRAID_AQ_BLK_MQ_DEPTH); +} + +static int spraid_add_device(struct spraid_dev *hdev, struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + sdev = scsi_device_lookup(shost, device->channel, le16_to_cpu(device->target), 0); + if (sdev) { + dev_warn(hdev->dev, "Device is already exist, channel: %d, target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + scsi_device_put(sdev); + return -EEXIST; + } + scsi_add_device(shost, device->channel, le16_to_cpu(device->target), 0); + return 0; +} + +static int spraid_rescan_device(struct spraid_dev *hdev, struct spraid_dev_info *device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + sdev = scsi_device_lookup(shost, device->channel, le16_to_cpu(device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "Device is not exit, channel: %d, target_id: %d, lun: %d\n", + device->channel, le16_to_cpu(device->target), 0); + return -ENODEV; + } + + scsi_rescan_device(&sdev->sdev_gendev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_remove_device(struct spraid_dev *hdev, struct spraid_dev_info *org_device) +{ + struct Scsi_Host *shost = hdev->shost; + struct scsi_device *sdev; + + sdev = scsi_device_lookup(shost, org_device->channel, le16_to_cpu(org_device->target), 0); + if (!sdev) { + dev_warn(hdev->dev, "Device is not exit, channel: %d, target_id: %d, lun: %d\n", + org_device->channel, le16_to_cpu(org_device->target), 0); + return -ENODEV; + } + + scsi_remove_device(sdev); + scsi_device_put(sdev); + return 0; +} + +static int spraid_dev_list_init(struct spraid_dev *hdev) +{ + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + int i, ret; + + hdev->devices = kzalloc_node(nd * sizeof(struct spraid_dev_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->devices) + return -ENOMEM; + + ret = spraid_get_dev_list(hdev, hdev->devices); + if (ret) { + dev_err(hdev->dev, "Ignore failure of getting device list within initialization\n"); + return 0; + } + + for (i = 0; i < nd; i++) { + if (SPRAID_DEV_INFO_FLAG_VALID(hdev->devices[i].flag) && + SPRAID_DEV_INFO_ATTR_BOOT(hdev->devices[i].attr)) { + spraid_add_device(hdev, &hdev->devices[i]); + break; + } + } + return 0; +} + +static void spraid_scan_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, scan_work); + struct spraid_dev_info *devices, *org_devices; + u32 nd = le32_to_cpu(hdev->ctrl_info->nd); + u8 flag, org_flag; + int i, ret; + + devices = kcalloc(nd, sizeof(struct spraid_dev_info), GFP_KERNEL); + if (!devices) + return; + ret = spraid_get_dev_list(hdev, devices); + if (ret) + goto free_list; + org_devices = hdev->devices; + for (i = 0; i < nd; i++) { + org_flag = org_devices[i].flag; + flag = devices[i].flag; + + dev_log_dbg(hdev->dev, "i: %d, org_flag: 0x%x, flag: 0x%x\n", + i, org_flag, flag); + + if (SPRAID_DEV_INFO_FLAG_VALID(flag)) { + if (!SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + memcpy(&org_devices[i], &devices[i], + sizeof(struct spraid_dev_info)); + up_write(&hdev->devices_rwsem); + spraid_add_device(hdev, &devices[i]); + } else if (SPRAID_DEV_INFO_FLAG_CHANGE(flag)) { + spraid_rescan_device(hdev, &devices[i]); + } + } else { + if (SPRAID_DEV_INFO_FLAG_VALID(org_flag)) { + down_write(&hdev->devices_rwsem); + org_devices[i].flag &= 0xfe; + up_write(&hdev->devices_rwsem); + spraid_remove_device(hdev, &org_devices[i]); + } + } + } +free_list: + kfree(devices); +} + +static void spraid_timesyn_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, timesyn_work); + + spraid_configure_timestamp(hdev); +} + +static void spraid_queue_scan(struct spraid_dev *hdev) +{ + queue_work(spraid_wq, &hdev->scan_work); +} + +static void spraid_handle_aen_notice(struct spraid_dev *hdev, u32 result) +{ + switch ((result & 0xff00) >> 8) { + case SPRAID_AEN_DEV_CHANGED: + spraid_queue_scan(hdev); + break; + case SPRAID_AEN_HOST_PROBING: + break; + default: + dev_warn(hdev->dev, "async event result %08x\n", result); + } +} + +static void spraid_handle_aen_vs(struct spraid_dev *hdev, u32 result) +{ + switch (result) { + case SPRAID_AEN_TIMESYN: + queue_work(spraid_wq, &hdev->timesyn_work); + break; + default: + dev_warn(hdev->dev, "async event result: %x\n", result); + } +} + +static void spraid_async_event_work(struct work_struct *work) +{ + struct spraid_dev *hdev = + container_of(work, struct spraid_dev, aen_work); + + spraid_send_aen(hdev); +} + +static int spraid_alloc_resources(struct spraid_dev *hdev) +{ + int ret, nqueue; + + ret = ida_alloc(&spraid_instance_ida, GFP_KERNEL); + if (ret < 0) { + dev_err(hdev->dev, "Get instance id failed\n"); + return ret; + } + hdev->instance = ret; + + hdev->ctrl_info = kzalloc_node(sizeof(*hdev->ctrl_info), + GFP_KERNEL, hdev->numa_node); + if (!hdev->ctrl_info) { + ret = -ENOMEM; + goto release_instance; + } + + ret = spraid_create_dma_pools(hdev); + if (ret) + goto free_ctrl_info; + nqueue = num_possible_cpus() + 1; + hdev->queues = kcalloc_node(nqueue, sizeof(struct spraid_queue), + GFP_KERNEL, hdev->numa_node); + if (!hdev->queues) { + ret = -ENOMEM; + goto destroy_dma_pools; + } + + dev_info(hdev->dev, "[%s] queues num: %d\n", __func__, nqueue); + + return 0; + +destroy_dma_pools: + spraid_destroy_dma_pools(hdev); +free_ctrl_info: + kfree(hdev->ctrl_info); +release_instance: + ida_free(&spraid_instance_ida, hdev->instance); + return ret; +} + +static void spraid_free_resources(struct spraid_dev *hdev) +{ + kfree(hdev->queues); + spraid_destroy_dma_pools(hdev); + kfree(hdev->ctrl_info); + ida_free(&spraid_instance_ida, hdev->instance); +} + +static void spraid_setup_passthrough(struct request *req, struct spraid_admin_command *cmd) +{ + memcpy(cmd, spraid_admin_req(req)->cmd, sizeof(*cmd)); + cmd->common.flags &= ~SPRAID_CMD_FLAG_SGL_ALL; +} + +static inline void spraid_clear_hreq(struct request *req) +{ + if (!(req->rq_flags & RQF_DONTPREP)) { + spraid_admin_req(req)->flags = 0; + req->rq_flags |= RQF_DONTPREP; + } +} + +static blk_status_t spraid_setup_admin_cmd(struct request *req, struct spraid_admin_command *cmd) +{ + spraid_clear_hreq(req); + + memset(cmd, 0, sizeof(*cmd)); + switch (req_op(req)) { + case REQ_OP_DRV_IN: + case REQ_OP_DRV_OUT: + spraid_setup_passthrough(req, cmd); + break; + default: + WARN_ON_ONCE(1); + return BLK_STS_IOERR; + } + + cmd->common.command_id = req->tag; + return BLK_STS_OK; +} + +static void spraid_unmap_data(struct spraid_dev *hdev, struct request *req) +{ + struct spraid_iod *iod = blk_mq_rq_to_pdu(req); + enum dma_data_direction dma_dir = rq_data_dir(req) ? + DMA_TO_DEVICE : DMA_FROM_DEVICE; + + if (iod->nsge) + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); + + spraid_free_iod_res(hdev, iod); +} + +static blk_status_t spraid_admin_map_data(struct spraid_dev *hdev, struct request *req, + struct spraid_admin_command *cmd) +{ + struct spraid_iod *iod = blk_mq_rq_to_pdu(req); + struct request_queue *admin_q = req->q; + enum dma_data_direction dma_dir = rq_data_dir(req) ? + DMA_TO_DEVICE : DMA_FROM_DEVICE; + blk_status_t ret = BLK_STS_IOERR; + int nr_mapped; + int res; + + sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); + iod->nsge = blk_rq_map_sg(admin_q, req, iod->sg); + if (!iod->nsge) + goto out; + + dev_info(hdev->dev, "nseg: %u, nsge: %u\n", + blk_rq_nr_phys_segments(req), iod->nsge); + + ret = BLK_STS_RESOURCE; + nr_mapped = dma_map_sg_attrs(hdev->dev, iod->sg, iod->nsge, dma_dir, DMA_ATTR_NO_WARN); + if (!nr_mapped) + goto out; + + res = spraid_setup_prps(hdev, iod); + if (res) + goto unmap; + cmd->common.dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); + cmd->common.dptr.prp2 = cpu_to_le64(iod->first_dma); + return BLK_STS_OK; + +unmap: + dma_unmap_sg(hdev->dev, iod->sg, iod->nsge, dma_dir); +out: + return ret; +} + +static blk_status_t spraid_init_admin_iod(struct request *rq, struct spraid_dev *hdev) +{ + struct spraid_iod *iod = blk_mq_rq_to_pdu(rq); + int nents = blk_rq_nr_phys_segments(rq); + unsigned int size = blk_rq_payload_bytes(rq); + + if (nents > SPRAID_INT_PAGES || size > SPRAID_INT_BYTES(hdev)) { + iod->sg = mempool_alloc(hdev->iod_mempool, GFP_ATOMIC); + if (!iod->sg) + return BLK_STS_RESOURCE; + } else { + iod->sg = iod->inline_sg; + } + + iod->nsge = 0; + iod->use_sgl = false; + iod->npages = -1; + iod->length = size; + iod->sg_drv_mgmt = true; + + return BLK_STS_OK; +} + +static blk_status_t spraid_queue_admin_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + struct spraid_queue *adminq = hctx->driver_data; + struct spraid_dev *hdev = adminq->hdev; + struct request *req = bd->rq; + struct spraid_iod *iod = blk_mq_rq_to_pdu(req); + struct spraid_admin_command cmd; + blk_status_t ret; + + ret = spraid_setup_admin_cmd(req, &cmd); + if (ret) + goto out; + + ret = spraid_init_admin_iod(req, hdev); + if (ret) + goto out; + + if (blk_rq_nr_phys_segments(req)) { + ret = spraid_admin_map_data(hdev, req, &cmd); + if (ret) + goto cleanup_iod; + } + + blk_mq_start_request(req); + spraid_submit_cmd(adminq, &cmd); + return BLK_STS_OK; + +cleanup_iod: + spraid_free_iod_res(hdev, iod); +out: + return ret; +} + +static blk_status_t spraid_error_status(struct request *req) +{ + switch (spraid_admin_req(req)->status & 0x7ff) { + case SPRAID_SC_SUCCESS: + return BLK_STS_OK; + default: + return BLK_STS_IOERR; + } +} + +static void spraid_complete_admin_rq(struct request *req) +{ + struct spraid_iod *iod = blk_mq_rq_to_pdu(req); + struct spraid_dev *hdev = iod->spraidq->hdev; + + if (blk_rq_nr_phys_segments(req)) + spraid_unmap_data(hdev, req); + blk_mq_end_request(req, spraid_error_status(req)); +} + +static int spraid_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) +{ + struct spraid_dev *hdev = data; + struct spraid_queue *adminq = &hdev->queues[0]; + + WARN_ON(hctx_idx != 0); + WARN_ON(hdev->admin_tagset.tags[0] != hctx->tags); + + hctx->driver_data = adminq; + return 0; +} + +static int spraid_admin_init_request(struct blk_mq_tag_set *set, struct request *req, + unsigned int hctx_idx, unsigned int numa_node) +{ + struct spraid_dev *hdev = set->driver_data; + struct spraid_iod *iod = blk_mq_rq_to_pdu(req); + struct spraid_queue *adminq = &hdev->queues[0]; + + WARN_ON(!adminq); + iod->spraidq = adminq; + return 0; +} + +static enum blk_eh_timer_return +spraid_admin_timeout(struct request *req, bool reserved) +{ + struct spraid_iod *iod = blk_mq_rq_to_pdu(req); + struct spraid_queue *spraidq = iod->spraidq; + struct spraid_dev *hdev = spraidq->hdev; + + dev_err(hdev->dev, "Admin cid[%d] qid[%d] timeout\n", + req->tag, spraidq->qid); + + if (spraid_poll_cq(spraidq, req->tag)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, completion polled\n", + req->tag, spraidq->qid); + return BLK_EH_DONE; + } + + spraid_end_admin_request(req, cpu_to_le16(-EINVAL), 0, 0); + return BLK_EH_DONE; +} + +static int spraid_get_ctrl_info(struct spraid_dev *hdev, struct spraid_ctrl_info *ctrl_info) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.get_info.opcode = SPRAID_ADMIN_GET_INFO; + admin_cmd.get_info.type = SPRAID_GET_INFO_CTRL; + + return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, + ctrl_info, sizeof(struct spraid_ctrl_info), 0, 0, 0); +} + +static int spraid_init_ctrl_info(struct spraid_dev *hdev) +{ + int ret; + + hdev->ctrl_info->nd = cpu_to_le32(240); + hdev->ctrl_info->mdts = 8; + hdev->ctrl_info->max_cmds = cpu_to_le16(4096); + hdev->ctrl_info->max_num_sge = cpu_to_le16(128); + hdev->ctrl_info->max_channel = cpu_to_le16(4); + hdev->ctrl_info->max_tgt_id = cpu_to_le32(3239); + hdev->ctrl_info->max_lun = cpu_to_le16(2); + + ret = spraid_get_ctrl_info(hdev, hdev->ctrl_info); + if (ret) + dev_err(hdev->dev, "get controller info failed: %d\n", ret); + + dev_info(hdev->dev, "[%s]nd = %d\n", __func__, hdev->ctrl_info->nd); + dev_info(hdev->dev, "[%s]max_cmd = %d\n", __func__, hdev->ctrl_info->max_cmds); + dev_info(hdev->dev, "[%s]max_channel = %d\n", __func__, hdev->ctrl_info->max_channel); + dev_info(hdev->dev, "[%s]max_tgt_id = %d\n", __func__, hdev->ctrl_info->max_tgt_id); + dev_info(hdev->dev, "[%s]max_lun = %d\n", __func__, hdev->ctrl_info->max_lun); + dev_info(hdev->dev, "[%s]max_num_sge = %d\n", __func__, hdev->ctrl_info->max_num_sge); + dev_info(hdev->dev, "[%s]lun_num_boot = %d\n", __func__, hdev->ctrl_info->lun_num_in_boot); + dev_info(hdev->dev, "[%s]mdts = %d\n", __func__, hdev->ctrl_info->mdts); + dev_info(hdev->dev, "[%s]acl = %d\n", __func__, hdev->ctrl_info->acl); + dev_info(hdev->dev, "[%s]aer1 = %d\n", __func__, hdev->ctrl_info->aerl); + dev_info(hdev->dev, "[%s]card_type = %d\n", __func__, hdev->ctrl_info->card_type); + dev_info(hdev->dev, "[%s]rtd3e = %d\n", __func__, hdev->ctrl_info->rtd3e); + dev_info(hdev->dev, "[%s]sn = %s\n", __func__, hdev->ctrl_info->sn); + dev_info(hdev->dev, "[%s]fr = %s\n", __func__, hdev->ctrl_info->fr); + + return 0; +} + +#define SPRAID_MAX_ADMIN_PAYLOAD_SIZE BIT(16) +static int spraid_alloc_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + u16 max_sge = le16_to_cpu(hdev->ctrl_info->max_num_sge); + size_t alloc_size; + + alloc_size = spraid_iod_ext_size(hdev, SPRAID_MAX_ADMIN_PAYLOAD_SIZE, + max_sge, true, false); + if (alloc_size > PAGE_SIZE) + dev_warn(hdev->dev, "It is unreasonable for sg allocation more than one page\n"); + hdev->iod_mempool = mempool_create_node(1, mempool_kmalloc, mempool_kfree, + (void *)alloc_size, GFP_KERNEL, hdev->numa_node); + if (!hdev->iod_mempool) { + dev_err(hdev->dev, "Create iod extension memory pool failed\n"); + return -ENOMEM; + } + + return 0; +} + +static void spraid_free_iod_ext_mem_pool(struct spraid_dev *hdev) +{ + mempool_destroy(hdev->iod_mempool); +} + +static int spraid_submit_user_cmd(struct request_queue *q, struct spraid_admin_command *cmd, + void __user *ubuffer, unsigned int bufflen, u32 *result, + unsigned int timeout) +{ + struct request *req; + struct bio *bio = NULL; + int ret; + + req = spraid_alloc_admin_request(q, cmd, 0); + if (IS_ERR(req)) + return PTR_ERR(req); + + req->timeout = timeout ? timeout : ADMIN_TIMEOUT; + spraid_admin_req(req)->flags |= SPRAID_REQ_USERCMD; + + if (ubuffer && bufflen) { + ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, GFP_KERNEL); + if (ret) + goto out; + bio = req->bio; + } + blk_execute_rq(req->q, NULL, req, 0); + if (spraid_admin_req(req)->flags & SPRAID_REQ_CANCELLED) + ret = -EINTR; + else + ret = spraid_admin_req(req)->status; + if (result) { + result[0] = spraid_admin_req(req)->result0; + result[1] = spraid_admin_req(req)->result1; + } + if (bio) + blk_rq_unmap_user(bio); +out: + blk_mq_free_request(req); + return ret; +} + +static int spraid_user_admin_cmd(struct spraid_dev *hdev, + struct spraid_passthru_common_cmd __user *ucmd) +{ + struct spraid_passthru_common_cmd cmd; + struct spraid_admin_command admin_cmd; + u32 timeout = 0; + int status; + + if (!capable(CAP_SYS_ADMIN)) { + dev_err(hdev->dev, "Current user hasn't administrator right, reject service\n"); + return -EACCES; + } + + if (copy_from_user(&cmd, ucmd, sizeof(cmd))) { + dev_err(hdev->dev, "Copy command from user space to kernel space failed\n"); + return -EFAULT; + } + + if (cmd.flags) { + dev_err(hdev->dev, "Invalid flags in user command\n"); + return -EINVAL; + } + + dev_info(hdev->dev, "user_admin_cmd opcode: 0x%x, subopcode: 0x%x\n", + cmd.opcode, cmd.cdw2 & 0x7ff); + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.common.opcode = cmd.opcode; + admin_cmd.common.flags = cmd.flags; + admin_cmd.common.hdid = cpu_to_le32(cmd.nsid); + admin_cmd.common.cdw2[0] = cpu_to_le32(cmd.cdw2); + admin_cmd.common.cdw2[1] = cpu_to_le32(cmd.cdw3); + admin_cmd.common.cdw10 = cpu_to_le32(cmd.cdw10); + admin_cmd.common.cdw11 = cpu_to_le32(cmd.cdw11); + admin_cmd.common.cdw12 = cpu_to_le32(cmd.cdw12); + admin_cmd.common.cdw13 = cpu_to_le32(cmd.cdw13); + admin_cmd.common.cdw14 = cpu_to_le32(cmd.cdw14); + admin_cmd.common.cdw15 = cpu_to_le32(cmd.cdw15); + + if (cmd.timeout_ms) + timeout = msecs_to_jiffies(cmd.timeout_ms); + + status = spraid_submit_user_cmd(hdev->admin_q, &admin_cmd, + (void __user *)(uintptr_t)cmd.addr, cmd.info_1.data_len, + &cmd.result0, timeout); + + dev_info(hdev->dev, "user_admin_cmd status: 0x%x, result0: 0x%x, result1: 0x%x\n", + status, cmd.result0, cmd.result1); + + if (status >= 0) { + if (put_user(cmd.result0, &ucmd->result0)) + return -EFAULT; + if (put_user(cmd.result1, &ucmd->result1)) + return -EFAULT; + } + + return status; +} + +static int spraid_alloc_ioq_ptcmds(struct spraid_dev *hdev) +{ + int i; + int ptnum = SPRAID_NR_IOQ_PTCMDS; + + INIT_LIST_HEAD(&hdev->ioq_pt_list); + spin_lock_init(&hdev->ioq_pt_lock); + + hdev->ioq_ptcmds = kcalloc_node(ptnum, sizeof(struct spraid_ioq_ptcmd), + GFP_KERNEL, hdev->numa_node); + + if (!hdev->ioq_ptcmds) { + dev_err(hdev->dev, "Alloc ioq_ptcmds failed\n"); + return -ENOMEM; + } + + for (i = 0; i < ptnum; i++) { + hdev->ioq_ptcmds[i].qid = i / SPRAID_PTCMDS_PERQ + 1; + hdev->ioq_ptcmds[i].cid = i % SPRAID_PTCMDS_PERQ + SPRAID_IO_BLK_MQ_DEPTH; + list_add_tail(&(hdev->ioq_ptcmds[i].list), &hdev->ioq_pt_list); + } + + dev_info(hdev->dev, "Alloc ioq_ptcmds success, ptnum[%d]\n", ptnum); + + return 0; +} + +static struct spraid_ioq_ptcmd *spraid_get_ioq_ptcmd(struct spraid_dev *hdev) +{ + struct spraid_ioq_ptcmd *cmd = NULL; + unsigned long flags; + + spin_lock_irqsave(&hdev->ioq_pt_lock, flags); + if (list_empty(&hdev->ioq_pt_list)) { + spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); + dev_err(hdev->dev, "err, ioq ptcmd list empty\n"); + return NULL; + } + cmd = list_entry((&hdev->ioq_pt_list)->next, struct spraid_ioq_ptcmd, list); + list_del_init(&cmd->list); + spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); + + WRITE_ONCE(cmd->state, SPRAID_CMD_IDLE); + + return cmd; +} + +static void spraid_put_ioq_ptcmd(struct spraid_dev *hdev, struct spraid_ioq_ptcmd *cmd) +{ + unsigned long flags; + + spin_lock_irqsave(&hdev->ioq_pt_lock, flags); + list_add(&cmd->list, (&hdev->ioq_pt_list)->next); + spin_unlock_irqrestore(&hdev->ioq_pt_lock, flags); +} + +static int spraid_submit_ioq_sync_cmd(struct spraid_dev *hdev, struct spraid_ioq_command *cmd, + u32 *result, void **sense, u32 timeout) +{ + struct spraid_queue *ioq; + int ret; + dma_addr_t sense_dma; + struct spraid_ioq_ptcmd *pt_cmd = spraid_get_ioq_ptcmd(hdev); + + *sense = NULL; + + if (!pt_cmd) + return -EFAULT; + + dev_info(hdev->dev, "[%s] ptcmd, cid[%d], qid[%d]\n", __func__, pt_cmd->cid, pt_cmd->qid); + + init_completion(&pt_cmd->cmd_done); + + ioq = &hdev->queues[pt_cmd->qid]; + ret = pt_cmd->cid * SCSI_SENSE_BUFFERSIZE; + pt_cmd->priv = ioq->sense + ret; + sense_dma = ioq->sense_dma_addr + ret; + + cmd->common.sense_addr = cpu_to_le64(sense_dma); + cmd->common.sense_len = cpu_to_le16(SCSI_SENSE_BUFFERSIZE); + cmd->common.command_id = pt_cmd->cid; + + spraid_submit_cmd(ioq, cmd); + + if (!wait_for_completion_timeout(&pt_cmd->cmd_done, timeout)) { + dev_err(hdev->dev, "[%s] cid[%d], qid[%d] timeout\n", + __func__, pt_cmd->cid, pt_cmd->qid); + WRITE_ONCE(pt_cmd->state, SPRAID_CMD_TIMEOUT); + return -EINVAL; + } + + if (result) { + result[0] = pt_cmd->result0; + result[1] = pt_cmd->result1; + } + + if ((pt_cmd->status & 0x17f) == 0x101) + *sense = pt_cmd->priv; + + return pt_cmd->status; +} + +static int spraid_user_ioq_cmd(struct spraid_dev *hdev, + struct spraid_ioq_passthru_cmd __user *ucmd) +{ + struct spraid_ioq_passthru_cmd cmd; + struct spraid_ioq_command ioq_cmd; + u32 timeout = 0; + int status = 0; + u8 *data_ptr = NULL; + dma_addr_t data_dma; + enum dma_data_direction dma_dir = DMA_NONE; + void *sense = NULL; + + if (!capable(CAP_SYS_ADMIN)) { + dev_err(hdev->dev, "Current user hasn't administrator right, reject service\n"); + return -EACCES; + } + + if (copy_from_user(&cmd, ucmd, sizeof(cmd))) { + dev_err(hdev->dev, "Copy command from user space to kernel space failed\n"); + return -EFAULT; + } + + if (cmd.data_len > PAGE_SIZE) { + dev_err(hdev->dev, "[%s] data len bigger than 4k\n", __func__); + return -EFAULT; + } + + dev_info(hdev->dev, "[%s] opcode: 0x%x, subopcode: 0x%x, datalen: %d\n", + __func__, cmd.opcode, cmd.info_1.subopcode, cmd.data_len); + + if (cmd.addr && cmd.data_len) { + data_ptr = dma_alloc_coherent(hdev->dev, PAGE_SIZE, &data_dma, GFP_KERNEL); + if (!data_ptr) + return -ENOMEM; + + dma_dir = (cmd.opcode & 1) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + } + + if (dma_dir == DMA_TO_DEVICE) { + if (copy_from_user(data_ptr, (void __user *)(uintptr_t)cmd.addr, cmd.data_len)) { + dev_err(hdev->dev, "[%s] copy user data failed\n", __func__); + status = -EFAULT; + goto free_dma_mem; + } + } + + memset(&ioq_cmd, 0, sizeof(ioq_cmd)); + ioq_cmd.common.opcode = cmd.opcode; + ioq_cmd.common.flags = cmd.flags; + ioq_cmd.common.hdid = cpu_to_le32(cmd.nsid); + ioq_cmd.common.sense_len = cpu_to_le16(cmd.info_0.res_sense_len); + ioq_cmd.common.cdb_len = cmd.info_0.cdb_len; + ioq_cmd.common.rsvd2 = cmd.info_0.rsvd0; + ioq_cmd.common.cdw3[0] = cpu_to_le32(cmd.cdw3); + ioq_cmd.common.cdw3[1] = cpu_to_le32(cmd.cdw4); + ioq_cmd.common.cdw3[2] = cpu_to_le32(cmd.cdw5); + ioq_cmd.common.dptr.prp1 = cpu_to_le64(data_dma); + + ioq_cmd.common.cdw10[0] = cpu_to_le32(cmd.cdw10); + ioq_cmd.common.cdw10[1] = cpu_to_le32(cmd.cdw11); + ioq_cmd.common.cdw10[2] = cpu_to_le32(cmd.cdw12); + ioq_cmd.common.cdw10[3] = cpu_to_le32(cmd.cdw13); + ioq_cmd.common.cdw10[4] = cpu_to_le32(cmd.cdw14); + ioq_cmd.common.cdw10[5] = cpu_to_le32(cmd.data_len); + + memcpy(ioq_cmd.common.cdb, &cmd.cdw16, cmd.info_0.cdb_len); + + ioq_cmd.common.cdw26[0] = cpu_to_le32(cmd.cdw26[0]); + ioq_cmd.common.cdw26[1] = cpu_to_le32(cmd.cdw26[1]); + ioq_cmd.common.cdw26[2] = cpu_to_le32(cmd.cdw26[2]); + ioq_cmd.common.cdw26[3] = cpu_to_le32(cmd.cdw26[3]); + + if (cmd.timeout_ms) + timeout = msecs_to_jiffies(cmd.timeout_ms); + timeout = timeout ? timeout : ADMIN_TIMEOUT; + + status = spraid_submit_ioq_sync_cmd(hdev, &ioq_cmd, &cmd.result0, &sense, timeout); + + if (status >= 0) { + if (put_user(cmd.result0, &ucmd->result0)) { + status = -EFAULT; + goto free_dma_mem; + } + if (put_user(cmd.result1, &ucmd->result1)) { + status = -EFAULT; + goto free_dma_mem; + } + if (dma_dir == DMA_FROM_DEVICE && + copy_to_user((void __user *)(uintptr_t)cmd.addr, data_ptr, cmd.data_len)) { + status = -EFAULT; + goto free_dma_mem; + } + } + + if (sense) { + if (copy_to_user((void *__user *)(uintptr_t)cmd.sense_addr, + sense, cmd.info_0.res_sense_len)) { + status = -EFAULT; + goto free_dma_mem; + } + } + +free_dma_mem: + if (data_ptr) + dma_free_coherent(hdev->dev, PAGE_SIZE, data_ptr, data_dma); + + return status; + +} + +static int spraid_reset_work_sync(struct spraid_dev *hdev); + +static int spraid_user_reset_cmd(struct spraid_dev *hdev) +{ + int ret; + + dev_info(hdev->dev, "[%s] start user reset cmd\n", __func__); + ret = spraid_reset_work_sync(hdev); + dev_info(hdev->dev, "[%s] stop user reset cmd[%d]\n", __func__, ret); + + return ret; +} + +static int hdev_open(struct inode *inode, struct file *file) +{ + struct spraid_dev *hdev = + container_of(inode->i_cdev, struct spraid_dev, cdev); + file->private_data = hdev; + return 0; +} + +static long hdev_ioctl(struct file *file, u32 cmd, unsigned long arg) +{ + struct spraid_dev *hdev = file->private_data; + void __user *argp = (void __user *)arg; + + switch (cmd) { + case SPRAID_IOCTL_ADMIN_CMD: + return spraid_user_admin_cmd(hdev, argp); + case SPRAID_IOCTL_IOQ_CMD: + return spraid_user_ioq_cmd(hdev, argp); + case SPRAID_IOCTL_RESET_CMD: + return spraid_user_reset_cmd(hdev); + default: + return -ENOTTY; + } +} + +static const struct file_operations spraid_dev_fops = { + .owner = THIS_MODULE, + .open = hdev_open, + .unlocked_ioctl = hdev_ioctl, + .compat_ioctl = hdev_ioctl, +}; + +static int spraid_create_cdev(struct spraid_dev *hdev) +{ + int ret; + + device_initialize(&hdev->ctrl_device); + hdev->ctrl_device.devt = MKDEV(MAJOR(spraid_chr_devt), hdev->instance); + hdev->ctrl_device.class = spraid_class; + hdev->ctrl_device.parent = hdev->dev; + dev_set_drvdata(&hdev->ctrl_device, hdev); + ret = dev_set_name(&hdev->ctrl_device, "spraid%d", hdev->instance); + if (ret) + return ret; + cdev_init(&hdev->cdev, &spraid_dev_fops); + hdev->cdev.owner = THIS_MODULE; + ret = cdev_device_add(&hdev->cdev, &hdev->ctrl_device); + if (ret) { + dev_err(hdev->dev, "Add cdev failed, ret: %d", ret); + put_device(&hdev->ctrl_device); + kfree_const(hdev->ctrl_device.kobj.name); + return ret; + } + + return 0; +} + +static inline void spraid_remove_cdev(struct spraid_dev *hdev) +{ + cdev_device_del(&hdev->cdev, &hdev->ctrl_device); +} + +static const struct blk_mq_ops spraid_admin_mq_ops = { + .queue_rq = spraid_queue_admin_rq, + .complete = spraid_complete_admin_rq, + .init_hctx = spraid_admin_init_hctx, + .init_request = spraid_admin_init_request, + .timeout = spraid_admin_timeout, +}; + +static void spraid_remove_admin_tagset(struct spraid_dev *hdev) +{ + if (hdev->admin_q && !blk_queue_dying(hdev->admin_q)) { + blk_mq_unquiesce_queue(hdev->admin_q); + blk_cleanup_queue(hdev->admin_q); + blk_mq_free_tag_set(&hdev->admin_tagset); + } +} + +static int spraid_alloc_admin_tags(struct spraid_dev *hdev) +{ + if (!hdev->admin_q) { + hdev->admin_tagset.ops = &spraid_admin_mq_ops; + hdev->admin_tagset.nr_hw_queues = 1; + + hdev->admin_tagset.queue_depth = SPRAID_AQ_MQ_TAG_DEPTH; + hdev->admin_tagset.timeout = ADMIN_TIMEOUT; + hdev->admin_tagset.numa_node = hdev->numa_node; + hdev->admin_tagset.cmd_size = + spraid_cmd_size(hdev, true, false); + hdev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; + hdev->admin_tagset.driver_data = hdev; + + if (blk_mq_alloc_tag_set(&hdev->admin_tagset)) { + dev_err(hdev->dev, "Allocate admin tagset failed\n"); + return -ENOMEM; + } + + hdev->admin_q = blk_mq_init_queue(&hdev->admin_tagset); + if (IS_ERR(hdev->admin_q)) { + dev_err(hdev->dev, "Initialize admin request queue failed\n"); + blk_mq_free_tag_set(&hdev->admin_tagset); + return -ENOMEM; + } + if (!blk_get_queue(hdev->admin_q)) { + dev_err(hdev->dev, "Get admin request queue failed\n"); + spraid_remove_admin_tagset(hdev); + hdev->admin_q = NULL; + return -ENODEV; + } + } else { + blk_mq_unquiesce_queue(hdev->admin_q); + } + return 0; +} + +static bool spraid_check_scmd_completed(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_queue *spraidq; + u16 hwq, cid; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + spraidq = &hdev->queues[hwq]; + if (READ_ONCE(iod->state) == SPRAID_CMD_COMPLETE || spraid_poll_cq(spraidq, cid)) { + dev_warn(hdev->dev, "cid[%d], qid[%d] has been completed\n", + cid, spraidq->qid); + return true; + } + return false; +} + +static enum blk_eh_timer_return spraid_scmd_timeout(struct scsi_cmnd *scmd) +{ + struct spraid_iod *iod = scsi_cmd_priv(scmd); + unsigned int timeout = scmd->device->request_queue->rq_timeout; + + if (spraid_check_scmd_completed(scmd)) + goto out; + + if (time_after(jiffies, scmd->jiffies_at_alloc + timeout)) { + if (cmpxchg(&iod->state, SPRAID_CMD_IN_FLIGHT, SPRAID_CMD_TIMEOUT) == + SPRAID_CMD_IN_FLIGHT) { + return BLK_EH_DONE; + } + } +out: + return BLK_EH_RESET_TIMER; +} + +/* send abort command by admin queue temporary */ +static int spraid_send_abort_cmd(struct spraid_dev *hdev, u32 hdid, u16 qid, u16 cid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.abort.opcode = SPRAID_ADMIN_ABORT_CMD; + admin_cmd.abort.hdid = cpu_to_le32(hdid); + admin_cmd.abort.sqid = cpu_to_le16(qid); + admin_cmd.abort.cid = cpu_to_le16(cid); + + return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, + NULL, 0, 0, 0, 0); +} + +/* send reset command by admin quueue temporary */ +static int spraid_send_reset_cmd(struct spraid_dev *hdev, int type, u32 hdid) +{ + struct spraid_admin_command admin_cmd; + + memset(&admin_cmd, 0, sizeof(admin_cmd)); + admin_cmd.reset.opcode = SPRAID_ADMIN_RESET; + admin_cmd.reset.hdid = cpu_to_le32(hdid); + admin_cmd.reset.type = type; + + return spraid_submit_admin_sync_cmd(hdev->admin_q, &admin_cmd, NULL, + NULL, 0, 0, 0, 0); +} + +static bool spraid_change_host_state(struct spraid_dev *hdev, enum spraid_state newstate) +{ + unsigned long flags; + enum spraid_state oldstate; + bool change = false; + + spin_lock_irqsave(&hdev->state_lock, flags); + + oldstate = hdev->state; + switch (newstate) { + case SPRAID_LIVE: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + case SPRAID_RESETTING: + switch (oldstate) { + case SPRAID_LIVE: + change = true; + break; + default: + break; + } + break; + case SPRAID_DELETING: + if (oldstate != SPRAID_DELETING) + change = true; + break; + case SPRAID_DEAD: + switch (oldstate) { + case SPRAID_NEW: + case SPRAID_LIVE: + case SPRAID_RESETTING: + change = true; + break; + default: + break; + } + break; + default: + break; + } + if (change) + hdev->state = newstate; + spin_unlock_irqrestore(&hdev->state_lock, flags); + + dev_info(hdev->dev, "[%s][%d]->[%d], change[%d]\n", __func__, oldstate, newstate, change); + + return change; +} + +static void spraid_back_fault_cqe(struct spraid_queue *ioq, struct spraid_completion *cqe) +{ + struct spraid_dev *hdev = ioq->hdev; + struct blk_mq_tags *tags; + struct scsi_cmnd *scmd; + struct spraid_iod *iod; + struct request *req; + + tags = hdev->shost->tag_set.tags[ioq->qid - 1]; + req = blk_mq_tag_to_rq(tags, cqe->cmd_id); + if (unlikely(!req || !blk_mq_request_started(req))) + return; + + scmd = blk_mq_rq_to_pdu(req); + iod = scsi_cmd_priv(scmd); + + set_host_byte(scmd, DID_NO_CONNECT); + if (iod->nsge) + scsi_dma_unmap(scmd); + spraid_free_iod_res(hdev, iod); + scmd->scsi_done(scmd); + dev_warn(hdev->dev, "Back fault CQE, cid[%d], qid[%d]\n", + cqe->cmd_id, ioq->qid); +} + +static void spraid_back_all_io(struct spraid_dev *hdev) +{ + int i, j; + struct spraid_queue *ioq; + struct spraid_completion cqe = { 0 }; + + for (i = 1; i <= hdev->shost->nr_hw_queues; i++) { + ioq = &hdev->queues[i]; + for (j = 0; j < hdev->shost->can_queue; j++) { + cqe.cmd_id = j; + spraid_back_fault_cqe(ioq, &cqe); + } + } +} + +static void spraid_dev_disable(struct spraid_dev *hdev, bool shutdown) +{ + struct spraid_queue *adminq = &hdev->queues[0]; + u16 start, end; + unsigned long timeout = jiffies + 600 * HZ; + + if (pci_device_is_present(hdev->pdev)) { + if (shutdown) + spraid_shutdown_ctrl(hdev); + else + spraid_disable_ctrl(hdev); + } + + while (!time_after(jiffies, timeout)) { + if (!pci_device_is_present(hdev->pdev)) { + dev_info(hdev->dev, "[%s] pci_device not present, skip wait\n", __func__); + break; + } + if (!spraid_wait_ready(hdev, hdev->cap, false)) { + dev_info(hdev->dev, "[%s] wait ready success after reset\n", __func__); + break; + } + dev_info(hdev->dev, "[%s] waiting csts_rdy ready\n", __func__); + } + + if (hdev->queue_count == 0) { + dev_err(hdev->dev, "[%s] warn, queue has been delete\n", __func__); + return; + } + + spin_lock_irq(&adminq->cq_lock); + spraid_process_cq(adminq, &start, &end, -1); + spin_unlock_irq(&adminq->cq_lock); + spraid_complete_cqes(adminq, start, end); + + spraid_pci_disable(hdev); + + spraid_back_all_io(hdev); +} + +static void spraid_reset_work(struct work_struct *work) +{ + int ret; + struct spraid_dev *hdev = container_of(work, struct spraid_dev, reset_work); + + if (hdev->state != SPRAID_RESETTING) { + dev_err(hdev->dev, "[%s] err, host is not reset state\n", __func__); + return; + } + + dev_info(hdev->dev, "[%s] enter host reset\n", __func__); + + if (hdev->ctrl_config & SPRAID_CC_ENABLE) { + dev_info(hdev->dev, "[%s] start dev_disable\n", __func__); + spraid_dev_disable(hdev, false); + } + + ret = spraid_pci_enable(hdev); + if (ret) + goto out; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_alloc_admin_tags(hdev); + if (ret) + goto pci_disable; + + ret = spraid_setup_io_queues(hdev); + if (ret || hdev->online_queues <= hdev->shost->nr_hw_queues) + goto pci_disable; + + spraid_change_host_state(hdev, SPRAID_LIVE); + + spraid_send_aen(hdev); + + return; + +pci_disable: + spraid_pci_disable(hdev); +out: + spraid_change_host_state(hdev, SPRAID_DEAD); + dev_err(hdev->dev, "[%s] err, host reset failed\n", __func__); +} + +static int spraid_reset_work_sync(struct spraid_dev *hdev) +{ + if (!spraid_change_host_state(hdev, SPRAID_RESETTING)) { + dev_info(hdev->dev, "[%s] can't change to reset state\n", __func__); + return -EBUSY; + } + + if (!queue_work(spraid_wq, &hdev->reset_work)) { + dev_err(hdev->dev, "[%s] err, host is already in reset state\n", __func__); + return -EBUSY; + } + + flush_work(&hdev->reset_work); + if (hdev->state != SPRAID_LIVE) + return -ENODEV; + + return 0; +} + +static int spraid_wait_abnl_cmd_done(struct spraid_iod *iod) +{ + u16 times = 0; + + do { + if (READ_ONCE(iod->state) == SPRAID_CMD_TMO_COMPLETE) + break; + msleep(500); + times++; + } while (times <= SPRAID_WAIT_ABNL_CMD_TIMEOUT); + + /* wait command completion timeout after abort/reset success */ + if (times >= SPRAID_WAIT_ABNL_CMD_TIMEOUT) + return -ETIMEDOUT; + + return 0; +} + +static int spraid_abort_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (!spraid_wait_abnl_cmd_done(iod) || spraid_check_scmd_completed(scmd) || + hdev->state != SPRAID_LIVE) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, aborting\n", cid, hwq); + ret = spraid_send_abort_cmd(hdev, hostdata->hdid, hwq, cid); + if (ret != ADMIN_ERR_TIMEOUT) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed, not found\n", cid, hwq); + return FAILED; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort succ\n", cid, hwq); + return SUCCESS; + } + dev_warn(hdev->dev, "cid[%d] qid[%d] abort failed, timeout\n", cid, hwq); + return FAILED; +} + +static int spraid_tgt_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (!spraid_wait_abnl_cmd_done(iod) || spraid_check_scmd_completed(scmd) || + hdev->state != SPRAID_LIVE) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, target reset\n", cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_TARGET, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, "cid[%d] qid[%d]target reset failed, not found\n", + cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] target reset success\n", cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] target reset failed\n", cid, hwq, ret); + return FAILED; +} + +static int spraid_bus_reset_handler(struct scsi_cmnd *scmd) +{ + struct spraid_dev *hdev = shost_priv(scmd->device->host); + struct spraid_iod *iod = scsi_cmd_priv(scmd); + struct spraid_sdev_hostdata *hostdata; + u16 hwq, cid; + int ret; + + scsi_print_command(scmd); + + if (!spraid_wait_abnl_cmd_done(iod) || spraid_check_scmd_completed(scmd) || + hdev->state != SPRAID_LIVE) + return SUCCESS; + + hostdata = scmd->device->hostdata; + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + + dev_warn(hdev->dev, "cid[%d] qid[%d] timeout, bus reset\n", cid, hwq); + ret = spraid_send_reset_cmd(hdev, SPRAID_RESET_BUS, hostdata->hdid); + if (ret == 0) { + ret = spraid_wait_abnl_cmd_done(iod); + if (ret) { + dev_warn(hdev->dev, "cid[%d] qid[%d] bus reset failed, not found\n", + cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] bus reset succ\n", cid, hwq); + return SUCCESS; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] ret[%d] bus reset failed\n", cid, hwq, ret); + return FAILED; +} + +static int spraid_shost_reset_handler(struct scsi_cmnd *scmd) +{ + u16 hwq, cid; + struct spraid_dev *hdev = shost_priv(scmd->device->host); + + scsi_print_command(scmd); + if (spraid_check_scmd_completed(scmd) || hdev->state != SPRAID_LIVE) + return SUCCESS; + + spraid_get_tag_from_scmd(scmd, &hwq, &cid); + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset\n", cid, hwq); + + if (spraid_reset_work_sync(hdev)) { + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset failed\n", cid, hwq); + return FAILED; + } + + dev_warn(hdev->dev, "cid[%d] qid[%d] host reset success\n", cid, hwq); + + return SUCCESS; +} + +static ssize_t csts_pp_show(struct device *cdev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_PP_MASK); + ret >>= SPRAID_CSTS_PP_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_shst_show(struct device *cdev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_SHST_MASK); + ret >>= SPRAID_CSTS_SHST_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_cfs_show(struct device *cdev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) { + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_CFS_MASK); + ret >>= SPRAID_CSTS_CFS_SHIFT; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t csts_rdy_show(struct device *cdev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + int ret = -1; + + if (pci_device_is_present(hdev->pdev)) + ret = (readl(hdev->bar + SPRAID_REG_CSTS) & SPRAID_CSTS_RDY); + + return snprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t fw_version_show(struct device *cdev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(cdev); + struct spraid_dev *hdev = shost_priv(shost); + + return snprintf(buf, sizeof(hdev->ctrl_info->fr), "%s\n", hdev->ctrl_info->fr); +} + +static DEVICE_ATTR_RO(csts_pp); +static DEVICE_ATTR_RO(csts_shst); +static DEVICE_ATTR_RO(csts_cfs); +static DEVICE_ATTR_RO(csts_rdy); +static DEVICE_ATTR_RO(fw_version); + +static struct device_attribute *spraid_host_attrs[] = { + &dev_attr_csts_pp, + &dev_attr_csts_shst, + &dev_attr_csts_cfs, + &dev_attr_csts_rdy, + &dev_attr_fw_version, + NULL, +}; + +static struct scsi_host_template spraid_driver_template = { + .module = THIS_MODULE, + .name = "Ramaxel Logic spraid driver", + .proc_name = "spraid", + .queuecommand = spraid_queue_command, + .slave_alloc = spraid_slave_alloc, + .slave_destroy = spraid_slave_destroy, + .slave_configure = spraid_slave_configure, + .eh_timed_out = spraid_scmd_timeout, + .eh_abort_handler = spraid_abort_handler, + .eh_target_reset_handler = spraid_tgt_reset_handler, + .eh_bus_reset_handler = spraid_bus_reset_handler, + .eh_host_reset_handler = spraid_shost_reset_handler, + .change_queue_depth = scsi_change_queue_depth, + .host_tagset = 1, + .this_id = -1, + .shost_attrs = spraid_host_attrs, +}; + +static void spraid_shutdown(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + + spraid_remove_io_queues(hdev); + spraid_disable_admin_queue(hdev, true); +} + +static int spraid_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct spraid_dev *hdev; + struct Scsi_Host *shost; + int node, ret; + + shost = scsi_host_alloc(&spraid_driver_template, sizeof(*hdev)); + if (!shost) { + dev_err(&pdev->dev, "Failed to allocate scsi host\n"); + return -ENOMEM; + } + hdev = shost_priv(shost); + hdev->pdev = pdev; + hdev->dev = get_device(&pdev->dev); + + node = dev_to_node(hdev->dev); + if (node == NUMA_NO_NODE) { + node = first_memory_node; + set_dev_node(hdev->dev, node); + } + hdev->numa_node = node; + hdev->shost = shost; + pci_set_drvdata(pdev, hdev); + + ret = spraid_dev_map(hdev); + if (ret) + goto put_dev; + + init_rwsem(&hdev->devices_rwsem); + INIT_WORK(&hdev->aen_work, spraid_async_event_work); + INIT_WORK(&hdev->scan_work, spraid_scan_work); + INIT_WORK(&hdev->timesyn_work, spraid_timesyn_work); + INIT_WORK(&hdev->reset_work, spraid_reset_work); + spin_lock_init(&hdev->state_lock); + + ret = spraid_alloc_resources(hdev); + if (ret) + goto dev_unmap; + + ret = spraid_pci_enable(hdev); + if (ret) + goto resources_free; + + ret = spraid_setup_admin_queue(hdev); + if (ret) + goto pci_disable; + + ret = spraid_alloc_admin_tags(hdev); + if (ret) + goto disable_admin_q; + + ret = spraid_init_ctrl_info(hdev); + if (ret) + goto free_admin_tagset; + + ret = spraid_alloc_iod_ext_mem_pool(hdev); + if (ret) + goto free_admin_tagset; + + ret = spraid_setup_io_queues(hdev); + if (ret) + goto free_iod_mempool; + + spraid_shost_init(hdev); + + ret = scsi_add_host(hdev->shost, hdev->dev); + if (ret) { + dev_err(hdev->dev, "Add shost to system failed, ret: %d\n", + ret); + goto remove_io_queues; + } + + ret = spraid_create_cdev(hdev); + if (ret) + goto remove_io_queues; + + if (hdev->online_queues == SPRAID_ADMIN_QUEUE_NUM) { + dev_warn(hdev->dev, "warn only admin queue can be used\n"); + return 0; + } + + hdev->state = SPRAID_LIVE; + + spraid_send_aen(hdev); + + ret = spraid_dev_list_init(hdev); + if (ret) + goto remove_cdev; + + ret = spraid_configure_timestamp(hdev); + if (ret) + dev_warn(hdev->dev, "init set timestamp failed\n"); + + ret = spraid_alloc_ioq_ptcmds(hdev); + if (ret) + goto remove_cdev; + + scsi_scan_host(hdev->shost); + + return 0; + +remove_cdev: + spraid_remove_cdev(hdev); +remove_io_queues: + spraid_remove_io_queues(hdev); +free_iod_mempool: + spraid_free_iod_ext_mem_pool(hdev); +free_admin_tagset: + spraid_remove_admin_tagset(hdev); +disable_admin_q: + spraid_disable_admin_queue(hdev, false); +pci_disable: + spraid_pci_disable(hdev); +resources_free: + spraid_free_resources(hdev); +dev_unmap: + spraid_dev_unmap(hdev); +put_dev: + put_device(hdev->dev); + scsi_host_put(shost); + + return -ENODEV; +} + +static void spraid_remove(struct pci_dev *pdev) +{ + struct spraid_dev *hdev = pci_get_drvdata(pdev); + struct Scsi_Host *shost = hdev->shost; + + dev_info(hdev->dev, "enter spraid remove\n"); + + spraid_change_host_state(hdev, SPRAID_DELETING); + + if (!pci_device_is_present(pdev)) { + scsi_block_requests(shost); + spraid_back_all_io(hdev); + scsi_unblock_requests(shost); + } + + flush_work(&hdev->reset_work); + scsi_remove_host(shost); + + kfree(hdev->ioq_ptcmds); + kfree(hdev->devices); + spraid_remove_cdev(hdev); + spraid_remove_io_queues(hdev); + spraid_free_iod_ext_mem_pool(hdev); + spraid_remove_admin_tagset(hdev); + spraid_disable_admin_queue(hdev, false); + spraid_pci_disable(hdev); + spraid_free_resources(hdev); + spraid_dev_unmap(hdev); + put_device(hdev->dev); + scsi_host_put(shost); + + dev_info(hdev->dev, "exit spraid remove\n"); +} + +static const struct pci_device_id spraid_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_HAB_DID) }, + { PCI_DEVICE(PCI_VENDOR_ID_RAMAXEL_LOGIC, SPRAID_SERVER_DEVICE_RAID_DID) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, spraid_id_table); + +static struct pci_driver spraid_driver = { + .name = "spraid", + .id_table = spraid_id_table, + .probe = spraid_probe, + .remove = spraid_remove, + .shutdown = spraid_shutdown, +}; + +static int __init spraid_init(void) +{ + int ret; + + spraid_wq = alloc_workqueue("spraid-wq", WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + if (!spraid_wq) + return -ENOMEM; + + ret = alloc_chrdev_region(&spraid_chr_devt, 0, SPRAID_MINORS, "spraid"); + if (ret < 0) + goto destroy_wq; + + spraid_class = class_create(THIS_MODULE, "spraid"); + if (IS_ERR(spraid_class)) { + ret = PTR_ERR(spraid_class); + goto unregister_chrdev; + } + + ret = pci_register_driver(&spraid_driver); + if (ret < 0) + goto destroy_class; + + return 0; + +destroy_class: + class_destroy(spraid_class); +unregister_chrdev: + unregister_chrdev_region(spraid_chr_devt, SPRAID_MINORS); +destroy_wq: + destroy_workqueue(spraid_wq); + + return ret; +} + +static void __exit spraid_exit(void) +{ + pci_unregister_driver(&spraid_driver); + class_destroy(spraid_class); + unregister_chrdev_region(spraid_chr_devt, SPRAID_MINORS); + destroy_workqueue(spraid_wq); + ida_destroy(&spraid_instance_ida); +} + +MODULE_AUTHOR("Ramaxel Memory Technology"); +MODULE_DESCRIPTION("Ramaxel Memory Technology SPraid Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(SPRAID_DRV_VERSION); +module_init(spraid_init); +module_exit(spraid_exit); -- 2.20.1

1 3

[PATCH] arm64/mpam: fix the problem that the ret variable is not initialized
by wenzhiwei 13 Oct '21

13 Oct '21

From: wenzhiwei11 <wenzhiwei(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AHUL?from=project-issue CVE: NA --------------------------------------------------- initialize the value "ret" in "schemata_list_init()" Signed-off-by: 温志伟 <wenzhiwei(a)kylinos.cn> --- arch/arm64/kernel/mpam/mpam_ctrlmon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/mpam/mpam_ctrlmon.c b/arch/arm64/kernel/mpam/mpam_ctrlmon.c index a4a298a455e0..9759eb223dac 100644 --- a/arch/arm64/kernel/mpam/mpam_ctrlmon.c +++ b/arch/arm64/kernel/mpam/mpam_ctrlmon.c @@ -131,7 +131,7 @@ static int add_schema(enum resctrl_conf_type t, struct resctrl_resource *r) int schemata_list_init(void) { - int ret; + int ret = 0; struct mpam_resctrl_res *res; struct resctrl_resource *r; -- 2.30.0

3 2

Please help me to unsubscribe
by Wangpeng (Forest, ISCP SRE) 13 Oct '21

13 Oct '21

Hi, I hava unsubscribed the list. (send an email to kernel-leave(a)openeuler.org<mailto:kernel-leave@openeuler.org>). Why is the system still sending me the mails? B.R.

1 0

[PATCH kernel-4.19 1/2] sched/topology: Make sched_init_numa() use a set for the deduplicating sort
by Yang Yingliang 13 Oct '21

13 Oct '21

From: Valentin Schneider <valentin.schneider(a)arm.com> mainline inclusion from mainline-v5.12-rc1 commit 620a6dc40754dc218f5b6389b5d335e9a107fd29 category: bugfix bugzilla: 182847,https://gitee.com/openeuler/kernel/issues/I48TV8 CVE: NA ---------------------------------------------------------- The deduplicating sort in sched_init_numa() assumes that the first line in the distance table contains all unique values in the entire table. I've been trying to pen what this exactly means for the topology, but it's not straightforward. For instance, topology.c uses this example: node 0 1 2 3 0: 10 20 20 30 1: 20 10 20 20 2: 20 20 10 20 3: 30 20 20 10 0 ----- 1 | / | | / | | / | 2 ----- 3 Which works out just fine. However, if we swap nodes 0 and 1: 1 ----- 0 | / | | / | | / | 2 ----- 3 we get this distance table: node 0 1 2 3 0: 10 20 20 20 1: 20 10 20 30 2: 20 20 10 20 3: 20 30 20 10 Which breaks the deduplicating sort (non-representative first line). In this case this would just be a renumbering exercise, but it so happens that we can have a deduplicating sort that goes through the whole table in O(n²) at the extra cost of a temporary memory allocation (i.e. any form of set). The ACPI spec (SLIT) mentions distances are encoded on 8 bits. Following this, implement the set as a 256-bits bitmap. Should this not be satisfactory (i.e. we want to support 32-bit values), then we'll have to go for some other sparse set implementation. This has the added benefit of letting us allocate just the right amount of memory for sched_domains_numa_distance[], rather than an arbitrary (nr_node_ids + 1). Note: DT binding equivalent (distance-map) decodes distances as 32-bit values. Signed-off-by: Valentin Schneider <valentin.schneider(a)arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lkml.kernel.org/r/20210122123943.1217-2-valentin.schneider@arm.com Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/topology.h | 1 + kernel/sched/topology.c | 99 +++++++++++++++++++--------------------- 2 files changed, 49 insertions(+), 51 deletions(-) diff --git a/include/linux/topology.h b/include/linux/topology.h index 5cc8595dd0e4e..a19771cd267d7 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -47,6 +47,7 @@ int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 +#define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f383a8f5a88bc..23f0a69b2ed49 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1442,66 +1442,58 @@ static void check_node_limit(void) static inline void check_node_limit(void) { } #endif /* CONFIG_SCHED_STEAL */ + +#define NR_DISTANCE_VALUES (1 << DISTANCE_BITS) + void sched_init_numa(void) { - int next_distance, curr_distance = node_distance(0, 0); struct sched_domain_topology_level *tl; - int level = 0; - int i, j, k; - - sched_domains_numa_distance = kzalloc(sizeof(int) * (nr_node_ids + 1), GFP_KERNEL); - if (!sched_domains_numa_distance) - return; - - /* Includes NUMA identity node at level 0. */ - sched_domains_numa_distance[level++] = curr_distance; - sched_domains_numa_levels = level; + unsigned long *distance_map; + int nr_levels = 0; + int i, j; /* * O(nr_nodes^2) deduplicating selection sort -- in order to find the * unique distances in the node_distance() table. - * - * Assumes node_distance(0,j) includes all distances in - * node_distance(i,j) in order to avoid cubic time. */ - next_distance = curr_distance; + distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL); + if (!distance_map) + return; + + bitmap_zero(distance_map, NR_DISTANCE_VALUES); for (i = 0; i < nr_node_ids; i++) { for (j = 0; j < nr_node_ids; j++) { - for (k = 0; k < nr_node_ids; k++) { - int distance = node_distance(i, k); - - if (distance > curr_distance && - (distance < next_distance || - next_distance == curr_distance)) - next_distance = distance; - - /* - * While not a strong assumption it would be nice to know - * about cases where if node A is connected to B, B is not - * equally connected to A. - */ - if (sched_debug() && node_distance(k, i) != distance) - sched_numa_warn("Node-distance not symmetric"); + int distance = node_distance(i, j); - if (sched_debug() && i && !find_numa_distance(distance)) - sched_numa_warn("Node-0 not representative"); + if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) { + sched_numa_warn("Invalid distance value range"); + return; } - if (next_distance != curr_distance) { - sched_domains_numa_distance[level++] = next_distance; - sched_domains_numa_levels = level; - curr_distance = next_distance; - } else break; + + bitmap_set(distance_map, distance, 1); } + } + /* + * We can now figure out how many unique distance values there are and + * allocate memory accordingly. + */ + nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES); - /* - * In case of sched_debug() we verify the above assumption. - */ - if (!sched_debug()) - break; + sched_domains_numa_distance = kcalloc(nr_levels, sizeof(int), GFP_KERNEL); + if (!sched_domains_numa_distance) { + bitmap_free(distance_map); + return; } + for (i = 0, j = 0; i < nr_levels; i++, j++) { + j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j); + sched_domains_numa_distance[i] = j; + } + + bitmap_free(distance_map); + /* - * 'level' contains the number of unique distances + * 'nr_levels' contains the number of unique distances * * The sched_domains_numa_distance[] array includes the actual distance * numbers. @@ -1510,15 +1502,15 @@ void sched_init_numa(void) /* * Here, we should temporarily reset sched_domains_numa_levels to 0. * If it fails to allocate memory for array sched_domains_numa_masks[][], - * the array will contain less then 'level' members. This could be + * the array will contain less then 'nr_levels' members. This could be * dangerous when we use it to iterate array sched_domains_numa_masks[][] * in other functions. * - * We reset it to 'level' at the end of this function. + * We reset it to 'nr_levels' at the end of this function. */ sched_domains_numa_levels = 0; - sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + sched_domains_numa_masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL); if (!sched_domains_numa_masks) return; @@ -1526,7 +1518,7 @@ void sched_init_numa(void) * Now for each level, construct a mask per node which contains all * CPUs of nodes that are that many hops away from us. */ - for (i = 0; i < level; i++) { + for (i = 0; i < nr_levels; i++) { sched_domains_numa_masks[i] = kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); if (!sched_domains_numa_masks[i]) @@ -1534,12 +1526,17 @@ void sched_init_numa(void) for (j = 0; j < nr_node_ids; j++) { struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + int k; + if (!mask) return; sched_domains_numa_masks[i][j] = mask; for_each_node(k) { + if (sched_debug() && (node_distance(j, k) != node_distance(k, j))) + sched_numa_warn("Node-distance not symmetric"); + if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; @@ -1551,7 +1548,7 @@ void sched_init_numa(void) /* Compute default topology size */ for (i = 0; sched_domain_topology[i].mask; i++); - tl = kzalloc((i + level + 1) * + tl = kzalloc((i + nr_levels) * sizeof(struct sched_domain_topology_level), GFP_KERNEL); if (!tl) return; @@ -1574,7 +1571,7 @@ void sched_init_numa(void) /* * .. and append 'j' levels of NUMA goodness. */ - for (j = 1; j < level; i++, j++) { + for (j = 1; j < nr_levels; i++, j++) { tl[i] = (struct sched_domain_topology_level){ .mask = sd_numa_mask, .sd_flags = cpu_numa_flags, @@ -1586,8 +1583,8 @@ void sched_init_numa(void) sched_domain_topology = tl; - sched_domains_numa_levels = level; - sched_max_numa_distance = sched_domains_numa_distance[level - 1]; + sched_domains_numa_levels = nr_levels; + sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1]; init_numa_topology_type(); check_node_limit(); -- 2.25.1

1 1

[PATCH openEuler-21.03] arch/arm64/kernel/mpam: fix Uninitialized scalar variable
by shenzijun 13 Oct '21

13 Oct '21

From: 沈子俊 <shenzijun(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AHUK?from=project-issue CVE: NA --------------------------------------------------- initialize the value "ret" Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- arch/arm64/kernel/mpam/mpam_ctrlmon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/mpam/mpam_ctrlmon.c b/arch/arm64/kernel/mpam/mpam_ctrlmon.c index b1d32d432556..6bcb4ca65b18 100644 --- a/arch/arm64/kernel/mpam/mpam_ctrlmon.c +++ b/arch/arm64/kernel/mpam/mpam_ctrlmon.c @@ -733,7 +733,7 @@ static int resctrl_group_mkdir_info_resdir(struct resctrl_resource *r, char *name,unsigned long fflags, struct kernfs_node *kn_info) { struct kernfs_node *kn_subdir; - int ret; + int ret = 0; kn_subdir = kernfs_create_dir(kn_info, name, kn_info->mode, r); -- 2.30.0

1 0

[PATCH openEuler-5.10 001/582] Revert "evm: Refuse EVM_ALLOW_METADATA_WRITES only if an HMAC key is loaded"
by Zheng Zengkai 13 Oct '21

13 Oct '21

hulk inclusion category: feature feature: IMA Digest Lists extension bugzilla: 46797 --------------------------- This reverts commit 9b772f4948fa513c501ae37c7afc89aa8613314c. backport patch from LTS 5.10.50 instead. Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- Documentation/ABI/testing/evm | 5 ++--- security/integrity/evm/evm_secfs.c | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/Documentation/ABI/testing/evm b/Documentation/ABI/testing/evm index eb6d70fd6fa2..3c477ba48a31 100644 --- a/Documentation/ABI/testing/evm +++ b/Documentation/ABI/testing/evm @@ -49,9 +49,8 @@ Description: modification of EVM-protected metadata and disable all further modification of policy - Note that once an HMAC key has been loaded, it will no longer - be possible to enable metadata modification and, if it is - already enabled, it will be disabled. + Note that once a key has been loaded, it will no longer be + possible to enable metadata modification. Until key loading has been signaled EVM can not create or validate the 'security.evm' xattr, but returns diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c index 92fe26ace797..cfc3075769bb 100644 --- a/security/integrity/evm/evm_secfs.c +++ b/security/integrity/evm/evm_secfs.c @@ -84,7 +84,7 @@ static ssize_t evm_write_key(struct file *file, const char __user *buf, * keys are loaded. */ if ((i & EVM_ALLOW_METADATA_WRITES) && - ((evm_initialized & EVM_INIT_HMAC) != 0) && + ((evm_initialized & EVM_KEY_MASK) != 0) && !(evm_initialized & EVM_ALLOW_METADATA_WRITES)) return -EPERM; -- 2.20.1

1 581

[PATCH openEuler-1.0-LTS 1/2] block: fix blk-iolatency accounting underflow
by Yang Yingliang 13 Oct '21

13 Oct '21

From: Dennis Zhou <dennis(a)kernel.org> mainline inclusion from mainline-v5.0-rc1 commit 13369816cb648f897ce9cbf57e55eeb742ce4eb3 category: bugfix bugzilla: 182234 CVE: NA --------------------------- The blk-iolatency controller measures the time from rq_qos_throttle() to rq_qos_done_bio() and attributes this time to the first bio that needs to create the request. This means if a bio is plug-mergeable or bio-mergeable, it gets to bypass the blk-iolatency controller. The recent series [1], to tag all bios w/ blkgs undermined how iolatency was determining which bios it was charging and should process in rq_qos_done_bio(). Because all bios are being tagged, this caused the atomic_t for the struct rq_wait inflight count to underflow and result in a stall. This patch adds a new flag BIO_TRACKED to let controllers know that a bio is going through the rq_qos path. blk-iolatency now checks if this flag is set to see if it should process the bio in rq_qos_done_bio(). Overloading BLK_QUEUE_ENTERED works, but makes the flag rules confusing. BIO_THROTTLED was another candidate, but the flag is set for all bios that have gone through blk-throttle code. Overloading a flag comes with the burden of making sure that when either implementation changes, a change in setting rules for one doesn't cause a bug in the other. So here, we unfortunately opt for adding a new flag. [1] https://lore.kernel.org/lkml/20181205171039.73066-1-dennis@kernel.org/ Fixes: 5cdf2e3fea5e ("blkcg: associate blkg when associating a device") Signed-off-by: Dennis Zhou <dennis(a)kernel.org> Cc: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflicts: block/blk-iolatency.c block/blk-rq-qos.c Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-iolatency.c | 2 +- block/blk-rq-qos.c | 6 ++++++ include/linux/blk_types.h | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 0529e94a20f7f..ae6ae7f50c6f7 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -563,7 +563,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) int inflight = 0; blkg = bio->bi_blkg; - if (!blkg) + if (!blkg || !bio_flagged(bio, BIO_TRACKED)) return; iolat = blkg_to_lat(bio->bi_blkg); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 43bcd4e7a7f9a..d1eaa118ce309 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -72,6 +72,12 @@ void rq_qos_throttle(struct request_queue *q, struct bio *bio, { struct rq_qos *rqos; + /* + * BIO_TRACKED lets controllers know that a bio went through the + * normal rq_qos path. + */ + bio_set_flag(bio, BIO_TRACKED); + for(rqos = q->rq_qos; rqos; rqos = rqos->next) { if (rqos->ops->throttle) rqos->ops->throttle(rqos, bio, lock); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index c07caa2a28429..8075b9955bb3c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -233,6 +233,7 @@ struct bio { #define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion * of this bio. */ #define BIO_QUEUE_ENTERED 11 /* can use blk_queue_enter_live() */ +#define BIO_TRACKED 12 /* set if bio goes through the rq_qos path */ /* See BVEC_POOL_OFFSET below before adding new flags */ -- 2.25.1

1 1

[PATCH kernel-4.19 1/2] block: fix blk-iolatency accounting underflow
by Yang Yingliang 13 Oct '21

13 Oct '21

From: Dennis Zhou <dennis(a)kernel.org> mainline inclusion from mainline-v5.0-rc1 commit 13369816cb648f897ce9cbf57e55eeb742ce4eb3 category: bugfix bugzilla: 182234 CVE: NA --------------------------- The blk-iolatency controller measures the time from rq_qos_throttle() to rq_qos_done_bio() and attributes this time to the first bio that needs to create the request. This means if a bio is plug-mergeable or bio-mergeable, it gets to bypass the blk-iolatency controller. The recent series [1], to tag all bios w/ blkgs undermined how iolatency was determining which bios it was charging and should process in rq_qos_done_bio(). Because all bios are being tagged, this caused the atomic_t for the struct rq_wait inflight count to underflow and result in a stall. This patch adds a new flag BIO_TRACKED to let controllers know that a bio is going through the rq_qos path. blk-iolatency now checks if this flag is set to see if it should process the bio in rq_qos_done_bio(). Overloading BLK_QUEUE_ENTERED works, but makes the flag rules confusing. BIO_THROTTLED was another candidate, but the flag is set for all bios that have gone through blk-throttle code. Overloading a flag comes with the burden of making sure that when either implementation changes, a change in setting rules for one doesn't cause a bug in the other. So here, we unfortunately opt for adding a new flag. [1] https://lore.kernel.org/lkml/20181205171039.73066-1-dennis@kernel.org/ Fixes: 5cdf2e3fea5e ("blkcg: associate blkg when associating a device") Signed-off-by: Dennis Zhou <dennis(a)kernel.org> Cc: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflicts: block/blk-iolatency.c block/blk-rq-qos.c Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-iolatency.c | 2 +- block/blk-rq-qos.c | 6 ++++++ include/linux/blk_types.h | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 8897f7c579ec7..b10336b401f6e 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -563,7 +563,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) int inflight = 0; blkg = bio->bi_blkg; - if (!blkg) + if (!blkg || !bio_flagged(bio, BIO_TRACKED)) return; iolat = blkg_to_lat(bio->bi_blkg); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 8f277518b21ba..86456d016cf92 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -72,6 +72,12 @@ void rq_qos_throttle(struct request_queue *q, struct bio *bio, { struct rq_qos *rqos; + /* + * BIO_TRACKED lets controllers know that a bio went through the + * normal rq_qos path. + */ + bio_set_flag(bio, BIO_TRACKED); + for(rqos = q->rq_qos; rqos; rqos = rqos->next) { if (rqos->ops->throttle) rqos->ops->throttle(rqos, bio, lock); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 29ffec0814e9a..78e701f34dc42 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -236,6 +236,7 @@ struct bio { #define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion * of this bio. */ #define BIO_QUEUE_ENTERED 11 /* can use blk_queue_enter_live() */ +#define BIO_TRACKED 12 /* set if bio goes through the rq_qos path */ /* See BVEC_POOL_OFFSET below before adding new flags */ -- 2.25.1

1 1

[PATCH kernel-4.19] ovl: fix missing negative dentry check in ovl_rename()
by Yang Yingliang 13 Oct '21

13 Oct '21

From: Zheng Liang <zhengliang6(a)huawei.com> mainline inclusion from mainline-v5.15-rc5 commit a295aef603e109a47af355477326bd41151765b6 category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- The following reproducer mkdir lower upper work merge touch lower/old touch lower/new mount -t overlay overlay -olowerdir=lower,upperdir=upper,workdir=work merge rm merge/new mv merge/old merge/new & unlink upper/new may result in this race: PROCESS A: rename("merge/old", "merge/new"); overwrite=true,ovl_lower_positive(old)=true, ovl_dentry_is_whiteout(new)=true -> flags |= RENAME_EXCHANGE PROCESS B: unlink("upper/new"); PROCESS A: lookup newdentry in new_upperdir call vfs_rename() with negative newdentry and RENAME_EXCHANGE Fix by adding the missing check for negative newdentry. Signed-off-by: Zheng Liang <zhengliang6(a)huawei.com> Fixes: e9be9d5e76e3 ("overlay filesystem") Cc: <stable(a)vger.kernel.org> # v3.18 Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/overlayfs/dir.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 9902c1706be91..1de8ef95ad960 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1188,9 +1188,13 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, goto out_dput; } } else { - if (!d_is_negative(newdentry) && - (!new_opaque || !ovl_is_whiteout(newdentry))) - goto out_dput; + if (!d_is_negative(newdentry)) { + if (!new_opaque || !ovl_is_whiteout(newdentry)) + goto out_dput; + } else { + if (flags & RENAME_EXCHANGE) + goto out_dput; + } } if (olddentry == trap) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] Revert "ext4: fix panic when mount failed with parallel flush_stashed_error_work"
by Yang Yingliang 13 Oct '21

13 Oct '21

From: yangerkun <yangerkun(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172146, https://gitee.com/openeuler/kernel/issues/I46HJ6 CVE: NA --------------------------- This reverts commit fde31a90246972ddb417381d2b26831a001edaa1. We will include the mainline patch, revert this now. Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/super.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 280e991e61f47..d793e597c0623 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4832,7 +4832,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_ea_block_cache = NULL; } if (sbi->s_journal) { - flush_work(&sbi->s_error_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } -- 2.25.1

1 1

[PATCH kernel-4.19 1/2] Revert "ext4: fix panic when mount failed with parallel flush_stashed_error_work"
by Yang Yingliang 13 Oct '21

13 Oct '21

From: yangerkun <yangerkun(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172146, https://gitee.com/openeuler/kernel/issues/I46HJ6 CVE: NA --------------------------- This reverts commit 881543818e4af30765ffb2604cd70a90f6007427. We will include the mainline patch, revert this now. Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/super.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 280e991e61f47..d793e597c0623 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4832,7 +4832,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_ea_block_cache = NULL; } if (sbi->s_journal) { - flush_work(&sbi->s_error_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/3] ext4: use true,false for bool variable
by Yang Yingliang 13 Oct '21

13 Oct '21

From: zhengbin <zhengbin13(a)huawei.com> mainline inclusion from mainline-5.6-rc1 commit 4756ee183f25b1fa2a7306a439da3bcd687244e0 category: bugfix bugzilla: 181871, https://gitee.com/openeuler/kernel/issues/I4DP71 CVE: NA --------------------------- Fixes coccicheck warning: fs/ext4/extents.c:5271:6-12: WARNING: Assignment of 0/1 to bool variable fs/ext4/extents.c:5287:4-10: WARNING: Assignment of 0/1 to bool variable Reported-by: Hulk Robot <hulkci(a)huawei.com> Signed-off-by: zhengbin <zhengbin13(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/1577241959-138695-1-git-send-email-zhengbin13@hua… Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/extents.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 6a0aab71a01f0..fe7398a5888b6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5295,7 +5295,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; - bool update = 0; + bool update = false; depth = path->p_depth; while (depth >= 0) { @@ -5311,7 +5311,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, goto out; if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) - update = 1; + update = true; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { -- 2.25.1

1 2

[PATCH kernel-4.19 1/3] ext4: use true,false for bool variable
by Yang Yingliang 13 Oct '21

13 Oct '21

From: zhengbin <zhengbin13(a)huawei.com> mainline inclusion from mainline-5.6-rc1 commit 4756ee183f25b1fa2a7306a439da3bcd687244e0 category: bugfix bugzilla: 181871, https://gitee.com/openeuler/kernel/issues/I4DP71 CVE: NA --------------------------- Fixes coccicheck warning: fs/ext4/extents.c:5271:6-12: WARNING: Assignment of 0/1 to bool variable fs/ext4/extents.c:5287:4-10: WARNING: Assignment of 0/1 to bool variable Reported-by: Hulk Robot <hulkci(a)huawei.com> Signed-off-by: zhengbin <zhengbin13(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/1577241959-138695-1-git-send-email-zhengbin13@hua… Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/extents.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 6a0aab71a01f0..fe7398a5888b6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5295,7 +5295,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; - bool update = 0; + bool update = false; depth = path->p_depth; while (depth >= 0) { @@ -5311,7 +5311,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, goto out; if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) - update = 1; + update = true; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { -- 2.25.1

1 2

[PATCH OLK-5.10 v4 0/2] net: spnic: initial commit Ramaxel NIC driver
by Yanling Song 13 Oct '21

13 Oct '21

This initial commit contains Ramaxel's spnic module Changes since v3: - Change VXLAN_OFFLOAD_PORT_LE to VXLAN_OFFLOAD_PORT_BE; Changes since v2: - Solve the "new blank line at EOF" error; - Change SPHW_COMM_H to SPHW_HW_COMM_H; Changes since v1: - Solve the compile error Yanling Song (2): net: spnic: initial commit the common module of Ramaxel NIC driver spnic: add NIC layer arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + drivers/net/ethernet/Kconfig | 1 + drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/ramaxel/Kconfig | 20 + drivers/net/ethernet/ramaxel/Makefile | 6 + drivers/net/ethernet/ramaxel/spnic/Kconfig | 14 + drivers/net/ethernet/ramaxel/spnic/Makefile | 39 + .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.c | 1165 +++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.h | 277 +++ .../ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h | 126 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c | 1605 +++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h | 195 ++ .../ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h | 60 + .../ramaxel/spnic/hw/sphw_comm_msg_intf.h | 273 +++ .../ethernet/ramaxel/spnic/hw/sphw_common.c | 88 + .../ethernet/ramaxel/spnic/hw/sphw_common.h | 118 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_crm.h | 984 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_csr.h | 171 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.c | 1374 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.h | 157 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_hw.h | 649 ++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c | 1338 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h | 326 +++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.c | 1253 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.h | 42 + .../ethernet/ramaxel/spnic/hw/sphw_hwdev.c | 1402 +++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hwdev.h | 93 + .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.c | 911 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.h | 102 + .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.c | 1808 +++++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.h | 273 +++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c | 1382 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h | 156 ++ .../ramaxel/spnic/hw/sphw_mgmt_msg_base.h | 19 + .../net/ethernet/ramaxel/spnic/hw/sphw_mt.h | 534 +++++ .../ramaxel/spnic/hw/sphw_prof_adap.c | 94 + .../ramaxel/spnic/hw/sphw_prof_adap.h | 49 + .../ethernet/ramaxel/spnic/hw/sphw_profile.h | 36 + .../net/ethernet/ramaxel/spnic/hw/sphw_wq.c | 152 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_wq.h | 119 ++ .../net/ethernet/ramaxel/spnic/spnic_dbg.c | 752 +++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.c | 965 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.h | 56 + .../ethernet/ramaxel/spnic/spnic_dev_mgmt.c | 811 ++++++++ .../ethernet/ramaxel/spnic/spnic_dev_mgmt.h | 78 + .../ethernet/ramaxel/spnic/spnic_ethtool.c | 988 +++++++++ .../ramaxel/spnic/spnic_ethtool_stats.c | 1035 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_filter.c | 411 ++++ .../net/ethernet/ramaxel/spnic/spnic_irq.c | 178 ++ .../net/ethernet/ramaxel/spnic/spnic_lld.c | 937 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_lld.h | 75 + .../ethernet/ramaxel/spnic/spnic_mag_cfg.c | 778 +++++++ .../ethernet/ramaxel/spnic/spnic_mag_cmd.h | 643 ++++++ .../net/ethernet/ramaxel/spnic/spnic_main.c | 925 +++++++++ .../ramaxel/spnic/spnic_mgmt_interface.h | 617 ++++++ .../ethernet/ramaxel/spnic/spnic_netdev_ops.c | 1526 ++++++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic.h | 148 ++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.c | 1321 ++++++++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.h | 724 +++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c | 647 ++++++ .../ethernet/ramaxel/spnic/spnic_nic_cmd.h | 105 + .../ethernet/ramaxel/spnic/spnic_nic_dbg.c | 151 ++ .../ethernet/ramaxel/spnic/spnic_nic_dbg.h | 16 + .../ethernet/ramaxel/spnic/spnic_nic_dev.h | 352 ++++ .../ethernet/ramaxel/spnic/spnic_nic_event.c | 506 +++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.c | 1123 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.h | 309 +++ .../net/ethernet/ramaxel/spnic/spnic_nic_qp.h | 421 ++++ .../net/ethernet/ramaxel/spnic/spnic_ntuple.c | 841 ++++++++ .../ethernet/ramaxel/spnic/spnic_pci_id_tbl.h | 12 + .../net/ethernet/ramaxel/spnic/spnic_rss.c | 750 +++++++ .../net/ethernet/ramaxel/spnic/spnic_rss.h | 48 + .../ethernet/ramaxel/spnic/spnic_rss_cfg.c | 390 ++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.c | 1249 ++++++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.h | 118 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.c | 200 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.h | 24 + drivers/net/ethernet/ramaxel/spnic/spnic_tx.c | 879 ++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_tx.h | 129 ++ 80 files changed, 38654 insertions(+) create mode 100644 drivers/net/ethernet/ramaxel/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/spnic/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_msg_intf.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_crm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_csr.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt_msg_base.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_profile.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool_stats.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_filter.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_irq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_main.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mgmt_interface.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_netdev_ops.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_event.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_qp.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ntuple.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_pci_id_tbl.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.h -- 2.30.0

2 3

[PATCH openEuler-5.10 001/136] module: limit enabling module.sig_enforce
by Zheng Zengkai 12 Oct '21

12 Oct '21

From: Mimi Zohar <zohar(a)linux.ibm.com> stable inclusion from stable-5.10.47 commit 3051f230f19feb02dfe5b36794f8c883b576e184 bugzilla: 172973 https://gitee.com/openeuler/kernel/issues/I4DAKB Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 0c18f29aae7ce3dadd26d8ee3505d07cc982df75 ] Irrespective as to whether CONFIG_MODULE_SIG is configured, specifying "module.sig_enforce=1" on the boot command line sets "sig_enforce". Only allow "sig_enforce" to be set when CONFIG_MODULE_SIG is configured. This patch makes the presence of /sys/module/module/parameters/sig_enforce dependent on CONFIG_MODULE_SIG=y. Fixes: fda784e50aac ("module: export module signature enforcement status") Reported-by: Nayna Jain <nayna(a)linux.ibm.com> Tested-by: Mimi Zohar <zohar(a)linux.ibm.com> Tested-by: Jessica Yu <jeyu(a)kernel.org> Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Signed-off-by: Jessica Yu <jeyu(a)kernel.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Acked-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- kernel/module.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/kernel/module.c b/kernel/module.c index a54dda703feb..c5af21dcb873 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -272,9 +272,18 @@ static void module_assert_mutex_or_preempt(void) #endif } +#ifdef CONFIG_MODULE_SIG static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); module_param(sig_enforce, bool_enable_only, 0644); +void set_module_sig_enforced(void) +{ + sig_enforce = true; +} +#else +#define sig_enforce false +#endif + /* * Export sig_enforce kernel cmdline parameter to allow other subsystems rely * on that instead of directly to CONFIG_MODULE_SIG_FORCE config. @@ -285,11 +294,6 @@ bool is_module_sig_enforced(void) } EXPORT_SYMBOL(is_module_sig_enforced); -void set_module_sig_enforced(void) -{ - sig_enforce = true; -} - /* Block module loading/unloading? */ int modules_disabled = 0; core_param(nomodule, modules_disabled, bint, 0); -- 2.20.1

1 135

【Meeting Notice】openEuler kernel 技术分享第十三期 & 双周例会 Time: 2021-10-15 14:00-16:30
by Meeting Book 12 Oct '21

12 Oct '21

1 0

[PATCH openEuler-1.0-LTS] net: 6pack: fix slab-out-of-bounds in decode_data
by Yang Yingliang 12 Oct '21

12 Oct '21

From: Pavel Skripkin <paskripkin(a)gmail.com> stable inclusion from linux-4.19.205 commit 4e370cc081a78ee23528311ca58fd98a06768ec7 CVE: CVE-2021-42008 -------------------------------- [ Upstream commit 19d1532a187669ce86d5a2696eb7275310070793 ] Syzbot reported slab-out-of bounds write in decode_data(). The problem was in missing validation checks. Syzbot's reproducer generated malicious input, which caused decode_data() to be called a lot in sixpack_decode(). Since rx_count_cooked is only 400 bytes and noone reported before, that 400 bytes is not enough, let's just check if input is malicious and complain about buffer overrun. Fail log: ================================================================== BUG: KASAN: slab-out-of-bounds in drivers/net/hamradio/6pack.c:843 Write of size 1 at addr ffff888087c5544e by task kworker/u4:0/7 CPU: 0 PID: 7 Comm: kworker/u4:0 Not tainted 5.6.0-rc3-syzkaller #0 ... Workqueue: events_unbound flush_to_ldisc Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 __kasan_report.cold+0x1b/0x32 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:641 __asan_report_store1_noabort+0x17/0x20 mm/kasan/generic_report.c:137 decode_data.part.0+0x23b/0x270 drivers/net/hamradio/6pack.c:843 decode_data drivers/net/hamradio/6pack.c:965 [inline] sixpack_decode drivers/net/hamradio/6pack.c:968 [inline] Reported-and-tested-by: syzbot+fc8cd9a673d4577fb2e4(a)syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Pavel Skripkin <paskripkin(a)gmail.com> Reviewed-by: Dan Carpenter <dan.carpenter(a)oracle.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> --- drivers/net/hamradio/6pack.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 8c636c4932274..1001e9a2edd4f 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -859,6 +859,12 @@ static void decode_data(struct sixpack *sp, unsigned char inbyte) return; } + if (sp->rx_count_cooked + 2 >= sizeof(sp->cooked_buf)) { + pr_err("6pack: cooked buffer overrun, data loss\n"); + sp->rx_count = 0; + return; + } + buf = sp->raw_buf; sp->cooked_buf[sp->rx_count_cooked++] = buf[0] | ((buf[1] << 2) & 0xc0); -- 2.25.1

1 0

[PATCH OLK-5.10 v3 0/2] net: spnic: initial commit Ramaxel NIC driver
by Yanling Song 12 Oct '21

12 Oct '21

This initial commit contains Ramaxel's spnic module Changes since v2: - Solve the "new blank line at EOF" error; - Change SPHW_COMM_H to SPHW_HW_COMM_H; Changes since v1: - Solve the compile error Yanling Song (2): net: spnic: initial commit the common module of Ramaxel NIC driver spnic: add NIC layer arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + drivers/net/ethernet/Kconfig | 1 + drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/ramaxel/Kconfig | 20 + drivers/net/ethernet/ramaxel/Makefile | 6 + drivers/net/ethernet/ramaxel/spnic/Kconfig | 14 + drivers/net/ethernet/ramaxel/spnic/Makefile | 39 + .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.c | 1165 +++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.h | 277 +++ .../ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h | 126 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c | 1605 +++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h | 195 ++ .../ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h | 60 + .../ramaxel/spnic/hw/sphw_comm_msg_intf.h | 273 +++ .../ethernet/ramaxel/spnic/hw/sphw_common.c | 88 + .../ethernet/ramaxel/spnic/hw/sphw_common.h | 118 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_crm.h | 984 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_csr.h | 171 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.c | 1374 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.h | 157 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_hw.h | 649 ++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c | 1338 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h | 326 +++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.c | 1253 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.h | 42 + .../ethernet/ramaxel/spnic/hw/sphw_hwdev.c | 1402 +++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hwdev.h | 93 + .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.c | 911 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.h | 102 + .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.c | 1808 +++++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.h | 273 +++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c | 1382 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h | 156 ++ .../ramaxel/spnic/hw/sphw_mgmt_msg_base.h | 19 + .../net/ethernet/ramaxel/spnic/hw/sphw_mt.h | 534 +++++ .../ramaxel/spnic/hw/sphw_prof_adap.c | 94 + .../ramaxel/spnic/hw/sphw_prof_adap.h | 49 + .../ethernet/ramaxel/spnic/hw/sphw_profile.h | 36 + .../net/ethernet/ramaxel/spnic/hw/sphw_wq.c | 152 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_wq.h | 119 ++ .../net/ethernet/ramaxel/spnic/spnic_dbg.c | 752 +++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.c | 965 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.h | 56 + .../ethernet/ramaxel/spnic/spnic_dev_mgmt.c | 811 ++++++++ .../ethernet/ramaxel/spnic/spnic_dev_mgmt.h | 78 + .../ethernet/ramaxel/spnic/spnic_ethtool.c | 988 +++++++++ .../ramaxel/spnic/spnic_ethtool_stats.c | 1035 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_filter.c | 411 ++++ .../net/ethernet/ramaxel/spnic/spnic_irq.c | 178 ++ .../net/ethernet/ramaxel/spnic/spnic_lld.c | 937 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_lld.h | 75 + .../ethernet/ramaxel/spnic/spnic_mag_cfg.c | 778 +++++++ .../ethernet/ramaxel/spnic/spnic_mag_cmd.h | 643 ++++++ .../net/ethernet/ramaxel/spnic/spnic_main.c | 925 +++++++++ .../ramaxel/spnic/spnic_mgmt_interface.h | 617 ++++++ .../ethernet/ramaxel/spnic/spnic_netdev_ops.c | 1526 ++++++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic.h | 148 ++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.c | 1321 ++++++++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.h | 724 +++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c | 647 ++++++ .../ethernet/ramaxel/spnic/spnic_nic_cmd.h | 105 + .../ethernet/ramaxel/spnic/spnic_nic_dbg.c | 151 ++ .../ethernet/ramaxel/spnic/spnic_nic_dbg.h | 16 + .../ethernet/ramaxel/spnic/spnic_nic_dev.h | 352 ++++ .../ethernet/ramaxel/spnic/spnic_nic_event.c | 506 +++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.c | 1123 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.h | 309 +++ .../net/ethernet/ramaxel/spnic/spnic_nic_qp.h | 421 ++++ .../net/ethernet/ramaxel/spnic/spnic_ntuple.c | 841 ++++++++ .../ethernet/ramaxel/spnic/spnic_pci_id_tbl.h | 12 + .../net/ethernet/ramaxel/spnic/spnic_rss.c | 750 +++++++ .../net/ethernet/ramaxel/spnic/spnic_rss.h | 48 + .../ethernet/ramaxel/spnic/spnic_rss_cfg.c | 390 ++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.c | 1249 ++++++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.h | 118 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.c | 200 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.h | 24 + drivers/net/ethernet/ramaxel/spnic/spnic_tx.c | 879 ++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_tx.h | 129 ++ 80 files changed, 38654 insertions(+) create mode 100644 drivers/net/ethernet/ramaxel/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/spnic/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_msg_intf.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_crm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_csr.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt_msg_base.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_profile.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool_stats.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_filter.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_irq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_main.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mgmt_interface.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_netdev_ops.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_event.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_qp.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ntuple.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_pci_id_tbl.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.h -- 2.30.0

1 2

[PATCH v2 OLK-5.10 0/2] net: spnic: initial commit Ramaxel NIC driver
by Yanling Song 12 Oct '21

12 Oct '21

This initial commit contains Ramaxel's spnic module Changes since v1: - Solve the compile error Yanling Song (2): spnic: initial commit the common module of Ramaxel NIC driver spnic: add NIC layer arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + drivers/net/ethernet/Kconfig | 1 + drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/ramaxel/Kconfig | 20 + drivers/net/ethernet/ramaxel/Makefile | 6 + drivers/net/ethernet/ramaxel/spnic/Kconfig | 15 + drivers/net/ethernet/ramaxel/spnic/Makefile | 40 + .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.c | 1165 +++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.h | 277 +++ .../ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h | 126 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c | 1606 +++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h | 196 ++ .../ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h | 60 + .../ramaxel/spnic/hw/sphw_comm_msg_intf.h | 273 +++ .../ethernet/ramaxel/spnic/hw/sphw_common.c | 88 + .../ethernet/ramaxel/spnic/hw/sphw_common.h | 118 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_crm.h | 984 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_csr.h | 171 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.c | 1374 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.h | 157 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_hw.h | 649 ++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c | 1339 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h | 327 +++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.c | 1253 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.h | 42 + .../ethernet/ramaxel/spnic/hw/sphw_hwdev.c | 1402 +++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hwdev.h | 93 + .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.c | 911 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.h | 102 + .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.c | 1808 +++++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.h | 274 +++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c | 1382 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h | 156 ++ .../ramaxel/spnic/hw/sphw_mgmt_msg_base.h | 19 + .../net/ethernet/ramaxel/spnic/hw/sphw_mt.h | 534 +++++ .../ramaxel/spnic/hw/sphw_prof_adap.c | 94 + .../ramaxel/spnic/hw/sphw_prof_adap.h | 49 + .../ethernet/ramaxel/spnic/hw/sphw_profile.h | 36 + .../net/ethernet/ramaxel/spnic/hw/sphw_wq.c | 152 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_wq.h | 119 ++ .../net/ethernet/ramaxel/spnic/spnic_dbg.c | 753 +++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.c | 965 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.h | 56 + .../ethernet/ramaxel/spnic/spnic_dev_mgmt.c | 811 ++++++++ .../ethernet/ramaxel/spnic/spnic_dev_mgmt.h | 78 + .../ethernet/ramaxel/spnic/spnic_ethtool.c | 989 +++++++++ .../ramaxel/spnic/spnic_ethtool_stats.c | 1035 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_filter.c | 412 ++++ .../net/ethernet/ramaxel/spnic/spnic_irq.c | 178 ++ .../net/ethernet/ramaxel/spnic/spnic_lld.c | 937 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_lld.h | 75 + .../ethernet/ramaxel/spnic/spnic_mag_cfg.c | 778 +++++++ .../ethernet/ramaxel/spnic/spnic_mag_cmd.h | 643 ++++++ .../net/ethernet/ramaxel/spnic/spnic_main.c | 925 +++++++++ .../ramaxel/spnic/spnic_mgmt_interface.h | 617 ++++++ .../ethernet/ramaxel/spnic/spnic_netdev_ops.c | 1526 ++++++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic.h | 148 ++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.c | 1321 ++++++++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.h | 724 +++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c | 647 ++++++ .../ethernet/ramaxel/spnic/spnic_nic_cmd.h | 105 + .../ethernet/ramaxel/spnic/spnic_nic_dbg.c | 151 ++ .../ethernet/ramaxel/spnic/spnic_nic_dbg.h | 16 + .../ethernet/ramaxel/spnic/spnic_nic_dev.h | 353 ++++ .../ethernet/ramaxel/spnic/spnic_nic_event.c | 506 +++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.c | 1124 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.h | 309 +++ .../net/ethernet/ramaxel/spnic/spnic_nic_qp.h | 421 ++++ .../net/ethernet/ramaxel/spnic/spnic_ntuple.c | 841 ++++++++ .../ethernet/ramaxel/spnic/spnic_pci_id_tbl.h | 13 + .../net/ethernet/ramaxel/spnic/spnic_rss.c | 750 +++++++ .../net/ethernet/ramaxel/spnic/spnic_rss.h | 48 + .../ethernet/ramaxel/spnic/spnic_rss_cfg.c | 391 ++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.c | 1250 ++++++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.h | 118 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.c | 200 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.h | 24 + drivers/net/ethernet/ramaxel/spnic/spnic_tx.c | 879 ++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_tx.h | 129 ++ 80 files changed, 38669 insertions(+) create mode 100644 drivers/net/ethernet/ramaxel/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/spnic/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_msg_intf.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_crm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_csr.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt_msg_base.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_profile.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool_stats.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_filter.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_irq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_main.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mgmt_interface.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_netdev_ops.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_event.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_qp.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ntuple.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_pci_id_tbl.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.h -- 2.30.0

2 5

[PATCH kernel-4.19] bpf: Fix integer overflow in prealloc_elems_and_freelist()
by Yang Yingliang 11 Oct '21

11 Oct '21

From: Xu Kuohai <xukuohai(a)huawei.com> mainline inclusion from mainline-5.15-rc4 commit 30e29a9a2bc6a4888335a6ede968b75cd329657a category: bugfix bugzilla: NA CVE: CVE-2021-41864 ------------------------------------------------- In prealloc_elems_and_freelist(), the multiplication to calculate the size passed to bpf_map_area_alloc() could lead to an integer overflow. As a result, out-of-bounds write could occur in pcpu_freelist_populate() as reported by KASAN: [...] [ 16.968613] BUG: KASAN: slab-out-of-bounds in pcpu_freelist_populate+0xd9/0x100 [ 16.969408] Write of size 8 at addr ffff888104fc6ea0 by task crash/78 [ 16.970038] [ 16.970195] CPU: 0 PID: 78 Comm: crash Not tainted 5.15.0-rc2+ #1 [ 16.970878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 16.972026] Call Trace: [ 16.972306] dump_stack_lvl+0x34/0x44 [ 16.972687] print_address_description.constprop.0+0x21/0x140 [ 16.973297] ? pcpu_freelist_populate+0xd9/0x100 [ 16.973777] ? pcpu_freelist_populate+0xd9/0x100 [ 16.974257] kasan_report.cold+0x7f/0x11b [ 16.974681] ? pcpu_freelist_populate+0xd9/0x100 [ 16.975190] pcpu_freelist_populate+0xd9/0x100 [ 16.975669] stack_map_alloc+0x209/0x2a0 [ 16.976106] __sys_bpf+0xd83/0x2ce0 [...] The possibility of this overflow was originally discussed in [0], but was overlooked. Fix the integer overflow by changing elem_size to u64 from u32. [0] https://lore.kernel.org/bpf/728b238e-a481-eb50-98e9-b0f430ab01e7@gmail.com/ Fixes: 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") Signed-off-by: Tatsuhiko Yasumatsu <th.yasumatsu(a)gmail.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20210930135545.173698-1-th.yasumatsu@gmail.com Signed-off-by: Xu Kuohai <xukuohai(a)huawei.com> Reviewed-by: Yang Jihong <yangjihong1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/bpf/stackmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index a47d623f59fe7..92310b07cb98e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -63,7 +63,8 @@ static inline int stack_map_data_size(struct bpf_map *map) static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { - u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + u64 elem_size = sizeof(struct stack_map_bucket) + + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, -- 2.25.1

1 0

你推荐，我翻译：openEuler G11N SIG文章/书籍翻译计划，请您在10月17日前将希望翻译的文章/书籍名称和链接邮件发送至G11N mailing list。谢啦~
by suqin (D) 11 Oct '21

11 Oct '21

请将您希望翻译的文章/书籍名称和链接，在10月17日前邮件发送至G11N mailing list：g11n(a)openeuler.org<mailto:g11n@openeuler.org> （订阅<https://mailweb.openeuler.org/postorius/lists/g11n.openeuler.org/>）关于该活动有任何意见和建议，欢迎反馈哦~ [cid:image003.png@01D7BEB6.79A7BBC0] · 文章或书籍选定我们将组织志愿者翻译符合以下条件的文章或书籍： * 版权要求：可自由传播的免费电子文章或书籍（启动翻译之前，我们会征求原作者的翻译许可） * 内容要求：开源技术、操作系统或软件相关 * 内容语言：英文 * 英文字数：文章，每篇 < 1万字；书籍：< 10万字 * 如何反馈：请订阅openEuler G11N mailing list（如何订阅？<https://gitee.com/openeuler/globalization/blob/master/openeuler-g11n-contri…>），并将您希望翻译的文章或书籍名称和链接，邮件发送至G11N mailing list。收到您的反馈后，我们将根据翻译工作量和项目周期，制定和公布翻译计划，多谢啦~ [cid:image004.png@01D7BEBB.05DAB4E0]

1 0

[PATCH openEuler-5.10 01/32] net: hns3: make hclgevf_cmd_caps_bit_map0 and hclge_cmd_caps_bit_map0 static
by Zheng Zengkai 11 Oct '21

11 Oct '21

From: chongjiapeng <jiapeng.chong(a)linux.alibaba.com> mainline inclusion from mainline-v5.15-rc1 commit 0c0383918a3e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CVS3 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- This symbols is not used outside of hclge_cmd.c and hclgevf_cmd.c, so marks it static. Fix the following sparse warning: drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c:345:35: warning: symbol 'hclgevf_cmd_caps_bit_map0' was not declared. Should it be static? drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c:365:33: warning: symbol 'hclge_cmd_caps_bit_map0' was not declared. Should it be static? Reported-by: Abaci Robot <abaci(a)linux.alibaba.com> Signed-off-by: chongjiapeng <jiapeng.chong(a)linux.alibaba.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Reviewed-by: Yongxin Li <liyongxin1(a)huawei.com> Signed-off-by: Junxin Chen <chenjunxin1(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 474c6d1664e7..ac9b69513332 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -362,7 +362,7 @@ static void hclge_set_default_capability(struct hclge_dev *hdev) } } -const struct hclge_caps_bit_map hclge_cmd_caps_bit_map0[] = { +static const struct hclge_caps_bit_map hclge_cmd_caps_bit_map0[] = { {HCLGE_CAP_UDP_GSO_B, HNAE3_DEV_SUPPORT_UDP_GSO_B}, {HCLGE_CAP_PTP_B, HNAE3_DEV_SUPPORT_PTP_B}, {HCLGE_CAP_INT_QL_B, HNAE3_DEV_SUPPORT_INT_QL_B}, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index 59772b0e9531..f89bfb352adf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -342,7 +342,7 @@ static void hclgevf_set_default_capability(struct hclgevf_dev *hdev) set_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps); } -const struct hclgevf_caps_bit_map hclgevf_cmd_caps_bit_map0[] = { +static const struct hclgevf_caps_bit_map hclgevf_cmd_caps_bit_map0[] = { {HCLGEVF_CAP_UDP_GSO_B, HNAE3_DEV_SUPPORT_UDP_GSO_B}, {HCLGEVF_CAP_INT_QL_B, HNAE3_DEV_SUPPORT_INT_QL_B}, {HCLGEVF_CAP_TQP_TXRX_INDEP_B, HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B}, -- 2.20.1

1 31

[PATCH openEuler-21.03] arm64/mpam: fix device_errcode out of bounds
by yinxiujiang 09 Oct '21

09 Oct '21

From: yin-xiujiang <yinxiujiang(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AHUH?from=project-issue CVE: NA --------------------------------------------------- the size of mpam_msc_err_str is _MPAM_NUM_ERRCODE, so device_errcode needs to be less than _MPAM_NUM_ERRCODE Signed-off-by: yin-xiujiang <yinxiujiang(a)kylinos.cn> --- arch/arm64/kernel/mpam/mpam_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/mpam/mpam_device.c b/arch/arm64/kernel/mpam/mpam_device.c index 86aaf52146bc..fd538fd22c6e 100644 --- a/arch/arm64/kernel/mpam/mpam_device.c +++ b/arch/arm64/kernel/mpam/mpam_device.c @@ -435,7 +435,7 @@ static irqreturn_t mpam_handle_error_irq(int irq, void *data) return IRQ_NONE; /* No-one expects MPAM errors! */ - if (device_errcode <= _MPAM_NUM_ERRCODE) + if (device_errcode < _MPAM_NUM_ERRCODE) pr_err_ratelimited("unexpected error '%s' [esr:%x]\n", mpam_msc_err_str[device_errcode], device_esr); -- 2.27.0

2 1

[PATCH OLK-5.10] perf stat: Add --quiet option
by yinxiujiang 09 Oct '21

09 Oct '21

From: Andi Kleen <andi(a)firstfloor.org> mainline inclusion from mainline-5.11 commit 55a4de94c64bacffbcd802c954764e0de2ab217f category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMQA CVE: NA -------------------------------- Add a new --quiet option to 'perf stat'. This is useful with 'perf stat record' to write the data only to the perf.data file, which can lower measurement overhead because the data doesn't need to be formatted. On my 4C desktop: % time ./perf stat record -e $(python -c 'print ",\ ".join(["cycles"]*1000)') -a -I 1000 sleep 5 ... real 0m5.377s user 0m0.238s sys 0m0.452s % time ./perf stat record --quiet -e $(python -c 'print ",\ ".join(["cycles"]*1000)') -a -I 1000 sleep 5 real 0m5.452s user 0m0.183s sys 0m0.423s In this example it cuts the user time by 20%. On systems with more cores the savings are higher. Signed-off-by: Andi Kleen <andi(a)firstfloor.org> Acked-by: Jiri Olsa <jolsa(a)kernel.org> Cc: Alexey Budankov <alexey.budankov(a)linux.intel.com> Link: http://lore.kernel.org/lkml/20201027002737.30942-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: yin-xiujiang <yinxiujiang(a)kylinos.cn> --- tools/perf/Documentation/perf-stat.txt | 4 ++++ tools/perf/builtin-stat.c | 6 +++++- tools/perf/util/stat.h | 1 + 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 9f9f29025e49..f9bcd95bf352 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -320,6 +320,10 @@ STAT RECORD ----------- Stores stat data into perf data file. +--quiet:: +Don't print output. This is useful with perf stat record below to only +write data to the perf.data file. + -o file:: --output file:: Output file name. diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b01af171d94f..89e80a3bc9c3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -973,6 +973,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) if (STAT_RECORD && perf_stat.data.is_pipe) return; + if (stat_config.quiet) + return; perf_evlist__print_counters(evsel_list, &stat_config, &target, ts, argc, argv); } @@ -1171,6 +1173,8 @@ static struct option stat_options[] = { "threads of same physical core"), OPT_BOOLEAN(0, "summary", &stat_config.summary, "print summary for interval mode"), + OPT_BOOLEAN(0, "quiet", &stat_config.quiet, + "don't print output (useful with record)"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", @@ -2132,7 +2136,7 @@ int cmd_stat(int argc, const char **argv) goto out; } - if (!output) { + if (!output && !stat_config.quiet) { struct timespec tm; mode = append_file ? "a" : "w"; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 487010c624be..05adf8165025 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -122,6 +122,7 @@ struct perf_stat_config { bool metric_no_group; bool metric_no_merge; bool stop_read_counter; + bool quiet; FILE *output; unsigned int interval; unsigned int timeout; -- 2.27.0

2 1

[PATCH v1 openEuler-1.0-LTS 0/4]
by jiazhenyuan 09 Oct '21

09 Oct '21

issue: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue jiazhenyuan (4): tcp: address problems caused by EDT misshaps tcp: always set retrans_stamp on recovery tcp: create a helper to model exponential backoff tcp: adjust rto_base in retransmits_timed_out() net/ipv4/tcp_input.c | 16 +++++++---- net/ipv4/tcp_output.c | 9 +++--- net/ipv4/tcp_timer.c | 65 ++++++++++++++++++++----------------------- 3 files changed, 44 insertions(+), 46 deletions(-) -- 2.27.0

2 6

[PATCH kernel-4.19 openEuler-1.0-LTS 0/2] lib/timerqueue: Rely
by Cheng Jian 08 Oct '21

08 Oct '21

Davidlohr Bueso (1): lib/timerqueue: Rely on rbtree semantics for next timer Xiongfeng Wang (1): timerqueue: fix kabi for struct timerqueue_head include/linux/timerqueue.h | 14 +++++++++----- lib/timerqueue.c | 30 ++++++++++++------------------ 2 files changed, 21 insertions(+), 23 deletions(-) -- 2.25.1

1 2

[PATCH openEuler-5.10] imans: Use initial ima namespace domain tag when IMANS is disabled.
by Zheng Zengkai 08 Oct '21

08 Oct '21

From: Ajo Jose Panoor <ajo.jose.panoor(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4C9AE CVE: NA ----------------------------------------------------------------- As part of the imans support, a key domain tag is added to the search criteria in digsig module. When IMA Namespace is disabled, the initial ima namespace domain tag should be used instead of nsproxy. Signed-off-by: Ajo Jose Panoor <ajo.jose.panoor(a)huawei.com> Reviewed-by: Zhang Tianxing <zhangtianxing3(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- security/integrity/digsig.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 2c923dc0dbd3..c866a5c2c9b1 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -74,8 +74,11 @@ static struct key_tag *domain_tag_from_id(const unsigned int id) return ERR_PTR(-EINVAL); if (id == INTEGRITY_KEYRING_IMA) +#ifdef CONFIG_IMA_NS return current->nsproxy->ima_ns->key_domain; - +#else + return init_ima_ns.key_domain; +#endif return NULL; } -- 2.20.1

1 0

[PATCH openEuler-1.0-LTS] Fix incorrect call to free srb in qla2xxx_mqueuecommand()
by yinxiujiang 08 Oct '21

08 Oct '21

From: Arun Easi <aeasi(a)marvell.com> stable inclusion from linux-4.19.207 commit c5ab9b67d8b061de74e2ca51bf787ee599bd7f89 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFG0?from=project-issue CVE: NA ------------------------------------------------- RIP: 0010:kmem_cache_free+0xfa/0x1b0 Call Trace: qla2xxx_mqueuecommand+0x2b5/0x2c0 [qla2xxx] scsi_queue_rq+0x5e2/0xa40 __blk_mq_try_issue_directly+0x128/0x1d0 blk_mq_request_issue_directly+0x4e/0xb0 Fix incorrect call to free srb in qla2xxx_mqueuecommand(), as srb is now allocated by upper layers. This fixes smatch warning of srb unintended free. Link: https://lore.kernel.org/r/20210329085229.4367-7-njavali@marvell.com Fixes: af2a0c51b120 ("scsi: qla2xxx: Fix SRB leak on switch command timeout") Cc: stable(a)vger.kernel.org # 5.5 Reported-by: Laurence Oberman <loberman(a)redhat.com> Reported-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reported-by: magicyan2022 Reviewed-by: Himanshu Madhani <himanshu.madhani(a)oracle.com> Signed-off-by: Arun Easi <aeasi(a)marvell.com> Signed-off-by: Nilesh Javali <njavali(a)marvell.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: yin-xiujiang <yinxiujiang(a)kylinos.cn> --- drivers/scsi/qla2xxx/qla_os.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bfbf213b15c0..8e9d386146ac 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1028,8 +1028,6 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, if (rval != QLA_SUCCESS) { ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3078, "Start scsi failed rval=%d for cmd=%p.\n", rval, cmd); - if (rval == QLA_INTERFACE_ERROR) - goto qc24_free_sp_fail_command; goto qc24_host_busy_free_sp; } @@ -1044,11 +1042,6 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, qc24_target_busy: return SCSI_MLQUEUE_TARGET_BUSY; -qc24_free_sp_fail_command: - sp->free(sp); - CMD_SP(cmd) = NULL; - qla2xxx_rel_qpair_sp(sp->qpair, sp); - qc24_fail_command: cmd->scsi_done(cmd); -- 2.27.0

3 2

[PATCH openEuler-21.09 2/2] tools: add a tool to calculate the idle rate
by Hongyu Li 30 Sep '21

30 Sep '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- This tool can help calculate the CPU idle rate in higher precision. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- tools/accounting/Makefile | 2 +- tools/accounting/idle_cal.c | 91 +++++++++++++++++++++++++++++++++++++ 2 files changed, 92 insertions(+), 1 deletion(-) create mode 100644 tools/accounting/idle_cal.c diff --git a/tools/accounting/Makefile b/tools/accounting/Makefile index 03687f19cbb1..d14151e28173 100644 --- a/tools/accounting/Makefile +++ b/tools/accounting/Makefile @@ -2,7 +2,7 @@ CC := $(CROSS_COMPILE)gcc CFLAGS := -I../../usr/include -PROGS := getdelays +PROGS := getdelays idle_cal all: $(PROGS) diff --git a/tools/accounting/idle_cal.c b/tools/accounting/idle_cal.c new file mode 100644 index 000000000000..397b0fc1c69c --- /dev/null +++ b/tools/accounting/idle_cal.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * idle_cal.c + * + * Copyright (C) 2007 + * + * cpu idle time accouting + */ + + +#include <stdlib.h> +#include <stdio.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <time.h> +#include <limits.h> +#include <sys/time.h> + +#define CPUS 4 +#define BUFFSIZE 4096 +#define HZ 100 +#define FILE_NAME "/proc/stat2" + +struct cpu_info { + char name[BUFFSIZE]; + long long value[1]; +}; + +int main(void) +{ + char buf[BUFFSIZE]; + struct cpu_info cpus[CPUS+1]; + struct cpu_info cpus_2[CPUS+1]; + long long sub; + double value; + + FILE *fp = fopen(FILE_NAME, "r"); + int i = 0; + struct timeval start, end; + + + while (i < CPUS+1) { + int n = fscanf(fp, "%s %lld\n", cpus[i].name, &cpus[i].value[0]); + + if (n < 0) { + printf("wrong"); + return -1; + } + i += 1; + } + + for (int i = 0; i < CPUS+1; i++) + printf("%s %lld\n", cpus[i].name, cpus[i].value[0]); + gettimeofday(&start, NULL); + fflush(fp); + fclose(fp); + i = 0; + + sleep(2); + + FILE *fp_2 = fopen(FILE_NAME, "r"); + + while (i < CPUS+1) { + int n = fscanf(fp_2, "%s %lld\n", cpus_2[i].name, &cpus_2[i].value[0]); + + if (n < 0) { + printf("wrong"); + return -1; + } + i += 1; + } + + for (int i = 0; i < CPUS+1; i++) + printf("%s %lld\n", cpus_2[i].name, cpus_2[i].value[0]); + gettimeofday(&end, NULL); + fclose(fp_2); + + sub = end.tv_sec-start.tv_sec; + value = sub*1000000.0+end.tv_usec-start.tv_usec; + + printf("CPU idle rate %f\n", 1000000/HZ*(cpus_2[0].value[0]-cpus[0].value[0])/value); + + for (int i = 1; i < CPUS+1; i++) { + printf("CPU%d idle rate %f\n", i-1, 1000000/HZ + *(cpus_2[i].value[0]-cpus[i].value[0])/value); + } + + return 0; +} + -- 2.17.1

2 1

[PATCH openEuler-21.09 1/2] eulerfs: add the /proc/stat2 file.
by Hongyu Li 30 Sep '21

30 Sep '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- The default way of calculating CPU utilization is to check which task is executed during the interval of two ticks. This leads to the inaccurate results of CPU utilization. This problem can be solved by counting the idle time via scheduler rather than the tick interval. We can record the time before executing idle process and calculate the execute time before quiting the idle process. The idle time of each CPU is given in the /proc/stat2 file. This way can give higher precision in accounting the CPU idle time compared with the /proc/stat. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++++ kernel/sched/idle.c | 28 +++++++++++++ 5 files changed, 161 insertions(+) create mode 100644 fs/proc/stat2.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..33588a37579e 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/stat2 file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/stat2 file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..b0d5f2b347d7 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += stat2.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/stat2.c b/fs/proc/stat2.c new file mode 100644 index 000000000000..6036a946c71d --- /dev/null +++ b/fs/proc/stat2.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/proc/stat2.c + * + * Copyright (C) 2007 + * + * cpu idle time accouting + */ + +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "stat2" + +extern u64 cal_idle_sum_exec_runtime(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cal_idle_sum_exec_runtime(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 32 + 32 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..25218a8f822f 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -19,6 +19,8 @@ */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); +extern struct static_key_true proc_idle; + static int sched_clock_irqtime; void enable_sched_clock_irqtime(void) @@ -1078,3 +1080,35 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cal_idle_sum_exec_runtime(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + if (!static_branch_likely(&proc_idle)) + return 0ULL; + + if (rq->curr == rq->idle) { + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return idle; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle += delta_exec; + } + + return idle; +} + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..15f076ab5823 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -10,6 +10,8 @@ #include <trace/events/power.h> +DEFINE_STATIC_KEY_TRUE(proc_idle); + /* Linker adds these: start and end of __cpuidle functions */ extern char __cpuidle_text_start[], __cpuidle_text_end[]; @@ -424,6 +426,23 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + if (!static_branch_likely(&proc_idle)) + return; + + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +455,15 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + if (static_branch_likely(&proc_idle)) { + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; + } +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

2 1

[PATCH openEuler-21.09 0/2] Improve the precisoin of accounuting CPU utilization rate
by Hongyu Li 30 Sep '21

30 Sep '21

The current way of calculating the CPU utilization rate is not accurate. The accounting system only works In the interval of two ticks. However, a process can give up the CPU before the tick ending. This can be fixed by counting the idel time via the scheduler. We can use the sum_exe_runtime of the idle process of each CPU to calculate the the CPU utilization rate. The idle time of each CPU is given in the /proc/stat2 file. An example of using this file is also attached. Hongyu Li (2): eulerfs: add the /proc/stat2 file. tools: add a tool to calculate the idle rate fs/proc/Kconfig | 7 +++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 +++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++ kernel/sched/idle.c | 28 ++++++++++++ tools/accounting/Makefile | 2 +- tools/accounting/idle_cal.c | 91 +++++++++++++++++++++++++++++++++++++ 7 files changed, 253 insertions(+), 1 deletion(-) create mode 100644 fs/proc/stat2.c create mode 100644 tools/accounting/idle_cal.c -- 2.17.1

1 0

Does Euler 2.9 support BPFTrace Or not?
by Wangpeng (Forest, ISCP SRE) 30 Sep '21

30 Sep '21

Hi Community: Does Euler 2.9 support BPFTrace Or not? It is very necessary for us now. B.R.

2 1

[PATCH openEuler-21.09] eulerfs: add the /proc/stat2 file.
by Hongyu Li 30 Sep '21

30 Sep '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- The default way of calculating CPU utilization is to check which task is executed during the interval of two ticks. This leads to the inaccurate results of CPU utilization. This problem can be solved by counting the idle time via scheduler rather than the tick interval. We can record the time before executing idle process and calculate the execute time before quiting the idle process. The idle time of each CPU is given in the /proc/stat2 file. This way can give higher precision in accounting the CPU idle time compared with the /proc/stat. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++++ kernel/sched/idle.c | 28 +++++++++++++ 5 files changed, 161 insertions(+) create mode 100644 fs/proc/stat2.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..33588a37579e 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/stat2 file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/stat2 file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..b0d5f2b347d7 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += stat2.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/stat2.c b/fs/proc/stat2.c new file mode 100644 index 000000000000..6036a946c71d --- /dev/null +++ b/fs/proc/stat2.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/proc/stat2.c + * + * Copyright (C) 2007 + * + * cpu idle time accouting + */ + +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "stat2" + +extern u64 cal_idle_sum_exec_runtime(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cal_idle_sum_exec_runtime(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 32 + 32 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..25218a8f822f 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -19,6 +19,8 @@ */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); +extern struct static_key_true proc_idle; + static int sched_clock_irqtime; void enable_sched_clock_irqtime(void) @@ -1078,3 +1080,35 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cal_idle_sum_exec_runtime(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + if (!static_branch_likely(&proc_idle)) + return 0ULL; + + if (rq->curr == rq->idle) { + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return idle; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle += delta_exec; + } + + return idle; +} + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..15f076ab5823 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -10,6 +10,8 @@ #include <trace/events/power.h> +DEFINE_STATIC_KEY_TRUE(proc_idle); + /* Linker adds these: start and end of __cpuidle functions */ extern char __cpuidle_text_start[], __cpuidle_text_end[]; @@ -424,6 +426,23 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + if (!static_branch_likely(&proc_idle)) + return; + + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +455,15 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + if (static_branch_likely(&proc_idle)) { + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; + } +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

1 0

[PATCH openEuler-21.09] eulerfs: add the /proc/idle file.
by Hongyu Li 30 Sep '21

30 Sep '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- The default way of calculating CPU utilization is to check which task is executed during the interval of two ticks. This leads to the inaccurate results of CPU utilization. This problem can be solved by counting the idle time via scheduler rather than the tick interval. We can record the time before executing idle process and calculate the execute time before quiting the idle process. The idle time of each CPU is given in the /proc/stat2 file. This way can give higher precision in accounting the CPU idle time compared with the /proc/stat. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++++ kernel/sched/idle.c | 28 +++++++++++++ 5 files changed, 161 insertions(+) create mode 100644 fs/proc/stat2.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..33588a37579e 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/stat2 file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/stat2 file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..b0d5f2b347d7 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += stat2.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/stat2.c b/fs/proc/stat2.c new file mode 100644 index 000000000000..6036a946c71d --- /dev/null +++ b/fs/proc/stat2.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/proc/stat2.c + * + * Copyright (C) 2007 + * + * cpu idle time accouting + */ + +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "stat2" + +extern u64 cal_idle_sum_exec_runtime(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cal_idle_sum_exec_runtime(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 32 + 32 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..25218a8f822f 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -19,6 +19,8 @@ */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); +extern struct static_key_true proc_idle; + static int sched_clock_irqtime; void enable_sched_clock_irqtime(void) @@ -1078,3 +1080,35 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cal_idle_sum_exec_runtime(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + if (!static_branch_likely(&proc_idle)) + return 0ULL; + + if (rq->curr == rq->idle) { + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return idle; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle += delta_exec; + } + + return idle; +} + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..15f076ab5823 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -10,6 +10,8 @@ #include <trace/events/power.h> +DEFINE_STATIC_KEY_TRUE(proc_idle); + /* Linker adds these: start and end of __cpuidle functions */ extern char __cpuidle_text_start[], __cpuidle_text_end[]; @@ -424,6 +426,23 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + if (!static_branch_likely(&proc_idle)) + return; + + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +455,15 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + if (static_branch_likely(&proc_idle)) { + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; + } +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

1 0

[PATCH OLK-5.10 1/9] mm: add Kernel Electric-Fence infrastructure
by 1415317271＠qq.com 30 Sep '21

30 Sep '21

From: Alexander Potapenko <glider(a)google.com> Patch series "KFENCE: A low-overhead sampling-based memory safety error detector", v7. This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. This series enables KFENCE for the x86 and arm64 architectures, and adds KFENCE hooks to the SLAB and SLUB allocators. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, the next allocation through the main allocator (SLAB or SLUB) returns a guarded allocation from the KFENCE object pool. At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. The KFENCE memory pool is of fixed size, and if the pool is exhausted no further KFENCE allocations occur. The default config is conservative with only 255 objects, resulting in a pool size of 2 MiB (with 4 KiB pages). We have verified by running synthetic benchmarks (sysbench I/O, hackbench) and production server-workload benchmarks that a kernel with KFENCE (using sample intervals 100-500ms) is performance-neutral compared to a non-KFENCE baseline kernel. KFENCE is inspired by GWP-ASan [1], a userspace tool with similar properties. The name "KFENCE" is a homage to the Electric Fence Malloc Debugger [2]. For more details, see Documentation/dev-tools/kfence.rst added in the series -- also viewable here: https://raw.githubusercontent.com/google/kasan/kfence/Documentation/dev-too… [1] http://llvm.org/docs/GwpAsan.html [2] https://linux.die.net/man/3/efence This patch (of 9): This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. To detect out-of-bounds writes to memory within the object's page itself, KFENCE also uses pattern-based redzones. The following figure illustrates the page layout: ---+-----------+-----------+-----------+-----------+-----------+--- | xxxxxxxxx | O : | xxxxxxxxx | : O | xxxxxxxxx | | xxxxxxxxx | B : | xxxxxxxxx | : B | xxxxxxxxx | | x GUARD x | J : RED- | x GUARD x | RED- : J | x GUARD x | | xxxxxxxxx | E : ZONE | xxxxxxxxx | ZONE : E | xxxxxxxxx | | xxxxxxxxx | C : | xxxxxxxxx | : C | xxxxxxxxx | | xxxxxxxxx | T : | xxxxxxxxx | : T | xxxxxxxxx | ---+-----------+-----------+-----------+-----------+-----------+--- Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, a guarded allocation from the KFENCE object pool is returned to the main allocator (SLAB or SLUB). At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. To date, we have verified by running synthetic benchmarks (sysbench I/O, hackbench) that a kernel compiled with KFENCE is performance-neutral compared to the non-KFENCE baseline. For more details, see Documentation/dev-tools/kfence.rst (added later in the series). [elver(a)google.com: fix parameter description for kfence_object_start()] Link: https://lkml.kernel.org/r/20201106092149.GA2851373@elver.google.com [elver(a)google.com: avoid stalling work queue task without allocations] Link: https://lkml.kernel.org/r/CADYN=9J0DQhizAGB0-jz4HOBBh+05kMBXb4c0cXMS7Qi5NAJ… Link: https://lkml.kernel.org/r/20201110135320.3309507-1-elver@google.com [elver(a)google.com: fix potential deadlock due to wake_up()] Link: https://lkml.kernel.org/r/000000000000c0645805b7f982e4@google.com Link: https://lkml.kernel.org/r/20210104130749.1768991-1-elver@google.com [elver(a)google.com: add option to use KFENCE without static keys] Link: https://lkml.kernel.org/r/20210111091544.3287013-1-elver@google.com [elver(a)google.com: add missing copyright and description headers] Link: https://lkml.kernel.org/r/20210118092159.145934-1-elver@google.com Link: https://lkml.kernel.org/r/20201103175841.3495947-2-elver@google.com Signed-off-by: Marco Elver <elver(a)google.com> Signed-off-by: Alexander Potapenko <glider(a)google.com> Reviewed-by: Dmitry Vyukov <dvyukov(a)google.com> Reviewed-by: SeongJae Park <sjpark(a)amazon.de> Co-developed-by: Marco Elver <elver(a)google.com> Reviewed-by: Jann Horn <jannh(a)google.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Paul E. McKenney <paulmck(a)kernel.org> Cc: Andrey Konovalov <andreyknvl(a)google.com> Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Christopher Lameter <cl(a)linux.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David Rientjes <rientjes(a)google.com> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Cc: Joern Engel <joern(a)purestorage.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Pekka Enberg <penberg(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Will Deacon <will(a)kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Yingjie Shang <1415317271(a)qq.com> Reviewed-by: Bixuan Cui <cuibixuan(a)huawei.com> --- include/linux/kfence.h | 216 +++++++++++ init/main.c | 3 + lib/Kconfig.debug | 1 + lib/Kconfig.kfence | 67 ++++ mm/Makefile | 1 + mm/kfence/Makefile | 3 + mm/kfence/core.c | 840 +++++++++++++++++++++++++++++++++++++++++ mm/kfence/kfence.h | 113 ++++++ mm/kfence/report.c | 240 ++++++++++++ 9 files changed, 1484 insertions(+) create mode 100644 include/linux/kfence.h create mode 100644 lib/Kconfig.kfence create mode 100644 mm/kfence/Makefile create mode 100644 mm/kfence/core.c create mode 100644 mm/kfence/kfence.h create mode 100644 mm/kfence/report.c diff --git a/include/linux/kfence.h b/include/linux/kfence.h new file mode 100644 index 000000000000..81f3911cb298 --- /dev/null +++ b/include/linux/kfence.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). Public interface for allocator and fault + * handler integration. For more info see Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _LINUX_KFENCE_H +#define _LINUX_KFENCE_H + +#include <linux/mm.h> +#include <linux/types.h> + +#ifdef CONFIG_KFENCE + +/* + * We allocate an even number of pages, as it simplifies calculations to map + * address to metadata indices; effectively, the very first page serves as an + * extended guard page, but otherwise has no special purpose. + */ +#define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) +extern char *__kfence_pool; + +#ifdef CONFIG_KFENCE_STATIC_KEYS +#include <linux/static_key.h> +DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); +#else +#include <linux/atomic.h> +extern atomic_t kfence_allocation_gate; +#endif + +/** + * is_kfence_address() - check if an address belongs to KFENCE pool + * @addr: address to check + * + * Return: true or false depending on whether the address is within the KFENCE + * object range. + * + * KFENCE objects live in a separate page range and are not to be intermixed + * with regular heap objects (e.g. KFENCE objects must never be added to the + * allocator freelists). Failing to do so may and will result in heap + * corruptions, therefore is_kfence_address() must be used to check whether + * an object requires specific handling. + * + * Note: This function may be used in fast-paths, and is performance critical. + * Future changes should take this into account; for instance, we want to avoid + * introducing another load and therefore need to keep KFENCE_POOL_SIZE a + * constant (until immediate patching support is added to the kernel). + */ +static __always_inline bool is_kfence_address(const void *addr) +{ + /* + * The non-NULL check is required in case the __kfence_pool pointer was + * never initialized; keep it in the slow-path after the range-check. + */ + return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr); +} + +/** + * kfence_alloc_pool() - allocate the KFENCE pool via memblock + */ +void __init kfence_alloc_pool(void); + +/** + * kfence_init() - perform KFENCE initialization at boot time + * + * Requires that kfence_alloc_pool() was called before. This sets up the + * allocation gate timer, and requires that workqueues are available. + */ +void __init kfence_init(void); + +/** + * kfence_shutdown_cache() - handle shutdown_cache() for KFENCE objects + * @s: cache being shut down + * + * Before shutting down a cache, one must ensure there are no remaining objects + * allocated from it. Because KFENCE objects are not referenced from the cache + * directly, we need to check them here. + * + * Note that shutdown_cache() is internal to SL*B, and kmem_cache_destroy() does + * not return if allocated objects still exist: it prints an error message and + * simply aborts destruction of a cache, leaking memory. + * + * If the only such objects are KFENCE objects, we will not leak the entire + * cache, but instead try to provide more useful debug info by making allocated + * objects "zombie allocations". Objects may then still be used or freed (which + * is handled gracefully), but usage will result in showing KFENCE error reports + * which include stack traces to the user of the object, the original allocation + * site, and caller to shutdown_cache(). + */ +void kfence_shutdown_cache(struct kmem_cache *s); + +/* + * Allocate a KFENCE object. Allocators must not call this function directly, + * use kfence_alloc() instead. + */ +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); + +/** + * kfence_alloc() - allocate a KFENCE object with a low probability + * @s: struct kmem_cache with object requirements + * @size: exact size of the object to allocate (can be less than @s->size + * e.g. for kmalloc caches) + * @flags: GFP flags + * + * Return: + * * NULL - must proceed with allocating as usual, + * * non-NULL - pointer to a KFENCE object. + * + * kfence_alloc() should be inserted into the heap allocation fast path, + * allowing it to transparently return KFENCE-allocated objects with a low + * probability using a static branch (the probability is controlled by the + * kfence.sample_interval boot parameter). + */ +static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ +#ifdef CONFIG_KFENCE_STATIC_KEYS + if (static_branch_unlikely(&kfence_allocation_key)) +#else + if (unlikely(!atomic_read(&kfence_allocation_gate))) +#endif + return __kfence_alloc(s, size, flags); + return NULL; +} + +/** + * kfence_ksize() - get actual amount of memory allocated for a KFENCE object + * @addr: pointer to a heap object + * + * Return: + * * 0 - not a KFENCE object, must call __ksize() instead, + * * non-0 - this many bytes can be accessed without causing a memory error. + * + * kfence_ksize() returns the number of bytes requested for a KFENCE object at + * allocation time. This number may be less than the object size of the + * corresponding struct kmem_cache. + */ +size_t kfence_ksize(const void *addr); + +/** + * kfence_object_start() - find the beginning of a KFENCE object + * @addr: address within a KFENCE-allocated object + * + * Return: address of the beginning of the object. + * + * SL[AU]B-allocated objects are laid out within a page one by one, so it is + * easy to calculate the beginning of an object given a pointer inside it and + * the object size. The same is not true for KFENCE, which places a single + * object at either end of the page. This helper function is used to find the + * beginning of a KFENCE-allocated object. + */ +void *kfence_object_start(const void *addr); + +/** + * __kfence_free() - release a KFENCE heap object to KFENCE pool + * @addr: object to be freed + * + * Requires: is_kfence_address(addr) + * + * Release a KFENCE object and mark it as freed. + */ +void __kfence_free(void *addr); + +/** + * kfence_free() - try to release an arbitrary heap object to KFENCE pool + * @addr: object to be freed + * + * Return: + * * false - object doesn't belong to KFENCE pool and was ignored, + * * true - object was released to KFENCE pool. + * + * Release a KFENCE object and mark it as freed. May be called on any object, + * even non-KFENCE objects, to simplify integration of the hooks into the + * allocator's free codepath. The allocator must check the return value to + * determine if it was a KFENCE object or not. + */ +static __always_inline __must_check bool kfence_free(void *addr) +{ + if (!is_kfence_address(addr)) + return false; + __kfence_free(addr); + return true; +} + +/** + * kfence_handle_page_fault() - perform page fault handling for KFENCE pages + * @addr: faulting address + * + * Return: + * * false - address outside KFENCE pool, + * * true - page fault handled by KFENCE, no additional handling required. + * + * A page fault inside KFENCE pool indicates a memory error, such as an + * out-of-bounds access, a use-after-free or an invalid memory access. In these + * cases KFENCE prints an error message and marks the offending page as + * present, so that the kernel can proceed. + */ +bool __must_check kfence_handle_page_fault(unsigned long addr); + +#else /* CONFIG_KFENCE */ + +static inline bool is_kfence_address(const void *addr) { return false; } +static inline void kfence_alloc_pool(void) { } +static inline void kfence_init(void) { } +static inline void kfence_shutdown_cache(struct kmem_cache *s) { } +static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; } +static inline size_t kfence_ksize(const void *addr) { return 0; } +static inline void *kfence_object_start(const void *addr) { return NULL; } +static inline void __kfence_free(void *addr) { } +static inline bool __must_check kfence_free(void *addr) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr) { return false; } + +#endif + +#endif /* _LINUX_KFENCE_H */ diff --git a/init/main.c b/init/main.c index fc0277a9e7a3..2d027dc11b10 100644 --- a/init/main.c +++ b/init/main.c @@ -40,6 +40,7 @@ #include <linux/security.h> #include <linux/smp.h> #include <linux/profile.h> +#include <linux/kfence.h> #include <linux/rcupdate.h> #include <linux/moduleparam.h> #include <linux/kallsyms.h> @@ -828,6 +829,7 @@ static void __init mm_init(void) */ page_ext_init_flatmem(); init_debug_pagealloc(); + kfence_alloc_pool(); report_meminit(); mem_init(); kmem_cache_init(); @@ -956,6 +958,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) hrtimers_init(); softirq_init(); timekeeping_init(); + kfence_init(); /* * For best initial stack canary entropy, prepare it after: diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 799e49a29797..29e64b4cd412 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -878,6 +878,7 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". source "lib/Kconfig.kasan" +source "lib/Kconfig.kfence" endmenu # "Memory Debugging" diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence new file mode 100644 index 000000000000..b88ac9d6b2e6 --- /dev/null +++ b/lib/Kconfig.kfence @@ -0,0 +1,67 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config HAVE_ARCH_KFENCE + bool + +menuconfig KFENCE + bool "KFENCE: low-overhead sampling-based memory safety error detector" + depends on HAVE_ARCH_KFENCE && !KASAN && (SLAB || SLUB) + select STACKTRACE + help + KFENCE is a low-overhead sampling-based detector of heap out-of-bounds + access, use-after-free, and invalid-free errors. KFENCE is designed + to have negligible cost to permit enabling it in production + environments. + + Note that, KFENCE is not a substitute for explicit testing with tools + such as KASAN. KFENCE can detect a subset of bugs that KASAN can + detect, albeit at very different performance profiles. If you can + afford to use KASAN, continue using KASAN, for example in test + environments. If your kernel targets production use, and cannot + enable KASAN due to its cost, consider using KFENCE. + +if KFENCE + +config KFENCE_STATIC_KEYS + bool "Use static keys to set up allocations" + default y + depends on JUMP_LABEL # To ensure performance, require jump labels + help + Use static keys (static branches) to set up KFENCE allocations. Using + static keys is normally recommended, because it avoids a dynamic + branch in the allocator's fast path. However, with very low sample + intervals, or on systems that do not support jump labels, a dynamic + branch may still be an acceptable performance trade-off. + +config KFENCE_SAMPLE_INTERVAL + int "Default sample interval in milliseconds" + default 100 + help + The KFENCE sample interval determines the frequency with which heap + allocations will be guarded by KFENCE. May be overridden via boot + parameter "kfence.sample_interval". + + Set this to 0 to disable KFENCE by default, in which case only + setting "kfence.sample_interval" to a non-zero value enables KFENCE. + +config KFENCE_NUM_OBJECTS + int "Number of guarded objects available" + range 1 65535 + default 255 + help + The number of guarded objects available. For each KFENCE object, 2 + pages are required; with one containing the object and two adjacent + ones used as guard pages. + +config KFENCE_STRESS_TEST_FAULTS + int "Stress testing of fault handling and error reporting" if EXPERT + default 0 + help + The inverse probability with which to randomly protect KFENCE object + pages, resulting in spurious use-after-frees. The main purpose of + this option is to stress test KFENCE with concurrent error reports + and allocations/frees. A value of 0 disables stress testing logic. + + Only for KFENCE testing; set to 0 if you are not a KFENCE developer. + +endif # KFENCE diff --git a/mm/Makefile b/mm/Makefile index 2b1991759835..3d81a67d66a2 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -82,6 +82,7 @@ obj-$(CONFIG_PAGE_POISONING) += page_poison.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_KASAN) += kasan/ +obj-$(CONFIG_KFENCE) += kfence/ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile new file mode 100644 index 000000000000..d991e9a349f0 --- /dev/null +++ b/mm/kfence/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_KFENCE) := core.o report.o diff --git a/mm/kfence/core.c b/mm/kfence/core.c new file mode 100644 index 000000000000..d6a32c13336b --- /dev/null +++ b/mm/kfence/core.c @@ -0,0 +1,840 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE guarded object allocator and fault handling. + * + * Copyright (C) 2020, Google LLC. + */ + +#define pr_fmt(fmt) "kfence: " fmt + +#include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/debugfs.h> +#include <linux/kcsan-checks.h> +#include <linux/kfence.h> +#include <linux/list.h> +#include <linux/lockdep.h> +#include <linux/memblock.h> +#include <linux/moduleparam.h> +#include <linux/random.h> +#include <linux/rcupdate.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/string.h> + +#include <asm/kfence.h> + +#include "kfence.h" + +/* Disables KFENCE on the first warning assuming an irrecoverable error. */ +#define KFENCE_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) \ + WRITE_ONCE(kfence_enabled, false); \ + __cond; \ + }) + +/* === Data ================================================================= */ + +static bool kfence_enabled __read_mostly; + +static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "kfence." + +static int param_set_sample_interval(const char *val, const struct kernel_param *kp) +{ + unsigned long num; + int ret = kstrtoul(val, 0, &num); + + if (ret < 0) + return ret; + + if (!num) /* Using 0 to indicate KFENCE is disabled. */ + WRITE_ONCE(kfence_enabled, false); + else if (!READ_ONCE(kfence_enabled) && system_state != SYSTEM_BOOTING) + return -EINVAL; /* Cannot (re-)enable KFENCE on-the-fly. */ + + *((unsigned long *)kp->arg) = num; + return 0; +} + +static int param_get_sample_interval(char *buffer, const struct kernel_param *kp) +{ + if (!READ_ONCE(kfence_enabled)) + return sprintf(buffer, "0\n"); + + return param_get_ulong(buffer, kp); +} + +static const struct kernel_param_ops sample_interval_param_ops = { + .set = param_set_sample_interval, + .get = param_get_sample_interval, +}; +module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600); + +/* The pool of pages used for guard pages and objects. */ +char *__kfence_pool __ro_after_init; +EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ + +/* + * Per-object metadata, with one-to-one mapping of object metadata to + * backing pages (in __kfence_pool). + */ +static_assert(CONFIG_KFENCE_NUM_OBJECTS > 0); +struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* Freelist with available objects. */ +static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); +static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ + +#ifdef CONFIG_KFENCE_STATIC_KEYS +/* The static key to set up a KFENCE allocation. */ +DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); +#endif + +/* Gates the allocation, ensuring only one succeeds in a given period. */ +atomic_t kfence_allocation_gate = ATOMIC_INIT(1); + +/* Statistics counters for debugfs. */ +enum kfence_counter_id { + KFENCE_COUNTER_ALLOCATED, + KFENCE_COUNTER_ALLOCS, + KFENCE_COUNTER_FREES, + KFENCE_COUNTER_ZOMBIES, + KFENCE_COUNTER_BUGS, + KFENCE_COUNTER_COUNT, +}; +static atomic_long_t counters[KFENCE_COUNTER_COUNT]; +static const char *const counter_names[] = { + [KFENCE_COUNTER_ALLOCATED] = "currently allocated", + [KFENCE_COUNTER_ALLOCS] = "total allocations", + [KFENCE_COUNTER_FREES] = "total frees", + [KFENCE_COUNTER_ZOMBIES] = "zombie allocations", + [KFENCE_COUNTER_BUGS] = "total bugs", +}; +static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); + +/* === Internals ============================================================ */ + +static bool kfence_protect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true)); +} + +static bool kfence_unprotect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); +} + +static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + +static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) +{ + unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; + unsigned long pageaddr = (unsigned long)&__kfence_pool[offset]; + + /* The checks do not affect performance; only called from slow-paths. */ + + /* Only call with a pointer into kfence_metadata. */ + if (KFENCE_WARN_ON(meta < kfence_metadata || + meta >= kfence_metadata + CONFIG_KFENCE_NUM_OBJECTS)) + return 0; + + /* + * This metadata object only ever maps to 1 page; verify that the stored + * address is in the expected range. + */ + if (KFENCE_WARN_ON(ALIGN_DOWN(meta->addr, PAGE_SIZE) != pageaddr)) + return 0; + + return pageaddr; +} + +/* + * Update the object's metadata state, including updating the alloc/free stacks + * depending on the state transition. + */ +static noinline void metadata_update_state(struct kfence_metadata *meta, + enum kfence_object_state next) +{ + struct kfence_track *track = + next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track; + + lockdep_assert_held(&meta->lock); + + /* + * Skip over 1 (this) functions; noinline ensures we do not accidentally + * skip over the caller by never inlining. + */ + track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + track->pid = task_pid_nr(current); + + /* + * Pairs with READ_ONCE() in + * kfence_shutdown_cache(), + * kfence_handle_page_fault(). + */ + WRITE_ONCE(meta->state, next); +} + +/* Write canary byte to @addr. */ +static inline bool set_canary_byte(u8 *addr) +{ + *addr = KFENCE_CANARY_PATTERN(addr); + return true; +} + +/* Check canary byte at @addr. */ +static inline bool check_canary_byte(u8 *addr) +{ + if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) + return true; + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, addr_to_metadata((unsigned long)addr), + KFENCE_ERROR_CORRUPTION); + return false; +} + +/* __always_inline this to ensure we won't do an indirect call to fn. */ +static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *)) +{ + const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); + unsigned long addr; + + lockdep_assert_held(&meta->lock); + + /* + * We'll iterate over each canary byte per-side until fn() returns + * false. However, we'll still iterate over the canary bytes to the + * right of the object even if there was an error in the canary bytes to + * the left of the object. Specifically, if check_canary_byte() + * generates an error, showing both sides might give more clues as to + * what the error is about when displaying which bytes were corrupted. + */ + + /* Apply to left of object. */ + for (addr = pageaddr; addr < meta->addr; addr++) { + if (!fn((u8 *)addr)) + break; + } + + /* Apply to right of object. */ + for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) { + if (!fn((u8 *)addr)) + break; + } +} + +static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp) +{ + struct kfence_metadata *meta = NULL; + unsigned long flags; + struct page *page; + void *addr; + + /* Try to obtain a free object. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + if (!list_empty(&kfence_freelist)) { + meta = list_entry(kfence_freelist.next, struct kfence_metadata, list); + list_del_init(&meta->list); + } + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + if (!meta) + return NULL; + + if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) { + /* + * This is extremely unlikely -- we are reporting on a + * use-after-free, which locked meta->lock, and the reporting + * code via printk calls kmalloc() which ends up in + * kfence_alloc() and tries to grab the same object that we're + * reporting on. While it has never been observed, lockdep does + * report that there is a possibility of deadlock. Fix it by + * using trylock and bailing out gracefully. + */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + /* Put the object back on the freelist. */ + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + return NULL; + } + + meta->addr = metadata_to_pageaddr(meta); + /* Unprotect if we're reusing this page. */ + if (meta->state == KFENCE_OBJECT_FREED) + kfence_unprotect(meta->addr); + + /* + * Note: for allocations made before RNG initialization, will always + * return zero. We still benefit from enabling KFENCE as early as + * possible, even when the RNG is not yet available, as this will allow + * KFENCE to detect bugs due to earlier allocations. The only downside + * is that the out-of-bounds accesses detected are deterministic for + * such allocations. + */ + if (prandom_u32_max(2)) { + /* Allocate on the "right" side, re-calculate address. */ + meta->addr += PAGE_SIZE - size; + meta->addr = ALIGN_DOWN(meta->addr, cache->align); + } + + addr = (void *)meta->addr; + + /* Update remaining metadata. */ + metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED); + /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ + WRITE_ONCE(meta->cache, cache); + meta->size = size; + for_each_canary(meta, set_canary_byte); + + /* Set required struct page fields. */ + page = virt_to_page(meta->addr); + page->slab_cache = cache; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Memory initialization. */ + + /* + * We check slab_want_init_on_alloc() ourselves, rather than letting + * SL*B do the initialization, as otherwise we might overwrite KFENCE's + * redzone. + */ + if (unlikely(slab_want_init_on_alloc(gfp, cache))) + memzero_explicit(addr, size); + if (cache->ctor) + cache->ctor(addr); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS && !prandom_u32_max(CONFIG_KFENCE_STRESS_TEST_FAULTS)) + kfence_protect(meta->addr); /* Random "faults" by protecting the object. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCS]); + + return addr; +} + +static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool zombie) +{ + struct kcsan_scoped_access assert_page_exclusive; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + + if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) { + /* Invalid or double-free, bail out. */ + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, meta, KFENCE_ERROR_INVALID_FREE); + raw_spin_unlock_irqrestore(&meta->lock, flags); + return; + } + + /* Detect racy use-after-free, or incorrect reallocation of this page by KFENCE. */ + kcsan_begin_scoped_access((void *)ALIGN_DOWN((unsigned long)addr, PAGE_SIZE), PAGE_SIZE, + KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT, + &assert_page_exclusive); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS) + kfence_unprotect((unsigned long)addr); /* To check canary bytes. */ + + /* Restore page protection if there was an OOB access. */ + if (meta->unprotected_page) { + kfence_protect(meta->unprotected_page); + meta->unprotected_page = 0; + } + + /* Check canary bytes for memory corruption. */ + for_each_canary(meta, check_canary_byte); + + /* + * Clear memory if init-on-free is set. While we protect the page, the + * data is still there, and after a use-after-free is detected, we + * unprotect the page, so the data is still accessible. + */ + if (!zombie && unlikely(slab_want_init_on_free(meta->cache))) + memzero_explicit(addr, meta->size); + + /* Mark the object as freed. */ + metadata_update_state(meta, KFENCE_OBJECT_FREED); + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Protect to detect use-after-frees. */ + kfence_protect((unsigned long)addr); + + kcsan_end_scoped_access(&assert_page_exclusive); + if (!zombie) { + /* Add it to the tail of the freelist for reuse. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + KFENCE_WARN_ON(!list_empty(&meta->list)); + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + atomic_long_dec(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_FREES]); + } else { + /* See kfence_shutdown_cache(). */ + atomic_long_inc(&counters[KFENCE_COUNTER_ZOMBIES]); + } +} + +static void rcu_guarded_free(struct rcu_head *h) +{ + struct kfence_metadata *meta = container_of(h, struct kfence_metadata, rcu_head); + + kfence_guarded_free((void *)meta->addr, meta, false); +} + +static bool __init kfence_init_pool(void) +{ + unsigned long addr = (unsigned long)__kfence_pool; + struct page *pages; + int i; + + if (!__kfence_pool) + return false; + + if (!arch_kfence_init_pool()) + goto err; + + pages = virt_to_page(addr); + + /* + * Set up object pages: they must have PG_slab set, to avoid freeing + * these as real pages. + * + * We also want to avoid inserting kfence_free() in the kfree() + * fast-path in SLUB, and therefore need to ensure kfree() correctly + * enters __slab_free() slow-path. + */ + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { + if (!i || (i % 2)) + continue; + + /* Verify we do not have a compound head page. */ + if (WARN_ON(compound_head(&pages[i]) != &pages[i])) + goto err; + + __SetPageSlab(&pages[i]); + } + + /* + * Protect the first 2 pages. The first page is mostly unnecessary, and + * merely serves as an extended guard page. However, adding one + * additional page in the beginning gives us an even number of pages, + * which simplifies the mapping of address to metadata index. + */ + for (i = 0; i < 2; i++) { + if (unlikely(!kfence_protect(addr))) + goto err; + + addr += PAGE_SIZE; + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta = &kfence_metadata[i]; + + /* Initialize metadata. */ + INIT_LIST_HEAD(&meta->list); + raw_spin_lock_init(&meta->lock); + meta->state = KFENCE_OBJECT_UNUSED; + meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ + list_add_tail(&meta->list, &kfence_freelist); + + /* Protect the right redzone. */ + if (unlikely(!kfence_protect(addr + PAGE_SIZE))) + goto err; + + addr += 2 * PAGE_SIZE; + } + + return true; + +err: + /* + * Only release unprotected pages, and do not try to go back and change + * page attributes due to risk of failing to do so as well. If changing + * page attributes for some pages fails, it is very likely that it also + * fails for the first page, and therefore expect addr==__kfence_pool in + * most failure cases. + */ + memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); + __kfence_pool = NULL; + return false; +} + +/* === DebugFS Interface ==================================================== */ + +static int stats_show(struct seq_file *seq, void *v) +{ + int i; + + seq_printf(seq, "enabled: %i\n", READ_ONCE(kfence_enabled)); + for (i = 0; i < KFENCE_COUNTER_COUNT; i++) + seq_printf(seq, "%s: %ld\n", counter_names[i], atomic_long_read(&counters[i])); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(stats); + +/* + * debugfs seq_file operations for /sys/kernel/debug/kfence/objects. + * start_object() and next_object() return the object index + 1, because NULL is used + * to stop iteration. + */ +static void *start_object(struct seq_file *seq, loff_t *pos) +{ + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static void stop_object(struct seq_file *seq, void *v) +{ +} + +static void *next_object(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static int show_object(struct seq_file *seq, void *v) +{ + struct kfence_metadata *meta = &kfence_metadata[(long)v - 1]; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + kfence_print_object(seq, meta); + raw_spin_unlock_irqrestore(&meta->lock, flags); + seq_puts(seq, "---------------------------------\n"); + + return 0; +} + +static const struct seq_operations object_seqops = { + .start = start_object, + .next = next_object, + .stop = stop_object, + .show = show_object, +}; + +static int open_objects(struct inode *inode, struct file *file) +{ + return seq_open(file, &object_seqops); +} + +static const struct file_operations objects_fops = { + .open = open_objects, + .read = seq_read, + .llseek = seq_lseek, +}; + +static int __init kfence_debugfs_init(void) +{ + struct dentry *kfence_dir = debugfs_create_dir("kfence", NULL); + + debugfs_create_file("stats", 0444, kfence_dir, NULL, &stats_fops); + debugfs_create_file("objects", 0400, kfence_dir, NULL, &objects_fops); + return 0; +} + +late_initcall(kfence_debugfs_init); + +/* === Allocation Gate Timer ================================================ */ + +/* + * Set up delayed work, which will enable and disable the static key. We need to + * use a work queue (rather than a simple timer), since enabling and disabling a + * static key cannot be done from an interrupt. + * + * Note: Toggling a static branch currently causes IPIs, and here we'll end up + * with a total of 2 IPIs to all CPUs. If this ends up a problem in future (with + * more aggressive sampling intervals), we could get away with a variant that + * avoids IPIs, at the cost of not immediately capturing allocations if the + * instructions remain cached. + */ +static struct delayed_work kfence_timer; +static void toggle_allocation_gate(struct work_struct *work) +{ + if (!READ_ONCE(kfence_enabled)) + return; + + /* Enable static key, and await allocation to happen. */ + atomic_set(&kfence_allocation_gate, 0); +#ifdef CONFIG_KFENCE_STATIC_KEYS + static_branch_enable(&kfence_allocation_key); + /* + * Await an allocation. Timeout after 1 second, in case the kernel stops + * doing allocations, to avoid stalling this worker task for too long. + */ + { + unsigned long end_wait = jiffies + HZ; + + do { + set_current_state(TASK_UNINTERRUPTIBLE); + if (atomic_read(&kfence_allocation_gate) != 0) + break; + schedule_timeout(1); + } while (time_before(jiffies, end_wait)); + __set_current_state(TASK_RUNNING); + } + /* Disable static key and reset timer. */ + static_branch_disable(&kfence_allocation_key); +#endif + schedule_delayed_work(&kfence_timer, msecs_to_jiffies(kfence_sample_interval)); +} +static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate); + +/* === Public interface ===================================================== */ + +void __init kfence_alloc_pool(void) +{ + if (!kfence_sample_interval) + return; + + __kfence_pool = memblock_alloc(KFENCE_POOL_SIZE, PAGE_SIZE); + + if (!__kfence_pool) + pr_err("failed to allocate pool\n"); +} + +void __init kfence_init(void) +{ + /* Setting kfence_sample_interval to 0 on boot disables KFENCE. */ + if (!kfence_sample_interval) + return; + + if (!kfence_init_pool()) { + pr_err("%s failed\n", __func__); + return; + } + + WRITE_ONCE(kfence_enabled, true); + schedule_delayed_work(&kfence_timer, 0); + pr_info("initialized - using %lu bytes for %d objects", KFENCE_POOL_SIZE, + CONFIG_KFENCE_NUM_OBJECTS); + if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + pr_cont(" at 0x%px-0x%px\n", (void *)__kfence_pool, + (void *)(__kfence_pool + KFENCE_POOL_SIZE)); + else + pr_cont("\n"); +} + +void kfence_shutdown_cache(struct kmem_cache *s) +{ + unsigned long flags; + struct kfence_metadata *meta; + int i; + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + bool in_use; + + meta = &kfence_metadata[i]; + + /* + * If we observe some inconsistent cache and state pair where we + * should have returned false here, cache destruction is racing + * with either kmem_cache_alloc() or kmem_cache_free(). Taking + * the lock will not help, as different critical section + * serialization will have the same outcome. + */ + if (READ_ONCE(meta->cache) != s || + READ_ONCE(meta->state) != KFENCE_OBJECT_ALLOCATED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + in_use = meta->cache == s && meta->state == KFENCE_OBJECT_ALLOCATED; + raw_spin_unlock_irqrestore(&meta->lock, flags); + + if (in_use) { + /* + * This cache still has allocations, and we should not + * release them back into the freelist so they can still + * safely be used and retain the kernel's default + * behaviour of keeping the allocations alive (leak the + * cache); however, they effectively become "zombie + * allocations" as the KFENCE objects are the only ones + * still in use and the owning cache is being destroyed. + * + * We mark them freed, so that any subsequent use shows + * more useful error messages that will include stack + * traces of the user of the object, the original + * allocation, and caller to shutdown_cache(). + */ + kfence_guarded_free((void *)meta->addr, meta, /*zombie=*/true); + } + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + meta = &kfence_metadata[i]; + + /* See above. */ + if (READ_ONCE(meta->cache) != s || READ_ONCE(meta->state) != KFENCE_OBJECT_FREED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + if (meta->cache == s && meta->state == KFENCE_OBJECT_FREED) + meta->cache = NULL; + raw_spin_unlock_irqrestore(&meta->lock, flags); + } +} + +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ + /* + * allocation_gate only needs to become non-zero, so it doesn't make + * sense to continue writing to it and pay the associated contention + * cost, in case we have a large number of concurrent allocations. + */ + if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) + return NULL; + + if (!READ_ONCE(kfence_enabled)) + return NULL; + + if (size > PAGE_SIZE) + return NULL; + + return kfence_guarded_alloc(s, size, flags); +} + +size_t kfence_ksize(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? meta->size : 0; +} + +void *kfence_object_start(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? (void *)meta->addr : NULL; +} + +void __kfence_free(void *addr) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing + * the object, as the object page may be recycled for other-typed + * objects once it has been freed. meta->cache may be NULL if the cache + * was destroyed. + */ + if (unlikely(meta->cache && (meta->cache->flags & SLAB_TYPESAFE_BY_RCU))) + call_rcu(&meta->rcu_head, rcu_guarded_free); + else + kfence_guarded_free(addr, meta, false); +} + +bool kfence_handle_page_fault(unsigned long addr) +{ + const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE; + struct kfence_metadata *to_report = NULL; + enum kfence_error_type error_type; + unsigned long flags; + + if (!is_kfence_address((void *)addr)) + return false; + + if (!READ_ONCE(kfence_enabled)) /* If disabled at runtime ... */ + return kfence_unprotect(addr); /* ... unprotect and proceed. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + + if (page_index % 2) { + /* This is a redzone, report a buffer overflow. */ + struct kfence_metadata *meta; + int distance = 0; + + meta = addr_to_metadata(addr - PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + to_report = meta; + /* Data race ok; distance calculation approximate. */ + distance = addr - data_race(meta->addr + meta->size); + } + + meta = addr_to_metadata(addr + PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + /* Data race ok; distance calculation approximate. */ + if (!to_report || distance > data_race(meta->addr) - addr) + to_report = meta; + } + + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + to_report->unprotected_page = addr; + error_type = KFENCE_ERROR_OOB; + + /* + * If the object was freed before we took the look we can still + * report this as an OOB -- the report will simply show the + * stacktrace of the free as well. + */ + } else { + to_report = addr_to_metadata(addr); + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + error_type = KFENCE_ERROR_UAF; + /* + * We may race with __kfence_alloc(), and it is possible that a + * freed object may be reallocated. We simply report this as a + * use-after-free, with the stack trace showing the place where + * the object was re-allocated. + */ + } + +out: + if (to_report) { + kfence_report_error(addr, to_report, error_type); + raw_spin_unlock_irqrestore(&to_report->lock, flags); + } else { + /* This may be a UAF or OOB access, but we can't be sure. */ + kfence_report_error(addr, NULL, KFENCE_ERROR_INVALID); + } + + return kfence_unprotect(addr); /* Unprotect and let access proceed. */ +} diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h new file mode 100644 index 000000000000..1014060f9707 --- /dev/null +++ b/mm/kfence/kfence.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). For more info please see + * Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef MM_KFENCE_KFENCE_H +#define MM_KFENCE_KFENCE_H + +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include "../slab.h" /* for struct kmem_cache */ + +/* For non-debug builds, avoid leaking kernel pointers into dmesg. */ +#ifdef CONFIG_DEBUG_KERNEL +#define PTR_FMT "%px" +#else +#define PTR_FMT "%p" +#endif + +/* + * Get the canary byte pattern for @addr. Use a pattern that varies based on the + * lower 3 bits of the address, to detect memory corruptions with higher + * probability, where similar constants are used. + */ +#define KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) + +/* Maximum stack depth for reports. */ +#define KFENCE_STACK_DEPTH 64 + +/* KFENCE object states. */ +enum kfence_object_state { + KFENCE_OBJECT_UNUSED, /* Object is unused. */ + KFENCE_OBJECT_ALLOCATED, /* Object is currently allocated. */ + KFENCE_OBJECT_FREED, /* Object was allocated, and then freed. */ +}; + +/* Alloc/free tracking information. */ +struct kfence_track { + pid_t pid; + int num_stack_entries; + unsigned long stack_entries[KFENCE_STACK_DEPTH]; +}; + +/* KFENCE metadata per guarded allocation. */ +struct kfence_metadata { + struct list_head list; /* Freelist node; access under kfence_freelist_lock. */ + struct rcu_head rcu_head; /* For delayed freeing. */ + + /* + * Lock protecting below data; to ensure consistency of the below data, + * since the following may execute concurrently: __kfence_alloc(), + * __kfence_free(), kfence_handle_page_fault(). However, note that we + * cannot grab the same metadata off the freelist twice, and multiple + * __kfence_alloc() cannot run concurrently on the same metadata. + */ + raw_spinlock_t lock; + + /* The current state of the object; see above. */ + enum kfence_object_state state; + + /* + * Allocated object address; cannot be calculated from size, because of + * alignment requirements. + * + * Invariant: ALIGN_DOWN(addr, PAGE_SIZE) is constant. + */ + unsigned long addr; + + /* + * The size of the original allocation. + */ + size_t size; + + /* + * The kmem_cache cache of the last allocation; NULL if never allocated + * or the cache has already been destroyed. + */ + struct kmem_cache *cache; + + /* + * In case of an invalid access, the page that was unprotected; we + * optimistically only store one address. + */ + unsigned long unprotected_page; + + /* Allocation and free stack information. */ + struct kfence_track alloc_track; + struct kfence_track free_track; +}; + +extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* KFENCE error types for report generation. */ +enum kfence_error_type { + KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ + KFENCE_ERROR_UAF, /* Detected a use-after-free access. */ + KFENCE_ERROR_CORRUPTION, /* Detected a memory corruption on free. */ + KFENCE_ERROR_INVALID, /* Invalid access of unknown type. */ + KFENCE_ERROR_INVALID_FREE, /* Invalid free. */ +}; + +void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, + enum kfence_error_type type); + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta); + +#endif /* MM_KFENCE_KFENCE_H */ diff --git a/mm/kfence/report.c b/mm/kfence/report.c new file mode 100644 index 000000000000..64f27c8d46a3 --- /dev/null +++ b/mm/kfence/report.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE reporting. + * + * Copyright (C) 2020, Google LLC. + */ + +#include <stdarg.h> + +#include <linux/kernel.h> +#include <linux/lockdep.h> +#include <linux/printk.h> +#include <linux/seq_file.h> +#include <linux/stacktrace.h> +#include <linux/string.h> + +#include <asm/kfence.h> + +#include "kfence.h" + +/* Helper function to either print to a seq_file or to console. */ +__printf(2, 3) +static void seq_con_printf(struct seq_file *seq, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + if (seq) + seq_vprintf(seq, fmt, args); + else + vprintk(fmt, args); + va_end(args); +} + +/* + * Get the number of stack entries to skip to get out of MM internals. @type is + * optional, and if set to NULL, assumes an allocation or free stack. + */ +static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries, + const enum kfence_error_type *type) +{ + char buf[64]; + int skipnr, fallback = 0; + bool is_access_fault = false; + + if (type) { + /* Depending on error type, find different stack entries. */ + switch (*type) { + case KFENCE_ERROR_UAF: + case KFENCE_ERROR_OOB: + case KFENCE_ERROR_INVALID: + is_access_fault = true; + break; + case KFENCE_ERROR_CORRUPTION: + case KFENCE_ERROR_INVALID_FREE: + break; + } + } + + for (skipnr = 0; skipnr < num_entries; skipnr++) { + int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]); + + if (is_access_fault) { + if (!strncmp(buf, KFENCE_SKIP_ARCH_FAULT_HANDLER, len)) + goto found; + } else { + if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") || + !strncmp(buf, "__slab_free", len)) { + /* + * In case of tail calls from any of the below + * to any of the above. + */ + fallback = skipnr + 1; + } + + /* Also the *_bulk() variants by only checking prefixes. */ + if (str_has_prefix(buf, "kfree") || + str_has_prefix(buf, "kmem_cache_free") || + str_has_prefix(buf, "__kmalloc") || + str_has_prefix(buf, "kmem_cache_alloc")) + goto found; + } + } + if (fallback < num_entries) + return fallback; +found: + skipnr++; + return skipnr < num_entries ? skipnr : 0; +} + +static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadata *meta, + bool show_alloc) +{ + const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track; + + if (track->num_stack_entries) { + /* Skip allocation/free internals stack. */ + int i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + + /* stack_trace_seq_print() does not exist; open code our own. */ + for (; i < track->num_stack_entries; i++) + seq_con_printf(seq, " %pS\n", (void *)track->stack_entries[i]); + } else { + seq_con_printf(seq, " no %s stack\n", show_alloc ? "allocation" : "deallocation"); + } +} + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta) +{ + const int size = abs(meta->size); + const unsigned long start = meta->addr; + const struct kmem_cache *const cache = meta->cache; + + lockdep_assert_held(&meta->lock); + + if (meta->state == KFENCE_OBJECT_UNUSED) { + seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata); + return; + } + + seq_con_printf(seq, + "kfence-#%zd [0x" PTR_FMT "-0x" PTR_FMT + ", size=%d, cache=%s] allocated by task %d:\n", + meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size, + (cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid); + kfence_print_stack(seq, meta, true); + + if (meta->state == KFENCE_OBJECT_FREED) { + seq_con_printf(seq, "\nfreed by task %d:\n", meta->free_track.pid); + kfence_print_stack(seq, meta, false); + } +} + +/* + * Show bytes at @addr that are different from the expected canary values, up to + * @max_bytes. + */ +static void print_diff_canary(unsigned long address, size_t bytes_to_show, + const struct kfence_metadata *meta) +{ + const unsigned long show_until_addr = address + bytes_to_show; + const u8 *cur, *end; + + /* Do not show contents of object nor read into following guard page. */ + end = (const u8 *)(address < meta->addr ? min(show_until_addr, meta->addr) + : min(show_until_addr, PAGE_ALIGN(address))); + + pr_cont("["); + for (cur = (const u8 *)address; cur < end; cur++) { + if (*cur == KFENCE_CANARY_PATTERN(cur)) + pr_cont(" ."); + else if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + pr_cont(" 0x%02x", *cur); + else /* Do not leak kernel memory in non-debug builds. */ + pr_cont(" !"); + } + pr_cont(" ]"); +} + +void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, + enum kfence_error_type type) +{ + unsigned long stack_entries[KFENCE_STACK_DEPTH] = { 0 }; + int num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 1); + int skipnr = get_stack_skipnr(stack_entries, num_stack_entries, &type); + const ptrdiff_t object_index = meta ? meta - kfence_metadata : -1; + + /* Require non-NULL meta, except if KFENCE_ERROR_INVALID. */ + if (WARN_ON(type != KFENCE_ERROR_INVALID && !meta)) + return; + + if (meta) + lockdep_assert_held(&meta->lock); + /* + * Because we may generate reports in printk-unfriendly parts of the + * kernel, such as scheduler code, the use of printk() could deadlock. + * Until such time that all printing code here is safe in all parts of + * the kernel, accept the risk, and just get our message out (given the + * system might already behave unpredictably due to the memory error). + * As such, also disable lockdep to hide warnings, and avoid disabling + * lockdep for the rest of the kernel. + */ + lockdep_off(); + + pr_err("==================================================================\n"); + /* Print report header. */ + switch (type) { + case KFENCE_ERROR_OOB: { + const bool left_of_object = address < meta->addr; + + pr_err("BUG: KFENCE: out-of-bounds in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Out-of-bounds access at 0x" PTR_FMT " (%luB %s of kfence-#%zd):\n", + (void *)address, + left_of_object ? meta->addr - address : address - meta->addr, + left_of_object ? "left" : "right", object_index); + break; + } + case KFENCE_ERROR_UAF: + pr_err("BUG: KFENCE: use-after-free in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Use-after-free access at 0x" PTR_FMT " (in kfence-#%zd):\n", + (void *)address, object_index); + break; + case KFENCE_ERROR_CORRUPTION: + pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Corrupted memory at 0x" PTR_FMT " ", (void *)address); + print_diff_canary(address, 16, meta); + pr_cont(" (in kfence-#%zd):\n", object_index); + break; + case KFENCE_ERROR_INVALID: + pr_err("BUG: KFENCE: invalid access in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Invalid access at 0x" PTR_FMT ":\n", (void *)address); + break; + case KFENCE_ERROR_INVALID_FREE: + pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Invalid free of 0x" PTR_FMT " (in kfence-#%zd):\n", (void *)address, + object_index); + break; + } + + /* Print stack trace and object info. */ + stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr, 0); + + if (meta) { + pr_err("\n"); + kfence_print_object(NULL, meta); + } + + /* Print report footer. */ + pr_err("\n"); + dump_stack_print_info(KERN_ERR); + pr_err("==================================================================\n"); + + lockdep_on(); + + if (panic_on_warn) + panic("panic_on_warn set ...\n"); + + /* We encountered a memory unsafety error, taint the kernel! */ + add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); +} -- 2.25.1

2 1

[PATCH kernel-4.19 1/2] ACPI / APEI: Add a notifier chain for unknown (vendor) CPER records
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Shiju Jose <shiju.jose(a)huawei.com> mainline inclusion from mainline-v5.10-rc1 commit 9aa9cf3ee9451d08adafc03cef8e44c7ea3898e7 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMAR CVE: NA -------------------------------- CPER records describing a firmware-first error are identified by GUID. The ghes driver currently logs, but ignores any unknown CPER records. This prevents describing errors that can't be represented by a standard entry, that would otherwise allow a driver to recover from an error. The UEFI spec calls these 'Non-standard Section Body' (N.2.3 of version 2.8). Add a notifier chain for these non-standard/vendor-records. Callers must identify their type of records by GUID. Record data is copied to memory from the ghes_estatus_pool to allow us to keep it until after the notifier has run. Co-developed-by: James Morse <james.morse(a)arm.com> Link: https://lore.kernel.org/r/20200903123456.1823-2-shiju.jose@huawei.com Signed-off-by: James Morse <james.morse(a)arm.com> Signed-off-by: Shiju Jose <shiju.jose(a)huawei.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi(a)arm.com> Acked-by: "Rafael J. Wysocki" <rjw(a)rjwysocki.net> Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/acpi/apei/ghes.c | 64 ++++++++++++++++++++++++++++++++++++++++ include/acpi/ghes.h | 18 +++++++++++ 2 files changed, 82 insertions(+) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index e807e8f74d1e0..08658c433b1fc 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -84,6 +84,12 @@ ((struct acpi_hest_generic_status *) \ ((struct ghes_estatus_node *)(estatus_node) + 1)) +#define GHES_VENDOR_ENTRY_LEN(gdata_len) \ + (sizeof(struct ghes_vendor_record_entry) + (gdata_len)) +#define GHES_GDATA_FROM_VENDOR_ENTRY(vendor_entry) \ + ((struct acpi_hest_generic_data *) \ + ((struct ghes_vendor_record_entry *)(vendor_entry) + 1)) + static inline bool is_hest_type_generic_v2(struct ghes *ghes) { return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2; @@ -126,6 +132,12 @@ EXPORT_SYMBOL(ghes_ts_err_chain); static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); +struct ghes_vendor_record_entry { + struct work_struct work; + int error_severity; + char vendor_record[]; +}; + static struct gen_pool *ghes_estatus_pool; static unsigned long ghes_estatus_pool_size_request; @@ -464,6 +476,57 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata) #endif } +static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list); + +int ghes_register_vendor_record_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&vendor_record_notify_list, nb); +} +EXPORT_SYMBOL_GPL(ghes_register_vendor_record_notifier); + +void ghes_unregister_vendor_record_notifier(struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&vendor_record_notify_list, nb); +} +EXPORT_SYMBOL_GPL(ghes_unregister_vendor_record_notifier); + +static void ghes_vendor_record_work_func(struct work_struct *work) +{ + struct ghes_vendor_record_entry *entry; + struct acpi_hest_generic_data *gdata; + u32 len; + + entry = container_of(work, struct ghes_vendor_record_entry, work); + gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry); + + blocking_notifier_call_chain(&vendor_record_notify_list, + entry->error_severity, gdata); + + len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata)); + gen_pool_free(ghes_estatus_pool, (unsigned long)entry, len); +} + +static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata, + int sev) +{ + struct acpi_hest_generic_data *copied_gdata; + struct ghes_vendor_record_entry *entry; + u32 len; + + len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata)); + entry = (void *)gen_pool_alloc(ghes_estatus_pool, len); + if (!entry) + return; + + copied_gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry); + memcpy(copied_gdata, gdata, acpi_hest_get_record_size(gdata)); + entry->error_severity = sev; + + INIT_WORK(&entry->work, ghes_vendor_record_work_func); + schedule_work(&entry->work); +} + + void __weak ghes_arm_process_error(struct ghes *ghes, struct cper_sec_proc_arm *err, int sec_sev) { @@ -517,6 +580,7 @@ static void ghes_do_proc(struct ghes *ghes, } else { void *err = acpi_hest_get_payload(gdata); + ghes_defer_non_standard_event(gdata, sev); log_non_standard_event(sec_type, fru_id, fru_text, sec_sev, err, gdata->error_data_length); diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 9aaeaaa3d1a7f..0e96c78f9f180 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -52,6 +52,24 @@ enum { GHES_SEV_PANIC = 0x3, }; +#ifdef CONFIG_ACPI_APEI_GHES +/** + * ghes_register_vendor_record_notifier - register a notifier for vendor + * records that the kernel would otherwise ignore. + * @nb: pointer to the notifier_block structure of the event handler. + * + * return 0 : SUCCESS, non-zero : FAIL + */ +int ghes_register_vendor_record_notifier(struct notifier_block *nb); + +/** + * ghes_unregister_vendor_record_notifier - unregister the previously + * registered vendor record notifier. + * @nb: pointer to the notifier_block structure of the vendor record handler. + */ +void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); +#endif + /* From drivers/edac/ghes_edac.c */ #ifdef CONFIG_EDAC_GHES -- 2.25.1

1 1

[PATCH kernel-4.19] blk-mq-sched: Fix blk_mq_sched_alloc_tags() error handling
by Yang Yingliang 30 Sep '21

30 Sep '21

From: John Garry <john.garry(a)huawei.com> mainline inclusion from mainline-v5.14-rc1 commit b93af3055d6f32d3b0361cfdb110c9399c1241ba category: bugfix bugzilla: 177012 CVE: NA --------------------------- If the blk_mq_sched_alloc_tags() -> blk_mq_alloc_rqs() call fails, then we call blk_mq_sched_free_tags() -> blk_mq_free_rqs(). It is incorrect to do so, as any rqs would have already been freed in the blk_mq_alloc_rqs() call. Fix by calling blk_mq_free_rq_map() only directly. Fixes: 6917ff0b5bd41 ("blk-mq-sched: refactor scheduler initialization") Signed-off-by: John Garry <john.garry(a)huawei.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Link: https://lore.kernel.org/r/1627378373-148090-1-git-send-email-john.garry@hua… Signed-off-by: Jens Axboe <axboe(a)kernel.dk> conflicts: block/blk-mq-sched.c Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq-sched.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index ce4b2ac6d6977..3521eca1b2984 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -513,8 +513,10 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, return -ENOMEM; ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests); - if (ret) - blk_mq_sched_free_tags(set, hctx, hctx_idx); + if (ret) { + blk_mq_free_rq_map(hctx->sched_tags); + hctx->sched_tags = NULL; + } return ret; } -- 2.25.1

1 0

[PATCH kernel-4.19 1/3] jbd2: Drop unnecessary branch from jbd2_journal_forget()
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Jan Kara <jack(a)suse.cz> mainline inclusion from mainline-5.5-rc1 commit 6d69843e5d3f0c394e1e3004cc2b36efbe402b71 category: bugfix bugzilla: 176007 CVE: NA --------------------------- We have cleared both dirty & jbddirty bits from the bh. So there's no difference between bforget() and brelse(). Thus there's no point jumping to no_jbd branch. Signed-off-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20190809124233.13277-5-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/jbd2/transaction.c Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/jbd2/transaction.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 4055929a043cf..c48658a4d53c0 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1639,10 +1639,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); } else { __jbd2_journal_unfile_buffer(jh); - if (!buffer_jbd(bh)) { - spin_unlock(&journal->j_list_lock); - goto not_jbd; - } } spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction) { -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS] USB: ehci: fix an interrupt calltrace error
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Longfang Liu <liulongfang(a)huawei.com> mainline inclusion from mainline-v5.11-rc5 commit 643a4df7fe3f6831d14536fd692be85f92670a52 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CDK3?from=project-issue CVE: NA ---------------------------------------- The system that use Synopsys USB host controllers goes to suspend when using USB audio player. This causes the USB host controller continuous send interrupt signal to system, When the number of interrupts exceeds 100000, the system will forcibly close the interrupts and output a calltrace error. When the system goes to suspend, the last interrupt is reported to the driver. At this time, the system has set the state to suspend. This causes the last interrupt to not be processed by the system and not clear the interrupt flag. This uncleared interrupt flag constantly triggers new interrupt event. This causing the driver to receive more than 100,000 interrupts, which causes the system to forcibly close the interrupt report and report the calltrace error. so, when the driver goes to sleep and changes the system state to suspend, the interrupt flag needs to be cleared. Signed-off-by: Longfang Liu <liulongfang(a)huawei.com> Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Link: https://lore.kernel.org/r/1610416647-45774-1-git-send-email-liulongfang@hua… Cc: stable <stable(a)vger.kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Longfang Liu <liulongfang(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/usb/host/ehci-hub.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index ce0eaf7d7c12a..a99c1ac5d8c8b 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -346,8 +346,12 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) unlink_empty_async_suspended(ehci); + /* Some Synopsys controllers mistakenly leave IAA turned on */ + ehci_writel(ehci, STS_IAA, &ehci->regs->status); + /* Any IAA cycle that started before the suspend is now invalid */ end_iaa_cycle(ehci); + ehci_handle_start_intr_unlinks(ehci); ehci_handle_intr_unlinks(ehci); end_free_itds(ehci); -- 2.25.1

1 0

[PATCH kernel-4.19 1/2] sched/topology: Warn when NUMA diameter > 2
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Valentin Schneider <valentin.schneider(a)arm.com> mainline inclusion from mainline-v5.11-rc1 commit b5b217346de85ed1b03fdecd5c5076b34fbb2f0b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CAA9 CVE: NA ---------------------------------------------------------- NUMA topologies where the shortest path between some two nodes requires three or more hops (i.e. diameter > 2) end up being misrepresented in the scheduler topology structures. This is currently detected when booting a kernel with CONFIG_SCHED_DEBUG=y + sched_debug on the cmdline, although this will only yield a warning about sched_group spans not matching sched_domain spans: ERROR: groups don't span domain->span Add an explicit warning for that case, triggered regardless of CONFIG_SCHED_DEBUG, and decorate it with an appropriate comment. The topology described in the comment can be booted up on QEMU by appending the following to your usual QEMU incantation: -smp cores=4 \ -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \ -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \ -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \ -numa dist,src=0,dst=3,val=40, -numa dist,src=1,dst=2,val=20, \ -numa dist,src=1,dst=3,val=30, -numa dist,src=2,dst=3,val=20 A somewhat more realistic topology (6-node mesh) with the same affliction can be conjured with: -smp cores=6 \ -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \ -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \ -numa node,cpus=4,nodeid=4, -numa node,cpus=5,nodeid=5, \ -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \ -numa dist,src=0,dst=3,val=40, -numa dist,src=0,dst=4,val=30, \ -numa dist,src=0,dst=5,val=20, \ -numa dist,src=1,dst=2,val=20, -numa dist,src=1,dst=3,val=30, \ -numa dist,src=1,dst=4,val=20, -numa dist,src=1,dst=5,val=30, \ -numa dist,src=2,dst=3,val=20, -numa dist,src=2,dst=4,val=30, \ -numa dist,src=2,dst=5,val=40, \ -numa dist,src=3,dst=4,val=20, -numa dist,src=3,dst=5,val=30, \ -numa dist,src=4,dst=5,val=20 Signed-off-by: Valentin Schneider <valentin.schneider(a)arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Acked-by: Mel Gorman <mgorman(a)techsingularity.net> Link: https://lore.kernel.org/lkml/jhjtux5edo2.mognet@arm.com Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/sched/topology.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 0002b269ed3da..cd2005832d59c 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -461,6 +461,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) { struct rq *rq = cpu_rq(cpu); struct sched_domain *tmp; + int numa_distance = 0; /* Remove the sched domains which do not contribute to scheduling. */ for (tmp = sd; tmp; ) { @@ -492,6 +493,38 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) sd->child = NULL; } + for (tmp = sd; tmp; tmp = tmp->parent) + numa_distance += !!(tmp->flags & SD_NUMA); + + /* + * FIXME: Diameter >=3 is misrepresented. + * + * Smallest diameter=3 topology is: + * + * node 0 1 2 3 + * 0: 10 20 30 40 + * 1: 20 10 20 30 + * 2: 30 20 10 20 + * 3: 40 30 20 10 + * + * 0 --- 1 --- 2 --- 3 + * + * NUMA-3 0-3 N/A N/A 0-3 + * groups: {0-2},{1-3} {1-3},{0-2} + * + * NUMA-2 0-2 0-3 0-3 1-3 + * groups: {0-1},{1-3} {0-2},{2-3} {1-3},{0-1} {2-3},{0-2} + * + * NUMA-1 0-1 0-2 1-3 2-3 + * groups: {0},{1} {1},{2},{0} {2},{3},{1} {3},{2} + * + * NUMA-0 0 1 2 3 + * + * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the + * group span isn't a subset of the domain span. + */ + WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n"); + sched_domain_debug(sd, cpu); rq_attach_root(rq, rd); -- 2.25.1

1 1

[PATCH kernel-4.19] ipc: replace costly bailout check in sysvipc_find_ipc()
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Rafael Aquini <aquini(a)redhat.com> mainline inclusion from mainline-v5.15 commit 20401d1058f3f841f35a594ac2fc1293710e55b9 category: bugfix bugzilla: NA CVE: CVE-2021-3669 -------------------------------- sysvipc_find_ipc() was left with a costly way to check if the offset position fed to it is bigger than the total number of IPC IDs in use. So much so that the time it takes to iterate over /proc/sysvipc/* files grows exponentially for a custom benchmark that creates "N" SYSV shm segments and then times the read of /proc/sysvipc/shm (milliseconds): 12 msecs to read 1024 segs from /proc/sysvipc/shm 18 msecs to read 2048 segs from /proc/sysvipc/shm 65 msecs to read 4096 segs from /proc/sysvipc/shm 325 msecs to read 8192 segs from /proc/sysvipc/shm 1303 msecs to read 16384 segs from /proc/sysvipc/shm 5182 msecs to read 32768 segs from /proc/sysvipc/shm The root problem lies with the loop that computes the total amount of ids in use to check if the "pos" feeded to sysvipc_find_ipc() grew bigger than "ids->in_use". That is a quite inneficient way to get to the maximum index in the id lookup table, specially when that value is already provided by struct ipc_ids.max_idx. This patch follows up on the optimization introduced via commit 15df03c879836 ("sysvipc: make get_maxid O(1) again") and gets rid of the aforementioned costly loop replacing it by a simpler checkpoint based on ipc_get_maxidx() returned value, which allows for a smooth linear increase in time complexity for the same custom benchmark: 2 msecs to read 1024 segs from /proc/sysvipc/shm 2 msecs to read 2048 segs from /proc/sysvipc/shm 4 msecs to read 4096 segs from /proc/sysvipc/shm 9 msecs to read 8192 segs from /proc/sysvipc/shm 19 msecs to read 16384 segs from /proc/sysvipc/shm 39 msecs to read 32768 segs from /proc/sysvipc/shm Link: https://lkml.kernel.org/r/20210809203554.1562989-1-aquini@redhat.com Signed-off-by: Rafael Aquini <aquini(a)redhat.com> Acked-by: Davidlohr Bueso <dbueso(a)suse.de> Acked-by: Manfred Spraul <manfred(a)colorfullife.com> Cc: Waiman Long <llong(a)redhat.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Conflicts: ipc/util.c Signed-off-by: zhiwentao <zhiwentao(a)huawei.com> Reviewed-by: Wang Hui <john.wanghui(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- ipc/util.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index af1b572effb14..53204b1d2e207 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -725,21 +725,14 @@ struct pid_namespace *ipc_seq_pid_ns(struct seq_file *s) static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, loff_t *new_pos) { - struct kern_ipc_perm *ipc; - int total, id; - - total = 0; - for (id = 0; id < pos && total < ids->in_use; id++) { - ipc = idr_find(&ids->ipcs_idr, id); - if (ipc != NULL) - total++; - } - ipc = NULL; - if (total >= ids->in_use) + struct kern_ipc_perm *ipc = NULL; + int max_idx = ipc_get_maxidx(ids); + + if (max_idx == -1 || pos > max_idx) goto out; - for (; pos < IPCMNI; pos++) { + for (; pos <= max_idx; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { rcu_read_lock(); -- 2.25.1

1 0

[PATCH kernel-4.19 1/4] net: hns3: fix memory override when bd_num is bigger than port info size
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Yonglong Liu <liuyonglong(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------- The bd_num is from firmware, it may be bigger than the size of struct hclge_port_info, and may cause memory override problem. Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c index 5404048ad60d1..ebbc25cc86940 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c @@ -88,9 +88,9 @@ int hns3_get_port_info(const struct hns3_nic_priv *net_priv, desc_data = (__le32 *)(&desc.data[0]); bd_num = le32_to_cpu(*desc_data); - if (bd_num > hdev->hw.cmq.csq.desc_num) { - dev_err(&hdev->pdev->dev, "get invalid BD num %u(max %u)\n", - bd_num, hdev->hw.cmq.csq.desc_num); + if (bd_num * sizeof(struct hclge_desc) > + sizeof(struct hclge_port_info)) { + dev_err(&hdev->pdev->dev, "get invalid BD num %u\n", bd_num); return -EINVAL; } -- 2.25.1

1 3

[PATCH kernel-4.19] scsi: hisi_sas: Optimize the code flow of setting sense data when ssp I/O abnormally completed
by Yang Yingliang 30 Sep '21

30 Sep '21

From: yangxingui <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA --------------------------- In the data underflow scenario, if correct sense data and response frame have been written to the host memory and the CQ RSPNS_GOOD bit is 0, then driver sends the sense data to the upper layer. Signed-off-by: yangxingui <yangxingui(a)huawei.com> Reviewed-by: Xiang Chen <chenxiang66(a)hisilicon.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas.h | 8 +++++-- drivers/scsi/hisi_sas/hisi_sas_main.c | 17 ------------- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 33 ++++++++++++++++++++++---- 3 files changed, 34 insertions(+), 24 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h index 193fc960d87fd..742ffcaeaa95c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas.h +++ b/drivers/scsi/hisi_sas/hisi_sas.h @@ -102,6 +102,12 @@ enum hisi_sas_dev_type { HISI_SAS_DEV_TYPE_SATA, }; +enum datapres_field { + NO_DATA = 0, + RESPONSE_DATA = 1, + SENSE_DATA = 2, +}; + struct hisi_sas_hw_error { u32 irq_msk; u32 msk; @@ -571,8 +577,6 @@ extern void hisi_sas_free(struct hisi_hba *hisi_hba); extern u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction); extern struct hisi_sas_port *to_hisi_sas_port(struct asd_sas_port *sas_port); -extern void hisi_sas_set_sense_data(struct sas_task *task, - struct hisi_sas_slot *slot); extern void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot); extern int hisi_sas_get_fw_info(struct hisi_hba *hisi_hba); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index ea08d53c11495..67befcc033126 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -105,23 +105,6 @@ u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction) } EXPORT_SYMBOL_GPL(hisi_sas_get_ata_protocol); -void hisi_sas_set_sense_data(struct sas_task *task, - struct hisi_sas_slot *slot) -{ - struct ssp_response_iu *iu = - hisi_sas_status_buf_addr_mem(slot) + - sizeof(struct hisi_sas_err_record); - if (iu->datapres == 2) { - struct task_status_struct *ts = &task->task_status; - - ts->buf_valid_size = - min_t(int, SAS_STATUS_BUF_SIZE, - be32_to_cpu(iu->sense_data_len)); - memcpy(ts->buf, iu->sense_data, ts->buf_valid_size); - } -} -EXPORT_SYMBOL_GPL(hisi_sas_set_sense_data); - void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 06b4f2db62f7b..9ce1177a8e455 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -395,6 +395,8 @@ #define CMPLT_HDR_ERROR_PHASE_MSK (0xff << CMPLT_HDR_ERROR_PHASE_OFF) #define CMPLT_HDR_RSPNS_XFRD_OFF 10 #define CMPLT_HDR_RSPNS_XFRD_MSK (0x1 << CMPLT_HDR_RSPNS_XFRD_OFF) +#define CMPLT_HDR_RSPNS_GOOD_OFF 11 +#define CMPLT_HDR_RSPNS_GOOD_MSK (0x1 << CMPLT_HDR_RSPNS_GOOD_OFF) #define CMPLT_HDR_ERX_OFF 12 #define CMPLT_HDR_ERX_MSK (0x1 << CMPLT_HDR_ERX_OFF) #define CMPLT_HDR_ABORT_STAT_OFF 13 @@ -2208,6 +2210,24 @@ static irqreturn_t fatal_axi_int_v3_hw(int irq_no, void *p) return IRQ_HANDLED; } +static void hisi_sas_set_sense_data(struct sas_task *task, + struct hisi_sas_slot *slot) +{ + struct ssp_response_iu *iu = + hisi_sas_status_buf_addr_mem(slot) + + sizeof(struct hisi_sas_err_record); + if ((iu->status == SAM_STAT_CHECK_CONDITION) && + (iu->datapres == SENSE_DATA)) { + struct task_status_struct *ts = &task->task_status; + + ts->buf_valid_size = + min_t(int, SAS_STATUS_BUF_SIZE, + be32_to_cpu(iu->sense_data_len)); + memcpy(ts->buf, iu->sense_data, ts->buf_valid_size); + ts->stat = SAM_STAT_CHECK_CONDITION; + } +} + static void slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, struct hisi_sas_slot *slot) @@ -2224,17 +2244,20 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, switch (task->task_proto) { case SAS_PROTOCOL_SSP: - if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { - ts->stat = SAS_QUEUE_FULL; - slot->abort = 1; - } else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { + if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { ts->residual = trans_tx_fail_type; ts->stat = SAS_DATA_UNDERRUN; + if ((!(complete_hdr->dw0 & CMPLT_HDR_RSPNS_GOOD_MSK)) && + (complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK)) { + hisi_sas_set_sense_data(task, slot); + } + } else if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { + ts->stat = SAS_QUEUE_FULL; + slot->abort = 1; } else { ts->stat = SAS_OPEN_REJECT; ts->open_rej_reason = SAS_OREJ_RSVD_RETRY; } - hisi_sas_set_sense_data(task, slot); break; case SAS_PROTOCOL_SATA: case SAS_PROTOCOL_STP: -- 2.25.1

1 0

How can I get the kernel config values in EulerOS 2.9?
by Wangpeng (Forest, ISCP SRE) 29 Sep '21

29 Sep '21

Hi Community: How can I get the kernel config values in EulerOS? For example, in other release, I can do that by "zcat /proc/config.gz" B.R.

2 1

openEuler Summit 2021 诚挚的邀请您提交演讲议题、成为共建单位、贡献展示方案
by Marketing openEuler 29 Sep '21

29 Sep '21

openEuler Summit 是由欧拉开源社区举办的开发者峰会。全新升级后的首场峰会将于 11 月10日在北京举行。 openEuler 从服务器操作系统，升级为数字基础设施的操作系统，支持 IT、CT、OT 等数字基础设施全场景，覆盖服务器、云、边、嵌入式等各种形态的需求。伴随 openEuler 21.09 的发布，openEuler 已经包含了服务器、云原生、边缘计算和嵌入式的四大应用场景。 openEuler 通过开源开放，不断探索科技创新的边界。开发者、用户、社区贡献者、软件爱好者在 openEuler Summit 汇聚，共同解读 openEuler 的最新版，探讨未来的技术路线，让技术、生态、商业在这里产生奇妙的化学反应。 *本次峰会旨在推动 openEuler 在多样性计算、云计算、边缘计算、嵌入式等技术方向的持续探索和创新。* 开源是一种态度、分享是一种精神。Call for Speaker、Call for Sponsor、Call for Demo 现已全面开放报名。大会报名通道同步开启。 *我们诚挚的邀请您提交演讲议题、发表联合演讲、成为共建单位、贡献展示方案、参与社区建设。* - *大会官网：*https://www.openeuler.org/zh/interaction/summit-list/summit2021/ - *Call for Speaker：*https://shimowendang.com/forms/X6X9jj9KPcdQwVr8/fill - *Call for Sponsor：*https://shimowendang.com/forms/k76zTLKvumYwRdsP/fill - *Call for Demo：*https://shimowendang.com/forms/LjHs8JlsLSsW92kl/fill

1 0

[PATCH] eulerfs: add the /proc/idle file.
by Hongyu Li 29 Sep '21

29 Sep '21

From: Hongyu Li <“543306408(a)qq.xn--com-9o0a> openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler-competition/summer-2021/issues/I3EBT6 CVE: NA ---------------------------------------------------------------------- The /proc/idle can give higher precision in accounting the CPU idle time compared with the traditional /proc/stat ways. Signed-off-by: Hongyu Li <“543306408(a)qq.xn--com-9o0a> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/proc_idle.c | 82 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 16 +++++++++ kernel/sched/idle.c | 21 +++++++++++ 5 files changed, 127 insertions(+) create mode 100644 fs/proc/proc_idle.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..46620afe9cac 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/idle file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/idle file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..69dd2da3a080 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += proc_idle.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/proc_idle.c b/fs/proc/proc_idle.c new file mode 100644 index 000000000000..bbb52e247448 --- /dev/null +++ b/fs/proc/proc_idle.c @@ -0,0 +1,82 @@ +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "idle" + +extern u64 cpu_rq_get(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cpu_rq_get(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 1024 + 128 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..bb280852bb06 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -1078,3 +1078,19 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cpu_rq_get(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + return idle; +} +EXPORT_SYMBOL_GPL(cpu_rq_get); + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..e3fb940a61e8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -424,6 +424,20 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +450,13 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

2 1

[PATCH kernel-4.19] Bluetooth: fix use-after-free error in lock_sock_nested()
by Yang Yingliang 29 Sep '21

29 Sep '21

From: Wang ShaoBo <bobo.shaobowang(a)huawei.com> mainline inclusion from mainline-v5.16 commit 1bff51ea59a9afb67d2dd78518ab0582a54a472c category: bugfix bugzilla: NA CVE: CVE-2021-3752 --------------------------- use-after-free error in lock_sock_nested is reported: [ 179.140137][ T3731] ===================================================== [ 179.142675][ T3731] BUG: KMSAN: use-after-free in lock_sock_nested+0x280/0x2c0 [ 179.145494][ T3731] CPU: 4 PID: 3731 Comm: kworker/4:2 Not tainted 5.12.0-rc6+ #54 [ 179.148432][ T3731] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 179.151806][ T3731] Workqueue: events l2cap_chan_timeout [ 179.152730][ T3731] Call Trace: [ 179.153301][ T3731] dump_stack+0x24c/0x2e0 [ 179.154063][ T3731] kmsan_report+0xfb/0x1e0 [ 179.154855][ T3731] __msan_warning+0x5c/0xa0 [ 179.155579][ T3731] lock_sock_nested+0x280/0x2c0 [ 179.156436][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.157257][ T3731] l2cap_sock_teardown_cb+0xb8/0x890 [ 179.158154][ T3731] ? __msan_metadata_ptr_for_load_8+0x10/0x20 [ 179.159141][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.159994][ T3731] ? kmsan_get_shadow_origin_ptr+0x84/0xb0 [ 179.160959][ T3731] ? l2cap_sock_recv_cb+0x420/0x420 [ 179.161834][ T3731] l2cap_chan_del+0x3e1/0x1d50 [ 179.162608][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.163435][ T3731] ? kmsan_get_shadow_origin_ptr+0x84/0xb0 [ 179.164406][ T3731] l2cap_chan_close+0xeea/0x1050 [ 179.165189][ T3731] ? kmsan_internal_unpoison_shadow+0x42/0x70 [ 179.166180][ T3731] l2cap_chan_timeout+0x1da/0x590 [ 179.167066][ T3731] ? __msan_metadata_ptr_for_load_8+0x10/0x20 [ 179.168023][ T3731] ? l2cap_chan_create+0x560/0x560 [ 179.168818][ T3731] process_one_work+0x121d/0x1ff0 [ 179.169598][ T3731] worker_thread+0x121b/0x2370 [ 179.170346][ T3731] kthread+0x4ef/0x610 [ 179.171010][ T3731] ? process_one_work+0x1ff0/0x1ff0 [ 179.171828][ T3731] ? kthread_blkcg+0x110/0x110 [ 179.172587][ T3731] ret_from_fork+0x1f/0x30 [ 179.173348][ T3731] [ 179.173752][ T3731] Uninit was created at: [ 179.174409][ T3731] kmsan_internal_poison_shadow+0x5c/0xf0 [ 179.175373][ T3731] kmsan_slab_free+0x76/0xc0 [ 179.176060][ T3731] kfree+0x3a5/0x1180 [ 179.176664][ T3731] __sk_destruct+0x8af/0xb80 [ 179.177375][ T3731] __sk_free+0x812/0x8c0 [ 179.178032][ T3731] sk_free+0x97/0x130 [ 179.178686][ T3731] l2cap_sock_release+0x3d5/0x4d0 [ 179.179457][ T3731] sock_close+0x150/0x450 [ 179.180117][ T3731] __fput+0x6bd/0xf00 [ 179.180787][ T3731] ____fput+0x37/0x40 [ 179.181481][ T3731] task_work_run+0x140/0x280 [ 179.182219][ T3731] do_exit+0xe51/0x3e60 [ 179.182930][ T3731] do_group_exit+0x20e/0x450 [ 179.183656][ T3731] get_signal+0x2dfb/0x38f0 [ 179.184344][ T3731] arch_do_signal_or_restart+0xaa/0xe10 [ 179.185266][ T3731] exit_to_user_mode_prepare+0x2d2/0x560 [ 179.186136][ T3731] syscall_exit_to_user_mode+0x35/0x60 [ 179.186984][ T3731] do_syscall_64+0xc5/0x140 [ 179.187681][ T3731] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 179.188604][ T3731] ===================================================== In our case, there are two Thread A and B: Context: Thread A: Context: Thread B: l2cap_chan_timeout() __se_sys_shutdown() l2cap_chan_close() l2cap_sock_shutdown() l2cap_chan_del() l2cap_chan_close() l2cap_sock_teardown_cb() l2cap_sock_teardown_cb() Once l2cap_sock_teardown_cb() excuted, this sock will be marked as SOCK_ZAPPED, and can be treated as killable in l2cap_sock_kill() if sock_orphan() has excuted, at this time we close sock through sock_close() which end to call l2cap_sock_kill() like Thread C: Context: Thread C: sock_close() l2cap_sock_release() sock_orphan() l2cap_sock_kill() #free sock if refcnt is 1 If C completed, Once A or B reaches l2cap_sock_teardown_cb() again, use-after-free happened. We should set chan->data to NULL if sock is destructed, for telling teardown operation is not allowed in l2cap_sock_teardown_cb(), and also we should avoid killing an already killed socket in l2cap_sock_close_cb(). Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Marcel Holtmann <marcel(a)holtmann.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/bluetooth/l2cap_sock.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d1d5fa35dcc9a..b4f6b74c40038 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1308,6 +1308,9 @@ static void l2cap_sock_close_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; + if (!sk) + return; + l2cap_sock_kill(sk); } @@ -1316,6 +1319,9 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) struct sock *sk = chan->data; struct sock *parent; + if (!sk) + return; + BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); /* This callback can be called both for server (BT_LISTEN) @@ -1498,8 +1504,10 @@ static void l2cap_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); - if (l2cap_pi(sk)->chan) + if (l2cap_pi(sk)->chan) { + l2cap_pi(sk)->chan->data = NULL; l2cap_chan_put(l2cap_pi(sk)->chan); + } if (l2cap_pi(sk)->rx_busy_skb) { kfree_skb(l2cap_pi(sk)->rx_busy_skb); -- 2.25.1

1 0

[PATCH openEuler-5.10 01/17] slub: fix unreclaimable slab stat for bulk free
by Zheng Zengkai 29 Sep '21

29 Sep '21

From: Shakeel Butt <shakeelb(a)google.com> mainline inclusion from mainline-v5.14-rc4 commit f227f0faf63b46a113c4d1aca633c80195622dd2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4C12I CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- SLUB uses page allocator for higher order allocations and update unreclaimable slab stat for such allocations. At the moment, the bulk free for SLUB does not share code with normal free code path for these type of allocations and have missed the stat update. So, fix the stat update by common code. The user visible impact of the bug is the potential of inconsistent unreclaimable slab stat visible through meminfo and vmstat. Link: https://lkml.kernel.org/r/20210728155354.3440560-1-shakeelb@google.com Fixes: 6a486c0ad4dc ("mm, sl[ou]b: improve memory accounting") Signed-off-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Acked-by: Roman Gushchin <guro(a)fb.com> Reviewed-by: Muchun Song <songmuchun(a)bytedance.com> Cc: Christoph Lameter <cl(a)linux.com> Cc: Pekka Enberg <penberg(a)kernel.org> Cc: David Rientjes <rientjes(a)google.com> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Chen Huang <chenhuang5(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- mm/slub.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index f06f002bb098..4a83fa347672 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3164,6 +3164,16 @@ struct detached_freelist { struct kmem_cache *s; }; +static inline void free_nonslab_page(struct page *page) +{ + unsigned int order = compound_order(page); + + VM_BUG_ON_PAGE(!PageCompound(page), page); + kfree_hook(page_address(page)); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); + __free_pages(page, order); +} + /* * This function progressively scans the array with free objects (with * a limited look ahead) and extract objects belonging to the same @@ -3200,9 +3210,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - BUG_ON(!PageCompound(page)); - kfree_hook(object); - __free_pages(page, compound_order(page)); + free_nonslab_page(page); p[size] = NULL; /* mark object processed */ return size; } @@ -4102,13 +4110,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - unsigned int order = compound_order(page); - - BUG_ON(!PageCompound(page)); - kfree_hook(object); - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, - -(PAGE_SIZE << order)); - __free_pages(page, order); + free_nonslab_page(page); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); -- 2.20.1

1 16